d79b553852
Model: fpadovani/hin-deva-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
96211 lines
2.6 MiB
96211 lines
2.6 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 4.610951008645533,
|
|
"eval_steps": 3000,
|
|
"global_step": 48000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 6.952651500701904,
|
|
"epoch": 0.0004803073967339097,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.599,
|
|
"mean_token_accuracy": 0.12166591063141823,
|
|
"num_tokens": 10855.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 6.9085437774658205,
|
|
"epoch": 0.0009606147934678194,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.5284,
|
|
"mean_token_accuracy": 0.12537284567952156,
|
|
"num_tokens": 24110.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 6.952181577682495,
|
|
"epoch": 0.001440922190201729,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.6331,
|
|
"mean_token_accuracy": 0.11882008239626884,
|
|
"num_tokens": 35984.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 6.972258520126343,
|
|
"epoch": 0.0019212295869356388,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.7525,
|
|
"mean_token_accuracy": 0.11603196635842324,
|
|
"num_tokens": 48152.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.930894613265991,
|
|
"epoch": 0.0024015369836695487,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.6323,
|
|
"mean_token_accuracy": 0.1231479749083519,
|
|
"num_tokens": 59810.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 6.855303478240967,
|
|
"epoch": 0.002881844380403458,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.4652,
|
|
"mean_token_accuracy": 0.13049934953451156,
|
|
"num_tokens": 70852.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.854698562622071,
|
|
"epoch": 0.0033621517771373678,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.5806,
|
|
"mean_token_accuracy": 0.1335124284029007,
|
|
"num_tokens": 83378.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 6.911005306243896,
|
|
"epoch": 0.0038424591738712775,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.6391,
|
|
"mean_token_accuracy": 0.12699131295084953,
|
|
"num_tokens": 95505.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 6.854988384246826,
|
|
"epoch": 0.004322766570605188,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.5744,
|
|
"mean_token_accuracy": 0.13103486746549606,
|
|
"num_tokens": 106812.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 6.905966472625733,
|
|
"epoch": 0.004803073967339097,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.5967,
|
|
"mean_token_accuracy": 0.12888517156243323,
|
|
"num_tokens": 118572.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 6.838922691345215,
|
|
"epoch": 0.005283381364073006,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.5377,
|
|
"mean_token_accuracy": 0.13722710385918618,
|
|
"num_tokens": 130051.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 6.8442412376403805,
|
|
"epoch": 0.005763688760806916,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.6378,
|
|
"mean_token_accuracy": 0.12994320318102837,
|
|
"num_tokens": 141920.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 6.843612909317017,
|
|
"epoch": 0.006243996157540826,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.497,
|
|
"mean_token_accuracy": 0.1343705639243126,
|
|
"num_tokens": 152706.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 6.861061000823975,
|
|
"epoch": 0.0067243035542747355,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.5322,
|
|
"mean_token_accuracy": 0.13384729102253914,
|
|
"num_tokens": 165253.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 6.844447374343872,
|
|
"epoch": 0.007204610951008645,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.4835,
|
|
"mean_token_accuracy": 0.1341896340250969,
|
|
"num_tokens": 176708.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 6.885022258758545,
|
|
"epoch": 0.007684918347742555,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.589,
|
|
"mean_token_accuracy": 0.1316533751785755,
|
|
"num_tokens": 188240.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 6.7767010688781735,
|
|
"epoch": 0.008165225744476465,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.3769,
|
|
"mean_token_accuracy": 0.1456473007798195,
|
|
"num_tokens": 198355.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 6.787592983245849,
|
|
"epoch": 0.008645533141210375,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.4768,
|
|
"mean_token_accuracy": 0.12947736755013467,
|
|
"num_tokens": 209497.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 6.784911251068115,
|
|
"epoch": 0.009125840537944284,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.5076,
|
|
"mean_token_accuracy": 0.1370517812669277,
|
|
"num_tokens": 220859.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 6.8974508285522464,
|
|
"epoch": 0.009606147934678195,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.615,
|
|
"mean_token_accuracy": 0.12887484207749367,
|
|
"num_tokens": 231550.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 6.895748138427734,
|
|
"epoch": 0.010086455331412104,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.5017,
|
|
"mean_token_accuracy": 0.12788755670189858,
|
|
"num_tokens": 244210.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 6.814875602722168,
|
|
"epoch": 0.010566762728146013,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.4667,
|
|
"mean_token_accuracy": 0.1335119165480137,
|
|
"num_tokens": 255745.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 6.79489426612854,
|
|
"epoch": 0.011047070124879923,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.4756,
|
|
"mean_token_accuracy": 0.1368195042014122,
|
|
"num_tokens": 266180.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 6.869257640838623,
|
|
"epoch": 0.011527377521613832,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.5495,
|
|
"mean_token_accuracy": 0.13439374342560767,
|
|
"num_tokens": 277736.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 6.852461671829223,
|
|
"epoch": 0.012007684918347743,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.5478,
|
|
"mean_token_accuracy": 0.12878389060497283,
|
|
"num_tokens": 289069.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 6.848910665512085,
|
|
"epoch": 0.012487992315081652,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.5323,
|
|
"mean_token_accuracy": 0.1328376464545727,
|
|
"num_tokens": 300240.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 6.870823621749878,
|
|
"epoch": 0.012968299711815562,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.5903,
|
|
"mean_token_accuracy": 0.13186233788728713,
|
|
"num_tokens": 311698.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 6.828889513015747,
|
|
"epoch": 0.013448607108549471,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.5379,
|
|
"mean_token_accuracy": 0.13085912838578223,
|
|
"num_tokens": 322844.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 6.913397550582886,
|
|
"epoch": 0.013928914505283382,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.5446,
|
|
"mean_token_accuracy": 0.13315542340278624,
|
|
"num_tokens": 335092.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 6.806525564193725,
|
|
"epoch": 0.01440922190201729,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.5284,
|
|
"mean_token_accuracy": 0.13454138562083245,
|
|
"num_tokens": 347033.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 6.82354998588562,
|
|
"epoch": 0.014889529298751201,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.524,
|
|
"mean_token_accuracy": 0.129171721637249,
|
|
"num_tokens": 358696.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 6.883605718612671,
|
|
"epoch": 0.01536983669548511,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.5348,
|
|
"mean_token_accuracy": 0.13050391227006913,
|
|
"num_tokens": 369390.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 6.7965363502502445,
|
|
"epoch": 0.01585014409221902,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.4805,
|
|
"mean_token_accuracy": 0.12942804098129274,
|
|
"num_tokens": 380540.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 6.873355865478516,
|
|
"epoch": 0.01633045148895293,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.4751,
|
|
"mean_token_accuracy": 0.13361193016171455,
|
|
"num_tokens": 391243.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 6.796223211288452,
|
|
"epoch": 0.01681075888568684,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.4566,
|
|
"mean_token_accuracy": 0.13809253871440888,
|
|
"num_tokens": 403336.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 6.818041896820068,
|
|
"epoch": 0.01729106628242075,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.4134,
|
|
"mean_token_accuracy": 0.13935156613588334,
|
|
"num_tokens": 413886.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 6.872933673858642,
|
|
"epoch": 0.01777137367915466,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.5177,
|
|
"mean_token_accuracy": 0.1318200945854187,
|
|
"num_tokens": 425277.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 6.881259727478027,
|
|
"epoch": 0.01825168107588857,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.5694,
|
|
"mean_token_accuracy": 0.13541515097022055,
|
|
"num_tokens": 436868.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 6.803873491287232,
|
|
"epoch": 0.018731988472622477,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.454,
|
|
"mean_token_accuracy": 0.1366116113960743,
|
|
"num_tokens": 448349.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 6.793039417266845,
|
|
"epoch": 0.01921229586935639,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.461,
|
|
"mean_token_accuracy": 0.1356694959104061,
|
|
"num_tokens": 459447.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 6.724572706222534,
|
|
"epoch": 0.0196926032660903,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.4481,
|
|
"mean_token_accuracy": 0.13523702695965767,
|
|
"num_tokens": 470734.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 6.918569087982178,
|
|
"epoch": 0.020172910662824207,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.549,
|
|
"mean_token_accuracy": 0.12832819297909737,
|
|
"num_tokens": 482015.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 6.791896152496338,
|
|
"epoch": 0.020653218059558116,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.4725,
|
|
"mean_token_accuracy": 0.13488442674279214,
|
|
"num_tokens": 493339.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 6.770703601837158,
|
|
"epoch": 0.021133525456292025,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.3969,
|
|
"mean_token_accuracy": 0.1356646716594696,
|
|
"num_tokens": 504924.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 6.825103092193603,
|
|
"epoch": 0.021613832853025938,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.4012,
|
|
"mean_token_accuracy": 0.1333916038274765,
|
|
"num_tokens": 516603.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 6.689947414398193,
|
|
"epoch": 0.022094140249759846,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.3451,
|
|
"mean_token_accuracy": 0.13920752108097076,
|
|
"num_tokens": 528347.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 6.759907960891724,
|
|
"epoch": 0.022574447646493755,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.4871,
|
|
"mean_token_accuracy": 0.13420616015791892,
|
|
"num_tokens": 539328.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 6.864851427078247,
|
|
"epoch": 0.023054755043227664,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.4447,
|
|
"mean_token_accuracy": 0.1447078913450241,
|
|
"num_tokens": 549297.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.662940216064453,
|
|
"epoch": 0.023535062439961577,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.446,
|
|
"mean_token_accuracy": 0.135732451826334,
|
|
"num_tokens": 560306.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 6.952810001373291,
|
|
"epoch": 0.024015369836695485,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.5334,
|
|
"mean_token_accuracy": 0.1299980416893959,
|
|
"num_tokens": 571972.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 6.724548578262329,
|
|
"epoch": 0.024495677233429394,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.422,
|
|
"mean_token_accuracy": 0.14118852019309996,
|
|
"num_tokens": 582962.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 6.645433044433593,
|
|
"epoch": 0.024975984630163303,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.4018,
|
|
"mean_token_accuracy": 0.1358654096722603,
|
|
"num_tokens": 597193.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 6.87578387260437,
|
|
"epoch": 0.025456292026897216,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.4819,
|
|
"mean_token_accuracy": 0.1312847390770912,
|
|
"num_tokens": 608982.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 6.726997041702271,
|
|
"epoch": 0.025936599423631124,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.5097,
|
|
"mean_token_accuracy": 0.130740699917078,
|
|
"num_tokens": 619953.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 6.889928674697876,
|
|
"epoch": 0.026416906820365033,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.5336,
|
|
"mean_token_accuracy": 0.1263997547328472,
|
|
"num_tokens": 631039.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 6.792715549468994,
|
|
"epoch": 0.026897214217098942,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.5002,
|
|
"mean_token_accuracy": 0.1386700987815857,
|
|
"num_tokens": 642656.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 6.711450719833374,
|
|
"epoch": 0.027377521613832854,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.384,
|
|
"mean_token_accuracy": 0.14428786486387252,
|
|
"num_tokens": 653748.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 6.738263273239136,
|
|
"epoch": 0.027857829010566763,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.3614,
|
|
"mean_token_accuracy": 0.13437313511967658,
|
|
"num_tokens": 665618.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 6.67711124420166,
|
|
"epoch": 0.028338136407300672,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.3993,
|
|
"mean_token_accuracy": 0.13979527801275254,
|
|
"num_tokens": 677329.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.75744104385376,
|
|
"epoch": 0.02881844380403458,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.4025,
|
|
"mean_token_accuracy": 0.13573719188570976,
|
|
"num_tokens": 688278.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.734046506881714,
|
|
"epoch": 0.029298751200768493,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.4712,
|
|
"mean_token_accuracy": 0.1387779027223587,
|
|
"num_tokens": 700739.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 6.69388518333435,
|
|
"epoch": 0.029779058597502402,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.4079,
|
|
"mean_token_accuracy": 0.13404352962970734,
|
|
"num_tokens": 712527.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.722341442108155,
|
|
"epoch": 0.03025936599423631,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.4387,
|
|
"mean_token_accuracy": 0.13380390629172326,
|
|
"num_tokens": 724514.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 6.802744388580322,
|
|
"epoch": 0.03073967339097022,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.4108,
|
|
"mean_token_accuracy": 0.1391956090927124,
|
|
"num_tokens": 735679.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 6.665415906906128,
|
|
"epoch": 0.03121998078770413,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.3804,
|
|
"mean_token_accuracy": 0.13823964521288873,
|
|
"num_tokens": 747896.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 6.729075574874878,
|
|
"epoch": 0.03170028818443804,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.13379578441381454,
|
|
"num_tokens": 759081.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.710840511322021,
|
|
"epoch": 0.03218059558117195,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.3964,
|
|
"mean_token_accuracy": 0.13790281116962433,
|
|
"num_tokens": 770459.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.6250053405761715,
|
|
"epoch": 0.03266090297790586,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.3447,
|
|
"mean_token_accuracy": 0.1371679797768593,
|
|
"num_tokens": 783960.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.7486225128173825,
|
|
"epoch": 0.03314121037463977,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.4629,
|
|
"mean_token_accuracy": 0.13776731938123704,
|
|
"num_tokens": 795425.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 6.752421426773071,
|
|
"epoch": 0.03362151777137368,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.4245,
|
|
"mean_token_accuracy": 0.13451636880636214,
|
|
"num_tokens": 807536.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.725520324707031,
|
|
"epoch": 0.034101825168107586,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.4777,
|
|
"mean_token_accuracy": 0.1328089639544487,
|
|
"num_tokens": 818801.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.751392602920532,
|
|
"epoch": 0.0345821325648415,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.3533,
|
|
"mean_token_accuracy": 0.13629962801933287,
|
|
"num_tokens": 831497.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.620713329315185,
|
|
"epoch": 0.03506243996157541,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.3369,
|
|
"mean_token_accuracy": 0.1402697041630745,
|
|
"num_tokens": 842491.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 6.729695653915405,
|
|
"epoch": 0.03554274735830932,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.4229,
|
|
"mean_token_accuracy": 0.13172629699110985,
|
|
"num_tokens": 854560.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.663899707794189,
|
|
"epoch": 0.03602305475504323,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.14512902200222016,
|
|
"num_tokens": 866688.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.71425142288208,
|
|
"epoch": 0.03650336215177714,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.4495,
|
|
"mean_token_accuracy": 0.12454762235283852,
|
|
"num_tokens": 879484.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.774377346038818,
|
|
"epoch": 0.036983669548511046,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.4499,
|
|
"mean_token_accuracy": 0.13328607976436616,
|
|
"num_tokens": 890807.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.669765377044678,
|
|
"epoch": 0.037463976945244955,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.3693,
|
|
"mean_token_accuracy": 0.13845364302396773,
|
|
"num_tokens": 901759.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.6271813869476315,
|
|
"epoch": 0.037944284341978864,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.3319,
|
|
"mean_token_accuracy": 0.1406074807047844,
|
|
"num_tokens": 912212.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.72962441444397,
|
|
"epoch": 0.03842459173871278,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.412,
|
|
"mean_token_accuracy": 0.13823732882738113,
|
|
"num_tokens": 923947.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.717016792297363,
|
|
"epoch": 0.03890489913544669,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.3606,
|
|
"mean_token_accuracy": 0.13896553441882134,
|
|
"num_tokens": 935732.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.56763482093811,
|
|
"epoch": 0.0393852065321806,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.3253,
|
|
"mean_token_accuracy": 0.1351393587887287,
|
|
"num_tokens": 948261.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.748458337783814,
|
|
"epoch": 0.039865513928914506,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.4394,
|
|
"mean_token_accuracy": 0.1367631360888481,
|
|
"num_tokens": 959574.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.698798179626465,
|
|
"epoch": 0.040345821325648415,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.5056,
|
|
"mean_token_accuracy": 0.13055995032191275,
|
|
"num_tokens": 970329.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.76392011642456,
|
|
"epoch": 0.040826128722382324,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.13992207497358322,
|
|
"num_tokens": 982037.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.600329208374023,
|
|
"epoch": 0.04130643611911623,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.3377,
|
|
"mean_token_accuracy": 0.13696533292531968,
|
|
"num_tokens": 994612.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.723447656631469,
|
|
"epoch": 0.04178674351585014,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.4662,
|
|
"mean_token_accuracy": 0.13584200516343117,
|
|
"num_tokens": 1005960.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.585640621185303,
|
|
"epoch": 0.04226705091258405,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.319,
|
|
"mean_token_accuracy": 0.13890077024698258,
|
|
"num_tokens": 1017618.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.657653045654297,
|
|
"epoch": 0.042747358309317966,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.3849,
|
|
"mean_token_accuracy": 0.13446858301758766,
|
|
"num_tokens": 1029307.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.677392196655274,
|
|
"epoch": 0.043227665706051875,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.4048,
|
|
"mean_token_accuracy": 0.13170919418334961,
|
|
"num_tokens": 1042027.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.635953140258789,
|
|
"epoch": 0.043707973102785784,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.3833,
|
|
"mean_token_accuracy": 0.13653595075011254,
|
|
"num_tokens": 1053125.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.679652452468872,
|
|
"epoch": 0.04418828049951969,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.3953,
|
|
"mean_token_accuracy": 0.13637286499142648,
|
|
"num_tokens": 1064908.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.587649869918823,
|
|
"epoch": 0.0446685878962536,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.2624,
|
|
"mean_token_accuracy": 0.14601578190922737,
|
|
"num_tokens": 1076328.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.7135566711425785,
|
|
"epoch": 0.04514889529298751,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.4999,
|
|
"mean_token_accuracy": 0.12689368948340415,
|
|
"num_tokens": 1088469.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.544733381271362,
|
|
"epoch": 0.04562920268972142,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.2991,
|
|
"mean_token_accuracy": 0.1377271056175232,
|
|
"num_tokens": 1099408.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.4988525867462155,
|
|
"epoch": 0.04610951008645533,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.2525,
|
|
"mean_token_accuracy": 0.14525126665830612,
|
|
"num_tokens": 1111101.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.573197364807129,
|
|
"epoch": 0.046589817483189244,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.2656,
|
|
"mean_token_accuracy": 0.14520046710968018,
|
|
"num_tokens": 1122877.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.563286590576172,
|
|
"epoch": 0.04707012487992315,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.353,
|
|
"mean_token_accuracy": 0.12840453535318375,
|
|
"num_tokens": 1133956.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.547583389282226,
|
|
"epoch": 0.04755043227665706,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.2683,
|
|
"mean_token_accuracy": 0.13759282901883124,
|
|
"num_tokens": 1146101.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.6805504322052,
|
|
"epoch": 0.04803073967339097,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.3555,
|
|
"mean_token_accuracy": 0.14784793183207512,
|
|
"num_tokens": 1157432.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.585719633102417,
|
|
"epoch": 0.04851104707012488,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.354,
|
|
"mean_token_accuracy": 0.14003706574440003,
|
|
"num_tokens": 1167601.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.563266372680664,
|
|
"epoch": 0.04899135446685879,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.2636,
|
|
"mean_token_accuracy": 0.14093808084726334,
|
|
"num_tokens": 1178818.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.707622337341308,
|
|
"epoch": 0.0494716618635927,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.4961,
|
|
"mean_token_accuracy": 0.13650018721818924,
|
|
"num_tokens": 1189977.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.607511234283447,
|
|
"epoch": 0.049951969260326606,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.3424,
|
|
"mean_token_accuracy": 0.13687357306480408,
|
|
"num_tokens": 1201039.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.642952966690063,
|
|
"epoch": 0.05043227665706052,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.13946828693151475,
|
|
"num_tokens": 1212573.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.587105321884155,
|
|
"epoch": 0.05091258405379443,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.2973,
|
|
"mean_token_accuracy": 0.14514252468943595,
|
|
"num_tokens": 1223382.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.593515920639038,
|
|
"epoch": 0.05139289145052834,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.3823,
|
|
"mean_token_accuracy": 0.14192649051547052,
|
|
"num_tokens": 1236501.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.630349588394165,
|
|
"epoch": 0.05187319884726225,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.4011,
|
|
"mean_token_accuracy": 0.13930339068174363,
|
|
"num_tokens": 1246798.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.586811113357544,
|
|
"epoch": 0.05235350624399616,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.3204,
|
|
"mean_token_accuracy": 0.1382439248263836,
|
|
"num_tokens": 1258182.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.513943099975586,
|
|
"epoch": 0.052833813640730067,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.2792,
|
|
"mean_token_accuracy": 0.13468218222260475,
|
|
"num_tokens": 1270273.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.534994459152221,
|
|
"epoch": 0.053314121037463975,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.354,
|
|
"mean_token_accuracy": 0.13334706872701646,
|
|
"num_tokens": 1281136.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.548804044723511,
|
|
"epoch": 0.053794428434197884,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.3131,
|
|
"mean_token_accuracy": 0.13876051902770997,
|
|
"num_tokens": 1294488.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.484967136383057,
|
|
"epoch": 0.05427473583093179,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.2596,
|
|
"mean_token_accuracy": 0.13667422607541085,
|
|
"num_tokens": 1304113.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.612146043777466,
|
|
"epoch": 0.05475504322766571,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.2944,
|
|
"mean_token_accuracy": 0.13832857757806777,
|
|
"num_tokens": 1315417.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.515767002105713,
|
|
"epoch": 0.05523535062439962,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.2749,
|
|
"mean_token_accuracy": 0.13825217634439468,
|
|
"num_tokens": 1328084.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.592691040039062,
|
|
"epoch": 0.05571565802113353,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.415,
|
|
"mean_token_accuracy": 0.13889241889119147,
|
|
"num_tokens": 1338696.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.58132038116455,
|
|
"epoch": 0.056195965417867436,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.368,
|
|
"mean_token_accuracy": 0.1339378274977207,
|
|
"num_tokens": 1350240.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.557730102539063,
|
|
"epoch": 0.056676272814601344,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.299,
|
|
"mean_token_accuracy": 0.13756103813648224,
|
|
"num_tokens": 1361720.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.484502220153809,
|
|
"epoch": 0.05715658021133525,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.3101,
|
|
"mean_token_accuracy": 0.14111735820770263,
|
|
"num_tokens": 1373286.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.547904539108276,
|
|
"epoch": 0.05763688760806916,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.13960244804620742,
|
|
"num_tokens": 1384274.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.445998477935791,
|
|
"epoch": 0.05811719500480307,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.3018,
|
|
"mean_token_accuracy": 0.14306503757834435,
|
|
"num_tokens": 1395355.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.5133966445922855,
|
|
"epoch": 0.05859750240153699,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.2432,
|
|
"mean_token_accuracy": 0.1462439626455307,
|
|
"num_tokens": 1406664.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.549827241897583,
|
|
"epoch": 0.059077809798270896,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.4006,
|
|
"mean_token_accuracy": 0.13411908224225044,
|
|
"num_tokens": 1418450.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.535983848571777,
|
|
"epoch": 0.059558117195004805,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.2808,
|
|
"mean_token_accuracy": 0.13845230266451836,
|
|
"num_tokens": 1430048.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.604789209365845,
|
|
"epoch": 0.060038424591738714,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.3291,
|
|
"mean_token_accuracy": 0.13734976723790168,
|
|
"num_tokens": 1441820.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.450564956665039,
|
|
"epoch": 0.06051873198847262,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.1741,
|
|
"mean_token_accuracy": 0.1435953736305237,
|
|
"num_tokens": 1453209.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.421152973175049,
|
|
"epoch": 0.06099903938520653,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.2012,
|
|
"mean_token_accuracy": 0.14217107146978378,
|
|
"num_tokens": 1465423.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.413800048828125,
|
|
"epoch": 0.06147934678194044,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.2062,
|
|
"mean_token_accuracy": 0.1439860425889492,
|
|
"num_tokens": 1476575.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.428792333602905,
|
|
"epoch": 0.06195965417867435,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.1531,
|
|
"mean_token_accuracy": 0.1400687262415886,
|
|
"num_tokens": 1486932.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.423939800262451,
|
|
"epoch": 0.06243996157540826,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.14491663873195648,
|
|
"num_tokens": 1498494.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.498752021789551,
|
|
"epoch": 0.06292026897214217,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.13722796365618706,
|
|
"num_tokens": 1509937.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.468093013763427,
|
|
"epoch": 0.06340057636887608,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.272,
|
|
"mean_token_accuracy": 0.14509280696511268,
|
|
"num_tokens": 1519823.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.522231483459473,
|
|
"epoch": 0.06388088376560999,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.3013,
|
|
"mean_token_accuracy": 0.13799824938178062,
|
|
"num_tokens": 1529943.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.394433879852295,
|
|
"epoch": 0.0643611911623439,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.158,
|
|
"mean_token_accuracy": 0.14639023020863534,
|
|
"num_tokens": 1540618.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.396191930770874,
|
|
"epoch": 0.06484149855907781,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.2737,
|
|
"mean_token_accuracy": 0.1327565498650074,
|
|
"num_tokens": 1553208.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.504687738418579,
|
|
"epoch": 0.06532180595581172,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.2458,
|
|
"mean_token_accuracy": 0.14418571442365646,
|
|
"num_tokens": 1563975.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.492403602600097,
|
|
"epoch": 0.06580211335254563,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.2874,
|
|
"mean_token_accuracy": 0.13431822657585143,
|
|
"num_tokens": 1575998.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.413771677017212,
|
|
"epoch": 0.06628242074927954,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.1769,
|
|
"mean_token_accuracy": 0.14885379895567893,
|
|
"num_tokens": 1586041.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.41043004989624,
|
|
"epoch": 0.06676272814601344,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.2555,
|
|
"mean_token_accuracy": 0.14138335809111596,
|
|
"num_tokens": 1597531.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.434475135803223,
|
|
"epoch": 0.06724303554274735,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.2467,
|
|
"mean_token_accuracy": 0.1396237537264824,
|
|
"num_tokens": 1609255.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.387577152252197,
|
|
"epoch": 0.06772334293948126,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2361,
|
|
"mean_token_accuracy": 0.1451232209801674,
|
|
"num_tokens": 1621098.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.36214804649353,
|
|
"epoch": 0.06820365033621517,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.1121,
|
|
"mean_token_accuracy": 0.15047377347946167,
|
|
"num_tokens": 1631941.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.307120418548584,
|
|
"epoch": 0.0686839577329491,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.1476641647517681,
|
|
"num_tokens": 1643117.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.312221193313599,
|
|
"epoch": 0.069164265129683,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.1821,
|
|
"mean_token_accuracy": 0.14429083168506623,
|
|
"num_tokens": 1653595.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.518056488037109,
|
|
"epoch": 0.06964457252641691,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.14543262720108033,
|
|
"num_tokens": 1664495.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.2866119861602785,
|
|
"epoch": 0.07012487992315082,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.14417687878012658,
|
|
"num_tokens": 1674923.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.355959510803222,
|
|
"epoch": 0.07060518731988473,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.1488643318414688,
|
|
"num_tokens": 1685904.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.358133983612061,
|
|
"epoch": 0.07108549471661864,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.3402,
|
|
"mean_token_accuracy": 0.13188703805208207,
|
|
"num_tokens": 1699133.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.358847427368164,
|
|
"epoch": 0.07156580211335255,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.147,
|
|
"mean_token_accuracy": 0.1398720182478428,
|
|
"num_tokens": 1711559.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.357234525680542,
|
|
"epoch": 0.07204610951008646,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.0539,
|
|
"mean_token_accuracy": 0.15405589044094087,
|
|
"num_tokens": 1722526.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.2410214900970455,
|
|
"epoch": 0.07252641690682037,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.1354,
|
|
"mean_token_accuracy": 0.14821420460939408,
|
|
"num_tokens": 1734261.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.338043832778931,
|
|
"epoch": 0.07300672430355427,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.1519014649093151,
|
|
"num_tokens": 1745151.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.476584768295288,
|
|
"epoch": 0.07348703170028818,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.2792,
|
|
"mean_token_accuracy": 0.14400802031159401,
|
|
"num_tokens": 1755463.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.3948328495025635,
|
|
"epoch": 0.07396733909702209,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.2234,
|
|
"mean_token_accuracy": 0.14461189657449722,
|
|
"num_tokens": 1767717.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.168685340881348,
|
|
"epoch": 0.074447646493756,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.0937,
|
|
"mean_token_accuracy": 0.1491263009607792,
|
|
"num_tokens": 1779115.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.222611951828003,
|
|
"epoch": 0.07492795389048991,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.14829141050577163,
|
|
"num_tokens": 1789644.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.3032676696777346,
|
|
"epoch": 0.07540826128722382,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2603,
|
|
"mean_token_accuracy": 0.14343128055334092,
|
|
"num_tokens": 1800606.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.40781946182251,
|
|
"epoch": 0.07588856868395773,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.2459,
|
|
"mean_token_accuracy": 0.14229424744844438,
|
|
"num_tokens": 1812168.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.402425479888916,
|
|
"epoch": 0.07636887608069164,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.1864,
|
|
"mean_token_accuracy": 0.14310432076454163,
|
|
"num_tokens": 1823830.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.313073348999024,
|
|
"epoch": 0.07684918347742556,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.1475934624671936,
|
|
"num_tokens": 1835611.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.372682237625122,
|
|
"epoch": 0.07732949087415947,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.2311,
|
|
"mean_token_accuracy": 0.14055584818124772,
|
|
"num_tokens": 1847036.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.271993827819824,
|
|
"epoch": 0.07780979827089338,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.14067554026842116,
|
|
"num_tokens": 1857476.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.364087867736816,
|
|
"epoch": 0.07829010566762729,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2153,
|
|
"mean_token_accuracy": 0.14368200302124023,
|
|
"num_tokens": 1869073.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.225147342681884,
|
|
"epoch": 0.0787704130643612,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.14699265360832214,
|
|
"num_tokens": 1880439.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.411924362182617,
|
|
"epoch": 0.0792507204610951,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.2363,
|
|
"mean_token_accuracy": 0.14428542256355287,
|
|
"num_tokens": 1891600.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.312764263153076,
|
|
"epoch": 0.07973102785782901,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2206,
|
|
"mean_token_accuracy": 0.14465458691120148,
|
|
"num_tokens": 1903126.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.4170550346374515,
|
|
"epoch": 0.08021133525456292,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.1711,
|
|
"mean_token_accuracy": 0.14698779433965684,
|
|
"num_tokens": 1913913.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.154744243621826,
|
|
"epoch": 0.08069164265129683,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.1134,
|
|
"mean_token_accuracy": 0.14713074266910553,
|
|
"num_tokens": 1924961.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.353956127166748,
|
|
"epoch": 0.08117195004803074,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.1932,
|
|
"mean_token_accuracy": 0.1369136855006218,
|
|
"num_tokens": 1936773.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.216285705566406,
|
|
"epoch": 0.08165225744476465,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.1194,
|
|
"mean_token_accuracy": 0.14373072981834412,
|
|
"num_tokens": 1948190.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.213874244689942,
|
|
"epoch": 0.08213256484149856,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.15150452703237532,
|
|
"num_tokens": 1960038.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.367424535751343,
|
|
"epoch": 0.08261287223823247,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.1886,
|
|
"mean_token_accuracy": 0.14658416658639908,
|
|
"num_tokens": 1970535.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.261027574539185,
|
|
"epoch": 0.08309317963496637,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.1628,
|
|
"mean_token_accuracy": 0.14296040832996368,
|
|
"num_tokens": 1981386.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.288147020339966,
|
|
"epoch": 0.08357348703170028,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.14790923446416854,
|
|
"num_tokens": 1993196.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.280757665634155,
|
|
"epoch": 0.08405379442843419,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.1099,
|
|
"mean_token_accuracy": 0.15565580278635024,
|
|
"num_tokens": 2004756.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.153049898147583,
|
|
"epoch": 0.0845341018251681,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.0842,
|
|
"mean_token_accuracy": 0.14847498014569283,
|
|
"num_tokens": 2016020.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.251008081436157,
|
|
"epoch": 0.08501440922190202,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.1486026793718338,
|
|
"num_tokens": 2027747.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.2820741653442385,
|
|
"epoch": 0.08549471661863593,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.1227,
|
|
"mean_token_accuracy": 0.14199740439653397,
|
|
"num_tokens": 2038841.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.242849683761596,
|
|
"epoch": 0.08597502401536984,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.1763,
|
|
"mean_token_accuracy": 0.13965106531977653,
|
|
"num_tokens": 2049905.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.315613698959351,
|
|
"epoch": 0.08645533141210375,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.14235491976141929,
|
|
"num_tokens": 2062492.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.2080460548400875,
|
|
"epoch": 0.08693563880883766,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.1778,
|
|
"mean_token_accuracy": 0.14161646142601966,
|
|
"num_tokens": 2073840.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.2826292514801025,
|
|
"epoch": 0.08741594620557157,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.0789,
|
|
"mean_token_accuracy": 0.14724974036216737,
|
|
"num_tokens": 2085720.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.22252049446106,
|
|
"epoch": 0.08789625360230548,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.1727,
|
|
"mean_token_accuracy": 0.14590057134628295,
|
|
"num_tokens": 2096649.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.287421941757202,
|
|
"epoch": 0.08837656099903939,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.1615,
|
|
"mean_token_accuracy": 0.1485862649977207,
|
|
"num_tokens": 2109030.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.248794651031494,
|
|
"epoch": 0.0888568683957733,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.146725195646286,
|
|
"num_tokens": 2121384.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.1745093822479244,
|
|
"epoch": 0.0893371757925072,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.15523850321769714,
|
|
"num_tokens": 2131377.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.230327844619751,
|
|
"epoch": 0.08981748318924111,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2319,
|
|
"mean_token_accuracy": 0.14350223392248154,
|
|
"num_tokens": 2142364.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.234197568893433,
|
|
"epoch": 0.09029779058597502,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.0954,
|
|
"mean_token_accuracy": 0.14754682183265685,
|
|
"num_tokens": 2153040.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.239541959762573,
|
|
"epoch": 0.09077809798270893,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.14540863707661628,
|
|
"num_tokens": 2165571.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.189713668823242,
|
|
"epoch": 0.09125840537944284,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.1345,
|
|
"mean_token_accuracy": 0.1447000600397587,
|
|
"num_tokens": 2177241.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.205877637863159,
|
|
"epoch": 0.09173871277617675,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.1497,
|
|
"mean_token_accuracy": 0.14220875799655913,
|
|
"num_tokens": 2187475.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.212519884109497,
|
|
"epoch": 0.09221902017291066,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.1917,
|
|
"mean_token_accuracy": 0.14497191533446313,
|
|
"num_tokens": 2198185.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.189974975585938,
|
|
"epoch": 0.09269932756964457,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.1227,
|
|
"mean_token_accuracy": 0.14929210245609284,
|
|
"num_tokens": 2210404.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.256520175933838,
|
|
"epoch": 0.09317963496637849,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.1039,
|
|
"mean_token_accuracy": 0.14744618237018586,
|
|
"num_tokens": 2222188.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.21520619392395,
|
|
"epoch": 0.0936599423631124,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.1677,
|
|
"mean_token_accuracy": 0.14622701331973076,
|
|
"num_tokens": 2233418.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.187162303924561,
|
|
"epoch": 0.0941402497598463,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.1354,
|
|
"mean_token_accuracy": 0.15184210613369942,
|
|
"num_tokens": 2245053.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.185460042953491,
|
|
"epoch": 0.09462055715658022,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.1439,
|
|
"mean_token_accuracy": 0.150452421605587,
|
|
"num_tokens": 2256375.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.118437194824219,
|
|
"epoch": 0.09510086455331412,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 5.992,
|
|
"mean_token_accuracy": 0.15518785417079925,
|
|
"num_tokens": 2267074.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.1264660358428955,
|
|
"epoch": 0.09558117195004803,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.034,
|
|
"mean_token_accuracy": 0.1509545549750328,
|
|
"num_tokens": 2277168.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.146339559555054,
|
|
"epoch": 0.09606147934678194,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.15311127305030822,
|
|
"num_tokens": 2288178.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.097985792160034,
|
|
"epoch": 0.09654178674351585,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999983283737,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.14778285026550292,
|
|
"num_tokens": 2299765.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.250259923934936,
|
|
"epoch": 0.09702209414024976,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999999915373924,
|
|
"loss": 6.1455,
|
|
"mean_token_accuracy": 0.13837159797549248,
|
|
"num_tokens": 2312047.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.205899620056153,
|
|
"epoch": 0.09750240153698367,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999999795225793,
|
|
"loss": 6.1327,
|
|
"mean_token_accuracy": 0.14082004576921464,
|
|
"num_tokens": 2324118.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.159180212020874,
|
|
"epoch": 0.09798270893371758,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999999622839347,
|
|
"loss": 6.1357,
|
|
"mean_token_accuracy": 0.14645567908883095,
|
|
"num_tokens": 2335171.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.1911696434021,
|
|
"epoch": 0.09846301633045149,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999999398214593,
|
|
"loss": 6.0471,
|
|
"mean_token_accuracy": 0.1486515149474144,
|
|
"num_tokens": 2346338.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.1179557800292965,
|
|
"epoch": 0.0989433237271854,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999121351532,
|
|
"loss": 6.0727,
|
|
"mean_token_accuracy": 0.1525813952088356,
|
|
"num_tokens": 2357185.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.1366747379302975,
|
|
"epoch": 0.0994236311239193,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999998792250173,
|
|
"loss": 6.0156,
|
|
"mean_token_accuracy": 0.1577829249203205,
|
|
"num_tokens": 2368494.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.192359781265258,
|
|
"epoch": 0.09990393852065321,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999998410910524,
|
|
"loss": 6.2155,
|
|
"mean_token_accuracy": 0.13934658840298653,
|
|
"num_tokens": 2380800.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.220779323577881,
|
|
"epoch": 0.10038424591738712,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999997977332592,
|
|
"loss": 6.1586,
|
|
"mean_token_accuracy": 0.14340569451451302,
|
|
"num_tokens": 2391753.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.0759320735931395,
|
|
"epoch": 0.10086455331412104,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999997491516389,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.1431613892316818,
|
|
"num_tokens": 2403324.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.173238754272461,
|
|
"epoch": 0.10134486071085495,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999996953461925,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.14316309839487076,
|
|
"num_tokens": 2414873.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 5.9853262424469,
|
|
"epoch": 0.10182516810758886,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999996363169212,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.15589012205600739,
|
|
"num_tokens": 2425308.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.014470767974854,
|
|
"epoch": 0.10230547550432277,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999995720638266,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.15411566495895385,
|
|
"num_tokens": 2436835.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.098240566253662,
|
|
"epoch": 0.10278578290105668,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00049999950258691,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.14945193827152253,
|
|
"num_tokens": 2446798.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.0551064014434814,
|
|
"epoch": 0.10326609029779059,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999994278861731,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.15379531532526017,
|
|
"num_tokens": 2457308.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.160330963134766,
|
|
"epoch": 0.1037463976945245,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999993479616175,
|
|
"loss": 6.0441,
|
|
"mean_token_accuracy": 0.1425388738512993,
|
|
"num_tokens": 2468917.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.0867311477661135,
|
|
"epoch": 0.1042267050912584,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999992628132451,
|
|
"loss": 6.0544,
|
|
"mean_token_accuracy": 0.14335305467247964,
|
|
"num_tokens": 2481363.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.063572645187378,
|
|
"epoch": 0.10470701248799232,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999991724410582,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.14588392674922943,
|
|
"num_tokens": 2493082.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.1117987632751465,
|
|
"epoch": 0.10518731988472622,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999990768450583,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.15032761096954345,
|
|
"num_tokens": 2503849.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.093571186065674,
|
|
"epoch": 0.10566762728146013,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999989760252482,
|
|
"loss": 6.0692,
|
|
"mean_token_accuracy": 0.14965578615665437,
|
|
"num_tokens": 2514528.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.067201423645019,
|
|
"epoch": 0.10614793467819404,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004999988699816299,
|
|
"loss": 6.0522,
|
|
"mean_token_accuracy": 0.15063507556915284,
|
|
"num_tokens": 2524971.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.034856176376342,
|
|
"epoch": 0.10662824207492795,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999987587142058,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.14890054613351822,
|
|
"num_tokens": 2535674.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.203412580490112,
|
|
"epoch": 0.10710854947166186,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999986422229789,
|
|
"loss": 6.2043,
|
|
"mean_token_accuracy": 0.13955387324094773,
|
|
"num_tokens": 2547108.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.03151125907898,
|
|
"epoch": 0.10758885686839577,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999985205079514,
|
|
"loss": 6.0125,
|
|
"mean_token_accuracy": 0.14646655619144439,
|
|
"num_tokens": 2559474.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 5.942519569396973,
|
|
"epoch": 0.10806916426512968,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999983935691265,
|
|
"loss": 5.8671,
|
|
"mean_token_accuracy": 0.1597619265317917,
|
|
"num_tokens": 2571264.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.055132722854614,
|
|
"epoch": 0.10854947166186359,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499998261406507,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.1494836613535881,
|
|
"num_tokens": 2583731.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.172086954116821,
|
|
"epoch": 0.10902977905859751,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999981240200958,
|
|
"loss": 6.0819,
|
|
"mean_token_accuracy": 0.1500307098031044,
|
|
"num_tokens": 2595497.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 5.985740613937378,
|
|
"epoch": 0.10951008645533142,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999979814098966,
|
|
"loss": 6.0511,
|
|
"mean_token_accuracy": 0.1474834844470024,
|
|
"num_tokens": 2607358.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.095105171203613,
|
|
"epoch": 0.10999039385206533,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999978335759121,
|
|
"loss": 5.9615,
|
|
"mean_token_accuracy": 0.15808446407318116,
|
|
"num_tokens": 2618936.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.056868362426758,
|
|
"epoch": 0.11047070124879924,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999976805181461,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.14292721673846245,
|
|
"num_tokens": 2631840.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.089091157913208,
|
|
"epoch": 0.11095100864553314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499997522236602,
|
|
"loss": 6.0524,
|
|
"mean_token_accuracy": 0.1545324720442295,
|
|
"num_tokens": 2642412.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.016473770141602,
|
|
"epoch": 0.11143131604226705,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999973587312837,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.15058596879243852,
|
|
"num_tokens": 2653890.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.1500414371490475,
|
|
"epoch": 0.11191162343900096,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999971900021947,
|
|
"loss": 6.08,
|
|
"mean_token_accuracy": 0.15312047600746154,
|
|
"num_tokens": 2664888.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.017521715164184,
|
|
"epoch": 0.11239193083573487,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999970160493391,
|
|
"loss": 5.9772,
|
|
"mean_token_accuracy": 0.14959615096449852,
|
|
"num_tokens": 2675550.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 5.969038391113282,
|
|
"epoch": 0.11287223823246878,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999968368727209,
|
|
"loss": 5.9944,
|
|
"mean_token_accuracy": 0.15736498236656188,
|
|
"num_tokens": 2688022.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.127727603912353,
|
|
"epoch": 0.11335254562920269,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999966524723442,
|
|
"loss": 5.9896,
|
|
"mean_token_accuracy": 0.14983469247817993,
|
|
"num_tokens": 2698737.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 5.977780055999756,
|
|
"epoch": 0.1138328530259366,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999964628482135,
|
|
"loss": 5.9519,
|
|
"mean_token_accuracy": 0.16247435212135314,
|
|
"num_tokens": 2709844.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.054257869720459,
|
|
"epoch": 0.1143131604226705,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999962680003328,
|
|
"loss": 6.0115,
|
|
"mean_token_accuracy": 0.15526500791311265,
|
|
"num_tokens": 2720273.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.038494014739991,
|
|
"epoch": 0.11479346781940442,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499996067928707,
|
|
"loss": 6.0375,
|
|
"mean_token_accuracy": 0.14822905212640763,
|
|
"num_tokens": 2731354.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.059918832778931,
|
|
"epoch": 0.11527377521613832,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999958626333406,
|
|
"loss": 6.0301,
|
|
"mean_token_accuracy": 0.1549976333975792,
|
|
"num_tokens": 2742966.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 5.971234321594238,
|
|
"epoch": 0.11575408261287223,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999956521142383,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.1558637171983719,
|
|
"num_tokens": 2755010.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.045121145248413,
|
|
"epoch": 0.11623439000960614,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999954363714051,
|
|
"loss": 5.9759,
|
|
"mean_token_accuracy": 0.14972745180130004,
|
|
"num_tokens": 2766176.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.113975477218628,
|
|
"epoch": 0.11671469740634005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999952154048459,
|
|
"loss": 6.1165,
|
|
"mean_token_accuracy": 0.14935739785432817,
|
|
"num_tokens": 2777861.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 5.9306525707244875,
|
|
"epoch": 0.11719500480307397,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499994989214566,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.1511348232626915,
|
|
"num_tokens": 2788725.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 5.944420194625854,
|
|
"epoch": 0.11767531219980788,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999947578005705,
|
|
"loss": 5.9701,
|
|
"mean_token_accuracy": 0.15558769553899765,
|
|
"num_tokens": 2801613.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.096777296066284,
|
|
"epoch": 0.11815561959654179,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999945211628648,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.1501984916627407,
|
|
"num_tokens": 2812474.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 5.895422315597534,
|
|
"epoch": 0.1186359269932757,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999942793014544,
|
|
"loss": 5.9386,
|
|
"mean_token_accuracy": 0.15895296037197112,
|
|
"num_tokens": 2823178.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 5.956892490386963,
|
|
"epoch": 0.11911623439000961,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499994032216345,
|
|
"loss": 5.951,
|
|
"mean_token_accuracy": 0.15528498589992523,
|
|
"num_tokens": 2836486.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.035536432266236,
|
|
"epoch": 0.11959654178674352,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999937799075422,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.15788709819316865,
|
|
"num_tokens": 2847902.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 5.859764623641968,
|
|
"epoch": 0.12007684918347743,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499993522375052,
|
|
"loss": 5.9065,
|
|
"mean_token_accuracy": 0.15673141777515412,
|
|
"num_tokens": 2859991.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.130489349365234,
|
|
"epoch": 0.12055715658021134,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999932596188802,
|
|
"loss": 6.0943,
|
|
"mean_token_accuracy": 0.14727426841855049,
|
|
"num_tokens": 2870269.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 5.9960047721862795,
|
|
"epoch": 0.12103746397694524,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999929916390331,
|
|
"loss": 5.9644,
|
|
"mean_token_accuracy": 0.14853706806898118,
|
|
"num_tokens": 2882191.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 5.932647705078125,
|
|
"epoch": 0.12151777137367915,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999927184355169,
|
|
"loss": 5.9762,
|
|
"mean_token_accuracy": 0.1510110802948475,
|
|
"num_tokens": 2892775.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 5.98958740234375,
|
|
"epoch": 0.12199807877041306,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999924400083377,
|
|
"loss": 5.96,
|
|
"mean_token_accuracy": 0.15953878462314605,
|
|
"num_tokens": 2904750.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.113637018203735,
|
|
"epoch": 0.12247838616714697,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999921563575022,
|
|
"loss": 6.0229,
|
|
"mean_token_accuracy": 0.1497579611837864,
|
|
"num_tokens": 2916150.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.034125900268554,
|
|
"epoch": 0.12295869356388088,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999918674830169,
|
|
"loss": 6.002,
|
|
"mean_token_accuracy": 0.15276891440153123,
|
|
"num_tokens": 2928452.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 5.956598520278931,
|
|
"epoch": 0.12343900096061479,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999915733848886,
|
|
"loss": 5.9795,
|
|
"mean_token_accuracy": 0.14799097031354905,
|
|
"num_tokens": 2940577.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 5.961469030380249,
|
|
"epoch": 0.1239193083573487,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499991274063124,
|
|
"loss": 5.9673,
|
|
"mean_token_accuracy": 0.15523803606629372,
|
|
"num_tokens": 2952302.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 5.988963794708252,
|
|
"epoch": 0.12439961575408261,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999909695177301,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.1574509933590889,
|
|
"num_tokens": 2964611.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.0221082210540775,
|
|
"epoch": 0.12487992315081652,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499990659748714,
|
|
"loss": 5.9972,
|
|
"mean_token_accuracy": 0.14904298931360244,
|
|
"num_tokens": 2975668.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.126944589614868,
|
|
"epoch": 0.12536023054755044,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999903447560828,
|
|
"loss": 6.0566,
|
|
"mean_token_accuracy": 0.15217916369438172,
|
|
"num_tokens": 2987303.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.0120045185089115,
|
|
"epoch": 0.12584053794428435,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999900245398439,
|
|
"loss": 5.9576,
|
|
"mean_token_accuracy": 0.15809344947338105,
|
|
"num_tokens": 3000400.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 5.929742479324341,
|
|
"epoch": 0.12632084534101826,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999896991000047,
|
|
"loss": 5.896,
|
|
"mean_token_accuracy": 0.15618198737502098,
|
|
"num_tokens": 3012336.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.027432537078857,
|
|
"epoch": 0.12680115273775217,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999893684365729,
|
|
"loss": 5.9446,
|
|
"mean_token_accuracy": 0.15072833970189095,
|
|
"num_tokens": 3023004.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 5.944407272338867,
|
|
"epoch": 0.12728146013448607,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999890325495559,
|
|
"loss": 6.0312,
|
|
"mean_token_accuracy": 0.14632753878831864,
|
|
"num_tokens": 3035147.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 5.983647346496582,
|
|
"epoch": 0.12776176753121998,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999886914389617,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.15314999967813492,
|
|
"num_tokens": 3045611.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 5.8729088306427,
|
|
"epoch": 0.1282420749279539,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999883451047981,
|
|
"loss": 5.8762,
|
|
"mean_token_accuracy": 0.15844262689352034,
|
|
"num_tokens": 3056420.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 5.954921579360962,
|
|
"epoch": 0.1287223823246878,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999879935470733,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.15611346065998077,
|
|
"num_tokens": 3068770.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.974037933349609,
|
|
"epoch": 0.1292026897214217,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999876367657954,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.14959089308977128,
|
|
"num_tokens": 3080806.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.0841004848480225,
|
|
"epoch": 0.12968299711815562,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999872747609725,
|
|
"loss": 6.0115,
|
|
"mean_token_accuracy": 0.148582760989666,
|
|
"num_tokens": 3091769.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 5.934437465667725,
|
|
"epoch": 0.13016330451488953,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999869075326132,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.15446539595723152,
|
|
"num_tokens": 3103121.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 5.926872205734253,
|
|
"epoch": 0.13064361191162344,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499986535080726,
|
|
"loss": 5.9118,
|
|
"mean_token_accuracy": 0.16010547876358033,
|
|
"num_tokens": 3115606.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 5.907022857666016,
|
|
"epoch": 0.13112391930835735,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999861574053196,
|
|
"loss": 5.817,
|
|
"mean_token_accuracy": 0.15984544306993484,
|
|
"num_tokens": 3127961.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 5.842336130142212,
|
|
"epoch": 0.13160422670509125,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999857745064027,
|
|
"loss": 5.8209,
|
|
"mean_token_accuracy": 0.16299932152032853,
|
|
"num_tokens": 3138316.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 5.8888438701629635,
|
|
"epoch": 0.13208453410182516,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499985386383984,
|
|
"loss": 5.8096,
|
|
"mean_token_accuracy": 0.16031325459480286,
|
|
"num_tokens": 3150818.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 5.9254203796386715,
|
|
"epoch": 0.13256484149855907,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999849930380729,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.15262809544801711,
|
|
"num_tokens": 3162066.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 5.905710363388062,
|
|
"epoch": 0.13304514889529298,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999845944686781,
|
|
"loss": 5.9448,
|
|
"mean_token_accuracy": 0.15179222375154494,
|
|
"num_tokens": 3172209.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.839788198471069,
|
|
"epoch": 0.1335254562920269,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999841906758093,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.1662571221590042,
|
|
"num_tokens": 3183248.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.891704511642456,
|
|
"epoch": 0.1340057636887608,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999837816594757,
|
|
"loss": 5.8751,
|
|
"mean_token_accuracy": 0.1616715520620346,
|
|
"num_tokens": 3194748.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.8394190788269045,
|
|
"epoch": 0.1344860710854947,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999833674196865,
|
|
"loss": 5.8262,
|
|
"mean_token_accuracy": 0.16983066648244857,
|
|
"num_tokens": 3205669.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 5.932120323181152,
|
|
"epoch": 0.13496637848222862,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999829479564518,
|
|
"loss": 5.9323,
|
|
"mean_token_accuracy": 0.15147673040628434,
|
|
"num_tokens": 3216035.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 5.91019926071167,
|
|
"epoch": 0.13544668587896252,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499982523269781,
|
|
"loss": 5.9229,
|
|
"mean_token_accuracy": 0.1604223743081093,
|
|
"num_tokens": 3227192.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 5.967643356323242,
|
|
"epoch": 0.13592699327569643,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999820933596842,
|
|
"loss": 5.9444,
|
|
"mean_token_accuracy": 0.1552926555275917,
|
|
"num_tokens": 3240237.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 5.8949769020080565,
|
|
"epoch": 0.13640730067243034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499981658226171,
|
|
"loss": 5.8197,
|
|
"mean_token_accuracy": 0.16560753658413888,
|
|
"num_tokens": 3251963.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 5.836411762237549,
|
|
"epoch": 0.13688760806916425,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499981217869252,
|
|
"loss": 5.9455,
|
|
"mean_token_accuracy": 0.1598033905029297,
|
|
"num_tokens": 3263101.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 5.931874179840088,
|
|
"epoch": 0.1373679154658982,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499980772288937,
|
|
"loss": 5.8244,
|
|
"mean_token_accuracy": 0.1647780194878578,
|
|
"num_tokens": 3275100.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 5.8633490085601805,
|
|
"epoch": 0.1378482228626321,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999803214852367,
|
|
"loss": 5.9191,
|
|
"mean_token_accuracy": 0.15635785311460496,
|
|
"num_tokens": 3287025.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 5.994219875335693,
|
|
"epoch": 0.138328530259366,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999798654581613,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.15802556350827218,
|
|
"num_tokens": 3299867.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.879111480712891,
|
|
"epoch": 0.13880883765609991,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999794042077214,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.15804315060377122,
|
|
"num_tokens": 3311183.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.878673124313354,
|
|
"epoch": 0.13928914505283382,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999789377339279,
|
|
"loss": 5.9276,
|
|
"mean_token_accuracy": 0.15720254927873611,
|
|
"num_tokens": 3322247.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.9163741111755375,
|
|
"epoch": 0.13976945244956773,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999784660367915,
|
|
"loss": 5.8385,
|
|
"mean_token_accuracy": 0.15729291439056398,
|
|
"num_tokens": 3333369.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 5.848420524597168,
|
|
"epoch": 0.14024975984630164,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999779891163231,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.15641703009605407,
|
|
"num_tokens": 3345876.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 5.823397970199585,
|
|
"epoch": 0.14073006724303555,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999775069725339,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.16413249373435973,
|
|
"num_tokens": 3357323.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.879242944717407,
|
|
"epoch": 0.14121037463976946,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499977019605435,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.16104292571544648,
|
|
"num_tokens": 3367689.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.7898133277893065,
|
|
"epoch": 0.14169068203650337,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999765270150378,
|
|
"loss": 5.8229,
|
|
"mean_token_accuracy": 0.1627983033657074,
|
|
"num_tokens": 3379472.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.936643600463867,
|
|
"epoch": 0.14217098943323728,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999760292013536,
|
|
"loss": 5.8592,
|
|
"mean_token_accuracy": 0.15795352756977082,
|
|
"num_tokens": 3390929.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.987182140350342,
|
|
"epoch": 0.14265129682997119,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999755261643941,
|
|
"loss": 5.8688,
|
|
"mean_token_accuracy": 0.16030031442642212,
|
|
"num_tokens": 3401242.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.724932861328125,
|
|
"epoch": 0.1431316042267051,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999750179041709,
|
|
"loss": 5.8341,
|
|
"mean_token_accuracy": 0.16148245185613633,
|
|
"num_tokens": 3411169.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.861591768264771,
|
|
"epoch": 0.143611911623439,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999745044206959,
|
|
"loss": 5.6953,
|
|
"mean_token_accuracy": 0.16694653928279876,
|
|
"num_tokens": 3423265.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.751557397842407,
|
|
"epoch": 0.1440922190201729,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999739857139809,
|
|
"loss": 5.7978,
|
|
"mean_token_accuracy": 0.17031814008951188,
|
|
"num_tokens": 3434793.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 5.758482551574707,
|
|
"epoch": 0.14457252641690682,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499973461784038,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.17440626472234727,
|
|
"num_tokens": 3445732.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.862774848937988,
|
|
"epoch": 0.14505283381364073,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999729326308792,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.15726853907108307,
|
|
"num_tokens": 3457090.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.91582670211792,
|
|
"epoch": 0.14553314121037464,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499972398254517,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.15424692034721374,
|
|
"num_tokens": 3468087.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.898725843429565,
|
|
"epoch": 0.14601344860710855,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499971858654964,
|
|
"loss": 5.8258,
|
|
"mean_token_accuracy": 0.16092963814735411,
|
|
"num_tokens": 3478820.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.792261123657227,
|
|
"epoch": 0.14649375600384246,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999713138322321,
|
|
"loss": 5.8591,
|
|
"mean_token_accuracy": 0.1586452417075634,
|
|
"num_tokens": 3489878.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.9086707592010494,
|
|
"epoch": 0.14697406340057637,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999707637863346,
|
|
"loss": 5.851,
|
|
"mean_token_accuracy": 0.16035019606351852,
|
|
"num_tokens": 3500944.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.832116031646729,
|
|
"epoch": 0.14745437079731027,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999702085172838,
|
|
"loss": 5.8328,
|
|
"mean_token_accuracy": 0.16494194120168687,
|
|
"num_tokens": 3511383.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.871267986297608,
|
|
"epoch": 0.14793467819404418,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999696480250929,
|
|
"loss": 5.9161,
|
|
"mean_token_accuracy": 0.15707188099622726,
|
|
"num_tokens": 3523300.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.878982782363892,
|
|
"epoch": 0.1484149855907781,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999690823097747,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.15446836575865747,
|
|
"num_tokens": 3534371.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.797754526138306,
|
|
"epoch": 0.148895292987512,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999685113713426,
|
|
"loss": 5.7968,
|
|
"mean_token_accuracy": 0.160531710088253,
|
|
"num_tokens": 3544847.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.870509910583496,
|
|
"epoch": 0.1493756003842459,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999679352098096,
|
|
"loss": 5.7779,
|
|
"mean_token_accuracy": 0.1664280965924263,
|
|
"num_tokens": 3555859.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.770110082626343,
|
|
"epoch": 0.14985590778097982,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999673538251891,
|
|
"loss": 5.8091,
|
|
"mean_token_accuracy": 0.163538558781147,
|
|
"num_tokens": 3568283.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.824569416046143,
|
|
"epoch": 0.15033621517771373,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999667672174947,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.15615147948265076,
|
|
"num_tokens": 3581442.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.916767597198486,
|
|
"epoch": 0.15081652257444764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049996617538674,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.153238382935524,
|
|
"num_tokens": 3594055.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.901634979248047,
|
|
"epoch": 0.15129682997118155,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999655783329386,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.15194391459226608,
|
|
"num_tokens": 3605952.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.905179977416992,
|
|
"epoch": 0.15177713736791545,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999649760561046,
|
|
"loss": 5.918,
|
|
"mean_token_accuracy": 0.15612740218639373,
|
|
"num_tokens": 3618544.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.822587013244629,
|
|
"epoch": 0.15225744476464936,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999643685562519,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.16425307244062423,
|
|
"num_tokens": 3630445.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.897658634185791,
|
|
"epoch": 0.15273775216138327,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999637558333945,
|
|
"loss": 5.847,
|
|
"mean_token_accuracy": 0.16267030090093612,
|
|
"num_tokens": 3642516.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.774902725219727,
|
|
"epoch": 0.15321805955811718,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999631378875467,
|
|
"loss": 5.7891,
|
|
"mean_token_accuracy": 0.16839728504419327,
|
|
"num_tokens": 3654425.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.729750633239746,
|
|
"epoch": 0.15369836695485112,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999625147187228,
|
|
"loss": 5.7867,
|
|
"mean_token_accuracy": 0.1628693163394928,
|
|
"num_tokens": 3666521.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.94893069267273,
|
|
"epoch": 0.15417867435158503,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999618863269373,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.15272799283266067,
|
|
"num_tokens": 3679121.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.843155765533448,
|
|
"epoch": 0.15465898174831894,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999612527122049,
|
|
"loss": 5.8525,
|
|
"mean_token_accuracy": 0.1609493985772133,
|
|
"num_tokens": 3691095.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.803921890258789,
|
|
"epoch": 0.15513928914505284,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999606138745402,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.1635987564921379,
|
|
"num_tokens": 3703426.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.907168912887573,
|
|
"epoch": 0.15561959654178675,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999599698139581,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.16405849605798722,
|
|
"num_tokens": 3715429.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.8696784496307375,
|
|
"epoch": 0.15609990393852066,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999593205304734,
|
|
"loss": 5.8666,
|
|
"mean_token_accuracy": 0.15650882422924042,
|
|
"num_tokens": 3726327.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.805680513381958,
|
|
"epoch": 0.15658021133525457,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999586660241012,
|
|
"loss": 5.8269,
|
|
"mean_token_accuracy": 0.1587029904127121,
|
|
"num_tokens": 3736818.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.871375560760498,
|
|
"epoch": 0.15706051873198848,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999580062948569,
|
|
"loss": 5.8187,
|
|
"mean_token_accuracy": 0.16604295521974563,
|
|
"num_tokens": 3747776.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.7270818710327145,
|
|
"epoch": 0.1575408261287224,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999573413427556,
|
|
"loss": 5.6821,
|
|
"mean_token_accuracy": 0.1644768789410591,
|
|
"num_tokens": 3758990.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.795487546920777,
|
|
"epoch": 0.1580211335254563,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999566711678128,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.16216196939349176,
|
|
"num_tokens": 3769686.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.823608541488648,
|
|
"epoch": 0.1585014409221902,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999559957700442,
|
|
"loss": 5.8296,
|
|
"mean_token_accuracy": 0.16916820257902146,
|
|
"num_tokens": 3781815.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.828753709793091,
|
|
"epoch": 0.15898174831892412,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999553151494653,
|
|
"loss": 5.8817,
|
|
"mean_token_accuracy": 0.163416787981987,
|
|
"num_tokens": 3793392.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.875366497039795,
|
|
"epoch": 0.15946205571565802,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999546293060919,
|
|
"loss": 5.8046,
|
|
"mean_token_accuracy": 0.16002268642187117,
|
|
"num_tokens": 3804974.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.679804134368896,
|
|
"epoch": 0.15994236311239193,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049995393823994,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.1683941051363945,
|
|
"num_tokens": 3817166.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.845706844329834,
|
|
"epoch": 0.16042267050912584,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999532419510255,
|
|
"loss": 5.7903,
|
|
"mean_token_accuracy": 0.15851810276508332,
|
|
"num_tokens": 3828151.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.775459575653076,
|
|
"epoch": 0.16090297790585975,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499952540439365,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.16600439697504044,
|
|
"num_tokens": 3839439.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.8537639617919925,
|
|
"epoch": 0.16138328530259366,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999518337049743,
|
|
"loss": 5.8575,
|
|
"mean_token_accuracy": 0.16149746179580687,
|
|
"num_tokens": 3851694.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.814331817626953,
|
|
"epoch": 0.16186359269932757,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049995112174787,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.16071560233831406,
|
|
"num_tokens": 3863593.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.757428455352783,
|
|
"epoch": 0.16234390009606148,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999504045680687,
|
|
"loss": 5.7451,
|
|
"mean_token_accuracy": 0.17077924609184264,
|
|
"num_tokens": 3874588.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.848338556289673,
|
|
"epoch": 0.1628242074927954,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999496821655869,
|
|
"loss": 5.8301,
|
|
"mean_token_accuracy": 0.16226118803024292,
|
|
"num_tokens": 3884662.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.919607067108155,
|
|
"epoch": 0.1633045148895293,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999489545404414,
|
|
"loss": 5.9373,
|
|
"mean_token_accuracy": 0.15780273377895354,
|
|
"num_tokens": 3896569.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.891122817993164,
|
|
"epoch": 0.1637848222862632,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999482216926493,
|
|
"loss": 5.7752,
|
|
"mean_token_accuracy": 0.1660735175013542,
|
|
"num_tokens": 3907691.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.800317049026489,
|
|
"epoch": 0.1642651296829971,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999474836222273,
|
|
"loss": 5.8132,
|
|
"mean_token_accuracy": 0.16834355145692825,
|
|
"num_tokens": 3918794.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.762091016769409,
|
|
"epoch": 0.16474543707973102,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999467403291928,
|
|
"loss": 5.8057,
|
|
"mean_token_accuracy": 0.17103115618228912,
|
|
"num_tokens": 3929773.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.827874994277954,
|
|
"epoch": 0.16522574447646493,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999459918135628,
|
|
"loss": 5.8165,
|
|
"mean_token_accuracy": 0.1614014983177185,
|
|
"num_tokens": 3940264.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.767197751998902,
|
|
"epoch": 0.16570605187319884,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499945238075355,
|
|
"loss": 5.7126,
|
|
"mean_token_accuracy": 0.16887413412332536,
|
|
"num_tokens": 3951500.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.768859052658081,
|
|
"epoch": 0.16618635926993275,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999444791145865,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.16888490319252014,
|
|
"num_tokens": 3963580.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.77203631401062,
|
|
"epoch": 0.16666666666666666,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999437149312754,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.17580520510673522,
|
|
"num_tokens": 3975994.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.750101137161255,
|
|
"epoch": 0.16714697406340057,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499942945525439,
|
|
"loss": 5.7407,
|
|
"mean_token_accuracy": 0.16059352904558183,
|
|
"num_tokens": 3987897.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.830537223815918,
|
|
"epoch": 0.16762728146013448,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999421708970954,
|
|
"loss": 5.9065,
|
|
"mean_token_accuracy": 0.15451293736696242,
|
|
"num_tokens": 3999829.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.702850294113159,
|
|
"epoch": 0.16810758885686838,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999413910462625,
|
|
"loss": 5.7402,
|
|
"mean_token_accuracy": 0.16505281925201415,
|
|
"num_tokens": 4010882.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.792970514297485,
|
|
"epoch": 0.1685878962536023,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999406059729586,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.1683162346482277,
|
|
"num_tokens": 4021423.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.862555932998657,
|
|
"epoch": 0.1690682036503362,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999398156772016,
|
|
"loss": 5.8596,
|
|
"mean_token_accuracy": 0.1502479761838913,
|
|
"num_tokens": 4033590.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.660853147506714,
|
|
"epoch": 0.16954851104707014,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049993902015901,
|
|
"loss": 5.7302,
|
|
"mean_token_accuracy": 0.16440801918506623,
|
|
"num_tokens": 4043978.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.899917888641357,
|
|
"epoch": 0.17002881844380405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999382194184023,
|
|
"loss": 5.8549,
|
|
"mean_token_accuracy": 0.16516084223985672,
|
|
"num_tokens": 4054513.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.817892074584961,
|
|
"epoch": 0.17050912584053796,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999374134553972,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.16183752417564393,
|
|
"num_tokens": 4066019.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.800725221633911,
|
|
"epoch": 0.17098943323727187,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999366022700131,
|
|
"loss": 5.7573,
|
|
"mean_token_accuracy": 0.16529648154973983,
|
|
"num_tokens": 4077688.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.798897457122803,
|
|
"epoch": 0.17146974063400577,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999357858622691,
|
|
"loss": 5.8469,
|
|
"mean_token_accuracy": 0.16481383070349692,
|
|
"num_tokens": 4089803.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.757664203643799,
|
|
"epoch": 0.17195004803073968,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999349642321842,
|
|
"loss": 5.7949,
|
|
"mean_token_accuracy": 0.1683555766940117,
|
|
"num_tokens": 4101969.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.800323820114135,
|
|
"epoch": 0.1724303554274736,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999341373797772,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.1607923164963722,
|
|
"num_tokens": 4113567.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.705751991271972,
|
|
"epoch": 0.1729106628242075,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999333053050675,
|
|
"loss": 5.7362,
|
|
"mean_token_accuracy": 0.167422915995121,
|
|
"num_tokens": 4125191.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.851807498931885,
|
|
"epoch": 0.1733909702209414,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999324680080744,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.16796549558639526,
|
|
"num_tokens": 4135050.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.720352649688721,
|
|
"epoch": 0.17387127761767532,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999316254888172,
|
|
"loss": 5.8385,
|
|
"mean_token_accuracy": 0.16350539326667785,
|
|
"num_tokens": 4146874.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.835164594650268,
|
|
"epoch": 0.17435158501440923,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999307777473157,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.16278114020824433,
|
|
"num_tokens": 4158118.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.767681217193603,
|
|
"epoch": 0.17483189241114314,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999299247835893,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.17328064888715744,
|
|
"num_tokens": 4169035.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.757311296463013,
|
|
"epoch": 0.17531219980787704,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499929066597658,
|
|
"loss": 5.7298,
|
|
"mean_token_accuracy": 0.1677858605980873,
|
|
"num_tokens": 4180314.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.794700860977173,
|
|
"epoch": 0.17579250720461095,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999282031895418,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.16751174479722977,
|
|
"num_tokens": 4192238.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.698655652999878,
|
|
"epoch": 0.17627281460134486,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999273345592604,
|
|
"loss": 5.7246,
|
|
"mean_token_accuracy": 0.1654239699244499,
|
|
"num_tokens": 4203346.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.774805736541748,
|
|
"epoch": 0.17675312199807877,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999264607068343,
|
|
"loss": 5.7998,
|
|
"mean_token_accuracy": 0.16761503517627716,
|
|
"num_tokens": 4213763.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.763230466842652,
|
|
"epoch": 0.17723342939481268,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999255816322837,
|
|
"loss": 5.7485,
|
|
"mean_token_accuracy": 0.17157458364963532,
|
|
"num_tokens": 4225553.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.814038228988648,
|
|
"epoch": 0.1777137367915466,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499924697335629,
|
|
"loss": 5.6599,
|
|
"mean_token_accuracy": 0.17285525798797607,
|
|
"num_tokens": 4236058.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.651153945922852,
|
|
"epoch": 0.1781940441882805,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999238078168906,
|
|
"loss": 5.7627,
|
|
"mean_token_accuracy": 0.16969517916440963,
|
|
"num_tokens": 4248299.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.73550329208374,
|
|
"epoch": 0.1786743515850144,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999229130760894,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.17190667539834975,
|
|
"num_tokens": 4259704.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.681738233566284,
|
|
"epoch": 0.17915465898174832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499922013113246,
|
|
"loss": 5.5603,
|
|
"mean_token_accuracy": 0.17824512124061584,
|
|
"num_tokens": 4270480.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.715903425216675,
|
|
"epoch": 0.17963496637848222,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999211079283814,
|
|
"loss": 5.8301,
|
|
"mean_token_accuracy": 0.16724407076835632,
|
|
"num_tokens": 4282104.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.824806594848633,
|
|
"epoch": 0.18011527377521613,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999201975215164,
|
|
"loss": 5.8023,
|
|
"mean_token_accuracy": 0.15896975696086885,
|
|
"num_tokens": 4294251.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.720139122009277,
|
|
"epoch": 0.18059558117195004,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999192818926725,
|
|
"loss": 5.671,
|
|
"mean_token_accuracy": 0.16729482859373093,
|
|
"num_tokens": 4305569.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.807558631896972,
|
|
"epoch": 0.18107588856868395,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999183610418706,
|
|
"loss": 5.8147,
|
|
"mean_token_accuracy": 0.15925741717219352,
|
|
"num_tokens": 4317845.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.724898910522461,
|
|
"epoch": 0.18155619596541786,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999174349691322,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.1716127187013626,
|
|
"num_tokens": 4329987.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.652930164337159,
|
|
"epoch": 0.18203650336215177,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999165036744788,
|
|
"loss": 5.6962,
|
|
"mean_token_accuracy": 0.16952552348375322,
|
|
"num_tokens": 4341628.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.793127250671387,
|
|
"epoch": 0.18251681075888568,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999155671579322,
|
|
"loss": 5.7653,
|
|
"mean_token_accuracy": 0.16651546359062194,
|
|
"num_tokens": 4352379.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.642123651504517,
|
|
"epoch": 0.1829971181556196,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499914625419514,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.17030369937419892,
|
|
"num_tokens": 4364800.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.780552530288697,
|
|
"epoch": 0.1834774255523535,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999136784592459,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.16404880583286285,
|
|
"num_tokens": 4376048.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.702418661117553,
|
|
"epoch": 0.1839577329490874,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999127262771502,
|
|
"loss": 5.7174,
|
|
"mean_token_accuracy": 0.16724415123462677,
|
|
"num_tokens": 4388072.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.787232398986816,
|
|
"epoch": 0.1844380403458213,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999117688732487,
|
|
"loss": 5.8078,
|
|
"mean_token_accuracy": 0.16127374917268752,
|
|
"num_tokens": 4399843.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.705273008346557,
|
|
"epoch": 0.18491834774255522,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999108062475638,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.16955924928188323,
|
|
"num_tokens": 4411373.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.6590807914733885,
|
|
"epoch": 0.18539865513928913,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499909838400118,
|
|
"loss": 5.6538,
|
|
"mean_token_accuracy": 0.16991744339466094,
|
|
"num_tokens": 4421857.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.794595336914062,
|
|
"epoch": 0.18587896253602307,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999088653309334,
|
|
"loss": 5.7445,
|
|
"mean_token_accuracy": 0.16888943165540696,
|
|
"num_tokens": 4432728.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.68063588142395,
|
|
"epoch": 0.18635926993275698,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999078870400329,
|
|
"loss": 5.6745,
|
|
"mean_token_accuracy": 0.1725231423974037,
|
|
"num_tokens": 4444683.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.8351945877075195,
|
|
"epoch": 0.18683957732949089,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999069035274391,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.16090195178985595,
|
|
"num_tokens": 4456961.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.708295679092407,
|
|
"epoch": 0.1873198847262248,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999059147931747,
|
|
"loss": 5.6544,
|
|
"mean_token_accuracy": 0.1740499570965767,
|
|
"num_tokens": 4468424.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.693359899520874,
|
|
"epoch": 0.1878001921229587,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999049208372629,
|
|
"loss": 5.8535,
|
|
"mean_token_accuracy": 0.15306217297911645,
|
|
"num_tokens": 4479813.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.9555785179138185,
|
|
"epoch": 0.1882804995196926,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999039216597267,
|
|
"loss": 5.857,
|
|
"mean_token_accuracy": 0.16386826783418657,
|
|
"num_tokens": 4491172.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.714920616149902,
|
|
"epoch": 0.18876080691642652,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999029172605892,
|
|
"loss": 5.7265,
|
|
"mean_token_accuracy": 0.1694802775979042,
|
|
"num_tokens": 4503063.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.728699588775635,
|
|
"epoch": 0.18924111431316043,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999019076398738,
|
|
"loss": 5.8081,
|
|
"mean_token_accuracy": 0.15379680097103118,
|
|
"num_tokens": 4514188.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.803501796722412,
|
|
"epoch": 0.18972142170989434,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499900892797604,
|
|
"loss": 5.7153,
|
|
"mean_token_accuracy": 0.17307915687561035,
|
|
"num_tokens": 4525293.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.681381177902222,
|
|
"epoch": 0.19020172910662825,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998998727338031,
|
|
"loss": 5.7995,
|
|
"mean_token_accuracy": 0.16841245889663697,
|
|
"num_tokens": 4536589.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.680044507980346,
|
|
"epoch": 0.19068203650336216,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998988474484952,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.19009238332509995,
|
|
"num_tokens": 4547594.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.723686408996582,
|
|
"epoch": 0.19116234390009607,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998978169417038,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.17050471901893616,
|
|
"num_tokens": 4559850.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.688448333740235,
|
|
"epoch": 0.19164265129682997,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998967812134529,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.16840659379959105,
|
|
"num_tokens": 4570727.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.627355909347534,
|
|
"epoch": 0.19212295869356388,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998957402637664,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.17101026326417923,
|
|
"num_tokens": 4582248.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.747193193435669,
|
|
"epoch": 0.1926032660902978,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998946940926687,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.16754180192947388,
|
|
"num_tokens": 4592604.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.705648469924927,
|
|
"epoch": 0.1930835734870317,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499893642700184,
|
|
"loss": 5.697,
|
|
"mean_token_accuracy": 0.16855939775705336,
|
|
"num_tokens": 4604398.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.7156165599822994,
|
|
"epoch": 0.1935638808837656,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998925860863368,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.16711266487836837,
|
|
"num_tokens": 4616434.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.8197449207305905,
|
|
"epoch": 0.19404418828049952,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998915242511516,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.17766132801771164,
|
|
"num_tokens": 4627577.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.760650587081909,
|
|
"epoch": 0.19452449567723343,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998904571946528,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.16647073179483413,
|
|
"num_tokens": 4639698.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.7918251037597654,
|
|
"epoch": 0.19500480307396734,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998893849168655,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.16515694856643676,
|
|
"num_tokens": 4650643.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.729197692871094,
|
|
"epoch": 0.19548511047070125,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998883074178144,
|
|
"loss": 5.7299,
|
|
"mean_token_accuracy": 0.16899616420269012,
|
|
"num_tokens": 4662897.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.78673620223999,
|
|
"epoch": 0.19596541786743515,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998872246975247,
|
|
"loss": 5.8035,
|
|
"mean_token_accuracy": 0.17029557675123214,
|
|
"num_tokens": 4673701.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.8532195568084715,
|
|
"epoch": 0.19644572526416906,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998861367560213,
|
|
"loss": 5.7681,
|
|
"mean_token_accuracy": 0.16402131766080857,
|
|
"num_tokens": 4685873.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.705864477157593,
|
|
"epoch": 0.19692603266090297,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998850435933296,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.1674431025981903,
|
|
"num_tokens": 4697179.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.69135422706604,
|
|
"epoch": 0.19740634005763688,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998839452094749,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.16994271278381348,
|
|
"num_tokens": 4707752.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.616186046600342,
|
|
"epoch": 0.1978866474543708,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998828416044829,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.1783631145954132,
|
|
"num_tokens": 4718413.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.688624095916748,
|
|
"epoch": 0.1983669548511047,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499881732778379,
|
|
"loss": 5.7564,
|
|
"mean_token_accuracy": 0.16201746314764023,
|
|
"num_tokens": 4730033.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.673749017715454,
|
|
"epoch": 0.1988472622478386,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499880618731189,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.17548538893461227,
|
|
"num_tokens": 4742084.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.797257137298584,
|
|
"epoch": 0.19932756964457252,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998794994629388,
|
|
"loss": 5.8426,
|
|
"mean_token_accuracy": 0.16158316135406495,
|
|
"num_tokens": 4753885.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.67535138130188,
|
|
"epoch": 0.19980787704130643,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998783749736545,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.1719197377562523,
|
|
"num_tokens": 4765686.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.73932523727417,
|
|
"epoch": 0.20028818443804033,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998772452633619,
|
|
"loss": 5.7153,
|
|
"mean_token_accuracy": 0.16890633404254912,
|
|
"num_tokens": 4777157.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.667795467376709,
|
|
"epoch": 0.20076849183477424,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998761103320876,
|
|
"loss": 5.6598,
|
|
"mean_token_accuracy": 0.17424789518117906,
|
|
"num_tokens": 4788583.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.773211097717285,
|
|
"epoch": 0.20124879923150815,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998749701798577,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.16303450614213943,
|
|
"num_tokens": 4800749.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.692271423339844,
|
|
"epoch": 0.2017291066282421,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998738248066986,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.16909822523593904,
|
|
"num_tokens": 4812488.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.726241397857666,
|
|
"epoch": 0.202209414024976,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998726742126372,
|
|
"loss": 5.6624,
|
|
"mean_token_accuracy": 0.17131896913051606,
|
|
"num_tokens": 4823495.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.6755859375,
|
|
"epoch": 0.2026897214217099,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998715183976999,
|
|
"loss": 5.7133,
|
|
"mean_token_accuracy": 0.1694028452038765,
|
|
"num_tokens": 4834450.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.707360458374024,
|
|
"epoch": 0.20317002881844382,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998703573619137,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.17751273810863494,
|
|
"num_tokens": 4846826.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.775042343139648,
|
|
"epoch": 0.20365033621517772,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998691911053056,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.15342799127101897,
|
|
"num_tokens": 4859668.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.706689357757568,
|
|
"epoch": 0.20413064361191163,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998680196279026,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.17123338729143142,
|
|
"num_tokens": 4871727.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.769245243072509,
|
|
"epoch": 0.20461095100864554,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998668429297319,
|
|
"loss": 5.7411,
|
|
"mean_token_accuracy": 0.17646165192127228,
|
|
"num_tokens": 4882191.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.694307518005371,
|
|
"epoch": 0.20509125840537945,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998656610108208,
|
|
"loss": 5.6871,
|
|
"mean_token_accuracy": 0.1733158901333809,
|
|
"num_tokens": 4892416.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.637541389465332,
|
|
"epoch": 0.20557156580211336,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998644738711969,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.16460631638765336,
|
|
"num_tokens": 4903572.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.831057977676392,
|
|
"epoch": 0.20605187319884727,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998632815108874,
|
|
"loss": 5.7508,
|
|
"mean_token_accuracy": 0.1634954646229744,
|
|
"num_tokens": 4915417.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.679442882537842,
|
|
"epoch": 0.20653218059558118,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998620839299203,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.17169499546289443,
|
|
"num_tokens": 4926943.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.637327718734741,
|
|
"epoch": 0.2070124879923151,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998608811283233,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.17698758840560913,
|
|
"num_tokens": 4937724.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.781380033493042,
|
|
"epoch": 0.207492795389049,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998596731061244,
|
|
"loss": 5.7564,
|
|
"mean_token_accuracy": 0.1639716997742653,
|
|
"num_tokens": 4949970.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.736811876296997,
|
|
"epoch": 0.2079731027857829,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998584598633516,
|
|
"loss": 5.7619,
|
|
"mean_token_accuracy": 0.16606154888868332,
|
|
"num_tokens": 4961389.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.77227520942688,
|
|
"epoch": 0.2084534101825168,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998572414000329,
|
|
"loss": 5.7965,
|
|
"mean_token_accuracy": 0.16175206303596495,
|
|
"num_tokens": 4973888.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.692326450347901,
|
|
"epoch": 0.20893371757925072,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998560177161969,
|
|
"loss": 5.7423,
|
|
"mean_token_accuracy": 0.16151960492134093,
|
|
"num_tokens": 4985423.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.703728437423706,
|
|
"epoch": 0.20941402497598463,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998547888118718,
|
|
"loss": 5.6991,
|
|
"mean_token_accuracy": 0.16135767474770546,
|
|
"num_tokens": 4997711.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.738592958450317,
|
|
"epoch": 0.20989433237271854,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998535546870862,
|
|
"loss": 5.7331,
|
|
"mean_token_accuracy": 0.1701716125011444,
|
|
"num_tokens": 5009633.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.697732830047608,
|
|
"epoch": 0.21037463976945245,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998523153418687,
|
|
"loss": 5.6588,
|
|
"mean_token_accuracy": 0.17793772220611573,
|
|
"num_tokens": 5021523.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.768330860137939,
|
|
"epoch": 0.21085494716618636,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998510707762481,
|
|
"loss": 5.7714,
|
|
"mean_token_accuracy": 0.17047424465417862,
|
|
"num_tokens": 5033513.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.80808277130127,
|
|
"epoch": 0.21133525456292027,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998498209902533,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.16494739651679993,
|
|
"num_tokens": 5047055.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.715298700332641,
|
|
"epoch": 0.21181556195965417,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998485659839134,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.1722339630126953,
|
|
"num_tokens": 5057613.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.690679025650025,
|
|
"epoch": 0.21229586935638808,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998473057572575,
|
|
"loss": 5.7583,
|
|
"mean_token_accuracy": 0.16326719522476196,
|
|
"num_tokens": 5068886.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.729583644866944,
|
|
"epoch": 0.212776176753122,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998460403103146,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.16544922143220903,
|
|
"num_tokens": 5079978.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.702667665481568,
|
|
"epoch": 0.2132564841498559,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998447696431146,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.1646025523543358,
|
|
"num_tokens": 5091021.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.6252116680145265,
|
|
"epoch": 0.2137367915465898,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998434937556865,
|
|
"loss": 5.5938,
|
|
"mean_token_accuracy": 0.18118904829025267,
|
|
"num_tokens": 5101483.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.687475872039795,
|
|
"epoch": 0.21421709894332372,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998422126480602,
|
|
"loss": 5.7294,
|
|
"mean_token_accuracy": 0.16596931368112564,
|
|
"num_tokens": 5113116.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.752994346618652,
|
|
"epoch": 0.21469740634005763,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998409263202653,
|
|
"loss": 5.6737,
|
|
"mean_token_accuracy": 0.1711043745279312,
|
|
"num_tokens": 5124824.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.625597286224365,
|
|
"epoch": 0.21517771373679154,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998396347723318,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.16584012061357498,
|
|
"num_tokens": 5137567.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.656725549697876,
|
|
"epoch": 0.21565802113352545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998383380042895,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.16893255859613418,
|
|
"num_tokens": 5149016.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.6132111072540285,
|
|
"epoch": 0.21613832853025935,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998370360161688,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.1746796503663063,
|
|
"num_tokens": 5160356.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.731980705261231,
|
|
"epoch": 0.21661863592699326,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998357288079996,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.1585668906569481,
|
|
"num_tokens": 5172100.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.742927980422974,
|
|
"epoch": 0.21709894332372717,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998344163798125,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.1649263843894005,
|
|
"num_tokens": 5183984.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.6998608112335205,
|
|
"epoch": 0.21757925072046108,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998330987316379,
|
|
"loss": 5.6959,
|
|
"mean_token_accuracy": 0.16934084445238112,
|
|
"num_tokens": 5195853.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.582950830459595,
|
|
"epoch": 0.21805955811719502,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998317758635062,
|
|
"loss": 5.553,
|
|
"mean_token_accuracy": 0.17454090416431428,
|
|
"num_tokens": 5206995.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.528365898132324,
|
|
"epoch": 0.21853986551392893,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998304477754484,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.17734886556863785,
|
|
"num_tokens": 5219291.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.698074150085449,
|
|
"epoch": 0.21902017291066284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998291144674952,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.1741125002503395,
|
|
"num_tokens": 5230856.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.550833034515381,
|
|
"epoch": 0.21950048030739674,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998277759396776,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.18115451484918593,
|
|
"num_tokens": 5242871.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.642746257781982,
|
|
"epoch": 0.21998078770413065,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998264321920265,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.17632727175951005,
|
|
"num_tokens": 5253835.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.607524776458741,
|
|
"epoch": 0.22046109510086456,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998250832245734,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.17378197759389877,
|
|
"num_tokens": 5266195.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.587347507476807,
|
|
"epoch": 0.22094140249759847,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998237290373494,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.1766304701566696,
|
|
"num_tokens": 5277499.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.808111667633057,
|
|
"epoch": 0.22142170989433238,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499822369630386,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.16190741956233978,
|
|
"num_tokens": 5288622.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.674302768707276,
|
|
"epoch": 0.2219020172910663,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998210050037148,
|
|
"loss": 5.7572,
|
|
"mean_token_accuracy": 0.16639357209205627,
|
|
"num_tokens": 5299664.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.712857103347778,
|
|
"epoch": 0.2223823246878002,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998196351573674,
|
|
"loss": 5.6606,
|
|
"mean_token_accuracy": 0.16955843269824983,
|
|
"num_tokens": 5311627.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.487867975234986,
|
|
"epoch": 0.2228626320845341,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998182600913757,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.1790629059076309,
|
|
"num_tokens": 5323000.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.663056659698486,
|
|
"epoch": 0.22334293948126802,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998168798057715,
|
|
"loss": 5.5905,
|
|
"mean_token_accuracy": 0.17954156398773194,
|
|
"num_tokens": 5333811.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.633950281143188,
|
|
"epoch": 0.22382324687800192,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499815494300587,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.17360343933105468,
|
|
"num_tokens": 5344762.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.6991064071655275,
|
|
"epoch": 0.22430355427473583,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998141035758542,
|
|
"loss": 5.6137,
|
|
"mean_token_accuracy": 0.17193799018859862,
|
|
"num_tokens": 5356112.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.693173122406006,
|
|
"epoch": 0.22478386167146974,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998127076316054,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.1709176391363144,
|
|
"num_tokens": 5367339.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.5998108863830565,
|
|
"epoch": 0.22526416906820365,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998113064678734,
|
|
"loss": 5.6671,
|
|
"mean_token_accuracy": 0.17647625803947448,
|
|
"num_tokens": 5378627.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.681573581695557,
|
|
"epoch": 0.22574447646493756,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998099000846901,
|
|
"loss": 5.676,
|
|
"mean_token_accuracy": 0.1716631054878235,
|
|
"num_tokens": 5390209.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.753207540512085,
|
|
"epoch": 0.22622478386167147,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998084884820887,
|
|
"loss": 5.6638,
|
|
"mean_token_accuracy": 0.17146301716566087,
|
|
"num_tokens": 5401578.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.559879016876221,
|
|
"epoch": 0.22670509125840538,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998070716601016,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.17349850237369538,
|
|
"num_tokens": 5413831.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.736428117752075,
|
|
"epoch": 0.2271853986551393,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004998056496187618,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.16810473650693894,
|
|
"num_tokens": 5425430.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.504029655456543,
|
|
"epoch": 0.2276657060518732,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998042223581025,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.18336689323186875,
|
|
"num_tokens": 5435353.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.672350740432739,
|
|
"epoch": 0.2281460134486071,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998027898781565,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.17117476016283034,
|
|
"num_tokens": 5446925.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.588083076477051,
|
|
"epoch": 0.228626320845341,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998013521789574,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.1782747909426689,
|
|
"num_tokens": 5456613.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.652026605606079,
|
|
"epoch": 0.22910662824207492,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997999092605384,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.1741020068526268,
|
|
"num_tokens": 5467790.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.674703168869018,
|
|
"epoch": 0.22958693563880883,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499798461122933,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.17193887382745743,
|
|
"num_tokens": 5479166.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.573598337173462,
|
|
"epoch": 0.23006724303554274,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997970077661748,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.18137670904397965,
|
|
"num_tokens": 5490186.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.619629526138306,
|
|
"epoch": 0.23054755043227665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997955491902977,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.1695369765162468,
|
|
"num_tokens": 5500416.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.604301977157593,
|
|
"epoch": 0.23102785782901056,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997940853953354,
|
|
"loss": 5.6431,
|
|
"mean_token_accuracy": 0.17374449223279953,
|
|
"num_tokens": 5512189.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.582362318038941,
|
|
"epoch": 0.23150816522574447,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499792616381322,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.18147529810667037,
|
|
"num_tokens": 5523631.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.593402290344239,
|
|
"epoch": 0.23198847262247838,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997911421482914,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.17937678545713426,
|
|
"num_tokens": 5535637.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.606865262985229,
|
|
"epoch": 0.23246878001921228,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499789662696278,
|
|
"loss": 5.5633,
|
|
"mean_token_accuracy": 0.17965568751096725,
|
|
"num_tokens": 5546470.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.732225847244263,
|
|
"epoch": 0.2329490874159462,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997881780253162,
|
|
"loss": 5.735,
|
|
"mean_token_accuracy": 0.16651479601860047,
|
|
"num_tokens": 5558633.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.65433440208435,
|
|
"epoch": 0.2334293948126801,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997866881354403,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.16686196625232697,
|
|
"num_tokens": 5570427.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.633258295059204,
|
|
"epoch": 0.23390970220941404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499785193026685,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.17191858291625978,
|
|
"num_tokens": 5580991.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.714870405197144,
|
|
"epoch": 0.23439000960614795,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997836926990851,
|
|
"loss": 5.6784,
|
|
"mean_token_accuracy": 0.16975432336330415,
|
|
"num_tokens": 5592777.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.562553024291992,
|
|
"epoch": 0.23487031700288186,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997821871526752,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.18020368814468385,
|
|
"num_tokens": 5603326.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.63916049003601,
|
|
"epoch": 0.23535062439961577,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997806763874905,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.1807892918586731,
|
|
"num_tokens": 5614504.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.566304111480713,
|
|
"epoch": 0.23583093179634967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997791604035659,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.17212841361761094,
|
|
"num_tokens": 5625150.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.6469151973724365,
|
|
"epoch": 0.23631123919308358,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997776392009366,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.17139502614736557,
|
|
"num_tokens": 5636815.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.676492214202881,
|
|
"epoch": 0.2367915465898175,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997761127796381,
|
|
"loss": 5.6309,
|
|
"mean_token_accuracy": 0.17232394814491273,
|
|
"num_tokens": 5648272.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.567654180526733,
|
|
"epoch": 0.2372718539865514,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997745811397056,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.17994675189256668,
|
|
"num_tokens": 5659227.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.675694322586059,
|
|
"epoch": 0.2377521613832853,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997730442811748,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.17343941926956177,
|
|
"num_tokens": 5670411.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.523682308197022,
|
|
"epoch": 0.23823246878001922,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997715022040814,
|
|
"loss": 5.5161,
|
|
"mean_token_accuracy": 0.1774153307080269,
|
|
"num_tokens": 5681570.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.56575231552124,
|
|
"epoch": 0.23871277617675313,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499769954908461,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.18815021812915803,
|
|
"num_tokens": 5693021.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.59642448425293,
|
|
"epoch": 0.23919308357348704,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997684023943498,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.17071316242218018,
|
|
"num_tokens": 5704043.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.5925071239471436,
|
|
"epoch": 0.23967339097022095,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997668446617837,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.16719016283750535,
|
|
"num_tokens": 5715735.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.758069133758545,
|
|
"epoch": 0.24015369836695485,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997652817107989,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.17078911662101745,
|
|
"num_tokens": 5725778.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.590348434448242,
|
|
"epoch": 0.24063400576368876,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997637135414315,
|
|
"loss": 5.6664,
|
|
"mean_token_accuracy": 0.1705973908305168,
|
|
"num_tokens": 5737224.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.738520574569702,
|
|
"epoch": 0.24111431316042267,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997621401537183,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.16897378265857696,
|
|
"num_tokens": 5749226.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.674526071548462,
|
|
"epoch": 0.24159462055715658,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997605615476955,
|
|
"loss": 5.6528,
|
|
"mean_token_accuracy": 0.1699451506137848,
|
|
"num_tokens": 5760282.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.537546300888062,
|
|
"epoch": 0.2420749279538905,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997589777234,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.18102957159280778,
|
|
"num_tokens": 5771756.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.607472324371338,
|
|
"epoch": 0.2425552353506244,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997573886808684,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.16630816012620925,
|
|
"num_tokens": 5783237.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.678776550292969,
|
|
"epoch": 0.2430355427473583,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997557944201375,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.16766075044870377,
|
|
"num_tokens": 5794825.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.666126108169555,
|
|
"epoch": 0.24351585014409222,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997541949412445,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.18059189170598983,
|
|
"num_tokens": 5805578.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.628619766235351,
|
|
"epoch": 0.24399615754082613,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997525902442266,
|
|
"loss": 5.6757,
|
|
"mean_token_accuracy": 0.16800872087478638,
|
|
"num_tokens": 5818201.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.603051424026489,
|
|
"epoch": 0.24447646493756003,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997509803291207,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.17619250267744063,
|
|
"num_tokens": 5830319.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.594012975692749,
|
|
"epoch": 0.24495677233429394,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997493651959647,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.1775872141122818,
|
|
"num_tokens": 5840638.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.638534832000732,
|
|
"epoch": 0.24543707973102785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997477448447955,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.17032771110534667,
|
|
"num_tokens": 5852472.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.638302135467529,
|
|
"epoch": 0.24591738712776176,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997461192756512,
|
|
"loss": 5.6046,
|
|
"mean_token_accuracy": 0.16819358468055726,
|
|
"num_tokens": 5863455.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.467128944396973,
|
|
"epoch": 0.24639769452449567,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997444884885694,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.17530121356248857,
|
|
"num_tokens": 5873141.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.595350074768066,
|
|
"epoch": 0.24687800192122958,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997428524835879,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.17465465068817138,
|
|
"num_tokens": 5884363.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.70411229133606,
|
|
"epoch": 0.2473583093179635,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997412112607446,
|
|
"loss": 5.6741,
|
|
"mean_token_accuracy": 0.16950604766607286,
|
|
"num_tokens": 5895856.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.538848733901977,
|
|
"epoch": 0.2478386167146974,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997395648200778,
|
|
"loss": 5.4891,
|
|
"mean_token_accuracy": 0.17632174789905547,
|
|
"num_tokens": 5906657.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.580999422073364,
|
|
"epoch": 0.2483189241114313,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997379131616257,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.17375119030475616,
|
|
"num_tokens": 5919496.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.697788429260254,
|
|
"epoch": 0.24879923150816521,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997362562854266,
|
|
"loss": 5.6852,
|
|
"mean_token_accuracy": 0.16293373256921767,
|
|
"num_tokens": 5932593.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.618240022659302,
|
|
"epoch": 0.24927953890489912,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997345941915187,
|
|
"loss": 5.6009,
|
|
"mean_token_accuracy": 0.17481830567121506,
|
|
"num_tokens": 5944080.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.582438802719116,
|
|
"epoch": 0.24975984630163303,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997329268799412,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.1803409516811371,
|
|
"num_tokens": 5955703.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.580913972854614,
|
|
"epoch": 0.25024015369836694,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997312543507322,
|
|
"loss": 5.653,
|
|
"mean_token_accuracy": 0.1710635617375374,
|
|
"num_tokens": 5966979.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.6705735206604,
|
|
"epoch": 0.2507204610951009,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997295766039309,
|
|
"loss": 5.5407,
|
|
"mean_token_accuracy": 0.1745874598622322,
|
|
"num_tokens": 5978808.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.65955605506897,
|
|
"epoch": 0.25120076849183476,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997278936395761,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.16464963108301162,
|
|
"num_tokens": 5992145.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.63467960357666,
|
|
"epoch": 0.2516810758885687,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997262054577071,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.17598808258771897,
|
|
"num_tokens": 6003723.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.644701385498047,
|
|
"epoch": 0.2521613832853026,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997245120583627,
|
|
"loss": 5.6317,
|
|
"mean_token_accuracy": 0.17510675489902497,
|
|
"num_tokens": 6014064.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.549881219863892,
|
|
"epoch": 0.2526416906820365,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997228134415825,
|
|
"loss": 5.519,
|
|
"mean_token_accuracy": 0.17940374165773393,
|
|
"num_tokens": 6025455.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.650017738342285,
|
|
"epoch": 0.2531219980787704,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997211096074059,
|
|
"loss": 5.6276,
|
|
"mean_token_accuracy": 0.16702284514904023,
|
|
"num_tokens": 6037347.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.593641376495361,
|
|
"epoch": 0.25360230547550433,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997194005558722,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.1768082469701767,
|
|
"num_tokens": 6049236.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.517231559753418,
|
|
"epoch": 0.2540826128722382,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997176862870216,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.17889825999736786,
|
|
"num_tokens": 6060982.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.642611408233643,
|
|
"epoch": 0.25456292026897215,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997159668008933,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.1735323816537857,
|
|
"num_tokens": 6070925.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.540967607498169,
|
|
"epoch": 0.25504322766570603,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997142420975277,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.17900281250476838,
|
|
"num_tokens": 6081279.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.574090194702149,
|
|
"epoch": 0.25552353506243997,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997125121769647,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.17885100841522217,
|
|
"num_tokens": 6091797.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.664024591445923,
|
|
"epoch": 0.25600384245917385,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997107770392444,
|
|
"loss": 5.6073,
|
|
"mean_token_accuracy": 0.17818948179483413,
|
|
"num_tokens": 6103435.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.642114448547363,
|
|
"epoch": 0.2564841498559078,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499709036684407,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.17127547413110733,
|
|
"num_tokens": 6114531.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.554770469665527,
|
|
"epoch": 0.25696445725264166,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997072911124932,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.17987904697656631,
|
|
"num_tokens": 6126110.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.676206350326538,
|
|
"epoch": 0.2574447646493756,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997055403235432,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.17020486444234847,
|
|
"num_tokens": 6137114.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.550066661834717,
|
|
"epoch": 0.2579250720461095,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997037843175978,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.17681319117546082,
|
|
"num_tokens": 6148696.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.599713706970215,
|
|
"epoch": 0.2584053794428434,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997020230946978,
|
|
"loss": 5.5767,
|
|
"mean_token_accuracy": 0.17681550830602646,
|
|
"num_tokens": 6160235.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.646247243881225,
|
|
"epoch": 0.25888568683957736,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997002566548841,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.17518645226955415,
|
|
"num_tokens": 6172031.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.4375087261199955,
|
|
"epoch": 0.25936599423631124,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996984849981976,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.19105923920869827,
|
|
"num_tokens": 6183547.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.61473822593689,
|
|
"epoch": 0.2598463016330452,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996967081246794,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.16578203439712524,
|
|
"num_tokens": 6194768.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.672692441940308,
|
|
"epoch": 0.26032660902977905,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996949260343711,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.17012662142515184,
|
|
"num_tokens": 6206099.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.580655574798584,
|
|
"epoch": 0.260806916426513,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996931387273137,
|
|
"loss": 5.6254,
|
|
"mean_token_accuracy": 0.17450093030929564,
|
|
"num_tokens": 6217530.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.68199577331543,
|
|
"epoch": 0.2612872238232469,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996913462035487,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.1745712473988533,
|
|
"num_tokens": 6228564.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.55266432762146,
|
|
"epoch": 0.2617675312199808,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499689548463118,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.17716386169195175,
|
|
"num_tokens": 6239945.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.609622240066528,
|
|
"epoch": 0.2622478386167147,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996877455060631,
|
|
"loss": 5.6334,
|
|
"mean_token_accuracy": 0.16969335377216338,
|
|
"num_tokens": 6251829.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.702735137939453,
|
|
"epoch": 0.2627281460134486,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996859373324259,
|
|
"loss": 5.7343,
|
|
"mean_token_accuracy": 0.15780047476291656,
|
|
"num_tokens": 6264823.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.595852184295654,
|
|
"epoch": 0.2632084534101825,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996841239422485,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.18117975145578386,
|
|
"num_tokens": 6276247.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.445358562469482,
|
|
"epoch": 0.26368876080691644,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996823053355729,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.17686043679714203,
|
|
"num_tokens": 6287593.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.711119318008423,
|
|
"epoch": 0.2641690682036503,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996804815124413,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.17098784446716309,
|
|
"num_tokens": 6299918.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.539738941192627,
|
|
"epoch": 0.26464937560038426,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996786524728962,
|
|
"loss": 5.53,
|
|
"mean_token_accuracy": 0.18036444634199142,
|
|
"num_tokens": 6311147.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.438918256759644,
|
|
"epoch": 0.26512968299711814,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996768182169797,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.18227623850107194,
|
|
"num_tokens": 6323239.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.685362672805786,
|
|
"epoch": 0.2656099903938521,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996749787447349,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.17261019647121428,
|
|
"num_tokens": 6334625.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.552652215957641,
|
|
"epoch": 0.26609029779058596,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499673134056204,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.17367497086524963,
|
|
"num_tokens": 6346068.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.559088802337646,
|
|
"epoch": 0.2665706051873199,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996712841514303,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.17600637525320054,
|
|
"num_tokens": 6357097.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.6992058753967285,
|
|
"epoch": 0.2670509125840538,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996694290304563,
|
|
"loss": 5.6307,
|
|
"mean_token_accuracy": 0.16546071022748948,
|
|
"num_tokens": 6367481.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.448730230331421,
|
|
"epoch": 0.2675312199807877,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996675686933255,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.1823368027806282,
|
|
"num_tokens": 6378873.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.654207944869995,
|
|
"epoch": 0.2680115273775216,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996657031400807,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.1771922379732132,
|
|
"num_tokens": 6390651.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.500947189331055,
|
|
"epoch": 0.26849183477425553,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996638323707655,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.1842489555478096,
|
|
"num_tokens": 6401631.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.470289945602417,
|
|
"epoch": 0.2689721421709894,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996619563854232,
|
|
"loss": 5.535,
|
|
"mean_token_accuracy": 0.18415504842996597,
|
|
"num_tokens": 6413875.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.6424308776855465,
|
|
"epoch": 0.26945244956772335,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996600751840974,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.1733962208032608,
|
|
"num_tokens": 6425764.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.528824186325073,
|
|
"epoch": 0.26993275696445723,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996581887668317,
|
|
"loss": 5.4793,
|
|
"mean_token_accuracy": 0.18224212825298308,
|
|
"num_tokens": 6437911.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.552932071685791,
|
|
"epoch": 0.27041306436119117,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00049965629713367,
|
|
"loss": 5.5054,
|
|
"mean_token_accuracy": 0.1778433382511139,
|
|
"num_tokens": 6449942.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.569303369522094,
|
|
"epoch": 0.27089337175792505,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996544002846561,
|
|
"loss": 5.6106,
|
|
"mean_token_accuracy": 0.17501538544893264,
|
|
"num_tokens": 6461729.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.655416488647461,
|
|
"epoch": 0.271373679154659,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996524982198343,
|
|
"loss": 5.5841,
|
|
"mean_token_accuracy": 0.1763883948326111,
|
|
"num_tokens": 6472046.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.587695741653443,
|
|
"epoch": 0.27185398655139287,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996505909392485,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.1729704797267914,
|
|
"num_tokens": 6483308.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.493324041366577,
|
|
"epoch": 0.2723342939481268,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996486784429429,
|
|
"loss": 5.4366,
|
|
"mean_token_accuracy": 0.18380706012248993,
|
|
"num_tokens": 6495093.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.566275644302368,
|
|
"epoch": 0.2728146013448607,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996467607309622,
|
|
"loss": 5.5283,
|
|
"mean_token_accuracy": 0.17835645377635956,
|
|
"num_tokens": 6505933.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.546031045913696,
|
|
"epoch": 0.2732949087415946,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996448378033507,
|
|
"loss": 5.5809,
|
|
"mean_token_accuracy": 0.1711354523897171,
|
|
"num_tokens": 6517280.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.596413040161133,
|
|
"epoch": 0.2737752161383285,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996429096601532,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.17175697535276413,
|
|
"num_tokens": 6528980.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.606202507019043,
|
|
"epoch": 0.27425552353506244,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996409763014144,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.17576562166213988,
|
|
"num_tokens": 6540670.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.565543270111084,
|
|
"epoch": 0.2747358309317964,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996390377271791,
|
|
"loss": 5.5891,
|
|
"mean_token_accuracy": 0.17818703204393388,
|
|
"num_tokens": 6551302.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.556024217605591,
|
|
"epoch": 0.27521613832853026,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996370939374924,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.17564931213855745,
|
|
"num_tokens": 6563177.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.746175384521484,
|
|
"epoch": 0.2756964457252642,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004996351449323994,
|
|
"loss": 5.6374,
|
|
"mean_token_accuracy": 0.17682098150253295,
|
|
"num_tokens": 6573323.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.57629361152649,
|
|
"epoch": 0.2761767531219981,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996331907119455,
|
|
"loss": 5.5811,
|
|
"mean_token_accuracy": 0.1701768457889557,
|
|
"num_tokens": 6585382.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.482797908782959,
|
|
"epoch": 0.276657060518732,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996312312761758,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.18398744612932205,
|
|
"num_tokens": 6596629.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.607573366165161,
|
|
"epoch": 0.2771373679154659,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499629266625136,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.17843256890773773,
|
|
"num_tokens": 6608408.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.635081243515015,
|
|
"epoch": 0.27761767531219983,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996272967588715,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.170115564763546,
|
|
"num_tokens": 6619375.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.6446939468383786,
|
|
"epoch": 0.2780979827089337,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004996253216774283,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.17216423898935318,
|
|
"num_tokens": 6631317.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.616905879974365,
|
|
"epoch": 0.27857829010566765,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996233413808521,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.1780126839876175,
|
|
"num_tokens": 6642009.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.571500539779663,
|
|
"epoch": 0.27905859750240153,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004996213558691889,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.16875739693641661,
|
|
"num_tokens": 6654713.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.588582563400268,
|
|
"epoch": 0.27953890489913547,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996193651424848,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.1764470860362053,
|
|
"num_tokens": 6667157.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.619789171218872,
|
|
"epoch": 0.28001921229586935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499617369200786,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.18174609988927842,
|
|
"num_tokens": 6679573.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.636269855499267,
|
|
"epoch": 0.2804995196926033,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996153680441389,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.1688329443335533,
|
|
"num_tokens": 6691768.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.621795511245727,
|
|
"epoch": 0.28097982708933716,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00049961336167259,
|
|
"loss": 5.5884,
|
|
"mean_token_accuracy": 0.1696314588189125,
|
|
"num_tokens": 6701964.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.6255316734313965,
|
|
"epoch": 0.2814601344860711,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996113500861857,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.17163842022418976,
|
|
"num_tokens": 6713506.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.621021032333374,
|
|
"epoch": 0.281940441882805,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996093332849729,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.16955934315919877,
|
|
"num_tokens": 6724616.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.560334825515747,
|
|
"epoch": 0.2824207492795389,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996073112689983,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.172370445728302,
|
|
"num_tokens": 6735054.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.659707832336426,
|
|
"epoch": 0.2829010566762728,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996052840383088,
|
|
"loss": 5.6403,
|
|
"mean_token_accuracy": 0.17384059429168702,
|
|
"num_tokens": 6746756.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.604048585891723,
|
|
"epoch": 0.28338136407300674,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996032515929516,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.17557519674301147,
|
|
"num_tokens": 6759566.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.573195457458496,
|
|
"epoch": 0.2838616714697406,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996012139329738,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.17383324801921846,
|
|
"num_tokens": 6771375.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.6653008460998535,
|
|
"epoch": 0.28434197886647455,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995991710584228,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.1679643452167511,
|
|
"num_tokens": 6783252.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.582359266281128,
|
|
"epoch": 0.28482228626320844,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004995971229693459,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.17220803648233413,
|
|
"num_tokens": 6795525.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.596712255477906,
|
|
"epoch": 0.28530259365994237,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995950696657909,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.17710976898670197,
|
|
"num_tokens": 6807212.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.573274946212768,
|
|
"epoch": 0.28578290105667625,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995930111478051,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.1754768967628479,
|
|
"num_tokens": 6819367.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.596656942367554,
|
|
"epoch": 0.2862632084534102,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995909474154365,
|
|
"loss": 5.5753,
|
|
"mean_token_accuracy": 0.17517277002334594,
|
|
"num_tokens": 6830405.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.562333059310913,
|
|
"epoch": 0.28674351585014407,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995888784687331,
|
|
"loss": 5.5417,
|
|
"mean_token_accuracy": 0.17887548506259918,
|
|
"num_tokens": 6841479.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.479148101806641,
|
|
"epoch": 0.287223823246878,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995868043077428,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.17242609709501266,
|
|
"num_tokens": 6851585.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.606111669540406,
|
|
"epoch": 0.2877041306436119,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995847249325137,
|
|
"loss": 5.5558,
|
|
"mean_token_accuracy": 0.17751109302043916,
|
|
"num_tokens": 6863176.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.632681655883789,
|
|
"epoch": 0.2881844380403458,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995826403430942,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.1762181207537651,
|
|
"num_tokens": 6874021.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2881844380403458,
|
|
"eval_entropy": 5.429550058140748,
|
|
"eval_loss": 5.586162090301514,
|
|
"eval_mean_token_accuracy": 0.18191353848448313,
|
|
"eval_num_tokens": 6874021.0,
|
|
"eval_runtime": 26.795,
|
|
"eval_samples_per_second": 1224.667,
|
|
"eval_steps_per_second": 153.088,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.600363540649414,
|
|
"epoch": 0.2886647454370797,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995805505395328,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.17339786887168884,
|
|
"num_tokens": 6884999.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.600484132766724,
|
|
"epoch": 0.28914505283381364,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004995784555218778,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.17429939657449722,
|
|
"num_tokens": 6897021.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.511123895645142,
|
|
"epoch": 0.2896253602305475,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995763552901779,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.17659427374601364,
|
|
"num_tokens": 6908320.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.652883100509643,
|
|
"epoch": 0.29010566762728146,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995742498444818,
|
|
"loss": 5.5371,
|
|
"mean_token_accuracy": 0.18115892112255097,
|
|
"num_tokens": 6919957.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.585669946670532,
|
|
"epoch": 0.2905859750240154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995721391848387,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.17262517660856247,
|
|
"num_tokens": 6930531.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.608732128143311,
|
|
"epoch": 0.2910662824207493,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995700233112972,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.17478831112384796,
|
|
"num_tokens": 6942556.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.606024694442749,
|
|
"epoch": 0.2915465898174832,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995679022239066,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.1781206950545311,
|
|
"num_tokens": 6954410.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.55260009765625,
|
|
"epoch": 0.2920268972142171,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004995657759227162,
|
|
"loss": 5.5944,
|
|
"mean_token_accuracy": 0.17391981631517411,
|
|
"num_tokens": 6964970.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.566141557693482,
|
|
"epoch": 0.29250720461095103,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995636444077751,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.18189731985330582,
|
|
"num_tokens": 6976016.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.5221411228179935,
|
|
"epoch": 0.2929875120076849,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995615076791333,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.18297768980264664,
|
|
"num_tokens": 6987199.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.531902885437011,
|
|
"epoch": 0.29346781940441885,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995593657368399,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.18220969140529633,
|
|
"num_tokens": 6999174.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.579030323028564,
|
|
"epoch": 0.29394812680115273,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499557218580945,
|
|
"loss": 5.6057,
|
|
"mean_token_accuracy": 0.1742488220334053,
|
|
"num_tokens": 7012148.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.51430869102478,
|
|
"epoch": 0.29442843419788667,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995550662114981,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.18066531866788865,
|
|
"num_tokens": 7023238.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.57521915435791,
|
|
"epoch": 0.29490874159462055,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995529086285495,
|
|
"loss": 5.563,
|
|
"mean_token_accuracy": 0.17579518109560013,
|
|
"num_tokens": 7034944.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.581096458435058,
|
|
"epoch": 0.2953890489913545,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499550745832149,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.18247623443603517,
|
|
"num_tokens": 7046880.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.522906064987183,
|
|
"epoch": 0.29586935638808837,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995485778223471,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.17416971772909165,
|
|
"num_tokens": 7057678.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.472863101959229,
|
|
"epoch": 0.2963496637848223,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995464045991939,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.18598580062389375,
|
|
"num_tokens": 7068336.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.528228807449341,
|
|
"epoch": 0.2968299711815562,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00049954422616274,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.1714586853981018,
|
|
"num_tokens": 7080341.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.669358205795288,
|
|
"epoch": 0.2973102785782901,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995420425130359,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.1685379832983017,
|
|
"num_tokens": 7090618.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.528180360794067,
|
|
"epoch": 0.297790585975024,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995398536501324,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.18209979832172393,
|
|
"num_tokens": 7101843.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.567078542709351,
|
|
"epoch": 0.29827089337175794,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995376595740801,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.17826035469770432,
|
|
"num_tokens": 7112014.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.610919427871704,
|
|
"epoch": 0.2987512007684918,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995354602849302,
|
|
"loss": 5.5982,
|
|
"mean_token_accuracy": 0.1687198132276535,
|
|
"num_tokens": 7123860.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.596198320388794,
|
|
"epoch": 0.29923150816522576,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995332557827337,
|
|
"loss": 5.5723,
|
|
"mean_token_accuracy": 0.17329292595386506,
|
|
"num_tokens": 7135901.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.565270042419433,
|
|
"epoch": 0.29971181556195964,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004995310460675416,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.18447502851486205,
|
|
"num_tokens": 7148743.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.604452514648438,
|
|
"epoch": 0.3001921229586936,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995288311394053,
|
|
"loss": 5.5654,
|
|
"mean_token_accuracy": 0.1805852472782135,
|
|
"num_tokens": 7160731.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.581399774551391,
|
|
"epoch": 0.30067243035542746,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995266109983764,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.1775326207280159,
|
|
"num_tokens": 7172861.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.539625930786133,
|
|
"epoch": 0.3011527377521614,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995243856445062,
|
|
"loss": 5.5141,
|
|
"mean_token_accuracy": 0.17208293378353118,
|
|
"num_tokens": 7183954.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.480448532104492,
|
|
"epoch": 0.3016330451488953,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995221550778466,
|
|
"loss": 5.4912,
|
|
"mean_token_accuracy": 0.1776828110218048,
|
|
"num_tokens": 7195466.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.590827178955078,
|
|
"epoch": 0.3021133525456292,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995199192984491,
|
|
"loss": 5.4863,
|
|
"mean_token_accuracy": 0.18054292649030684,
|
|
"num_tokens": 7207173.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.608777952194214,
|
|
"epoch": 0.3025936599423631,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995176783063657,
|
|
"loss": 5.626,
|
|
"mean_token_accuracy": 0.17653027623891832,
|
|
"num_tokens": 7220095.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.560349750518799,
|
|
"epoch": 0.30307396733909703,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995154321016487,
|
|
"loss": 5.5407,
|
|
"mean_token_accuracy": 0.18061470240354538,
|
|
"num_tokens": 7230664.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.547581672668457,
|
|
"epoch": 0.3035542747358309,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995131806843499,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.1806902602314949,
|
|
"num_tokens": 7241278.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.488682126998901,
|
|
"epoch": 0.30403458213256485,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004995109240545218,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.17149197161197663,
|
|
"num_tokens": 7252999.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.577103805541992,
|
|
"epoch": 0.3045148895292987,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995086622122167,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.1804819107055664,
|
|
"num_tokens": 7263949.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.570094347000122,
|
|
"epoch": 0.30499519692603266,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995063951574871,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.18004708141088485,
|
|
"num_tokens": 7275467.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.5571205615997314,
|
|
"epoch": 0.30547550432276654,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004995041228903856,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.19042035788297654,
|
|
"num_tokens": 7285534.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.64586911201477,
|
|
"epoch": 0.3059558117195005,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499501845410965,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.17913737446069716,
|
|
"num_tokens": 7297252.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.538606977462768,
|
|
"epoch": 0.30643611911623436,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994995627192781,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.18582532107830046,
|
|
"num_tokens": 7308492.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.50892915725708,
|
|
"epoch": 0.3069164265129683,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994972748153781,
|
|
"loss": 5.5244,
|
|
"mean_token_accuracy": 0.17597380876541138,
|
|
"num_tokens": 7319703.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.590646076202392,
|
|
"epoch": 0.30739673390970224,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499494981699318,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.18500274270772935,
|
|
"num_tokens": 7331022.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.519442319869995,
|
|
"epoch": 0.3078770413064361,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499492683371151,
|
|
"loss": 5.5315,
|
|
"mean_token_accuracy": 0.17760216891765596,
|
|
"num_tokens": 7342977.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.630467796325684,
|
|
"epoch": 0.30835734870317005,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994903798309306,
|
|
"loss": 5.513,
|
|
"mean_token_accuracy": 0.17566098272800446,
|
|
"num_tokens": 7353227.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.5716699123382565,
|
|
"epoch": 0.30883765609990393,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994880710787102,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.16306095123291015,
|
|
"num_tokens": 7364165.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.500264453887939,
|
|
"epoch": 0.30931796349663787,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994857571145432,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.17793892621994017,
|
|
"num_tokens": 7374800.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.477330923080444,
|
|
"epoch": 0.30979827089337175,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994834379384837,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.18106601238250733,
|
|
"num_tokens": 7386360.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.546009302139282,
|
|
"epoch": 0.3102785782901057,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004994811135505851,
|
|
"loss": 5.4895,
|
|
"mean_token_accuracy": 0.1845191791653633,
|
|
"num_tokens": 7397066.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.59111065864563,
|
|
"epoch": 0.31075888568683957,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004994787839509018,
|
|
"loss": 5.5778,
|
|
"mean_token_accuracy": 0.1716102570295334,
|
|
"num_tokens": 7408349.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.602340984344482,
|
|
"epoch": 0.3112391930835735,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994764491394876,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.1701334610581398,
|
|
"num_tokens": 7420343.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.617624425888062,
|
|
"epoch": 0.3117195004803074,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994741091163969,
|
|
"loss": 5.5164,
|
|
"mean_token_accuracy": 0.17915263921022415,
|
|
"num_tokens": 7431683.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.452288436889648,
|
|
"epoch": 0.3121998078770413,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499471763881684,
|
|
"loss": 5.4223,
|
|
"mean_token_accuracy": 0.1848103031516075,
|
|
"num_tokens": 7443327.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.590960597991943,
|
|
"epoch": 0.3126801152737752,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994694134354031,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.17861520498991013,
|
|
"num_tokens": 7454002.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.4782013416290285,
|
|
"epoch": 0.31316042267050914,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000499467057777609,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.17802254259586334,
|
|
"num_tokens": 7464074.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.438896894454956,
|
|
"epoch": 0.313640730067243,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994646969083565,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.18714377731084825,
|
|
"num_tokens": 7475543.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.571201324462891,
|
|
"epoch": 0.31412103746397696,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994623308277002,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.17577572166919708,
|
|
"num_tokens": 7486818.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.56628189086914,
|
|
"epoch": 0.31460134486071084,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000499459959535695,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.1765957310795784,
|
|
"num_tokens": 7499046.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.547894525527954,
|
|
"epoch": 0.3150816522574448,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004994575830323962,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.17400237619876863,
|
|
"num_tokens": 7509853.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.464238691329956,
|
|
"epoch": 0.31556195965417866,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994552013178586,
|
|
"loss": 5.3644,
|
|
"mean_token_accuracy": 0.18130476027727127,
|
|
"num_tokens": 7521091.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.531323957443237,
|
|
"epoch": 0.3160422670509126,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000499452814392138,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.1937162309885025,
|
|
"num_tokens": 7531317.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.600437831878662,
|
|
"epoch": 0.3165225744476465,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994504222552894,
|
|
"loss": 5.618,
|
|
"mean_token_accuracy": 0.1745721884071827,
|
|
"num_tokens": 7542822.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.659745740890503,
|
|
"epoch": 0.3170028818443804,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004994480249073684,
|
|
"loss": 5.5448,
|
|
"mean_token_accuracy": 0.178367081284523,
|
|
"num_tokens": 7552434.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.456921482086182,
|
|
"epoch": 0.3174831892411143,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994456223484308,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.18477557152509688,
|
|
"num_tokens": 7563895.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.423321485519409,
|
|
"epoch": 0.31796349663784823,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994432145785323,
|
|
"loss": 5.4591,
|
|
"mean_token_accuracy": 0.1826289027929306,
|
|
"num_tokens": 7575391.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.624456739425659,
|
|
"epoch": 0.3184438040345821,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004994408015977288,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.1818215385079384,
|
|
"num_tokens": 7587119.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.569375514984131,
|
|
"epoch": 0.31892411143131605,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004994383834060764,
|
|
"loss": 5.5772,
|
|
"mean_token_accuracy": 0.1734785705804825,
|
|
"num_tokens": 7598615.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.572255849838257,
|
|
"epoch": 0.31940441882804993,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994359600036311,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.1831957072019577,
|
|
"num_tokens": 7610159.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.59397931098938,
|
|
"epoch": 0.31988472622478387,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004994335313904493,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.1816868230700493,
|
|
"num_tokens": 7620922.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.485593795776367,
|
|
"epoch": 0.32036503362151775,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994310975665873,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.18188621252775192,
|
|
"num_tokens": 7632343.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.654634952545166,
|
|
"epoch": 0.3208453410182517,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994286585321017,
|
|
"loss": 5.618,
|
|
"mean_token_accuracy": 0.16822532564401627,
|
|
"num_tokens": 7644748.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.619227313995362,
|
|
"epoch": 0.32132564841498557,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000499426214287049,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.18332976400852202,
|
|
"num_tokens": 7655449.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.517597341537476,
|
|
"epoch": 0.3218059558117195,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994237648314862,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.18118724673986436,
|
|
"num_tokens": 7665623.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.454781436920166,
|
|
"epoch": 0.3222862632084534,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994213101654697,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.18383088260889052,
|
|
"num_tokens": 7676860.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.604706859588623,
|
|
"epoch": 0.3227665706051873,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499418850289057,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.175212861597538,
|
|
"num_tokens": 7687778.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.568313789367676,
|
|
"epoch": 0.32324687800192126,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994163852023048,
|
|
"loss": 5.5257,
|
|
"mean_token_accuracy": 0.17771939039230347,
|
|
"num_tokens": 7699154.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.516863393783569,
|
|
"epoch": 0.32372718539865514,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994139149052706,
|
|
"loss": 5.5341,
|
|
"mean_token_accuracy": 0.18178620636463166,
|
|
"num_tokens": 7711010.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.64791841506958,
|
|
"epoch": 0.3242074927953891,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994114393980117,
|
|
"loss": 5.5793,
|
|
"mean_token_accuracy": 0.1766408860683441,
|
|
"num_tokens": 7721969.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.5866681098937985,
|
|
"epoch": 0.32468780019212296,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.18192908465862273,
|
|
"num_tokens": 7733762.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.530384969711304,
|
|
"epoch": 0.3251681075888569,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994064727530496,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.18091918230056764,
|
|
"num_tokens": 7744614.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.517992448806763,
|
|
"epoch": 0.3256484149855908,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994039816154618,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.18558885753154755,
|
|
"num_tokens": 7755799.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.447378921508789,
|
|
"epoch": 0.3261287223823247,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00049940148526788,
|
|
"loss": 5.5054,
|
|
"mean_token_accuracy": 0.1780296966433525,
|
|
"num_tokens": 7768140.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.567817878723145,
|
|
"epoch": 0.3266090297790586,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004993989837103618,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.1833523318171501,
|
|
"num_tokens": 7778494.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.629387664794922,
|
|
"epoch": 0.3270893371757925,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993964769429657,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.18286123126745224,
|
|
"num_tokens": 7789234.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.544597578048706,
|
|
"epoch": 0.3275696445725264,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993939649657498,
|
|
"loss": 5.5495,
|
|
"mean_token_accuracy": 0.18183192014694213,
|
|
"num_tokens": 7800602.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.471805143356323,
|
|
"epoch": 0.32804995196926034,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004993914477787721,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.1888096049427986,
|
|
"num_tokens": 7812803.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.71797547340393,
|
|
"epoch": 0.3285302593659942,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993889253820915,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.16442025750875472,
|
|
"num_tokens": 7825432.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.589930582046509,
|
|
"epoch": 0.32901056676272816,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993863977757663,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.18198246657848358,
|
|
"num_tokens": 7837258.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.421857833862305,
|
|
"epoch": 0.32949087415946204,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993838649598552,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.18571746796369554,
|
|
"num_tokens": 7847573.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.561519813537598,
|
|
"epoch": 0.329971181556196,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993813269344171,
|
|
"loss": 5.5265,
|
|
"mean_token_accuracy": 0.17412028163671495,
|
|
"num_tokens": 7857957.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.541936731338501,
|
|
"epoch": 0.33045148895292986,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993787836995108,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.19084869623184203,
|
|
"num_tokens": 7867996.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.47579345703125,
|
|
"epoch": 0.3309317963496638,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993762352551954,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.17615825533866883,
|
|
"num_tokens": 7879245.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.59015417098999,
|
|
"epoch": 0.3314121037463977,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993736816015301,
|
|
"loss": 5.5797,
|
|
"mean_token_accuracy": 0.16978901773691177,
|
|
"num_tokens": 7891186.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.637670612335205,
|
|
"epoch": 0.3318924111431316,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993711227385742,
|
|
"loss": 5.5961,
|
|
"mean_token_accuracy": 0.18024379312992095,
|
|
"num_tokens": 7902231.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.589706659317017,
|
|
"epoch": 0.3323727185398655,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993685586663871,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.1754046931862831,
|
|
"num_tokens": 7913364.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.754637956619263,
|
|
"epoch": 0.33285302593659943,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004993659893850281,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.16411951035261155,
|
|
"num_tokens": 7925217.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.534233140945434,
|
|
"epoch": 0.3333333333333333,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993634148945573,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.17274767756462098,
|
|
"num_tokens": 7937636.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.602685928344727,
|
|
"epoch": 0.33381364073006725,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993608351950341,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.1731838569045067,
|
|
"num_tokens": 7948958.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.604113912582397,
|
|
"epoch": 0.33429394812680113,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993582502865185,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.18086513131856918,
|
|
"num_tokens": 7960013.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.530916404724121,
|
|
"epoch": 0.33477425552353507,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993556601690706,
|
|
"loss": 5.5724,
|
|
"mean_token_accuracy": 0.17360547482967376,
|
|
"num_tokens": 7971041.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.620208835601806,
|
|
"epoch": 0.33525456292026895,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993530648427505,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.17021283507347107,
|
|
"num_tokens": 7982752.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.556317329406738,
|
|
"epoch": 0.3357348703170029,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993504643076184,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.18065172135829927,
|
|
"num_tokens": 7993681.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.515970182418823,
|
|
"epoch": 0.33621517771373677,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993478585637347,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.17996718138456344,
|
|
"num_tokens": 8004727.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.55832986831665,
|
|
"epoch": 0.3366954851104707,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004993452476111599,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.18072617799043655,
|
|
"num_tokens": 8015423.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.524600887298584,
|
|
"epoch": 0.3371757925072046,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993426314499546,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.18434552550315858,
|
|
"num_tokens": 8027911.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.552202653884888,
|
|
"epoch": 0.3376560999039385,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993400100801796,
|
|
"loss": 5.5079,
|
|
"mean_token_accuracy": 0.18370311260223388,
|
|
"num_tokens": 8038831.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.449936866760254,
|
|
"epoch": 0.3381364073006724,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004993373835018956,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.1887590005993843,
|
|
"num_tokens": 8049906.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.406693935394287,
|
|
"epoch": 0.33861671469740634,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993347517151638,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.1799078568816185,
|
|
"num_tokens": 8061158.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.581608772277832,
|
|
"epoch": 0.3390970220941403,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004993321147200452,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.17504534125328064,
|
|
"num_tokens": 8071958.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.508309268951416,
|
|
"epoch": 0.33957732949087416,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499329472516601,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.17321627140045165,
|
|
"num_tokens": 8084068.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.460131883621216,
|
|
"epoch": 0.3400576368876081,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993268251048925,
|
|
"loss": 5.3674,
|
|
"mean_token_accuracy": 0.19298069328069686,
|
|
"num_tokens": 8096132.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.5027237892150875,
|
|
"epoch": 0.340537944284342,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993241724849814,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.18277010321617126,
|
|
"num_tokens": 8107327.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.559181499481201,
|
|
"epoch": 0.3410182516810759,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499321514656929,
|
|
"loss": 5.508,
|
|
"mean_token_accuracy": 0.17941301316022873,
|
|
"num_tokens": 8118584.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.612706422805786,
|
|
"epoch": 0.3414985590778098,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993188516207972,
|
|
"loss": 5.5674,
|
|
"mean_token_accuracy": 0.17390409708023072,
|
|
"num_tokens": 8130081.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.565273189544678,
|
|
"epoch": 0.34197886647454373,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993161833766478,
|
|
"loss": 5.5178,
|
|
"mean_token_accuracy": 0.17747482657432556,
|
|
"num_tokens": 8141463.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.589842128753662,
|
|
"epoch": 0.3424591738712776,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993135099245426,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.17925816029310226,
|
|
"num_tokens": 8153863.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.43801441192627,
|
|
"epoch": 0.34293948126801155,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004993108312645438,
|
|
"loss": 5.4883,
|
|
"mean_token_accuracy": 0.17569864243268968,
|
|
"num_tokens": 8165695.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.547050857543946,
|
|
"epoch": 0.34341978866474543,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004993081473967135,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.18033247739076613,
|
|
"num_tokens": 8176456.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.595006895065308,
|
|
"epoch": 0.34390009606147937,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993054583211143,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.1829513505101204,
|
|
"num_tokens": 8189050.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.503920698165894,
|
|
"epoch": 0.34438040345821325,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993027640378081,
|
|
"loss": 5.4349,
|
|
"mean_token_accuracy": 0.18146423995494843,
|
|
"num_tokens": 8200011.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.52493462562561,
|
|
"epoch": 0.3448607108549472,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000499300064546858,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.18384402990341187,
|
|
"num_tokens": 8211770.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.513854122161865,
|
|
"epoch": 0.34534101825168106,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004992973598483264,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.17984576523303986,
|
|
"num_tokens": 8223582.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.641219758987427,
|
|
"epoch": 0.345821325648415,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000499294649942276,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.17455415278673173,
|
|
"num_tokens": 8234336.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.620729064941406,
|
|
"epoch": 0.3463016330451489,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992919348287699,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.1798400104045868,
|
|
"num_tokens": 8244605.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.573699188232422,
|
|
"epoch": 0.3467819404418828,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992892145078711,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.17481158524751664,
|
|
"num_tokens": 8255876.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.498121738433838,
|
|
"epoch": 0.3472622478386167,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992864889796427,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.18113334625959396,
|
|
"num_tokens": 8266602.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.561939430236817,
|
|
"epoch": 0.34774255523535064,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992837582441481,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.1779914915561676,
|
|
"num_tokens": 8279804.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.57861852645874,
|
|
"epoch": 0.3482228626320845,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004992810223014506,
|
|
"loss": 5.5446,
|
|
"mean_token_accuracy": 0.179275344312191,
|
|
"num_tokens": 8291020.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.528412961959839,
|
|
"epoch": 0.34870317002881845,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004992782811516137,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.18148062080144883,
|
|
"num_tokens": 8302192.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.5225166320800785,
|
|
"epoch": 0.34918347742555234,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992755347947011,
|
|
"loss": 5.4512,
|
|
"mean_token_accuracy": 0.17893909066915512,
|
|
"num_tokens": 8313649.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.442665147781372,
|
|
"epoch": 0.34966378482228627,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992727832307766,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.18404687196016312,
|
|
"num_tokens": 8324694.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.660800504684448,
|
|
"epoch": 0.35014409221902015,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992700264599039,
|
|
"loss": 5.6103,
|
|
"mean_token_accuracy": 0.16942178905010224,
|
|
"num_tokens": 8336517.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.563683032989502,
|
|
"epoch": 0.3506243996157541,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992672644821473,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.17284948676824569,
|
|
"num_tokens": 8349001.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.5911766529083256,
|
|
"epoch": 0.35110470701248797,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992644972975707,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.1816067561507225,
|
|
"num_tokens": 8361230.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.457846641540527,
|
|
"epoch": 0.3515850144092219,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992617249062383,
|
|
"loss": 5.4142,
|
|
"mean_token_accuracy": 0.189373779296875,
|
|
"num_tokens": 8372159.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.508694648742676,
|
|
"epoch": 0.3520653218059558,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992589473082147,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.18024334609508513,
|
|
"num_tokens": 8383228.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.553424453735351,
|
|
"epoch": 0.3525456292026897,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992561645035641,
|
|
"loss": 5.4796,
|
|
"mean_token_accuracy": 0.17851777076721193,
|
|
"num_tokens": 8394582.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.522850894927979,
|
|
"epoch": 0.3530259365994236,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992533764923515,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.17730434238910675,
|
|
"num_tokens": 8406784.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.531966829299927,
|
|
"epoch": 0.35350624399615754,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992505832746412,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.18808674216270446,
|
|
"num_tokens": 8418405.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.487172174453735,
|
|
"epoch": 0.3539865513928914,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004992477848504983,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.1825198143720627,
|
|
"num_tokens": 8430432.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.582427597045898,
|
|
"epoch": 0.35446685878962536,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992449812199877,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.1771538183093071,
|
|
"num_tokens": 8442423.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.593672513961792,
|
|
"epoch": 0.3549471661863593,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992421723831745,
|
|
"loss": 5.5859,
|
|
"mean_token_accuracy": 0.17417273074388503,
|
|
"num_tokens": 8454951.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.4941259860992435,
|
|
"epoch": 0.3554274735830932,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992393583401239,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.18477054536342621,
|
|
"num_tokens": 8467758.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.539112949371338,
|
|
"epoch": 0.3559077809798271,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992365390909014,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.18091605752706527,
|
|
"num_tokens": 8479728.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.564965009689331,
|
|
"epoch": 0.356388088376561,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992337146355721,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.17358343452215194,
|
|
"num_tokens": 8492099.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.595949316024781,
|
|
"epoch": 0.35686839577329493,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992308849742019,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.16807685792446136,
|
|
"num_tokens": 8504657.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.5478321552276615,
|
|
"epoch": 0.3573487031700288,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004992280501068563,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.18297590613365172,
|
|
"num_tokens": 8514728.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.545225334167481,
|
|
"epoch": 0.35782901056676275,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004992252100336012,
|
|
"loss": 5.5894,
|
|
"mean_token_accuracy": 0.17881780564785005,
|
|
"num_tokens": 8525588.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.582157373428345,
|
|
"epoch": 0.35830931796349663,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004992223647545027,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.1758353590965271,
|
|
"num_tokens": 8537468.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.611612844467163,
|
|
"epoch": 0.35878962536023057,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004992195142696266,
|
|
"loss": 5.4777,
|
|
"mean_token_accuracy": 0.18256427645683287,
|
|
"num_tokens": 8548598.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.381786298751831,
|
|
"epoch": 0.35926993275696445,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004992166585790391,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.18911873996257783,
|
|
"num_tokens": 8560301.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.504955625534057,
|
|
"epoch": 0.3597502401536984,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992137976828067,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.18709949553012847,
|
|
"num_tokens": 8571186.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.537512016296387,
|
|
"epoch": 0.36023054755043227,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992109315809955,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.18778423219919205,
|
|
"num_tokens": 8580725.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.505564737319946,
|
|
"epoch": 0.3607108549471662,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004992080602736725,
|
|
"loss": 5.5863,
|
|
"mean_token_accuracy": 0.17066614478826522,
|
|
"num_tokens": 8594598.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.655724573135376,
|
|
"epoch": 0.3611911623439001,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992051837609039,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.173820960521698,
|
|
"num_tokens": 8606733.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.638949203491211,
|
|
"epoch": 0.361671469740634,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992023020427568,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.17976907789707183,
|
|
"num_tokens": 8618863.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.412998104095459,
|
|
"epoch": 0.3621517771373679,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004991994151192979,
|
|
"loss": 5.3704,
|
|
"mean_token_accuracy": 0.18301213681697845,
|
|
"num_tokens": 8629270.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.524809217453003,
|
|
"epoch": 0.36263208453410184,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004991965229905943,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.18172184824943544,
|
|
"num_tokens": 8641363.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.6027158260345455,
|
|
"epoch": 0.3631123919308357,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991936256567133,
|
|
"loss": 5.5284,
|
|
"mean_token_accuracy": 0.1772402986884117,
|
|
"num_tokens": 8653233.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.559889030456543,
|
|
"epoch": 0.36359269932756966,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499190723117722,
|
|
"loss": 5.531,
|
|
"mean_token_accuracy": 0.17365886718034745,
|
|
"num_tokens": 8665192.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.660091257095337,
|
|
"epoch": 0.36407300672430354,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004991878153736877,
|
|
"loss": 5.6023,
|
|
"mean_token_accuracy": 0.1698717176914215,
|
|
"num_tokens": 8677669.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.450968647003174,
|
|
"epoch": 0.3645533141210375,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004991849024246781,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.18292109668254852,
|
|
"num_tokens": 8688002.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.467974901199341,
|
|
"epoch": 0.36503362151777136,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991819842707608,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.18255285322666168,
|
|
"num_tokens": 8698396.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.61320128440857,
|
|
"epoch": 0.3655139289145053,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004991790609120035,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.1790803998708725,
|
|
"num_tokens": 8711135.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.522697162628174,
|
|
"epoch": 0.3659942363112392,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000499176132348474,
|
|
"loss": 5.502,
|
|
"mean_token_accuracy": 0.18287073373794555,
|
|
"num_tokens": 8723707.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.55441312789917,
|
|
"epoch": 0.3664745437079731,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004991731985802405,
|
|
"loss": 5.4413,
|
|
"mean_token_accuracy": 0.1824128061532974,
|
|
"num_tokens": 8734193.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.530513715744019,
|
|
"epoch": 0.366954851104707,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004991702596073708,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.17552330493927001,
|
|
"num_tokens": 8745619.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.441557264328003,
|
|
"epoch": 0.36743515850144093,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004991673154299335,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.17917024344205856,
|
|
"num_tokens": 8757331.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.518283796310425,
|
|
"epoch": 0.3679154658981748,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991643660479967,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.18602569699287413,
|
|
"num_tokens": 8768840.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.497606897354126,
|
|
"epoch": 0.36839577329490875,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004991614114616289,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.18451025635004042,
|
|
"num_tokens": 8781214.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.6236552715301515,
|
|
"epoch": 0.3688760806916426,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991584516708988,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.18326642066240312,
|
|
"num_tokens": 8791645.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.601273775100708,
|
|
"epoch": 0.36935638808837656,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004991554866758751,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.17235216423869132,
|
|
"num_tokens": 8803286.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.527058744430542,
|
|
"epoch": 0.36983669548511044,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991525164766265,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.1800006926059723,
|
|
"num_tokens": 8814207.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.547538185119629,
|
|
"epoch": 0.3703170028818444,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991495410732222,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.17793162614107133,
|
|
"num_tokens": 8825540.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.639381837844849,
|
|
"epoch": 0.37079731027857826,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991465604657311,
|
|
"loss": 5.6115,
|
|
"mean_token_accuracy": 0.17024020701646805,
|
|
"num_tokens": 8838182.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.554458284378052,
|
|
"epoch": 0.3712776176753122,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004991435746542224,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.1847655951976776,
|
|
"num_tokens": 8850211.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.481682777404785,
|
|
"epoch": 0.37175792507204614,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004991405836387655,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.17258640825748445,
|
|
"num_tokens": 8862804.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.572489976882935,
|
|
"epoch": 0.37223823246878,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004991375874194298,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.17570974081754684,
|
|
"num_tokens": 8874112.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.535647583007813,
|
|
"epoch": 0.37271853986551395,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499134585996285,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.17717500925064086,
|
|
"num_tokens": 8885114.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.524375534057617,
|
|
"epoch": 0.37319884726224783,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004991315793694004,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.182638780772686,
|
|
"num_tokens": 8895555.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.464910840988159,
|
|
"epoch": 0.37367915465898177,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004991285675388463,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.19255885779857634,
|
|
"num_tokens": 8906073.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.498408555984497,
|
|
"epoch": 0.37415946205571565,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004991255505046922,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.17598401010036469,
|
|
"num_tokens": 8916587.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.6104248523712155,
|
|
"epoch": 0.3746397694524496,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004991225282670083,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.17930763512849807,
|
|
"num_tokens": 8927923.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.4726780414581295,
|
|
"epoch": 0.37512007684918347,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499119500825865,
|
|
"loss": 5.4913,
|
|
"mean_token_accuracy": 0.17923665493726731,
|
|
"num_tokens": 8939939.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.448997497558594,
|
|
"epoch": 0.3756003842459174,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004991164681813323,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.18578034192323684,
|
|
"num_tokens": 8951748.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.507438516616821,
|
|
"epoch": 0.3760806916426513,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991134303334807,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.19084998369216918,
|
|
"num_tokens": 8962922.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.407788991928101,
|
|
"epoch": 0.3765609990393852,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004991103872823807,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.1891293540596962,
|
|
"num_tokens": 8974013.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.453758192062378,
|
|
"epoch": 0.3770413064361191,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000499107339028103,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.17976069152355195,
|
|
"num_tokens": 8986032.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.578662443161011,
|
|
"epoch": 0.37752161383285304,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004991042855707184,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.17424533367156983,
|
|
"num_tokens": 8996889.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.480362176895142,
|
|
"epoch": 0.3780019212295869,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004991012269102977,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.18112412244081497,
|
|
"num_tokens": 9007594.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.408944797515869,
|
|
"epoch": 0.37848222862632086,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004990981630469119,
|
|
"loss": 5.4121,
|
|
"mean_token_accuracy": 0.1786349192261696,
|
|
"num_tokens": 9018097.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.516328239440918,
|
|
"epoch": 0.37896253602305474,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004990950939806323,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.17626695781946183,
|
|
"num_tokens": 9029554.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.577874946594238,
|
|
"epoch": 0.3794428434197887,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00049909201971153,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.17826686203479766,
|
|
"num_tokens": 9042518.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.496927785873413,
|
|
"epoch": 0.37992315081652256,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004990889402396763,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.1870885595679283,
|
|
"num_tokens": 9054524.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.5391520977020265,
|
|
"epoch": 0.3804034582132565,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004990858555651431,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.1826850652694702,
|
|
"num_tokens": 9065375.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.531686687469483,
|
|
"epoch": 0.3808837656099904,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990827656880015,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.18493682295084,
|
|
"num_tokens": 9076338.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.4945813655853275,
|
|
"epoch": 0.3813640730067243,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990796706083235,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.1815017580986023,
|
|
"num_tokens": 9088407.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.484382295608521,
|
|
"epoch": 0.3818443804034582,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004990765703261809,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.18176448941230774,
|
|
"num_tokens": 9099833.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.4244927883148195,
|
|
"epoch": 0.38232468780019213,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990734648416458,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.19074706882238388,
|
|
"num_tokens": 9111126.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.483927536010742,
|
|
"epoch": 0.382804995196926,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990703541547901,
|
|
"loss": 5.4716,
|
|
"mean_token_accuracy": 0.1818612113595009,
|
|
"num_tokens": 9121979.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.585857200622558,
|
|
"epoch": 0.38328530259365995,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990672382656863,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.18304081559181212,
|
|
"num_tokens": 9132929.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.575928497314453,
|
|
"epoch": 0.38376560999039383,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990641171744064,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.18569256216287613,
|
|
"num_tokens": 9143903.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.547336101531982,
|
|
"epoch": 0.38424591738712777,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004990609908810231,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.18215738236904144,
|
|
"num_tokens": 9154416.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.516099166870117,
|
|
"epoch": 0.38472622478386165,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004990578593856089,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.17502751499414443,
|
|
"num_tokens": 9165613.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.5226569175720215,
|
|
"epoch": 0.3852065321805956,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990547226882366,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.18428245335817336,
|
|
"num_tokens": 9177884.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.624368572235108,
|
|
"epoch": 0.38568683957732947,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990515807889788,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.17172971218824387,
|
|
"num_tokens": 9190041.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.622077322006225,
|
|
"epoch": 0.3861671469740634,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004990484336879087,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.18016511350870132,
|
|
"num_tokens": 9202390.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.45042667388916,
|
|
"epoch": 0.3866474543707973,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004990452813850992,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.1824759066104889,
|
|
"num_tokens": 9213437.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.539326953887939,
|
|
"epoch": 0.3871277617675312,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004990421238806236,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.16786248236894608,
|
|
"num_tokens": 9226310.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.638813781738281,
|
|
"epoch": 0.38760806916426516,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990389611745551,
|
|
"loss": 5.4894,
|
|
"mean_token_accuracy": 0.17611218839883805,
|
|
"num_tokens": 9236271.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.570121097564697,
|
|
"epoch": 0.38808837656099904,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004990357932669672,
|
|
"loss": 5.5523,
|
|
"mean_token_accuracy": 0.1819245472550392,
|
|
"num_tokens": 9247755.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.480488061904907,
|
|
"epoch": 0.388568683957733,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004990326201579335,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.1880244106054306,
|
|
"num_tokens": 9259821.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.543564367294311,
|
|
"epoch": 0.38904899135446686,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004990294418475274,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.1806348368525505,
|
|
"num_tokens": 9270663.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.500760746002197,
|
|
"epoch": 0.3895292987512008,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004990262583358231,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.17671822905540466,
|
|
"num_tokens": 9282588.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.592128467559815,
|
|
"epoch": 0.3900096061479347,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990230696228943,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.17411451190710067,
|
|
"num_tokens": 9293368.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.518519496917724,
|
|
"epoch": 0.3904899135446686,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004990198757088149,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.17570164203643798,
|
|
"num_tokens": 9305962.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.5013747215271,
|
|
"epoch": 0.3909702209414025,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004990166765936593,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.18421950489282607,
|
|
"num_tokens": 9317955.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.5406488418579105,
|
|
"epoch": 0.3914505283381364,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990134722775016,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.18471345007419587,
|
|
"num_tokens": 9329491.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.501897478103638,
|
|
"epoch": 0.3919308357348703,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990102627604162,
|
|
"loss": 5.5635,
|
|
"mean_token_accuracy": 0.1838073894381523,
|
|
"num_tokens": 9341612.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.562529611587524,
|
|
"epoch": 0.39241114313160425,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990070480424778,
|
|
"loss": 5.5136,
|
|
"mean_token_accuracy": 0.1770092248916626,
|
|
"num_tokens": 9352302.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.5317894458770756,
|
|
"epoch": 0.3928914505283381,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990038281237608,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.17851878553628922,
|
|
"num_tokens": 9363303.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.4764632225036625,
|
|
"epoch": 0.39337175792507206,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004990006030043401,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.179496368765831,
|
|
"num_tokens": 9375878.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.506278705596924,
|
|
"epoch": 0.39385206532180594,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004989973726842906,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.1811349019408226,
|
|
"num_tokens": 9388342.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.495283365249634,
|
|
"epoch": 0.3943323727185399,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004989941371636872,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.18487658202648163,
|
|
"num_tokens": 9399047.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.547529077529907,
|
|
"epoch": 0.39481268011527376,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004989908964426051,
|
|
"loss": 5.4655,
|
|
"mean_token_accuracy": 0.18323731869459153,
|
|
"num_tokens": 9410172.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.5741394519805905,
|
|
"epoch": 0.3952929875120077,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004989876505211194,
|
|
"loss": 5.5955,
|
|
"mean_token_accuracy": 0.1734453931450844,
|
|
"num_tokens": 9422287.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.592891454696655,
|
|
"epoch": 0.3957732949087416,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004989843993993056,
|
|
"loss": 5.4685,
|
|
"mean_token_accuracy": 0.18500566929578782,
|
|
"num_tokens": 9433709.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.422618579864502,
|
|
"epoch": 0.3962536023054755,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004989811430772392,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.18421114832162858,
|
|
"num_tokens": 9445138.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.462180280685425,
|
|
"epoch": 0.3967339097022094,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004989778815549957,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.17901234924793244,
|
|
"num_tokens": 9455263.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.5721040725708,
|
|
"epoch": 0.39721421709894333,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004989746148326508,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.1848315954208374,
|
|
"num_tokens": 9465491.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.456335878372192,
|
|
"epoch": 0.3976945244956772,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989713429102805,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.17743828743696213,
|
|
"num_tokens": 9477601.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.487836313247681,
|
|
"epoch": 0.39817483189241115,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989680657879607,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.18285394459962845,
|
|
"num_tokens": 9489385.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.491547346115112,
|
|
"epoch": 0.39865513928914503,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004989647834657675,
|
|
"loss": 5.3653,
|
|
"mean_token_accuracy": 0.18652124106884002,
|
|
"num_tokens": 9501131.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.449353837966919,
|
|
"epoch": 0.39913544668587897,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000498961495943777,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.1801174148917198,
|
|
"num_tokens": 9513094.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.647522783279419,
|
|
"epoch": 0.39961575408261285,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004989582032220656,
|
|
"loss": 5.619,
|
|
"mean_token_accuracy": 0.1744399979710579,
|
|
"num_tokens": 9524538.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.535951614379883,
|
|
"epoch": 0.4000960614793468,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004989549053007096,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.1917867437005043,
|
|
"num_tokens": 9535284.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.500121355056763,
|
|
"epoch": 0.40057636887608067,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004989516021797858,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.18134415298700332,
|
|
"num_tokens": 9546472.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.517411756515503,
|
|
"epoch": 0.4010566762728146,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000498948293859371,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.17909413427114487,
|
|
"num_tokens": 9558358.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.550367832183838,
|
|
"epoch": 0.4015369836695485,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989449803395415,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.18158189356327056,
|
|
"num_tokens": 9570653.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.596060037612915,
|
|
"epoch": 0.4020172910662824,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004989416616203747,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.1808697208762169,
|
|
"num_tokens": 9582150.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.539777755737305,
|
|
"epoch": 0.4024975984630163,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004989383377019476,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.1830178678035736,
|
|
"num_tokens": 9592462.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.476257228851319,
|
|
"epoch": 0.40297790585975024,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989350085843371,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.18378883451223374,
|
|
"num_tokens": 9604027.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.48982605934143,
|
|
"epoch": 0.4034582132564842,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004989316742676207,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.18200782537460328,
|
|
"num_tokens": 9616325.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.402288150787354,
|
|
"epoch": 0.40393852065321806,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004989283347518757,
|
|
"loss": 5.3805,
|
|
"mean_token_accuracy": 0.18248170912265776,
|
|
"num_tokens": 9628133.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.6253981590271,
|
|
"epoch": 0.404418828049952,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004989249900371797,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.17385684996843337,
|
|
"num_tokens": 9639686.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.555801439285278,
|
|
"epoch": 0.4048991354466859,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004989216401236103,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.1808287799358368,
|
|
"num_tokens": 9650222.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.343467664718628,
|
|
"epoch": 0.4053794428434198,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989182850112455,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.1927611470222473,
|
|
"num_tokens": 9661792.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.519754695892334,
|
|
"epoch": 0.4058597502401537,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989149247001629,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.17862116694450378,
|
|
"num_tokens": 9673000.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.641636943817138,
|
|
"epoch": 0.40634005763688763,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989115591904407,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.18593902587890626,
|
|
"num_tokens": 9685253.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.461031913757324,
|
|
"epoch": 0.4068203650336215,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004989081884821569,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.18008065968751907,
|
|
"num_tokens": 9697245.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.4681854248046875,
|
|
"epoch": 0.40730067243035545,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004989048125753899,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.17974332869052886,
|
|
"num_tokens": 9710095.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.526550054550171,
|
|
"epoch": 0.40778097982708933,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000498901431470218,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.189200496673584,
|
|
"num_tokens": 9721488.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.357129240036011,
|
|
"epoch": 0.40826128722382327,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988980451667198,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.18925195336341857,
|
|
"num_tokens": 9733280.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.495548152923584,
|
|
"epoch": 0.40874159462055715,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004988946536649737,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.18091641068458558,
|
|
"num_tokens": 9744514.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.465915489196777,
|
|
"epoch": 0.4092219020172911,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004988912569650585,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.18548748940229415,
|
|
"num_tokens": 9754931.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.442157649993897,
|
|
"epoch": 0.40970220941402496,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004988878550670533,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.18438775688409806,
|
|
"num_tokens": 9765635.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.523358678817749,
|
|
"epoch": 0.4101825168107589,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004988844479710369,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.1746458664536476,
|
|
"num_tokens": 9777512.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.563890552520752,
|
|
"epoch": 0.4106628242074928,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004988810356770884,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.16993873864412307,
|
|
"num_tokens": 9790128.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.507837009429932,
|
|
"epoch": 0.4111431316042267,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000498877618185287,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.18530694842338563,
|
|
"num_tokens": 9802549.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.483244276046753,
|
|
"epoch": 0.4116234390009606,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004988741954957121,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.18335859328508378,
|
|
"num_tokens": 9813736.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.4134934425354,
|
|
"epoch": 0.41210374639769454,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004988707676084432,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.19594984352588654,
|
|
"num_tokens": 9823785.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.456879281997681,
|
|
"epoch": 0.4125840537944284,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004988673345235597,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.1909172162413597,
|
|
"num_tokens": 9834910.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.512362861633301,
|
|
"epoch": 0.41306436119116235,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004988638962411416,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.18260153979063035,
|
|
"num_tokens": 9845593.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.471342515945435,
|
|
"epoch": 0.41354466858789624,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004988604527612685,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.19799539744853972,
|
|
"num_tokens": 9856763.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.550112056732178,
|
|
"epoch": 0.4140249759846302,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004988570040840205,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.17671879082918168,
|
|
"num_tokens": 9869528.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.499665069580078,
|
|
"epoch": 0.41450528338136405,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004988535502094774,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.18691301792860032,
|
|
"num_tokens": 9881170.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.502493000030517,
|
|
"epoch": 0.414985590778098,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988500911377198,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.17932388037443162,
|
|
"num_tokens": 9893119.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.428243637084961,
|
|
"epoch": 0.41546589817483187,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988466268688276,
|
|
"loss": 5.3653,
|
|
"mean_token_accuracy": 0.19261398315429687,
|
|
"num_tokens": 9905339.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.482554960250854,
|
|
"epoch": 0.4159462055715658,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988431574028814,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.18734948486089706,
|
|
"num_tokens": 9917500.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.4933525085449215,
|
|
"epoch": 0.4164265129682997,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004988396827399618,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.17684542685747145,
|
|
"num_tokens": 9929667.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.554034757614136,
|
|
"epoch": 0.4169068203650336,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004988362028801495,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.18378268033266068,
|
|
"num_tokens": 9941102.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.434017658233643,
|
|
"epoch": 0.4173871277617675,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988327178235253,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.1936184659600258,
|
|
"num_tokens": 9951986.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.4353831768035885,
|
|
"epoch": 0.41786743515850144,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004988292275701699,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.192474102973938,
|
|
"num_tokens": 9964486.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.466612339019775,
|
|
"epoch": 0.4183477425552353,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004988257321201646,
|
|
"loss": 5.4702,
|
|
"mean_token_accuracy": 0.18254957869648933,
|
|
"num_tokens": 9975909.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.528854608535767,
|
|
"epoch": 0.41882804995196926,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004988222314735902,
|
|
"loss": 5.4571,
|
|
"mean_token_accuracy": 0.1850148007273674,
|
|
"num_tokens": 9986951.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.578570699691772,
|
|
"epoch": 0.41930835734870314,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004988187256305284,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.17636647075414658,
|
|
"num_tokens": 9999234.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.415150833129883,
|
|
"epoch": 0.4197886647454371,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004988152145910603,
|
|
"loss": 5.4163,
|
|
"mean_token_accuracy": 0.1876254841685295,
|
|
"num_tokens": 10010178.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.4491785049438475,
|
|
"epoch": 0.420268972142171,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988116983552675,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.18330142349004747,
|
|
"num_tokens": 10021183.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.6285693645477295,
|
|
"epoch": 0.4207492795389049,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004988081769232317,
|
|
"loss": 5.6663,
|
|
"mean_token_accuracy": 0.17082005888223648,
|
|
"num_tokens": 10033686.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.496864986419678,
|
|
"epoch": 0.42122958693563883,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004988046502950346,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.18226284831762313,
|
|
"num_tokens": 10045923.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.345745944976807,
|
|
"epoch": 0.4217098943323727,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000498801118470758,
|
|
"loss": 5.2875,
|
|
"mean_token_accuracy": 0.19129029661417007,
|
|
"num_tokens": 10057196.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.400056791305542,
|
|
"epoch": 0.42219020172910665,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000498797581450484,
|
|
"loss": 5.4913,
|
|
"mean_token_accuracy": 0.17837453335523606,
|
|
"num_tokens": 10069655.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.56167426109314,
|
|
"epoch": 0.42267050912584053,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004987940392342948,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.18617917746305465,
|
|
"num_tokens": 10080876.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.498322010040283,
|
|
"epoch": 0.42315081652257447,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987904918222726,
|
|
"loss": 5.4423,
|
|
"mean_token_accuracy": 0.17843594700098037,
|
|
"num_tokens": 10091986.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.537495088577271,
|
|
"epoch": 0.42363112391930835,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004987869392144996,
|
|
"loss": 5.5328,
|
|
"mean_token_accuracy": 0.1800243929028511,
|
|
"num_tokens": 10104027.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.489960527420044,
|
|
"epoch": 0.4241114313160423,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004987833814110584,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.1842568412423134,
|
|
"num_tokens": 10114665.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.460880279541016,
|
|
"epoch": 0.42459173871277617,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004987798184120316,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.18735718131065368,
|
|
"num_tokens": 10126032.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.533997440338135,
|
|
"epoch": 0.4250720461095101,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004987762502175018,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.18091178983449935,
|
|
"num_tokens": 10137256.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.394541025161743,
|
|
"epoch": 0.425552353506244,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.000498772676827552,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.1898224025964737,
|
|
"num_tokens": 10149445.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.483163595199585,
|
|
"epoch": 0.4260326609029779,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987690982422652,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.17469687163829803,
|
|
"num_tokens": 10161607.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.536775732040406,
|
|
"epoch": 0.4265129682997118,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004987655144617243,
|
|
"loss": 5.5154,
|
|
"mean_token_accuracy": 0.18161867707967758,
|
|
"num_tokens": 10173184.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.4779456615447994,
|
|
"epoch": 0.42699327569644574,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004987619254860126,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.19340196698904039,
|
|
"num_tokens": 10184617.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.505557107925415,
|
|
"epoch": 0.4274735830931796,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004987583313152134,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.1813488185405731,
|
|
"num_tokens": 10195608.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.460960626602173,
|
|
"epoch": 0.42795389048991356,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004987547319494104,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.18232409358024598,
|
|
"num_tokens": 10206763.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.497169113159179,
|
|
"epoch": 0.42843419788664744,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987511273886867,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.1861417517066002,
|
|
"num_tokens": 10218714.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.472766447067261,
|
|
"epoch": 0.4289145052833814,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004987475176331263,
|
|
"loss": 5.4423,
|
|
"mean_token_accuracy": 0.1846688136458397,
|
|
"num_tokens": 10229902.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.466876745223999,
|
|
"epoch": 0.42939481268011526,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004987439026828129,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.18498282581567765,
|
|
"num_tokens": 10241578.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.381464290618896,
|
|
"epoch": 0.4298751200768492,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987402825378305,
|
|
"loss": 5.3178,
|
|
"mean_token_accuracy": 0.18822970390319824,
|
|
"num_tokens": 10252109.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.492452716827392,
|
|
"epoch": 0.4303554274735831,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004987366571982631,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.1814950406551361,
|
|
"num_tokens": 10263357.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.516273403167725,
|
|
"epoch": 0.430835734870317,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004987330266641948,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.18026821911334992,
|
|
"num_tokens": 10275536.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.567843055725097,
|
|
"epoch": 0.4313160422670509,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004987293909357101,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.1830426648259163,
|
|
"num_tokens": 10286901.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.400497674942017,
|
|
"epoch": 0.43179634966378483,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004987257500128933,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.1850377067923546,
|
|
"num_tokens": 10298961.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.508952999114991,
|
|
"epoch": 0.4322766570605187,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004987221038958288,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.1820940375328064,
|
|
"num_tokens": 10310911.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.6083094596862795,
|
|
"epoch": 0.43275696445725265,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987184525846015,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.17781338542699815,
|
|
"num_tokens": 10322267.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.473596286773682,
|
|
"epoch": 0.4332372718539865,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004987147960792958,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.1821509137749672,
|
|
"num_tokens": 10335111.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.497584342956543,
|
|
"epoch": 0.43371757925072046,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004987111343799971,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.1844386041164398,
|
|
"num_tokens": 10345672.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.5401129722595215,
|
|
"epoch": 0.43419788664745435,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00049870746748679,
|
|
"loss": 5.4145,
|
|
"mean_token_accuracy": 0.18377436846494674,
|
|
"num_tokens": 10357369.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.516617059707642,
|
|
"epoch": 0.4346781940441883,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004987037953997598,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.1811770722270012,
|
|
"num_tokens": 10368842.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.508967542648316,
|
|
"epoch": 0.43515850144092216,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004987001181189918,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.1840538814663887,
|
|
"num_tokens": 10380096.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.36380410194397,
|
|
"epoch": 0.4356388088376561,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004986964356445713,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.18465624302625655,
|
|
"num_tokens": 10391996.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.5177970886230465,
|
|
"epoch": 0.43611911623439004,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004986927479765837,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.18245675563812255,
|
|
"num_tokens": 10403607.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.492802524566651,
|
|
"epoch": 0.4365994236311239,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004986890551151148,
|
|
"loss": 5.4028,
|
|
"mean_token_accuracy": 0.18143354654312133,
|
|
"num_tokens": 10413580.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.445534610748291,
|
|
"epoch": 0.43707973102785785,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004986853570602503,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.18216769844293595,
|
|
"num_tokens": 10426456.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.587636709213257,
|
|
"epoch": 0.43756003842459174,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004986816538120758,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.1740506410598755,
|
|
"num_tokens": 10438869.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.479203557968139,
|
|
"epoch": 0.43804034582132567,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004986779453706778,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.17830465137958526,
|
|
"num_tokens": 10450672.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.49304165840149,
|
|
"epoch": 0.43852065321805955,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004986742317361419,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.18656738847494125,
|
|
"num_tokens": 10461890.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.560182905197143,
|
|
"epoch": 0.4390009606147935,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986705129085546,
|
|
"loss": 5.5161,
|
|
"mean_token_accuracy": 0.17243352830410003,
|
|
"num_tokens": 10473866.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.506742811203003,
|
|
"epoch": 0.43948126801152737,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004986667888880021,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.18097116947174072,
|
|
"num_tokens": 10484889.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.455934143066406,
|
|
"epoch": 0.4399615754082613,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004986630596745709,
|
|
"loss": 5.4532,
|
|
"mean_token_accuracy": 0.18290567100048066,
|
|
"num_tokens": 10496108.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.44108214378357,
|
|
"epoch": 0.4404418828049952,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004986593252683477,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.1821491926908493,
|
|
"num_tokens": 10505472.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.347932052612305,
|
|
"epoch": 0.4409221902017291,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004986555856694191,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.18910347074270248,
|
|
"num_tokens": 10516954.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.549670791625976,
|
|
"epoch": 0.441402497598463,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986518408778718,
|
|
"loss": 5.4375,
|
|
"mean_token_accuracy": 0.18230860978364943,
|
|
"num_tokens": 10528166.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.410103225708008,
|
|
"epoch": 0.44188280499519694,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004986480908937929,
|
|
"loss": 5.3522,
|
|
"mean_token_accuracy": 0.1797751307487488,
|
|
"num_tokens": 10538112.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.477563571929932,
|
|
"epoch": 0.4423631123919308,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986443357172695,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.1840632364153862,
|
|
"num_tokens": 10549888.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.618176603317261,
|
|
"epoch": 0.44284341978866476,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004986405753483887,
|
|
"loss": 5.5705,
|
|
"mean_token_accuracy": 0.16967248618602754,
|
|
"num_tokens": 10561710.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.479874134063721,
|
|
"epoch": 0.44332372718539864,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004986368097872377,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.181022110581398,
|
|
"num_tokens": 10574564.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.498565435409546,
|
|
"epoch": 0.4438040345821326,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004986330390339042,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.18595313280820847,
|
|
"num_tokens": 10586639.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.468168878555298,
|
|
"epoch": 0.44428434197886646,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004986292630884755,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.18555108308792115,
|
|
"num_tokens": 10598730.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.423819303512573,
|
|
"epoch": 0.4447646493756004,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004986254819510393,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.19339857548475264,
|
|
"num_tokens": 10610352.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.476513481140136,
|
|
"epoch": 0.4452449567723343,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004986216956216835,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.18237403333187102,
|
|
"num_tokens": 10621951.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.439531326293945,
|
|
"epoch": 0.4457252641690682,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000498617904100496,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.18807268440723418,
|
|
"num_tokens": 10633207.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.553469562530518,
|
|
"epoch": 0.4462055715658021,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004986141073875646,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.17650653123855592,
|
|
"num_tokens": 10645853.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.438301992416382,
|
|
"epoch": 0.44668587896253603,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004986103054829779,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.18930209279060364,
|
|
"num_tokens": 10656892.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.441705322265625,
|
|
"epoch": 0.4471661863592699,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004986064983868237,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.1787632092833519,
|
|
"num_tokens": 10670110.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.549786186218261,
|
|
"epoch": 0.44764649375600385,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004986026860991906,
|
|
"loss": 5.5066,
|
|
"mean_token_accuracy": 0.1793380305171013,
|
|
"num_tokens": 10681255.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.570867490768433,
|
|
"epoch": 0.44812680115273773,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004985988686201672,
|
|
"loss": 5.5576,
|
|
"mean_token_accuracy": 0.1818427100777626,
|
|
"num_tokens": 10692631.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.436335945129395,
|
|
"epoch": 0.44860710854947167,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985950459498419,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.18658163249492646,
|
|
"num_tokens": 10704880.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.481291627883911,
|
|
"epoch": 0.44908741594620555,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004985912180883037,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.19357271492481232,
|
|
"num_tokens": 10715561.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.4576582431793215,
|
|
"epoch": 0.4495677233429395,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985873850356411,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.18074813187122346,
|
|
"num_tokens": 10727232.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.4327513694763185,
|
|
"epoch": 0.45004803073967337,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004985835467919436,
|
|
"loss": 5.4061,
|
|
"mean_token_accuracy": 0.18214502632617952,
|
|
"num_tokens": 10739404.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.528501701354981,
|
|
"epoch": 0.4505283381364073,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004985797033572999,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.1820250302553177,
|
|
"num_tokens": 10751948.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.435817432403565,
|
|
"epoch": 0.4510086455331412,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004985758547317994,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.18103179037570954,
|
|
"num_tokens": 10764611.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.475479650497436,
|
|
"epoch": 0.4514889529298751,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985720009155315,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.17909349948167802,
|
|
"num_tokens": 10775954.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.535087585449219,
|
|
"epoch": 0.45196926032660906,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985681419085856,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.17889766544103622,
|
|
"num_tokens": 10788723.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.510971117019653,
|
|
"epoch": 0.45244956772334294,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004985642777110513,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.1858873263001442,
|
|
"num_tokens": 10799879.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.399571466445923,
|
|
"epoch": 0.4529298751200769,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004985604083230183,
|
|
"loss": 5.3992,
|
|
"mean_token_accuracy": 0.18622933328151703,
|
|
"num_tokens": 10811838.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.520981073379517,
|
|
"epoch": 0.45341018251681076,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004985565337445765,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.1855739548802376,
|
|
"num_tokens": 10822910.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.532252025604248,
|
|
"epoch": 0.4538904899135447,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004985526539758158,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.17770517021417617,
|
|
"num_tokens": 10835344.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.440028238296509,
|
|
"epoch": 0.4543707973102786,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985487690168263,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.18244538307189942,
|
|
"num_tokens": 10846043.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.452834892272949,
|
|
"epoch": 0.4548511047070125,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000498544878867698,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.18833234757184983,
|
|
"num_tokens": 10857783.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.5130455493927,
|
|
"epoch": 0.4553314121037464,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004985409835285215,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.18405425250530244,
|
|
"num_tokens": 10870527.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.488106632232666,
|
|
"epoch": 0.45581171950048033,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004985370829993873,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.18260936439037323,
|
|
"num_tokens": 10882285.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.526673412322998,
|
|
"epoch": 0.4562920268972142,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004985331772803857,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.1846647620201111,
|
|
"num_tokens": 10895319.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.569026803970337,
|
|
"epoch": 0.45677233429394815,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004985292663716074,
|
|
"loss": 5.4307,
|
|
"mean_token_accuracy": 0.18395293802022933,
|
|
"num_tokens": 10906253.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.333486604690552,
|
|
"epoch": 0.457252641690682,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004985253502731435,
|
|
"loss": 5.3059,
|
|
"mean_token_accuracy": 0.1912243977189064,
|
|
"num_tokens": 10918197.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.461763858795166,
|
|
"epoch": 0.45773294908741596,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004985214289850845,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.17738655358552932,
|
|
"num_tokens": 10930771.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.500912475585937,
|
|
"epoch": 0.45821325648414984,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985175025075217,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.1847668319940567,
|
|
"num_tokens": 10942759.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.604831647872925,
|
|
"epoch": 0.4586935638808838,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004985135708405462,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.17481530904769899,
|
|
"num_tokens": 10953557.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.503426218032837,
|
|
"epoch": 0.45917387127761766,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004985096339842493,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.18891924917697905,
|
|
"num_tokens": 10963142.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.370479488372803,
|
|
"epoch": 0.4596541786743516,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004985056919387224,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.19065655767917633,
|
|
"num_tokens": 10974321.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.509304141998291,
|
|
"epoch": 0.4601344860710855,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004985017447040569,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.17673837691545485,
|
|
"num_tokens": 10985524.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.556762981414795,
|
|
"epoch": 0.4606147934678194,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004984977922803447,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.18580958843231202,
|
|
"num_tokens": 10997606.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.4708620548248295,
|
|
"epoch": 0.4610951008645533,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004984938346676772,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.17487015575170517,
|
|
"num_tokens": 11010692.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.474565124511718,
|
|
"epoch": 0.46157540826128723,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984898718661468,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.18959158807992935,
|
|
"num_tokens": 11022517.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.486980676651001,
|
|
"epoch": 0.4620557156580211,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004984859038758451,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.18491147160530091,
|
|
"num_tokens": 11033141.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.449812412261963,
|
|
"epoch": 0.46253602305475505,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004984819306968642,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.1848921850323677,
|
|
"num_tokens": 11044619.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.535708284378051,
|
|
"epoch": 0.46301633045148893,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004984779523292966,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.18369874805212022,
|
|
"num_tokens": 11055934.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.477626991271973,
|
|
"epoch": 0.46349663784822287,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984739687732345,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.18971931487321853,
|
|
"num_tokens": 11066203.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.247989749908447,
|
|
"epoch": 0.46397694524495675,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004984699800287705,
|
|
"loss": 5.2501,
|
|
"mean_token_accuracy": 0.19335371404886245,
|
|
"num_tokens": 11079664.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.38968596458435,
|
|
"epoch": 0.4644572526416907,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000498465986095997,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.1878895416855812,
|
|
"num_tokens": 11091186.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.533202981948852,
|
|
"epoch": 0.46493756003842457,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004984619869750069,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.18179282695055007,
|
|
"num_tokens": 11102710.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.401765394210815,
|
|
"epoch": 0.4654178674351585,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000498457982665893,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.1888763949275017,
|
|
"num_tokens": 11114746.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.47950119972229,
|
|
"epoch": 0.4658981748318924,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004984539731687483,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.18246447890996934,
|
|
"num_tokens": 11126572.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.4360514163970945,
|
|
"epoch": 0.4663784822286263,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004984499584836659,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.1890285938978195,
|
|
"num_tokens": 11137830.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.359745025634766,
|
|
"epoch": 0.4668587896253602,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000498445938610739,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.18278533071279526,
|
|
"num_tokens": 11148860.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.516309499740601,
|
|
"epoch": 0.46733909702209414,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004984419135500608,
|
|
"loss": 5.4489,
|
|
"mean_token_accuracy": 0.17562684118747712,
|
|
"num_tokens": 11161311.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.477908658981323,
|
|
"epoch": 0.4678194044188281,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004984378833017249,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.18358855396509172,
|
|
"num_tokens": 11173124.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.420060014724731,
|
|
"epoch": 0.46829971181556196,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004984338478658248,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.18347779512405396,
|
|
"num_tokens": 11184879.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.5258119106292725,
|
|
"epoch": 0.4687800192122959,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004984298072424542,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.18503387421369552,
|
|
"num_tokens": 11196243.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.442278146743774,
|
|
"epoch": 0.4692603266090298,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000498425761431707,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.196873277425766,
|
|
"num_tokens": 11207485.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.409700775146485,
|
|
"epoch": 0.4697406340057637,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000498421710433677,
|
|
"loss": 5.3513,
|
|
"mean_token_accuracy": 0.18322594314813614,
|
|
"num_tokens": 11219891.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.509650707244873,
|
|
"epoch": 0.4702209414024976,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004984176542484584,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.1837195187807083,
|
|
"num_tokens": 11231329.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.454485130310059,
|
|
"epoch": 0.47070124879923153,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984135928761452,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.19730102270841599,
|
|
"num_tokens": 11241367.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.457817792892456,
|
|
"epoch": 0.4711815561959654,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004984095263168317,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.17746436446905137,
|
|
"num_tokens": 11254532.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.491858100891113,
|
|
"epoch": 0.47166186359269935,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004984054545706124,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.17749812602996826,
|
|
"num_tokens": 11265223.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.438859224319458,
|
|
"epoch": 0.47214217098943323,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000498401377637582,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.18164921402931214,
|
|
"num_tokens": 11278228.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.612646055221558,
|
|
"epoch": 0.47262247838616717,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000498397295517835,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.1760594516992569,
|
|
"num_tokens": 11289654.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.462486839294433,
|
|
"epoch": 0.47310278578290105,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004983932082114659,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.19031091034412384,
|
|
"num_tokens": 11301911.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.4843346118927006,
|
|
"epoch": 0.473583093179635,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004983891157185699,
|
|
"loss": 5.4924,
|
|
"mean_token_accuracy": 0.17719163075089456,
|
|
"num_tokens": 11312945.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.648605394363403,
|
|
"epoch": 0.47406340057636887,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004983850180392421,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.17459377497434617,
|
|
"num_tokens": 11324126.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.499599027633667,
|
|
"epoch": 0.4745437079731028,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004983809151735775,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.1775331065058708,
|
|
"num_tokens": 11336395.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.450175380706787,
|
|
"epoch": 0.4750240153698367,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983768071216713,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.186611807346344,
|
|
"num_tokens": 11347387.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.426102352142334,
|
|
"epoch": 0.4755043227665706,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004983726938836189,
|
|
"loss": 5.3608,
|
|
"mean_token_accuracy": 0.18698815405368804,
|
|
"num_tokens": 11358467.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.539723682403564,
|
|
"epoch": 0.4759846301633045,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983685754595159,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.17893662601709365,
|
|
"num_tokens": 11370322.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.391429758071899,
|
|
"epoch": 0.47646493756003844,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004983644518494578,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.19383544325828553,
|
|
"num_tokens": 11381719.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.384700012207031,
|
|
"epoch": 0.4769452449567723,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004983603230535403,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.18786550909280778,
|
|
"num_tokens": 11393561.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.525062990188599,
|
|
"epoch": 0.47742555235350626,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004983561890718594,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.18443512916564941,
|
|
"num_tokens": 11405411.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.569968318939209,
|
|
"epoch": 0.47790585975024014,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000498352049904511,
|
|
"loss": 5.538,
|
|
"mean_token_accuracy": 0.17363222390413285,
|
|
"num_tokens": 11417419.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.45677170753479,
|
|
"epoch": 0.4783861671469741,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004983479055515914,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.18214483708143234,
|
|
"num_tokens": 11428145.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.377432441711425,
|
|
"epoch": 0.47886647454370795,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004983437560131964,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.19136955142021178,
|
|
"num_tokens": 11439224.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.481130743026734,
|
|
"epoch": 0.4793467819404419,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004983396012894228,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.18173141181468963,
|
|
"num_tokens": 11451731.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.4927207946777346,
|
|
"epoch": 0.47982708933717577,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004983354413803666,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.18813264966011048,
|
|
"num_tokens": 11463058.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.541668891906738,
|
|
"epoch": 0.4803073967339097,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004983312762861248,
|
|
"loss": 5.4915,
|
|
"mean_token_accuracy": 0.1748691439628601,
|
|
"num_tokens": 11472618.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.423635530471802,
|
|
"epoch": 0.4807877041306436,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004983271060067939,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.18497644513845443,
|
|
"num_tokens": 11483114.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.39136438369751,
|
|
"epoch": 0.4812680115273775,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004983229305424707,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.18773939609527587,
|
|
"num_tokens": 11494281.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.450998973846436,
|
|
"epoch": 0.4817483189241114,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004983187498932522,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.18099243491888045,
|
|
"num_tokens": 11505962.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.482204103469849,
|
|
"epoch": 0.48222862632084534,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004983145640592354,
|
|
"loss": 5.4819,
|
|
"mean_token_accuracy": 0.18032473623752593,
|
|
"num_tokens": 11517558.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.518228244781494,
|
|
"epoch": 0.4827089337175792,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983103730405176,
|
|
"loss": 5.4781,
|
|
"mean_token_accuracy": 0.18203603178262712,
|
|
"num_tokens": 11529184.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.500524473190308,
|
|
"epoch": 0.48318924111431316,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000498306176837196,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.17953826785087584,
|
|
"num_tokens": 11540727.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.412310314178467,
|
|
"epoch": 0.48366954851104704,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004983019754493681,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.18378405421972274,
|
|
"num_tokens": 11551510.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.468509769439697,
|
|
"epoch": 0.484149855907781,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004982977688771314,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.18473168313503266,
|
|
"num_tokens": 11563203.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.4333024501800535,
|
|
"epoch": 0.4846301633045149,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004982935571205835,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.1896449312567711,
|
|
"num_tokens": 11576013.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.321088027954102,
|
|
"epoch": 0.4851104707012488,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004982893401798223,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.19963925182819367,
|
|
"num_tokens": 11587535.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.453434753417969,
|
|
"epoch": 0.48559077809798273,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004982851180549456,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.19101324528455735,
|
|
"num_tokens": 11598487.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.3744926929473875,
|
|
"epoch": 0.4860710854947166,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982808907460515,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.2023797392845154,
|
|
"num_tokens": 11609457.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.311481618881226,
|
|
"epoch": 0.48655139289145055,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982766582532382,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.18937668353319168,
|
|
"num_tokens": 11620251.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.397979736328125,
|
|
"epoch": 0.48703170028818443,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004982724205766038,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.19131511002779006,
|
|
"num_tokens": 11630956.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.444111061096192,
|
|
"epoch": 0.48751200768491837,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982681777162468,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.1843711793422699,
|
|
"num_tokens": 11642560.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.334614372253418,
|
|
"epoch": 0.48799231508165225,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004982639296722657,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.18654131144285202,
|
|
"num_tokens": 11654050.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.377294111251831,
|
|
"epoch": 0.4884726224783862,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004982596764447591,
|
|
"loss": 5.4642,
|
|
"mean_token_accuracy": 0.18597072064876558,
|
|
"num_tokens": 11664947.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.5037812232971195,
|
|
"epoch": 0.48895292987512007,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004982554180338258,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.1887000247836113,
|
|
"num_tokens": 11676927.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.561541652679443,
|
|
"epoch": 0.489433237271854,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982511544395646,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.17555807232856752,
|
|
"num_tokens": 11688573.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.364769363403321,
|
|
"epoch": 0.4899135446685879,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004982468856620745,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.18414994776248933,
|
|
"num_tokens": 11698704.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.418073081970215,
|
|
"epoch": 0.4903938520653218,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004982426117014545,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.19092437028884887,
|
|
"num_tokens": 11709466.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.417795038223266,
|
|
"epoch": 0.4908741594620557,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004982383325578041,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.1838390588760376,
|
|
"num_tokens": 11721120.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.4944010257720945,
|
|
"epoch": 0.49135446685878964,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004982340482312226,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.1809481531381607,
|
|
"num_tokens": 11732120.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.407310962677002,
|
|
"epoch": 0.4918347742555235,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982297587218092,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.1922930136322975,
|
|
"num_tokens": 11743501.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.418401432037354,
|
|
"epoch": 0.49231508165225746,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004982254640296637,
|
|
"loss": 5.3644,
|
|
"mean_token_accuracy": 0.18890146762132645,
|
|
"num_tokens": 11755051.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.452147197723389,
|
|
"epoch": 0.49279538904899134,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982211641548857,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.17898448258638383,
|
|
"num_tokens": 11767663.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.513096618652344,
|
|
"epoch": 0.4932756964457253,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004982168590975752,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.1893145740032196,
|
|
"num_tokens": 11778828.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.492355585098267,
|
|
"epoch": 0.49375600384245916,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004982125488578321,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.17757345587015153,
|
|
"num_tokens": 11790654.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.489732265472412,
|
|
"epoch": 0.4942363112391931,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004982082334357563,
|
|
"loss": 5.3358,
|
|
"mean_token_accuracy": 0.1855372592806816,
|
|
"num_tokens": 11801489.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.422472906112671,
|
|
"epoch": 0.494716618635927,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982039128314481,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.18657658696174623,
|
|
"num_tokens": 11813818.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.332447814941406,
|
|
"epoch": 0.4951969260326609,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004981995870450079,
|
|
"loss": 5.3437,
|
|
"mean_token_accuracy": 0.1884280785918236,
|
|
"num_tokens": 11824814.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.4929829120635985,
|
|
"epoch": 0.4956772334293948,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004981952560765361,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.1872633785009384,
|
|
"num_tokens": 11836252.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.458308219909668,
|
|
"epoch": 0.49615754082612873,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981909199261331,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.18419483453035354,
|
|
"num_tokens": 11847715.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.344194746017456,
|
|
"epoch": 0.4966378482228626,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004981865785938998,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.18824000060558319,
|
|
"num_tokens": 11860309.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.398108625411988,
|
|
"epoch": 0.49711815561959655,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004981822320799367,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.18898028880357742,
|
|
"num_tokens": 11872569.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.436135721206665,
|
|
"epoch": 0.49759846301633043,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004981778803843449,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.19181872308254241,
|
|
"num_tokens": 11884778.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.479934644699097,
|
|
"epoch": 0.49807877041306436,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004981735235072256,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.18691713064908982,
|
|
"num_tokens": 11897324.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.470985698699951,
|
|
"epoch": 0.49855907780979825,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004981691614486796,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.18618110567331314,
|
|
"num_tokens": 11909145.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.437635850906372,
|
|
"epoch": 0.4990393852065322,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004981647942088084,
|
|
"loss": 5.3304,
|
|
"mean_token_accuracy": 0.19082048386335373,
|
|
"num_tokens": 11921021.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.526174402236938,
|
|
"epoch": 0.49951969260326606,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004981604217877135,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.18330883830785752,
|
|
"num_tokens": 11932565.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.345232439041138,
|
|
"epoch": 0.5,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000498156044185496,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.18701259940862655,
|
|
"num_tokens": 11943225.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.465616703033447,
|
|
"epoch": 0.5004803073967339,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004981516614022579,
|
|
"loss": 5.4109,
|
|
"mean_token_accuracy": 0.18917031586170197,
|
|
"num_tokens": 11954821.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.502865839004516,
|
|
"epoch": 0.5009606147934679,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004981472734381008,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.19262072294950486,
|
|
"num_tokens": 11966090.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.429664421081543,
|
|
"epoch": 0.5014409221902018,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004981428802931267,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.1865019828081131,
|
|
"num_tokens": 11977410.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.3951630115509035,
|
|
"epoch": 0.5019212295869356,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004981384819674375,
|
|
"loss": 5.3624,
|
|
"mean_token_accuracy": 0.17831767350435257,
|
|
"num_tokens": 11989119.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.531827020645141,
|
|
"epoch": 0.5024015369836695,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004981340784611354,
|
|
"loss": 5.4693,
|
|
"mean_token_accuracy": 0.18034402132034302,
|
|
"num_tokens": 12000165.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.450638246536255,
|
|
"epoch": 0.5028818443804035,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004981296697743224,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.1806849643588066,
|
|
"num_tokens": 12012118.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.48490161895752,
|
|
"epoch": 0.5033621517771374,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004981252559071012,
|
|
"loss": 5.4737,
|
|
"mean_token_accuracy": 0.18156729638576508,
|
|
"num_tokens": 12023432.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.473294115066528,
|
|
"epoch": 0.5038424591738713,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004981208368595739,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.1928842544555664,
|
|
"num_tokens": 12034323.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.422391796112061,
|
|
"epoch": 0.5043227665706052,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004981164126318435,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.18605168908834457,
|
|
"num_tokens": 12045532.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.46921215057373,
|
|
"epoch": 0.5048030739673391,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004981119832240124,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.1844169646501541,
|
|
"num_tokens": 12057346.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.39854679107666,
|
|
"epoch": 0.505283381364073,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004981075486361837,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.1936122879385948,
|
|
"num_tokens": 12068670.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.457751893997193,
|
|
"epoch": 0.5057636887608069,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004981031088684601,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.17743652164936066,
|
|
"num_tokens": 12079664.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.518600416183472,
|
|
"epoch": 0.5062439961575408,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004980986639209448,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.19642359614372254,
|
|
"num_tokens": 12089984.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.393462324142456,
|
|
"epoch": 0.5067243035542748,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000498094213793741,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.18708879202604295,
|
|
"num_tokens": 12101182.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.446018695831299,
|
|
"epoch": 0.5072046109510087,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000498089758486952,
|
|
"loss": 5.4111,
|
|
"mean_token_accuracy": 0.1844146728515625,
|
|
"num_tokens": 12112002.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.531693029403686,
|
|
"epoch": 0.5076849183477425,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004980852980006812,
|
|
"loss": 5.5153,
|
|
"mean_token_accuracy": 0.17170377671718598,
|
|
"num_tokens": 12124194.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.461968898773193,
|
|
"epoch": 0.5081652257444764,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004980808323350323,
|
|
"loss": 5.3885,
|
|
"mean_token_accuracy": 0.19202515631914138,
|
|
"num_tokens": 12133966.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.440899229049682,
|
|
"epoch": 0.5086455331412104,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004980763614901089,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.19208761155605317,
|
|
"num_tokens": 12145643.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.385034036636353,
|
|
"epoch": 0.5091258405379443,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004980718854660146,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.1833948090672493,
|
|
"num_tokens": 12156804.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.4892936706542965,
|
|
"epoch": 0.5096061479346782,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980674042628537,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.1843682885169983,
|
|
"num_tokens": 12168700.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.481081342697143,
|
|
"epoch": 0.5100864553314121,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00049806291788073,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.18239480257034302,
|
|
"num_tokens": 12181050.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.522937059402466,
|
|
"epoch": 0.510566762728146,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004980584263197477,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.18213443607091903,
|
|
"num_tokens": 12192001.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.541745185852051,
|
|
"epoch": 0.5110470701248799,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004980539295800111,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.17945037484169007,
|
|
"num_tokens": 12202436.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.446646213531494,
|
|
"epoch": 0.5115273775216138,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004980494276616246,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.18965711295604706,
|
|
"num_tokens": 12214454.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.481778717041015,
|
|
"epoch": 0.5120076849183477,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004980449205646926,
|
|
"loss": 5.3694,
|
|
"mean_token_accuracy": 0.19147139489650727,
|
|
"num_tokens": 12225924.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.455231142044068,
|
|
"epoch": 0.5124879923150817,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00049804040828932,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.19228583872318267,
|
|
"num_tokens": 12236456.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.457484149932862,
|
|
"epoch": 0.5129682997118156,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004980358908356113,
|
|
"loss": 5.4071,
|
|
"mean_token_accuracy": 0.18461320102214812,
|
|
"num_tokens": 12247719.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.446361446380616,
|
|
"epoch": 0.5134486071085494,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004980313682036717,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.18727196305990218,
|
|
"num_tokens": 12259141.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.534922361373901,
|
|
"epoch": 0.5139289145052833,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004980268403936058,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.18048009723424913,
|
|
"num_tokens": 12269748.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.48303861618042,
|
|
"epoch": 0.5144092219020173,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004980223074055189,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.1854291871190071,
|
|
"num_tokens": 12281456.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.500311708450317,
|
|
"epoch": 0.5148895292987512,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004980177692395164,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.1798258066177368,
|
|
"num_tokens": 12293763.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.442075490951538,
|
|
"epoch": 0.5153698366954851,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004980132258957035,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.19021637886762618,
|
|
"num_tokens": 12305398.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.342968511581421,
|
|
"epoch": 0.515850144092219,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004980086773741856,
|
|
"loss": 5.3244,
|
|
"mean_token_accuracy": 0.18798098117113113,
|
|
"num_tokens": 12316582.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.57574429512024,
|
|
"epoch": 0.516330451488953,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004980041236750685,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.1825951561331749,
|
|
"num_tokens": 12328463.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.500926208496094,
|
|
"epoch": 0.5168107588856868,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004979995647984577,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.18738120049238205,
|
|
"num_tokens": 12341040.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.3554994583129885,
|
|
"epoch": 0.5172910662824207,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004979950007444593,
|
|
"loss": 5.3343,
|
|
"mean_token_accuracy": 0.18686822205781936,
|
|
"num_tokens": 12353024.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.481510972976684,
|
|
"epoch": 0.5177713736791547,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004979904315131792,
|
|
"loss": 5.3489,
|
|
"mean_token_accuracy": 0.18890507370233536,
|
|
"num_tokens": 12366100.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.394613790512085,
|
|
"epoch": 0.5182516810758886,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004979858571047233,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.19260989874601364,
|
|
"num_tokens": 12377829.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.477848100662231,
|
|
"epoch": 0.5187319884726225,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004979812775191979,
|
|
"loss": 5.4748,
|
|
"mean_token_accuracy": 0.18508642464876174,
|
|
"num_tokens": 12390830.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.398797273635864,
|
|
"epoch": 0.5192122958693564,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004979766927567094,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.1886269196867943,
|
|
"num_tokens": 12401642.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.439389944076538,
|
|
"epoch": 0.5196926032660903,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004979721028173643,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.18543334156274796,
|
|
"num_tokens": 12411653.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.432659101486206,
|
|
"epoch": 0.5201729106628242,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497967507701269,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.19121986180543898,
|
|
"num_tokens": 12422891.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.499238014221191,
|
|
"epoch": 0.5206532180595581,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004979629074085303,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.18685709238052367,
|
|
"num_tokens": 12434190.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.500961399078369,
|
|
"epoch": 0.521133525456292,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004979583019392548,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.18506830781698227,
|
|
"num_tokens": 12445796.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.51903338432312,
|
|
"epoch": 0.521613832853026,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004979536912935497,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.18300459831953048,
|
|
"num_tokens": 12456212.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.388899660110473,
|
|
"epoch": 0.5220941402497599,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000497949075471522,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.1917024716734886,
|
|
"num_tokens": 12467871.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.439182090759277,
|
|
"epoch": 0.5225744476464937,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004979444544732786,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.18094808459281922,
|
|
"num_tokens": 12478626.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.41655855178833,
|
|
"epoch": 0.5230547550432276,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497939828298927,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.18398275077342988,
|
|
"num_tokens": 12491487.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.484344625473023,
|
|
"epoch": 0.5235350624399616,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004979351969485747,
|
|
"loss": 5.3835,
|
|
"mean_token_accuracy": 0.18404082506895064,
|
|
"num_tokens": 12503240.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.489088773727417,
|
|
"epoch": 0.5240153698366955,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004979305604223291,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.18565881848335267,
|
|
"num_tokens": 12513860.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.381880474090576,
|
|
"epoch": 0.5244956772334294,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004979259187202978,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.18901094943284988,
|
|
"num_tokens": 12525884.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.451713991165161,
|
|
"epoch": 0.5249759846301633,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004979212718425887,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.1874476283788681,
|
|
"num_tokens": 12536709.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.440581321716309,
|
|
"epoch": 0.5254562920268973,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004979166197893096,
|
|
"loss": 5.3251,
|
|
"mean_token_accuracy": 0.18595523983240128,
|
|
"num_tokens": 12549727.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.4044106006622314,
|
|
"epoch": 0.5259365994236311,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004979119625605683,
|
|
"loss": 5.3914,
|
|
"mean_token_accuracy": 0.1832865759730339,
|
|
"num_tokens": 12562053.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.316522741317749,
|
|
"epoch": 0.526416906820365,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004979073001564734,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.19792743325233458,
|
|
"num_tokens": 12574096.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.482320833206177,
|
|
"epoch": 0.5268972142170989,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004979026325771328,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.18214018940925597,
|
|
"num_tokens": 12585416.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.491317701339722,
|
|
"epoch": 0.5273775216138329,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004978979598226549,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.19032478481531143,
|
|
"num_tokens": 12596861.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.390259265899658,
|
|
"epoch": 0.5278578290105668,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004978932818931483,
|
|
"loss": 5.3253,
|
|
"mean_token_accuracy": 0.18920665681362153,
|
|
"num_tokens": 12607761.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.473287439346313,
|
|
"epoch": 0.5283381364073007,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004978885987887216,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.1845549613237381,
|
|
"num_tokens": 12619889.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.533308649063111,
|
|
"epoch": 0.5288184438040345,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004978839105094833,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.18522590398788452,
|
|
"num_tokens": 12630604.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.301638841629028,
|
|
"epoch": 0.5292987512007685,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004978792170555426,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.18722065538167953,
|
|
"num_tokens": 12641172.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.364657211303711,
|
|
"epoch": 0.5297790585975024,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004978745184270083,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.20139759480953218,
|
|
"num_tokens": 12651731.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.46110167503357,
|
|
"epoch": 0.5302593659942363,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004978698146239893,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.18798331320285797,
|
|
"num_tokens": 12663050.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.497533178329467,
|
|
"epoch": 0.5307396733909702,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004978651056465952,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.18002002090215682,
|
|
"num_tokens": 12674732.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.3636658668518065,
|
|
"epoch": 0.5312199807877042,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000497860391494935,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.19072228968143462,
|
|
"num_tokens": 12685981.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.505597305297852,
|
|
"epoch": 0.531700288184438,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978556721691183,
|
|
"loss": 5.4251,
|
|
"mean_token_accuracy": 0.1849287748336792,
|
|
"num_tokens": 12697139.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.414861011505127,
|
|
"epoch": 0.5321805955811719,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004978509476692547,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.1806318387389183,
|
|
"num_tokens": 12708268.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.427301645278931,
|
|
"epoch": 0.5326609029779059,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004978462179954538,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.1861569717526436,
|
|
"num_tokens": 12720715.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.469281959533691,
|
|
"epoch": 0.5331412103746398,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004978414831478253,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.19195597767829894,
|
|
"num_tokens": 12732409.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.406266069412231,
|
|
"epoch": 0.5336215177713737,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004978367431264794,
|
|
"loss": 5.4609,
|
|
"mean_token_accuracy": 0.17862372249364852,
|
|
"num_tokens": 12745174.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.49880428314209,
|
|
"epoch": 0.5341018251681076,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004978319979315261,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.18962205946445465,
|
|
"num_tokens": 12756116.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.463791561126709,
|
|
"epoch": 0.5345821325648416,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004978272475630752,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.18390014469623567,
|
|
"num_tokens": 12768183.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.351048612594605,
|
|
"epoch": 0.5350624399615754,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004978224920212374,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.1906448557972908,
|
|
"num_tokens": 12778537.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.4156632900238035,
|
|
"epoch": 0.5355427473583093,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004978177313061232,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.1866355761885643,
|
|
"num_tokens": 12789691.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.504591846466065,
|
|
"epoch": 0.5360230547550432,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004978129654178426,
|
|
"loss": 5.415,
|
|
"mean_token_accuracy": 0.18533917516469955,
|
|
"num_tokens": 12801438.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.419155597686768,
|
|
"epoch": 0.5365033621517772,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004978081943565067,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.1880238965153694,
|
|
"num_tokens": 12812425.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.426073837280273,
|
|
"epoch": 0.5369836695485111,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004978034181222261,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.18411885201931,
|
|
"num_tokens": 12824735.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.493219566345215,
|
|
"epoch": 0.537463976945245,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004977986367151119,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.18410976380109786,
|
|
"num_tokens": 12835454.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.491406679153442,
|
|
"epoch": 0.5379442843419788,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004977938501352747,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.17602443397045137,
|
|
"num_tokens": 12847086.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.488929605484008,
|
|
"epoch": 0.5384245917387128,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004977890583828259,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.18267697393894194,
|
|
"num_tokens": 12857713.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.415392827987671,
|
|
"epoch": 0.5389048991354467,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004977842614578768,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.1866528034210205,
|
|
"num_tokens": 12869967.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.494250965118408,
|
|
"epoch": 0.5393852065321806,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004977794593605386,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.18361620604991913,
|
|
"num_tokens": 12881230.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.402005004882812,
|
|
"epoch": 0.5398655139289145,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000497774652090923,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.18383389264345168,
|
|
"num_tokens": 12892376.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.511453294754029,
|
|
"epoch": 0.5403458213256485,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004977698396491414,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.18852853924036025,
|
|
"num_tokens": 12903709.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.340311717987061,
|
|
"epoch": 0.5408261287223823,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004977650220353055,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.1889250561594963,
|
|
"num_tokens": 12914958.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.3945904731750485,
|
|
"epoch": 0.5413064361191162,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004977601992495274,
|
|
"loss": 5.3405,
|
|
"mean_token_accuracy": 0.19035583436489106,
|
|
"num_tokens": 12927418.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.494799375534058,
|
|
"epoch": 0.5417867435158501,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977553712919189,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.18629820346832277,
|
|
"num_tokens": 12939874.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.4801758289337155,
|
|
"epoch": 0.5422670509125841,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004977505381625921,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.18406068682670593,
|
|
"num_tokens": 12951113.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.420956039428711,
|
|
"epoch": 0.542747358309318,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004977456998616593,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.19231484681367875,
|
|
"num_tokens": 12961940.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.364702749252319,
|
|
"epoch": 0.5432276657060519,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004977408563892327,
|
|
"loss": 5.3057,
|
|
"mean_token_accuracy": 0.18347083628177643,
|
|
"num_tokens": 12973938.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.4463921070098875,
|
|
"epoch": 0.5437079731027857,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004977360077454249,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.1936550334095955,
|
|
"num_tokens": 12985400.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.4479351997375485,
|
|
"epoch": 0.5441882804995197,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004977311539303483,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.19745397716760635,
|
|
"num_tokens": 12996402.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.347278833389282,
|
|
"epoch": 0.5446685878962536,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004977262949441158,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.1973622664809227,
|
|
"num_tokens": 13006991.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.4158118724822994,
|
|
"epoch": 0.5451488952929875,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004977214307868399,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.1877162501215935,
|
|
"num_tokens": 13016969.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.389847135543823,
|
|
"epoch": 0.5456292026897214,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000497716561458634,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.1943765476346016,
|
|
"num_tokens": 13027759.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.558808994293213,
|
|
"epoch": 0.5461095100864554,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004977116869596107,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.18179238438606263,
|
|
"num_tokens": 13039881.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.506471157073975,
|
|
"epoch": 0.5465898174831892,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004977068072898834,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.18669772446155547,
|
|
"num_tokens": 13051443.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.484284687042236,
|
|
"epoch": 0.5470701248799231,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004977019224495652,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.17737057507038118,
|
|
"num_tokens": 13063474.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.408006858825684,
|
|
"epoch": 0.547550432276657,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004976970324387698,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.198506860435009,
|
|
"num_tokens": 13074365.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.443795824050904,
|
|
"epoch": 0.548030739673391,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004976921372576104,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.1899048388004303,
|
|
"num_tokens": 13087354.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.414175224304199,
|
|
"epoch": 0.5485110470701249,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004976872369062011,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.1859481692314148,
|
|
"num_tokens": 13099306.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.4926599025726315,
|
|
"epoch": 0.5489913544668588,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004976823313846552,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.17889707237482072,
|
|
"num_tokens": 13111259.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.540021705627441,
|
|
"epoch": 0.5494716618635928,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004976774206930869,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.1789768472313881,
|
|
"num_tokens": 13123589.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.398435163497925,
|
|
"epoch": 0.5499519692603266,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004976725048316101,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.18425357192754746,
|
|
"num_tokens": 13136485.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.450462532043457,
|
|
"epoch": 0.5504322766570605,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004976675838003388,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.18509329855442047,
|
|
"num_tokens": 13148067.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.457958745956421,
|
|
"epoch": 0.5509125840537944,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004976626575993877,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.18458358198404312,
|
|
"num_tokens": 13159813.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.471329593658448,
|
|
"epoch": 0.5513928914505284,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004976577262288705,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.1858591079711914,
|
|
"num_tokens": 13170828.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.38016037940979,
|
|
"epoch": 0.5518731988472623,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004976527896889023,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.19918034821748734,
|
|
"num_tokens": 13181883.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.3633551597595215,
|
|
"epoch": 0.5523535062439962,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004976478479795974,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.19209487438201905,
|
|
"num_tokens": 13193530.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.506115436553955,
|
|
"epoch": 0.55283381364073,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004976429011010706,
|
|
"loss": 5.5431,
|
|
"mean_token_accuracy": 0.17332375347614287,
|
|
"num_tokens": 13205822.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.410343837738037,
|
|
"epoch": 0.553314121037464,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004976379490534366,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.19642258882522584,
|
|
"num_tokens": 13216698.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.427161312103271,
|
|
"epoch": 0.5537944284341979,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004976329918368107,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.18739383518695832,
|
|
"num_tokens": 13228389.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.503793430328369,
|
|
"epoch": 0.5542747358309318,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004976280294513079,
|
|
"loss": 5.4131,
|
|
"mean_token_accuracy": 0.17858489900827407,
|
|
"num_tokens": 13239628.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.483133363723755,
|
|
"epoch": 0.5547550432276657,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004976230618970431,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.18742662370204927,
|
|
"num_tokens": 13251149.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.5702611923217775,
|
|
"epoch": 0.5552353506243997,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000497618089174132,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.1794966369867325,
|
|
"num_tokens": 13264846.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.397415685653686,
|
|
"epoch": 0.5557156580211335,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004976131112826898,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.1930725798010826,
|
|
"num_tokens": 13275409.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.325386571884155,
|
|
"epoch": 0.5561959654178674,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004976081282228323,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.1947207883000374,
|
|
"num_tokens": 13287173.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.459070682525635,
|
|
"epoch": 0.5566762728146013,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497603139994675,
|
|
"loss": 5.31,
|
|
"mean_token_accuracy": 0.19227202236652374,
|
|
"num_tokens": 13298225.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.428604793548584,
|
|
"epoch": 0.5571565802113353,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004975981465983338,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.1896632730960846,
|
|
"num_tokens": 13309685.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.374756288528443,
|
|
"epoch": 0.5576368876080692,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004975931480339246,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.19549430906772614,
|
|
"num_tokens": 13320837.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.499799346923828,
|
|
"epoch": 0.5581171950048031,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004975881443015635,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.18693017661571504,
|
|
"num_tokens": 13333512.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.491879081726074,
|
|
"epoch": 0.5585975024015369,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004975831354013667,
|
|
"loss": 5.4607,
|
|
"mean_token_accuracy": 0.18330429941415788,
|
|
"num_tokens": 13345189.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.414880704879761,
|
|
"epoch": 0.5590778097982709,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004975781213334503,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.18983246982097626,
|
|
"num_tokens": 13356123.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.401202821731568,
|
|
"epoch": 0.5595581171950048,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004975731020979309,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.1871092990040779,
|
|
"num_tokens": 13366902.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.530173349380493,
|
|
"epoch": 0.5600384245917387,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004975680776949249,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.1845644235610962,
|
|
"num_tokens": 13377567.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.486733770370483,
|
|
"epoch": 0.5605187319884726,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004975630481245492,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.19489670991897584,
|
|
"num_tokens": 13387297.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.432850551605225,
|
|
"epoch": 0.5609990393852066,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004975580133869202,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.1909385144710541,
|
|
"num_tokens": 13397723.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.451133441925049,
|
|
"epoch": 0.5614793467819404,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004975529734821552,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.18235652148723602,
|
|
"num_tokens": 13409875.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.4372701168060305,
|
|
"epoch": 0.5619596541786743,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004975479284103708,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.187623094022274,
|
|
"num_tokens": 13421338.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.453873252868652,
|
|
"epoch": 0.5624399615754082,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004975428781716845,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.18782854378223418,
|
|
"num_tokens": 13431373.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.459550523757935,
|
|
"epoch": 0.5629202689721422,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004975378227662134,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.18972014784812927,
|
|
"num_tokens": 13443158.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.562433958053589,
|
|
"epoch": 0.5634005763688761,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004975327621940746,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.1824294939637184,
|
|
"num_tokens": 13454559.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.537427568435669,
|
|
"epoch": 0.56388088376561,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004975276964553861,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.18315037339925766,
|
|
"num_tokens": 13466934.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.42641019821167,
|
|
"epoch": 0.5643611911623438,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004975226255502651,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.193961800634861,
|
|
"num_tokens": 13477770.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.4611729145050045,
|
|
"epoch": 0.5648414985590778,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004975175494788297,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.17596953064203263,
|
|
"num_tokens": 13490093.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.532013177871704,
|
|
"epoch": 0.5653218059558117,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004975124682411974,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.1848944365978241,
|
|
"num_tokens": 13500663.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.470360279083252,
|
|
"epoch": 0.5658021133525456,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004975073818374863,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.1867206409573555,
|
|
"num_tokens": 13512369.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.437374830245972,
|
|
"epoch": 0.5662824207492796,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004975022902678145,
|
|
"loss": 5.334,
|
|
"mean_token_accuracy": 0.18200965970754623,
|
|
"num_tokens": 13523181.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.417144346237182,
|
|
"epoch": 0.5667627281460135,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004974971935323003,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.1899948462843895,
|
|
"num_tokens": 13534113.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.387775802612305,
|
|
"epoch": 0.5672430355427474,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004974920916310619,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.18716303408145904,
|
|
"num_tokens": 13545037.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.449446487426758,
|
|
"epoch": 0.5677233429394812,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004974869845642178,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.18605249971151352,
|
|
"num_tokens": 13555541.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.40853533744812,
|
|
"epoch": 0.5682036503362152,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004974818723318866,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.18721728920936584,
|
|
"num_tokens": 13566951.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.445446729660034,
|
|
"epoch": 0.5686839577329491,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004974767549341868,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.18748206049203872,
|
|
"num_tokens": 13578492.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.522714233398437,
|
|
"epoch": 0.569164265129683,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004974716323712376,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.19605986773967743,
|
|
"num_tokens": 13589183.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.477721214294434,
|
|
"epoch": 0.5696445725264169,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004974665046431576,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.187206406891346,
|
|
"num_tokens": 13600588.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.363747215270996,
|
|
"epoch": 0.5701248799231509,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004974613717500659,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.19260012060403825,
|
|
"num_tokens": 13612107.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.564688587188721,
|
|
"epoch": 0.5706051873198847,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004974562336920818,
|
|
"loss": 5.4877,
|
|
"mean_token_accuracy": 0.1817738100886345,
|
|
"num_tokens": 13623973.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.474991369247436,
|
|
"epoch": 0.5710854947166186,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004974510904693245,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.19045573920011521,
|
|
"num_tokens": 13634994.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.467713260650635,
|
|
"epoch": 0.5715658021133525,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004974459420819134,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.1847134292125702,
|
|
"num_tokens": 13646361.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.439850473403931,
|
|
"epoch": 0.5720461095100865,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000497440788529968,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.1893735870718956,
|
|
"num_tokens": 13656975.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.5145658493042,
|
|
"epoch": 0.5725264169068204,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004974356298136081,
|
|
"loss": 5.3887,
|
|
"mean_token_accuracy": 0.18407737463712692,
|
|
"num_tokens": 13668434.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.418645715713501,
|
|
"epoch": 0.5730067243035543,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004974304659329533,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.18530304580926896,
|
|
"num_tokens": 13679266.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.390876960754395,
|
|
"epoch": 0.5734870317002881,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004974252968881236,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.18427622318267822,
|
|
"num_tokens": 13690921.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.494585609436035,
|
|
"epoch": 0.5739673390970221,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000497420122679239,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.18745731115341185,
|
|
"num_tokens": 13702329.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.393915748596191,
|
|
"epoch": 0.574447646493756,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004974149433064196,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.1956883668899536,
|
|
"num_tokens": 13713356.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.365210914611817,
|
|
"epoch": 0.5749279538904899,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974097587697856,
|
|
"loss": 5.2783,
|
|
"mean_token_accuracy": 0.18870642334222792,
|
|
"num_tokens": 13724718.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.288666534423828,
|
|
"epoch": 0.5754082612872238,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004974045690694575,
|
|
"loss": 5.3244,
|
|
"mean_token_accuracy": 0.19229794144630433,
|
|
"num_tokens": 13736113.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.4823143005371096,
|
|
"epoch": 0.5758885686839578,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004973993742055557,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.19289510846138,
|
|
"num_tokens": 13748322.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.451804304122925,
|
|
"epoch": 0.5763688760806917,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004973941741782007,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.18272108733654022,
|
|
"num_tokens": 13759433.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5763688760806917,
|
|
"eval_entropy": 5.287622318216674,
|
|
"eval_loss": 5.3876953125,
|
|
"eval_mean_token_accuracy": 0.1935112771048219,
|
|
"eval_num_tokens": 13759433.0,
|
|
"eval_runtime": 26.6988,
|
|
"eval_samples_per_second": 1229.079,
|
|
"eval_steps_per_second": 153.64,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.357053565979004,
|
|
"epoch": 0.5768491834774255,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004973889689875135,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.1953121080994606,
|
|
"num_tokens": 13770181.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.408752727508545,
|
|
"epoch": 0.5773294908741594,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004973837586336147,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.18587519526481627,
|
|
"num_tokens": 13781792.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.420009994506836,
|
|
"epoch": 0.5778097982708934,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004973785431166254,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.18482285290956496,
|
|
"num_tokens": 13792101.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.372207736968994,
|
|
"epoch": 0.5782901056676273,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004973733224366666,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.18989176154136658,
|
|
"num_tokens": 13803640.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.4729570865631105,
|
|
"epoch": 0.5787704130643612,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004973680965938597,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.1922180876135826,
|
|
"num_tokens": 13815017.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.51697039604187,
|
|
"epoch": 0.579250720461095,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004973628655883258,
|
|
"loss": 5.5042,
|
|
"mean_token_accuracy": 0.1849636271595955,
|
|
"num_tokens": 13826119.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.4138994216918945,
|
|
"epoch": 0.579731027857829,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004973576294201865,
|
|
"loss": 5.3191,
|
|
"mean_token_accuracy": 0.18563202917575836,
|
|
"num_tokens": 13837869.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.614084625244141,
|
|
"epoch": 0.5802113352545629,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004973523880895633,
|
|
"loss": 5.4828,
|
|
"mean_token_accuracy": 0.18225589543581008,
|
|
"num_tokens": 13849333.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.511847114562988,
|
|
"epoch": 0.5806916426512968,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004973471415965779,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.18965902775526047,
|
|
"num_tokens": 13860648.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.516112518310547,
|
|
"epoch": 0.5811719500480308,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000497341889941352,
|
|
"loss": 5.4815,
|
|
"mean_token_accuracy": 0.1797430247068405,
|
|
"num_tokens": 13872979.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.413092756271363,
|
|
"epoch": 0.5816522574447647,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004973366331240078,
|
|
"loss": 5.369,
|
|
"mean_token_accuracy": 0.1896885961294174,
|
|
"num_tokens": 13884363.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.454212331771851,
|
|
"epoch": 0.5821325648414986,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000497331371144667,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.18695404082536698,
|
|
"num_tokens": 13895424.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.482513523101806,
|
|
"epoch": 0.5826128722382324,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004973261040034521,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.17660230100154878,
|
|
"num_tokens": 13907319.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.349012851715088,
|
|
"epoch": 0.5830931796349664,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004973208317004852,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.1929755389690399,
|
|
"num_tokens": 13920013.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.424505567550659,
|
|
"epoch": 0.5835734870317003,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004973155542358889,
|
|
"loss": 5.2867,
|
|
"mean_token_accuracy": 0.1894547238945961,
|
|
"num_tokens": 13932033.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.374952173233032,
|
|
"epoch": 0.5840537944284342,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004973102716097853,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.19180847108364105,
|
|
"num_tokens": 13943324.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.417754888534546,
|
|
"epoch": 0.5845341018251681,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004973049838222973,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.19688345044851302,
|
|
"num_tokens": 13954291.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.53399510383606,
|
|
"epoch": 0.5850144092219021,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004972996908735479,
|
|
"loss": 5.4855,
|
|
"mean_token_accuracy": 0.17760788947343825,
|
|
"num_tokens": 13966264.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.526733303070069,
|
|
"epoch": 0.585494716618636,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004972943927636597,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.18102135211229325,
|
|
"num_tokens": 13977785.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.3560892105102536,
|
|
"epoch": 0.5859750240153698,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004972890894927558,
|
|
"loss": 5.3513,
|
|
"mean_token_accuracy": 0.18770986050367355,
|
|
"num_tokens": 13989704.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.439371347427368,
|
|
"epoch": 0.5864553314121037,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004972837810609592,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.19178614616394044,
|
|
"num_tokens": 14000565.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.365533781051636,
|
|
"epoch": 0.5869356388088377,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004972784674683933,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.19611951857805252,
|
|
"num_tokens": 14011521.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.37313814163208,
|
|
"epoch": 0.5874159462055716,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004972731487151815,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.1963666558265686,
|
|
"num_tokens": 14022966.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.493708992004395,
|
|
"epoch": 0.5878962536023055,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004972678248014471,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.18432873338460923,
|
|
"num_tokens": 14034905.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.35796799659729,
|
|
"epoch": 0.5883765609990393,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004972624957273139,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.19322846382856368,
|
|
"num_tokens": 14045816.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.35459303855896,
|
|
"epoch": 0.5888568683957733,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004972571614929055,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.18595367074012756,
|
|
"num_tokens": 14057316.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.491276216506958,
|
|
"epoch": 0.5893371757925072,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004972518220983457,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.1800537422299385,
|
|
"num_tokens": 14067542.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.376386976242065,
|
|
"epoch": 0.5898174831892411,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004972464775437586,
|
|
"loss": 5.2497,
|
|
"mean_token_accuracy": 0.191409370303154,
|
|
"num_tokens": 14079467.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.334438943862915,
|
|
"epoch": 0.590297790585975,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004972411278292683,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.19782230406999587,
|
|
"num_tokens": 14090695.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.3625304222106935,
|
|
"epoch": 0.590778097982709,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004972357729549988,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.1956690177321434,
|
|
"num_tokens": 14101380.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.370040321350098,
|
|
"epoch": 0.5912584053794429,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004972304129210746,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.19186623096466066,
|
|
"num_tokens": 14112265.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.415378522872925,
|
|
"epoch": 0.5917387127761767,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004972250477276202,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.18848633915185928,
|
|
"num_tokens": 14124294.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.4126544952392575,
|
|
"epoch": 0.5922190201729106,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004972196773747599,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.19258213937282562,
|
|
"num_tokens": 14135230.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.485003852844239,
|
|
"epoch": 0.5926993275696446,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004972143018626186,
|
|
"loss": 5.4168,
|
|
"mean_token_accuracy": 0.18494608998298645,
|
|
"num_tokens": 14147576.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.388586807250976,
|
|
"epoch": 0.5931796349663785,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004972089211913211,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.19147883951663972,
|
|
"num_tokens": 14158834.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.4305541038513185,
|
|
"epoch": 0.5936599423631124,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972035353609923,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.18219966888427735,
|
|
"num_tokens": 14170694.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.417696857452393,
|
|
"epoch": 0.5941402497598463,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004971981443717572,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.18917144238948821,
|
|
"num_tokens": 14183184.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.487231588363647,
|
|
"epoch": 0.5946205571565802,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004971927482237409,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.18151831477880478,
|
|
"num_tokens": 14194761.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.3529094696044925,
|
|
"epoch": 0.5951008645533141,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004971873469170689,
|
|
"loss": 5.2486,
|
|
"mean_token_accuracy": 0.1928182139992714,
|
|
"num_tokens": 14205820.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.290451335906982,
|
|
"epoch": 0.595581171950048,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004971819404518664,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.19241809397935866,
|
|
"num_tokens": 14217826.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.3535737037658695,
|
|
"epoch": 0.5960614793467819,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000497176528828259,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19581965059041978,
|
|
"num_tokens": 14228632.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.452146100997925,
|
|
"epoch": 0.5965417867435159,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004971711120463722,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.18160438984632493,
|
|
"num_tokens": 14240231.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.535069513320923,
|
|
"epoch": 0.5970220941402498,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000497165690106332,
|
|
"loss": 5.3,
|
|
"mean_token_accuracy": 0.19084799885749817,
|
|
"num_tokens": 14251718.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.438978815078736,
|
|
"epoch": 0.5975024015369836,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004971602630082642,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.19391429871320726,
|
|
"num_tokens": 14263129.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.3131103515625,
|
|
"epoch": 0.5979827089337176,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004971548307522947,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.18711184114217758,
|
|
"num_tokens": 14274465.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.538304662704467,
|
|
"epoch": 0.5984630163304515,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004971493933385498,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.18774707913398742,
|
|
"num_tokens": 14286190.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.478298997879028,
|
|
"epoch": 0.5989433237271854,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004971439507671556,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.18472006171941757,
|
|
"num_tokens": 14297638.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.368980026245117,
|
|
"epoch": 0.5994236311239193,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004971385030382384,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.18834463655948638,
|
|
"num_tokens": 14309773.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.439523363113404,
|
|
"epoch": 0.5999039385206533,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004971330501519248,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.1911393091082573,
|
|
"num_tokens": 14320543.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.41556077003479,
|
|
"epoch": 0.6003842459173871,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004971275921083414,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.18108362406492234,
|
|
"num_tokens": 14332076.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.399434566497803,
|
|
"epoch": 0.600864553314121,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000497122128907615,
|
|
"loss": 5.2985,
|
|
"mean_token_accuracy": 0.18784073144197463,
|
|
"num_tokens": 14343768.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.407549285888672,
|
|
"epoch": 0.6013448607108549,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004971166605498722,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.1832826092839241,
|
|
"num_tokens": 14357051.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.461259746551514,
|
|
"epoch": 0.6018251681075889,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004971111870352401,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.18479823023080827,
|
|
"num_tokens": 14368800.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.486971426010132,
|
|
"epoch": 0.6023054755043228,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004971057083638458,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.19364019930362703,
|
|
"num_tokens": 14379617.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.355595588684082,
|
|
"epoch": 0.6027857829010567,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004971002245358166,
|
|
"loss": 5.297,
|
|
"mean_token_accuracy": 0.19656323492527009,
|
|
"num_tokens": 14391454.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.4019834995269775,
|
|
"epoch": 0.6032660902977905,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004970947355512795,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.19415158182382583,
|
|
"num_tokens": 14402379.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.375125885009766,
|
|
"epoch": 0.6037463976945245,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004970892414103622,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.1906362369656563,
|
|
"num_tokens": 14415040.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.424692058563233,
|
|
"epoch": 0.6042267050912584,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004970837421131921,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.18340786695480346,
|
|
"num_tokens": 14426677.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.423460483551025,
|
|
"epoch": 0.6047070124879923,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004970782376598972,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.1922990247607231,
|
|
"num_tokens": 14436676.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.462413024902344,
|
|
"epoch": 0.6051873198847262,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004970727280506048,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.18476360738277436,
|
|
"num_tokens": 14448294.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.38554277420044,
|
|
"epoch": 0.6056676272814602,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004970672132854431,
|
|
"loss": 5.3464,
|
|
"mean_token_accuracy": 0.180729740858078,
|
|
"num_tokens": 14460642.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.356734275817871,
|
|
"epoch": 0.6061479346781941,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004970616933645403,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.19817392230033876,
|
|
"num_tokens": 14471370.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.5012274265289305,
|
|
"epoch": 0.6066282420749279,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004970561682880242,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.18490924090147018,
|
|
"num_tokens": 14482358.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.429724407196045,
|
|
"epoch": 0.6071085494716618,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004970506380560233,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.188473641872406,
|
|
"num_tokens": 14494413.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.444656276702881,
|
|
"epoch": 0.6075888568683958,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004970451026686659,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.1973887041211128,
|
|
"num_tokens": 14506370.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.481788587570191,
|
|
"epoch": 0.6080691642651297,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004970395621260806,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.1924980342388153,
|
|
"num_tokens": 14517198.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.503510284423828,
|
|
"epoch": 0.6085494716618636,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000497034016428396,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.17975382953882219,
|
|
"num_tokens": 14529434.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.331223726272583,
|
|
"epoch": 0.6090297790585975,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004970284655757409,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.1927952289581299,
|
|
"num_tokens": 14540857.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.382576847076416,
|
|
"epoch": 0.6095100864553314,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004970229095682439,
|
|
"loss": 5.3292,
|
|
"mean_token_accuracy": 0.18967534154653548,
|
|
"num_tokens": 14552594.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.4875997543334964,
|
|
"epoch": 0.6099903938520653,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004970173484060344,
|
|
"loss": 5.38,
|
|
"mean_token_accuracy": 0.18148671090602875,
|
|
"num_tokens": 14563599.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.44437165260315,
|
|
"epoch": 0.6104707012487992,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004970117820892414,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.18892624825239182,
|
|
"num_tokens": 14575905.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.46058497428894,
|
|
"epoch": 0.6109510086455331,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004970062106179939,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.1898595690727234,
|
|
"num_tokens": 14587800.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.396344900131226,
|
|
"epoch": 0.6114313160422671,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004970006339924214,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.19229891896247864,
|
|
"num_tokens": 14600654.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.369927310943604,
|
|
"epoch": 0.611911623439001,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004969950522126534,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.19018779397010804,
|
|
"num_tokens": 14611985.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.354878950119018,
|
|
"epoch": 0.6123919308357348,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004969894652788196,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.19348015040159225,
|
|
"num_tokens": 14625004.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.457360696792603,
|
|
"epoch": 0.6128722382324687,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004969838731910494,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.19135722517967224,
|
|
"num_tokens": 14635381.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.369653367996216,
|
|
"epoch": 0.6133525456292027,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004969782759494729,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.19438933581113815,
|
|
"num_tokens": 14646582.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.354100608825684,
|
|
"epoch": 0.6138328530259366,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00049697267355422,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.19523880630731583,
|
|
"num_tokens": 14658024.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.549592161178589,
|
|
"epoch": 0.6143131604226705,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004969670660054208,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.18366368114948273,
|
|
"num_tokens": 14669933.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.455493974685669,
|
|
"epoch": 0.6147934678194045,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004969614533032054,
|
|
"loss": 5.3597,
|
|
"mean_token_accuracy": 0.18563628792762757,
|
|
"num_tokens": 14681331.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.326854848861695,
|
|
"epoch": 0.6152737752161384,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004969558354477041,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.19822522699832917,
|
|
"num_tokens": 14691361.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.361669921875,
|
|
"epoch": 0.6157540826128722,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004969502124390474,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.18852231353521348,
|
|
"num_tokens": 14701791.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.439621782302856,
|
|
"epoch": 0.6162343900096061,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004969445842773658,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.18183095902204513,
|
|
"num_tokens": 14713672.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.359001398086548,
|
|
"epoch": 0.6167146974063401,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00049693895096279,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.19406521171331406,
|
|
"num_tokens": 14724789.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.410259151458741,
|
|
"epoch": 0.617195004803074,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004969333124954508,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.18816329389810563,
|
|
"num_tokens": 14737212.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.340834140777588,
|
|
"epoch": 0.6176753121998079,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004969276688754791,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.18978990167379378,
|
|
"num_tokens": 14748387.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.376304864883423,
|
|
"epoch": 0.6181556195965417,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004969220201030059,
|
|
"loss": 5.3268,
|
|
"mean_token_accuracy": 0.18788918107748032,
|
|
"num_tokens": 14758477.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.478161859512329,
|
|
"epoch": 0.6186359269932757,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004969163661781624,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.19322396367788314,
|
|
"num_tokens": 14769650.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.391557788848877,
|
|
"epoch": 0.6191162343900096,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004969107071010798,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.1968097507953644,
|
|
"num_tokens": 14780988.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.456065464019775,
|
|
"epoch": 0.6195965417867435,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004969050428718895,
|
|
"loss": 5.3178,
|
|
"mean_token_accuracy": 0.19225712567567826,
|
|
"num_tokens": 14792458.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.474890804290771,
|
|
"epoch": 0.6200768491834774,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000496899373490723,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.18946533948183059,
|
|
"num_tokens": 14804772.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.48835506439209,
|
|
"epoch": 0.6205571565802114,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000496893698957712,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.18382560461759567,
|
|
"num_tokens": 14816126.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.480646705627441,
|
|
"epoch": 0.6210374639769453,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004968880192729882,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.18375624120235443,
|
|
"num_tokens": 14829376.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.385024547576904,
|
|
"epoch": 0.6215177713736791,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004968823344366835,
|
|
"loss": 5.2697,
|
|
"mean_token_accuracy": 0.1940453439950943,
|
|
"num_tokens": 14841098.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.396718311309814,
|
|
"epoch": 0.621998078770413,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004968766444489298,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.19451095908880234,
|
|
"num_tokens": 14852690.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.419198131561279,
|
|
"epoch": 0.622478386167147,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004968709493098593,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.19692527800798415,
|
|
"num_tokens": 14863327.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.440805530548095,
|
|
"epoch": 0.6229586935638809,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004968652490196041,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.18730003088712693,
|
|
"num_tokens": 14875213.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.42525053024292,
|
|
"epoch": 0.6234390009606148,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004968595435782967,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.19641293287277223,
|
|
"num_tokens": 14886129.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.544739007949829,
|
|
"epoch": 0.6239193083573487,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004968538329860695,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.1791739895939827,
|
|
"num_tokens": 14897217.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.486395263671875,
|
|
"epoch": 0.6243996157540826,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004968481172430549,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.1903992310166359,
|
|
"num_tokens": 14908438.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.3397129535675045,
|
|
"epoch": 0.6248799231508165,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000496842396349386,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.19306804239749908,
|
|
"num_tokens": 14920472.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.379376220703125,
|
|
"epoch": 0.6253602305475504,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004968366703051952,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.19095073789358138,
|
|
"num_tokens": 14932075.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.4581060886383055,
|
|
"epoch": 0.6258405379442843,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004968309391106157,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.19246679097414016,
|
|
"num_tokens": 14942971.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.439628076553345,
|
|
"epoch": 0.6263208453410183,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004968252027657806,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.19625172168016433,
|
|
"num_tokens": 14954288.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.284691047668457,
|
|
"epoch": 0.6268011527377522,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004968194612708229,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.19190774559974672,
|
|
"num_tokens": 14966017.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.403012323379516,
|
|
"epoch": 0.627281460134486,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004968137146258759,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.1942574456334114,
|
|
"num_tokens": 14978022.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.375046253204346,
|
|
"epoch": 0.6277617675312199,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004968079628310732,
|
|
"loss": 5.2536,
|
|
"mean_token_accuracy": 0.19315956383943558,
|
|
"num_tokens": 14990370.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.3779456615448,
|
|
"epoch": 0.6282420749279539,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004968022058865482,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.19746362715959548,
|
|
"num_tokens": 15001535.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.514092206954956,
|
|
"epoch": 0.6287223823246878,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004967964437924346,
|
|
"loss": 5.3537,
|
|
"mean_token_accuracy": 0.1910748988389969,
|
|
"num_tokens": 15012560.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.358428001403809,
|
|
"epoch": 0.6292026897214217,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004967906765488662,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.19692065715789794,
|
|
"num_tokens": 15024594.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.355824136734009,
|
|
"epoch": 0.6296829971181557,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004967849041559769,
|
|
"loss": 5.2758,
|
|
"mean_token_accuracy": 0.19033686816692352,
|
|
"num_tokens": 15034735.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.439026117324829,
|
|
"epoch": 0.6301633045148896,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004967791266139006,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.18297341614961624,
|
|
"num_tokens": 15046955.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.4186070442199705,
|
|
"epoch": 0.6306436119116234,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004967733439227716,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.19243780374526978,
|
|
"num_tokens": 15058250.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.439732599258423,
|
|
"epoch": 0.6311239193083573,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000496767556082724,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.18913595825433732,
|
|
"num_tokens": 15069451.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.436646747589111,
|
|
"epoch": 0.6316042267050913,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004967617630938924,
|
|
"loss": 5.3492,
|
|
"mean_token_accuracy": 0.19468814730644227,
|
|
"num_tokens": 15080920.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.390475034713745,
|
|
"epoch": 0.6320845341018252,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000496755964956411,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.18934084475040436,
|
|
"num_tokens": 15091579.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.43261489868164,
|
|
"epoch": 0.6325648414985591,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004967501616704147,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.18936194330453873,
|
|
"num_tokens": 15103097.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.368798923492432,
|
|
"epoch": 0.633045148895293,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000496744353236038,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.1917736351490021,
|
|
"num_tokens": 15114646.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.476302003860473,
|
|
"epoch": 0.633525456292027,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000496738539653416,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.189273464679718,
|
|
"num_tokens": 15126019.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.442473554611206,
|
|
"epoch": 0.6340057636887608,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004967327209226835,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.18826874792575837,
|
|
"num_tokens": 15136132.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.4540853023529055,
|
|
"epoch": 0.6344860710854947,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004967268970439755,
|
|
"loss": 5.4127,
|
|
"mean_token_accuracy": 0.18535282611846923,
|
|
"num_tokens": 15149016.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.495935010910034,
|
|
"epoch": 0.6349663784822286,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004967210680174274,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.19302425384521485,
|
|
"num_tokens": 15160302.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.392695713043213,
|
|
"epoch": 0.6354466858789626,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004967152338431745,
|
|
"loss": 5.349,
|
|
"mean_token_accuracy": 0.18540611267089843,
|
|
"num_tokens": 15171770.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.387290954589844,
|
|
"epoch": 0.6359269932756965,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004967093945213523,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.19330676943063735,
|
|
"num_tokens": 15182283.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.393410491943359,
|
|
"epoch": 0.6364073006724303,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004967035500520962,
|
|
"loss": 5.3362,
|
|
"mean_token_accuracy": 0.19362882375717164,
|
|
"num_tokens": 15193917.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.548230218887329,
|
|
"epoch": 0.6368876080691642,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004966977004355421,
|
|
"loss": 5.415,
|
|
"mean_token_accuracy": 0.18277304470539094,
|
|
"num_tokens": 15205854.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.353105592727661,
|
|
"epoch": 0.6373679154658982,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004966918456718256,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.19419651329517365,
|
|
"num_tokens": 15217884.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.449846410751343,
|
|
"epoch": 0.6378482228626321,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004966859857610828,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.18877679854631424,
|
|
"num_tokens": 15229493.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.435251140594483,
|
|
"epoch": 0.638328530259366,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004966801207034497,
|
|
"loss": 5.3601,
|
|
"mean_token_accuracy": 0.18677332997322083,
|
|
"num_tokens": 15241402.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.477271270751953,
|
|
"epoch": 0.6388088376560999,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004966742504990624,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.19029135406017303,
|
|
"num_tokens": 15252981.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.460357427597046,
|
|
"epoch": 0.6392891450528339,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004966683751480572,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.19481291621923447,
|
|
"num_tokens": 15264171.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.412302494049072,
|
|
"epoch": 0.6397694524495677,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004966624946505706,
|
|
"loss": 5.2967,
|
|
"mean_token_accuracy": 0.19341345578432084,
|
|
"num_tokens": 15275595.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.432217454910278,
|
|
"epoch": 0.6402497598463016,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004966566090067391,
|
|
"loss": 5.3704,
|
|
"mean_token_accuracy": 0.18972284495830535,
|
|
"num_tokens": 15286074.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.48450288772583,
|
|
"epoch": 0.6407300672430355,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004966507182166993,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.1897859662771225,
|
|
"num_tokens": 15296230.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.43498387336731,
|
|
"epoch": 0.6412103746397695,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000496644822280588,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.19209778010845185,
|
|
"num_tokens": 15307428.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.4863481521606445,
|
|
"epoch": 0.6416906820365034,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000496638921198542,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.18019873797893524,
|
|
"num_tokens": 15318796.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.381554126739502,
|
|
"epoch": 0.6421709894332372,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004966330149706984,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.19566068947315216,
|
|
"num_tokens": 15330914.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.371698093414307,
|
|
"epoch": 0.6426512968299711,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004966271035971944,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.18286263048648835,
|
|
"num_tokens": 15341756.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.490469074249267,
|
|
"epoch": 0.6431316042267051,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004966211870781671,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.18412328213453294,
|
|
"num_tokens": 15353217.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.439953327178955,
|
|
"epoch": 0.643611911623439,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000496615265413754,
|
|
"loss": 5.2812,
|
|
"mean_token_accuracy": 0.18626564890146255,
|
|
"num_tokens": 15363813.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.393799257278443,
|
|
"epoch": 0.6440922190201729,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004966093386040923,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.19141743332147598,
|
|
"num_tokens": 15375223.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.41720404624939,
|
|
"epoch": 0.6445725264169068,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00049660340664932,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.1908285066485405,
|
|
"num_tokens": 15385523.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.481564664840699,
|
|
"epoch": 0.6450528338136408,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004965974695495746,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.1851609691977501,
|
|
"num_tokens": 15397262.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.320267534255981,
|
|
"epoch": 0.6455331412103746,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004965915273049938,
|
|
"loss": 5.2749,
|
|
"mean_token_accuracy": 0.1933172568678856,
|
|
"num_tokens": 15409043.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.392423868179321,
|
|
"epoch": 0.6460134486071085,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004965855799157158,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.19334859997034073,
|
|
"num_tokens": 15420859.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.492722368240356,
|
|
"epoch": 0.6464937560038425,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004965796273818787,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.18350023329257964,
|
|
"num_tokens": 15433650.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.414972400665283,
|
|
"epoch": 0.6469740634005764,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004965736697036206,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.18937459141016005,
|
|
"num_tokens": 15445158.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.447385358810425,
|
|
"epoch": 0.6474543707973103,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004965677068810798,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.1803368479013443,
|
|
"num_tokens": 15456974.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.537943935394287,
|
|
"epoch": 0.6479346781940442,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004965617389143947,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.18926629722118377,
|
|
"num_tokens": 15467395.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.412473583221436,
|
|
"epoch": 0.6484149855907781,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000496555765803704,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.1906597323715687,
|
|
"num_tokens": 15479396.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.426792955398559,
|
|
"epoch": 0.648895292987512,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004965497875491462,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.1942463994026184,
|
|
"num_tokens": 15490992.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.5669855117797855,
|
|
"epoch": 0.6493756003842459,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004965438041508604,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.17857103943824768,
|
|
"num_tokens": 15502413.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.420809364318847,
|
|
"epoch": 0.6498559077809798,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004965378156089851,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.18572657257318498,
|
|
"num_tokens": 15512588.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.395385265350342,
|
|
"epoch": 0.6503362151777138,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004965318219236597,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.18925640136003494,
|
|
"num_tokens": 15523252.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.410533332824707,
|
|
"epoch": 0.6508165225744477,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004965258230950232,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.18793747574090958,
|
|
"num_tokens": 15534975.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.421842384338379,
|
|
"epoch": 0.6512968299711815,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004965198191232148,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.19612715244293213,
|
|
"num_tokens": 15545709.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.436142206192017,
|
|
"epoch": 0.6517771373679154,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000496513810008374,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.19046129435300826,
|
|
"num_tokens": 15557270.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.4739344120025635,
|
|
"epoch": 0.6522574447646494,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004965077957506403,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.18898641914129258,
|
|
"num_tokens": 15569156.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.407978582382202,
|
|
"epoch": 0.6527377521613833,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004965017763501533,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.19041388630867004,
|
|
"num_tokens": 15579270.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.30359902381897,
|
|
"epoch": 0.6532180595581172,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004964957518070529,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.19937118589878083,
|
|
"num_tokens": 15589912.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.385896635055542,
|
|
"epoch": 0.6536983669548511,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004964897221214788,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.1895860731601715,
|
|
"num_tokens": 15601088.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.548845958709717,
|
|
"epoch": 0.654178674351585,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000496483687293571,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.18972813487052917,
|
|
"num_tokens": 15612520.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.396096706390381,
|
|
"epoch": 0.6546589817483189,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004964776473234696,
|
|
"loss": 5.2776,
|
|
"mean_token_accuracy": 0.20008952766656876,
|
|
"num_tokens": 15623991.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.269886445999146,
|
|
"epoch": 0.6551392891450528,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000496471602211315,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.1977632984519005,
|
|
"num_tokens": 15635389.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.394750165939331,
|
|
"epoch": 0.6556195965417867,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004964655519572475,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.19477542787790297,
|
|
"num_tokens": 15646427.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.331007289886474,
|
|
"epoch": 0.6560999039385207,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004964594965614072,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.18943443447351455,
|
|
"num_tokens": 15657518.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.4607117652893065,
|
|
"epoch": 0.6565802113352546,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004964534360239353,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.18536604195833206,
|
|
"num_tokens": 15669775.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.453538179397583,
|
|
"epoch": 0.6570605187319885,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000496447370344972,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.18184838742017745,
|
|
"num_tokens": 15682566.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.391561031341553,
|
|
"epoch": 0.6575408261287223,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004964412995246584,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.19193878918886184,
|
|
"num_tokens": 15693168.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.411485433578491,
|
|
"epoch": 0.6580211335254563,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004964352235631354,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.19338710755109786,
|
|
"num_tokens": 15703879.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.466008567810059,
|
|
"epoch": 0.6585014409221902,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000496429142460544,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.18269607722759246,
|
|
"num_tokens": 15716015.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.513949155807495,
|
|
"epoch": 0.6589817483189241,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004964230562170254,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.1902955502271652,
|
|
"num_tokens": 15728254.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.440059947967529,
|
|
"epoch": 0.659462055715658,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004964169648327209,
|
|
"loss": 5.3372,
|
|
"mean_token_accuracy": 0.19121697098016738,
|
|
"num_tokens": 15738778.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.496658658981323,
|
|
"epoch": 0.659942363112392,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000496410868307772,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.18916360884904862,
|
|
"num_tokens": 15750305.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.464032173156738,
|
|
"epoch": 0.6604226705091258,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004964047666423203,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.19020300060510636,
|
|
"num_tokens": 15761303.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.38676176071167,
|
|
"epoch": 0.6609029779058597,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004963986598365072,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.19783349931240082,
|
|
"num_tokens": 15773095.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.4643943309783936,
|
|
"epoch": 0.6613832853025937,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004963925478904746,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.19114467054605483,
|
|
"num_tokens": 15784405.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.339839839935303,
|
|
"epoch": 0.6618635926993276,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004963864308043645,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.1876211866736412,
|
|
"num_tokens": 15795178.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.362161684036255,
|
|
"epoch": 0.6623439000960615,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004963803085783189,
|
|
"loss": 5.2876,
|
|
"mean_token_accuracy": 0.1926844075322151,
|
|
"num_tokens": 15806205.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.371932125091552,
|
|
"epoch": 0.6628242074927954,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004963741812124799,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.19651996344327927,
|
|
"num_tokens": 15817474.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.403625106811523,
|
|
"epoch": 0.6633045148895294,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004963680487069898,
|
|
"loss": 5.3257,
|
|
"mean_token_accuracy": 0.18721811026334761,
|
|
"num_tokens": 15829728.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.4906658172607425,
|
|
"epoch": 0.6637848222862632,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004963619110619908,
|
|
"loss": 5.3962,
|
|
"mean_token_accuracy": 0.18898224979639053,
|
|
"num_tokens": 15840082.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.403733205795288,
|
|
"epoch": 0.6642651296829971,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004963557682776256,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.19132282733917236,
|
|
"num_tokens": 15851450.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.47521448135376,
|
|
"epoch": 0.664745437079731,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004963496203540368,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.18462074249982835,
|
|
"num_tokens": 15864168.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.529342889785767,
|
|
"epoch": 0.665225744476465,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004963434672913671,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.1934638351202011,
|
|
"num_tokens": 15875634.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.490385866165161,
|
|
"epoch": 0.6657060518731989,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004963373090897592,
|
|
"loss": 5.3898,
|
|
"mean_token_accuracy": 0.1816974997520447,
|
|
"num_tokens": 15888411.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.412318086624145,
|
|
"epoch": 0.6661863592699327,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004963311457493563,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.18437298983335496,
|
|
"num_tokens": 15901084.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.532782173156738,
|
|
"epoch": 0.6666666666666666,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004963249772703015,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.18226184099912643,
|
|
"num_tokens": 15912061.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.445433712005615,
|
|
"epoch": 0.6671469740634006,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004963188036527378,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.18681012839078903,
|
|
"num_tokens": 15925439.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.334096050262451,
|
|
"epoch": 0.6676272814601345,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004963126248968087,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.20017411112785338,
|
|
"num_tokens": 15937762.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.36285719871521,
|
|
"epoch": 0.6681075888568684,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004963064410026577,
|
|
"loss": 5.2164,
|
|
"mean_token_accuracy": 0.19785531610250473,
|
|
"num_tokens": 15948656.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.491459655761719,
|
|
"epoch": 0.6685878962536023,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004963002519704281,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.1837204158306122,
|
|
"num_tokens": 15960376.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.424830055236816,
|
|
"epoch": 0.6690682036503363,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000496294057800264,
|
|
"loss": 5.3369,
|
|
"mean_token_accuracy": 0.18562808632850647,
|
|
"num_tokens": 15971913.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.438348913192749,
|
|
"epoch": 0.6695485110470701,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004962878584923089,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.17853061258792877,
|
|
"num_tokens": 15984775.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.459320211410523,
|
|
"epoch": 0.670028818443804,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004962816540467068,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.18482270687818528,
|
|
"num_tokens": 15996717.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.432131767272949,
|
|
"epoch": 0.6705091258405379,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004962754444636017,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.19075636565685272,
|
|
"num_tokens": 16007964.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.360487699508667,
|
|
"epoch": 0.6709894332372719,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000496269229743138,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.18819989114999772,
|
|
"num_tokens": 16019185.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.445584106445312,
|
|
"epoch": 0.6714697406340058,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004962630098854597,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.19621512144804001,
|
|
"num_tokens": 16029983.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.413072967529297,
|
|
"epoch": 0.6719500480307397,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004962567848907113,
|
|
"loss": 5.2451,
|
|
"mean_token_accuracy": 0.1927248239517212,
|
|
"num_tokens": 16040574.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.455062007904052,
|
|
"epoch": 0.6724303554274735,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004962505547590374,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.18644539266824722,
|
|
"num_tokens": 16052037.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.428081893920899,
|
|
"epoch": 0.6729106628242075,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004962443194905826,
|
|
"loss": 5.3729,
|
|
"mean_token_accuracy": 0.183872027695179,
|
|
"num_tokens": 16063413.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.433167314529419,
|
|
"epoch": 0.6733909702209414,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004962380790854916,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.18665792793035507,
|
|
"num_tokens": 16074373.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.4718366146087645,
|
|
"epoch": 0.6738712776176753,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004962318335439094,
|
|
"loss": 5.4101,
|
|
"mean_token_accuracy": 0.18109694719314576,
|
|
"num_tokens": 16086575.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.421692037582398,
|
|
"epoch": 0.6743515850144092,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004962255828659809,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.1897415041923523,
|
|
"num_tokens": 16098529.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.377682685852051,
|
|
"epoch": 0.6748318924111432,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004962193270518513,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.19679708331823348,
|
|
"num_tokens": 16110085.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.400438213348389,
|
|
"epoch": 0.675312199807877,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004962130661016659,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.19395572245121,
|
|
"num_tokens": 16120249.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.467017364501953,
|
|
"epoch": 0.6757925072046109,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004962068000155699,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.17520357817411422,
|
|
"num_tokens": 16132645.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.4300931930542,
|
|
"epoch": 0.6762728146013448,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004962005287937088,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.1908533677458763,
|
|
"num_tokens": 16143808.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.417350339889526,
|
|
"epoch": 0.6767531219980788,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004961942524362283,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.19097587019205092,
|
|
"num_tokens": 16154309.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.439221620559692,
|
|
"epoch": 0.6772334293948127,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004961879709432741,
|
|
"loss": 5.2788,
|
|
"mean_token_accuracy": 0.18384848684072494,
|
|
"num_tokens": 16164654.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.494296836853027,
|
|
"epoch": 0.6777137367915466,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000496181684314992,
|
|
"loss": 5.3557,
|
|
"mean_token_accuracy": 0.18831141740083696,
|
|
"num_tokens": 16177837.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.381369876861572,
|
|
"epoch": 0.6781940441882806,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004961753925515279,
|
|
"loss": 5.2451,
|
|
"mean_token_accuracy": 0.19840732365846633,
|
|
"num_tokens": 16189073.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.5010161876678465,
|
|
"epoch": 0.6786743515850144,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000496169095653028,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.1846903681755066,
|
|
"num_tokens": 16200371.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.425731134414673,
|
|
"epoch": 0.6791546589817483,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004961627936196384,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.1927168995141983,
|
|
"num_tokens": 16210526.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.420339298248291,
|
|
"epoch": 0.6796349663784822,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004961564864515055,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.1907577857375145,
|
|
"num_tokens": 16221687.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.344882965087891,
|
|
"epoch": 0.6801152737752162,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004961501741487757,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.19812528938055038,
|
|
"num_tokens": 16233828.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.353463506698608,
|
|
"epoch": 0.6805955811719501,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004961438567115955,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.20078285932540893,
|
|
"num_tokens": 16243900.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.3441691398620605,
|
|
"epoch": 0.681075888568684,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004961375341401116,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.19146115332841873,
|
|
"num_tokens": 16256347.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.340963888168335,
|
|
"epoch": 0.6815561959654178,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004961312064344708,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.19417633563280107,
|
|
"num_tokens": 16267743.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.286987924575806,
|
|
"epoch": 0.6820365033621518,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00049612487359482,
|
|
"loss": 5.2378,
|
|
"mean_token_accuracy": 0.19621652811765672,
|
|
"num_tokens": 16278280.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.308349514007569,
|
|
"epoch": 0.6825168107588857,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004961185356213062,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.1986348956823349,
|
|
"num_tokens": 16288568.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.3843225002288815,
|
|
"epoch": 0.6829971181556196,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004961121925140767,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.19194537848234178,
|
|
"num_tokens": 16300730.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.416932916641235,
|
|
"epoch": 0.6834774255523535,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004961058442732786,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.18604491353034974,
|
|
"num_tokens": 16311789.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.397182607650757,
|
|
"epoch": 0.6839577329490875,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004960994908990594,
|
|
"loss": 5.3034,
|
|
"mean_token_accuracy": 0.18527194410562514,
|
|
"num_tokens": 16324439.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.507112216949463,
|
|
"epoch": 0.6844380403458213,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004960931323915665,
|
|
"loss": 5.4178,
|
|
"mean_token_accuracy": 0.19717762768268585,
|
|
"num_tokens": 16335344.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.425092267990112,
|
|
"epoch": 0.6849183477425552,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004960867687509475,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.1947552040219307,
|
|
"num_tokens": 16349018.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.406477355957032,
|
|
"epoch": 0.6853986551392891,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004960803999773504,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.18694589883089066,
|
|
"num_tokens": 16360137.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.458607006072998,
|
|
"epoch": 0.6858789625360231,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004960740260709228,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.18401143401861192,
|
|
"num_tokens": 16372277.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.4775834560394285,
|
|
"epoch": 0.686359269932757,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004960676470318128,
|
|
"loss": 5.3482,
|
|
"mean_token_accuracy": 0.18985600471496583,
|
|
"num_tokens": 16383440.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.465761423110962,
|
|
"epoch": 0.6868395773294909,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004960612628601683,
|
|
"loss": 5.334,
|
|
"mean_token_accuracy": 0.18960196971893312,
|
|
"num_tokens": 16394330.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.314107084274292,
|
|
"epoch": 0.6873198847262247,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004960548735561379,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.19742396026849746,
|
|
"num_tokens": 16405734.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.413222217559815,
|
|
"epoch": 0.6878001921229587,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004960484791198697,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.19005996584892274,
|
|
"num_tokens": 16416025.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.3849324703216555,
|
|
"epoch": 0.6882804995196926,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004960420795515121,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.18683192282915115,
|
|
"num_tokens": 16427416.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.364479303359985,
|
|
"epoch": 0.6887608069164265,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004960356748512138,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.19363223165273666,
|
|
"num_tokens": 16438073.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.39097113609314,
|
|
"epoch": 0.6892411143131604,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004960292650191236,
|
|
"loss": 5.2191,
|
|
"mean_token_accuracy": 0.19252923727035523,
|
|
"num_tokens": 16449994.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.354184198379516,
|
|
"epoch": 0.6897214217098944,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004960228500553899,
|
|
"loss": 5.2241,
|
|
"mean_token_accuracy": 0.20535511523485184,
|
|
"num_tokens": 16460355.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.42663426399231,
|
|
"epoch": 0.6902017291066282,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004960164299601623,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.1861085534095764,
|
|
"num_tokens": 16472274.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.47387843132019,
|
|
"epoch": 0.6906820365033621,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004960100047335892,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.1927446484565735,
|
|
"num_tokens": 16482959.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.443005132675171,
|
|
"epoch": 0.691162343900096,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004960035743758202,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.1826966032385826,
|
|
"num_tokens": 16494533.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.353251791000366,
|
|
"epoch": 0.69164265129683,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004959971388870044,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.19136521071195603,
|
|
"num_tokens": 16506124.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.358429765701294,
|
|
"epoch": 0.6921229586935639,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004959906982672912,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.18939739614725112,
|
|
"num_tokens": 16517867.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.3140510559082035,
|
|
"epoch": 0.6926032660902978,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004959842525168302,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.1981380447745323,
|
|
"num_tokens": 16529075.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.425293970108032,
|
|
"epoch": 0.6930835734870316,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004959778016357712,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.1942730277776718,
|
|
"num_tokens": 16540326.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.42542576789856,
|
|
"epoch": 0.6935638808837656,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004959713456242637,
|
|
"loss": 5.2857,
|
|
"mean_token_accuracy": 0.19006777107715606,
|
|
"num_tokens": 16551570.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.429000568389893,
|
|
"epoch": 0.6940441882804995,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004959648844824576,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.18575582951307296,
|
|
"num_tokens": 16562636.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.400074148178101,
|
|
"epoch": 0.6945244956772334,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004959584182105032,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.19248428493738173,
|
|
"num_tokens": 16573867.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.362949848175049,
|
|
"epoch": 0.6950048030739674,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004959519468085504,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.20341502279043197,
|
|
"num_tokens": 16584533.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.385730648040772,
|
|
"epoch": 0.6954851104707013,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004959454702767494,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.1950566962361336,
|
|
"num_tokens": 16596562.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.424708366394043,
|
|
"epoch": 0.6959654178674352,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004959389886152507,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.19886927157640458,
|
|
"num_tokens": 16607508.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.366083097457886,
|
|
"epoch": 0.696445725264169,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004959325018242048,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.1924608454108238,
|
|
"num_tokens": 16617737.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.427731084823608,
|
|
"epoch": 0.696926032660903,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004959260099037622,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.18845672458410262,
|
|
"num_tokens": 16628518.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.47143440246582,
|
|
"epoch": 0.6974063400576369,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004959195128540737,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.18321446776390077,
|
|
"num_tokens": 16639644.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.538464069366455,
|
|
"epoch": 0.6978866474543708,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00049591301067529,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.17454033493995666,
|
|
"num_tokens": 16650882.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.501030111312867,
|
|
"epoch": 0.6983669548511047,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004959065033675623,
|
|
"loss": 5.3394,
|
|
"mean_token_accuracy": 0.18889677673578262,
|
|
"num_tokens": 16662464.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.4669442653656,
|
|
"epoch": 0.6988472622478387,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004958999909310414,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.18427836000919343,
|
|
"num_tokens": 16673718.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.355691766738891,
|
|
"epoch": 0.6993275696445725,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004958934733658788,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.1897352620959282,
|
|
"num_tokens": 16684957.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.398211526870727,
|
|
"epoch": 0.6998078770413064,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004958869506722256,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.19128641486167908,
|
|
"num_tokens": 16695782.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.462493753433227,
|
|
"epoch": 0.7002881844380403,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004958804228502332,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.20094609260559082,
|
|
"num_tokens": 16707448.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.364071226119995,
|
|
"epoch": 0.7007684918347743,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004958738899000534,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.18903368413448335,
|
|
"num_tokens": 16718074.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.393236875534058,
|
|
"epoch": 0.7012487992315082,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004958673518218377,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.19744063764810563,
|
|
"num_tokens": 16728656.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.3618604183197025,
|
|
"epoch": 0.7017291066282421,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004958608086157379,
|
|
"loss": 5.3479,
|
|
"mean_token_accuracy": 0.1934794917702675,
|
|
"num_tokens": 16740703.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.366200160980225,
|
|
"epoch": 0.7022094140249759,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000495854260281906,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.19950000196695328,
|
|
"num_tokens": 16753320.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.324510526657105,
|
|
"epoch": 0.7026897214217099,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004958477068204941,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.19531755298376083,
|
|
"num_tokens": 16764889.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.492941284179688,
|
|
"epoch": 0.7031700288184438,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000495841148231654,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.19673400819301606,
|
|
"num_tokens": 16776301.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.4144305229187015,
|
|
"epoch": 0.7036503362151777,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004958345845155383,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.20224857926368714,
|
|
"num_tokens": 16786935.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.361083364486694,
|
|
"epoch": 0.7041306436119116,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004958280156722992,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.18941789865493774,
|
|
"num_tokens": 16799335.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.315510654449463,
|
|
"epoch": 0.7046109510086456,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004958214417020894,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.1952172815799713,
|
|
"num_tokens": 16811376.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.447247457504273,
|
|
"epoch": 0.7050912584053795,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004958148626050614,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.1868259444832802,
|
|
"num_tokens": 16822859.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.386044549942016,
|
|
"epoch": 0.7055715658021133,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.18494077026844025,
|
|
"num_tokens": 16833831.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.416794347763061,
|
|
"epoch": 0.7060518731988472,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.000495801689031162,
|
|
"loss": 5.3178,
|
|
"mean_token_accuracy": 0.18923115581274033,
|
|
"num_tokens": 16846827.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.427305555343628,
|
|
"epoch": 0.7065321805955812,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004957950945545965,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.19124404191970826,
|
|
"num_tokens": 16858166.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.423590469360351,
|
|
"epoch": 0.7070124879923151,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004957884949518246,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.17632461786270143,
|
|
"num_tokens": 16870201.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.4485126495361325,
|
|
"epoch": 0.707492795389049,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004957818902229992,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.1914941743016243,
|
|
"num_tokens": 16880891.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.443580579757691,
|
|
"epoch": 0.7079731027857828,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004957752803682741,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.18744525611400603,
|
|
"num_tokens": 16893498.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.430360507965088,
|
|
"epoch": 0.7084534101825168,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004957686653878024,
|
|
"loss": 5.3235,
|
|
"mean_token_accuracy": 0.19000324606895447,
|
|
"num_tokens": 16904959.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.475503158569336,
|
|
"epoch": 0.7089337175792507,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000495762045281738,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.19178977906703948,
|
|
"num_tokens": 16916547.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.379904556274414,
|
|
"epoch": 0.7094140249759846,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004957554200502344,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.19259582757949828,
|
|
"num_tokens": 16928580.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.42095365524292,
|
|
"epoch": 0.7098943323727186,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004957487896934454,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.19163490682840348,
|
|
"num_tokens": 16941247.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.471564817428589,
|
|
"epoch": 0.7103746397694525,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000495742154211525,
|
|
"loss": 5.3459,
|
|
"mean_token_accuracy": 0.19166067987680435,
|
|
"num_tokens": 16951119.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.4357222557067875,
|
|
"epoch": 0.7108549471661864,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004957355136046272,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.19560655504465102,
|
|
"num_tokens": 16962608.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.4040158748626705,
|
|
"epoch": 0.7113352545629202,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004957288678729064,
|
|
"loss": 5.2887,
|
|
"mean_token_accuracy": 0.19282960295677185,
|
|
"num_tokens": 16973291.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.464023637771606,
|
|
"epoch": 0.7118155619596542,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004957222170165166,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.18538960367441176,
|
|
"num_tokens": 16984895.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.437390518188477,
|
|
"epoch": 0.7122958693563881,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004957155610356124,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.1851879209280014,
|
|
"num_tokens": 16997109.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.402000808715821,
|
|
"epoch": 0.712776176753122,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004957088999303481,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.1896701619029045,
|
|
"num_tokens": 17008640.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.393481206893921,
|
|
"epoch": 0.7132564841498559,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004957022337008787,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.19272141605615617,
|
|
"num_tokens": 17018924.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.385486221313476,
|
|
"epoch": 0.7137367915465899,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004956955623473587,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.19193373024463653,
|
|
"num_tokens": 17029932.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.432203769683838,
|
|
"epoch": 0.7142170989433237,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000495688885869943,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.18896414786577226,
|
|
"num_tokens": 17042164.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.427480697631836,
|
|
"epoch": 0.7146974063400576,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004956822042687868,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.18362648636102677,
|
|
"num_tokens": 17054729.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.368029499053955,
|
|
"epoch": 0.7151777137367915,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004956755175440451,
|
|
"loss": 5.2207,
|
|
"mean_token_accuracy": 0.2035231813788414,
|
|
"num_tokens": 17066537.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.361916732788086,
|
|
"epoch": 0.7156580211335255,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004956688256958731,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.19434696584939956,
|
|
"num_tokens": 17077787.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.387641763687133,
|
|
"epoch": 0.7161383285302594,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004956621287244262,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.19008096903562546,
|
|
"num_tokens": 17089555.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.490763998031616,
|
|
"epoch": 0.7166186359269933,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004956554266298599,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.19534847438335418,
|
|
"num_tokens": 17099911.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.300196504592895,
|
|
"epoch": 0.7170989433237271,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004956487194123298,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.19324128031730653,
|
|
"num_tokens": 17110880.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.385277462005615,
|
|
"epoch": 0.7175792507204611,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004956420070719918,
|
|
"loss": 5.2207,
|
|
"mean_token_accuracy": 0.19511604756116868,
|
|
"num_tokens": 17122272.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.43329496383667,
|
|
"epoch": 0.718059558117195,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004956352896090014,
|
|
"loss": 5.3624,
|
|
"mean_token_accuracy": 0.18780047297477723,
|
|
"num_tokens": 17133995.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.460303926467896,
|
|
"epoch": 0.7185398655139289,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004956285670235147,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.19487278312444686,
|
|
"num_tokens": 17145970.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.468688726425171,
|
|
"epoch": 0.7190201729106628,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004956218393156879,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.18288641422986984,
|
|
"num_tokens": 17157747.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.397162818908692,
|
|
"epoch": 0.7195004803073968,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004956151064856772,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.19440642446279527,
|
|
"num_tokens": 17168357.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.461247777938842,
|
|
"epoch": 0.7199807877041307,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004956083685336386,
|
|
"loss": 5.3129,
|
|
"mean_token_accuracy": 0.19480185210704803,
|
|
"num_tokens": 17179871.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.4779870986938475,
|
|
"epoch": 0.7204610951008645,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004956016254597289,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.19740982949733735,
|
|
"num_tokens": 17190456.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.351036596298218,
|
|
"epoch": 0.7209414024975984,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004955948772641044,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.18681231141090393,
|
|
"num_tokens": 17201623.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.379030561447143,
|
|
"epoch": 0.7214217098943324,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000495588123946922,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.19301369041204453,
|
|
"num_tokens": 17212891.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.398847675323486,
|
|
"epoch": 0.7219020172910663,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004955813655083384,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.18949487805366516,
|
|
"num_tokens": 17223983.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.444115829467774,
|
|
"epoch": 0.7223823246878002,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004955746019485104,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.19172431528568268,
|
|
"num_tokens": 17233701.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.4491418361663815,
|
|
"epoch": 0.722862632084534,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000495567833267595,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.18804671317338945,
|
|
"num_tokens": 17245958.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.533933162689209,
|
|
"epoch": 0.723342939481268,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004955610594657496,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.18324004709720612,
|
|
"num_tokens": 17257687.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.486747884750367,
|
|
"epoch": 0.7238232468780019,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004955542805431313,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.19131520837545396,
|
|
"num_tokens": 17270247.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.431939792633057,
|
|
"epoch": 0.7243035542747358,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004955474964998976,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.1965686485171318,
|
|
"num_tokens": 17281920.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.521546745300293,
|
|
"epoch": 0.7247838616714697,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004955407073362058,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.17748983353376388,
|
|
"num_tokens": 17293602.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.537368726730347,
|
|
"epoch": 0.7252641690682037,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004955339130522136,
|
|
"loss": 5.2572,
|
|
"mean_token_accuracy": 0.19582899361848832,
|
|
"num_tokens": 17304484.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.3129504203796385,
|
|
"epoch": 0.7257444764649376,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000495527113648079,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.19539716839790344,
|
|
"num_tokens": 17314953.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.379434871673584,
|
|
"epoch": 0.7262247838616714,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004955203091239596,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.1896032989025116,
|
|
"num_tokens": 17326813.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.500126743316651,
|
|
"epoch": 0.7267050912584054,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004955134994800134,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.18540330827236176,
|
|
"num_tokens": 17337968.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.468137645721436,
|
|
"epoch": 0.7271853986551393,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004955066847163984,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.18784013986587525,
|
|
"num_tokens": 17350406.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.341634798049927,
|
|
"epoch": 0.7276657060518732,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004954998648332731,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.19882252365350722,
|
|
"num_tokens": 17361888.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.4041882991790775,
|
|
"epoch": 0.7281460134486071,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004954930398307956,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.18960834443569183,
|
|
"num_tokens": 17374047.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.500823259353638,
|
|
"epoch": 0.7286263208453411,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004954862097091245,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.1816348537802696,
|
|
"num_tokens": 17386175.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.395717620849609,
|
|
"epoch": 0.729106628242075,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004954793744684184,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.1996360793709755,
|
|
"num_tokens": 17398168.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.357359409332275,
|
|
"epoch": 0.7295869356388088,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004954725341088358,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.1952305555343628,
|
|
"num_tokens": 17408825.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.390852689743042,
|
|
"epoch": 0.7300672430355427,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004954656886305356,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.19365876019001008,
|
|
"num_tokens": 17419813.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.489410161972046,
|
|
"epoch": 0.7305475504322767,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004954588380336768,
|
|
"loss": 5.3439,
|
|
"mean_token_accuracy": 0.18417534679174424,
|
|
"num_tokens": 17431134.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.369253253936767,
|
|
"epoch": 0.7310278578290106,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004954519823184184,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.1921952784061432,
|
|
"num_tokens": 17442614.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.359159755706787,
|
|
"epoch": 0.7315081652257445,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004954451214849196,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.18935904055833816,
|
|
"num_tokens": 17454615.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.537013149261474,
|
|
"epoch": 0.7319884726224783,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004954382555333397,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.18759541660547258,
|
|
"num_tokens": 17467025.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.40692400932312,
|
|
"epoch": 0.7324687800192123,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000495431384463838,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.19633986949920654,
|
|
"num_tokens": 17477681.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.343720388412476,
|
|
"epoch": 0.7329490874159462,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004954245082765741,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.18974438160657883,
|
|
"num_tokens": 17489814.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.451648855209351,
|
|
"epoch": 0.7334293948126801,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004954176269717077,
|
|
"loss": 5.3279,
|
|
"mean_token_accuracy": 0.1915590688586235,
|
|
"num_tokens": 17501701.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.386299419403076,
|
|
"epoch": 0.733909702209414,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004954107405493984,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.1934077963232994,
|
|
"num_tokens": 17513585.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.444968223571777,
|
|
"epoch": 0.734390009606148,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004954038490098064,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.19142983108758926,
|
|
"num_tokens": 17525557.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.379229736328125,
|
|
"epoch": 0.7348703170028819,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004953969523530914,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.19123659580945968,
|
|
"num_tokens": 17538312.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.490963459014893,
|
|
"epoch": 0.7353506243996157,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004953900505794136,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.1925169438123703,
|
|
"num_tokens": 17550248.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.3926159858703615,
|
|
"epoch": 0.7358309317963496,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004953831436889332,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.19118221700191498,
|
|
"num_tokens": 17560624.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.40871753692627,
|
|
"epoch": 0.7363112391930836,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004953762316818106,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.19061001688241958,
|
|
"num_tokens": 17572439.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.441591501235962,
|
|
"epoch": 0.7367915465898175,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004953693145582064,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.18119185268878937,
|
|
"num_tokens": 17583120.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.331739330291748,
|
|
"epoch": 0.7372718539865514,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000495362392318281,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.20138302594423294,
|
|
"num_tokens": 17593677.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.37236909866333,
|
|
"epoch": 0.7377521613832853,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004953554649621951,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.18752527087926865,
|
|
"num_tokens": 17605180.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.4513434886932375,
|
|
"epoch": 0.7382324687800192,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004953485324901098,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.19254124760627747,
|
|
"num_tokens": 17617459.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.455876111984253,
|
|
"epoch": 0.7387127761767531,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004953415949021857,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.18982446044683457,
|
|
"num_tokens": 17628024.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.317249965667725,
|
|
"epoch": 0.739193083573487,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004953346521985843,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.1910696342587471,
|
|
"num_tokens": 17639833.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.441685914993286,
|
|
"epoch": 0.7396733909702209,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004953277043794663,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.1798558607697487,
|
|
"num_tokens": 17651057.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.4308277606964115,
|
|
"epoch": 0.7401536983669549,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004953207514449933,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.20061071664094926,
|
|
"num_tokens": 17662288.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.411059999465943,
|
|
"epoch": 0.7406340057636888,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004953137933953267,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.19094688594341278,
|
|
"num_tokens": 17673885.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.389277839660645,
|
|
"epoch": 0.7411143131604226,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000495306830230628,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.19512724727392197,
|
|
"num_tokens": 17685030.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.370732212066651,
|
|
"epoch": 0.7415946205571565,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004952998619510589,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.20075538605451584,
|
|
"num_tokens": 17696624.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.366802740097046,
|
|
"epoch": 0.7420749279538905,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.0004952928885567811,
|
|
"loss": 5.2623,
|
|
"mean_token_accuracy": 0.19420749694108963,
|
|
"num_tokens": 17707386.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.47811222076416,
|
|
"epoch": 0.7425552353506244,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004952859100479566,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.18234145492315293,
|
|
"num_tokens": 17718605.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.396338844299317,
|
|
"epoch": 0.7430355427473583,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004952789264247474,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.19224460870027543,
|
|
"num_tokens": 17730275.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.486719274520874,
|
|
"epoch": 0.7435158501440923,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004952719376873156,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.18618267476558686,
|
|
"num_tokens": 17741390.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.448188161849975,
|
|
"epoch": 0.7439961575408262,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004952649438358234,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.1972104236483574,
|
|
"num_tokens": 17752354.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.430622482299805,
|
|
"epoch": 0.74447646493756,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004952579448704334,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.19211036264896392,
|
|
"num_tokens": 17762839.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.431973028182983,
|
|
"epoch": 0.7449567723342939,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000495250940791308,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.18252928853034972,
|
|
"num_tokens": 17775800.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.467150735855102,
|
|
"epoch": 0.7454370797310279,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004952439315986096,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.18941785395145416,
|
|
"num_tokens": 17787804.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.547841548919678,
|
|
"epoch": 0.7459173871277618,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004952369172925012,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.18960139900445938,
|
|
"num_tokens": 17800291.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.404936456680298,
|
|
"epoch": 0.7463976945244957,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004952298978731454,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.19399454146623613,
|
|
"num_tokens": 17811548.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.389427232742309,
|
|
"epoch": 0.7468780019212296,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004952228733407055,
|
|
"loss": 5.1876,
|
|
"mean_token_accuracy": 0.19684941321611404,
|
|
"num_tokens": 17822589.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.319245862960815,
|
|
"epoch": 0.7473583093179635,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004952158436953444,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.1943836659193039,
|
|
"num_tokens": 17834203.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.3926421165466305,
|
|
"epoch": 0.7478386167146974,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004952088089372252,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.18852603137493135,
|
|
"num_tokens": 17846238.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.439556121826172,
|
|
"epoch": 0.7483189241114313,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004952017690665114,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.19354287683963775,
|
|
"num_tokens": 17857640.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.391794109344483,
|
|
"epoch": 0.7487992315081652,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004951947240833664,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.19658850282430648,
|
|
"num_tokens": 17868755.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.376672887802124,
|
|
"epoch": 0.7492795389048992,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004951876739879537,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.18713760524988174,
|
|
"num_tokens": 17881078.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.378430604934692,
|
|
"epoch": 0.7497598463016331,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004951806187804371,
|
|
"loss": 5.2596,
|
|
"mean_token_accuracy": 0.19280228316783904,
|
|
"num_tokens": 17893888.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.419843673706055,
|
|
"epoch": 0.7502401536983669,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004951735584609804,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.18798921555280684,
|
|
"num_tokens": 17904443.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.38177981376648,
|
|
"epoch": 0.7507204610951008,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004951664930297474,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.19300176650285722,
|
|
"num_tokens": 17918090.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.310542058944702,
|
|
"epoch": 0.7512007684918348,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000495159422486902,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.19428865760564804,
|
|
"num_tokens": 17929233.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.413312196731567,
|
|
"epoch": 0.7516810758885687,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004951523468326088,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.18861110955476762,
|
|
"num_tokens": 17940580.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.4677266597747805,
|
|
"epoch": 0.7521613832853026,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004951452660670317,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.18299274742603303,
|
|
"num_tokens": 17953993.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.391315221786499,
|
|
"epoch": 0.7526416906820365,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004951381801903352,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.19027505069971085,
|
|
"num_tokens": 17966033.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.320323848724366,
|
|
"epoch": 0.7531219980787704,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004951310892026839,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.19828407615423202,
|
|
"num_tokens": 17977943.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.379558944702149,
|
|
"epoch": 0.7536023054755043,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004951239931042424,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.1953260362148285,
|
|
"num_tokens": 17990135.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.41697211265564,
|
|
"epoch": 0.7540826128722382,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004951168918951753,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.19323987364768982,
|
|
"num_tokens": 18002126.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.345477485656739,
|
|
"epoch": 0.7545629202689721,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004951097855756476,
|
|
"loss": 5.1832,
|
|
"mean_token_accuracy": 0.19381873160600663,
|
|
"num_tokens": 18013147.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.471619892120361,
|
|
"epoch": 0.7550432276657061,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004951026741458243,
|
|
"loss": 5.286,
|
|
"mean_token_accuracy": 0.1943528711795807,
|
|
"num_tokens": 18025146.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.361651754379272,
|
|
"epoch": 0.75552353506244,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004950955576058705,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.19078268706798554,
|
|
"num_tokens": 18036412.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.410406112670898,
|
|
"epoch": 0.7560038424591738,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004950884359559513,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.19134726375341415,
|
|
"num_tokens": 18048041.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.4635584354400635,
|
|
"epoch": 0.7564841498559077,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004950813091962324,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.18341733515262604,
|
|
"num_tokens": 18060163.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.461487102508545,
|
|
"epoch": 0.7569644572526417,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004950741773268788,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.19013395309448242,
|
|
"num_tokens": 18071628.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.314058828353882,
|
|
"epoch": 0.7574447646493756,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004950670403480562,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.19070881158113479,
|
|
"num_tokens": 18082979.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.375623655319214,
|
|
"epoch": 0.7579250720461095,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004950598982599306,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.19409219771623612,
|
|
"num_tokens": 18093889.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.3679296493530275,
|
|
"epoch": 0.7584053794428435,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004950527510626675,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.18781346529722215,
|
|
"num_tokens": 18105559.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.433981895446777,
|
|
"epoch": 0.7588856868395774,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004950455987564329,
|
|
"loss": 5.3933,
|
|
"mean_token_accuracy": 0.1884242683649063,
|
|
"num_tokens": 18116316.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.476165437698365,
|
|
"epoch": 0.7593659942363112,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004950384413413931,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.19407722502946853,
|
|
"num_tokens": 18126851.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.498535394668579,
|
|
"epoch": 0.7598463016330451,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004950312788177139,
|
|
"loss": 5.3915,
|
|
"mean_token_accuracy": 0.18364253044128417,
|
|
"num_tokens": 18139571.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.495917320251465,
|
|
"epoch": 0.7603266090297791,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004950241111855618,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.1896468222141266,
|
|
"num_tokens": 18150680.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.4452379703521725,
|
|
"epoch": 0.760806916426513,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004950169384451031,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.19199316054582596,
|
|
"num_tokens": 18161911.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.440609359741211,
|
|
"epoch": 0.7612872238232469,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004950097605965045,
|
|
"loss": 5.2862,
|
|
"mean_token_accuracy": 0.19456473737955093,
|
|
"num_tokens": 18172714.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.465766382217407,
|
|
"epoch": 0.7617675312199808,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004950025776399326,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.1952493816614151,
|
|
"num_tokens": 18184250.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.464382457733154,
|
|
"epoch": 0.7622478386167147,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000494995389575554,
|
|
"loss": 5.405,
|
|
"mean_token_accuracy": 0.17983411103487015,
|
|
"num_tokens": 18195299.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.472284746170044,
|
|
"epoch": 0.7627281460134486,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004949881964035357,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.18016218394041061,
|
|
"num_tokens": 18206863.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.505875015258789,
|
|
"epoch": 0.7632084534101825,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004949809981240448,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.18186725974082946,
|
|
"num_tokens": 18219643.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.409666538238525,
|
|
"epoch": 0.7636887608069164,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004949737947372483,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.20003483593463897,
|
|
"num_tokens": 18230461.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.424594163894653,
|
|
"epoch": 0.7641690682036504,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004949665862433134,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.1825257956981659,
|
|
"num_tokens": 18243768.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.423941230773925,
|
|
"epoch": 0.7646493756003843,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004949593726424077,
|
|
"loss": 5.2676,
|
|
"mean_token_accuracy": 0.1982079863548279,
|
|
"num_tokens": 18255322.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.444241619110107,
|
|
"epoch": 0.7651296829971181,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004949521539346985,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.1952738121151924,
|
|
"num_tokens": 18267262.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.426650428771973,
|
|
"epoch": 0.765609990393852,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004949449301203533,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.1906588852405548,
|
|
"num_tokens": 18277332.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.426930570602417,
|
|
"epoch": 0.766090297790586,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004949377011995399,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.19307608306407928,
|
|
"num_tokens": 18289547.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.360224628448487,
|
|
"epoch": 0.7665706051873199,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004949304671724263,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.19629723578691483,
|
|
"num_tokens": 18302097.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.433572912216187,
|
|
"epoch": 0.7670509125840538,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004949232280391802,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.18926830738782882,
|
|
"num_tokens": 18314151.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.419026136398315,
|
|
"epoch": 0.7675312199807877,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004949159837999698,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.18758469372987746,
|
|
"num_tokens": 18326085.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.410974645614624,
|
|
"epoch": 0.7680115273775217,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004949087344549633,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.18807757943868636,
|
|
"num_tokens": 18338158.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.404014968872071,
|
|
"epoch": 0.7684918347742555,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.000494901480004329,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.1937829941511154,
|
|
"num_tokens": 18349418.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.413689184188843,
|
|
"epoch": 0.7689721421709894,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004948942204482351,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.190411801636219,
|
|
"num_tokens": 18361964.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.352678346633911,
|
|
"epoch": 0.7694524495677233,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004948869557868506,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.20040010511875153,
|
|
"num_tokens": 18373108.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.296018981933594,
|
|
"epoch": 0.7699327569644573,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004948796860203439,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.19369546324014664,
|
|
"num_tokens": 18385310.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.502485370635986,
|
|
"epoch": 0.7704130643611912,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004948724111488838,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.1858559235930443,
|
|
"num_tokens": 18396132.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.597889423370361,
|
|
"epoch": 0.770893371757925,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004948651311726391,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.18312230557203293,
|
|
"num_tokens": 18409930.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.453195333480835,
|
|
"epoch": 0.7713736791546589,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004948578460917789,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.184532730281353,
|
|
"num_tokens": 18421204.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.449152851104737,
|
|
"epoch": 0.7718539865513929,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004948505559064725,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.19551548659801482,
|
|
"num_tokens": 18433194.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.39205150604248,
|
|
"epoch": 0.7723342939481268,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004948432606168889,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.19400351196527482,
|
|
"num_tokens": 18445282.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.379894399642945,
|
|
"epoch": 0.7728146013448607,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004948359602231976,
|
|
"loss": 5.2747,
|
|
"mean_token_accuracy": 0.19268660098314286,
|
|
"num_tokens": 18456264.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.342808437347412,
|
|
"epoch": 0.7732949087415946,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004948286547255681,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.19346899390220643,
|
|
"num_tokens": 18467573.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.407975101470948,
|
|
"epoch": 0.7737752161383286,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00049482134412417,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.20092470049858094,
|
|
"num_tokens": 18478333.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.4008460521698,
|
|
"epoch": 0.7742555235350624,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000494814028419173,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.19972852915525435,
|
|
"num_tokens": 18489106.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.428393030166626,
|
|
"epoch": 0.7747358309317963,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000494806707610747,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.19097500592470168,
|
|
"num_tokens": 18500090.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.412510728836059,
|
|
"epoch": 0.7752161383285303,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000494799381699062,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.1992083877325058,
|
|
"num_tokens": 18510305.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.41508846282959,
|
|
"epoch": 0.7756964457252642,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004947920506842879,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.19287320077419282,
|
|
"num_tokens": 18523048.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.374328517913819,
|
|
"epoch": 0.7761767531219981,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004947847145665951,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.19573139846324922,
|
|
"num_tokens": 18534145.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.388862133026123,
|
|
"epoch": 0.776657060518732,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004947773733461539,
|
|
"loss": 5.2682,
|
|
"mean_token_accuracy": 0.19629741609096527,
|
|
"num_tokens": 18545045.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.480919075012207,
|
|
"epoch": 0.777137367915466,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004947700270231347,
|
|
"loss": 5.2627,
|
|
"mean_token_accuracy": 0.19508594274520874,
|
|
"num_tokens": 18557531.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.425774955749512,
|
|
"epoch": 0.7776176753121998,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004947626755977079,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.18983712345361708,
|
|
"num_tokens": 18569127.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.4588545799255375,
|
|
"epoch": 0.7780979827089337,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004947553190700444,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.19727216511964799,
|
|
"num_tokens": 18580606.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.534365653991699,
|
|
"epoch": 0.7785782901056676,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.000494747957440315,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.18067182302474977,
|
|
"num_tokens": 18592330.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.560704708099365,
|
|
"epoch": 0.7790585975024016,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004947405907086905,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.1834690809249878,
|
|
"num_tokens": 18604721.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.445353412628174,
|
|
"epoch": 0.7795389048991355,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004947332188753419,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.19181837737560273,
|
|
"num_tokens": 18616814.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.395102453231812,
|
|
"epoch": 0.7800192122958693,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004947258419404405,
|
|
"loss": 5.2726,
|
|
"mean_token_accuracy": 0.19361393749713898,
|
|
"num_tokens": 18628224.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.4511572360992435,
|
|
"epoch": 0.7804995196926032,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004947184599041576,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.189791539311409,
|
|
"num_tokens": 18639777.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.387516593933105,
|
|
"epoch": 0.7809798270893372,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004947110727666644,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.19379826486110688,
|
|
"num_tokens": 18651044.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.397434711456299,
|
|
"epoch": 0.7814601344860711,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004947036805281325,
|
|
"loss": 5.3059,
|
|
"mean_token_accuracy": 0.19373724609613419,
|
|
"num_tokens": 18663142.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.542802476882935,
|
|
"epoch": 0.781940441882805,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004946962831887336,
|
|
"loss": 5.3846,
|
|
"mean_token_accuracy": 0.1856202334165573,
|
|
"num_tokens": 18674079.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.5152007102966305,
|
|
"epoch": 0.7824207492795389,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004946888807486393,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.18622805476188659,
|
|
"num_tokens": 18685744.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.356904363632202,
|
|
"epoch": 0.7829010566762729,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004946814732080214,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.19371848851442336,
|
|
"num_tokens": 18697049.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.368295288085937,
|
|
"epoch": 0.7833813640730067,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004946740605670523,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.19403277188539506,
|
|
"num_tokens": 18708765.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.413602828979492,
|
|
"epoch": 0.7838616714697406,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004946666428259037,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.19469162672758103,
|
|
"num_tokens": 18719819.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.511895751953125,
|
|
"epoch": 0.7843419788664745,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004946592199847478,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.18569377362728118,
|
|
"num_tokens": 18730668.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.366625213623047,
|
|
"epoch": 0.7848222862632085,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004946517920437571,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.19980715662240983,
|
|
"num_tokens": 18741991.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.413477563858033,
|
|
"epoch": 0.7853025936599424,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004946443590031041,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.188918100297451,
|
|
"num_tokens": 18753919.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.4686939239501955,
|
|
"epoch": 0.7857829010566763,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004946369208629613,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.19828154295682907,
|
|
"num_tokens": 18764342.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.363447189331055,
|
|
"epoch": 0.7862632084534101,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004946294776235013,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.19545882493257521,
|
|
"num_tokens": 18776044.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.5042516708374025,
|
|
"epoch": 0.7867435158501441,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004946220292848971,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.18935187458992003,
|
|
"num_tokens": 18787354.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.448554372787475,
|
|
"epoch": 0.787223823246878,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004946145758473214,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.19602509588003159,
|
|
"num_tokens": 18797845.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.448045110702514,
|
|
"epoch": 0.7877041306436119,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004946071173109475,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.18894803822040557,
|
|
"num_tokens": 18809253.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.384985637664795,
|
|
"epoch": 0.7881844380403458,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004945996536759484,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.20108186602592468,
|
|
"num_tokens": 18819768.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.533975982666016,
|
|
"epoch": 0.7886647454370798,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004945921849424974,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.18477168828248977,
|
|
"num_tokens": 18831151.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.368637180328369,
|
|
"epoch": 0.7891450528338136,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004945847111107679,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.20102160722017287,
|
|
"num_tokens": 18842133.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.452265501022339,
|
|
"epoch": 0.7896253602305475,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004945772321809334,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.18794292211532593,
|
|
"num_tokens": 18853295.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.418984699249267,
|
|
"epoch": 0.7901056676272814,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004945697481531677,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.1946453258395195,
|
|
"num_tokens": 18865802.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.372564506530762,
|
|
"epoch": 0.7905859750240154,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004945622590276443,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.1987846240401268,
|
|
"num_tokens": 18877693.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.455006694793701,
|
|
"epoch": 0.7910662824207493,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004945547648045373,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.1957358807325363,
|
|
"num_tokens": 18888549.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.384636545181275,
|
|
"epoch": 0.7915465898174832,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004945472654840206,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.19511064738035203,
|
|
"num_tokens": 18899132.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.277899169921875,
|
|
"epoch": 0.7920268972142172,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004945397610662683,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.19098789542913436,
|
|
"num_tokens": 18911774.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.483994245529175,
|
|
"epoch": 0.792507204610951,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004945322515514547,
|
|
"loss": 5.3157,
|
|
"mean_token_accuracy": 0.19059932827949524,
|
|
"num_tokens": 18922806.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.45802116394043,
|
|
"epoch": 0.7929875120076849,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000494524736939754,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.19994459748268129,
|
|
"num_tokens": 18934861.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.421169900894165,
|
|
"epoch": 0.7934678194044188,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004945172172313408,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.19804629534482956,
|
|
"num_tokens": 18944269.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.4324627876281735,
|
|
"epoch": 0.7939481268011528,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004945096924263896,
|
|
"loss": 5.3163,
|
|
"mean_token_accuracy": 0.1877553790807724,
|
|
"num_tokens": 18957197.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.428729009628296,
|
|
"epoch": 0.7944284341978867,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004945021625250753,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.18720821291208267,
|
|
"num_tokens": 18968254.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.381123638153076,
|
|
"epoch": 0.7949087415946205,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004944946275275724,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.20089622288942338,
|
|
"num_tokens": 18979372.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.403303384780884,
|
|
"epoch": 0.7953890489913544,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004944870874340561,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.19709096997976303,
|
|
"num_tokens": 18991075.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.358301639556885,
|
|
"epoch": 0.7958693563880884,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004944795422447013,
|
|
"loss": 5.1535,
|
|
"mean_token_accuracy": 0.1996439665555954,
|
|
"num_tokens": 19002324.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.445419406890869,
|
|
"epoch": 0.7963496637848223,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004944719919596835,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.18793108463287353,
|
|
"num_tokens": 19014406.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.368029356002808,
|
|
"epoch": 0.7968299711815562,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004944644365791776,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.19681814610958098,
|
|
"num_tokens": 19025984.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.421530151367188,
|
|
"epoch": 0.7973102785782901,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000494456876103359,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.19396770745515823,
|
|
"num_tokens": 19036189.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.4341600894927975,
|
|
"epoch": 0.7977905859750241,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004944493105324035,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.18886428624391555,
|
|
"num_tokens": 19047587.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.469302654266357,
|
|
"epoch": 0.7982708933717579,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004944417398664866,
|
|
"loss": 5.303,
|
|
"mean_token_accuracy": 0.1894800066947937,
|
|
"num_tokens": 19058467.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.416854953765869,
|
|
"epoch": 0.7987512007684918,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004944341641057843,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.18853143602609634,
|
|
"num_tokens": 19070235.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.435975408554077,
|
|
"epoch": 0.7992315081652257,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004944265832504721,
|
|
"loss": 5.3369,
|
|
"mean_token_accuracy": 0.18985726237297057,
|
|
"num_tokens": 19082005.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.4500726699829105,
|
|
"epoch": 0.7997118155619597,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004944189973007262,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.19081617444753646,
|
|
"num_tokens": 19092922.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.530605411529541,
|
|
"epoch": 0.8001921229586936,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004944114062567229,
|
|
"loss": 5.325,
|
|
"mean_token_accuracy": 0.18821552991867066,
|
|
"num_tokens": 19104832.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.45482234954834,
|
|
"epoch": 0.8006724303554275,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004944038101186381,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.19373996406793595,
|
|
"num_tokens": 19116261.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.435201168060303,
|
|
"epoch": 0.8011527377521613,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004943962088866483,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.18850855231285096,
|
|
"num_tokens": 19127195.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.447613143920899,
|
|
"epoch": 0.8016330451488953,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004943886025609301,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.18747612982988357,
|
|
"num_tokens": 19138164.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.529285192489624,
|
|
"epoch": 0.8021133525456292,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00049438099114166,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.18186384439468384,
|
|
"num_tokens": 19149153.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.482778120040893,
|
|
"epoch": 0.8025936599423631,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004943733746290147,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.1813454359769821,
|
|
"num_tokens": 19161023.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.342861270904541,
|
|
"epoch": 0.803073967339097,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000494365753023171,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.20069017261266708,
|
|
"num_tokens": 19172466.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.378940010070801,
|
|
"epoch": 0.803554274735831,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004943581263243059,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.19599779397249223,
|
|
"num_tokens": 19183684.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.3622236251831055,
|
|
"epoch": 0.8040345821325648,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004943504945325965,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.1975469782948494,
|
|
"num_tokens": 19194479.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.444317483901978,
|
|
"epoch": 0.8045148895292987,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004943428576482198,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.18655437529087066,
|
|
"num_tokens": 19206323.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.504732751846314,
|
|
"epoch": 0.8049951969260326,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004943352156713535,
|
|
"loss": 5.3669,
|
|
"mean_token_accuracy": 0.18603195399045944,
|
|
"num_tokens": 19218849.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.358531379699707,
|
|
"epoch": 0.8054755043227666,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004943275686021747,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.19521573483943938,
|
|
"num_tokens": 19229603.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.410021734237671,
|
|
"epoch": 0.8059558117195005,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000494319916440861,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.18732102811336518,
|
|
"num_tokens": 19241318.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.448578882217407,
|
|
"epoch": 0.8064361191162344,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004943122591875901,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.19280615597963333,
|
|
"num_tokens": 19252640.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.397020149230957,
|
|
"epoch": 0.8069164265129684,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004943045968425398,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.19911836981773376,
|
|
"num_tokens": 19262971.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.4335608959198,
|
|
"epoch": 0.8073967339097022,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004942969294058878,
|
|
"loss": 5.3397,
|
|
"mean_token_accuracy": 0.19015580266714097,
|
|
"num_tokens": 19274426.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.410697174072266,
|
|
"epoch": 0.8078770413064361,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004942892568778125,
|
|
"loss": 5.3,
|
|
"mean_token_accuracy": 0.1919780984520912,
|
|
"num_tokens": 19286806.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.431985521316529,
|
|
"epoch": 0.80835734870317,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004942815792584917,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.1923940137028694,
|
|
"num_tokens": 19297997.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.413062906265258,
|
|
"epoch": 0.808837656099904,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004942738965481038,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.19406114816665648,
|
|
"num_tokens": 19309789.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.410136604309082,
|
|
"epoch": 0.8093179634966379,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004942662087468272,
|
|
"loss": 5.26,
|
|
"mean_token_accuracy": 0.1997787743806839,
|
|
"num_tokens": 19320688.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.419143581390381,
|
|
"epoch": 0.8097982708933718,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004942585158548402,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.19373372495174407,
|
|
"num_tokens": 19331670.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.393004894256592,
|
|
"epoch": 0.8102785782901056,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004942508178723214,
|
|
"loss": 5.2615,
|
|
"mean_token_accuracy": 0.18775656521320344,
|
|
"num_tokens": 19343578.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.401038122177124,
|
|
"epoch": 0.8107588856868396,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004942431147994499,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.19167630970478058,
|
|
"num_tokens": 19354875.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.411659574508667,
|
|
"epoch": 0.8112391930835735,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004942354066364042,
|
|
"loss": 5.2464,
|
|
"mean_token_accuracy": 0.19427219182252883,
|
|
"num_tokens": 19366353.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.292094993591308,
|
|
"epoch": 0.8117195004803074,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004942276933833634,
|
|
"loss": 5.1736,
|
|
"mean_token_accuracy": 0.20411385595798492,
|
|
"num_tokens": 19377534.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.409317398071289,
|
|
"epoch": 0.8121998078770413,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004942199750405064,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.1877780020236969,
|
|
"num_tokens": 19388188.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.310885906219482,
|
|
"epoch": 0.8126801152737753,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004942122516080127,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.203945392370224,
|
|
"num_tokens": 19399910.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.427954816818238,
|
|
"epoch": 0.8131604226705091,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004942045230860614,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.19696923941373826,
|
|
"num_tokens": 19411715.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.506597423553467,
|
|
"epoch": 0.813640730067243,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004941967894748319,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.1823534920811653,
|
|
"num_tokens": 19423275.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.427609062194824,
|
|
"epoch": 0.8141210374639769,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004941890507745039,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.18587649166584014,
|
|
"num_tokens": 19436035.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.337133359909058,
|
|
"epoch": 0.8146013448607109,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004941813069852569,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.19434040337800979,
|
|
"num_tokens": 19447755.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.46027135848999,
|
|
"epoch": 0.8150816522574448,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004941735581072708,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.1966329336166382,
|
|
"num_tokens": 19459044.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.424165439605713,
|
|
"epoch": 0.8155619596541787,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004941658041407255,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.19137422293424605,
|
|
"num_tokens": 19471486.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.294514942169189,
|
|
"epoch": 0.8160422670509125,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000494158045085801,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.20420806109905243,
|
|
"num_tokens": 19482428.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.4167234897613525,
|
|
"epoch": 0.8165225744476465,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004941502809426776,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.18871811777353287,
|
|
"num_tokens": 19494616.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.496824598312378,
|
|
"epoch": 0.8170028818443804,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004941425117115354,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.19342519342899323,
|
|
"num_tokens": 19504953.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.404203796386719,
|
|
"epoch": 0.8174831892411143,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004941347373925547,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.19285758435726166,
|
|
"num_tokens": 19517408.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.371304893493653,
|
|
"epoch": 0.8179634966378482,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004941269579859161,
|
|
"loss": 5.2619,
|
|
"mean_token_accuracy": 0.19370961487293242,
|
|
"num_tokens": 19529190.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.389757204055786,
|
|
"epoch": 0.8184438040345822,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004941191734918002,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.190931236743927,
|
|
"num_tokens": 19540278.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.406822872161865,
|
|
"epoch": 0.818924111431316,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000494111383910388,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.19551188200712205,
|
|
"num_tokens": 19551224.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.500415325164795,
|
|
"epoch": 0.8194044188280499,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004941035892418597,
|
|
"loss": 5.3237,
|
|
"mean_token_accuracy": 0.18760576397180556,
|
|
"num_tokens": 19564386.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.439950370788575,
|
|
"epoch": 0.8198847262247838,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004940957894863968,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.19479889422655106,
|
|
"num_tokens": 19576170.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.405121994018555,
|
|
"epoch": 0.8203650336215178,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004940879846441804,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.19330257922410965,
|
|
"num_tokens": 19587220.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.408662557601929,
|
|
"epoch": 0.8208453410182517,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004940801747153914,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.1938901200890541,
|
|
"num_tokens": 19598649.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.428944206237793,
|
|
"epoch": 0.8213256484149856,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004940723597002113,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.19172851592302323,
|
|
"num_tokens": 19610243.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.426394128799439,
|
|
"epoch": 0.8218059558117194,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004940645395988216,
|
|
"loss": 5.3251,
|
|
"mean_token_accuracy": 0.19313576072454453,
|
|
"num_tokens": 19621467.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.511049127578735,
|
|
"epoch": 0.8222862632084534,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004940567144114036,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.18334650248289108,
|
|
"num_tokens": 19633367.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.343498182296753,
|
|
"epoch": 0.8227665706051873,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004940488841381393,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.19553158879280091,
|
|
"num_tokens": 19643144.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.404687166213989,
|
|
"epoch": 0.8232468780019212,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004940410487792103,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.18715355396270753,
|
|
"num_tokens": 19654501.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.487803268432617,
|
|
"epoch": 0.8237271853986552,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004940332083347986,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.18759988248348236,
|
|
"num_tokens": 19665382.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.4314981460571286,
|
|
"epoch": 0.8242074927953891,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004940253628050861,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.19690021723508835,
|
|
"num_tokens": 19677222.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.371196651458741,
|
|
"epoch": 0.824687800192123,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004940175121902552,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.19561927169561386,
|
|
"num_tokens": 19688550.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.464402961730957,
|
|
"epoch": 0.8251681075888568,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000494009656490488,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.18769710659980773,
|
|
"num_tokens": 19700125.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.504851627349853,
|
|
"epoch": 0.8256484149855908,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004940017957059668,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.1892169564962387,
|
|
"num_tokens": 19711969.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.439552640914917,
|
|
"epoch": 0.8261287223823247,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004939939298368742,
|
|
"loss": 5.2951,
|
|
"mean_token_accuracy": 0.18978720307350158,
|
|
"num_tokens": 19723813.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.456730937957763,
|
|
"epoch": 0.8266090297790586,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004939860588833929,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.18832490742206573,
|
|
"num_tokens": 19735539.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.578947067260742,
|
|
"epoch": 0.8270893371757925,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004939781828457055,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.18782947212457657,
|
|
"num_tokens": 19747106.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.440155553817749,
|
|
"epoch": 0.8275696445725265,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000493970301723995,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.2006667897105217,
|
|
"num_tokens": 19760156.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.36789116859436,
|
|
"epoch": 0.8280499519692603,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004939624155184443,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.20215553790330887,
|
|
"num_tokens": 19771256.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.394541835784912,
|
|
"epoch": 0.8285302593659942,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004939545242292365,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.19983264952898025,
|
|
"num_tokens": 19781332.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.456749153137207,
|
|
"epoch": 0.8290105667627281,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004939466278565547,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.18888089656829835,
|
|
"num_tokens": 19793573.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.444495105743409,
|
|
"epoch": 0.8294908741594621,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004939387264005825,
|
|
"loss": 5.2687,
|
|
"mean_token_accuracy": 0.1956050455570221,
|
|
"num_tokens": 19803421.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.333672189712525,
|
|
"epoch": 0.829971181556196,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004939308198615031,
|
|
"loss": 5.1357,
|
|
"mean_token_accuracy": 0.20328568518161774,
|
|
"num_tokens": 19814440.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.308907794952392,
|
|
"epoch": 0.8304514889529299,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004939229082395001,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.19684605449438095,
|
|
"num_tokens": 19825721.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.394447898864746,
|
|
"epoch": 0.8309317963496637,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004939149915347573,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.2011892691254616,
|
|
"num_tokens": 19837273.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.508377647399902,
|
|
"epoch": 0.8314121037463977,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004939070697474585,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.19834886193275453,
|
|
"num_tokens": 19849436.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.3805619239807125,
|
|
"epoch": 0.8318924111431316,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004938991428777875,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.20552821457386017,
|
|
"num_tokens": 19860222.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.398198032379151,
|
|
"epoch": 0.8323727185398655,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004938912109259284,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.2014584168791771,
|
|
"num_tokens": 19870934.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.457409143447876,
|
|
"epoch": 0.8328530259365994,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004938832738920654,
|
|
"loss": 5.304,
|
|
"mean_token_accuracy": 0.18501372784376144,
|
|
"num_tokens": 19882149.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.4318445205688475,
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004938753317763826,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.19784683585166932,
|
|
"num_tokens": 19893276.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.470212078094482,
|
|
"epoch": 0.8338136407300673,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004938673845790646,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.18210153728723527,
|
|
"num_tokens": 19904723.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.436478042602539,
|
|
"epoch": 0.8342939481268011,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004938594323002957,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.1896723285317421,
|
|
"num_tokens": 19915226.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.415202999114991,
|
|
"epoch": 0.834774255523535,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004938514749402609,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.19294490218162536,
|
|
"num_tokens": 19927911.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.427253198623657,
|
|
"epoch": 0.835254562920269,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004938435124991447,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.19052144140005112,
|
|
"num_tokens": 19940356.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.481690359115601,
|
|
"epoch": 0.8357348703170029,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004938355449771318,
|
|
"loss": 5.317,
|
|
"mean_token_accuracy": 0.18698959201574325,
|
|
"num_tokens": 19951108.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.39211859703064,
|
|
"epoch": 0.8362151777137368,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004938275723744075,
|
|
"loss": 5.2596,
|
|
"mean_token_accuracy": 0.2011283278465271,
|
|
"num_tokens": 19962427.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.4694208145141605,
|
|
"epoch": 0.8366954851104706,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004938195946911567,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.18186972588300704,
|
|
"num_tokens": 19973476.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.487786674499512,
|
|
"epoch": 0.8371757925072046,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004938116119275645,
|
|
"loss": 5.2993,
|
|
"mean_token_accuracy": 0.19480633586645127,
|
|
"num_tokens": 19984034.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.4615153789520265,
|
|
"epoch": 0.8376560999039385,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004938036240838166,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.18912490904331208,
|
|
"num_tokens": 19996035.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.441403532028199,
|
|
"epoch": 0.8381364073006724,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004937956311600983,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.1946357235312462,
|
|
"num_tokens": 20007259.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.362337970733643,
|
|
"epoch": 0.8386167146974063,
|
|
"grad_norm": 7.40625,
|
|
"learning_rate": 0.0004937876331565951,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.19242254495620728,
|
|
"num_tokens": 20018673.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.378799343109131,
|
|
"epoch": 0.8390970220941403,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.0004937796300734926,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.19401991069316865,
|
|
"num_tokens": 20030767.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.49781346321106,
|
|
"epoch": 0.8395773294908742,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004937716219109769,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.18898262232542037,
|
|
"num_tokens": 20041268.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.453662490844726,
|
|
"epoch": 0.840057636887608,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004937636086692336,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.19720974564552307,
|
|
"num_tokens": 20052285.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.513510084152221,
|
|
"epoch": 0.840537944284342,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000493755590348449,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.18603450059890747,
|
|
"num_tokens": 20065113.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.522548198699951,
|
|
"epoch": 0.8410182516810759,
|
|
"grad_norm": 6.59375,
|
|
"learning_rate": 0.0004937475669488091,
|
|
"loss": 5.3768,
|
|
"mean_token_accuracy": 0.1924232766032219,
|
|
"num_tokens": 20076151.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.454394197463989,
|
|
"epoch": 0.8414985590778098,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004937395384705004,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.19434130191802979,
|
|
"num_tokens": 20088195.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.3365062236785885,
|
|
"epoch": 0.8419788664745437,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004937315049137089,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.20213029235601426,
|
|
"num_tokens": 20098576.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.4791755199432375,
|
|
"epoch": 0.8424591738712777,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004937234662786216,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.185519477725029,
|
|
"num_tokens": 20110176.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.505225658416748,
|
|
"epoch": 0.8429394812680115,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004937154225654246,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.1932585805654526,
|
|
"num_tokens": 20121713.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.528212022781372,
|
|
"epoch": 0.8434197886647454,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004937073737743051,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.18896793872117995,
|
|
"num_tokens": 20134126.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.4223387241363525,
|
|
"epoch": 0.8439000960614793,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004936993199054499,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.19668785333633423,
|
|
"num_tokens": 20144791.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.4404583930969235,
|
|
"epoch": 0.8443804034582133,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004936912609590458,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.18443630635738373,
|
|
"num_tokens": 20157214.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.526898431777954,
|
|
"epoch": 0.8448607108549472,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00049368319693528,
|
|
"loss": 5.4195,
|
|
"mean_token_accuracy": 0.17976684719324112,
|
|
"num_tokens": 20168952.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.493253946304321,
|
|
"epoch": 0.8453410182516811,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004936751278343397,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.18920029997825621,
|
|
"num_tokens": 20181829.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.502943754196167,
|
|
"epoch": 0.845821325648415,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004936670536564123,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.17929635494947432,
|
|
"num_tokens": 20193362.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.4905109882354735,
|
|
"epoch": 0.8463016330451489,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004936589744016853,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.18860941082239152,
|
|
"num_tokens": 20205159.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.4954063415527346,
|
|
"epoch": 0.8467819404418828,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000493650890070346,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.19540442824363707,
|
|
"num_tokens": 20217075.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.426065349578858,
|
|
"epoch": 0.8472622478386167,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004936428006625824,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.1953060358762741,
|
|
"num_tokens": 20227901.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.425052499771118,
|
|
"epoch": 0.8477425552353506,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004936347061785823,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.19576554000377655,
|
|
"num_tokens": 20239945.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.541347360610962,
|
|
"epoch": 0.8482228626320846,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004936266066185334,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.18867553621530533,
|
|
"num_tokens": 20251503.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.474639844894409,
|
|
"epoch": 0.8487031700288185,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004936185019826239,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.19478006064891815,
|
|
"num_tokens": 20263044.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.448990297317505,
|
|
"epoch": 0.8491834774255523,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004936103922710419,
|
|
"loss": 5.2654,
|
|
"mean_token_accuracy": 0.1919919580221176,
|
|
"num_tokens": 20273563.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.410304689407349,
|
|
"epoch": 0.8496637848222862,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.0004936022774839759,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.19330882132053376,
|
|
"num_tokens": 20285482.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.5379705905914305,
|
|
"epoch": 0.8501440922190202,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004935941576216141,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.18526654243469237,
|
|
"num_tokens": 20296666.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.364816188812256,
|
|
"epoch": 0.8506243996157541,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.000493586032684145,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.20126208215951918,
|
|
"num_tokens": 20308978.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.383402299880982,
|
|
"epoch": 0.851104707012488,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004935779026717573,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.19292386770248413,
|
|
"num_tokens": 20321488.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.3920821189880375,
|
|
"epoch": 0.8515850144092219,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004935697675846396,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.20606416761875151,
|
|
"num_tokens": 20332938.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.4154479026794435,
|
|
"epoch": 0.8520653218059558,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004935616274229811,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.20128644108772278,
|
|
"num_tokens": 20342986.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.424758672714233,
|
|
"epoch": 0.8525456292026897,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004935534821869705,
|
|
"loss": 5.2985,
|
|
"mean_token_accuracy": 0.18809338212013244,
|
|
"num_tokens": 20355791.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.348780870437622,
|
|
"epoch": 0.8530259365994236,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004935453318767971,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.19693395644426345,
|
|
"num_tokens": 20367080.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.501302671432495,
|
|
"epoch": 0.8535062439961575,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00049353717649265,
|
|
"loss": 5.2523,
|
|
"mean_token_accuracy": 0.201241372525692,
|
|
"num_tokens": 20376697.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.495076704025268,
|
|
"epoch": 0.8539865513928915,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004935290160347185,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.19502430707216262,
|
|
"num_tokens": 20387430.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.4262817859649655,
|
|
"epoch": 0.8544668587896254,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004935208505031922,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.19394478052854539,
|
|
"num_tokens": 20398488.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.361809539794922,
|
|
"epoch": 0.8549471661863592,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004935126798982606,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.1966690257191658,
|
|
"num_tokens": 20410316.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.45485553741455,
|
|
"epoch": 0.8554274735830932,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004935045042201135,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.2006060838699341,
|
|
"num_tokens": 20421645.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.508545589447022,
|
|
"epoch": 0.8559077809798271,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004934963234689407,
|
|
"loss": 5.3386,
|
|
"mean_token_accuracy": 0.18619626760482788,
|
|
"num_tokens": 20433397.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.3808855533599855,
|
|
"epoch": 0.856388088376561,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000493488137644932,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.19659044742584228,
|
|
"num_tokens": 20446218.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.486376667022705,
|
|
"epoch": 0.8568683957732949,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004934799467482774,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.19420091062784195,
|
|
"num_tokens": 20457265.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.455189418792725,
|
|
"epoch": 0.8573487031700289,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004934717507791673,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.18957421332597732,
|
|
"num_tokens": 20468748.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.486153411865234,
|
|
"epoch": 0.8578290105667628,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004934635497377919,
|
|
"loss": 5.3472,
|
|
"mean_token_accuracy": 0.18951629996299743,
|
|
"num_tokens": 20481416.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.398213005065918,
|
|
"epoch": 0.8583093179634966,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004934553436243415,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.1895105540752411,
|
|
"num_tokens": 20493063.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.367551660537719,
|
|
"epoch": 0.8587896253602305,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004934471324390067,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.19198835045099258,
|
|
"num_tokens": 20504000.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.431077146530152,
|
|
"epoch": 0.8592699327569645,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004934389161819783,
|
|
"loss": 5.3222,
|
|
"mean_token_accuracy": 0.197113274037838,
|
|
"num_tokens": 20516419.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.441454029083252,
|
|
"epoch": 0.8597502401536984,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004934306948534467,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.19323156028985977,
|
|
"num_tokens": 20527385.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.471669101715088,
|
|
"epoch": 0.8602305475504323,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004934224684536031,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.19473379254341125,
|
|
"num_tokens": 20538051.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.4765232563018795,
|
|
"epoch": 0.8607108549471661,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004934142369826382,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.18887096494436265,
|
|
"num_tokens": 20550321.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.4616186141967775,
|
|
"epoch": 0.8611911623439001,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004934060004407434,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.19557591080665587,
|
|
"num_tokens": 20561229.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.430670166015625,
|
|
"epoch": 0.861671469740634,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004933977588281099,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.19680995792150496,
|
|
"num_tokens": 20572040.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.423302173614502,
|
|
"epoch": 0.8621517771373679,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004933895121449288,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.19825332313776017,
|
|
"num_tokens": 20583110.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.4062117576599125,
|
|
"epoch": 0.8626320845341018,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004933812603913917,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19275658577680588,
|
|
"num_tokens": 20593647.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.285828304290772,
|
|
"epoch": 0.8631123919308358,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004933730035676903,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.20892462283372878,
|
|
"num_tokens": 20604428.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.301270246505737,
|
|
"epoch": 0.8635926993275697,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004933647416740161,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.20536972135305404,
|
|
"num_tokens": 20615811.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.494419431686401,
|
|
"epoch": 0.8640730067243035,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000493356474710561,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.19076516330242158,
|
|
"num_tokens": 20627679.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.464853763580322,
|
|
"epoch": 0.8645533141210374,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000493348202677517,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.1919398859143257,
|
|
"num_tokens": 20638879.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.8645533141210374,
|
|
"eval_entropy": 5.286833784162911,
|
|
"eval_loss": 5.323857307434082,
|
|
"eval_mean_token_accuracy": 0.1975427721247898,
|
|
"eval_num_tokens": 20638879.0,
|
|
"eval_runtime": 26.7611,
|
|
"eval_samples_per_second": 1226.221,
|
|
"eval_steps_per_second": 153.282,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.465018701553345,
|
|
"epoch": 0.8650336215177714,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004933399255750761,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.19821795225143432,
|
|
"num_tokens": 20649729.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.473826360702515,
|
|
"epoch": 0.8655139289145053,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004933316434034304,
|
|
"loss": 5.3513,
|
|
"mean_token_accuracy": 0.1979672983288765,
|
|
"num_tokens": 20660473.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.465569639205933,
|
|
"epoch": 0.8659942363112392,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004933233561627723,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.19368159919977188,
|
|
"num_tokens": 20671776.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.410588788986206,
|
|
"epoch": 0.866474543707973,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004933150638532942,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.19459910690784454,
|
|
"num_tokens": 20684147.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.4519812107086185,
|
|
"epoch": 0.866954851104707,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004933067664751885,
|
|
"loss": 5.26,
|
|
"mean_token_accuracy": 0.19342486262321473,
|
|
"num_tokens": 20695248.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.455672264099121,
|
|
"epoch": 0.8674351585014409,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000493298464028648,
|
|
"loss": 5.2891,
|
|
"mean_token_accuracy": 0.1953929379582405,
|
|
"num_tokens": 20707772.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.421330499649048,
|
|
"epoch": 0.8679154658981748,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004932901565138653,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.18553505837917328,
|
|
"num_tokens": 20718813.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.388991022109986,
|
|
"epoch": 0.8683957732949087,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004932818439310334,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.19860336780548096,
|
|
"num_tokens": 20730939.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.50047082901001,
|
|
"epoch": 0.8688760806916427,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004932735262803452,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.18946021050214767,
|
|
"num_tokens": 20742990.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.403319835662842,
|
|
"epoch": 0.8693563880883766,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004932652035619939,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.19417099207639693,
|
|
"num_tokens": 20754076.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.43856725692749,
|
|
"epoch": 0.8698366954851104,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004932568757761727,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.1962976187467575,
|
|
"num_tokens": 20765538.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.459097242355346,
|
|
"epoch": 0.8703170028818443,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004932485429230748,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.1885312393307686,
|
|
"num_tokens": 20776359.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.463164806365967,
|
|
"epoch": 0.8707973102785783,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.000493240205002894,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.19182345718145372,
|
|
"num_tokens": 20787581.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.481852436065674,
|
|
"epoch": 0.8712776176753122,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004932318620158235,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.18450047373771666,
|
|
"num_tokens": 20799904.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.4440511703491214,
|
|
"epoch": 0.8717579250720461,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004932235139620574,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.19503526985645295,
|
|
"num_tokens": 20810238.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.399209022521973,
|
|
"epoch": 0.8722382324687801,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004932151608417892,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.19505088329315184,
|
|
"num_tokens": 20821349.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.338546323776245,
|
|
"epoch": 0.872718539865514,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004932068026552127,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.19114267230033874,
|
|
"num_tokens": 20834788.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.471367216110229,
|
|
"epoch": 0.8731988472622478,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004931984394025224,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.1920815736055374,
|
|
"num_tokens": 20845571.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.511144161224365,
|
|
"epoch": 0.8736791546589817,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004931900710839123,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.19066193997859954,
|
|
"num_tokens": 20857209.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.496369647979736,
|
|
"epoch": 0.8741594620557157,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004931816976995766,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.18918283730745317,
|
|
"num_tokens": 20870624.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.434632158279419,
|
|
"epoch": 0.8746397694524496,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004931733192497097,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.19692012220621108,
|
|
"num_tokens": 20881769.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.403829193115234,
|
|
"epoch": 0.8751200768491835,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004931649357345062,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.19137932360172272,
|
|
"num_tokens": 20892817.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.42297682762146,
|
|
"epoch": 0.8756003842459174,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004931565471541606,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.19673141539096833,
|
|
"num_tokens": 20903042.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.398336696624756,
|
|
"epoch": 0.8760806916426513,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004931481535088679,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.20198381543159485,
|
|
"num_tokens": 20914684.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.313979530334473,
|
|
"epoch": 0.8765609990393852,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004931397547988229,
|
|
"loss": 5.2463,
|
|
"mean_token_accuracy": 0.19970450103282927,
|
|
"num_tokens": 20926585.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.456323289871216,
|
|
"epoch": 0.8770413064361191,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004931313510242204,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.19428781419992447,
|
|
"num_tokens": 20939729.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.490614891052246,
|
|
"epoch": 0.877521613832853,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004931229421852557,
|
|
"loss": 5.2158,
|
|
"mean_token_accuracy": 0.19378915280103684,
|
|
"num_tokens": 20951697.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.516729497909546,
|
|
"epoch": 0.878001921229587,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000493114528282124,
|
|
"loss": 5.3364,
|
|
"mean_token_accuracy": 0.19237001240253448,
|
|
"num_tokens": 20962729.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.335696220397949,
|
|
"epoch": 0.8784822286263209,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004931061093150206,
|
|
"loss": 5.2139,
|
|
"mean_token_accuracy": 0.1974906161427498,
|
|
"num_tokens": 20973331.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.326574850082397,
|
|
"epoch": 0.8789625360230547,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004930976852841409,
|
|
"loss": 5.2236,
|
|
"mean_token_accuracy": 0.19659557938575745,
|
|
"num_tokens": 20985609.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.3948503017425535,
|
|
"epoch": 0.8794428434197886,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004930892561896806,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.18980914056301118,
|
|
"num_tokens": 20997231.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.483728122711182,
|
|
"epoch": 0.8799231508165226,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004930808220318354,
|
|
"loss": 5.2438,
|
|
"mean_token_accuracy": 0.19808146804571153,
|
|
"num_tokens": 21008511.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.427802610397339,
|
|
"epoch": 0.8804034582132565,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004930723828108012,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.19404202550649643,
|
|
"num_tokens": 21019108.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.379651308059692,
|
|
"epoch": 0.8808837656099904,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004930639385267736,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.19692479968070983,
|
|
"num_tokens": 21030621.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.341795492172241,
|
|
"epoch": 0.8813640730067243,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.000493055489179949,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.19510714262723922,
|
|
"num_tokens": 21041778.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.3855572700500485,
|
|
"epoch": 0.8818443804034583,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004930470347705234,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.19265422374010086,
|
|
"num_tokens": 21054257.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.4251580238342285,
|
|
"epoch": 0.8823246878001921,
|
|
"grad_norm": 4.75,
|
|
"learning_rate": 0.000493038575298693,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.18532087057828903,
|
|
"num_tokens": 21066378.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.390190076828003,
|
|
"epoch": 0.882804995196926,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004930301107646545,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.1949562445282936,
|
|
"num_tokens": 21078913.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.4374512195587155,
|
|
"epoch": 0.8832853025936599,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004930216411686042,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.19003055542707442,
|
|
"num_tokens": 21090500.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.456872606277466,
|
|
"epoch": 0.8837656099903939,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004930131665107387,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.19188951402902604,
|
|
"num_tokens": 21102793.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.51307864189148,
|
|
"epoch": 0.8842459173871278,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000493004686791255,
|
|
"loss": 5.3625,
|
|
"mean_token_accuracy": 0.18110193461179733,
|
|
"num_tokens": 21114504.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.461127519607544,
|
|
"epoch": 0.8847262247838616,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004929962020103496,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.19226648956537246,
|
|
"num_tokens": 21126733.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.382491874694824,
|
|
"epoch": 0.8852065321805955,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004929877121682198,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.19614624381065368,
|
|
"num_tokens": 21138045.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.408035373687744,
|
|
"epoch": 0.8856868395773295,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004929792172650627,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.18462480753660201,
|
|
"num_tokens": 21151562.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.442537450790406,
|
|
"epoch": 0.8861671469740634,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004929707173010753,
|
|
"loss": 5.2544,
|
|
"mean_token_accuracy": 0.19313101023435592,
|
|
"num_tokens": 21162943.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.441433429718018,
|
|
"epoch": 0.8866474543707973,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004929622122764552,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.19395060688257218,
|
|
"num_tokens": 21174392.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.398846864700317,
|
|
"epoch": 0.8871277617675313,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004929537021913997,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.20172928124666215,
|
|
"num_tokens": 21185372.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.403616046905517,
|
|
"epoch": 0.8876080691642652,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004929451870461064,
|
|
"loss": 5.277,
|
|
"mean_token_accuracy": 0.18911509811878205,
|
|
"num_tokens": 21197044.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.322634983062744,
|
|
"epoch": 0.888088376560999,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004929366668407731,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.2012103334069252,
|
|
"num_tokens": 21207729.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.468259954452515,
|
|
"epoch": 0.8885686839577329,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004929281415755974,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.18907846808433532,
|
|
"num_tokens": 21218909.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.529673290252686,
|
|
"epoch": 0.8890489913544669,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004929196112507775,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.18847547620534896,
|
|
"num_tokens": 21230543.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.423626852035523,
|
|
"epoch": 0.8895292987512008,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004929110758665112,
|
|
"loss": 5.3056,
|
|
"mean_token_accuracy": 0.1910865843296051,
|
|
"num_tokens": 21242064.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.4400286197662355,
|
|
"epoch": 0.8900096061479347,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004929025354229969,
|
|
"loss": 5.3362,
|
|
"mean_token_accuracy": 0.18930555433034896,
|
|
"num_tokens": 21254321.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.3451207160949705,
|
|
"epoch": 0.8904899135446686,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004928939899204326,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.1981326386332512,
|
|
"num_tokens": 21264741.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.412546539306641,
|
|
"epoch": 0.8909702209414025,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000492885439359017,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.19139549434185027,
|
|
"num_tokens": 21276834.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.3864452838897705,
|
|
"epoch": 0.8914505283381364,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004928768837389485,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.20062124282121657,
|
|
"num_tokens": 21287108.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.391584873199463,
|
|
"epoch": 0.8919308357348703,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004928683230604257,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.18854022026062012,
|
|
"num_tokens": 21299942.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.509386730194092,
|
|
"epoch": 0.8924111431316042,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004928597573236474,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.18812628239393234,
|
|
"num_tokens": 21311243.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.454556941986084,
|
|
"epoch": 0.8928914505283382,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004928511865288123,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.19766252487897873,
|
|
"num_tokens": 21322291.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.4456394672393795,
|
|
"epoch": 0.8933717579250721,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004928426106761197,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.19672485589981079,
|
|
"num_tokens": 21333257.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.33490309715271,
|
|
"epoch": 0.8938520653218059,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004928340297657685,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.19007812291383744,
|
|
"num_tokens": 21345848.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.412633752822876,
|
|
"epoch": 0.8943323727185398,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004928254437979578,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.191494420170784,
|
|
"num_tokens": 21357693.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.457951450347901,
|
|
"epoch": 0.8948126801152738,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004928168527728873,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.18513780683279038,
|
|
"num_tokens": 21369653.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.5386919498443605,
|
|
"epoch": 0.8952929875120077,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004928082566907562,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.1909639209508896,
|
|
"num_tokens": 21383924.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.5054093360900875,
|
|
"epoch": 0.8957732949087416,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004927996555517642,
|
|
"loss": 5.2727,
|
|
"mean_token_accuracy": 0.19004034399986267,
|
|
"num_tokens": 21395963.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.416197824478149,
|
|
"epoch": 0.8962536023054755,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004927910493561109,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.1947443053126335,
|
|
"num_tokens": 21408200.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.468182706832886,
|
|
"epoch": 0.8967339097022095,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000492782438103996,
|
|
"loss": 5.3877,
|
|
"mean_token_accuracy": 0.1846337378025055,
|
|
"num_tokens": 21419963.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.438816738128662,
|
|
"epoch": 0.8972142170989433,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004927738217956197,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.18921612203121185,
|
|
"num_tokens": 21431824.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.319002103805542,
|
|
"epoch": 0.8976945244956772,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004927652004311819,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.205044224858284,
|
|
"num_tokens": 21442354.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.465283536911011,
|
|
"epoch": 0.8981748318924111,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004927565740108828,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.190805584192276,
|
|
"num_tokens": 21453734.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.451039218902588,
|
|
"epoch": 0.8986551392891451,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004927479425349226,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.19552082270383836,
|
|
"num_tokens": 21465471.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.484200096130371,
|
|
"epoch": 0.899135446685879,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004927393060035018,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.18132619708776473,
|
|
"num_tokens": 21477775.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.413498020172119,
|
|
"epoch": 0.8996157540826129,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004927306644168207,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.20159902423620224,
|
|
"num_tokens": 21489319.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.5404274463653564,
|
|
"epoch": 0.9000960614793467,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004927220177750803,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.18541965037584304,
|
|
"num_tokens": 21499742.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.381626319885254,
|
|
"epoch": 0.9005763688760807,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004927133660784811,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.19671661108732225,
|
|
"num_tokens": 21511063.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.477992582321167,
|
|
"epoch": 0.9010566762728146,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004927047093272241,
|
|
"loss": 5.2235,
|
|
"mean_token_accuracy": 0.19456267952919007,
|
|
"num_tokens": 21522500.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.4860467433929445,
|
|
"epoch": 0.9015369836695485,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00049269604752151,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.18959935158491134,
|
|
"num_tokens": 21533578.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.428734636306762,
|
|
"epoch": 0.9020172910662824,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004926873806615403,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.1863044410943985,
|
|
"num_tokens": 21544296.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.45260214805603,
|
|
"epoch": 0.9024975984630164,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004926787087475158,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.1807158872485161,
|
|
"num_tokens": 21555386.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.4186985969543455,
|
|
"epoch": 0.9029779058597502,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004926700317796382,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.20300321131944657,
|
|
"num_tokens": 21566527.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.508444929122925,
|
|
"epoch": 0.9034582132564841,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004926613497581088,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.1892908990383148,
|
|
"num_tokens": 21576870.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.359063148498535,
|
|
"epoch": 0.9039385206532181,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004926526626831292,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.19587481319904326,
|
|
"num_tokens": 21588113.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.353362083435059,
|
|
"epoch": 0.904418828049952,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 0.0004926439705549011,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.19386613965034485,
|
|
"num_tokens": 21599307.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.408993339538574,
|
|
"epoch": 0.9048991354466859,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004926352733736262,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.1931881159543991,
|
|
"num_tokens": 21609961.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.386229658126831,
|
|
"epoch": 0.9053794428434198,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004926265711395065,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.1952400028705597,
|
|
"num_tokens": 21622222.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.427256631851196,
|
|
"epoch": 0.9058597502401537,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000492617863852744,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.19958580285310745,
|
|
"num_tokens": 21632843.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.442908668518067,
|
|
"epoch": 0.9063400576368876,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004926091515135409,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.1915742814540863,
|
|
"num_tokens": 21645387.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.4399489402771,
|
|
"epoch": 0.9068203650336215,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004926004341220995,
|
|
"loss": 5.2511,
|
|
"mean_token_accuracy": 0.19855644255876542,
|
|
"num_tokens": 21656787.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.497275400161743,
|
|
"epoch": 0.9073006724303554,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004925917116786222,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.1951787829399109,
|
|
"num_tokens": 21667800.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.495297241210937,
|
|
"epoch": 0.9077809798270894,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004925829841833114,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.18935434073209761,
|
|
"num_tokens": 21679297.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.450942420959473,
|
|
"epoch": 0.9082612872238233,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004925742516363699,
|
|
"loss": 5.3369,
|
|
"mean_token_accuracy": 0.18925965428352357,
|
|
"num_tokens": 21692956.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.4104471683502195,
|
|
"epoch": 0.9087415946205571,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004925655140380002,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.20237629115581512,
|
|
"num_tokens": 21704852.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.428700923919678,
|
|
"epoch": 0.909221902017291,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004925567713884054,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.1968642830848694,
|
|
"num_tokens": 21715886.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.405050420761109,
|
|
"epoch": 0.909702209414025,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004925480236877884,
|
|
"loss": 5.2518,
|
|
"mean_token_accuracy": 0.1946304351091385,
|
|
"num_tokens": 21727157.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.447952604293823,
|
|
"epoch": 0.9101825168107589,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004925392709363522,
|
|
"loss": 5.2679,
|
|
"mean_token_accuracy": 0.19367639422416688,
|
|
"num_tokens": 21738232.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.4061009883880615,
|
|
"epoch": 0.9106628242074928,
|
|
"grad_norm": 8.375,
|
|
"learning_rate": 0.0004925305131343001,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.1921161398291588,
|
|
"num_tokens": 21749029.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.449977064132691,
|
|
"epoch": 0.9111431316042267,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004925217502818355,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.1900743365287781,
|
|
"num_tokens": 21761243.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.421607542037964,
|
|
"epoch": 0.9116234390009607,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004925129823791616,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.18976200073957444,
|
|
"num_tokens": 21772623.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.518741035461426,
|
|
"epoch": 0.9121037463976945,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004925042094264822,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.19375300854444505,
|
|
"num_tokens": 21782611.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.358087348937988,
|
|
"epoch": 0.9125840537944284,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000492495431424001,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.20286647230386734,
|
|
"num_tokens": 21793946.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.495607376098633,
|
|
"epoch": 0.9130643611911623,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004924866483719216,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.1815917894244194,
|
|
"num_tokens": 21803878.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.444768953323364,
|
|
"epoch": 0.9135446685878963,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004924778602704481,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.19565667062997819,
|
|
"num_tokens": 21815187.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.430060148239136,
|
|
"epoch": 0.9140249759846302,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004924690671197845,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.19788024872541427,
|
|
"num_tokens": 21825597.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.357778072357178,
|
|
"epoch": 0.914505283381364,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004924602689201348,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.19639855921268462,
|
|
"num_tokens": 21837110.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.611219787597657,
|
|
"epoch": 0.9149855907780979,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004924514656717034,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.18200843185186386,
|
|
"num_tokens": 21847754.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.407113742828369,
|
|
"epoch": 0.9154658981748319,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004924426573746948,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.18910196274518967,
|
|
"num_tokens": 21859162.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.417432260513306,
|
|
"epoch": 0.9159462055715658,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004924338440293131,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.19544493556022643,
|
|
"num_tokens": 21870826.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.455105400085449,
|
|
"epoch": 0.9164265129682997,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004924250256357635,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.19488669335842132,
|
|
"num_tokens": 21882003.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.4050263404846195,
|
|
"epoch": 0.9169068203650336,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004924162021942502,
|
|
"loss": 5.235,
|
|
"mean_token_accuracy": 0.19613129198551177,
|
|
"num_tokens": 21894132.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.371571254730225,
|
|
"epoch": 0.9173871277617676,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004924073737049784,
|
|
"loss": 5.2127,
|
|
"mean_token_accuracy": 0.1983230859041214,
|
|
"num_tokens": 21904951.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.398392105102539,
|
|
"epoch": 0.9178674351585014,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004923985401681528,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.1969005659222603,
|
|
"num_tokens": 21917100.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.426608943939209,
|
|
"epoch": 0.9183477425552353,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.0004923897015839788,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.19067178815603256,
|
|
"num_tokens": 21927541.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.450834941864014,
|
|
"epoch": 0.9188280499519692,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004923808579526613,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.19361897855997084,
|
|
"num_tokens": 21938723.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.417177438735962,
|
|
"epoch": 0.9193083573487032,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004923720092744059,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.2003900244832039,
|
|
"num_tokens": 21950424.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.422094869613647,
|
|
"epoch": 0.9197886647454371,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004923631555494179,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.18971359729766846,
|
|
"num_tokens": 21961030.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.448723220825196,
|
|
"epoch": 0.920268972142171,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004923542967779028,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.19773112684488298,
|
|
"num_tokens": 21971625.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.4015871524810795,
|
|
"epoch": 0.920749279538905,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004923454329600664,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.19428745657205582,
|
|
"num_tokens": 21983733.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.3828229904174805,
|
|
"epoch": 0.9212295869356388,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004923365640961143,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.2001131609082222,
|
|
"num_tokens": 21995621.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.473578929901123,
|
|
"epoch": 0.9217098943323727,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004923276901862526,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.19182861596345901,
|
|
"num_tokens": 22007325.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.423218774795532,
|
|
"epoch": 0.9221902017291066,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004923188112306874,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.19283992648124695,
|
|
"num_tokens": 22017733.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.444092273712158,
|
|
"epoch": 0.9226705091258406,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004923099272296246,
|
|
"loss": 5.345,
|
|
"mean_token_accuracy": 0.1922829493880272,
|
|
"num_tokens": 22030451.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.440569734573364,
|
|
"epoch": 0.9231508165225745,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004923010381832706,
|
|
"loss": 5.3004,
|
|
"mean_token_accuracy": 0.1827593296766281,
|
|
"num_tokens": 22042626.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.383125972747803,
|
|
"epoch": 0.9236311239193083,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004922921440918318,
|
|
"loss": 5.2689,
|
|
"mean_token_accuracy": 0.1932683065533638,
|
|
"num_tokens": 22053314.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.496197509765625,
|
|
"epoch": 0.9241114313160422,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004922832449555144,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.1852697476744652,
|
|
"num_tokens": 22064395.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.434769201278686,
|
|
"epoch": 0.9245917387127762,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004922743407745255,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.19321634620428085,
|
|
"num_tokens": 22075960.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.474955129623413,
|
|
"epoch": 0.9250720461095101,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004922654315490714,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.19444866627454757,
|
|
"num_tokens": 22086034.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.433138084411621,
|
|
"epoch": 0.925552353506244,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004922565172793593,
|
|
"loss": 5.305,
|
|
"mean_token_accuracy": 0.19347228705883027,
|
|
"num_tokens": 22096184.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.395916604995728,
|
|
"epoch": 0.9260326609029779,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004922475979655958,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.1929107204079628,
|
|
"num_tokens": 22108795.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.364714574813843,
|
|
"epoch": 0.9265129682997119,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004922386736079883,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.19042983651161194,
|
|
"num_tokens": 22119608.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.429565668106079,
|
|
"epoch": 0.9269932756964457,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004922297442067438,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.1987159162759781,
|
|
"num_tokens": 22131621.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.491347694396973,
|
|
"epoch": 0.9274735830931796,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004922208097620697,
|
|
"loss": 5.2033,
|
|
"mean_token_accuracy": 0.19708802551031113,
|
|
"num_tokens": 22142745.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.383749055862427,
|
|
"epoch": 0.9279538904899135,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004922118702741735,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.18604227900505066,
|
|
"num_tokens": 22155457.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.446541404724121,
|
|
"epoch": 0.9284341978866475,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004922029257432625,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.2081572011113167,
|
|
"num_tokens": 22165955.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.443132305145264,
|
|
"epoch": 0.9289145052833814,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004921939761695446,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.1943787917494774,
|
|
"num_tokens": 22178142.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.3700165271759035,
|
|
"epoch": 0.9293948126801153,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004921850215532275,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.19673469960689544,
|
|
"num_tokens": 22190315.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.4112269401550295,
|
|
"epoch": 0.9298751200768491,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004921760618945192,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.1971499055624008,
|
|
"num_tokens": 22201785.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.409576416015625,
|
|
"epoch": 0.9303554274735831,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004921670971936276,
|
|
"loss": 5.2066,
|
|
"mean_token_accuracy": 0.1991860091686249,
|
|
"num_tokens": 22212471.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.426486539840698,
|
|
"epoch": 0.930835734870317,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004921581274507607,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.19514895975589752,
|
|
"num_tokens": 22223188.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.363044929504395,
|
|
"epoch": 0.9313160422670509,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000492149152666127,
|
|
"loss": 5.2746,
|
|
"mean_token_accuracy": 0.19247548878192902,
|
|
"num_tokens": 22233978.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.4238334655761715,
|
|
"epoch": 0.9317963496637848,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004921401728399348,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.2040674388408661,
|
|
"num_tokens": 22244713.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.4172224521636965,
|
|
"epoch": 0.9322766570605188,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004921311879723926,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.19613376408815383,
|
|
"num_tokens": 22256192.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.405217790603638,
|
|
"epoch": 0.9327569644572526,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004921221980637088,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.190078204870224,
|
|
"num_tokens": 22268294.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.441168260574341,
|
|
"epoch": 0.9332372718539865,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004921132031140925,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.1992150589823723,
|
|
"num_tokens": 22278952.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.43465576171875,
|
|
"epoch": 0.9337175792507204,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004921042031237521,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.19227020293474198,
|
|
"num_tokens": 22291057.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.454956960678101,
|
|
"epoch": 0.9341978866474544,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004920951980928969,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.1936467096209526,
|
|
"num_tokens": 22302479.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.520135116577149,
|
|
"epoch": 0.9346781940441883,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004920861880217359,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.18474303483963012,
|
|
"num_tokens": 22315116.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.487334823608398,
|
|
"epoch": 0.9351585014409222,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004920771729104781,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.19045030176639557,
|
|
"num_tokens": 22327548.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.400779676437378,
|
|
"epoch": 0.9356388088376562,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004920681527593329,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.1992402970790863,
|
|
"num_tokens": 22339154.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.39352502822876,
|
|
"epoch": 0.93611911623439,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004920591275685098,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.19385868757963182,
|
|
"num_tokens": 22350781.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.460879516601563,
|
|
"epoch": 0.9365994236311239,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004920500973382184,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.1979560524225235,
|
|
"num_tokens": 22361990.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.372137975692749,
|
|
"epoch": 0.9370797310278578,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004920410620686682,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.20329722613096238,
|
|
"num_tokens": 22372973.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.351499605178833,
|
|
"epoch": 0.9375600384245918,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004920320217600689,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.2007537841796875,
|
|
"num_tokens": 22384369.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.457377338409424,
|
|
"epoch": 0.9380403458213257,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004920229764126306,
|
|
"loss": 5.3103,
|
|
"mean_token_accuracy": 0.19769012033939362,
|
|
"num_tokens": 22395792.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.3956748962402346,
|
|
"epoch": 0.9385206532180596,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004920139260265632,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.18901417404413223,
|
|
"num_tokens": 22408182.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.506560230255127,
|
|
"epoch": 0.9390009606147934,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004920048706020769,
|
|
"loss": 5.42,
|
|
"mean_token_accuracy": 0.18410638719797134,
|
|
"num_tokens": 22419774.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.390211725234986,
|
|
"epoch": 0.9394812680115274,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004919958101393817,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.20409280955791473,
|
|
"num_tokens": 22430210.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.3944535732269285,
|
|
"epoch": 0.9399615754082613,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004919867446386883,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.1972271278500557,
|
|
"num_tokens": 22442444.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.337864923477173,
|
|
"epoch": 0.9404418828049952,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000491977674100207,
|
|
"loss": 5.2497,
|
|
"mean_token_accuracy": 0.19875272661447524,
|
|
"num_tokens": 22455521.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.48582239151001,
|
|
"epoch": 0.9409221902017291,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004919685985241483,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.19794100373983384,
|
|
"num_tokens": 22466997.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.420718431472778,
|
|
"epoch": 0.9414024975984631,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000491959517910723,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.2002217650413513,
|
|
"num_tokens": 22477851.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.325788736343384,
|
|
"epoch": 0.9418828049951969,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004919504322601421,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.19008239656686782,
|
|
"num_tokens": 22489319.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.317502832412719,
|
|
"epoch": 0.9423631123919308,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004919413415726162,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.20310045182704925,
|
|
"num_tokens": 22500847.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.4683756828308105,
|
|
"epoch": 0.9428434197886647,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004919322458483566,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.19434639513492585,
|
|
"num_tokens": 22512719.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.398497915267944,
|
|
"epoch": 0.9433237271853987,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004919231450875745,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.1974311351776123,
|
|
"num_tokens": 22522984.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.40466160774231,
|
|
"epoch": 0.9438040345821326,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004919140392904809,
|
|
"loss": 5.2554,
|
|
"mean_token_accuracy": 0.1965935543179512,
|
|
"num_tokens": 22534816.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.371817255020142,
|
|
"epoch": 0.9442843419788665,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004919049284572875,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.19110070317983627,
|
|
"num_tokens": 22545753.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.461672353744507,
|
|
"epoch": 0.9447646493756003,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004918958125882058,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.18368452340364455,
|
|
"num_tokens": 22557237.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.475539255142212,
|
|
"epoch": 0.9452449567723343,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004918866916834474,
|
|
"loss": 5.2518,
|
|
"mean_token_accuracy": 0.19763409495353698,
|
|
"num_tokens": 22568909.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.441458368301392,
|
|
"epoch": 0.9457252641690682,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004918775657432239,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.18044845014810562,
|
|
"num_tokens": 22582162.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.37942419052124,
|
|
"epoch": 0.9462055715658021,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004918684347677474,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.1916930004954338,
|
|
"num_tokens": 22592405.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.490902757644653,
|
|
"epoch": 0.946685878962536,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004918592987572298,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.1960650846362114,
|
|
"num_tokens": 22603588.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.541545867919922,
|
|
"epoch": 0.94716618635927,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004918501577118832,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.19618629813194274,
|
|
"num_tokens": 22614995.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.39432201385498,
|
|
"epoch": 0.9476464937560038,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00049184101163192,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.1880181163549423,
|
|
"num_tokens": 22627556.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.391653347015381,
|
|
"epoch": 0.9481268011527377,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004918318605175522,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.19757845103740693,
|
|
"num_tokens": 22638339.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.469990015029907,
|
|
"epoch": 0.9486071085494716,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004918227043689924,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.19942961037158966,
|
|
"num_tokens": 22648922.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.377200937271118,
|
|
"epoch": 0.9490874159462056,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004918135431864534,
|
|
"loss": 5.2762,
|
|
"mean_token_accuracy": 0.19819725155830384,
|
|
"num_tokens": 22662006.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.35459942817688,
|
|
"epoch": 0.9495677233429395,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004918043769701478,
|
|
"loss": 5.2347,
|
|
"mean_token_accuracy": 0.1963895782828331,
|
|
"num_tokens": 22674649.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.467649030685425,
|
|
"epoch": 0.9500480307396734,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004917952057202882,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.1841025710105896,
|
|
"num_tokens": 22685971.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.379204130172729,
|
|
"epoch": 0.9505283381364072,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004917860294370877,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.19822804480791092,
|
|
"num_tokens": 22696174.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.485464286804199,
|
|
"epoch": 0.9510086455331412,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004917768481207593,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.19342151433229446,
|
|
"num_tokens": 22706983.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.385168981552124,
|
|
"epoch": 0.9514889529298751,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004917676617715162,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.19519501626491548,
|
|
"num_tokens": 22718251.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.3356578826904295,
|
|
"epoch": 0.951969260326609,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004917584703895717,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.20291350781917572,
|
|
"num_tokens": 22730071.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.422244310379028,
|
|
"epoch": 0.952449567723343,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004917492739751391,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.1945216625928879,
|
|
"num_tokens": 22742027.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.371307468414306,
|
|
"epoch": 0.9529298751200769,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000491740072528432,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.2084452837705612,
|
|
"num_tokens": 22752946.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.4368510246276855,
|
|
"epoch": 0.9534101825168108,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.000491730866049664,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.19621892422437667,
|
|
"num_tokens": 22763944.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.406138706207275,
|
|
"epoch": 0.9538904899135446,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004917216545390489,
|
|
"loss": 5.2098,
|
|
"mean_token_accuracy": 0.1996043637394905,
|
|
"num_tokens": 22774414.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.372554540634155,
|
|
"epoch": 0.9543707973102786,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004917124379968004,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.20525473058223725,
|
|
"num_tokens": 22785533.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.2957335948944095,
|
|
"epoch": 0.9548511047070125,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004917032164231327,
|
|
"loss": 5.1165,
|
|
"mean_token_accuracy": 0.20203149318695068,
|
|
"num_tokens": 22795809.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.407790422439575,
|
|
"epoch": 0.9553314121037464,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004916939898182598,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.19422866106033326,
|
|
"num_tokens": 22807705.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.4711041927337645,
|
|
"epoch": 0.9558117195004803,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004916847581823958,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.19753745943307877,
|
|
"num_tokens": 22818852.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.345225811004639,
|
|
"epoch": 0.9562920268972143,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004916755215157552,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.1991084486246109,
|
|
"num_tokens": 22829146.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.348565673828125,
|
|
"epoch": 0.9567723342939481,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004916662798185524,
|
|
"loss": 5.2327,
|
|
"mean_token_accuracy": 0.20377150774002076,
|
|
"num_tokens": 22840088.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.453205251693726,
|
|
"epoch": 0.957252641690682,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004916570330910019,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.19948677569627762,
|
|
"num_tokens": 22852470.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.464549446105957,
|
|
"epoch": 0.9577329490874159,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004916477813333185,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.18716312646865846,
|
|
"num_tokens": 22863673.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.395220947265625,
|
|
"epoch": 0.9582132564841499,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004916385245457168,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.18905411511659623,
|
|
"num_tokens": 22874888.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.394779539108276,
|
|
"epoch": 0.9586935638808838,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000491629262728412,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.18617796152830124,
|
|
"num_tokens": 22886811.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.446366930007935,
|
|
"epoch": 0.9591738712776177,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004916199958816188,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.196870881319046,
|
|
"num_tokens": 22898777.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.441407680511475,
|
|
"epoch": 0.9596541786743515,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004916107240055527,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.19878754615783692,
|
|
"num_tokens": 22910804.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.473761034011841,
|
|
"epoch": 0.9601344860710855,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004916014471004287,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.19703474044799804,
|
|
"num_tokens": 22922002.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.406247186660766,
|
|
"epoch": 0.9606147934678194,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004915921651664622,
|
|
"loss": 5.2423,
|
|
"mean_token_accuracy": 0.1918477311730385,
|
|
"num_tokens": 22933471.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.338607263565064,
|
|
"epoch": 0.9610951008645533,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000491582878203869,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.20101817995309829,
|
|
"num_tokens": 22945303.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.408805561065674,
|
|
"epoch": 0.9615754082612872,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004915735862128643,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.18877181857824327,
|
|
"num_tokens": 22956620.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.453514099121094,
|
|
"epoch": 0.9620557156580212,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004915642891936641,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.19188073575496672,
|
|
"num_tokens": 22968941.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.435528182983399,
|
|
"epoch": 0.962536023054755,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004915549871464841,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.19511342495679856,
|
|
"num_tokens": 22980222.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.518212747573853,
|
|
"epoch": 0.9630163304514889,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004915456800715403,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.1914032906293869,
|
|
"num_tokens": 22991156.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.46331205368042,
|
|
"epoch": 0.9634966378482228,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000491536367969049,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.18710901588201523,
|
|
"num_tokens": 23002939.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.50247859954834,
|
|
"epoch": 0.9639769452449568,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004915270508392261,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.18953993022441865,
|
|
"num_tokens": 23015590.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.3677287101745605,
|
|
"epoch": 0.9644572526416907,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000491517728682288,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.20130778700113297,
|
|
"num_tokens": 23026387.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.335800695419311,
|
|
"epoch": 0.9649375600384246,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004915084014984512,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.20094712674617768,
|
|
"num_tokens": 23037475.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.405805444717407,
|
|
"epoch": 0.9654178674351584,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004914990692879322,
|
|
"loss": 5.1927,
|
|
"mean_token_accuracy": 0.19749083369970322,
|
|
"num_tokens": 23049305.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.392905569076538,
|
|
"epoch": 0.9658981748318924,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004914897320509478,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.19956698566675185,
|
|
"num_tokens": 23061765.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.356211233139038,
|
|
"epoch": 0.9663784822286263,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004914803897877146,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.18860531151294707,
|
|
"num_tokens": 23072355.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.486581802368164,
|
|
"epoch": 0.9668587896253602,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004914710424984495,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.19056099206209182,
|
|
"num_tokens": 23085583.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.539778089523315,
|
|
"epoch": 0.9673390970220941,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004914616901833696,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.19322179704904557,
|
|
"num_tokens": 23095942.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.410343170166016,
|
|
"epoch": 0.9678194044188281,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000491452332842692,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.20075419694185256,
|
|
"num_tokens": 23106540.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.408917665481567,
|
|
"epoch": 0.968299711815562,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000491442970476634,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.19609098136425018,
|
|
"num_tokens": 23118006.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.3709639549255375,
|
|
"epoch": 0.9687800192122958,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004914336030854129,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.2073349252343178,
|
|
"num_tokens": 23129103.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.35005898475647,
|
|
"epoch": 0.9692603266090298,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004914242306692461,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.203034870326519,
|
|
"num_tokens": 23140009.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.426367378234863,
|
|
"epoch": 0.9697406340057637,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004914148532283516,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.198285274207592,
|
|
"num_tokens": 23150982.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.405374574661255,
|
|
"epoch": 0.9702209414024976,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004914054707629466,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.19507062286138535,
|
|
"num_tokens": 23161834.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.450302648544311,
|
|
"epoch": 0.9707012487992315,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004913960832732493,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.19049630612134932,
|
|
"num_tokens": 23173355.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.41361436843872,
|
|
"epoch": 0.9711815561959655,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004913866907594774,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.19158721417188646,
|
|
"num_tokens": 23185075.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.400365924835205,
|
|
"epoch": 0.9716618635926993,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004913772932218491,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.2066294312477112,
|
|
"num_tokens": 23195590.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.46629638671875,
|
|
"epoch": 0.9721421709894332,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004913678906605825,
|
|
"loss": 5.2426,
|
|
"mean_token_accuracy": 0.19075394421815872,
|
|
"num_tokens": 23207668.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.3628182888031,
|
|
"epoch": 0.9726224783861671,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004913584830758961,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.20411105304956437,
|
|
"num_tokens": 23218497.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.485825920104981,
|
|
"epoch": 0.9731027857829011,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004913490704680081,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.19035015255212784,
|
|
"num_tokens": 23230575.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.443599700927734,
|
|
"epoch": 0.973583093179635,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004913396528371371,
|
|
"loss": 5.3108,
|
|
"mean_token_accuracy": 0.1952358603477478,
|
|
"num_tokens": 23242348.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.4539878368377686,
|
|
"epoch": 0.9740634005763689,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004913302301835018,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.2000483050942421,
|
|
"num_tokens": 23253297.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.363252115249634,
|
|
"epoch": 0.9745437079731027,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000491320802507321,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.20342864245176315,
|
|
"num_tokens": 23265830.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.37382926940918,
|
|
"epoch": 0.9750240153698367,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004913113698088133,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.19232627749443054,
|
|
"num_tokens": 23275591.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.411358594894409,
|
|
"epoch": 0.9755043227665706,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.000491301932088198,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.19993337541818618,
|
|
"num_tokens": 23286685.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.396875524520874,
|
|
"epoch": 0.9759846301633045,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004912924893456942,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.19969007968902588,
|
|
"num_tokens": 23298776.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.398948097229004,
|
|
"epoch": 0.9764649375600384,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000491283041581521,
|
|
"loss": 5.2074,
|
|
"mean_token_accuracy": 0.19674785435199738,
|
|
"num_tokens": 23310498.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.404614448547363,
|
|
"epoch": 0.9769452449567724,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004912735887958978,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.19386743754148483,
|
|
"num_tokens": 23321089.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.397444152832032,
|
|
"epoch": 0.9774255523535063,
|
|
"grad_norm": 7.3125,
|
|
"learning_rate": 0.0004912641309890441,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.19845797270536422,
|
|
"num_tokens": 23332142.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.365348625183105,
|
|
"epoch": 0.9779058597502401,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004912546681611794,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.20434190779924394,
|
|
"num_tokens": 23343014.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.41248574256897,
|
|
"epoch": 0.978386167146974,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004912452003125234,
|
|
"loss": 5.1764,
|
|
"mean_token_accuracy": 0.2003762811422348,
|
|
"num_tokens": 23354611.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.356007862091064,
|
|
"epoch": 0.978866474543708,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.000491235727443296,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.19472320079803468,
|
|
"num_tokens": 23365608.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.415962839126587,
|
|
"epoch": 0.9793467819404419,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004912262495537171,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.19437787532806397,
|
|
"num_tokens": 23377884.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.3636270523071286,
|
|
"epoch": 0.9798270893371758,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004912167666440068,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.1989520788192749,
|
|
"num_tokens": 23389553.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.423063182830811,
|
|
"epoch": 0.9803073967339097,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004912072787143852,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.1973157823085785,
|
|
"num_tokens": 23401079.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.3419661045074465,
|
|
"epoch": 0.9807877041306436,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004911977857650725,
|
|
"loss": 5.2207,
|
|
"mean_token_accuracy": 0.19503132104873658,
|
|
"num_tokens": 23412886.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.408292293548584,
|
|
"epoch": 0.9812680115273775,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004911882877962893,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.18871003091335298,
|
|
"num_tokens": 23424758.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.3648481369018555,
|
|
"epoch": 0.9817483189241114,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004911787848082559,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.20602917820215225,
|
|
"num_tokens": 23435552.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.327121782302856,
|
|
"epoch": 0.9822286263208453,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004911692768011931,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.1991025373339653,
|
|
"num_tokens": 23446584.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.471063756942749,
|
|
"epoch": 0.9827089337175793,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004911597637753217,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.1831743985414505,
|
|
"num_tokens": 23458452.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.3861640930175785,
|
|
"epoch": 0.9831892411143132,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004911502457308623,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19358626008033752,
|
|
"num_tokens": 23470310.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.462844467163086,
|
|
"epoch": 0.983669548511047,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000491140722668036,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.19620780944824218,
|
|
"num_tokens": 23481166.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.419097423553467,
|
|
"epoch": 0.984149855907781,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000491131194587064,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.19872098714113234,
|
|
"num_tokens": 23493134.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.309445571899414,
|
|
"epoch": 0.9846301633045149,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004911216614881675,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.19742152392864226,
|
|
"num_tokens": 23504983.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.43677020072937,
|
|
"epoch": 0.9851104707012488,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004911121233715677,
|
|
"loss": 5.2451,
|
|
"mean_token_accuracy": 0.19701493978500367,
|
|
"num_tokens": 23516119.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.487496185302734,
|
|
"epoch": 0.9855907780979827,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004911025802374861,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.19557499289512634,
|
|
"num_tokens": 23528242.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.367623996734619,
|
|
"epoch": 0.9860710854947167,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004910930320861442,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.20655215233564378,
|
|
"num_tokens": 23539738.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.249183893203735,
|
|
"epoch": 0.9865513928914506,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004910834789177639,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.20073135197162628,
|
|
"num_tokens": 23551228.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.478230810165405,
|
|
"epoch": 0.9870317002881844,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004910739207325668,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.19577898383140563,
|
|
"num_tokens": 23563084.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.428914260864258,
|
|
"epoch": 0.9875120076849183,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004910643575307749,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.19401755928993225,
|
|
"num_tokens": 23574328.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.305451393127441,
|
|
"epoch": 0.9879923150816523,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004910547893126102,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.19698152542114258,
|
|
"num_tokens": 23585230.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.3722731590271,
|
|
"epoch": 0.9884726224783862,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004910452160782948,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.19246109426021576,
|
|
"num_tokens": 23596951.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.463429260253906,
|
|
"epoch": 0.9889529298751201,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000491035637828051,
|
|
"loss": 5.2438,
|
|
"mean_token_accuracy": 0.1988312765955925,
|
|
"num_tokens": 23607759.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.479205369949341,
|
|
"epoch": 0.989433237271854,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004910260545621012,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.18905027061700821,
|
|
"num_tokens": 23619631.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.387127780914307,
|
|
"epoch": 0.9899135446685879,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004910164662806679,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.20064392387866975,
|
|
"num_tokens": 23630601.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.403849124908447,
|
|
"epoch": 0.9903938520653218,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004910068729839736,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.20497233122587205,
|
|
"num_tokens": 23641330.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.4326708793640135,
|
|
"epoch": 0.9908741594620557,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004909972746722413,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.1933955430984497,
|
|
"num_tokens": 23651492.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.323132419586182,
|
|
"epoch": 0.9913544668587896,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004909876713456935,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.19787878394126893,
|
|
"num_tokens": 23661773.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.355273485183716,
|
|
"epoch": 0.9918347742555236,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004909780630045534,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.19961498230695723,
|
|
"num_tokens": 23673534.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.4471495151519775,
|
|
"epoch": 0.9923150816522575,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000490968449649044,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.19400671422481536,
|
|
"num_tokens": 23684892.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.4562681198120115,
|
|
"epoch": 0.9927953890489913,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004909588312793884,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.18994846940040588,
|
|
"num_tokens": 23696076.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.478567314147949,
|
|
"epoch": 0.9932756964457252,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004909492078958101,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.19210431426763536,
|
|
"num_tokens": 23707795.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.4126229763031,
|
|
"epoch": 0.9937560038424592,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004909395794985324,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.19707155227661133,
|
|
"num_tokens": 23720802.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.393163347244263,
|
|
"epoch": 0.9942363112391931,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004909299460877788,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.1923367574810982,
|
|
"num_tokens": 23732854.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.422337198257447,
|
|
"epoch": 0.994716618635927,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004909203076637732,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.19397395551204683,
|
|
"num_tokens": 23743593.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.4535685062408445,
|
|
"epoch": 0.9951969260326609,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004909106642267392,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.18884722143411636,
|
|
"num_tokens": 23755447.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.3973030090332035,
|
|
"epoch": 0.9956772334293948,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004909010157769006,
|
|
"loss": 5.2706,
|
|
"mean_token_accuracy": 0.19058052599430084,
|
|
"num_tokens": 23767181.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.4875547885894775,
|
|
"epoch": 0.9961575408261287,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004908913623144814,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.18907858431339264,
|
|
"num_tokens": 23776356.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.403455018997192,
|
|
"epoch": 0.9966378482228626,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000490881703839706,
|
|
"loss": 5.303,
|
|
"mean_token_accuracy": 0.19476273357868196,
|
|
"num_tokens": 23787965.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.336147689819336,
|
|
"epoch": 0.9971181556195965,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004908720403527984,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.20294632017612457,
|
|
"num_tokens": 23800327.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.365981197357177,
|
|
"epoch": 0.9975984630163305,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000490862371853983,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.19789950251579286,
|
|
"num_tokens": 23812845.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.548996543884277,
|
|
"epoch": 0.9980787704130644,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004908526983434844,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.18867339938879013,
|
|
"num_tokens": 23824831.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.400851154327393,
|
|
"epoch": 0.9985590778097982,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000490843019821527,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.19841510504484178,
|
|
"num_tokens": 23836697.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.333160829544068,
|
|
"epoch": 0.9990393852065321,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004908333362883358,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.198573562502861,
|
|
"num_tokens": 23847112.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.421288728713989,
|
|
"epoch": 0.9995196926032661,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004908236477441353,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.20078373104333877,
|
|
"num_tokens": 23858185.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.325456619262695,
|
|
"epoch": 1.0,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004908139541891505,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.2082591563463211,
|
|
"num_tokens": 23868536.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.48796706199646,
|
|
"epoch": 1.0004803073967339,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004908042556236066,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.2055366098880768,
|
|
"num_tokens": 23880283.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.445875930786133,
|
|
"epoch": 1.0009606147934678,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004907945520477286,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.199335078895092,
|
|
"num_tokens": 23892413.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.479926538467407,
|
|
"epoch": 1.0014409221902016,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004907848434617419,
|
|
"loss": 5.3238,
|
|
"mean_token_accuracy": 0.18834184110164642,
|
|
"num_tokens": 23903977.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.435224437713623,
|
|
"epoch": 1.0019212295869357,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.000490775129865872,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.19189663529396056,
|
|
"num_tokens": 23915153.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.389529132843018,
|
|
"epoch": 1.0024015369836696,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004907654112603442,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.1983468160033226,
|
|
"num_tokens": 23926043.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.299742031097412,
|
|
"epoch": 1.0028818443804035,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004907556876453843,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.20621725916862488,
|
|
"num_tokens": 23936658.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.358866500854492,
|
|
"epoch": 1.0033621517771374,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.000490745959021218,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.1891361027956009,
|
|
"num_tokens": 23947676.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.431235933303833,
|
|
"epoch": 1.0038424591738713,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004907362253880711,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.19502199590206146,
|
|
"num_tokens": 23959130.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.428387832641602,
|
|
"epoch": 1.0043227665706052,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004907264867461697,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.19288273751735688,
|
|
"num_tokens": 23969905.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.326195955276489,
|
|
"epoch": 1.004803073967339,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004907167430957399,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.1969818040728569,
|
|
"num_tokens": 23982016.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.3986588478088375,
|
|
"epoch": 1.005283381364073,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004907069944370077,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.19382412880659103,
|
|
"num_tokens": 23994200.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.509462308883667,
|
|
"epoch": 1.005763688760807,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004906972407701998,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.20254671722650527,
|
|
"num_tokens": 24004695.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.344752502441406,
|
|
"epoch": 1.006243996157541,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004906874820955423,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.20152929425239563,
|
|
"num_tokens": 24015922.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.302721929550171,
|
|
"epoch": 1.0067243035542748,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004906777184132621,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.19876589328050615,
|
|
"num_tokens": 24026759.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.441859722137451,
|
|
"epoch": 1.0072046109510087,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004906679497235856,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.18939081132411956,
|
|
"num_tokens": 24037988.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.431847381591797,
|
|
"epoch": 1.0076849183477425,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004906581760267397,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.19650298804044725,
|
|
"num_tokens": 24050837.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.388985586166382,
|
|
"epoch": 1.0081652257444764,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004906483973229513,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.1995102882385254,
|
|
"num_tokens": 24063085.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.360555791854859,
|
|
"epoch": 1.0086455331412103,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004906386136124476,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.19522133469581604,
|
|
"num_tokens": 24074082.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.473991870880127,
|
|
"epoch": 1.0091258405379442,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004906288248954554,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.19207900613546372,
|
|
"num_tokens": 24085050.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.396671485900879,
|
|
"epoch": 1.0096061479346783,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004906190311722023,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.20093227922916412,
|
|
"num_tokens": 24095523.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.318253993988037,
|
|
"epoch": 1.0100864553314122,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004906092324429155,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.1935594454407692,
|
|
"num_tokens": 24107157.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.420668363571167,
|
|
"epoch": 1.010566762728146,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004905994287078227,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.19988345801830293,
|
|
"num_tokens": 24118668.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.39336667060852,
|
|
"epoch": 1.01104707012488,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004905896199671512,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.19728273004293442,
|
|
"num_tokens": 24129563.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.490720748901367,
|
|
"epoch": 1.0115273775216138,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000490579806221129,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.18932935297489167,
|
|
"num_tokens": 24139965.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.464150524139404,
|
|
"epoch": 1.0120076849183477,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004905699874699838,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.19245534390211105,
|
|
"num_tokens": 24152109.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.406421041488647,
|
|
"epoch": 1.0124879923150816,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004905601637139436,
|
|
"loss": 5.1882,
|
|
"mean_token_accuracy": 0.19585479646921158,
|
|
"num_tokens": 24162558.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.298392105102539,
|
|
"epoch": 1.0129682997118155,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004905503349532365,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.20920679867267608,
|
|
"num_tokens": 24173963.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.302287960052491,
|
|
"epoch": 1.0134486071085496,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004905405011880906,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.20042704641819,
|
|
"num_tokens": 24184369.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.5188305377960205,
|
|
"epoch": 1.0139289145052834,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004905306624187343,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.19433754235506057,
|
|
"num_tokens": 24194692.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.441524028778076,
|
|
"epoch": 1.0144092219020173,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004905208186453961,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.19718621522188187,
|
|
"num_tokens": 24205363.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.4292487621307375,
|
|
"epoch": 1.0148895292987512,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004905109698683044,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.18926580548286437,
|
|
"num_tokens": 24216678.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.35649037361145,
|
|
"epoch": 1.015369836695485,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004905011160876878,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.19385797679424285,
|
|
"num_tokens": 24227541.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.423275089263916,
|
|
"epoch": 1.015850144092219,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004904912573037753,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.20409995317459106,
|
|
"num_tokens": 24238118.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.408213329315186,
|
|
"epoch": 1.0163304514889528,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004904813935167957,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.18912750631570815,
|
|
"num_tokens": 24250044.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.415236186981201,
|
|
"epoch": 1.0168107588856867,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004904715247269779,
|
|
"loss": 5.2758,
|
|
"mean_token_accuracy": 0.1863135889172554,
|
|
"num_tokens": 24262805.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.42376971244812,
|
|
"epoch": 1.0172910662824208,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004904616509345514,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.1884153500199318,
|
|
"num_tokens": 24274287.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.3051690578460695,
|
|
"epoch": 1.0177713736791547,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004904517721397449,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.20322244316339494,
|
|
"num_tokens": 24284839.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.332529973983765,
|
|
"epoch": 1.0182516810758886,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004904418883427881,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.20154062509536744,
|
|
"num_tokens": 24295812.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.3823083400726315,
|
|
"epoch": 1.0187319884726225,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004904319995439104,
|
|
"loss": 5.1523,
|
|
"mean_token_accuracy": 0.20485446453094483,
|
|
"num_tokens": 24306365.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.388655662536621,
|
|
"epoch": 1.0192122958693564,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004904221057433412,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.19627542197704315,
|
|
"num_tokens": 24317557.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.330709409713745,
|
|
"epoch": 1.0196926032660902,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004904122069413105,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.20369454175233842,
|
|
"num_tokens": 24328874.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.486793327331543,
|
|
"epoch": 1.0201729106628241,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000490402303138048,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.18850115239620208,
|
|
"num_tokens": 24340918.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.471416997909546,
|
|
"epoch": 1.0206532180595582,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004903923943337836,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.19280854761600494,
|
|
"num_tokens": 24352642.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.3351459980010985,
|
|
"epoch": 1.021133525456292,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004903824805287475,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.2055082142353058,
|
|
"num_tokens": 24364874.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.316182327270508,
|
|
"epoch": 1.021613832853026,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004903725617231696,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.19844818562269212,
|
|
"num_tokens": 24376566.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.379147577285766,
|
|
"epoch": 1.0220941402497599,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004903626379172805,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.20634965747594833,
|
|
"num_tokens": 24387283.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.4593699932098385,
|
|
"epoch": 1.0225744476464937,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004903527091113102,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.19321691542863845,
|
|
"num_tokens": 24397970.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.3974676609039305,
|
|
"epoch": 1.0230547550432276,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004903427753054897,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.19375632256269454,
|
|
"num_tokens": 24411223.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.425050354003906,
|
|
"epoch": 1.0235350624399615,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004903328365000492,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.1965757578611374,
|
|
"num_tokens": 24422117.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.378111219406128,
|
|
"epoch": 1.0240153698366954,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004903228926952199,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.19537427127361298,
|
|
"num_tokens": 24434142.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.3584973335266115,
|
|
"epoch": 1.0244956772334295,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004903129438912322,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.19940481930971146,
|
|
"num_tokens": 24445295.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.352972984313965,
|
|
"epoch": 1.0249759846301634,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004903029900883174,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.20094187557697296,
|
|
"num_tokens": 24456092.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.370056104660034,
|
|
"epoch": 1.0254562920268973,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004902930312867063,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.18523428589105606,
|
|
"num_tokens": 24467653.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.484010314941406,
|
|
"epoch": 1.0259365994236311,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004902830674866306,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.19864919930696487,
|
|
"num_tokens": 24479164.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.376621675491333,
|
|
"epoch": 1.026416906820365,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004902730986883211,
|
|
"loss": 5.0744,
|
|
"mean_token_accuracy": 0.20569845288991928,
|
|
"num_tokens": 24489785.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.3931983470916744,
|
|
"epoch": 1.026897214217099,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004902631248920096,
|
|
"loss": 5.1669,
|
|
"mean_token_accuracy": 0.20193443149328233,
|
|
"num_tokens": 24500158.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.440870571136474,
|
|
"epoch": 1.0273775216138328,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004902531460979274,
|
|
"loss": 5.2998,
|
|
"mean_token_accuracy": 0.1916906416416168,
|
|
"num_tokens": 24512851.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.467244720458984,
|
|
"epoch": 1.0278578290105667,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004902431623063065,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.1967723399400711,
|
|
"num_tokens": 24524016.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.3333399295806885,
|
|
"epoch": 1.0283381364073008,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004902331735173785,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.1955583170056343,
|
|
"num_tokens": 24536348.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.31047625541687,
|
|
"epoch": 1.0288184438040346,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004902231797313752,
|
|
"loss": 5.2032,
|
|
"mean_token_accuracy": 0.19320364892482758,
|
|
"num_tokens": 24548718.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.341657543182373,
|
|
"epoch": 1.0292987512007685,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004902131809485288,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.20883229672908782,
|
|
"num_tokens": 24560567.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.384114074707031,
|
|
"epoch": 1.0297790585975024,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004902031771690713,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.20224715620279313,
|
|
"num_tokens": 24572610.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.373651599884033,
|
|
"epoch": 1.0302593659942363,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004901931683932352,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.19622482657432555,
|
|
"num_tokens": 24584738.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.423996448516846,
|
|
"epoch": 1.0307396733909702,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004901831546212526,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.19782585203647612,
|
|
"num_tokens": 24596603.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.327542543411255,
|
|
"epoch": 1.031219980787704,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004901731358533562,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.20182158052921295,
|
|
"num_tokens": 24607061.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.300077819824219,
|
|
"epoch": 1.031700288184438,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004901631120897785,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.19894571453332902,
|
|
"num_tokens": 24619177.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.329964542388916,
|
|
"epoch": 1.032180595581172,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004901530833307522,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.2028071790933609,
|
|
"num_tokens": 24631336.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.363113594055176,
|
|
"epoch": 1.032660902977906,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004901430495765103,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.20512140095233916,
|
|
"num_tokens": 24641743.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.3512063980102536,
|
|
"epoch": 1.0331412103746398,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004901330108272855,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.20420791804790497,
|
|
"num_tokens": 24652318.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.3060606002807615,
|
|
"epoch": 1.0336215177713737,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004901229670833111,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.19446881711483002,
|
|
"num_tokens": 24664129.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.402115774154663,
|
|
"epoch": 1.0341018251681076,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004901129183448201,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.20021976977586747,
|
|
"num_tokens": 24674921.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.3878522396087645,
|
|
"epoch": 1.0345821325648414,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004901028646120459,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.19470849335193635,
|
|
"num_tokens": 24686052.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.4007936954498295,
|
|
"epoch": 1.0350624399615753,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000490092805885222,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.20079933255910873,
|
|
"num_tokens": 24698625.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.340693569183349,
|
|
"epoch": 1.0355427473583094,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004900827421645816,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.20690946131944657,
|
|
"num_tokens": 24709322.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.311433458328247,
|
|
"epoch": 1.0360230547550433,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004900726734503589,
|
|
"loss": 5.0871,
|
|
"mean_token_accuracy": 0.2044057622551918,
|
|
"num_tokens": 24719512.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.340931940078735,
|
|
"epoch": 1.0365033621517772,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004900625997427872,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.20267050266265868,
|
|
"num_tokens": 24729947.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.31875376701355,
|
|
"epoch": 1.036983669548511,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004900525210421006,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.208098167181015,
|
|
"num_tokens": 24741423.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.410179948806762,
|
|
"epoch": 1.037463976945245,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004900424373485329,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.1962114915251732,
|
|
"num_tokens": 24753403.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.4055768013000485,
|
|
"epoch": 1.0379442843419788,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004900323486623185,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.18971707820892333,
|
|
"num_tokens": 24763660.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.407596254348755,
|
|
"epoch": 1.0384245917387127,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004900222549836914,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.20027221292257308,
|
|
"num_tokens": 24775061.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.379222059249878,
|
|
"epoch": 1.0389048991354466,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000490012156312886,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.19764596670866014,
|
|
"num_tokens": 24785248.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.285338687896728,
|
|
"epoch": 1.0393852065321807,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004900020526501369,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.20534291118383408,
|
|
"num_tokens": 24797024.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.466693305969239,
|
|
"epoch": 1.0398655139289146,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004899919439956785,
|
|
"loss": 5.3362,
|
|
"mean_token_accuracy": 0.18802452087402344,
|
|
"num_tokens": 24808500.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.480980682373047,
|
|
"epoch": 1.0403458213256485,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004899818303497455,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.19282276183366776,
|
|
"num_tokens": 24818805.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.393410682678223,
|
|
"epoch": 1.0408261287223823,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004899717117125728,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.19436366558074952,
|
|
"num_tokens": 24829247.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.285433721542359,
|
|
"epoch": 1.0413064361191162,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004899615880843953,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.20492787808179855,
|
|
"num_tokens": 24840139.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.412865066528321,
|
|
"epoch": 1.04178674351585,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004899514594654481,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.19102416336536407,
|
|
"num_tokens": 24851734.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.4186468601226805,
|
|
"epoch": 1.042267050912584,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004899413258559662,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.2009807527065277,
|
|
"num_tokens": 24863424.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.4386467933654785,
|
|
"epoch": 1.0427473583093179,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004899311872561849,
|
|
"loss": 5.2203,
|
|
"mean_token_accuracy": 0.19095490127801895,
|
|
"num_tokens": 24875086.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.342430925369262,
|
|
"epoch": 1.043227665706052,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004899210436663398,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.1986426293849945,
|
|
"num_tokens": 24888408.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.2934637546539305,
|
|
"epoch": 1.0437079731027858,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004899108950866661,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.20423916429281236,
|
|
"num_tokens": 24900357.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.422609519958496,
|
|
"epoch": 1.0441882804995197,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004899007415173997,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.20382613837718963,
|
|
"num_tokens": 24910790.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.333870935440063,
|
|
"epoch": 1.0446685878962536,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004898905829587762,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.19688949286937713,
|
|
"num_tokens": 24922124.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.273890686035156,
|
|
"epoch": 1.0451488952929875,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004898804194110313,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.20974807888269426,
|
|
"num_tokens": 24933591.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.3619232177734375,
|
|
"epoch": 1.0456292026897214,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004898702508744012,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.20185718983411788,
|
|
"num_tokens": 24944708.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.3504400730133055,
|
|
"epoch": 1.0461095100864553,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004898600773491221,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.20096213668584822,
|
|
"num_tokens": 24955966.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.414824056625366,
|
|
"epoch": 1.0465898174831891,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004898498988354297,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.2024759516119957,
|
|
"num_tokens": 24967292.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.431546974182129,
|
|
"epoch": 1.0470701248799232,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004898397153335608,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.1968492090702057,
|
|
"num_tokens": 24977407.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.468177366256714,
|
|
"epoch": 1.0475504322766571,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004898295268437517,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.19568923115730286,
|
|
"num_tokens": 24988804.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.350510883331299,
|
|
"epoch": 1.048030739673391,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004898193333662388,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.19943883866071702,
|
|
"num_tokens": 25000297.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.418834781646728,
|
|
"epoch": 1.0485110470701249,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004898091349012588,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.1936987891793251,
|
|
"num_tokens": 25012135.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.361229705810547,
|
|
"epoch": 1.0489913544668588,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004897989314490486,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.20732239931821822,
|
|
"num_tokens": 25023572.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.3188426971435545,
|
|
"epoch": 1.0494716618635926,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004897887230098451,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.2003694325685501,
|
|
"num_tokens": 25035015.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.352558374404907,
|
|
"epoch": 1.0499519692603265,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004897785095838852,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.19751752763986588,
|
|
"num_tokens": 25045931.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.4048971176147464,
|
|
"epoch": 1.0504322766570606,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004897682911714061,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.20248712748289108,
|
|
"num_tokens": 25056767.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.317250299453735,
|
|
"epoch": 1.0509125840537945,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000489758067772645,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.20746947228908538,
|
|
"num_tokens": 25068731.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.370254898071289,
|
|
"epoch": 1.0513928914505284,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004897478393878392,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.18695386946201326,
|
|
"num_tokens": 25081268.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.322613000869751,
|
|
"epoch": 1.0518731988472623,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004897376060172264,
|
|
"loss": 5.1148,
|
|
"mean_token_accuracy": 0.20413462072610855,
|
|
"num_tokens": 25093105.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.334506607055664,
|
|
"epoch": 1.0523535062439962,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004897273676610438,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.20305339694023133,
|
|
"num_tokens": 25103766.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.382137489318848,
|
|
"epoch": 1.05283381364073,
|
|
"grad_norm": 5.0,
|
|
"learning_rate": 0.0004897171243195295,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.19625720828771592,
|
|
"num_tokens": 25115675.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.368733739852905,
|
|
"epoch": 1.053314121037464,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000489706875992921,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.19928213208913803,
|
|
"num_tokens": 25127907.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.4173348903656,
|
|
"epoch": 1.0537944284341978,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004896966226814565,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.19909847527742386,
|
|
"num_tokens": 25139675.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.450517797470093,
|
|
"epoch": 1.054274735830932,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004896863643853739,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.19505783468484877,
|
|
"num_tokens": 25150960.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.459024143218994,
|
|
"epoch": 1.0547550432276658,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004896761011049114,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.19448428750038146,
|
|
"num_tokens": 25163676.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.371391630172729,
|
|
"epoch": 1.0552353506243997,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004896658328403074,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.19672573506832122,
|
|
"num_tokens": 25174317.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.325609827041626,
|
|
"epoch": 1.0557156580211335,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004896555595918001,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.1921961262822151,
|
|
"num_tokens": 25186585.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.387838745117188,
|
|
"epoch": 1.0561959654178674,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004896452813596281,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.19774259775876998,
|
|
"num_tokens": 25199014.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.418529796600342,
|
|
"epoch": 1.0566762728146013,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004896349981440301,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.1923758089542389,
|
|
"num_tokens": 25210544.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.40743670463562,
|
|
"epoch": 1.0571565802113352,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004896247099452447,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.2030924767255783,
|
|
"num_tokens": 25221583.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.379515647888184,
|
|
"epoch": 1.057636887608069,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004896144167635108,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.2086687535047531,
|
|
"num_tokens": 25231724.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.358378744125366,
|
|
"epoch": 1.0581171950048032,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004896041185990675,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.19169405549764634,
|
|
"num_tokens": 25243021.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.453790330886841,
|
|
"epoch": 1.058597502401537,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004895938154521538,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.19818150848150254,
|
|
"num_tokens": 25254189.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.424182462692261,
|
|
"epoch": 1.059077809798271,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004895835073230089,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.19890464842319489,
|
|
"num_tokens": 25265556.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.35037670135498,
|
|
"epoch": 1.0595581171950048,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004895731942118722,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.19843342453241347,
|
|
"num_tokens": 25276789.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.374223423004151,
|
|
"epoch": 1.0600384245917387,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004895628761189829,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.19223990738391877,
|
|
"num_tokens": 25288505.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.350738191604615,
|
|
"epoch": 1.0605187319884726,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004895525530445809,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.20899250954389573,
|
|
"num_tokens": 25301490.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.406547117233276,
|
|
"epoch": 1.0609990393852065,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004895422249889057,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.19628418236970901,
|
|
"num_tokens": 25313303.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.464979219436645,
|
|
"epoch": 1.0614793467819403,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004895318919521971,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.18317241221666336,
|
|
"num_tokens": 25324379.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.381422662734986,
|
|
"epoch": 1.0619596541786744,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004895215539346949,
|
|
"loss": 5.1066,
|
|
"mean_token_accuracy": 0.20204539000988006,
|
|
"num_tokens": 25335834.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.3912934303283695,
|
|
"epoch": 1.0624399615754083,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004895112109366393,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.19370175004005433,
|
|
"num_tokens": 25347591.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.3389111995697025,
|
|
"epoch": 1.0629202689721422,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004895008629582703,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.19789793938398362,
|
|
"num_tokens": 25358483.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.367819309234619,
|
|
"epoch": 1.063400576368876,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004894905099998283,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.19483150988817216,
|
|
"num_tokens": 25369434.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.375917100906372,
|
|
"epoch": 1.06388088376561,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004894801520615535,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.19991028159856797,
|
|
"num_tokens": 25381007.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.383973503112793,
|
|
"epoch": 1.0643611911623438,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004894697891436863,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.19340840876102447,
|
|
"num_tokens": 25393809.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.434722566604615,
|
|
"epoch": 1.0648414985590777,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004894594212464676,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.20349488854408265,
|
|
"num_tokens": 25404967.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.391611099243164,
|
|
"epoch": 1.0653218059558118,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004894490483701381,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.20830817222595216,
|
|
"num_tokens": 25417092.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.389318990707397,
|
|
"epoch": 1.0658021133525457,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004894386705149382,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.19301486164331436,
|
|
"num_tokens": 25428425.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.371826696395874,
|
|
"epoch": 1.0662824207492796,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004894282876811093,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.20606110244989395,
|
|
"num_tokens": 25440134.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.359651947021485,
|
|
"epoch": 1.0667627281460135,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004894178998688921,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.2057764545083046,
|
|
"num_tokens": 25452222.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.382782459259033,
|
|
"epoch": 1.0672430355427474,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004894075070785281,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.19721873998641967,
|
|
"num_tokens": 25464541.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.445518875122071,
|
|
"epoch": 1.0677233429394812,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004893971093102585,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.18894643485546112,
|
|
"num_tokens": 25476537.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.475181913375854,
|
|
"epoch": 1.0682036503362151,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004893867065643245,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.19041333347558975,
|
|
"num_tokens": 25486737.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.364242839813232,
|
|
"epoch": 1.068683957732949,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004893762988409678,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.19505753815174104,
|
|
"num_tokens": 25497278.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.378061580657959,
|
|
"epoch": 1.069164265129683,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004893658861404301,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.1955024540424347,
|
|
"num_tokens": 25508716.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.456086587905884,
|
|
"epoch": 1.069644572526417,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004893554684629529,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.19080305695533753,
|
|
"num_tokens": 25519439.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.335903882980347,
|
|
"epoch": 1.0701248799231509,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004893450458087784,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.20811732411384581,
|
|
"num_tokens": 25530911.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.425146961212159,
|
|
"epoch": 1.0706051873198847,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004893346181781483,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.18407331258058549,
|
|
"num_tokens": 25542452.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.3917309761047365,
|
|
"epoch": 1.0710854947166186,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004893241855713048,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.1917176812887192,
|
|
"num_tokens": 25554105.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.48886547088623,
|
|
"epoch": 1.0715658021133525,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004893137479884903,
|
|
"loss": 5.2637,
|
|
"mean_token_accuracy": 0.19534027725458145,
|
|
"num_tokens": 25564806.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.34090633392334,
|
|
"epoch": 1.0720461095100864,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004893033054299468,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.20664169490337372,
|
|
"num_tokens": 25575664.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.329424953460693,
|
|
"epoch": 1.0725264169068203,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000489292857895917,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.20746021270751952,
|
|
"num_tokens": 25586227.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.396088600158691,
|
|
"epoch": 1.0730067243035544,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004892824053866432,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.19714417308568954,
|
|
"num_tokens": 25597475.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.338240385055542,
|
|
"epoch": 1.0734870317002883,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004892719479023683,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.2057972341775894,
|
|
"num_tokens": 25608098.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.406243515014649,
|
|
"epoch": 1.0739673390970221,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000489261485443335,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.19310028105974197,
|
|
"num_tokens": 25620053.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.4029604434967045,
|
|
"epoch": 1.074447646493756,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004892510180097863,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.19133893996477128,
|
|
"num_tokens": 25630534.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.466851806640625,
|
|
"epoch": 1.07492795389049,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004892405456019651,
|
|
"loss": 5.2041,
|
|
"mean_token_accuracy": 0.20040323138236998,
|
|
"num_tokens": 25641413.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.270170068740844,
|
|
"epoch": 1.0754082612872238,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004892300682201147,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.20679468661546707,
|
|
"num_tokens": 25652081.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.388210487365723,
|
|
"epoch": 1.0758885686839577,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004892195858644782,
|
|
"loss": 5.229,
|
|
"mean_token_accuracy": 0.20188132524490357,
|
|
"num_tokens": 25664282.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.444235801696777,
|
|
"epoch": 1.0763688760806915,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000489209098535299,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.19060481786727906,
|
|
"num_tokens": 25675310.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.489648532867432,
|
|
"epoch": 1.0768491834774256,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004891986062328205,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.19932085871696473,
|
|
"num_tokens": 25686895.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.322609758377075,
|
|
"epoch": 1.0773294908741595,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004891881089572865,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.2028209835290909,
|
|
"num_tokens": 25697778.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.333473110198975,
|
|
"epoch": 1.0778097982708934,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004891776067089406,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.1931999772787094,
|
|
"num_tokens": 25708602.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.3813293933868405,
|
|
"epoch": 1.0782901056676273,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004891670994880266,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.20110365450382234,
|
|
"num_tokens": 25719671.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.473407793045044,
|
|
"epoch": 1.0787704130643612,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004891565872947888,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.19285018593072892,
|
|
"num_tokens": 25731797.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.352025651931763,
|
|
"epoch": 1.079250720461095,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004891460701294706,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.19890260994434356,
|
|
"num_tokens": 25743984.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.286668109893799,
|
|
"epoch": 1.079731027857829,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004891355479923167,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.19730135351419448,
|
|
"num_tokens": 25755252.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.293460130691528,
|
|
"epoch": 1.080211335254563,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004891250208835712,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.19844501465559006,
|
|
"num_tokens": 25765715.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.438339805603027,
|
|
"epoch": 1.080691642651297,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004891144888034784,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.19169185012578965,
|
|
"num_tokens": 25777866.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.40947585105896,
|
|
"epoch": 1.0811719500480308,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004891039517522832,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.20117480009794236,
|
|
"num_tokens": 25791199.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.253937005996704,
|
|
"epoch": 1.0816522574447647,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004890934097302299,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.2104889139533043,
|
|
"num_tokens": 25802979.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.2297004699707035,
|
|
"epoch": 1.0821325648414986,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004890828627375632,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.20461921095848085,
|
|
"num_tokens": 25814696.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.401715660095215,
|
|
"epoch": 1.0826128722382324,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004890723107745283,
|
|
"loss": 5.2066,
|
|
"mean_token_accuracy": 0.1876143619418144,
|
|
"num_tokens": 25825376.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.457053184509277,
|
|
"epoch": 1.0830931796349663,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004890617538413699,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.20004055202007293,
|
|
"num_tokens": 25835491.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.388221216201782,
|
|
"epoch": 1.0835734870317002,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004890511919383333,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.19414729624986649,
|
|
"num_tokens": 25848154.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.359829568862915,
|
|
"epoch": 1.084053794428434,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004890406250656636,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.19618980437517167,
|
|
"num_tokens": 25859471.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.386313772201538,
|
|
"epoch": 1.0845341018251682,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004890300532236062,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.20352212488651275,
|
|
"num_tokens": 25869460.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.366284036636353,
|
|
"epoch": 1.085014409221902,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004890194764124064,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.19900275766849518,
|
|
"num_tokens": 25881892.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.407566404342651,
|
|
"epoch": 1.085494716618636,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004890088946323099,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.19526465982198715,
|
|
"num_tokens": 25893774.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.323100948333741,
|
|
"epoch": 1.0859750240153698,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004889983078835623,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.2026428148150444,
|
|
"num_tokens": 25904758.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.337569808959961,
|
|
"epoch": 1.0864553314121037,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.1935545101761818,
|
|
"num_tokens": 25917013.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.490104866027832,
|
|
"epoch": 1.0869356388088376,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004889771194810974,
|
|
"loss": 5.2617,
|
|
"mean_token_accuracy": 0.20188507735729216,
|
|
"num_tokens": 25927780.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.32041974067688,
|
|
"epoch": 1.0874159462055715,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004889665178278719,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.20194960981607438,
|
|
"num_tokens": 25939339.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.309616327285767,
|
|
"epoch": 1.0878962536023056,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004889559112069792,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.19975393116474152,
|
|
"num_tokens": 25950440.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.39558596611023,
|
|
"epoch": 1.0883765609990395,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004889452996186657,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.19510021209716796,
|
|
"num_tokens": 25962849.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.3870491027832035,
|
|
"epoch": 1.0888568683957733,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004889346830631774,
|
|
"loss": 5.2139,
|
|
"mean_token_accuracy": 0.1988331750035286,
|
|
"num_tokens": 25973616.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.337776708602905,
|
|
"epoch": 1.0893371757925072,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000488924061540761,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.20268790572881698,
|
|
"num_tokens": 25984727.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.36871337890625,
|
|
"epoch": 1.089817483189241,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004889134350516633,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.19895684868097305,
|
|
"num_tokens": 25996431.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.420349645614624,
|
|
"epoch": 1.090297790585975,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004889028035961308,
|
|
"loss": 5.1882,
|
|
"mean_token_accuracy": 0.19862073808908462,
|
|
"num_tokens": 26008936.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.432696104049683,
|
|
"epoch": 1.0907780979827089,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004888921671744103,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.19283294677734375,
|
|
"num_tokens": 26019308.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.37703275680542,
|
|
"epoch": 1.0912584053794427,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004888815257867488,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.20610872954130172,
|
|
"num_tokens": 26030705.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.364771747589112,
|
|
"epoch": 1.0917387127761768,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004888708794333934,
|
|
"loss": 5.1669,
|
|
"mean_token_accuracy": 0.19873858690261842,
|
|
"num_tokens": 26042759.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.383549213409424,
|
|
"epoch": 1.0922190201729107,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004888602281145913,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.19825351238250732,
|
|
"num_tokens": 26054719.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.363201999664307,
|
|
"epoch": 1.0926993275696446,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004888495718305897,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.1944555163383484,
|
|
"num_tokens": 26065765.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.276873636245727,
|
|
"epoch": 1.0931796349663785,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000488838910581636,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.20164201110601426,
|
|
"num_tokens": 26077719.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.377471685409546,
|
|
"epoch": 1.0936599423631124,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004888282443679777,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.19267560988664628,
|
|
"num_tokens": 26089924.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.543978452682495,
|
|
"epoch": 1.0941402497598463,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004888175731898627,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.19328917115926741,
|
|
"num_tokens": 26100312.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.374999094009399,
|
|
"epoch": 1.0946205571565801,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004888068970475384,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.1926673725247383,
|
|
"num_tokens": 26111932.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.383733701705933,
|
|
"epoch": 1.0951008645533142,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004887962159412529,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.20165913850069045,
|
|
"num_tokens": 26123989.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.4617822647094725,
|
|
"epoch": 1.0955811719500481,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004887855298712541,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.19817150235176087,
|
|
"num_tokens": 26135589.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.328017807006836,
|
|
"epoch": 1.096061479346782,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048877483883779,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.20411452651023865,
|
|
"num_tokens": 26147069.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.316229391098022,
|
|
"epoch": 1.0965417867435159,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004887641428411091,
|
|
"loss": 5.1947,
|
|
"mean_token_accuracy": 0.196431402862072,
|
|
"num_tokens": 26159331.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.391355657577515,
|
|
"epoch": 1.0970220941402498,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004887534418814595,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.1992008239030838,
|
|
"num_tokens": 26169863.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.3888506412506105,
|
|
"epoch": 1.0975024015369836,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004887427359590897,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.1930580496788025,
|
|
"num_tokens": 26182888.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.374685907363892,
|
|
"epoch": 1.0979827089337175,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004887320250742482,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.20320331454277038,
|
|
"num_tokens": 26194979.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.309309005737305,
|
|
"epoch": 1.0984630163304514,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004887213092271838,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.20536947697401048,
|
|
"num_tokens": 26207309.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.353480291366577,
|
|
"epoch": 1.0989433237271853,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004887105884181451,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.19829550683498381,
|
|
"num_tokens": 26219231.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.470127964019776,
|
|
"epoch": 1.0994236311239194,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004886998626473813,
|
|
"loss": 5.2312,
|
|
"mean_token_accuracy": 0.1940376043319702,
|
|
"num_tokens": 26229355.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.4371985912323,
|
|
"epoch": 1.0999039385206533,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004886891319151411,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.19973791539669036,
|
|
"num_tokens": 26239069.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.429724788665771,
|
|
"epoch": 1.1003842459173871,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004886783962216738,
|
|
"loss": 5.2518,
|
|
"mean_token_accuracy": 0.19404187053442,
|
|
"num_tokens": 26250403.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.429457378387451,
|
|
"epoch": 1.100864553314121,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004886676555672287,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.1941487103700638,
|
|
"num_tokens": 26262926.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.461712503433228,
|
|
"epoch": 1.101344860710855,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004886569099520551,
|
|
"loss": 5.3007,
|
|
"mean_token_accuracy": 0.18488921970129013,
|
|
"num_tokens": 26274030.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.3495361328125,
|
|
"epoch": 1.1018251681075888,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004886461593764024,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.20603205114603043,
|
|
"num_tokens": 26284799.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.317038488388062,
|
|
"epoch": 1.1023054755043227,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004886354038405204,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.20941875129938126,
|
|
"num_tokens": 26295154.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.443295431137085,
|
|
"epoch": 1.1027857829010568,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004886246433446586,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.19406017214059829,
|
|
"num_tokens": 26306181.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.484092473983765,
|
|
"epoch": 1.1032660902977907,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004886138778890669,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.18723338544368745,
|
|
"num_tokens": 26318674.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.427069425582886,
|
|
"epoch": 1.1037463976945245,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004886031074739953,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.1848438188433647,
|
|
"num_tokens": 26330257.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.443810558319091,
|
|
"epoch": 1.1042267050912584,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004885923320996938,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.19050682932138444,
|
|
"num_tokens": 26342035.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.403368949890137,
|
|
"epoch": 1.1047070124879923,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004885815517664127,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.19268637746572495,
|
|
"num_tokens": 26352703.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.454485654830933,
|
|
"epoch": 1.1051873198847262,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000488570766474402,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.1983371138572693,
|
|
"num_tokens": 26362324.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.417402648925782,
|
|
"epoch": 1.10566762728146,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004885599762239124,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.19100573807954788,
|
|
"num_tokens": 26373540.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.376094341278076,
|
|
"epoch": 1.106147934678194,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004885491810151943,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.19673055559396743,
|
|
"num_tokens": 26384259.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.373725891113281,
|
|
"epoch": 1.106628242074928,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004885383808484982,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.20042554587125777,
|
|
"num_tokens": 26395193.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.379770040512085,
|
|
"epoch": 1.107108549471662,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004885275757240751,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.19974727034568787,
|
|
"num_tokens": 26408556.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.3124510765075685,
|
|
"epoch": 1.1075888568683958,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004885167656421757,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.1964297726750374,
|
|
"num_tokens": 26420066.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.368311166763306,
|
|
"epoch": 1.1080691642651297,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000488505950603051,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.2022274389863014,
|
|
"num_tokens": 26432533.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.410836887359619,
|
|
"epoch": 1.1085494716618636,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000488495130606952,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.1977706089615822,
|
|
"num_tokens": 26443878.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.349820375442505,
|
|
"epoch": 1.1090297790585975,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004884843056541302,
|
|
"loss": 5.1509,
|
|
"mean_token_accuracy": 0.19636111259460448,
|
|
"num_tokens": 26455111.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.363452911376953,
|
|
"epoch": 1.1095100864553313,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004884734757448367,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.19738590866327285,
|
|
"num_tokens": 26466577.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.380586385726929,
|
|
"epoch": 1.1099903938520654,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000488462640879323,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.19821802526712418,
|
|
"num_tokens": 26479637.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.3282112121582035,
|
|
"epoch": 1.1104707012487993,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004884518010578405,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.1996982976794243,
|
|
"num_tokens": 26489923.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.46231164932251,
|
|
"epoch": 1.1109510086455332,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004884409562806411,
|
|
"loss": 5.2626,
|
|
"mean_token_accuracy": 0.19047495871782302,
|
|
"num_tokens": 26501236.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.39301815032959,
|
|
"epoch": 1.111431316042267,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004884301065479765,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.19979702234268187,
|
|
"num_tokens": 26511509.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.285901308059692,
|
|
"epoch": 1.111911623439001,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004884192518600986,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.20860260725021362,
|
|
"num_tokens": 26520931.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.250344896316529,
|
|
"epoch": 1.1123919308357348,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004884083922172593,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.20346393287181855,
|
|
"num_tokens": 26531333.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.344915676116943,
|
|
"epoch": 1.1128722382324687,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004883975276197108,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.1972086548805237,
|
|
"num_tokens": 26543696.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.413683605194092,
|
|
"epoch": 1.1133525456292026,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004883866580677055,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.1973527893424034,
|
|
"num_tokens": 26556292.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.39650297164917,
|
|
"epoch": 1.1138328530259365,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004883757835614956,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.18919681161642074,
|
|
"num_tokens": 26568023.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.314826393127442,
|
|
"epoch": 1.1143131604226706,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004883649041013335,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.1997550442814827,
|
|
"num_tokens": 26579469.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.417600536346436,
|
|
"epoch": 1.1147934678194045,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000488354019687472,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.19775457084178924,
|
|
"num_tokens": 26591592.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.392254114151001,
|
|
"epoch": 1.1152737752161384,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004883431303201636,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.19871224611997604,
|
|
"num_tokens": 26604075.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.300816869735717,
|
|
"epoch": 1.1157540826128722,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004883322359996613,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.20315623730421067,
|
|
"num_tokens": 26616448.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.424475193023682,
|
|
"epoch": 1.1162343900096061,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004883213367262179,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.2026465952396393,
|
|
"num_tokens": 26628749.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.378135728836059,
|
|
"epoch": 1.11671469740634,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004883104325000866,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.20778037309646608,
|
|
"num_tokens": 26640163.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.427231550216675,
|
|
"epoch": 1.1171950048030739,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004882995233215203,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.19885045737028123,
|
|
"num_tokens": 26650729.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.313515710830688,
|
|
"epoch": 1.117675312199808,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004882886091907726,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.19789895862340928,
|
|
"num_tokens": 26661995.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.336483430862427,
|
|
"epoch": 1.1181556195965419,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048827769010809666,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.20310165584087372,
|
|
"num_tokens": 26673224.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.435932302474976,
|
|
"epoch": 1.1186359269932757,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048826676607374606,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.19770387560129166,
|
|
"num_tokens": 26686331.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.443671369552613,
|
|
"epoch": 1.1191162343900096,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048825583708797434,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.20107847601175308,
|
|
"num_tokens": 26696816.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.3470789909362795,
|
|
"epoch": 1.1195965417867435,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004882449031510354,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.19950841516256332,
|
|
"num_tokens": 26708126.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.435420846939087,
|
|
"epoch": 1.1200768491834774,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000488233964263183,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.19885293990373612,
|
|
"num_tokens": 26718951.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.413599014282227,
|
|
"epoch": 1.1205571565802113,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048822302042467115,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.1890918418765068,
|
|
"num_tokens": 26730550.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.316771554946899,
|
|
"epoch": 1.1210374639769451,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004882120716357539,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.20879027098417283,
|
|
"num_tokens": 26741485.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.25130033493042,
|
|
"epoch": 1.1215177713736793,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004882011178966854,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.20567907989025117,
|
|
"num_tokens": 26753947.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.328771162033081,
|
|
"epoch": 1.1219980787704131,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004881901592077201,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.2045335054397583,
|
|
"num_tokens": 26764921.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.38278980255127,
|
|
"epoch": 1.122478386167147,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004881791955691123,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.20039097368717193,
|
|
"num_tokens": 26777384.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.4077401638031,
|
|
"epoch": 1.122958693563881,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048816822698111655,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.19082235395908356,
|
|
"num_tokens": 26789916.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.353139638900757,
|
|
"epoch": 1.1234390009606148,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048815725344398766,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.20162887275218963,
|
|
"num_tokens": 26801167.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.4568287372589115,
|
|
"epoch": 1.1239193083573487,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048814627495798017,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.1942308261990547,
|
|
"num_tokens": 26813235.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.419614315032959,
|
|
"epoch": 1.1243996157540825,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004881352915233492,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.19639881700277328,
|
|
"num_tokens": 26824758.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.376121187210083,
|
|
"epoch": 1.1248799231508164,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048812430314034956,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.1970758393406868,
|
|
"num_tokens": 26836877.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.248546123504639,
|
|
"epoch": 1.1253602305475505,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004881133098092365,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.2167480245232582,
|
|
"num_tokens": 26848394.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.327980613708496,
|
|
"epoch": 1.1258405379442844,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004881023115302652,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.20048938393592836,
|
|
"num_tokens": 26859064.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.443533992767334,
|
|
"epoch": 1.1263208453410183,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000488091308303691,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.18744636327028275,
|
|
"num_tokens": 26870401.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.381682872772217,
|
|
"epoch": 1.1268011527377522,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004880803001297694,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.19839031249284744,
|
|
"num_tokens": 26881767.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.339331865310669,
|
|
"epoch": 1.127281460134486,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004880692870087559,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.1959598183631897,
|
|
"num_tokens": 26892854.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.476315021514893,
|
|
"epoch": 1.12776176753122,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048805826894090626,
|
|
"loss": 5.2505,
|
|
"mean_token_accuracy": 0.19431565403938295,
|
|
"num_tokens": 26905079.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.434010696411133,
|
|
"epoch": 1.1282420749279538,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048804724592647626,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.19630527943372728,
|
|
"num_tokens": 26915640.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.3531194686889645,
|
|
"epoch": 1.1287223823246877,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004880362179657218,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.19762447327375413,
|
|
"num_tokens": 26927039.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.391130161285401,
|
|
"epoch": 1.1292026897214218,
|
|
"grad_norm": 5.6875,
|
|
"learning_rate": 0.00048802518505889904,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.19973956197500228,
|
|
"num_tokens": 26939368.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.3634108543396,
|
|
"epoch": 1.1296829971181557,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048801414720626404,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.18471236377954484,
|
|
"num_tokens": 26952051.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.314442729949951,
|
|
"epoch": 1.1301633045148896,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048800310440807294,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.20135910511016847,
|
|
"num_tokens": 26963680.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.281684732437133,
|
|
"epoch": 1.1306436119116234,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004879920566645823,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.20670076459646225,
|
|
"num_tokens": 26973899.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.3779764652252195,
|
|
"epoch": 1.1311239193083573,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004879810039760486,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.19252123087644576,
|
|
"num_tokens": 26985692.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.374066352844238,
|
|
"epoch": 1.1316042267050912,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004879699463427284,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.2054677352309227,
|
|
"num_tokens": 26996354.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.4028901100158695,
|
|
"epoch": 1.132084534101825,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004879588837648785,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.19994594752788544,
|
|
"num_tokens": 27007925.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.3277709007263185,
|
|
"epoch": 1.1325648414985592,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048794781624275554,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.20461585968732834,
|
|
"num_tokens": 27019222.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.280467557907104,
|
|
"epoch": 1.133045148895293,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048793674377661664,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.20979010164737702,
|
|
"num_tokens": 27029973.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.413479423522949,
|
|
"epoch": 1.133525456292027,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048792566636671886,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.1939689874649048,
|
|
"num_tokens": 27042002.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.360994911193847,
|
|
"epoch": 1.1340057636887608,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004879145840133194,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.20655664503574372,
|
|
"num_tokens": 27052770.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.37757830619812,
|
|
"epoch": 1.1344860710854947,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004879034967166755,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.1909607619047165,
|
|
"num_tokens": 27063375.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.349298906326294,
|
|
"epoch": 1.1349663784822286,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004878924044770446,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.20069160908460618,
|
|
"num_tokens": 27075908.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.3474914073944095,
|
|
"epoch": 1.1354466858789625,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004878813072946843,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.1989054411649704,
|
|
"num_tokens": 27087590.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.3797157287597654,
|
|
"epoch": 1.1359269932756964,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048787020516985203,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.20755711048841477,
|
|
"num_tokens": 27098076.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.339752721786499,
|
|
"epoch": 1.1364073006724302,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00048785909810280576,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.2066489040851593,
|
|
"num_tokens": 27109851.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.360318231582641,
|
|
"epoch": 1.1368876080691643,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004878479860938033,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.20510947555303574,
|
|
"num_tokens": 27121288.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.370573997497559,
|
|
"epoch": 1.1373679154658982,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048783686914310266,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.1978868991136551,
|
|
"num_tokens": 27133877.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.213607549667358,
|
|
"epoch": 1.137848222862632,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004878257472509619,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.20816704034805297,
|
|
"num_tokens": 27145616.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.243274116516114,
|
|
"epoch": 1.138328530259366,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004878146204176392,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.20020941644906998,
|
|
"num_tokens": 27157182.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.332354927062989,
|
|
"epoch": 1.1388088376560999,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000487803488643393,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.2005708023905754,
|
|
"num_tokens": 27167609.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.390336990356445,
|
|
"epoch": 1.1392891450528337,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048779235192848166,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.1929536283016205,
|
|
"num_tokens": 27180043.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.313104486465454,
|
|
"epoch": 1.1397694524495678,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004877812102731638,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.20513586401939393,
|
|
"num_tokens": 27191870.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.353136110305786,
|
|
"epoch": 1.1402497598463017,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048777006367769804,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.1980505183339119,
|
|
"num_tokens": 27203291.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.367413902282715,
|
|
"epoch": 1.1407300672430356,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004877589121423432,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.20064722746610641,
|
|
"num_tokens": 27214607.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.343343877792359,
|
|
"epoch": 1.1412103746397695,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004877477556673582,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.20142433494329454,
|
|
"num_tokens": 27224658.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.30929217338562,
|
|
"epoch": 1.1416906820365034,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000487736594253002,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.19426832795143129,
|
|
"num_tokens": 27235306.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.4126396656036375,
|
|
"epoch": 1.1421709894332372,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00048772542789953384,
|
|
"loss": 5.1764,
|
|
"mean_token_accuracy": 0.1978692263364792,
|
|
"num_tokens": 27246679.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.461403703689575,
|
|
"epoch": 1.1426512968299711,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048771425660721284,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.19653720408678055,
|
|
"num_tokens": 27257799.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.307733106613159,
|
|
"epoch": 1.143131604226705,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048770308037629853,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.19659828394651413,
|
|
"num_tokens": 27268651.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.379173612594604,
|
|
"epoch": 1.143611911623439,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004876918992070502,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.20153645873069764,
|
|
"num_tokens": 27280655.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.4180139064788815,
|
|
"epoch": 1.144092219020173,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004876807130997276,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.1959937870502472,
|
|
"num_tokens": 27292664.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.4104715347290036,
|
|
"epoch": 1.1445725264169069,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004876695220545903,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.19415178298950195,
|
|
"num_tokens": 27306143.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.341716241836548,
|
|
"epoch": 1.1450528338136408,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048765832607189824,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.2040667086839676,
|
|
"num_tokens": 27316926.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.432511520385742,
|
|
"epoch": 1.1455331412103746,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00048764712515191136,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.20223041325807573,
|
|
"num_tokens": 27327472.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.40002179145813,
|
|
"epoch": 1.1460134486071085,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048763591929488966,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.1982942596077919,
|
|
"num_tokens": 27338388.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.357805919647217,
|
|
"epoch": 1.1464937560038424,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004876247085010933,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.2054908514022827,
|
|
"num_tokens": 27349879.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.3025483131408695,
|
|
"epoch": 1.1469740634005763,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048761349277078253,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.20434694290161132,
|
|
"num_tokens": 27361226.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.356570291519165,
|
|
"epoch": 1.1474543707973104,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048760227210421775,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.20274200439453124,
|
|
"num_tokens": 27373512.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.322547674179077,
|
|
"epoch": 1.1479346781940443,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004875910465016596,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.20543191879987716,
|
|
"num_tokens": 27384950.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.481065273284912,
|
|
"epoch": 1.1484149855907781,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004875798159633686,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.20089646875858308,
|
|
"num_tokens": 27395877.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.3793903350830075,
|
|
"epoch": 1.148895292987512,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004875685804896055,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.19907495379447937,
|
|
"num_tokens": 27407783.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.336903238296509,
|
|
"epoch": 1.149375600384246,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004875573400806312,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.19993287622928618,
|
|
"num_tokens": 27420598.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.41229395866394,
|
|
"epoch": 1.1498559077809798,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048754609473670654,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.19810105562210084,
|
|
"num_tokens": 27431961.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.377918386459351,
|
|
"epoch": 1.1503362151777137,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004875348444580927,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.20238653123378753,
|
|
"num_tokens": 27444010.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.432789421081543,
|
|
"epoch": 1.1508165225744476,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.000487523589245051,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.19724316596984864,
|
|
"num_tokens": 27455576.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.3245526313781735,
|
|
"epoch": 1.1512968299711814,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004875123290978425,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.1956126257777214,
|
|
"num_tokens": 27468957.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.300604057312012,
|
|
"epoch": 1.1517771373679155,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048750106401672876,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.20426657050848007,
|
|
"num_tokens": 27479992.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.3841681480407715,
|
|
"epoch": 1.1522574447646494,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048748979400197134,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.19643299728631974,
|
|
"num_tokens": 27490878.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.308560705184936,
|
|
"epoch": 1.1527377521613833,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048747851905383183,
|
|
"loss": 5.0707,
|
|
"mean_token_accuracy": 0.2070022165775299,
|
|
"num_tokens": 27502009.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1527377521613833,
|
|
"eval_entropy": 5.197656180555213,
|
|
"eval_loss": 5.2574920654296875,
|
|
"eval_mean_token_accuracy": 0.2030526876371483,
|
|
"eval_num_tokens": 27502009.0,
|
|
"eval_runtime": 26.6951,
|
|
"eval_samples_per_second": 1229.251,
|
|
"eval_steps_per_second": 153.661,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.403885221481323,
|
|
"epoch": 1.1532180595581172,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004874672391725721,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.19340700954198836,
|
|
"num_tokens": 27513376.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.327795743942261,
|
|
"epoch": 1.153698366954851,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004874559543584539,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.19813020676374435,
|
|
"num_tokens": 27525166.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.2932392120361325,
|
|
"epoch": 1.154178674351585,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004874446646117394,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.21223140358924866,
|
|
"num_tokens": 27535994.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.362952852249146,
|
|
"epoch": 1.154658981748319,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004874333699326906,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.2008701428771019,
|
|
"num_tokens": 27546883.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.444707918167114,
|
|
"epoch": 1.155139289145053,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004874220703215697,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.19083331376314164,
|
|
"num_tokens": 27558840.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.316365718841553,
|
|
"epoch": 1.1556195965417868,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004874107657786391,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.19912893772125245,
|
|
"num_tokens": 27569776.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.400084543228149,
|
|
"epoch": 1.1560999039385207,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048739945630416124,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.20130958110094072,
|
|
"num_tokens": 27580097.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.421789836883545,
|
|
"epoch": 1.1565802113352546,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004873881418983987,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.1976413443684578,
|
|
"num_tokens": 27592035.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.374824047088623,
|
|
"epoch": 1.1570605187319885,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004873768225616141,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.20245745480060579,
|
|
"num_tokens": 27604409.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.396100234985352,
|
|
"epoch": 1.1575408261287223,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048736549829407047,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.1959798067808151,
|
|
"num_tokens": 27615019.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.424737596511841,
|
|
"epoch": 1.1580211335254562,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004873541690960305,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.19504277408123016,
|
|
"num_tokens": 27627924.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.291185712814331,
|
|
"epoch": 1.15850144092219,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004873428349677573,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.20147943496704102,
|
|
"num_tokens": 27639188.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.447781610488891,
|
|
"epoch": 1.1589817483189242,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000487331495909514,
|
|
"loss": 5.2876,
|
|
"mean_token_accuracy": 0.19072507619857787,
|
|
"num_tokens": 27652621.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.4043315887451175,
|
|
"epoch": 1.159462055715658,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048732015192156383,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.19154627472162247,
|
|
"num_tokens": 27665726.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.394845390319825,
|
|
"epoch": 1.159942363112392,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048730880300417015,
|
|
"loss": 5.1814,
|
|
"mean_token_accuracy": 0.19666818529367447,
|
|
"num_tokens": 27676984.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.4137085437774655,
|
|
"epoch": 1.1604226705091258,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048729744915759657,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.1964266061782837,
|
|
"num_tokens": 27688812.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.293023204803466,
|
|
"epoch": 1.1609029779058597,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048728609038210655,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.20518343299627304,
|
|
"num_tokens": 27699152.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.40082015991211,
|
|
"epoch": 1.1613832853025936,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048727472667796395,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.20061883926391602,
|
|
"num_tokens": 27710347.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.315311336517334,
|
|
"epoch": 1.1618635926993275,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004872633580454325,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.2058119148015976,
|
|
"num_tokens": 27721112.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.39327449798584,
|
|
"epoch": 1.1623439000960616,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048725198448477616,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.19871051013469695,
|
|
"num_tokens": 27731766.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.359863424301148,
|
|
"epoch": 1.1628242074927955,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048724060599625893,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.20252033323049545,
|
|
"num_tokens": 27743718.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.347027158737182,
|
|
"epoch": 1.1633045148895294,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 0.00048722922258014506,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.19481330960989,
|
|
"num_tokens": 27754999.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.425617122650147,
|
|
"epoch": 1.1637848222862632,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004872178342366989,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.190083909034729,
|
|
"num_tokens": 27767684.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.315219736099243,
|
|
"epoch": 1.1642651296829971,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048720644096618475,
|
|
"loss": 5.1615,
|
|
"mean_token_accuracy": 0.20343200117349625,
|
|
"num_tokens": 27779103.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.338711500167847,
|
|
"epoch": 1.164745437079731,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004871950427688672,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.2057225674390793,
|
|
"num_tokens": 27791223.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.390639066696167,
|
|
"epoch": 1.1652257444764649,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048718363964501087,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.2053227260708809,
|
|
"num_tokens": 27802660.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.385347127914429,
|
|
"epoch": 1.1657060518731988,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004871722315948805,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.19497512578964232,
|
|
"num_tokens": 27814370.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.29230227470398,
|
|
"epoch": 1.1661863592699326,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004871608186187408,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.20355011969804765,
|
|
"num_tokens": 27825035.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.275160217285157,
|
|
"epoch": 1.1666666666666667,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048714940071685703,
|
|
"loss": 5.0533,
|
|
"mean_token_accuracy": 0.2002776861190796,
|
|
"num_tokens": 27837276.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.447699642181396,
|
|
"epoch": 1.1671469740634006,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048713797788949405,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.192610727250576,
|
|
"num_tokens": 27848618.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.35824728012085,
|
|
"epoch": 1.1676272814601345,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048712655013691714,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.19288371056318282,
|
|
"num_tokens": 27861556.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.388370609283447,
|
|
"epoch": 1.1681075888568684,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048711511745939165,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.19696660786867143,
|
|
"num_tokens": 27873211.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.3787675380706785,
|
|
"epoch": 1.1685878962536023,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000487103679857183,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.2005490094423294,
|
|
"num_tokens": 27883365.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.265456628799439,
|
|
"epoch": 1.1690682036503361,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004870922373305567,
|
|
"loss": 5.0484,
|
|
"mean_token_accuracy": 0.2099016010761261,
|
|
"num_tokens": 27894669.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.3137329578399655,
|
|
"epoch": 1.1695485110470702,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048708078987977837,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.20062563419342042,
|
|
"num_tokens": 27906480.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.339382266998291,
|
|
"epoch": 1.1700288184438041,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048706933750511394,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.206752011179924,
|
|
"num_tokens": 27918383.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.470038318634034,
|
|
"epoch": 1.170509125840538,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004870578802068292,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.1973343923687935,
|
|
"num_tokens": 27928944.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.261570644378662,
|
|
"epoch": 1.170989433237272,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048704641798519006,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.19926105439662933,
|
|
"num_tokens": 27941105.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.345675420761109,
|
|
"epoch": 1.1714697406340058,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048703495084046286,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.20363007634878158,
|
|
"num_tokens": 27952925.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.312554359436035,
|
|
"epoch": 1.1719500480307397,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004870234787729137,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.20582563281059266,
|
|
"num_tokens": 27965504.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.31930022239685,
|
|
"epoch": 1.1724303554274735,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004870120017828089,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.2087841585278511,
|
|
"num_tokens": 27975985.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.42659740447998,
|
|
"epoch": 1.1729106628242074,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.000487000519870415,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.1862453818321228,
|
|
"num_tokens": 27987784.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.344219732284546,
|
|
"epoch": 1.1733909702209413,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004869890330359986,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.19474149495363235,
|
|
"num_tokens": 27999623.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.3386194705963135,
|
|
"epoch": 1.1738712776176754,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004869775412798262,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.19656020998954774,
|
|
"num_tokens": 28011561.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.378550720214844,
|
|
"epoch": 1.1743515850144093,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048696604460216476,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.2080312803387642,
|
|
"num_tokens": 28022108.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.398981237411499,
|
|
"epoch": 1.1748318924111432,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048695454300328123,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.19528879523277282,
|
|
"num_tokens": 28033497.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.408945083618164,
|
|
"epoch": 1.175312199807877,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048694303648344256,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.20341200530529022,
|
|
"num_tokens": 28044790.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.291707229614258,
|
|
"epoch": 1.175792507204611,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048693152504291595,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.20424589961767198,
|
|
"num_tokens": 28056000.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.3088390827178955,
|
|
"epoch": 1.1762728146013448,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004869200086819686,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.19793660193681717,
|
|
"num_tokens": 28068264.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.389866018295288,
|
|
"epoch": 1.1767531219980787,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048690848740086796,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.20440614670515062,
|
|
"num_tokens": 28080220.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.383376502990723,
|
|
"epoch": 1.1772334293948128,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004868969611998814,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.19918202012777328,
|
|
"num_tokens": 28091531.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.309906673431397,
|
|
"epoch": 1.1777137367915467,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004868854300792767,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.19687680006027222,
|
|
"num_tokens": 28102982.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.376034212112427,
|
|
"epoch": 1.1781940441882806,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048687389403932144,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.20128699243068696,
|
|
"num_tokens": 28114131.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.358645391464234,
|
|
"epoch": 1.1786743515850144,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004868623530802835,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.1990375578403473,
|
|
"num_tokens": 28125637.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.420641326904297,
|
|
"epoch": 1.1791546589817483,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048685080720243086,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.20076376348733901,
|
|
"num_tokens": 28137284.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.3986773014068605,
|
|
"epoch": 1.1796349663784822,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004868392564060315,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.2002471372485161,
|
|
"num_tokens": 28148909.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.428885793685913,
|
|
"epoch": 1.180115273775216,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004868277006913537,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.20442042946815492,
|
|
"num_tokens": 28160392.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.391793918609619,
|
|
"epoch": 1.18059558117195,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004868161400586656,
|
|
"loss": 5.2497,
|
|
"mean_token_accuracy": 0.19369091242551803,
|
|
"num_tokens": 28172957.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.4584527015686035,
|
|
"epoch": 1.1810758885686838,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004868045745082357,
|
|
"loss": 5.2113,
|
|
"mean_token_accuracy": 0.1962095245718956,
|
|
"num_tokens": 28183239.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.358831787109375,
|
|
"epoch": 1.181556195965418,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004867930040403326,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.19603935033082961,
|
|
"num_tokens": 28195382.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.353927850723267,
|
|
"epoch": 1.1820365033621518,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00048678142865522475,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.19120893478393555,
|
|
"num_tokens": 28206645.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.438548946380616,
|
|
"epoch": 1.1825168107588857,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.000486769848353181,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.19612261801958084,
|
|
"num_tokens": 28218420.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.4169069766998295,
|
|
"epoch": 1.1829971181556196,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048675826313447027,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.19354679435491562,
|
|
"num_tokens": 28229458.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.392427635192871,
|
|
"epoch": 1.1834774255523535,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00048674667299936135,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.19513934403657912,
|
|
"num_tokens": 28242240.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.507054281234741,
|
|
"epoch": 1.1839577329490873,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048673507794812356,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.18856725245714187,
|
|
"num_tokens": 28254597.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.428821611404419,
|
|
"epoch": 1.1844380403458212,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004867234779810259,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.19882023632526397,
|
|
"num_tokens": 28266674.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.379216003417969,
|
|
"epoch": 1.1849183477425553,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004867118730983378,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.19652123302221297,
|
|
"num_tokens": 28278671.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.397844696044922,
|
|
"epoch": 1.1853986551392892,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004867002633003286,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20388589948415756,
|
|
"num_tokens": 28291085.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.334000968933106,
|
|
"epoch": 1.185878962536023,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000486688648587268,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.2041385516524315,
|
|
"num_tokens": 28303457.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.389097547531128,
|
|
"epoch": 1.186359269932757,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004866770289594256,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.19826333373785018,
|
|
"num_tokens": 28314599.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.505264472961426,
|
|
"epoch": 1.1868395773294909,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048666540441707107,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.19661984890699385,
|
|
"num_tokens": 28326266.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.380534505844116,
|
|
"epoch": 1.1873198847262247,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004866537749604744,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.20049924552440643,
|
|
"num_tokens": 28337238.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.310135316848755,
|
|
"epoch": 1.1878001921229586,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048664214058990546,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.20168502628803253,
|
|
"num_tokens": 28348060.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.356815195083618,
|
|
"epoch": 1.1882804995196925,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004866305013056346,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.19573729783296584,
|
|
"num_tokens": 28359442.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.383669996261597,
|
|
"epoch": 1.1887608069164266,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004866188571079318,
|
|
"loss": 5.2242,
|
|
"mean_token_accuracy": 0.20173468589782714,
|
|
"num_tokens": 28370827.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.437600135803223,
|
|
"epoch": 1.1892411143131605,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004866072079970676,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.18785340189933777,
|
|
"num_tokens": 28383115.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.3841907501220705,
|
|
"epoch": 1.1897214217098944,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048659555397331236,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.2010280191898346,
|
|
"num_tokens": 28394904.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.393501424789429,
|
|
"epoch": 1.1902017291066282,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004865838950369366,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.19555304646492006,
|
|
"num_tokens": 28407357.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.371555614471435,
|
|
"epoch": 1.1906820365033621,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048657223118821116,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.20490770041942596,
|
|
"num_tokens": 28418088.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.22875862121582,
|
|
"epoch": 1.191162343900096,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048656056242740665,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.20671380162239075,
|
|
"num_tokens": 28430022.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.326667451858521,
|
|
"epoch": 1.19164265129683,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004865488887547942,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.20249451994895934,
|
|
"num_tokens": 28440530.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.3966591358184814,
|
|
"epoch": 1.192122958693564,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004865372101706446,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.19606692492961883,
|
|
"num_tokens": 28452707.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.3031196117401125,
|
|
"epoch": 1.1926032660902979,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004865255266752292,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.21115377843379973,
|
|
"num_tokens": 28465131.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.314536666870117,
|
|
"epoch": 1.1930835734870318,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004865138382688191,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.20444202572107315,
|
|
"num_tokens": 28476136.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.422046756744384,
|
|
"epoch": 1.1935638808837656,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004865021449516859,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.19441829174757003,
|
|
"num_tokens": 28488374.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.353349256515503,
|
|
"epoch": 1.1940441882804995,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004864904467241008,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.20029931664466857,
|
|
"num_tokens": 28499585.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.26760721206665,
|
|
"epoch": 1.1945244956772334,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048647874358633556,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.2067888855934143,
|
|
"num_tokens": 28510707.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.396572494506836,
|
|
"epoch": 1.1950048030739673,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048646703553866183,
|
|
"loss": 5.2123,
|
|
"mean_token_accuracy": 0.19679928421974183,
|
|
"num_tokens": 28522398.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.326457786560058,
|
|
"epoch": 1.1954851104707012,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004864553225813515,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.20719118267297745,
|
|
"num_tokens": 28532949.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.282912540435791,
|
|
"epoch": 1.195965417867435,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004864436047146765,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.20763897895812988,
|
|
"num_tokens": 28544292.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.374918222427368,
|
|
"epoch": 1.1964457252641691,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048643188193890874,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.1954755127429962,
|
|
"num_tokens": 28556430.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.475298690795898,
|
|
"epoch": 1.196926032660903,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004864201542543206,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.1953951507806778,
|
|
"num_tokens": 28568475.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.424256658554077,
|
|
"epoch": 1.197406340057637,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004864084216611843,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.19842854589223863,
|
|
"num_tokens": 28579653.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.321965312957763,
|
|
"epoch": 1.1978866474543708,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048639668415977207,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.1996859207749367,
|
|
"num_tokens": 28590108.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.363766717910766,
|
|
"epoch": 1.1983669548511047,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048638494175035665,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.20593550354242324,
|
|
"num_tokens": 28602008.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.313108921051025,
|
|
"epoch": 1.1988472622478386,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004863731944332105,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.2061125487089157,
|
|
"num_tokens": 28613286.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.312188673019409,
|
|
"epoch": 1.1993275696445724,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004863614422086065,
|
|
"loss": 5.0541,
|
|
"mean_token_accuracy": 0.2112337365746498,
|
|
"num_tokens": 28625497.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.278160429000854,
|
|
"epoch": 1.1998078770413065,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004863496850768174,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.20094389319419861,
|
|
"num_tokens": 28638046.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.274611330032348,
|
|
"epoch": 1.2002881844380404,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004863379230381162,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.2022514209151268,
|
|
"num_tokens": 28647923.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.3361891746521,
|
|
"epoch": 1.2007684918347743,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000486326156092776,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.20273226052522658,
|
|
"num_tokens": 28660023.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.344466876983643,
|
|
"epoch": 1.2012487992315082,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00048631438424106985,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.20409687161445617,
|
|
"num_tokens": 28671568.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.259323215484619,
|
|
"epoch": 1.201729106628242,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048630260748327124,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.2069643631577492,
|
|
"num_tokens": 28682897.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.3738549709320065,
|
|
"epoch": 1.202209414024976,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048629082581965355,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.20119693726301194,
|
|
"num_tokens": 28694067.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.4160534858703615,
|
|
"epoch": 1.2026897214217098,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048627903925049033,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.19989402890205382,
|
|
"num_tokens": 28705738.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.3014359951019285,
|
|
"epoch": 1.2031700288184437,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048626724777605507,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.20294270515441895,
|
|
"num_tokens": 28717419.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.342375898361206,
|
|
"epoch": 1.2036503362151778,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004862554513966217,
|
|
"loss": 5.2487,
|
|
"mean_token_accuracy": 0.19172562509775162,
|
|
"num_tokens": 28728587.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.412291812896728,
|
|
"epoch": 1.2041306436119117,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048624365011246405,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.19578710198402405,
|
|
"num_tokens": 28740818.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.3454736232757565,
|
|
"epoch": 1.2046109510086456,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004862318439238561,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.21446070522069932,
|
|
"num_tokens": 28751936.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.331107425689697,
|
|
"epoch": 1.2050912584053795,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000486220032831072,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.199016235768795,
|
|
"num_tokens": 28763271.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.380507707595825,
|
|
"epoch": 1.2055715658021133,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004862082168343859,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.20214309245347978,
|
|
"num_tokens": 28774282.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.3720344543457035,
|
|
"epoch": 1.2060518731988472,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004861963959340722,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.20117385536432267,
|
|
"num_tokens": 28785826.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.294094800949097,
|
|
"epoch": 1.206532180595581,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004861845701304053,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.20598790496587754,
|
|
"num_tokens": 28797669.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.351427888870239,
|
|
"epoch": 1.2070124879923152,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048617273942365977,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.19645900577306746,
|
|
"num_tokens": 28808438.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.321493482589721,
|
|
"epoch": 1.207492795389049,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004861609038141103,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.20699209719896317,
|
|
"num_tokens": 28819707.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.389062309265137,
|
|
"epoch": 1.207973102785783,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048614906330203165,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.20063450932502747,
|
|
"num_tokens": 28831829.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.326475381851196,
|
|
"epoch": 1.2084534101825168,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004861372178876987,
|
|
"loss": 5.148,
|
|
"mean_token_accuracy": 0.19967350661754607,
|
|
"num_tokens": 28843429.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.28063473701477,
|
|
"epoch": 1.2089337175792507,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048612536757138653,
|
|
"loss": 5.0665,
|
|
"mean_token_accuracy": 0.2066696360707283,
|
|
"num_tokens": 28856239.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.3996397972106935,
|
|
"epoch": 1.2094140249759846,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004861135123533702,
|
|
"loss": 5.1553,
|
|
"mean_token_accuracy": 0.19807262271642684,
|
|
"num_tokens": 28868599.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.339787769317627,
|
|
"epoch": 1.2098943323727185,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048610165223392503,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.20046315342187881,
|
|
"num_tokens": 28880234.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.406326866149902,
|
|
"epoch": 1.2103746397694524,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004860897872133263,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.1996910333633423,
|
|
"num_tokens": 28892198.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.414484882354737,
|
|
"epoch": 1.2108549471661862,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004860779172918496,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.19422879666090012,
|
|
"num_tokens": 28904153.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.408674716949463,
|
|
"epoch": 1.2113352545629203,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004860660424697704,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.1973506912589073,
|
|
"num_tokens": 28915284.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.351528739929199,
|
|
"epoch": 1.2118155619596542,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048605416274736434,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.20026987493038179,
|
|
"num_tokens": 28928168.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.310980939865113,
|
|
"epoch": 1.2122958693563881,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048604227812490744,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.21178123652935027,
|
|
"num_tokens": 28938548.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.341546678543091,
|
|
"epoch": 1.212776176753122,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048603038860267546,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.1974686712026596,
|
|
"num_tokens": 28949252.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.3657927989959715,
|
|
"epoch": 1.2132564841498559,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004860184941809445,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.20353519469499587,
|
|
"num_tokens": 28960758.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.367190933227539,
|
|
"epoch": 1.2137367915465898,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048600659485999073,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.2001407191157341,
|
|
"num_tokens": 28972604.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.34518461227417,
|
|
"epoch": 1.2142170989433236,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048599469064009027,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.20637290179729462,
|
|
"num_tokens": 28983617.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.312652969360352,
|
|
"epoch": 1.2146974063400577,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00048598278152151974,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.20037295669317245,
|
|
"num_tokens": 28994277.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.487977743148804,
|
|
"epoch": 1.2151777137367916,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004859708675045555,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.20140786319971085,
|
|
"num_tokens": 29004844.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.243425035476685,
|
|
"epoch": 1.2156580211335255,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004859589485894741,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.21186215579509735,
|
|
"num_tokens": 29015978.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.392303991317749,
|
|
"epoch": 1.2161383285302594,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004859470247765524,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.1990487441420555,
|
|
"num_tokens": 29026966.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.397476720809936,
|
|
"epoch": 1.2166186359269933,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004859350960660671,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.2090051218867302,
|
|
"num_tokens": 29037943.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.4366357803344725,
|
|
"epoch": 1.2170989433237271,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004859231624582953,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.19415497332811354,
|
|
"num_tokens": 29049939.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.317119693756103,
|
|
"epoch": 1.217579250720461,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048591122395351394,
|
|
"loss": 5.1673,
|
|
"mean_token_accuracy": 0.19993019551038743,
|
|
"num_tokens": 29062442.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.290191793441773,
|
|
"epoch": 1.218059558117195,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004858992805520003,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.20055499523878098,
|
|
"num_tokens": 29074240.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.4654120922088625,
|
|
"epoch": 1.218539865513929,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048588733225403153,
|
|
"loss": 5.1829,
|
|
"mean_token_accuracy": 0.19694548845291138,
|
|
"num_tokens": 29085550.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.371953821182251,
|
|
"epoch": 1.219020172910663,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004858753790598851,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20303001999855042,
|
|
"num_tokens": 29097092.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.264970445632935,
|
|
"epoch": 1.2195004803073968,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004858634209698386,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.20328317135572432,
|
|
"num_tokens": 29108119.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.331994295120239,
|
|
"epoch": 1.2199807877041307,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048585145798416956,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.19819319993257523,
|
|
"num_tokens": 29120605.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.436542558670044,
|
|
"epoch": 1.2204610951008645,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004858394901031558,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.20241838097572326,
|
|
"num_tokens": 29131582.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.37907977104187,
|
|
"epoch": 1.2209414024975984,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004858275173270751,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.19640718549489974,
|
|
"num_tokens": 29143436.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.295017719268799,
|
|
"epoch": 1.2214217098943323,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048581553965620553,
|
|
"loss": 5.0685,
|
|
"mean_token_accuracy": 0.20247238874435425,
|
|
"num_tokens": 29154445.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.354412984848023,
|
|
"epoch": 1.2219020172910664,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048580355709082506,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.2037876695394516,
|
|
"num_tokens": 29164599.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.334515142440796,
|
|
"epoch": 1.2223823246878003,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000485791569631212,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.1990063965320587,
|
|
"num_tokens": 29176275.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.402159929275513,
|
|
"epoch": 1.2228626320845342,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004857795772776446,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.197144778072834,
|
|
"num_tokens": 29189102.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.3538671970367435,
|
|
"epoch": 1.223342939481268,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048576758003040127,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.19858692288398744,
|
|
"num_tokens": 29200953.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.3314831256866455,
|
|
"epoch": 1.223823246878002,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048575557788976066,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.19703435003757477,
|
|
"num_tokens": 29212942.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.310234546661377,
|
|
"epoch": 1.2243035542747358,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004857435708560013,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20938374996185302,
|
|
"num_tokens": 29224949.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.473360776901245,
|
|
"epoch": 1.2247838616714697,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00048573155892940204,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.19021537154912949,
|
|
"num_tokens": 29236044.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.326746463775635,
|
|
"epoch": 1.2252641690682036,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048571954211024164,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.19844659119844438,
|
|
"num_tokens": 29248084.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.32636137008667,
|
|
"epoch": 1.2257444764649374,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048570752039879924,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.20538586378097534,
|
|
"num_tokens": 29258710.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.3926513671875,
|
|
"epoch": 1.2262247838616716,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004856954937953539,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.1884328842163086,
|
|
"num_tokens": 29270173.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.42624340057373,
|
|
"epoch": 1.2267050912584054,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004856834623001848,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.19374579191207886,
|
|
"num_tokens": 29280407.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.363224887847901,
|
|
"epoch": 1.2271853986551393,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004856714259135713,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.21092236340045928,
|
|
"num_tokens": 29292287.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.333473348617554,
|
|
"epoch": 1.2276657060518732,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004856593846357929,
|
|
"loss": 5.2062,
|
|
"mean_token_accuracy": 0.1955728903412819,
|
|
"num_tokens": 29303099.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.409201669692993,
|
|
"epoch": 1.228146013448607,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004856473384671291,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.19757024198770523,
|
|
"num_tokens": 29314445.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.31076078414917,
|
|
"epoch": 1.228626320845341,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00048563528740785955,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.20026419162750245,
|
|
"num_tokens": 29325309.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.343060159683228,
|
|
"epoch": 1.2291066282420748,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048562323145826414,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.20737859904766082,
|
|
"num_tokens": 29338582.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.378735494613648,
|
|
"epoch": 1.229586935638809,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004856111706186227,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.2014962464570999,
|
|
"num_tokens": 29349875.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.444497680664062,
|
|
"epoch": 1.2300672430355428,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048559910488921534,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.19321610629558564,
|
|
"num_tokens": 29361800.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.342003393173218,
|
|
"epoch": 1.2305475504322767,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000485587034270322,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.20041815489530562,
|
|
"num_tokens": 29372795.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.411420392990112,
|
|
"epoch": 1.2310278578290106,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000485574958762223,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.1953429400920868,
|
|
"num_tokens": 29385391.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.245332098007202,
|
|
"epoch": 1.2315081652257445,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048556287836519886,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.20825864523649215,
|
|
"num_tokens": 29397113.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.427263021469116,
|
|
"epoch": 1.2319884726224783,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004855507930795299,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.19889317005872725,
|
|
"num_tokens": 29407552.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.412282037734985,
|
|
"epoch": 1.2324687800192122,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048553870290549665,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.20339487493038177,
|
|
"num_tokens": 29418500.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.405433893203735,
|
|
"epoch": 1.232949087415946,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.00048552660784338,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.19940159022808074,
|
|
"num_tokens": 29430335.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.346133518218994,
|
|
"epoch": 1.23342939481268,
|
|
"grad_norm": 6.0625,
|
|
"learning_rate": 0.0004855145078934606,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.19356145411729814,
|
|
"num_tokens": 29441435.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.376684522628784,
|
|
"epoch": 1.233909702209414,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004855024030560195,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.20228267163038255,
|
|
"num_tokens": 29453140.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.26374249458313,
|
|
"epoch": 1.234390009606148,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004854902933313376,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.20979991406202317,
|
|
"num_tokens": 29464572.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.409177494049072,
|
|
"epoch": 1.2348703170028819,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048547817871969607,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.18599925488233565,
|
|
"num_tokens": 29477069.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.469481134414673,
|
|
"epoch": 1.2353506243996157,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048546605922137633,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.1993350937962532,
|
|
"num_tokens": 29486860.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.463558626174927,
|
|
"epoch": 1.2358309317963496,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004854539348366596,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.19616340547800065,
|
|
"num_tokens": 29499129.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.269811344146729,
|
|
"epoch": 1.2363112391930835,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004854418055658274,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.20640467405319213,
|
|
"num_tokens": 29510764.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.348705863952636,
|
|
"epoch": 1.2367915465898176,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048542967140916134,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.1993205264210701,
|
|
"num_tokens": 29522882.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.412566375732422,
|
|
"epoch": 1.2372718539865515,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004854175323669432,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.19906629770994186,
|
|
"num_tokens": 29533348.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.302993631362915,
|
|
"epoch": 1.2377521613832854,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004854053884394547,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.2029001832008362,
|
|
"num_tokens": 29545649.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.3617262840271,
|
|
"epoch": 1.2382324687800192,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048539323962697796,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.20096800327301026,
|
|
"num_tokens": 29558252.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.474723625183105,
|
|
"epoch": 1.2387127761767531,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004853810859297949,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.19714667797088622,
|
|
"num_tokens": 29569495.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.337574100494384,
|
|
"epoch": 1.239193083573487,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048536892734818773,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.2002403050661087,
|
|
"num_tokens": 29582167.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.3920482158660885,
|
|
"epoch": 1.239673390970221,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004853567638824387,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.20029108971357346,
|
|
"num_tokens": 29593964.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.407089138031006,
|
|
"epoch": 1.2401536983669548,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048534459553283026,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20376240313053132,
|
|
"num_tokens": 29604844.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.377049398422241,
|
|
"epoch": 1.2406340057636887,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004853324222996449,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.21023209244012833,
|
|
"num_tokens": 29615219.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.487801218032837,
|
|
"epoch": 1.2411143131604228,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.00048532024418316525,
|
|
"loss": 5.2516,
|
|
"mean_token_accuracy": 0.19671308547258376,
|
|
"num_tokens": 29626472.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.340252637863159,
|
|
"epoch": 1.2415946205571566,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004853080611836741,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.20971932411193847,
|
|
"num_tokens": 29637966.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.321205997467041,
|
|
"epoch": 1.2420749279538905,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048529587330145427,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.20443299859762193,
|
|
"num_tokens": 29648730.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.28255181312561,
|
|
"epoch": 1.2425552353506244,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048528368053678863,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.20166535824537277,
|
|
"num_tokens": 29660576.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.338960790634156,
|
|
"epoch": 1.2430355427473583,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004852714828899604,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.20124776363372804,
|
|
"num_tokens": 29672906.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.336222410202026,
|
|
"epoch": 1.2435158501440922,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048525928036125264,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.20149919241666794,
|
|
"num_tokens": 29685360.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.369892930984497,
|
|
"epoch": 1.243996157540826,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048524707295094884,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.19467362016439438,
|
|
"num_tokens": 29697257.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.33024640083313,
|
|
"epoch": 1.2444764649375601,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004852348606593322,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.20635769367218018,
|
|
"num_tokens": 29707877.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.329155969619751,
|
|
"epoch": 1.244956772334294,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048522264348668646,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.2005823940038681,
|
|
"num_tokens": 29719358.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.308385705947876,
|
|
"epoch": 1.245437079731028,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004852104214332951,
|
|
"loss": 5.0219,
|
|
"mean_token_accuracy": 0.21624912768602372,
|
|
"num_tokens": 29730383.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.394252824783325,
|
|
"epoch": 1.2459173871277618,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048519819449944205,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.20642869919538498,
|
|
"num_tokens": 29741142.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.302992963790894,
|
|
"epoch": 1.2463976945244957,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000485185962685411,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.2015356183052063,
|
|
"num_tokens": 29754618.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.413315773010254,
|
|
"epoch": 1.2468780019212296,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000485173725991486,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.19952298402786256,
|
|
"num_tokens": 29767115.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.429574298858642,
|
|
"epoch": 1.2473583093179634,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048516148441795124,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.19643279165029526,
|
|
"num_tokens": 29778165.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.445894861221314,
|
|
"epoch": 1.2478386167146973,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004851492379650908,
|
|
"loss": 5.2603,
|
|
"mean_token_accuracy": 0.19133627712726592,
|
|
"num_tokens": 29790528.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.346064233779908,
|
|
"epoch": 1.2483189241114312,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004851369866331891,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.20327979773283006,
|
|
"num_tokens": 29801709.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.3408127784729,
|
|
"epoch": 1.2487992315081653,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004851247304225306,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.196063594520092,
|
|
"num_tokens": 29812963.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.370650959014893,
|
|
"epoch": 1.2492795389048992,
|
|
"grad_norm": 6.6875,
|
|
"learning_rate": 0.0004851124693333997,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.2047895073890686,
|
|
"num_tokens": 29823711.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.318699979782105,
|
|
"epoch": 1.249759846301633,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004851002033660812,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.20476754009723663,
|
|
"num_tokens": 29834038.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.38987627029419,
|
|
"epoch": 1.250240153698367,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048508793252085994,
|
|
"loss": 5.1255,
|
|
"mean_token_accuracy": 0.20020674616098405,
|
|
"num_tokens": 29844759.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.236159992218018,
|
|
"epoch": 1.2507204610951008,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004850756567980206,
|
|
"loss": 4.9912,
|
|
"mean_token_accuracy": 0.2056865692138672,
|
|
"num_tokens": 29855643.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.369000244140625,
|
|
"epoch": 1.2512007684918347,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048506337619784836,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.19961898177862167,
|
|
"num_tokens": 29866917.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.485680723190308,
|
|
"epoch": 1.2516810758885688,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004850510907206283,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.19271115064620972,
|
|
"num_tokens": 29878937.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.279966926574707,
|
|
"epoch": 1.2521613832853027,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048503880036664555,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.2081865206360817,
|
|
"num_tokens": 29889544.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.273176860809326,
|
|
"epoch": 1.2526416906820366,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004850265051361857,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.19775716513395308,
|
|
"num_tokens": 29901919.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.4128316879272464,
|
|
"epoch": 1.2531219980787704,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004850142050295339,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.20159833282232284,
|
|
"num_tokens": 29913870.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.369484710693359,
|
|
"epoch": 1.2536023054755043,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048500190004697595,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.20957815647125244,
|
|
"num_tokens": 29925180.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.2413774013519285,
|
|
"epoch": 1.2540826128722382,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004849895901887974,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.21247663646936416,
|
|
"num_tokens": 29936433.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.372003650665283,
|
|
"epoch": 1.254562920268972,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004849772754552842,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.19564427733421325,
|
|
"num_tokens": 29948891.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.339636516571045,
|
|
"epoch": 1.255043227665706,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048496495584672214,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.20694905817508696,
|
|
"num_tokens": 29960113.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.3573887825012205,
|
|
"epoch": 1.2555235350624399,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048495263136339725,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.19890657365322112,
|
|
"num_tokens": 29972168.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.341222143173217,
|
|
"epoch": 1.2560038424591737,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004849403020055956,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.2031906306743622,
|
|
"num_tokens": 29982996.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.357997941970825,
|
|
"epoch": 1.2564841498559078,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.00048492796777360373,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.19873852133750916,
|
|
"num_tokens": 29994088.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.474556922912598,
|
|
"epoch": 1.2569644572526417,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048491562866770767,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.1989903226494789,
|
|
"num_tokens": 30005403.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.374645233154297,
|
|
"epoch": 1.2574447646493756,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048490328468819404,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.20840147733688355,
|
|
"num_tokens": 30015961.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.3042113304138185,
|
|
"epoch": 1.2579250720461095,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048489093583534945,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.20314032435417176,
|
|
"num_tokens": 30026670.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.343568181991577,
|
|
"epoch": 1.2584053794428434,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004848785821094606,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.20473890453577043,
|
|
"num_tokens": 30036711.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.368521404266358,
|
|
"epoch": 1.2588856868395775,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004848662235108142,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.19966153800487518,
|
|
"num_tokens": 30047587.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.340132236480713,
|
|
"epoch": 1.2593659942363113,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004848538600396973,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.20400311350822448,
|
|
"num_tokens": 30059348.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.3327916145324705,
|
|
"epoch": 1.2598463016330452,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048484149169639694,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.20369334220886232,
|
|
"num_tokens": 30070485.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.3156068325042725,
|
|
"epoch": 1.260326609029779,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004848291184812003,
|
|
"loss": 5.0593,
|
|
"mean_token_accuracy": 0.21424184441566468,
|
|
"num_tokens": 30081114.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.336349153518677,
|
|
"epoch": 1.260806916426513,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004848167403943945,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.20139845311641694,
|
|
"num_tokens": 30092634.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.319647550582886,
|
|
"epoch": 1.2612872238232469,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048480435743626703,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.2054018869996071,
|
|
"num_tokens": 30104205.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.326454830169678,
|
|
"epoch": 1.2617675312199808,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004847919696071054,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.2023329496383667,
|
|
"num_tokens": 30116978.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.305848550796509,
|
|
"epoch": 1.2622478386167146,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048477957690719716,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.20905521959066392,
|
|
"num_tokens": 30128549.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.373541450500488,
|
|
"epoch": 1.2627281460134485,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004847671793368301,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.2029866486787796,
|
|
"num_tokens": 30139492.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.330583906173706,
|
|
"epoch": 1.2632084534101824,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000484754776896292,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.2056432768702507,
|
|
"num_tokens": 30150450.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.394663333892822,
|
|
"epoch": 1.2636887608069165,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004847423695858708,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.2026163622736931,
|
|
"num_tokens": 30162204.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.361279535293579,
|
|
"epoch": 1.2641690682036504,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048472995740585456,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.1980403855443001,
|
|
"num_tokens": 30172574.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.2294697761535645,
|
|
"epoch": 1.2646493756003843,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004847175403565316,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.2066290944814682,
|
|
"num_tokens": 30183957.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.347656393051148,
|
|
"epoch": 1.2651296829971181,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048470511843818996,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.20896881222724914,
|
|
"num_tokens": 30194207.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.332297992706299,
|
|
"epoch": 1.265609990393852,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004846926916511182,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.2130802646279335,
|
|
"num_tokens": 30205180.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.360416269302368,
|
|
"epoch": 1.266090297790586,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004846802599956048,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.2031206026673317,
|
|
"num_tokens": 30217734.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.453233528137207,
|
|
"epoch": 1.26657060518732,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048466782347193847,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.18984228521585464,
|
|
"num_tokens": 30229835.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.4105456352233885,
|
|
"epoch": 1.267050912584054,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048465538208040775,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.19797122478485107,
|
|
"num_tokens": 30241932.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.367320585250854,
|
|
"epoch": 1.2675312199807878,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048464293582130166,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.1995729014277458,
|
|
"num_tokens": 30253149.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.382949447631836,
|
|
"epoch": 1.2680115273775217,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004846304846949091,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.20114304572343827,
|
|
"num_tokens": 30264083.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.301146411895752,
|
|
"epoch": 1.2684918347742555,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048461802870151916,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.20814597308635713,
|
|
"num_tokens": 30274832.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.253353881835937,
|
|
"epoch": 1.2689721421709894,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048460556784142106,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.20501581877470015,
|
|
"num_tokens": 30284945.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.388607358932495,
|
|
"epoch": 1.2694524495677233,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048459310211490406,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.20503615736961364,
|
|
"num_tokens": 30295133.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.371882534027099,
|
|
"epoch": 1.2699327569644572,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004845806315222576,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.19821202903985977,
|
|
"num_tokens": 30305268.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.311619520187378,
|
|
"epoch": 1.270413064361191,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004845681560637711,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.20660299062728882,
|
|
"num_tokens": 30317118.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.360806703567505,
|
|
"epoch": 1.270893371757925,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004845556757397344,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.19914165884256363,
|
|
"num_tokens": 30328684.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.396165800094605,
|
|
"epoch": 1.271373679154659,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004845431905504372,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.19578873217105866,
|
|
"num_tokens": 30341433.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.376298952102661,
|
|
"epoch": 1.271853986551393,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048453070049616926,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.21136078834533692,
|
|
"num_tokens": 30353159.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.328975677490234,
|
|
"epoch": 1.2723342939481268,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048451820557722064,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.2027696415781975,
|
|
"num_tokens": 30363251.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.43357400894165,
|
|
"epoch": 1.2728146013448607,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004845057057938815,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.20103075206279755,
|
|
"num_tokens": 30375850.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.389856624603271,
|
|
"epoch": 1.2732949087415946,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048449320114644185,
|
|
"loss": 5.2284,
|
|
"mean_token_accuracy": 0.19401920288801194,
|
|
"num_tokens": 30386839.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.3865491390228275,
|
|
"epoch": 1.2737752161383284,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004844806916351922,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.19698424637317657,
|
|
"num_tokens": 30398872.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.368124103546142,
|
|
"epoch": 1.2742555235350626,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004844681772604229,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.209516678750515,
|
|
"num_tokens": 30409581.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.3348973274230955,
|
|
"epoch": 1.2747358309317964,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048445565802242454,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.1989857643842697,
|
|
"num_tokens": 30420209.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.369249773025513,
|
|
"epoch": 1.2752161383285303,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004844431339214878,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.2068863332271576,
|
|
"num_tokens": 30432093.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.357045030593872,
|
|
"epoch": 1.2756964457252642,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004844306049579034,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.20102150589227677,
|
|
"num_tokens": 30442796.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.363987684249878,
|
|
"epoch": 1.276176753121998,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048441807113196216,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.19339045137166977,
|
|
"num_tokens": 30455226.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.450055885314941,
|
|
"epoch": 1.276657060518732,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048440553244395517,
|
|
"loss": 5.2449,
|
|
"mean_token_accuracy": 0.1956735298037529,
|
|
"num_tokens": 30467082.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.425793313980103,
|
|
"epoch": 1.2771373679154658,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048439298889417357,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.19411949962377548,
|
|
"num_tokens": 30479051.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.344773817062378,
|
|
"epoch": 1.2776176753121997,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048438044048290847,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.19852303117513656,
|
|
"num_tokens": 30489989.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.345989513397217,
|
|
"epoch": 1.2780979827089336,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.00048436788721045135,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.20266603976488112,
|
|
"num_tokens": 30501533.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.372400712966919,
|
|
"epoch": 1.2785782901056677,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004843553290770935,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.20096248537302017,
|
|
"num_tokens": 30512231.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.3523646831512455,
|
|
"epoch": 1.2790585975024016,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004843427660831266,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.20112545788288116,
|
|
"num_tokens": 30523204.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.447382688522339,
|
|
"epoch": 1.2795389048991355,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048433019822884235,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.18958229571580887,
|
|
"num_tokens": 30534956.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.320156621932983,
|
|
"epoch": 1.2800192122958693,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004843176255145325,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.20451148599386215,
|
|
"num_tokens": 30545938.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.3395366191864015,
|
|
"epoch": 1.2804995196926032,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004843050479404888,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.21097815036773682,
|
|
"num_tokens": 30557323.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.340563106536865,
|
|
"epoch": 1.280979827089337,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048429246550700343,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.19994896203279494,
|
|
"num_tokens": 30569960.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.305930089950562,
|
|
"epoch": 1.2814601344860712,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004842798782143686,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.19788095653057097,
|
|
"num_tokens": 30581904.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.3605536937713625,
|
|
"epoch": 1.281940441882805,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048426728606287627,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.2083275467157364,
|
|
"num_tokens": 30592955.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.350933980941773,
|
|
"epoch": 1.282420749279539,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004842546890528191,
|
|
"loss": 5.1685,
|
|
"mean_token_accuracy": 0.20206224620342256,
|
|
"num_tokens": 30604020.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.332548379898071,
|
|
"epoch": 1.2829010566762729,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004842420871844893,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.199458347260952,
|
|
"num_tokens": 30615623.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.420214986801147,
|
|
"epoch": 1.2833813640730067,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004842294804581796,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.20628878176212312,
|
|
"num_tokens": 30626258.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.382568454742431,
|
|
"epoch": 1.2838616714697406,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048421686887418266,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.19404437243938447,
|
|
"num_tokens": 30637861.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.36430082321167,
|
|
"epoch": 1.2843419788664745,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004842042524327912,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.2024310678243637,
|
|
"num_tokens": 30648835.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.4410735130310055,
|
|
"epoch": 1.2848222862632084,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004841916311342983,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.19039245694875717,
|
|
"num_tokens": 30659117.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.349467802047729,
|
|
"epoch": 1.2853025936599423,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004841790049789969,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.202546164393425,
|
|
"num_tokens": 30670282.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.385199642181396,
|
|
"epoch": 1.2857829010566761,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048416637396718004,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.1973421573638916,
|
|
"num_tokens": 30681967.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.448413991928101,
|
|
"epoch": 1.2862632084534102,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004841537380991411,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.19564255326986313,
|
|
"num_tokens": 30692803.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.3083484172821045,
|
|
"epoch": 1.2867435158501441,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00048414109737517346,
|
|
"loss": 5.0354,
|
|
"mean_token_accuracy": 0.20847150385379792,
|
|
"num_tokens": 30704097.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.334354972839355,
|
|
"epoch": 1.287223823246878,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004841284517955706,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.19359100610017776,
|
|
"num_tokens": 30717983.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.272618198394776,
|
|
"epoch": 1.2877041306436119,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000484115801360626,
|
|
"loss": 5.0029,
|
|
"mean_token_accuracy": 0.21284743994474412,
|
|
"num_tokens": 30728446.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.258653068542481,
|
|
"epoch": 1.2881844380403458,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004841031460706335,
|
|
"loss": 4.9614,
|
|
"mean_token_accuracy": 0.2102557361125946,
|
|
"num_tokens": 30739587.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.284115409851074,
|
|
"epoch": 1.2886647454370797,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048409048592588683,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.20472023040056228,
|
|
"num_tokens": 30750093.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.344434022903442,
|
|
"epoch": 1.2891450528338138,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004840778209266799,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.204330475628376,
|
|
"num_tokens": 30761692.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.325588512420654,
|
|
"epoch": 1.2896253602305476,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00048406515107330685,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.19818190783262252,
|
|
"num_tokens": 30773474.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.471381044387817,
|
|
"epoch": 1.2901056676272815,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048405247636606173,
|
|
"loss": 5.2523,
|
|
"mean_token_accuracy": 0.19113411754369736,
|
|
"num_tokens": 30785464.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.364251708984375,
|
|
"epoch": 1.2905859750240154,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048403979680523894,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.20033991634845733,
|
|
"num_tokens": 30796343.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.365818929672241,
|
|
"epoch": 1.2910662824207493,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004840271123911328,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.20222489535808563,
|
|
"num_tokens": 30807795.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.335166645050049,
|
|
"epoch": 1.2915465898174832,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004840144231240377,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.1961706429719925,
|
|
"num_tokens": 30819629.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.363595819473266,
|
|
"epoch": 1.292026897214217,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004840017290042484,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.20668612271547318,
|
|
"num_tokens": 30831545.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.3687896728515625,
|
|
"epoch": 1.292507204610951,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048398903003205957,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.20432914048433304,
|
|
"num_tokens": 30843614.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.299862337112427,
|
|
"epoch": 1.2929875120076848,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048397632620776604,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.20915237367153167,
|
|
"num_tokens": 30853749.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.317346239089966,
|
|
"epoch": 1.293467819404419,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048396361753166276,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.2043304428458214,
|
|
"num_tokens": 30865065.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.376353788375854,
|
|
"epoch": 1.2939481268011528,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048395090400404466,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.2022722229361534,
|
|
"num_tokens": 30876746.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.408205366134643,
|
|
"epoch": 1.2944284341978867,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048393818562520715,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.1984675258398056,
|
|
"num_tokens": 30889543.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.374189233779907,
|
|
"epoch": 1.2949087415946205,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048392546239544535,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.1956399619579315,
|
|
"num_tokens": 30901949.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.3719408988952635,
|
|
"epoch": 1.2953890489913544,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004839127343150547,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.20173372328281403,
|
|
"num_tokens": 30912660.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.359444427490234,
|
|
"epoch": 1.2958693563880883,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004839000013843307,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.2040621519088745,
|
|
"num_tokens": 30924276.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.3478456974029545,
|
|
"epoch": 1.2963496637848224,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048388726360356894,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.20215616524219512,
|
|
"num_tokens": 30935169.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.433650922775269,
|
|
"epoch": 1.2968299711815563,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004838745209730653,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.19483187943696975,
|
|
"num_tokens": 30946116.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.414237689971924,
|
|
"epoch": 1.2973102785782902,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048386177349311535,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.19886140376329423,
|
|
"num_tokens": 30958509.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.379494667053223,
|
|
"epoch": 1.297790585975024,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004838490211640153,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.2018559232354164,
|
|
"num_tokens": 30969501.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.307286739349365,
|
|
"epoch": 1.298270893371758,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004838362639860611,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.1969323828816414,
|
|
"num_tokens": 30979768.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.2598748207092285,
|
|
"epoch": 1.2987512007684918,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000483823501959549,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.2079791858792305,
|
|
"num_tokens": 30992020.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.399859523773193,
|
|
"epoch": 1.2992315081652257,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048381073508477527,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.19624945074319838,
|
|
"num_tokens": 31004081.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.498485517501831,
|
|
"epoch": 1.2997118155619596,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048379796336203625,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.194696606695652,
|
|
"num_tokens": 31015776.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.310241079330444,
|
|
"epoch": 1.3001921229586935,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004837851867916286,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.1958205968141556,
|
|
"num_tokens": 31028066.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.316801595687866,
|
|
"epoch": 1.3006724303554273,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004837724053738488,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.20547377914190293,
|
|
"num_tokens": 31040234.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.391037845611573,
|
|
"epoch": 1.3011527377521614,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00048375961910899373,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.20251529067754745,
|
|
"num_tokens": 31051158.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.435376739501953,
|
|
"epoch": 1.3016330451488953,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004837468279973602,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.20004211664199828,
|
|
"num_tokens": 31063404.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.370404529571533,
|
|
"epoch": 1.3021133525456292,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004837340320392451,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.20598925203084945,
|
|
"num_tokens": 31073845.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.279167222976684,
|
|
"epoch": 1.302593659942363,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048372123123494563,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.1981288120150566,
|
|
"num_tokens": 31086914.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.34626784324646,
|
|
"epoch": 1.303073967339097,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000483708425584759,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.2096984162926674,
|
|
"num_tokens": 31098627.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.471300315856934,
|
|
"epoch": 1.3035542747358309,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004836956150889825,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.19153014123439788,
|
|
"num_tokens": 31110064.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.392726230621338,
|
|
"epoch": 1.304034582132565,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004836827997479134,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.2105356425046921,
|
|
"num_tokens": 31121572.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.465579652786255,
|
|
"epoch": 1.3045148895292988,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004836699795618494,
|
|
"loss": 5.2159,
|
|
"mean_token_accuracy": 0.19697636216878892,
|
|
"num_tokens": 31133276.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.381417512893677,
|
|
"epoch": 1.3049951969260327,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004836571545310881,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.19439461082220078,
|
|
"num_tokens": 31144524.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.327375841140747,
|
|
"epoch": 1.3054755043227666,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048364432465592723,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.2126304104924202,
|
|
"num_tokens": 31155775.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.36745924949646,
|
|
"epoch": 1.3059558117195005,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004836314899366647,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.20683857500553132,
|
|
"num_tokens": 31166176.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.403178644180298,
|
|
"epoch": 1.3064361191162344,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048361865037359846,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.20262635499238968,
|
|
"num_tokens": 31178568.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.391726064682007,
|
|
"epoch": 1.3069164265129682,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048360580596702664,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.19984792321920394,
|
|
"num_tokens": 31188897.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.351366472244263,
|
|
"epoch": 1.3073967339097021,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048359295671724744,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.1972188636660576,
|
|
"num_tokens": 31201370.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.342919826507568,
|
|
"epoch": 1.307877041306436,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004835801026245592,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.19579764008522033,
|
|
"num_tokens": 31212704.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.416233348846435,
|
|
"epoch": 1.30835734870317,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048356724368926035,
|
|
"loss": 5.1632,
|
|
"mean_token_accuracy": 0.20171422362327576,
|
|
"num_tokens": 31224447.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.4233448028564455,
|
|
"epoch": 1.308837656099904,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048355437991164937,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.205408076941967,
|
|
"num_tokens": 31235648.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.308753108978271,
|
|
"epoch": 1.3093179634966379,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000483541511292025,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.1970699593424797,
|
|
"num_tokens": 31248330.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.420334577560425,
|
|
"epoch": 1.3097982708933718,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048352863783068594,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.19882771670818328,
|
|
"num_tokens": 31260036.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.307511568069458,
|
|
"epoch": 1.3102785782901056,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048351575952793117,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.20462859570980071,
|
|
"num_tokens": 31271473.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.227953672409058,
|
|
"epoch": 1.3107588856868395,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004835028763840595,
|
|
"loss": 5.008,
|
|
"mean_token_accuracy": 0.21247871369123458,
|
|
"num_tokens": 31282045.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.389016437530517,
|
|
"epoch": 1.3112391930835736,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004834899883993703,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.1998434394598007,
|
|
"num_tokens": 31292644.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.394155120849609,
|
|
"epoch": 1.3117195004803075,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048347709557416263,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.2068080872297287,
|
|
"num_tokens": 31304422.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.283581304550171,
|
|
"epoch": 1.3121998078770414,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004834641979087359,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.20116272419691086,
|
|
"num_tokens": 31314845.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.423130941390991,
|
|
"epoch": 1.3126801152737753,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004834512954033894,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.1995086967945099,
|
|
"num_tokens": 31325669.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.390828323364258,
|
|
"epoch": 1.3131604226705091,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048343838805842284,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.20633677989244462,
|
|
"num_tokens": 31336023.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.368362236022949,
|
|
"epoch": 1.313640730067243,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048342547587413583,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.19732645750045777,
|
|
"num_tokens": 31347146.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.3952912330627445,
|
|
"epoch": 1.314121037463977,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004834125588508282,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.20183661729097366,
|
|
"num_tokens": 31357616.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.4574745178222654,
|
|
"epoch": 1.3146013448607108,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004833996369887998,
|
|
"loss": 5.2054,
|
|
"mean_token_accuracy": 0.20222333520650865,
|
|
"num_tokens": 31369189.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.345199728012085,
|
|
"epoch": 1.3150816522574447,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048338671028835063,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.20776601433753966,
|
|
"num_tokens": 31380841.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.262567615509033,
|
|
"epoch": 1.3155619596541785,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048337377874978086,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.21065473109483718,
|
|
"num_tokens": 31393092.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.3129064559936525,
|
|
"epoch": 1.3160422670509127,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048336084237339067,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.20487397760152817,
|
|
"num_tokens": 31404228.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.379480934143066,
|
|
"epoch": 1.3165225744476465,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004833479011594804,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.19169089198112488,
|
|
"num_tokens": 31416233.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.441320896148682,
|
|
"epoch": 1.3170028818443804,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048333495510835057,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.20218756347894667,
|
|
"num_tokens": 31427787.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.230286455154419,
|
|
"epoch": 1.3174831892411143,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048332200422030163,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.21231602877378464,
|
|
"num_tokens": 31438736.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.2132175922393795,
|
|
"epoch": 1.3179634966378482,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004833090484956345,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.20443275719881057,
|
|
"num_tokens": 31449225.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.464901399612427,
|
|
"epoch": 1.318443804034582,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048329608793464966,
|
|
"loss": 5.2236,
|
|
"mean_token_accuracy": 0.20016036927700043,
|
|
"num_tokens": 31461223.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.497300529479981,
|
|
"epoch": 1.3189241114313162,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004832831225376482,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.1977096363902092,
|
|
"num_tokens": 31472397.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.328596735000611,
|
|
"epoch": 1.31940441882805,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004832701523049312,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.21123499572277069,
|
|
"num_tokens": 31484079.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.277539157867432,
|
|
"epoch": 1.319884726224784,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004832571772367997,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.19888059347867965,
|
|
"num_tokens": 31496732.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.340926837921143,
|
|
"epoch": 1.3203650336215178,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048324419733355485,
|
|
"loss": 5.0348,
|
|
"mean_token_accuracy": 0.21129054427146912,
|
|
"num_tokens": 31507601.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.313457679748535,
|
|
"epoch": 1.3208453410182517,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048323121259549805,
|
|
"loss": 5.0989,
|
|
"mean_token_accuracy": 0.2036265328526497,
|
|
"num_tokens": 31519551.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.291695976257325,
|
|
"epoch": 1.3213256484149856,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048321822302293095,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.2036072328686714,
|
|
"num_tokens": 31531531.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.355756521224976,
|
|
"epoch": 1.3218059558117194,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004832052286161549,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.19782871007919312,
|
|
"num_tokens": 31542386.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.381161689758301,
|
|
"epoch": 1.3222862632084533,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048319222937547176,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.20573843717575074,
|
|
"num_tokens": 31554142.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.345448398590088,
|
|
"epoch": 1.3227665706051872,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048317922530118323,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.2000872388482094,
|
|
"num_tokens": 31566687.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.437745857238769,
|
|
"epoch": 1.3232468780019213,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004831662163935912,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.19741231799125672,
|
|
"num_tokens": 31577893.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.4776527881622314,
|
|
"epoch": 1.3237271853986552,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048315320265299784,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.19352358281612397,
|
|
"num_tokens": 31590483.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.383467960357666,
|
|
"epoch": 1.324207492795389,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048314018407970516,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.1970451921224594,
|
|
"num_tokens": 31601373.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.373129796981812,
|
|
"epoch": 1.324687800192123,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048312716067401535,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.20007715970277787,
|
|
"num_tokens": 31613981.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.438017082214356,
|
|
"epoch": 1.3251681075888568,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000483114132436231,
|
|
"loss": 5.1813,
|
|
"mean_token_accuracy": 0.19657982438802718,
|
|
"num_tokens": 31626727.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.293847560882568,
|
|
"epoch": 1.3256484149855907,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004831010993666545,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.20588299483060837,
|
|
"num_tokens": 31638519.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.242141962051392,
|
|
"epoch": 1.3261287223823248,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004830880614655884,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.20326041728258132,
|
|
"num_tokens": 31649184.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.3668779850006105,
|
|
"epoch": 1.3266090297790587,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048307501873333527,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.20251715779304505,
|
|
"num_tokens": 31660266.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.344674730300904,
|
|
"epoch": 1.3270893371757926,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004830619711701982,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.20661376118659974,
|
|
"num_tokens": 31670841.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.336579036712647,
|
|
"epoch": 1.3275696445725265,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004830489187764799,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.20004140734672546,
|
|
"num_tokens": 31680786.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.266639518737793,
|
|
"epoch": 1.3280499519692603,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004830358615524835,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.20161621123552323,
|
|
"num_tokens": 31692639.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.447183465957641,
|
|
"epoch": 1.3285302593659942,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048302279949851215,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.202225524187088,
|
|
"num_tokens": 31703520.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.365837860107422,
|
|
"epoch": 1.329010566762728,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.00048300973261486906,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.21298494637012483,
|
|
"num_tokens": 31715659.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.319388818740845,
|
|
"epoch": 1.329490874159462,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004829966609018577,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.20073260366916656,
|
|
"num_tokens": 31727896.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.346878719329834,
|
|
"epoch": 1.3299711815561959,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048298358435978146,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.2075430154800415,
|
|
"num_tokens": 31738618.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.369692325592041,
|
|
"epoch": 1.3304514889529298,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048297050298894394,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.19844014346599578,
|
|
"num_tokens": 31750306.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.394980812072754,
|
|
"epoch": 1.3309317963496639,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004829574167896489,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.1947400078177452,
|
|
"num_tokens": 31762015.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.372121429443359,
|
|
"epoch": 1.3314121037463977,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048294432576220027,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.20307625085115433,
|
|
"num_tokens": 31774120.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.3283994674682615,
|
|
"epoch": 1.3318924111431316,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004829312299069017,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.20872168093919755,
|
|
"num_tokens": 31785485.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.3376270771026615,
|
|
"epoch": 1.3323727185398655,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048291812922405755,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.2028579980134964,
|
|
"num_tokens": 31795621.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.3207354068756105,
|
|
"epoch": 1.3328530259365994,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004829050237139717,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.2053963989019394,
|
|
"num_tokens": 31806761.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.397493696212768,
|
|
"epoch": 1.3333333333333333,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004828919133769486,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.19852778762578965,
|
|
"num_tokens": 31817996.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.354830026626587,
|
|
"epoch": 1.3338136407300674,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004828787982132926,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.20072319805622102,
|
|
"num_tokens": 31829888.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.412594795227051,
|
|
"epoch": 1.3342939481268012,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048286567822330815,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.19912067502737046,
|
|
"num_tokens": 31842582.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.2976819515228275,
|
|
"epoch": 1.3347742555235351,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004828525534072999,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.20685300529003142,
|
|
"num_tokens": 31854765.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.335469484329224,
|
|
"epoch": 1.335254562920269,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048283942376557254,
|
|
"loss": 5.1013,
|
|
"mean_token_accuracy": 0.19701035171747208,
|
|
"num_tokens": 31865505.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.305283784866333,
|
|
"epoch": 1.3357348703170029,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00048282628929843097,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.203286711871624,
|
|
"num_tokens": 31876599.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.395487546920776,
|
|
"epoch": 1.3362151777137368,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048281315000617996,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.20879360884428025,
|
|
"num_tokens": 31887292.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.37358832359314,
|
|
"epoch": 1.3366954851104706,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004828000058891248,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.19988144040107728,
|
|
"num_tokens": 31899018.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.313088846206665,
|
|
"epoch": 1.3371757925072045,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004827868569475706,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.21080673336982728,
|
|
"num_tokens": 31910402.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.389514398574829,
|
|
"epoch": 1.3376560999039384,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048277370318182243,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.19579225778579712,
|
|
"num_tokens": 31921792.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.417444229125977,
|
|
"epoch": 1.3381364073006723,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048276054459218596,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.1937682092189789,
|
|
"num_tokens": 31932786.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.4295440196990965,
|
|
"epoch": 1.3386167146974064,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048274738117896643,
|
|
"loss": 5.1559,
|
|
"mean_token_accuracy": 0.20484541058540345,
|
|
"num_tokens": 31944286.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.345168685913086,
|
|
"epoch": 1.3390970220941403,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048273421294246966,
|
|
"loss": 5.1997,
|
|
"mean_token_accuracy": 0.193796306848526,
|
|
"num_tokens": 31956304.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.33720703125,
|
|
"epoch": 1.3395773294908742,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048272103988300134,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.20464810281991958,
|
|
"num_tokens": 31968978.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.423181009292603,
|
|
"epoch": 1.340057636887608,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004827078620008672,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.19563246965408326,
|
|
"num_tokens": 31980133.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.358336162567139,
|
|
"epoch": 1.340537944284342,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048269467929637337,
|
|
"loss": 5.0919,
|
|
"mean_token_accuracy": 0.2143523558974266,
|
|
"num_tokens": 31990331.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.352067565917968,
|
|
"epoch": 1.341018251681076,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048268149176982576,
|
|
"loss": 5.1673,
|
|
"mean_token_accuracy": 0.19833752512931824,
|
|
"num_tokens": 32001956.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.423780536651611,
|
|
"epoch": 1.34149855907781,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048266829942153055,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.2008989304304123,
|
|
"num_tokens": 32013577.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.494021606445313,
|
|
"epoch": 1.3419788664745438,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048265510225179413,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.19946567267179488,
|
|
"num_tokens": 32025751.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.289702987670898,
|
|
"epoch": 1.3424591738712777,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004826419002609229,
|
|
"loss": 5.209,
|
|
"mean_token_accuracy": 0.19658195972442627,
|
|
"num_tokens": 32036592.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.452092885971069,
|
|
"epoch": 1.3429394812680115,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048262869344922326,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.19998496472835542,
|
|
"num_tokens": 32048122.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.3869071960449215,
|
|
"epoch": 1.3434197886647454,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048261548181700186,
|
|
"loss": 5.128,
|
|
"mean_token_accuracy": 0.1997670888900757,
|
|
"num_tokens": 32058673.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.205999803543091,
|
|
"epoch": 1.3439000960614793,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004826022653645655,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.20361050367355346,
|
|
"num_tokens": 32070219.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.371896839141845,
|
|
"epoch": 1.3443804034582132,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000482589044092221,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.20105068683624266,
|
|
"num_tokens": 32081883.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.485547590255737,
|
|
"epoch": 1.344860710854947,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048257581800027527,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.192411345243454,
|
|
"num_tokens": 32094107.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.305849838256836,
|
|
"epoch": 1.345341018251681,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004825625870890354,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.20125783681869508,
|
|
"num_tokens": 32105242.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.350560855865479,
|
|
"epoch": 1.345821325648415,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004825493513588086,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.20420416742563247,
|
|
"num_tokens": 32117326.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.399466800689697,
|
|
"epoch": 1.346301633045149,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048253611080990226,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.19904770851135253,
|
|
"num_tokens": 32129002.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.364911317825317,
|
|
"epoch": 1.3467819404418828,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004825228654426236,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.19794921427965165,
|
|
"num_tokens": 32140380.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.293016719818115,
|
|
"epoch": 1.3472622478386167,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004825096152572803,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.21047295928001403,
|
|
"num_tokens": 32151806.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.410971164703369,
|
|
"epoch": 1.3477425552353506,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048249636025417974,
|
|
"loss": 5.2594,
|
|
"mean_token_accuracy": 0.1995522990822792,
|
|
"num_tokens": 32163426.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.407171678543091,
|
|
"epoch": 1.3482228626320845,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048248310043362997,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.20812000781297685,
|
|
"num_tokens": 32174349.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.470804166793823,
|
|
"epoch": 1.3487031700288186,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004824698357959386,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.1961935505270958,
|
|
"num_tokens": 32185382.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.334240245819092,
|
|
"epoch": 1.3491834774255524,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048245656634141385,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.20533836930990218,
|
|
"num_tokens": 32195687.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.322557544708252,
|
|
"epoch": 1.3496637848222863,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048244329207036354,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.20497046858072282,
|
|
"num_tokens": 32205973.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.306572914123535,
|
|
"epoch": 1.3501440922190202,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048243001298309604,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.20198435634374617,
|
|
"num_tokens": 32217469.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.307004642486572,
|
|
"epoch": 1.350624399615754,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048241672907991954,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.20244280099868775,
|
|
"num_tokens": 32228257.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.398568725585937,
|
|
"epoch": 1.351104707012488,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004824034403611424,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.20399668365716933,
|
|
"num_tokens": 32239420.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.390717077255249,
|
|
"epoch": 1.3515850144092219,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004823901468270733,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.20080154836177827,
|
|
"num_tokens": 32250962.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.357997894287109,
|
|
"epoch": 1.3520653218059557,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004823768484780209,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.20370426625013352,
|
|
"num_tokens": 32262310.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.325276517868042,
|
|
"epoch": 1.3525456292026896,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048236354531429375,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.20499752312898636,
|
|
"num_tokens": 32273373.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.443119096755981,
|
|
"epoch": 1.3530259365994235,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004823502373362009,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.19950730949640275,
|
|
"num_tokens": 32285020.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.334796047210693,
|
|
"epoch": 1.3535062439961576,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004823369245440512,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.20197726041078568,
|
|
"num_tokens": 32296224.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.310855484008789,
|
|
"epoch": 1.3539865513928915,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048232360693815387,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.19952235370874405,
|
|
"num_tokens": 32306913.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.436777210235595,
|
|
"epoch": 1.3544668587896254,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048231028451881786,
|
|
"loss": 5.1116,
|
|
"mean_token_accuracy": 0.19769713282585144,
|
|
"num_tokens": 32317981.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.2687201499938965,
|
|
"epoch": 1.3549471661863592,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004822969572863527,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.2055681824684143,
|
|
"num_tokens": 32329656.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.34511170387268,
|
|
"epoch": 1.3554274735830931,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048228362524106776,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.2099799707531929,
|
|
"num_tokens": 32339460.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.354806518554687,
|
|
"epoch": 1.3559077809798272,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048227028838327253,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.20189944058656692,
|
|
"num_tokens": 32351237.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.374829864501953,
|
|
"epoch": 1.356388088376561,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048225694671327665,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.19875938445329666,
|
|
"num_tokens": 32362368.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.256130504608154,
|
|
"epoch": 1.356868395773295,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004822436002313899,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.2072485625743866,
|
|
"num_tokens": 32373738.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.330228185653686,
|
|
"epoch": 1.3573487031700289,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.0004822302489379222,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.19890401661396026,
|
|
"num_tokens": 32384274.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.260733032226563,
|
|
"epoch": 1.3578290105667628,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048221689283318335,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.21080899089574814,
|
|
"num_tokens": 32395692.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.32096004486084,
|
|
"epoch": 1.3583093179634966,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004822035319174837,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.2033696338534355,
|
|
"num_tokens": 32407367.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.381122589111328,
|
|
"epoch": 1.3587896253602305,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004821901661911332,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.1996179401874542,
|
|
"num_tokens": 32418753.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.393187618255615,
|
|
"epoch": 1.3592699327569644,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004821767956544423,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.19853486269712448,
|
|
"num_tokens": 32429499.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.339402198791504,
|
|
"epoch": 1.3597502401536983,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004821634203077214,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.20290581583976747,
|
|
"num_tokens": 32441246.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.3618285179138185,
|
|
"epoch": 1.3602305475504322,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000482150040151281,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.1952323079109192,
|
|
"num_tokens": 32452953.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.360871028900147,
|
|
"epoch": 1.3607108549471663,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004821366551854318,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.20591263025999068,
|
|
"num_tokens": 32464030.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.273940992355347,
|
|
"epoch": 1.3611911623439001,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004821232654104845,
|
|
"loss": 4.9491,
|
|
"mean_token_accuracy": 0.20800916850566864,
|
|
"num_tokens": 32475091.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.294663953781128,
|
|
"epoch": 1.361671469740634,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048210987082675005,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.2024068295955658,
|
|
"num_tokens": 32486047.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.322147417068481,
|
|
"epoch": 1.362151777137368,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048209647143453946,
|
|
"loss": 5.0767,
|
|
"mean_token_accuracy": 0.20839687287807465,
|
|
"num_tokens": 32497141.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.350426769256591,
|
|
"epoch": 1.3626320845341018,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048208306723416356,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.2026175782084465,
|
|
"num_tokens": 32509282.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.379834890365601,
|
|
"epoch": 1.3631123919308357,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004820696582259339,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.19458702504634856,
|
|
"num_tokens": 32521383.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.344017219543457,
|
|
"epoch": 1.3635926993275698,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004820562444101616,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.20336774587631226,
|
|
"num_tokens": 32533168.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.3267711162567135,
|
|
"epoch": 1.3640730067243036,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004820428257871581,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.20398667454719543,
|
|
"num_tokens": 32545333.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.2565593242645265,
|
|
"epoch": 1.3645533141210375,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004820294023572351,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.20526546835899354,
|
|
"num_tokens": 32556665.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.410391569137573,
|
|
"epoch": 1.3650336215177714,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000482015974120704,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.1963676005601883,
|
|
"num_tokens": 32568318.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.410532855987549,
|
|
"epoch": 1.3655139289145053,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048200254107787677,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.20035615116357802,
|
|
"num_tokens": 32580010.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.391696929931641,
|
|
"epoch": 1.3659942363112392,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048198910322906516,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.19170089066028595,
|
|
"num_tokens": 32592075.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.442966079711914,
|
|
"epoch": 1.366474543707973,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048197566057458125,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.1971960112452507,
|
|
"num_tokens": 32604548.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.449193382263184,
|
|
"epoch": 1.366954851104707,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000481962213114737,
|
|
"loss": 5.1749,
|
|
"mean_token_accuracy": 0.20039330422878265,
|
|
"num_tokens": 32616036.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.297258520126343,
|
|
"epoch": 1.3674351585014408,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004819487608498448,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.20119822174310684,
|
|
"num_tokens": 32628157.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.40396032333374,
|
|
"epoch": 1.3679154658981747,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048193530378021687,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.20014068186283113,
|
|
"num_tokens": 32640571.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.385211372375489,
|
|
"epoch": 1.3683957732949088,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048192184190616567,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.19541212618350984,
|
|
"num_tokens": 32652005.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.390274620056152,
|
|
"epoch": 1.3688760806916427,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004819083752280037,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.2013690412044525,
|
|
"num_tokens": 32663655.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.339043855667114,
|
|
"epoch": 1.3693563880883766,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048189490374604373,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.19711499363183976,
|
|
"num_tokens": 32675419.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.3816934585571286,
|
|
"epoch": 1.3698366954851104,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004818814274605983,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.2019793376326561,
|
|
"num_tokens": 32686680.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.312632656097412,
|
|
"epoch": 1.3703170028818443,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004818679463719805,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.20914498567581177,
|
|
"num_tokens": 32697321.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.257076025009155,
|
|
"epoch": 1.3707973102785782,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004818544604805033,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.19818746596574782,
|
|
"num_tokens": 32708885.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.3838128566741945,
|
|
"epoch": 1.3712776176753123,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004818409697864798,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.21211158037185668,
|
|
"num_tokens": 32720517.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.328588819503784,
|
|
"epoch": 1.3717579250720462,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048182747429022303,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.20824936628341675,
|
|
"num_tokens": 32731072.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.4308757305145265,
|
|
"epoch": 1.37223823246878,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004818139739920465,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.20173214375972748,
|
|
"num_tokens": 32742117.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.377332544326782,
|
|
"epoch": 1.372718539865514,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004818004688922637,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.19923641681671142,
|
|
"num_tokens": 32753754.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.307647228240967,
|
|
"epoch": 1.3731988472622478,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000481786958991188,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.20362937599420547,
|
|
"num_tokens": 32766511.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.445419597625732,
|
|
"epoch": 1.3736791546589817,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048177344428913316,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.19595624655485153,
|
|
"num_tokens": 32777715.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.409852647781372,
|
|
"epoch": 1.3741594620557156,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048175992478641293,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.20377529114484788,
|
|
"num_tokens": 32789132.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.41539192199707,
|
|
"epoch": 1.3746397694524495,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004817464004833412,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.19652828425168992,
|
|
"num_tokens": 32800439.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.342273902893067,
|
|
"epoch": 1.3751200768491834,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048173287138023204,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.20175189524888992,
|
|
"num_tokens": 32813605.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.461595773696899,
|
|
"epoch": 1.3756003842459175,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004817193374773993,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.19934556931257247,
|
|
"num_tokens": 32824225.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.446244430541992,
|
|
"epoch": 1.3760806916426513,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048170579877515753,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.19133036881685256,
|
|
"num_tokens": 32836917.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.378753280639648,
|
|
"epoch": 1.3765609990393852,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004816922552738209,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.20304266214370728,
|
|
"num_tokens": 32847972.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.23174409866333,
|
|
"epoch": 1.377041306436119,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048167870697370373,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.21342985033988954,
|
|
"num_tokens": 32858922.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.349138450622559,
|
|
"epoch": 1.377521613832853,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004816651538751207,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.2048991158604622,
|
|
"num_tokens": 32869788.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.512812232971191,
|
|
"epoch": 1.3780019212295869,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048165159597838664,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.1845387727022171,
|
|
"num_tokens": 32881678.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.347246789932251,
|
|
"epoch": 1.378482228626321,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000481638033283816,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.19798745065927506,
|
|
"num_tokens": 32894183.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.355525398254395,
|
|
"epoch": 1.3789625360230549,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.00048162446579172387,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.2039244920015335,
|
|
"num_tokens": 32906001.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.393274116516113,
|
|
"epoch": 1.3794428434197887,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004816108935024252,
|
|
"loss": 5.1481,
|
|
"mean_token_accuracy": 0.20046081840991975,
|
|
"num_tokens": 32917236.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.376561832427979,
|
|
"epoch": 1.3799231508165226,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00048159731641623507,
|
|
"loss": 5.1927,
|
|
"mean_token_accuracy": 0.19527550637722016,
|
|
"num_tokens": 32929710.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.317066049575805,
|
|
"epoch": 1.3804034582132565,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004815837345334687,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.20568896532058717,
|
|
"num_tokens": 32941565.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.464717817306519,
|
|
"epoch": 1.3808837656099904,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004815701478544415,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.19789301306009294,
|
|
"num_tokens": 32952730.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.341267156600952,
|
|
"epoch": 1.3813640730067243,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048155655637946876,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.2035706728696823,
|
|
"num_tokens": 32963589.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.325777530670166,
|
|
"epoch": 1.3818443804034581,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004815429601088662,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.20386212319135666,
|
|
"num_tokens": 32975008.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.392207431793213,
|
|
"epoch": 1.382324687800192,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004815293590429494,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.19357021749019623,
|
|
"num_tokens": 32986497.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.265930414199829,
|
|
"epoch": 1.382804995196926,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048151575318203417,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.21305642575025557,
|
|
"num_tokens": 32998298.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.472185039520264,
|
|
"epoch": 1.38328530259366,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048150214252643637,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.1983982503414154,
|
|
"num_tokens": 33010943.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.418670034408569,
|
|
"epoch": 1.3837656099903939,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000481488527076472,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.203060545027256,
|
|
"num_tokens": 33022139.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.394924640655518,
|
|
"epoch": 1.3842459173871278,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004814749068324571,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.199508935213089,
|
|
"num_tokens": 33034653.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.291094732284546,
|
|
"epoch": 1.3847262247838616,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048146128179470804,
|
|
"loss": 4.909,
|
|
"mean_token_accuracy": 0.22053591459989547,
|
|
"num_tokens": 33044339.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.327397346496582,
|
|
"epoch": 1.3852065321805955,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004814476519635411,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.20481428354978562,
|
|
"num_tokens": 33055418.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.389827108383178,
|
|
"epoch": 1.3856868395773294,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048143401733927274,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.2018747568130493,
|
|
"num_tokens": 33067239.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.347398567199707,
|
|
"epoch": 1.3861671469740635,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048142037792221943,
|
|
"loss": 5.0214,
|
|
"mean_token_accuracy": 0.20946198850870132,
|
|
"num_tokens": 33079101.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.340820026397705,
|
|
"epoch": 1.3866474543707974,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004814067337126978,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.2114260599017143,
|
|
"num_tokens": 33090265.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.3661597728729244,
|
|
"epoch": 1.3871277617675313,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004813930847110248,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.20788215100765228,
|
|
"num_tokens": 33101724.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.323405742645264,
|
|
"epoch": 1.3876080691642652,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004813794309175173,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.20483731478452682,
|
|
"num_tokens": 33113111.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.367096614837647,
|
|
"epoch": 1.388088376560999,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048136577233249205,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.19249417185783385,
|
|
"num_tokens": 33123925.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.4021071434021,
|
|
"epoch": 1.388568683957733,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004813521089562666,
|
|
"loss": 5.1927,
|
|
"mean_token_accuracy": 0.19724307507276534,
|
|
"num_tokens": 33137400.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.337522220611572,
|
|
"epoch": 1.3890489913544668,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004813384407891577,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.2096565470099449,
|
|
"num_tokens": 33149326.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.433620548248291,
|
|
"epoch": 1.3895292987512007,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000481324767831483,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.19163325428962708,
|
|
"num_tokens": 33159904.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.362641000747681,
|
|
"epoch": 1.3900096061479346,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004813110900835598,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.20630415230989457,
|
|
"num_tokens": 33171701.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.324493885040283,
|
|
"epoch": 1.3904899135446687,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004812974075457058,
|
|
"loss": 5.0166,
|
|
"mean_token_accuracy": 0.20670453161001207,
|
|
"num_tokens": 33181598.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.322141838073731,
|
|
"epoch": 1.3909702209414025,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048128372021823845,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.20464530885219573,
|
|
"num_tokens": 33192674.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.277734231948853,
|
|
"epoch": 1.3914505283381364,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048127002810147574,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.2058214485645294,
|
|
"num_tokens": 33203356.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.368610572814942,
|
|
"epoch": 1.3919308357348703,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004812563311957355,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.19961784034967422,
|
|
"num_tokens": 33215471.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.35471773147583,
|
|
"epoch": 1.3924111431316042,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004812426295013356,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.20225704908370973,
|
|
"num_tokens": 33227656.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.390611457824707,
|
|
"epoch": 1.392891450528338,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048122892301859433,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.19485735148191452,
|
|
"num_tokens": 33239752.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.426832771301269,
|
|
"epoch": 1.3933717579250722,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048121521174782983,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.19992454200983048,
|
|
"num_tokens": 33251352.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.41427788734436,
|
|
"epoch": 1.393852065321806,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048120149568936044,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.19807483851909638,
|
|
"num_tokens": 33262276.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.42465558052063,
|
|
"epoch": 1.39433237271854,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004811877748435046,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.1990452840924263,
|
|
"num_tokens": 33273615.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.365324401855469,
|
|
"epoch": 1.3948126801152738,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004811740492105809,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.20412847101688386,
|
|
"num_tokens": 33283990.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.3201024532318115,
|
|
"epoch": 1.3952929875120077,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000481160318790908,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.20799044966697694,
|
|
"num_tokens": 33295472.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.37564697265625,
|
|
"epoch": 1.3957732949087416,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048114658358480467,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.19837984591722488,
|
|
"num_tokens": 33306742.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.425158929824829,
|
|
"epoch": 1.3962536023054755,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048113284359258977,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.2004937246441841,
|
|
"num_tokens": 33317737.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.357522821426391,
|
|
"epoch": 1.3967339097022093,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048111909881458234,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.199340383708477,
|
|
"num_tokens": 33329673.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.2719066619873045,
|
|
"epoch": 1.3972142170989432,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048110534925110146,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.2129276528954506,
|
|
"num_tokens": 33342047.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.30756573677063,
|
|
"epoch": 1.397694524495677,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004810915949024664,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.2104130581021309,
|
|
"num_tokens": 33353287.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.404580926895141,
|
|
"epoch": 1.3981748318924112,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004810778357689965,
|
|
"loss": 5.1612,
|
|
"mean_token_accuracy": 0.205659419298172,
|
|
"num_tokens": 33365465.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.337996006011963,
|
|
"epoch": 1.398655139289145,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048106407185101116,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.20334515273571013,
|
|
"num_tokens": 33376680.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.314851570129394,
|
|
"epoch": 1.399135446685879,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048105030314883,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.20197126716375352,
|
|
"num_tokens": 33387995.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.352795600891113,
|
|
"epoch": 1.3996157540826129,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004810365296627725,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.2053541734814644,
|
|
"num_tokens": 33400455.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.386382675170898,
|
|
"epoch": 1.4000960614793467,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004810227513931587,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.196034674346447,
|
|
"num_tokens": 33413264.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.329139661788941,
|
|
"epoch": 1.4005763688760806,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004810089683403084,
|
|
"loss": 5.0277,
|
|
"mean_token_accuracy": 0.2152287781238556,
|
|
"num_tokens": 33423516.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.349635410308838,
|
|
"epoch": 1.4010566762728147,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004809951805045415,
|
|
"loss": 5.1684,
|
|
"mean_token_accuracy": 0.195552359521389,
|
|
"num_tokens": 33434952.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.334937238693238,
|
|
"epoch": 1.4015369836695486,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.00048098138788617815,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.20016899406909944,
|
|
"num_tokens": 33447025.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.394659996032715,
|
|
"epoch": 1.4020172910662825,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004809675904855387,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.19921733438968658,
|
|
"num_tokens": 33459990.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.374874877929687,
|
|
"epoch": 1.4024975984630164,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048095378830294343,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.20449578166007995,
|
|
"num_tokens": 33471334.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.3814808368682865,
|
|
"epoch": 1.4029779058597502,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.00048093998133871276,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.19867161214351653,
|
|
"num_tokens": 33483744.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.3795287132263185,
|
|
"epoch": 1.4034582132564841,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004809261695931671,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.20150798112154006,
|
|
"num_tokens": 33496532.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.310295438766479,
|
|
"epoch": 1.403938520653218,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004809123530666273,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.20708370357751846,
|
|
"num_tokens": 33507545.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.392156171798706,
|
|
"epoch": 1.4044188280499519,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004808985317594142,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.20832026302814483,
|
|
"num_tokens": 33519232.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.302455902099609,
|
|
"epoch": 1.4048991354466858,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048088470567184854,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.20083181858062743,
|
|
"num_tokens": 33531088.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.388827753067017,
|
|
"epoch": 1.4053794428434199,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048087087480425133,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.19813691228628158,
|
|
"num_tokens": 33543991.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.44530029296875,
|
|
"epoch": 1.4058597502401537,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004808570391569437,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.193914058804512,
|
|
"num_tokens": 33555303.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.413883781433105,
|
|
"epoch": 1.4063400576368876,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048084319873024694,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.19609931856393814,
|
|
"num_tokens": 33565587.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.303432130813599,
|
|
"epoch": 1.4068203650336215,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004808293535244823,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.20052550733089447,
|
|
"num_tokens": 33576874.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.32558126449585,
|
|
"epoch": 1.4073006724303554,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004808155035399712,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.21359051167964935,
|
|
"num_tokens": 33587703.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.328500461578369,
|
|
"epoch": 1.4077809798270893,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004808016487770354,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.21201693266630173,
|
|
"num_tokens": 33598487.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.340681171417236,
|
|
"epoch": 1.4082612872238234,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048078778923599637,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.19801372587680816,
|
|
"num_tokens": 33610838.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.314969110488891,
|
|
"epoch": 1.4087415946205573,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048077392491717593,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.19724190682172776,
|
|
"num_tokens": 33622726.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.307091760635376,
|
|
"epoch": 1.4092219020172911,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00048076005582089597,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.20281048417091369,
|
|
"num_tokens": 33635922.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.510155820846558,
|
|
"epoch": 1.409702209414025,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048074618194747845,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.195133675634861,
|
|
"num_tokens": 33648486.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.388053703308105,
|
|
"epoch": 1.410182516810759,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004807323032972456,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.2040333166718483,
|
|
"num_tokens": 33659812.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.327765560150146,
|
|
"epoch": 1.4106628242074928,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004807184198705196,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.20504141896963118,
|
|
"num_tokens": 33671878.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.313097286224365,
|
|
"epoch": 1.4111431316042267,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004807045316676226,
|
|
"loss": 5.0328,
|
|
"mean_token_accuracy": 0.20687769651412963,
|
|
"num_tokens": 33683759.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.4317583560943605,
|
|
"epoch": 1.4116234390009605,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004806906386888773,
|
|
"loss": 5.2264,
|
|
"mean_token_accuracy": 0.19981102645397186,
|
|
"num_tokens": 33694085.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.380100536346435,
|
|
"epoch": 1.4121037463976944,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048067674093460607,
|
|
"loss": 5.0738,
|
|
"mean_token_accuracy": 0.2038256496191025,
|
|
"num_tokens": 33705810.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.343209505081177,
|
|
"epoch": 1.4125840537944283,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00048066283840513175,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.2013676717877388,
|
|
"num_tokens": 33716798.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.288878536224365,
|
|
"epoch": 1.4130643611911624,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004806489311007769,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.20784870982170106,
|
|
"num_tokens": 33728515.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.355249977111816,
|
|
"epoch": 1.4135446685878963,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048063501902186463,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.2009478062391281,
|
|
"num_tokens": 33740684.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.396293449401855,
|
|
"epoch": 1.4140249759846302,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048062110216871775,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.20453639030456544,
|
|
"num_tokens": 33753017.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.371892309188842,
|
|
"epoch": 1.414505283381364,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048060718054165945,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.20265826880931853,
|
|
"num_tokens": 33764393.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.3923139572143555,
|
|
"epoch": 1.414985590778098,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.000480593254141013,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.1949861004948616,
|
|
"num_tokens": 33774941.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.2395812511444095,
|
|
"epoch": 1.4154658981748318,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048057932296710165,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.21399983912706375,
|
|
"num_tokens": 33786534.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.447940063476563,
|
|
"epoch": 1.415946205571566,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004805653870202489,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.1959482952952385,
|
|
"num_tokens": 33798339.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.437653923034668,
|
|
"epoch": 1.4164265129682998,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048055144630077825,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.19499351531267167,
|
|
"num_tokens": 33810368.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.412339353561402,
|
|
"epoch": 1.4169068203650337,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048053750080901336,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.19864614754915239,
|
|
"num_tokens": 33821111.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.311427640914917,
|
|
"epoch": 1.4173871277617676,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048052355054527794,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.20125917941331864,
|
|
"num_tokens": 33833629.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.439679050445557,
|
|
"epoch": 1.4178674351585014,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048050959550989606,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.1994342476129532,
|
|
"num_tokens": 33846531.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.331101179122925,
|
|
"epoch": 1.4183477425552353,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004804956357031916,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.20436210483312606,
|
|
"num_tokens": 33857251.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.301807928085327,
|
|
"epoch": 1.4188280499519692,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048048167112548873,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.20051545649766922,
|
|
"num_tokens": 33869314.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.4217267513275145,
|
|
"epoch": 1.419308357348703,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048046770177711157,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.19803316593170167,
|
|
"num_tokens": 33880203.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.348030710220337,
|
|
"epoch": 1.419788664745437,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004804537276583844,
|
|
"loss": 5.0398,
|
|
"mean_token_accuracy": 0.20976334065198898,
|
|
"num_tokens": 33891379.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.313481187820434,
|
|
"epoch": 1.420268972142171,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004804397487696319,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.20837375074625014,
|
|
"num_tokens": 33902788.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.297556591033936,
|
|
"epoch": 1.420749279538905,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004804257651111783,
|
|
"loss": 5.1223,
|
|
"mean_token_accuracy": 0.20727469325065612,
|
|
"num_tokens": 33913609.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.332670116424561,
|
|
"epoch": 1.4212295869356388,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048041177668334853,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.20650487691164016,
|
|
"num_tokens": 33924379.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.370602130889893,
|
|
"epoch": 1.4217098943323727,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004803977834864672,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.20262874513864518,
|
|
"num_tokens": 33936209.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.360746097564697,
|
|
"epoch": 1.4221902017291066,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048038378552085927,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.19836071282625198,
|
|
"num_tokens": 33947679.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.333289337158203,
|
|
"epoch": 1.4226705091258405,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048036978278684974,
|
|
"loss": 5.1164,
|
|
"mean_token_accuracy": 0.2003627210855484,
|
|
"num_tokens": 33959474.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.464787578582763,
|
|
"epoch": 1.4231508165225746,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004803557752847636,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.19643506407737732,
|
|
"num_tokens": 33970831.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.46349983215332,
|
|
"epoch": 1.4236311239193085,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048034176301492616,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.20180942714214326,
|
|
"num_tokens": 33981765.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.3222472190856935,
|
|
"epoch": 1.4241114313160423,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004803277459776628,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.20288561582565307,
|
|
"num_tokens": 33992435.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.281150770187378,
|
|
"epoch": 1.4245917387127762,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048031372417329875,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.2101571574807167,
|
|
"num_tokens": 34004570.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.345453882217408,
|
|
"epoch": 1.42507204610951,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004802996976021598,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.21014197915792465,
|
|
"num_tokens": 34015494.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.398283576965332,
|
|
"epoch": 1.425552353506244,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.00048028566626457145,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.19598751217126847,
|
|
"num_tokens": 34026684.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.333102703094482,
|
|
"epoch": 1.4260326609029779,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048027163016085947,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.19686230570077895,
|
|
"num_tokens": 34038948.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.398800373077393,
|
|
"epoch": 1.4265129682997117,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048025758929134976,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.19249648302793504,
|
|
"num_tokens": 34052216.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.416674995422364,
|
|
"epoch": 1.4269932756964456,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004802435436563684,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.2065944641828537,
|
|
"num_tokens": 34062602.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.369269990921021,
|
|
"epoch": 1.4274735830931795,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048022949325624134,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.2058451607823372,
|
|
"num_tokens": 34075049.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.326748943328857,
|
|
"epoch": 1.4279538904899136,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048021543809129483,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.19589586108922957,
|
|
"num_tokens": 34086719.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.339957809448242,
|
|
"epoch": 1.4284341978866475,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004802013781618552,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.20643536895513534,
|
|
"num_tokens": 34098439.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.44960355758667,
|
|
"epoch": 1.4289145052833814,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048018731346824895,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.20344579219818115,
|
|
"num_tokens": 34110711.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.297912883758545,
|
|
"epoch": 1.4293948126801153,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004801732440108026,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.20314314365386962,
|
|
"num_tokens": 34122191.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.232313728332519,
|
|
"epoch": 1.4298751200768491,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004801591697898427,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.2093231722712517,
|
|
"num_tokens": 34132838.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.3605400085449215,
|
|
"epoch": 1.430355427473583,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004801450908056961,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.19935905784368516,
|
|
"num_tokens": 34143394.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.503569555282593,
|
|
"epoch": 1.4308357348703171,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004801310070586896,
|
|
"loss": 5.2025,
|
|
"mean_token_accuracy": 0.1995997205376625,
|
|
"num_tokens": 34155934.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.2338861465454105,
|
|
"epoch": 1.431316042267051,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004801169185491503,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.21466548889875411,
|
|
"num_tokens": 34167949.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.380476093292236,
|
|
"epoch": 1.4317963496637849,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048010282527740516,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.19138071984052657,
|
|
"num_tokens": 34179733.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.383456420898438,
|
|
"epoch": 1.4322766570605188,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048008872724378146,
|
|
"loss": 5.0348,
|
|
"mean_token_accuracy": 0.20647053569555282,
|
|
"num_tokens": 34190513.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.3623968124389645,
|
|
"epoch": 1.4327569644572526,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004800746244486065,
|
|
"loss": 5.0916,
|
|
"mean_token_accuracy": 0.20701171904802323,
|
|
"num_tokens": 34201562.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.226936912536621,
|
|
"epoch": 1.4332372718539865,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004800605168922077,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.20459163188934326,
|
|
"num_tokens": 34212637.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.313013315200806,
|
|
"epoch": 1.4337175792507204,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048004640457491267,
|
|
"loss": 5.1116,
|
|
"mean_token_accuracy": 0.2024821013212204,
|
|
"num_tokens": 34225394.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.443166971206665,
|
|
"epoch": 1.4341978866474543,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000480032287497049,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.20271422117948532,
|
|
"num_tokens": 34236977.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.380861043930054,
|
|
"epoch": 1.4346781940441882,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048001816565894427,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.20310237556695937,
|
|
"num_tokens": 34247486.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.335670328140258,
|
|
"epoch": 1.435158501440922,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004800040390609267,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.20934849232435226,
|
|
"num_tokens": 34259404.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.34085259437561,
|
|
"epoch": 1.4356388088376562,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00047998990770332396,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.21263392716646196,
|
|
"num_tokens": 34270388.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.41104793548584,
|
|
"epoch": 1.43611911623439,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004799757715864643,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.20275283306837083,
|
|
"num_tokens": 34281321.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.396457481384277,
|
|
"epoch": 1.436599423631124,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004799616307106759,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.19397408664226531,
|
|
"num_tokens": 34293177.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.401641511917115,
|
|
"epoch": 1.4370797310278578,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000479947485076287,
|
|
"loss": 5.1947,
|
|
"mean_token_accuracy": 0.1979562133550644,
|
|
"num_tokens": 34305175.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.402565383911133,
|
|
"epoch": 1.4375600384245917,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047993333468362607,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.19418162554502488,
|
|
"num_tokens": 34317969.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.472748422622681,
|
|
"epoch": 1.4380403458213258,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047991917953302173,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.19356372058391572,
|
|
"num_tokens": 34329913.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.397890281677246,
|
|
"epoch": 1.4385206532180597,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047990501962480236,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.2056276634335518,
|
|
"num_tokens": 34341656.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.350678586959839,
|
|
"epoch": 1.4390009606147935,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000479890854959297,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.20148863196372985,
|
|
"num_tokens": 34351767.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.304176378250122,
|
|
"epoch": 1.4394812680115274,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004798766855368344,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.20078179389238357,
|
|
"num_tokens": 34363437.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.422183179855347,
|
|
"epoch": 1.4399615754082613,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00047986251135774343,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.20399434566497804,
|
|
"num_tokens": 34374991.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.331448698043824,
|
|
"epoch": 1.4404418828049952,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004798483324223533,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.20740891993045807,
|
|
"num_tokens": 34386218.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.3644918441772464,
|
|
"epoch": 1.440922190201729,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004798341487309932,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.20490514785051345,
|
|
"num_tokens": 34396287.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.440922190201729,
|
|
"eval_entropy": 5.139314280900067,
|
|
"eval_loss": 5.20700216293335,
|
|
"eval_mean_token_accuracy": 0.2077228651486014,
|
|
"eval_num_tokens": 34396287.0,
|
|
"eval_runtime": 26.7051,
|
|
"eval_samples_per_second": 1228.792,
|
|
"eval_steps_per_second": 153.604,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.362489843368531,
|
|
"epoch": 1.441402497598463,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047981996028399233,
|
|
"loss": 5.1615,
|
|
"mean_token_accuracy": 0.19601617753505707,
|
|
"num_tokens": 34407251.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.482280206680298,
|
|
"epoch": 1.4418828049951968,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004798057670816802,
|
|
"loss": 5.2788,
|
|
"mean_token_accuracy": 0.19547625482082367,
|
|
"num_tokens": 34419185.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.4053483486175535,
|
|
"epoch": 1.4423631123919307,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004797915691243863,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.2025802403688431,
|
|
"num_tokens": 34431159.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.33237042427063,
|
|
"epoch": 1.4428434197886648,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004797773664124403,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.2046749010682106,
|
|
"num_tokens": 34442614.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.29823670387268,
|
|
"epoch": 1.4433237271853987,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047976315894617195,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.20695242583751677,
|
|
"num_tokens": 34453984.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.260715579986572,
|
|
"epoch": 1.4438040345821326,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000479748946725911,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.20609388798475264,
|
|
"num_tokens": 34466296.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.467827081680298,
|
|
"epoch": 1.4442843419788665,
|
|
"grad_norm": 9.25,
|
|
"learning_rate": 0.0004797347297519875,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.19312234967947006,
|
|
"num_tokens": 34478088.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.411195564270019,
|
|
"epoch": 1.4447646493756003,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00047972050802473154,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.1932742103934288,
|
|
"num_tokens": 34491664.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.29674506187439,
|
|
"epoch": 1.4452449567723342,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004797062815444733,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.20714800357818602,
|
|
"num_tokens": 34502977.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.348169374465942,
|
|
"epoch": 1.4457252641690683,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000479692050311543,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.20602938383817673,
|
|
"num_tokens": 34515067.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.397802305221558,
|
|
"epoch": 1.4462055715658022,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004796778143262711,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.20173681676387786,
|
|
"num_tokens": 34525012.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.238165760040284,
|
|
"epoch": 1.446685878962536,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004796635735889882,
|
|
"loss": 5.0038,
|
|
"mean_token_accuracy": 0.21523723304271697,
|
|
"num_tokens": 34535789.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.395851373672485,
|
|
"epoch": 1.44716618635927,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00047964932810002476,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.20574514120817183,
|
|
"num_tokens": 34546276.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.392111921310425,
|
|
"epoch": 1.4476464937560038,
|
|
"grad_norm": 6.03125,
|
|
"learning_rate": 0.0004796350778597117,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.2003644049167633,
|
|
"num_tokens": 34558361.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.278994226455689,
|
|
"epoch": 1.4481268011527377,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004796208228683796,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.20860782116651536,
|
|
"num_tokens": 34569482.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.366148376464844,
|
|
"epoch": 1.4486071085494716,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047960656312635977,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.20821984559297563,
|
|
"num_tokens": 34580128.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.363970470428467,
|
|
"epoch": 1.4490874159462055,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004795922986339831,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.19975730478763581,
|
|
"num_tokens": 34591105.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.409661388397216,
|
|
"epoch": 1.4495677233429394,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047957802939158057,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.20529214441776275,
|
|
"num_tokens": 34602618.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.408677577972412,
|
|
"epoch": 1.4500480307396733,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004795637553994838,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.1944472685456276,
|
|
"num_tokens": 34614179.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.455041408538818,
|
|
"epoch": 1.4505283381364074,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047954947665802404,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.1960166573524475,
|
|
"num_tokens": 34625456.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.363129472732544,
|
|
"epoch": 1.4510086455331412,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004795351931675329,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.21076080352067947,
|
|
"num_tokens": 34636268.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.295994663238526,
|
|
"epoch": 1.4514889529298751,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004795209049283419,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.20598308145999908,
|
|
"num_tokens": 34647665.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.402158594131469,
|
|
"epoch": 1.451969260326609,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004795066119407827,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.19898003339767456,
|
|
"num_tokens": 34659965.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.3761979103088375,
|
|
"epoch": 1.4524495677233429,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004794923142051873,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.19963922649621962,
|
|
"num_tokens": 34671724.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.2990394115448,
|
|
"epoch": 1.452929875120077,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047947801172188755,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.21478975862264632,
|
|
"num_tokens": 34682445.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.306337547302246,
|
|
"epoch": 1.4534101825168109,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004794637044912155,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.20963166803121566,
|
|
"num_tokens": 34693621.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.318267726898194,
|
|
"epoch": 1.4538904899135447,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004794493925135034,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.22138864547014236,
|
|
"num_tokens": 34703978.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.332370090484619,
|
|
"epoch": 1.4543707973102786,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047943507578908357,
|
|
"loss": 5.1749,
|
|
"mean_token_accuracy": 0.20934356153011321,
|
|
"num_tokens": 34715468.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.399098587036133,
|
|
"epoch": 1.4548511047070125,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004794207543182883,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.19859857857227325,
|
|
"num_tokens": 34726383.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.373412227630615,
|
|
"epoch": 1.4553314121037464,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00047940642810145005,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.20526949763298036,
|
|
"num_tokens": 34737123.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.285305786132812,
|
|
"epoch": 1.4558117195004803,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047939209713890156,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.20610247552394867,
|
|
"num_tokens": 34749197.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.294309473037719,
|
|
"epoch": 1.4562920268972142,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047937776143097547,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.20179203301668167,
|
|
"num_tokens": 34759785.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.267324352264405,
|
|
"epoch": 1.456772334293948,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004793634209780047,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.21108057200908661,
|
|
"num_tokens": 34770938.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.343147897720337,
|
|
"epoch": 1.457252641690682,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004793490757803221,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.2102021023631096,
|
|
"num_tokens": 34782126.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.294695091247559,
|
|
"epoch": 1.457732949087416,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00047933472583826063,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.203795026242733,
|
|
"num_tokens": 34793802.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.326722955703735,
|
|
"epoch": 1.45821325648415,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004793203711521537,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.21175481379032135,
|
|
"num_tokens": 34805696.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.47420301437378,
|
|
"epoch": 1.4586935638808838,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047930601172233446,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.1912037417292595,
|
|
"num_tokens": 34818679.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.439678478240967,
|
|
"epoch": 1.4591738712776177,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047929164754913624,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.20581602901220322,
|
|
"num_tokens": 34830528.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.3318838596344,
|
|
"epoch": 1.4596541786743515,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004792772786328926,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.21582498252391816,
|
|
"num_tokens": 34841621.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.254693937301636,
|
|
"epoch": 1.4601344860710854,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00047926290497393714,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.20690861493349075,
|
|
"num_tokens": 34854448.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.366745138168335,
|
|
"epoch": 1.4606147934678195,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004792485265726036,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.2018947944045067,
|
|
"num_tokens": 34866492.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.360023784637451,
|
|
"epoch": 1.4610951008645534,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004792341434292257,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.20488402545452117,
|
|
"num_tokens": 34876869.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.275164699554443,
|
|
"epoch": 1.4615754082612873,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004792197555441374,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.213503797352314,
|
|
"num_tokens": 34888449.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.276980543136597,
|
|
"epoch": 1.4620557156580212,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004792053629176729,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.21541889160871505,
|
|
"num_tokens": 34898124.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.369081640243531,
|
|
"epoch": 1.462536023054755,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004791909655501662,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.20995785295963287,
|
|
"num_tokens": 34909128.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.280434942245483,
|
|
"epoch": 1.463016330451489,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004791765634419516,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.20798680186271667,
|
|
"num_tokens": 34920541.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.2264453887939455,
|
|
"epoch": 1.4634966378482228,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047916215659336343,
|
|
"loss": 5.0196,
|
|
"mean_token_accuracy": 0.2085188403725624,
|
|
"num_tokens": 34931605.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.267530393600464,
|
|
"epoch": 1.4639769452449567,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004791477450047363,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.20670379400253297,
|
|
"num_tokens": 34943057.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.421672821044922,
|
|
"epoch": 1.4644572526416906,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047913332867640464,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.1982573613524437,
|
|
"num_tokens": 34954386.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.355084562301636,
|
|
"epoch": 1.4649375600384245,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004791189076087033,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.20823611468076705,
|
|
"num_tokens": 34965874.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.386474323272705,
|
|
"epoch": 1.4654178674351586,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00047910448180196703,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.2011822819709778,
|
|
"num_tokens": 34977408.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.373803377151489,
|
|
"epoch": 1.4658981748318924,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004790900512565307,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.21174615919589995,
|
|
"num_tokens": 34987788.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.397695875167846,
|
|
"epoch": 1.4663784822286263,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004790756159727294,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.20355158746242524,
|
|
"num_tokens": 35001051.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.3749583721160885,
|
|
"epoch": 1.4668587896253602,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047906117595089835,
|
|
"loss": 5.0955,
|
|
"mean_token_accuracy": 0.20833303183317184,
|
|
"num_tokens": 35012621.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.317798519134522,
|
|
"epoch": 1.467339097022094,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004790467311913727,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.20068335086107253,
|
|
"num_tokens": 35023789.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.290668678283692,
|
|
"epoch": 1.4678194044188282,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004790322816944879,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.21028541922569274,
|
|
"num_tokens": 35035839.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.385327625274658,
|
|
"epoch": 1.468299711815562,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004790178274605793,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.1985410585999489,
|
|
"num_tokens": 35047823.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.379476404190063,
|
|
"epoch": 1.468780019212296,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047900336848998254,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.1933244451880455,
|
|
"num_tokens": 35058597.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.259315013885498,
|
|
"epoch": 1.4692603266090298,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004789889047830334,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.20867012143135072,
|
|
"num_tokens": 35069822.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.371738433837891,
|
|
"epoch": 1.4697406340057637,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047897443634006766,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.2017176166176796,
|
|
"num_tokens": 35081423.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.391587591171264,
|
|
"epoch": 1.4702209414024976,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004789599631614211,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.20000742226839066,
|
|
"num_tokens": 35092565.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.313291358947754,
|
|
"epoch": 1.4707012487992315,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004789454852474298,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.20980483144521714,
|
|
"num_tokens": 35103811.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.379567289352417,
|
|
"epoch": 1.4711815561959654,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004789310025984299,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.19440847337245942,
|
|
"num_tokens": 35115516.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.37249641418457,
|
|
"epoch": 1.4716618635926992,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047891651521475776,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.2068789303302765,
|
|
"num_tokens": 35127285.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.336257219314575,
|
|
"epoch": 1.4721421709894331,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00047890202309674963,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.20637605637311934,
|
|
"num_tokens": 35137884.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.402774286270142,
|
|
"epoch": 1.4726224783861672,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047888752624474195,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.19153431057929993,
|
|
"num_tokens": 35149935.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.373490619659424,
|
|
"epoch": 1.473102785782901,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004788730246590714,
|
|
"loss": 5.1829,
|
|
"mean_token_accuracy": 0.20351831912994384,
|
|
"num_tokens": 35162610.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.375169324874878,
|
|
"epoch": 1.473583093179635,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047885851834007456,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.20470778942108153,
|
|
"num_tokens": 35174799.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.338375186920166,
|
|
"epoch": 1.4740634005763689,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00047884400728808824,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.2073012188076973,
|
|
"num_tokens": 35186004.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.3553167343139645,
|
|
"epoch": 1.4745437079731027,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004788294915034494,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.20631051063537598,
|
|
"num_tokens": 35197310.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.268295574188232,
|
|
"epoch": 1.4750240153698366,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000478814970986495,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.20851985067129136,
|
|
"num_tokens": 35208703.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.294045257568359,
|
|
"epoch": 1.4755043227665707,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047880044573756213,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.20532659590244293,
|
|
"num_tokens": 35219927.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.301111364364624,
|
|
"epoch": 1.4759846301633046,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047878591575698816,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.2103084906935692,
|
|
"num_tokens": 35231077.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.364637231826782,
|
|
"epoch": 1.4764649375600385,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004787713810451103,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.19775525778532027,
|
|
"num_tokens": 35241984.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.304605007171631,
|
|
"epoch": 1.4769452449567724,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00047875684160226606,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.21033854335546492,
|
|
"num_tokens": 35252717.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.378051519393921,
|
|
"epoch": 1.4774255523535063,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000478742297428793,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.2076215147972107,
|
|
"num_tokens": 35263916.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.309385156631469,
|
|
"epoch": 1.4779058597502401,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00047872774852502877,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.20376682430505752,
|
|
"num_tokens": 35274772.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.265638542175293,
|
|
"epoch": 1.478386167146974,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004787131948913112,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.21143898367881775,
|
|
"num_tokens": 35287150.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.31267728805542,
|
|
"epoch": 1.478866474543708,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047869863652797806,
|
|
"loss": 5.0238,
|
|
"mean_token_accuracy": 0.21366485059261323,
|
|
"num_tokens": 35298538.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.2526123046875,
|
|
"epoch": 1.4793467819404418,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004786840734353675,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.20793842673301696,
|
|
"num_tokens": 35309395.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.283991193771362,
|
|
"epoch": 1.4798270893371757,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00047866950561381756,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.20542063564062119,
|
|
"num_tokens": 35320741.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.456654405593872,
|
|
"epoch": 1.4803073967339098,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004786549330636665,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.20301507264375687,
|
|
"num_tokens": 35331895.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.281301736831665,
|
|
"epoch": 1.4807877041306436,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047864035578525256,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.21732020676136016,
|
|
"num_tokens": 35343775.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.294640445709229,
|
|
"epoch": 1.4812680115273775,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004786257737789143,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.20381265729665757,
|
|
"num_tokens": 35355043.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.434656286239624,
|
|
"epoch": 1.4817483189241114,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004786111870449902,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.19944988042116166,
|
|
"num_tokens": 35365387.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.346152973175049,
|
|
"epoch": 1.4822286263208453,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047859659558381894,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.21193132549524307,
|
|
"num_tokens": 35376400.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.334381771087647,
|
|
"epoch": 1.4827089337175792,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00047858199939573935,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.2051519438624382,
|
|
"num_tokens": 35387315.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.367770671844482,
|
|
"epoch": 1.4831892411143133,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00047856739848109014,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.20667224377393723,
|
|
"num_tokens": 35398666.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.2829447269439695,
|
|
"epoch": 1.4836695485110472,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047855279284021046,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.2045323446393013,
|
|
"num_tokens": 35409192.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.333701801300049,
|
|
"epoch": 1.484149855907781,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00047853818247343933,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.19949372857809067,
|
|
"num_tokens": 35419812.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.443350887298584,
|
|
"epoch": 1.484630163304515,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00047852356738111606,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.2152531012892723,
|
|
"num_tokens": 35430875.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.331792116165161,
|
|
"epoch": 1.4851104707012488,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004785089475635799,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.21281103938817977,
|
|
"num_tokens": 35441065.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.249078893661499,
|
|
"epoch": 1.4855907780979827,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047849432302117024,
|
|
"loss": 5.0994,
|
|
"mean_token_accuracy": 0.20494410395622253,
|
|
"num_tokens": 35452164.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.386143970489502,
|
|
"epoch": 1.4860710854947166,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047847969375422656,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.19749953895807265,
|
|
"num_tokens": 35463158.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.300423717498779,
|
|
"epoch": 1.4865513928914504,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004784650597630887,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.21542577147483827,
|
|
"num_tokens": 35474153.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.356301021575928,
|
|
"epoch": 1.4870317002881843,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047845042104809635,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.20366594046354294,
|
|
"num_tokens": 35485680.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.348676013946533,
|
|
"epoch": 1.4875120076849184,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004784357776095892,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.20614221841096877,
|
|
"num_tokens": 35497271.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.350858068466186,
|
|
"epoch": 1.4879923150816523,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004784211294479075,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.2128287062048912,
|
|
"num_tokens": 35509166.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.327647638320923,
|
|
"epoch": 1.4884726224783862,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004784064765633912,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.20619376450777055,
|
|
"num_tokens": 35521289.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.3066057682037355,
|
|
"epoch": 1.48895292987512,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00047839181895638057,
|
|
"loss": 5.1066,
|
|
"mean_token_accuracy": 0.2093535155057907,
|
|
"num_tokens": 35532179.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.449065017700195,
|
|
"epoch": 1.489433237271854,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047837715662721575,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.1961241289973259,
|
|
"num_tokens": 35544703.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.4617303848266605,
|
|
"epoch": 1.4899135446685878,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004783624895762372,
|
|
"loss": 5.2663,
|
|
"mean_token_accuracy": 0.18792153298854827,
|
|
"num_tokens": 35557853.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.333270931243897,
|
|
"epoch": 1.490393852065322,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047834781780378563,
|
|
"loss": 4.9916,
|
|
"mean_token_accuracy": 0.2154626190662384,
|
|
"num_tokens": 35570340.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.383132743835449,
|
|
"epoch": 1.4908741594620558,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004783331413102015,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.2036404252052307,
|
|
"num_tokens": 35582387.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.413096761703491,
|
|
"epoch": 1.4913544668587897,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047831846009582557,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.19859371483325958,
|
|
"num_tokens": 35595105.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.403652715682983,
|
|
"epoch": 1.4918347742555236,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004783037741609988,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.20334693491458894,
|
|
"num_tokens": 35607160.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.38970193862915,
|
|
"epoch": 1.4923150816522575,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004782890835060621,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.20598850697278975,
|
|
"num_tokens": 35619097.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.222178030014038,
|
|
"epoch": 1.4927953890489913,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004782743881313564,
|
|
"loss": 4.9873,
|
|
"mean_token_accuracy": 0.21189357042312623,
|
|
"num_tokens": 35629868.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.342463254928589,
|
|
"epoch": 1.4932756964457252,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047825968803722315,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.20484336614608764,
|
|
"num_tokens": 35640622.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.350011968612671,
|
|
"epoch": 1.493756003842459,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004782449832240035,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.2011991798877716,
|
|
"num_tokens": 35652383.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.249768400192261,
|
|
"epoch": 1.494236311239193,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004782302736920387,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.20720833986997605,
|
|
"num_tokens": 35663838.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.390760087966919,
|
|
"epoch": 1.4947166186359269,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004782155594416705,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.21101955473423004,
|
|
"num_tokens": 35674564.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.414097547531128,
|
|
"epoch": 1.495196926032661,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047820084047324045,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.20302077531814575,
|
|
"num_tokens": 35685518.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.382009410858155,
|
|
"epoch": 1.4956772334293948,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047818611678709027,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.2015741065144539,
|
|
"num_tokens": 35696597.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.255480480194092,
|
|
"epoch": 1.4961575408261287,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004781713883835618,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.2140153244137764,
|
|
"num_tokens": 35707229.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.315263032913208,
|
|
"epoch": 1.4966378482228626,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047815665526299695,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.20489682406187057,
|
|
"num_tokens": 35719440.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.373601341247559,
|
|
"epoch": 1.4971181556195965,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004781419174257378,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.1972115457057953,
|
|
"num_tokens": 35731611.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.324247741699219,
|
|
"epoch": 1.4975984630163304,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004781271748721266,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.20018618553876877,
|
|
"num_tokens": 35743047.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.389548683166504,
|
|
"epoch": 1.4980787704130645,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004781124276025055,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.2180386081337929,
|
|
"num_tokens": 35753499.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.388045024871826,
|
|
"epoch": 1.4985590778097984,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000478097675617217,
|
|
"loss": 5.2709,
|
|
"mean_token_accuracy": 0.20039983540773393,
|
|
"num_tokens": 35764682.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.443998622894287,
|
|
"epoch": 1.4990393852065322,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047808291891660357,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.213158543407917,
|
|
"num_tokens": 35775160.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.334929609298706,
|
|
"epoch": 1.4995196926032661,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047806815750100774,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.20487746298313142,
|
|
"num_tokens": 35786089.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.318635129928589,
|
|
"epoch": 1.5,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004780533913707723,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.20553116500377655,
|
|
"num_tokens": 35796851.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.411638307571411,
|
|
"epoch": 1.5004803073967339,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047803862052624006,
|
|
"loss": 5.1506,
|
|
"mean_token_accuracy": 0.1979074150323868,
|
|
"num_tokens": 35808553.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.474843502044678,
|
|
"epoch": 1.5009606147934678,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047802384496775397,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.20093749463558197,
|
|
"num_tokens": 35820108.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.3027019023895265,
|
|
"epoch": 1.5014409221902016,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004780090646956571,
|
|
"loss": 5.023,
|
|
"mean_token_accuracy": 0.21168416291475295,
|
|
"num_tokens": 35831672.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.402424144744873,
|
|
"epoch": 1.5019212295869355,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047799427971029245,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.19929228872060775,
|
|
"num_tokens": 35843164.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.404357671737671,
|
|
"epoch": 1.5024015369836694,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004779794900120034,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.1987962543964386,
|
|
"num_tokens": 35854677.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.379780626296997,
|
|
"epoch": 1.5028818443804035,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004779646956011334,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.21240822970867157,
|
|
"num_tokens": 35865956.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.320407676696777,
|
|
"epoch": 1.5033621517771374,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047794989647802574,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.20387045443058013,
|
|
"num_tokens": 35877451.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.332996463775634,
|
|
"epoch": 1.5038424591738713,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047793509264302424,
|
|
"loss": 5.1051,
|
|
"mean_token_accuracy": 0.20763415545225145,
|
|
"num_tokens": 35888436.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.345939970016479,
|
|
"epoch": 1.5043227665706052,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047792028409647237,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.20067185908555984,
|
|
"num_tokens": 35901010.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.371581554412842,
|
|
"epoch": 1.5048030739673393,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047790547083871414,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.2032038614153862,
|
|
"num_tokens": 35912697.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.320012331008911,
|
|
"epoch": 1.5052833813640731,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047789065287009335,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.21251355707645417,
|
|
"num_tokens": 35924614.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.360231971740722,
|
|
"epoch": 1.505763688760807,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004778758301909542,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.20674294382333755,
|
|
"num_tokens": 35935492.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.311260843276978,
|
|
"epoch": 1.506243996157541,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004778610028016405,
|
|
"loss": 5.1386,
|
|
"mean_token_accuracy": 0.20527916103601457,
|
|
"num_tokens": 35947901.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.2937037467956545,
|
|
"epoch": 1.5067243035542748,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004778461707024967,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.21260720789432525,
|
|
"num_tokens": 35959690.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.320909214019776,
|
|
"epoch": 1.5072046109510087,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004778313338938672,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.20709127336740493,
|
|
"num_tokens": 35971209.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.254273748397827,
|
|
"epoch": 1.5076849183477425,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047781649237609643,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.21677872389554978,
|
|
"num_tokens": 35981795.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.271739053726196,
|
|
"epoch": 1.5081652257444764,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004778016461495289,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20693135112524033,
|
|
"num_tokens": 35993358.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.3429286003112795,
|
|
"epoch": 1.5086455331412103,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004777867952145094,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.2076400861144066,
|
|
"num_tokens": 36005353.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.387282943725586,
|
|
"epoch": 1.5091258405379442,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004777719395713826,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.2029297798871994,
|
|
"num_tokens": 36017510.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.340511512756348,
|
|
"epoch": 1.509606147934678,
|
|
"grad_norm": 19.25,
|
|
"learning_rate": 0.00047775707922049354,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.2103155732154846,
|
|
"num_tokens": 36028687.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.300938987731934,
|
|
"epoch": 1.510086455331412,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004777422141621871,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.2078416809439659,
|
|
"num_tokens": 36039851.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.335451698303222,
|
|
"epoch": 1.510566762728146,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004777273443968085,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.20069583803415297,
|
|
"num_tokens": 36050776.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.278595685958862,
|
|
"epoch": 1.51104707012488,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004777124699247029,
|
|
"loss": 5.0097,
|
|
"mean_token_accuracy": 0.21100762039422988,
|
|
"num_tokens": 36062151.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.319891691207886,
|
|
"epoch": 1.5115273775216138,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004776975907462157,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.20665891021490096,
|
|
"num_tokens": 36074601.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.313487243652344,
|
|
"epoch": 1.5120076849183477,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004776827068616924,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.21432878375053405,
|
|
"num_tokens": 36085436.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.414702224731445,
|
|
"epoch": 1.5124879923150818,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004776678182714785,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.19157951176166535,
|
|
"num_tokens": 36097589.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.305859661102295,
|
|
"epoch": 1.5129682997118157,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047765292497591955,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.20123548805713654,
|
|
"num_tokens": 36109993.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.345835208892822,
|
|
"epoch": 1.5134486071085496,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00047763802697536146,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.20509061217308044,
|
|
"num_tokens": 36122439.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.3465784072875975,
|
|
"epoch": 1.5139289145052834,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00047762312427015015,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.20333320945501326,
|
|
"num_tokens": 36133867.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.388094425201416,
|
|
"epoch": 1.5144092219020173,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047760821686063153,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.1987990066409111,
|
|
"num_tokens": 36144202.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.389839744567871,
|
|
"epoch": 1.5148895292987512,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00047759330474715173,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.2065802440047264,
|
|
"num_tokens": 36154863.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.378533744812012,
|
|
"epoch": 1.515369836695485,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047757838793005704,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.19844311624765396,
|
|
"num_tokens": 36166360.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.263777351379394,
|
|
"epoch": 1.515850144092219,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047756346640969366,
|
|
"loss": 5.0146,
|
|
"mean_token_accuracy": 0.21695467978715896,
|
|
"num_tokens": 36177477.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.357493114471436,
|
|
"epoch": 1.5163304514889528,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047754854018640803,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.20143990218639374,
|
|
"num_tokens": 36188510.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.329339981079102,
|
|
"epoch": 1.5168107588856867,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047753360926054684,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.20852287262678146,
|
|
"num_tokens": 36199084.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.276885080337524,
|
|
"epoch": 1.5172910662824206,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047751867363245653,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.20756489187479019,
|
|
"num_tokens": 36211265.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.488957834243775,
|
|
"epoch": 1.5177713736791547,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004775037333024841,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.19342653155326844,
|
|
"num_tokens": 36223070.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.344230318069458,
|
|
"epoch": 1.5182516810758886,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004774887882709762,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.20849687457084656,
|
|
"num_tokens": 36235021.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.293058300018311,
|
|
"epoch": 1.5187319884726225,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047747383853827995,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.20169561505317687,
|
|
"num_tokens": 36245647.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.390277004241943,
|
|
"epoch": 1.5192122958693564,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004774588841047424,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.195385080575943,
|
|
"num_tokens": 36257470.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.338135051727295,
|
|
"epoch": 1.5196926032660905,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004774439249707108,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.2035131961107254,
|
|
"num_tokens": 36268839.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.3570277214050295,
|
|
"epoch": 1.5201729106628243,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004774289611365323,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.19804610311985016,
|
|
"num_tokens": 36280624.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.333049249649048,
|
|
"epoch": 1.5206532180595582,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047741399260255434,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.21040584295988082,
|
|
"num_tokens": 36292696.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.375274562835694,
|
|
"epoch": 1.521133525456292,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047739901936912467,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.21060912907123566,
|
|
"num_tokens": 36303612.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.284633207321167,
|
|
"epoch": 1.521613832853026,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004773840414365907,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.20732045620679856,
|
|
"num_tokens": 36314511.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.4543005466461185,
|
|
"epoch": 1.5220941402497599,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00047736905880530026,
|
|
"loss": 5.2123,
|
|
"mean_token_accuracy": 0.19676833152770995,
|
|
"num_tokens": 36327276.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.361385297775269,
|
|
"epoch": 1.5225744476464937,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004773540714756012,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.2046758145093918,
|
|
"num_tokens": 36339373.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.395473432540894,
|
|
"epoch": 1.5230547550432276,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047733907944784144,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.19377227872610092,
|
|
"num_tokens": 36351863.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.341022157669068,
|
|
"epoch": 1.5235350624399615,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004773240827223691,
|
|
"loss": 5.0843,
|
|
"mean_token_accuracy": 0.21160105019807815,
|
|
"num_tokens": 36363961.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.354917430877686,
|
|
"epoch": 1.5240153698366954,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004773090812995323,
|
|
"loss": 5.0579,
|
|
"mean_token_accuracy": 0.21362899094820023,
|
|
"num_tokens": 36374738.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.313607406616211,
|
|
"epoch": 1.5244956772334293,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00047729407517967945,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.20757139921188356,
|
|
"num_tokens": 36386472.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.266999387741089,
|
|
"epoch": 1.5249759846301632,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047727906436315884,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.2164509430527687,
|
|
"num_tokens": 36397042.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.30981411933899,
|
|
"epoch": 1.5254562920268973,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047726404885031895,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.21092346757650376,
|
|
"num_tokens": 36408720.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.330272531509399,
|
|
"epoch": 1.5259365994236311,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047724902864150845,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.2049933284521103,
|
|
"num_tokens": 36420885.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.388141250610351,
|
|
"epoch": 1.526416906820365,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047723400373707607,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.19642669409513475,
|
|
"num_tokens": 36433678.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.43842248916626,
|
|
"epoch": 1.526897214217099,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004772189741373707,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.20668911337852477,
|
|
"num_tokens": 36445143.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.269496154785156,
|
|
"epoch": 1.527377521613833,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047720393984274117,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.2047015130519867,
|
|
"num_tokens": 36456214.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.3842573165893555,
|
|
"epoch": 1.5278578290105669,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047718890085353654,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.20562046021223068,
|
|
"num_tokens": 36466767.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.408462810516357,
|
|
"epoch": 1.5283381364073008,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000477173857170106,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.1999749571084976,
|
|
"num_tokens": 36478150.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.342231273651123,
|
|
"epoch": 1.5288184438040346,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047715880879279894,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.20302062928676606,
|
|
"num_tokens": 36488280.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.370736408233642,
|
|
"epoch": 1.5292987512007685,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004771437557219646,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.2005226880311966,
|
|
"num_tokens": 36498505.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.270921945571899,
|
|
"epoch": 1.5297790585975024,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004771286979579524,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.20107046514749527,
|
|
"num_tokens": 36509271.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.361762380599975,
|
|
"epoch": 1.5302593659942363,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.0004771136355011121,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.20150717049837114,
|
|
"num_tokens": 36520022.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.374870824813843,
|
|
"epoch": 1.5307396733909702,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047709856835179333,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.20640832036733628,
|
|
"num_tokens": 36532769.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.335799694061279,
|
|
"epoch": 1.531219980787704,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047708349651034586,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.2115209296345711,
|
|
"num_tokens": 36544454.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.3313955783844,
|
|
"epoch": 1.531700288184438,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047706841997711974,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.19776013046503066,
|
|
"num_tokens": 36555916.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.353946542739868,
|
|
"epoch": 1.5321805955811718,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047705333875246495,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.20787457674741744,
|
|
"num_tokens": 36567829.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.376368045806885,
|
|
"epoch": 1.532660902977906,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047703825283673153,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.20357674062252046,
|
|
"num_tokens": 36578216.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.35842866897583,
|
|
"epoch": 1.5331412103746398,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004770231622302699,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.20474180430173874,
|
|
"num_tokens": 36589945.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.366703796386719,
|
|
"epoch": 1.5336215177713737,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047700806693343016,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.20407650172710418,
|
|
"num_tokens": 36600724.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.22491044998169,
|
|
"epoch": 1.5341018251681076,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047699296694656316,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.21476714313030243,
|
|
"num_tokens": 36611154.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.274138498306274,
|
|
"epoch": 1.5345821325648417,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004769778622700192,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.20523118376731872,
|
|
"num_tokens": 36621750.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.339191627502442,
|
|
"epoch": 1.5350624399615755,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047696275290414885,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.20554739087820054,
|
|
"num_tokens": 36633294.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.320988035202026,
|
|
"epoch": 1.5355427473583094,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047694763884930324,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.20745536983013152,
|
|
"num_tokens": 36646377.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.255217885971069,
|
|
"epoch": 1.5360230547550433,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047693252010583314,
|
|
"loss": 4.9782,
|
|
"mean_token_accuracy": 0.2132929101586342,
|
|
"num_tokens": 36656159.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.282615375518799,
|
|
"epoch": 1.5365033621517772,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004769173966740895,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.19837405532598495,
|
|
"num_tokens": 36667522.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.4073854923248295,
|
|
"epoch": 1.536983669548511,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047690226855442346,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.20160532295703887,
|
|
"num_tokens": 36678662.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.359419059753418,
|
|
"epoch": 1.537463976945245,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004768871357471863,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.2042565494775772,
|
|
"num_tokens": 36689876.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.358853054046631,
|
|
"epoch": 1.5379442843419788,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00047687199825272936,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.20953985750675203,
|
|
"num_tokens": 36701140.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.385087299346924,
|
|
"epoch": 1.5384245917387127,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047685685607140403,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.20035172551870345,
|
|
"num_tokens": 36711077.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.390719413757324,
|
|
"epoch": 1.5389048991354466,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047684170920356185,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.2071935534477234,
|
|
"num_tokens": 36722705.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.283608293533325,
|
|
"epoch": 1.5393852065321805,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004768265576495546,
|
|
"loss": 5.036,
|
|
"mean_token_accuracy": 0.20918122977018355,
|
|
"num_tokens": 36733446.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.231543016433716,
|
|
"epoch": 1.5398655139289144,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047681140140973396,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.21150099188089372,
|
|
"num_tokens": 36744529.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.2416994094848635,
|
|
"epoch": 1.5403458213256485,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004767962404844517,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.21080541014671325,
|
|
"num_tokens": 36756248.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.4368218898773195,
|
|
"epoch": 1.5408261287223823,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047678107487406015,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.20474813133478165,
|
|
"num_tokens": 36768097.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.333090877532959,
|
|
"epoch": 1.5413064361191162,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047676590457891116,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.2102869763970375,
|
|
"num_tokens": 36780395.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.314136505126953,
|
|
"epoch": 1.54178674351585,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004767507295993569,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.20238774716854097,
|
|
"num_tokens": 36791897.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.3387768268585205,
|
|
"epoch": 1.5422670509125842,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004767355499357498,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.21374789923429488,
|
|
"num_tokens": 36802716.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.319512224197387,
|
|
"epoch": 1.542747358309318,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004767203655884423,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.20384922474622727,
|
|
"num_tokens": 36814471.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.303890180587769,
|
|
"epoch": 1.543227665706052,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004767051765577869,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.2069879338145256,
|
|
"num_tokens": 36825975.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.34586730003357,
|
|
"epoch": 1.5437079731027858,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047668998284413624,
|
|
"loss": 5.1558,
|
|
"mean_token_accuracy": 0.19741415679454805,
|
|
"num_tokens": 36837990.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.345730924606324,
|
|
"epoch": 1.5441882804995197,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047667478444784306,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.20368138551712037,
|
|
"num_tokens": 36849115.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.363532018661499,
|
|
"epoch": 1.5446685878962536,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004766595813692602,
|
|
"loss": 5.0217,
|
|
"mean_token_accuracy": 0.2065050408244133,
|
|
"num_tokens": 36860626.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.3811217784881595,
|
|
"epoch": 1.5451488952929875,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047664437360874076,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.19795233607292176,
|
|
"num_tokens": 36871926.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.360392761230469,
|
|
"epoch": 1.5456292026897214,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047662916116663766,
|
|
"loss": 5.0933,
|
|
"mean_token_accuracy": 0.2080858439207077,
|
|
"num_tokens": 36883511.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.3733134269714355,
|
|
"epoch": 1.5461095100864553,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047661394404330417,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.20051140934228898,
|
|
"num_tokens": 36895468.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.338058757781982,
|
|
"epoch": 1.5465898174831891,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047659872223909357,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.20882569700479509,
|
|
"num_tokens": 36906957.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.331639146804809,
|
|
"epoch": 1.547070124879923,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004765834957543592,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.21182290017604827,
|
|
"num_tokens": 36916495.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.287138366699219,
|
|
"epoch": 1.547550432276657,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047656826458945475,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.20434169322252274,
|
|
"num_tokens": 36927301.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.320382833480835,
|
|
"epoch": 1.548030739673391,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047655302874473365,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.2063968762755394,
|
|
"num_tokens": 36938116.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.362010478973389,
|
|
"epoch": 1.5485110470701249,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004765377882205498,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.20505149215459822,
|
|
"num_tokens": 36950292.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.284274530410767,
|
|
"epoch": 1.5489913544668588,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004765225430172568,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.2094516560435295,
|
|
"num_tokens": 36962017.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.3773328304290775,
|
|
"epoch": 1.5494716618635929,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004765072931352089,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.19986600428819656,
|
|
"num_tokens": 36972831.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.355137968063355,
|
|
"epoch": 1.5499519692603267,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00047649203857476,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.2125322014093399,
|
|
"num_tokens": 36983324.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.333048963546753,
|
|
"epoch": 1.5504322766570606,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047647677933626423,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.19074799567461015,
|
|
"num_tokens": 36996093.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.347494983673096,
|
|
"epoch": 1.5509125840537945,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047646151542007583,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.21338075995445252,
|
|
"num_tokens": 37006548.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.372770643234253,
|
|
"epoch": 1.5513928914505284,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004764462468265494,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.20590476393699647,
|
|
"num_tokens": 37019181.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.395451974868775,
|
|
"epoch": 1.5518731988472623,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047643097355603913,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.2076515629887581,
|
|
"num_tokens": 37029808.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.266849231719971,
|
|
"epoch": 1.5523535062439962,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004764156956088999,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.20122644454240798,
|
|
"num_tokens": 37040352.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.262643718719483,
|
|
"epoch": 1.55283381364073,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004764004129854863,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.20805729776620865,
|
|
"num_tokens": 37050780.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.396789836883545,
|
|
"epoch": 1.553314121037464,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047638512568615307,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.20637665688991547,
|
|
"num_tokens": 37062608.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.344249105453491,
|
|
"epoch": 1.5537944284341978,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004763698337112553,
|
|
"loss": 5.1506,
|
|
"mean_token_accuracy": 0.20474762320518494,
|
|
"num_tokens": 37074578.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.411241769790649,
|
|
"epoch": 1.5542747358309317,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004763545370611479,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.20527851730585098,
|
|
"num_tokens": 37086487.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.3516082763671875,
|
|
"epoch": 1.5547550432276656,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047633923573618605,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.2163894444704056,
|
|
"num_tokens": 37097249.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.397604131698609,
|
|
"epoch": 1.5552353506243997,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000476323929736725,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.19136781096458436,
|
|
"num_tokens": 37109274.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.3552024364471436,
|
|
"epoch": 1.5557156580211335,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047630861906312004,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.2084275647997856,
|
|
"num_tokens": 37120100.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.326160430908203,
|
|
"epoch": 1.5561959654178674,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004762933037157268,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.205147647857666,
|
|
"num_tokens": 37131889.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.24719009399414,
|
|
"epoch": 1.5566762728146013,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047627798369490076,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.21237130761146544,
|
|
"num_tokens": 37142538.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.40060338973999,
|
|
"epoch": 1.5571565802113354,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047626265900099757,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.20019867420196533,
|
|
"num_tokens": 37153639.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.370278978347779,
|
|
"epoch": 1.5576368876080693,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047624732963437314,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.19972605109214783,
|
|
"num_tokens": 37164029.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.331926012039185,
|
|
"epoch": 1.5581171950048032,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047623199559538324,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.20203202068805695,
|
|
"num_tokens": 37175880.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.4090296745300295,
|
|
"epoch": 1.558597502401537,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000476216656884384,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.20373557209968568,
|
|
"num_tokens": 37187483.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.332933807373047,
|
|
"epoch": 1.559077809798271,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047620131350173135,
|
|
"loss": 5.1298,
|
|
"mean_token_accuracy": 0.20811337530612944,
|
|
"num_tokens": 37198978.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.402440023422241,
|
|
"epoch": 1.5595581171950048,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004761859654477817,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.19405061155557632,
|
|
"num_tokens": 37210054.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.331914472579956,
|
|
"epoch": 1.5600384245917387,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004761706127228914,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.20949917584657668,
|
|
"num_tokens": 37221744.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.310286903381348,
|
|
"epoch": 1.5605187319884726,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004761552553274168,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.20567347407341002,
|
|
"num_tokens": 37234629.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.4485554695129395,
|
|
"epoch": 1.5609990393852065,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004761398932617144,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.19572184085845948,
|
|
"num_tokens": 37246960.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.270813131332398,
|
|
"epoch": 1.5614793467819403,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000476124526526141,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.20923960506916045,
|
|
"num_tokens": 37259326.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.22882490158081,
|
|
"epoch": 1.5619596541786742,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047610915512105327,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.20745850950479508,
|
|
"num_tokens": 37271436.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.393317461013794,
|
|
"epoch": 1.562439961575408,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004760937790468082,
|
|
"loss": 5.1913,
|
|
"mean_token_accuracy": 0.19974317401647568,
|
|
"num_tokens": 37283230.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.340368843078613,
|
|
"epoch": 1.5629202689721422,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004760783983037627,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.20942372381687163,
|
|
"num_tokens": 37295185.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.338806438446045,
|
|
"epoch": 1.563400576368876,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004760630128922738,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.20351314097642897,
|
|
"num_tokens": 37307573.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.421369123458862,
|
|
"epoch": 1.56388088376561,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004760476228126989,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.1947831392288208,
|
|
"num_tokens": 37319084.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.240672779083252,
|
|
"epoch": 1.5643611911623438,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004760322280653951,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.20856100469827651,
|
|
"num_tokens": 37330447.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.276405763626099,
|
|
"epoch": 1.564841498559078,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004760168286507199,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.20684563368558884,
|
|
"num_tokens": 37341184.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.390963506698609,
|
|
"epoch": 1.5653218059558118,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047600142456903085,
|
|
"loss": 5.128,
|
|
"mean_token_accuracy": 0.20565336048603058,
|
|
"num_tokens": 37352712.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.3532508373260494,
|
|
"epoch": 1.5658021133525457,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047598601582068555,
|
|
"loss": 5.1969,
|
|
"mean_token_accuracy": 0.20069622099399567,
|
|
"num_tokens": 37365001.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.427234077453614,
|
|
"epoch": 1.5662824207492796,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004759706024060418,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.19782114028930664,
|
|
"num_tokens": 37377005.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.337739753723144,
|
|
"epoch": 1.5667627281460135,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004759551843254575,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.20714056491851807,
|
|
"num_tokens": 37387329.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.434166049957275,
|
|
"epoch": 1.5672430355427474,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047593976157929034,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.20676285177469253,
|
|
"num_tokens": 37398894.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.3528838634490965,
|
|
"epoch": 1.5677233429394812,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004759243341678987,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.20864019691944122,
|
|
"num_tokens": 37409913.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.372010660171509,
|
|
"epoch": 1.5682036503362151,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004759089020916407,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.20513806194067002,
|
|
"num_tokens": 37421859.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.32415452003479,
|
|
"epoch": 1.568683957732949,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047589346535087444,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.19919564872980117,
|
|
"num_tokens": 37432827.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.322457885742187,
|
|
"epoch": 1.5691642651296829,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004758780239459586,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.21101703643798828,
|
|
"num_tokens": 37444171.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.314602518081665,
|
|
"epoch": 1.5696445725264168,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004758625778772514,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.20149385780096055,
|
|
"num_tokens": 37455194.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.188059282302857,
|
|
"epoch": 1.5701248799231509,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047584712714511166,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.21558443158864976,
|
|
"num_tokens": 37465839.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.306926488876343,
|
|
"epoch": 1.5706051873198847,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047583167174989797,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.21301937103271484,
|
|
"num_tokens": 37476948.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.356966257095337,
|
|
"epoch": 1.5710854947166186,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004758162116919692,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.20731268525123597,
|
|
"num_tokens": 37487382.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.235500812530518,
|
|
"epoch": 1.5715658021133525,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047580074697168434,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.21568770855665206,
|
|
"num_tokens": 37498347.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.3319268226623535,
|
|
"epoch": 1.5720461095100866,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00047578527758940236,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.20042426735162736,
|
|
"num_tokens": 37509620.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.3519128322601315,
|
|
"epoch": 1.5725264169068205,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004757698035454825,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.21530093848705292,
|
|
"num_tokens": 37519768.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.278085470199585,
|
|
"epoch": 1.5730067243035544,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004757543248402839,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.2074356958270073,
|
|
"num_tokens": 37530476.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.321021032333374,
|
|
"epoch": 1.5734870317002883,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047573884147416597,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.20275044739246367,
|
|
"num_tokens": 37541702.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.34502100944519,
|
|
"epoch": 1.5739673390970221,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004757233534474883,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.20099678188562392,
|
|
"num_tokens": 37553323.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.36727933883667,
|
|
"epoch": 1.574447646493756,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004757078607606103,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.19849574714899063,
|
|
"num_tokens": 37564882.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.32201509475708,
|
|
"epoch": 1.57492795389049,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004756923634138918,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.20684879869222642,
|
|
"num_tokens": 37575612.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.321388530731201,
|
|
"epoch": 1.5754082612872238,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047567686140769264,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.20341874659061432,
|
|
"num_tokens": 37587089.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.330423307418823,
|
|
"epoch": 1.5758885686839577,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047566135474237247,
|
|
"loss": 5.075,
|
|
"mean_token_accuracy": 0.20159256160259248,
|
|
"num_tokens": 37598429.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.380420160293579,
|
|
"epoch": 1.5763688760806915,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047564584341829166,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.19856813549995422,
|
|
"num_tokens": 37609769.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.375794553756714,
|
|
"epoch": 1.5768491834774254,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047563032743581,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.1992516875267029,
|
|
"num_tokens": 37622425.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.332228565216065,
|
|
"epoch": 1.5773294908741593,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047561480679528804,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.2088681012392044,
|
|
"num_tokens": 37634819.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.322473764419556,
|
|
"epoch": 1.5778097982708934,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004755992814970859,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.2100428283214569,
|
|
"num_tokens": 37645531.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.264721393585205,
|
|
"epoch": 1.5782901056676273,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000475583751541564,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.20870945751667022,
|
|
"num_tokens": 37657243.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.380912351608276,
|
|
"epoch": 1.5787704130643612,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047556821692908315,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.20734132081270218,
|
|
"num_tokens": 37668218.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.366556310653687,
|
|
"epoch": 1.579250720461095,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004755526776600038,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.2055700644850731,
|
|
"num_tokens": 37680173.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.321234560012817,
|
|
"epoch": 1.5797310278578292,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047553713373468684,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.2027549847960472,
|
|
"num_tokens": 37691281.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.342939329147339,
|
|
"epoch": 1.580211335254563,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047552158515349306,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.19415684491395951,
|
|
"num_tokens": 37702320.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.338265085220337,
|
|
"epoch": 1.580691642651297,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047550603191678356,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.20144219547510148,
|
|
"num_tokens": 37713724.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.314921522140503,
|
|
"epoch": 1.5811719500480308,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004754904740249194,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.2057027831673622,
|
|
"num_tokens": 37724532.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.272519254684449,
|
|
"epoch": 1.5816522574447647,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047547491147826156,
|
|
"loss": 5.0227,
|
|
"mean_token_accuracy": 0.21291377544403076,
|
|
"num_tokens": 37735174.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.337765550613403,
|
|
"epoch": 1.5821325648414986,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004754593442771718,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.2011957898736,
|
|
"num_tokens": 37746981.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.386694622039795,
|
|
"epoch": 1.5826128722382324,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047544377242201115,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.20656838417053222,
|
|
"num_tokens": 37757576.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.38105845451355,
|
|
"epoch": 1.5830931796349663,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00047542819591314136,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.20088604390621184,
|
|
"num_tokens": 37769053.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.369358253479004,
|
|
"epoch": 1.5835734870317002,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004754126147509241,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20610165894031524,
|
|
"num_tokens": 37780517.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.431971549987793,
|
|
"epoch": 1.584053794428434,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047539702893572086,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.19686395972967147,
|
|
"num_tokens": 37791333.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.304670524597168,
|
|
"epoch": 1.584534101825168,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047538143846789376,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.21254798620939255,
|
|
"num_tokens": 37802635.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.221541261672973,
|
|
"epoch": 1.585014409221902,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004753658433478047,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.21444637328386307,
|
|
"num_tokens": 37814788.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.279641151428223,
|
|
"epoch": 1.585494716618636,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047535024357581564,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.20599871277809143,
|
|
"num_tokens": 37826650.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.357758617401123,
|
|
"epoch": 1.5859750240153698,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004753346391522889,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.20274247974157333,
|
|
"num_tokens": 37839362.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.397005414962768,
|
|
"epoch": 1.5864553314121037,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047531903007758667,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.19929560869932175,
|
|
"num_tokens": 37851057.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.334317064285278,
|
|
"epoch": 1.5869356388088378,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004753034163520714,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.2155345618724823,
|
|
"num_tokens": 37863507.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.309065961837769,
|
|
"epoch": 1.5874159462055717,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047528779797610557,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.20441029369831085,
|
|
"num_tokens": 37874439.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.316015720367432,
|
|
"epoch": 1.5878962536023056,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047527217495005184,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.20348903089761733,
|
|
"num_tokens": 37886720.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.324199914932251,
|
|
"epoch": 1.5883765609990395,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047525654727427285,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.20347173810005187,
|
|
"num_tokens": 37897919.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.384753036499023,
|
|
"epoch": 1.5888568683957733,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004752409149491315,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.2054938331246376,
|
|
"num_tokens": 37911061.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.348992538452149,
|
|
"epoch": 1.5893371757925072,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047522527797499075,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.20016083866357803,
|
|
"num_tokens": 37922677.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.22733063697815,
|
|
"epoch": 1.589817483189241,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004752096363522135,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.21978869289159775,
|
|
"num_tokens": 37932802.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.327661514282227,
|
|
"epoch": 1.590297790585975,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047519399008116305,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.2032608300447464,
|
|
"num_tokens": 37944782.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.320115613937378,
|
|
"epoch": 1.5907780979827089,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004751783391622026,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.20704956650733947,
|
|
"num_tokens": 37956577.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.360431814193726,
|
|
"epoch": 1.5912584053794427,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004751626835956955,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.2020716905593872,
|
|
"num_tokens": 37967937.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.263855361938477,
|
|
"epoch": 1.5917387127761766,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004751470233820053,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.2222474843263626,
|
|
"num_tokens": 37978113.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.281993341445923,
|
|
"epoch": 1.5922190201729105,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004751313585214955,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.21091385185718536,
|
|
"num_tokens": 37988852.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.332202529907226,
|
|
"epoch": 1.5926993275696446,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004751156890145298,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.20330223441123962,
|
|
"num_tokens": 38000531.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.31399130821228,
|
|
"epoch": 1.5931796349663785,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000475100014861472,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.21218648105859755,
|
|
"num_tokens": 38011818.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.384591770172119,
|
|
"epoch": 1.5936599423631124,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004750843360626861,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.20596445053815843,
|
|
"num_tokens": 38022455.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.292432641983032,
|
|
"epoch": 1.5941402497598463,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004750686526185359,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.2102372542023659,
|
|
"num_tokens": 38033126.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.179778957366944,
|
|
"epoch": 1.5946205571565804,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047505296452938584,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.20765287727117537,
|
|
"num_tokens": 38044935.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.367109775543213,
|
|
"epoch": 1.5951008645533142,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047503727179559995,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.20397893637418746,
|
|
"num_tokens": 38056080.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.346532487869263,
|
|
"epoch": 1.5955811719500481,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047502157441754256,
|
|
"loss": 5.1255,
|
|
"mean_token_accuracy": 0.20738336443901062,
|
|
"num_tokens": 38066788.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.362172698974609,
|
|
"epoch": 1.596061479346782,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004750058723955781,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.20433002412319184,
|
|
"num_tokens": 38079529.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.328582382202148,
|
|
"epoch": 1.5965417867435159,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004749901657300713,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.20460902750492097,
|
|
"num_tokens": 38091484.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.357063293457031,
|
|
"epoch": 1.5970220941402498,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047497445442138667,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.2087539479136467,
|
|
"num_tokens": 38103102.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.336227035522461,
|
|
"epoch": 1.5975024015369836,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047495873846988896,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.19874853491783143,
|
|
"num_tokens": 38115565.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.317013120651245,
|
|
"epoch": 1.5979827089337175,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004749430178759431,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.20707642138004304,
|
|
"num_tokens": 38126741.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.31748514175415,
|
|
"epoch": 1.5984630163304514,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047492729263991413,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.20387114435434342,
|
|
"num_tokens": 38137149.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.296435928344726,
|
|
"epoch": 1.5989433237271853,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047491156276216695,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.2179768607020378,
|
|
"num_tokens": 38148537.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.300688219070435,
|
|
"epoch": 1.5994236311239192,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047489582824306704,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.2073400765657425,
|
|
"num_tokens": 38159097.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.294732618331909,
|
|
"epoch": 1.5999039385206533,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047488008908297955,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.21514989882707597,
|
|
"num_tokens": 38171400.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.396916770935059,
|
|
"epoch": 1.6003842459173871,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004748643452822699,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.20831346213817598,
|
|
"num_tokens": 38181876.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.366373062133789,
|
|
"epoch": 1.600864553314121,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004748485968413036,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.2115179106593132,
|
|
"num_tokens": 38193680.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.230943441390991,
|
|
"epoch": 1.601344860710855,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047483284376044634,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.21225739270448685,
|
|
"num_tokens": 38204944.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.324364042282104,
|
|
"epoch": 1.601825168107589,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004748170860400638,
|
|
"loss": 5.0038,
|
|
"mean_token_accuracy": 0.2157621517777443,
|
|
"num_tokens": 38216381.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.340117359161377,
|
|
"epoch": 1.602305475504323,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047480132368052185,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.21436965018510817,
|
|
"num_tokens": 38227420.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.337131404876709,
|
|
"epoch": 1.6027857829010568,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047478555668218643,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.2086513951420784,
|
|
"num_tokens": 38237869.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.301999855041504,
|
|
"epoch": 1.6032660902977907,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004747697850454237,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.2019444689154625,
|
|
"num_tokens": 38250362.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.4196068286895756,
|
|
"epoch": 1.6037463976945245,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004747540087705997,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.20310890525579453,
|
|
"num_tokens": 38262887.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.336194324493408,
|
|
"epoch": 1.6042267050912584,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004747382278580808,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.2152033492922783,
|
|
"num_tokens": 38273206.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.316478490829468,
|
|
"epoch": 1.6047070124879923,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004747224423082333,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.20765644311904907,
|
|
"num_tokens": 38283307.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.355515432357788,
|
|
"epoch": 1.6051873198847262,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047470665212142384,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.20727937519550324,
|
|
"num_tokens": 38293830.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.332584571838379,
|
|
"epoch": 1.60566762728146,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047469085729801887,
|
|
"loss": 5.1204,
|
|
"mean_token_accuracy": 0.209553299844265,
|
|
"num_tokens": 38306523.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.376001024246216,
|
|
"epoch": 1.606147934678194,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047467505783838515,
|
|
"loss": 5.0833,
|
|
"mean_token_accuracy": 0.21241646856069565,
|
|
"num_tokens": 38318468.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.392667245864868,
|
|
"epoch": 1.6066282420749278,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004746592537428895,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.2137730672955513,
|
|
"num_tokens": 38329852.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.224036931991577,
|
|
"epoch": 1.6071085494716617,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047464344501189877,
|
|
"loss": 4.9803,
|
|
"mean_token_accuracy": 0.2205580323934555,
|
|
"num_tokens": 38340951.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.346596813201904,
|
|
"epoch": 1.6075888568683958,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047462763164578015,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.201506370306015,
|
|
"num_tokens": 38351490.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.344342851638794,
|
|
"epoch": 1.6080691642651297,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004746118136449007,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.20854796022176741,
|
|
"num_tokens": 38362364.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.3225466251373295,
|
|
"epoch": 1.6085494716618636,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004745959910096276,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.21408485621213913,
|
|
"num_tokens": 38374132.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.3176016330719,
|
|
"epoch": 1.6090297790585975,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047458016374032837,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.20980617702007293,
|
|
"num_tokens": 38384608.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.346223258972168,
|
|
"epoch": 1.6095100864553316,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004745643318373703,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.20544659793376924,
|
|
"num_tokens": 38396639.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.345020961761475,
|
|
"epoch": 1.6099903938520654,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047454849530112106,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20134957134723663,
|
|
"num_tokens": 38407954.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.418855047225952,
|
|
"epoch": 1.6104707012487993,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047453265413194826,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.20917006582021713,
|
|
"num_tokens": 38418939.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.346999549865723,
|
|
"epoch": 1.6109510086455332,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047451680833021973,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.2042980119585991,
|
|
"num_tokens": 38429717.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.242443180084228,
|
|
"epoch": 1.611431316042267,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004745009578963034,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.21287173181772232,
|
|
"num_tokens": 38441054.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.266035890579223,
|
|
"epoch": 1.611911623439001,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047448510283056716,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.21431116312742232,
|
|
"num_tokens": 38451329.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.378233861923218,
|
|
"epoch": 1.6123919308357348,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047446924313337925,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.20490553230047226,
|
|
"num_tokens": 38462118.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.325045013427735,
|
|
"epoch": 1.6128722382324687,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047445337880510773,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.21280529350042343,
|
|
"num_tokens": 38472642.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.2984106063842775,
|
|
"epoch": 1.6133525456292026,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004744375098461211,
|
|
"loss": 5.01,
|
|
"mean_token_accuracy": 0.21392353028059005,
|
|
"num_tokens": 38483866.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.258964776992798,
|
|
"epoch": 1.6138328530259365,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004744216362567876,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.2138601467013359,
|
|
"num_tokens": 38494164.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.356624031066895,
|
|
"epoch": 1.6143131604226704,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047440575803747595,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.1968373700976372,
|
|
"num_tokens": 38505340.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.507034111022949,
|
|
"epoch": 1.6147934678194045,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047438987518855463,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.19639117866754532,
|
|
"num_tokens": 38516164.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.388960170745849,
|
|
"epoch": 1.6152737752161384,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004743739877103926,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.2084641635417938,
|
|
"num_tokens": 38526545.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.281947278976441,
|
|
"epoch": 1.6157540826128722,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004743580956033585,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.2069193735718727,
|
|
"num_tokens": 38538102.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.376881551742554,
|
|
"epoch": 1.6162343900096061,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047434219886782135,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.20001419484615326,
|
|
"num_tokens": 38550594.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.358303689956665,
|
|
"epoch": 1.6167146974063402,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004743262975041504,
|
|
"loss": 5.0479,
|
|
"mean_token_accuracy": 0.2085604265332222,
|
|
"num_tokens": 38561666.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.309662103652954,
|
|
"epoch": 1.617195004803074,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004743103915127146,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.21332116276025773,
|
|
"num_tokens": 38572923.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.289978885650635,
|
|
"epoch": 1.617675312199808,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00047429448089388336,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.21148585081100463,
|
|
"num_tokens": 38584108.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.446104621887207,
|
|
"epoch": 1.6181556195965419,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047427856564802605,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.19839626401662827,
|
|
"num_tokens": 38594974.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.402093029022216,
|
|
"epoch": 1.6186359269932757,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004742626457755122,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.20730700194835663,
|
|
"num_tokens": 38606436.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.290849828720093,
|
|
"epoch": 1.6191162343900096,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004742467212767114,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.20743528455495835,
|
|
"num_tokens": 38618760.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.3024739742279055,
|
|
"epoch": 1.6195965417867435,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004742307921519933,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.2165915086865425,
|
|
"num_tokens": 38629901.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.406929588317871,
|
|
"epoch": 1.6200768491834774,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00047421485840172794,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.19562574476003647,
|
|
"num_tokens": 38640798.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.338291215896606,
|
|
"epoch": 1.6205571565802113,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004741989200262851,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.20833427906036378,
|
|
"num_tokens": 38653048.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.362213087081909,
|
|
"epoch": 1.6210374639769451,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004741829770260347,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.20335849821567537,
|
|
"num_tokens": 38666219.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.36060905456543,
|
|
"epoch": 1.621517771373679,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047416702940134714,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.20874348282814026,
|
|
"num_tokens": 38678584.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.3094099998474125,
|
|
"epoch": 1.621998078770413,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047415107715259255,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.20378148555755615,
|
|
"num_tokens": 38690164.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.354102277755738,
|
|
"epoch": 1.622478386167147,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047413512028014125,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.20871107578277587,
|
|
"num_tokens": 38702035.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.365681838989258,
|
|
"epoch": 1.622958693563881,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004741191587843638,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.20495332032442093,
|
|
"num_tokens": 38713802.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.378784465789795,
|
|
"epoch": 1.6234390009606148,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004741031926656308,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.21609766483306886,
|
|
"num_tokens": 38725682.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.356968402862549,
|
|
"epoch": 1.6239193083573487,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004740872219243128,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.2089461624622345,
|
|
"num_tokens": 38737897.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.367392492294312,
|
|
"epoch": 1.6243996157540828,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004740712465607807,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.20465130656957625,
|
|
"num_tokens": 38749446.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.307091093063354,
|
|
"epoch": 1.6248799231508166,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004740552665754054,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.20404231995344163,
|
|
"num_tokens": 38761406.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.359304332733155,
|
|
"epoch": 1.6253602305475505,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047403928196855776,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.2115563526749611,
|
|
"num_tokens": 38772574.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.3173693180084225,
|
|
"epoch": 1.6258405379442844,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047402329274060916,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.21670598685741424,
|
|
"num_tokens": 38782932.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.389703416824341,
|
|
"epoch": 1.6263208453410183,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004740072988919306,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.2034495562314987,
|
|
"num_tokens": 38793799.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.2908281803131105,
|
|
"epoch": 1.6268011527377522,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004739913004228936,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.21521564871072768,
|
|
"num_tokens": 38804899.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.278717422485352,
|
|
"epoch": 1.627281460134486,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004739752973338694,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.2018439933657646,
|
|
"num_tokens": 38816455.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.351008510589599,
|
|
"epoch": 1.62776176753122,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047395928962522965,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.2044850617647171,
|
|
"num_tokens": 38827735.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.329311180114746,
|
|
"epoch": 1.6282420749279538,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047394327729734595,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.20414405316114426,
|
|
"num_tokens": 38838536.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.423568201065064,
|
|
"epoch": 1.6287223823246877,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004739272603505901,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.2054711863398552,
|
|
"num_tokens": 38849577.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.423656702041626,
|
|
"epoch": 1.6292026897214216,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000473911238785334,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.19968030452728272,
|
|
"num_tokens": 38861370.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.278105449676514,
|
|
"epoch": 1.6296829971181557,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004738952126019496,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.20936828404664992,
|
|
"num_tokens": 38872885.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.305017042160034,
|
|
"epoch": 1.6301633045148896,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004738791818008089,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.20629408955574036,
|
|
"num_tokens": 38885440.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.320605278015137,
|
|
"epoch": 1.6306436119116234,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004738631463822841,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.2072140634059906,
|
|
"num_tokens": 38897108.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.284084129333496,
|
|
"epoch": 1.6311239193083573,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047384710634674766,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.20420551896095276,
|
|
"num_tokens": 38908020.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.361372995376587,
|
|
"epoch": 1.6316042267050914,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047383106169457184,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.20543216317892074,
|
|
"num_tokens": 38919558.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.3947460651397705,
|
|
"epoch": 1.6320845341018253,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004738150124261292,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.2134486436843872,
|
|
"num_tokens": 38931008.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.283546876907349,
|
|
"epoch": 1.6325648414985592,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047379895854179226,
|
|
"loss": 5.0199,
|
|
"mean_token_accuracy": 0.21125537008047104,
|
|
"num_tokens": 38943474.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.34180474281311,
|
|
"epoch": 1.633045148895293,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004737829000419338,
|
|
"loss": 5.1832,
|
|
"mean_token_accuracy": 0.20207796543836593,
|
|
"num_tokens": 38954592.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.349941539764404,
|
|
"epoch": 1.633525456292027,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047376683692692666,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.20842725932598113,
|
|
"num_tokens": 38965627.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.295697116851807,
|
|
"epoch": 1.6340057636887608,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004737507691971439,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.21493651270866393,
|
|
"num_tokens": 38975731.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.29139084815979,
|
|
"epoch": 1.6344860710854947,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047373469685295833,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.21557608842849732,
|
|
"num_tokens": 38987101.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.341855573654175,
|
|
"epoch": 1.6349663784822286,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047371861989474326,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.20779862850904465,
|
|
"num_tokens": 38999584.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.2759791851043705,
|
|
"epoch": 1.6354466858789625,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004737025383228719,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.21324484348297118,
|
|
"num_tokens": 39012025.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.2151326656341555,
|
|
"epoch": 1.6359269932756964,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00047368645213771764,
|
|
"loss": 4.9779,
|
|
"mean_token_accuracy": 0.2156819522380829,
|
|
"num_tokens": 39024102.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.3269298553466795,
|
|
"epoch": 1.6364073006724302,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000473670361339654,
|
|
"loss": 5.0973,
|
|
"mean_token_accuracy": 0.20363570302724837,
|
|
"num_tokens": 39035295.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.304220199584961,
|
|
"epoch": 1.6368876080691641,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004736542659290544,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.2081578016281128,
|
|
"num_tokens": 39046493.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.318496322631836,
|
|
"epoch": 1.6373679154658982,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004736381659062927,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.2123178631067276,
|
|
"num_tokens": 39056746.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.332658863067627,
|
|
"epoch": 1.637848222862632,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047362206127174255,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.1998867690563202,
|
|
"num_tokens": 39068263.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.370604515075684,
|
|
"epoch": 1.638328530259366,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047360595202577786,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.20581155270338058,
|
|
"num_tokens": 39080666.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.286146831512451,
|
|
"epoch": 1.6388088376560999,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00047358983816877284,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.20591960698366166,
|
|
"num_tokens": 39091851.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.3453644752502445,
|
|
"epoch": 1.639289145052834,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004735737197011015,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.2128559246659279,
|
|
"num_tokens": 39102893.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.280206918716431,
|
|
"epoch": 1.6397694524495678,
|
|
"grad_norm": 8.125,
|
|
"learning_rate": 0.00047355759662313793,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.20645055770874024,
|
|
"num_tokens": 39113582.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.377158117294312,
|
|
"epoch": 1.6402497598463017,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004735414689352566,
|
|
"loss": 5.1983,
|
|
"mean_token_accuracy": 0.2005127638578415,
|
|
"num_tokens": 39124616.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.268523788452148,
|
|
"epoch": 1.6407300672430356,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004735253366378318,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.21742093116044997,
|
|
"num_tokens": 39135537.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.371387147903443,
|
|
"epoch": 1.6412103746397695,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004735091997312383,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.21181072741746904,
|
|
"num_tokens": 39146363.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.346005392074585,
|
|
"epoch": 1.6416906820365034,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.00047349305821585067,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.2133706733584404,
|
|
"num_tokens": 39157319.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.307374048233032,
|
|
"epoch": 1.6421709894332372,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004734769120920435,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.21041153520345687,
|
|
"num_tokens": 39169352.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.363344430923462,
|
|
"epoch": 1.6426512968299711,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004734607613601919,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.21158917993307114,
|
|
"num_tokens": 39180989.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.36431999206543,
|
|
"epoch": 1.643131604226705,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00047344460602067077,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.20351341217756272,
|
|
"num_tokens": 39192309.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.261372518539429,
|
|
"epoch": 1.643611911623439,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000473428446073855,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.207463863492012,
|
|
"num_tokens": 39203586.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.297838830947876,
|
|
"epoch": 1.6440922190201728,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047341228152012003,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.2044737756252289,
|
|
"num_tokens": 39216248.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.323724699020386,
|
|
"epoch": 1.6445725264169067,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000473396112359841,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.2106313079595566,
|
|
"num_tokens": 39227244.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.321554803848267,
|
|
"epoch": 1.6450528338136408,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047337993859339334,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.21611708253622056,
|
|
"num_tokens": 39238769.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.292935371398926,
|
|
"epoch": 1.6455331412103746,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047336376022115255,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.2059275448322296,
|
|
"num_tokens": 39251424.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.267062997817993,
|
|
"epoch": 1.6460134486071085,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047334757724349437,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.21574784964323043,
|
|
"num_tokens": 39262451.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.297372817993164,
|
|
"epoch": 1.6464937560038426,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004733313896607943,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.21189188957214355,
|
|
"num_tokens": 39275129.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.389811849594116,
|
|
"epoch": 1.6469740634005765,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004733151974734284,
|
|
"loss": 5.1838,
|
|
"mean_token_accuracy": 0.20333020389080048,
|
|
"num_tokens": 39287399.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.3335987567901615,
|
|
"epoch": 1.6474543707973104,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047329900068177245,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.2105117753148079,
|
|
"num_tokens": 39297755.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.40178952217102,
|
|
"epoch": 1.6479346781940443,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047328279928620244,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.1994369074702263,
|
|
"num_tokens": 39311012.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.378004360198974,
|
|
"epoch": 1.6484149855907781,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004732665932870947,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.20845113098621368,
|
|
"num_tokens": 39321797.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.331858205795288,
|
|
"epoch": 1.648895292987512,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047325038268482544,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.2183534786105156,
|
|
"num_tokens": 39333598.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.37274203300476,
|
|
"epoch": 1.649375600384246,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004732341674797709,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.203118896484375,
|
|
"num_tokens": 39345578.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.25265097618103,
|
|
"epoch": 1.6498559077809798,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047321794767230766,
|
|
"loss": 4.9687,
|
|
"mean_token_accuracy": 0.21946283876895906,
|
|
"num_tokens": 39356744.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.3263099670410154,
|
|
"epoch": 1.6503362151777137,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047320172326281224,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.20020170360803605,
|
|
"num_tokens": 39368138.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.265275621414185,
|
|
"epoch": 1.6508165225744476,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047318549425166134,
|
|
"loss": 4.9748,
|
|
"mean_token_accuracy": 0.21338768750429155,
|
|
"num_tokens": 39380117.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.338293170928955,
|
|
"epoch": 1.6512968299711814,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004731692606392318,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.20998999774456023,
|
|
"num_tokens": 39390913.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.393780708312988,
|
|
"epoch": 1.6517771373679153,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004731530224259004,
|
|
"loss": 5.1813,
|
|
"mean_token_accuracy": 0.19677422493696212,
|
|
"num_tokens": 39401001.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.286955499649048,
|
|
"epoch": 1.6522574447646494,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004731367796120442,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.21183586716651917,
|
|
"num_tokens": 39411982.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.384113025665283,
|
|
"epoch": 1.6527377521613833,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004731205321980404,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.20482180416584014,
|
|
"num_tokens": 39423363.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.38191409111023,
|
|
"epoch": 1.6532180595581172,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047310428018426616,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.20294642001390456,
|
|
"num_tokens": 39434002.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.262417936325074,
|
|
"epoch": 1.653698366954851,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004730880235710987,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.20881202220916747,
|
|
"num_tokens": 39444629.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.303467702865601,
|
|
"epoch": 1.6541786743515852,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004730717623589155,
|
|
"loss": 4.9836,
|
|
"mean_token_accuracy": 0.2192396804690361,
|
|
"num_tokens": 39454803.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.327382946014405,
|
|
"epoch": 1.654658981748319,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004730554965480942,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.20744114071130754,
|
|
"num_tokens": 39466931.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.329761695861817,
|
|
"epoch": 1.655139289145053,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004730392261390124,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.21195732951164245,
|
|
"num_tokens": 39478127.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.359872674942016,
|
|
"epoch": 1.6556195965417868,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004730229511320478,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.20128597021102906,
|
|
"num_tokens": 39488188.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.3516058921813965,
|
|
"epoch": 1.6560999039385207,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047300667152757827,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.21075146347284318,
|
|
"num_tokens": 39500035.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.39392352104187,
|
|
"epoch": 1.6565802113352546,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047299038732598184,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.2048359304666519,
|
|
"num_tokens": 39510922.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.290698671340943,
|
|
"epoch": 1.6570605187319885,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047297409852763644,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.20781012028455734,
|
|
"num_tokens": 39521319.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.348071718215943,
|
|
"epoch": 1.6575408261287223,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004729578051329204,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.20956083089113237,
|
|
"num_tokens": 39532408.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.3730498313903805,
|
|
"epoch": 1.6580211335254562,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047294150714221185,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.199243201315403,
|
|
"num_tokens": 39543323.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.369166660308838,
|
|
"epoch": 1.65850144092219,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004729252045558894,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.202621628344059,
|
|
"num_tokens": 39554133.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.304240417480469,
|
|
"epoch": 1.658981748318924,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047290889737433133,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.21071861684322357,
|
|
"num_tokens": 39565990.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.326796197891236,
|
|
"epoch": 1.6594620557156579,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047289258559791633,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.21145529299974442,
|
|
"num_tokens": 39577591.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.3354085922241214,
|
|
"epoch": 1.659942363112392,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00047287626922702317,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.20707816183567046,
|
|
"num_tokens": 39589922.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.290621709823609,
|
|
"epoch": 1.6604226705091258,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047285994826203054,
|
|
"loss": 5.0929,
|
|
"mean_token_accuracy": 0.20997002124786376,
|
|
"num_tokens": 39602183.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.339214754104614,
|
|
"epoch": 1.6609029779058597,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004728436227033175,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.20782216042280197,
|
|
"num_tokens": 39612922.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.395445489883423,
|
|
"epoch": 1.6613832853025938,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047282729255126294,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.20867014974355697,
|
|
"num_tokens": 39624475.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.19140887260437,
|
|
"epoch": 1.6618635926993277,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004728109578062461,
|
|
"loss": 4.938,
|
|
"mean_token_accuracy": 0.21735318154096603,
|
|
"num_tokens": 39635230.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.235133123397827,
|
|
"epoch": 1.6623439000960616,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047279461846864626,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.20933284759521484,
|
|
"num_tokens": 39646788.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.298409843444825,
|
|
"epoch": 1.6628242074927955,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047277827453884265,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.20768668055534362,
|
|
"num_tokens": 39657531.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.3938579082489015,
|
|
"epoch": 1.6633045148895294,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047276192601721477,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.1956944689154625,
|
|
"num_tokens": 39669008.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.321354341506958,
|
|
"epoch": 1.6637848222862632,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004727455729041422,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.21143176257610322,
|
|
"num_tokens": 39680772.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.42832236289978,
|
|
"epoch": 1.6642651296829971,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047272921520000465,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.1957120731472969,
|
|
"num_tokens": 39694107.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.320689105987549,
|
|
"epoch": 1.664745437079731,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004727128529051819,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.20269545763731003,
|
|
"num_tokens": 39705440.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.263955211639404,
|
|
"epoch": 1.6652257444764649,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004726964860200537,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.21025270372629165,
|
|
"num_tokens": 39716246.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.358638334274292,
|
|
"epoch": 1.6657060518731988,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004726801145450002,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.20432433038949965,
|
|
"num_tokens": 39727233.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.347072410583496,
|
|
"epoch": 1.6661863592699326,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004726637384804014,
|
|
"loss": 5.0479,
|
|
"mean_token_accuracy": 0.20644643604755403,
|
|
"num_tokens": 39738929.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.310742425918579,
|
|
"epoch": 1.6666666666666665,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004726473578266375,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.20560942888259887,
|
|
"num_tokens": 39750714.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.295433807373047,
|
|
"epoch": 1.6671469740634006,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047263097258408893,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.20695324689149858,
|
|
"num_tokens": 39762810.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.356151008605957,
|
|
"epoch": 1.6676272814601345,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004726145827531359,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.19908519387245177,
|
|
"num_tokens": 39774611.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.2780872821807865,
|
|
"epoch": 1.6681075888568684,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00047259818833415916,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.22256645262241365,
|
|
"num_tokens": 39784900.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.402129793167115,
|
|
"epoch": 1.6685878962536023,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047258178932753917,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.21007601916790009,
|
|
"num_tokens": 39794805.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.371637344360352,
|
|
"epoch": 1.6690682036503364,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047256538573365675,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.20157858580350876,
|
|
"num_tokens": 39806444.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.46169810295105,
|
|
"epoch": 1.6695485110470702,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004725489775528928,
|
|
"loss": 5.2526,
|
|
"mean_token_accuracy": 0.19736103862524032,
|
|
"num_tokens": 39817724.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.345140504837036,
|
|
"epoch": 1.6700288184438041,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00047253256478562805,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.2029756247997284,
|
|
"num_tokens": 39828944.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.290038347244263,
|
|
"epoch": 1.670509125840538,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047251614743224374,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.2048950210213661,
|
|
"num_tokens": 39839978.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.310587596893311,
|
|
"epoch": 1.670989433237272,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047249972549312107,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.2102477639913559,
|
|
"num_tokens": 39850787.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.396619749069214,
|
|
"epoch": 1.6714697406340058,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004724832989686411,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.20779721140861512,
|
|
"num_tokens": 39862245.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.315993309020996,
|
|
"epoch": 1.6719500480307397,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047246686785918545,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.21335069835186005,
|
|
"num_tokens": 39872295.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.219392204284668,
|
|
"epoch": 1.6724303554274735,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047245043216513546,
|
|
"loss": 4.9958,
|
|
"mean_token_accuracy": 0.20502994656562806,
|
|
"num_tokens": 39882839.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.199974012374878,
|
|
"epoch": 1.6729106628242074,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004724339918868727,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.21321591585874558,
|
|
"num_tokens": 39894767.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.387861919403076,
|
|
"epoch": 1.6733909702209413,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000472417547024779,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.19464466273784636,
|
|
"num_tokens": 39907492.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.289026069641113,
|
|
"epoch": 1.6738712776176752,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047240109757923593,
|
|
"loss": 4.9382,
|
|
"mean_token_accuracy": 0.21812178641557695,
|
|
"num_tokens": 39919005.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.289284896850586,
|
|
"epoch": 1.674351585014409,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004723846435506256,
|
|
"loss": 5.0501,
|
|
"mean_token_accuracy": 0.2101389855146408,
|
|
"num_tokens": 39930417.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.270689392089844,
|
|
"epoch": 1.6748318924111432,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047236818493932994,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.20898133665323257,
|
|
"num_tokens": 39941873.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.358610057830811,
|
|
"epoch": 1.675312199807877,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004723517217457311,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.20479418933391572,
|
|
"num_tokens": 39953280.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.39880747795105,
|
|
"epoch": 1.675792507204611,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004723352539702113,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.20602872371673583,
|
|
"num_tokens": 39964898.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.3427740097045895,
|
|
"epoch": 1.6762728146013448,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004723187816131529,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.21175304800271988,
|
|
"num_tokens": 39976945.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.377019262313842,
|
|
"epoch": 1.676753121998079,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004723023046749383,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.20502844601869583,
|
|
"num_tokens": 39987760.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.253666591644287,
|
|
"epoch": 1.6772334293948128,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00047228582315595,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.22095100879669188,
|
|
"num_tokens": 39998171.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.279906940460205,
|
|
"epoch": 1.6777137367915467,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004722693370565708,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.20730687081813812,
|
|
"num_tokens": 40010124.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.269788503646851,
|
|
"epoch": 1.6781940441882806,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047225284637718323,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.20546937733888626,
|
|
"num_tokens": 40022599.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.333118343353272,
|
|
"epoch": 1.6786743515850144,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004722363511181703,
|
|
"loss": 5.0218,
|
|
"mean_token_accuracy": 0.21803490817546844,
|
|
"num_tokens": 40033738.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.354845190048218,
|
|
"epoch": 1.6791546589817483,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000472219851279915,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.20916338860988617,
|
|
"num_tokens": 40044148.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.341347503662109,
|
|
"epoch": 1.6796349663784822,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004722033468628004,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.21204735338687897,
|
|
"num_tokens": 40055430.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.286327219009399,
|
|
"epoch": 1.680115273775216,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004721868378672098,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.21062094271183013,
|
|
"num_tokens": 40066147.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.3261185646057125,
|
|
"epoch": 1.68059558117195,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004721703242935261,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.2093953087925911,
|
|
"num_tokens": 40077567.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.419674015045166,
|
|
"epoch": 1.6810758885686838,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004721538061421331,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.205782513320446,
|
|
"num_tokens": 40089544.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.2339273452758786,
|
|
"epoch": 1.6815561959654177,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047213728341341407,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.21970771849155427,
|
|
"num_tokens": 40100557.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.346922159194946,
|
|
"epoch": 1.6820365033621518,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004721207561077527,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.20410882830619811,
|
|
"num_tokens": 40112052.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.5167985439300535,
|
|
"epoch": 1.6825168107588857,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004721042242255327,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.19392096400260925,
|
|
"num_tokens": 40123830.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.346066665649414,
|
|
"epoch": 1.6829971181556196,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047208768776713805,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.20705606490373613,
|
|
"num_tokens": 40134222.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.326477575302124,
|
|
"epoch": 1.6834774255523535,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004720711467329523,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.2056407406926155,
|
|
"num_tokens": 40145552.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.318469715118408,
|
|
"epoch": 1.6839577329490876,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004720546011233599,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.21266083419322968,
|
|
"num_tokens": 40156615.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.2931938648223875,
|
|
"epoch": 1.6844380403458215,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004720380509387446,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.2128259852528572,
|
|
"num_tokens": 40168825.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.310484266281128,
|
|
"epoch": 1.6849183477425553,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000472021496179491,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.21031631529331207,
|
|
"num_tokens": 40179523.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.293830347061157,
|
|
"epoch": 1.6853986551392892,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047200493684598316,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.2074023649096489,
|
|
"num_tokens": 40191362.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.332072734832764,
|
|
"epoch": 1.685878962536023,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047198837293860573,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.20392894446849824,
|
|
"num_tokens": 40202274.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.368592548370361,
|
|
"epoch": 1.686359269932757,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004719718044577432,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.20032278895378114,
|
|
"num_tokens": 40213907.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.273600625991821,
|
|
"epoch": 1.6868395773294909,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047195523140378034,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.20448191463947296,
|
|
"num_tokens": 40225300.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.23798565864563,
|
|
"epoch": 1.6873198847262247,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047193865377710177,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.21825893670320512,
|
|
"num_tokens": 40236197.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.432412242889404,
|
|
"epoch": 1.6878001921229586,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047192207157809246,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.20275999754667282,
|
|
"num_tokens": 40247887.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.414694499969483,
|
|
"epoch": 1.6882804995196925,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047190548480713736,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.20691258013248442,
|
|
"num_tokens": 40258262.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.361690473556519,
|
|
"epoch": 1.6887608069164264,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047188889346462163,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.20480191707611084,
|
|
"num_tokens": 40268735.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.336686420440674,
|
|
"epoch": 1.6892411143131603,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047187229755093037,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.20108706951141359,
|
|
"num_tokens": 40279905.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.349285411834717,
|
|
"epoch": 1.6897214217098944,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000471855697066449,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.2081129476428032,
|
|
"num_tokens": 40290580.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.355312633514404,
|
|
"epoch": 1.6902017291066282,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047183909201156297,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.20822833627462387,
|
|
"num_tokens": 40302472.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.3735276222229,
|
|
"epoch": 1.6906820365033621,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004718224823866576,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.20330996215343475,
|
|
"num_tokens": 40314238.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.2461646556854244,
|
|
"epoch": 1.691162343900096,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004718058681921186,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.20768005698919295,
|
|
"num_tokens": 40326147.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.350877571105957,
|
|
"epoch": 1.6916426512968301,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047178924942833185,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.2145967200398445,
|
|
"num_tokens": 40338210.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.310636806488037,
|
|
"epoch": 1.692122958693564,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004717726260956831,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.2172916427254677,
|
|
"num_tokens": 40349293.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.248133325576783,
|
|
"epoch": 1.6926032660902979,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004717559981945581,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.2069757401943207,
|
|
"num_tokens": 40360916.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.300935888290406,
|
|
"epoch": 1.6930835734870318,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004717393657253432,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.20492299199104308,
|
|
"num_tokens": 40373525.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.375859880447388,
|
|
"epoch": 1.6935638808837656,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004717227286884243,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.20458998233079911,
|
|
"num_tokens": 40385286.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.287223672866821,
|
|
"epoch": 1.6940441882804995,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004717060870841879,
|
|
"loss": 5.0126,
|
|
"mean_token_accuracy": 0.2081642597913742,
|
|
"num_tokens": 40396371.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.306209421157837,
|
|
"epoch": 1.6945244956772334,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004716894409130202,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.20983507633209228,
|
|
"num_tokens": 40407304.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.277754163742065,
|
|
"epoch": 1.6950048030739673,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004716727901753078,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.21170998513698577,
|
|
"num_tokens": 40418384.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.409881496429444,
|
|
"epoch": 1.6954851104707012,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004716561348714371,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.20574371814727782,
|
|
"num_tokens": 40430603.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.299568510055542,
|
|
"epoch": 1.695965417867435,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00047163947500179494,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.21051265746355058,
|
|
"num_tokens": 40442597.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.194208335876465,
|
|
"epoch": 1.696445725264169,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004716228105667681,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.2139817014336586,
|
|
"num_tokens": 40454078.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.255525588989258,
|
|
"epoch": 1.696926032660903,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004716061415667435,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.21582538336515428,
|
|
"num_tokens": 40465561.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.339214897155761,
|
|
"epoch": 1.697406340057637,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000471589468002108,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.21206815391778946,
|
|
"num_tokens": 40476883.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.351578569412231,
|
|
"epoch": 1.6978866474543708,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004715727898732488,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.21338408887386323,
|
|
"num_tokens": 40488139.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.324730682373047,
|
|
"epoch": 1.6983669548511047,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047155610718055315,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.20848306268453598,
|
|
"num_tokens": 40499367.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.211904239654541,
|
|
"epoch": 1.6988472622478388,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047153941992440833,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.2030050590634346,
|
|
"num_tokens": 40510628.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.254138660430908,
|
|
"epoch": 1.6993275696445727,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004715227281052018,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.21608465015888215,
|
|
"num_tokens": 40522680.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.256714534759522,
|
|
"epoch": 1.6998078770413065,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004715060317233211,
|
|
"loss": 4.9519,
|
|
"mean_token_accuracy": 0.22222647815942764,
|
|
"num_tokens": 40533139.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.333749580383301,
|
|
"epoch": 1.7002881844380404,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004714893307791538,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.20971357673406602,
|
|
"num_tokens": 40544578.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.377049112319947,
|
|
"epoch": 1.7007684918347743,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047147262527308766,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.21358333379030228,
|
|
"num_tokens": 40555667.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.269075775146485,
|
|
"epoch": 1.7012487992315082,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004714559152055106,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.2136329635977745,
|
|
"num_tokens": 40567123.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.360239553451538,
|
|
"epoch": 1.701729106628242,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004714392005768106,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.20860441476106645,
|
|
"num_tokens": 40579692.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.312709856033325,
|
|
"epoch": 1.702209414024976,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004714224813873756,
|
|
"loss": 5.0267,
|
|
"mean_token_accuracy": 0.21902200430631638,
|
|
"num_tokens": 40590989.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.265335416793823,
|
|
"epoch": 1.7026897214217098,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047140575763759393,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.2143070802092552,
|
|
"num_tokens": 40602050.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.276479434967041,
|
|
"epoch": 1.7031700288184437,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047138902932785363,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.21114458292722701,
|
|
"num_tokens": 40614552.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.319697999954224,
|
|
"epoch": 1.7036503362151776,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047137229645854333,
|
|
"loss": 5.008,
|
|
"mean_token_accuracy": 0.21707181334495546,
|
|
"num_tokens": 40625903.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.319426250457764,
|
|
"epoch": 1.7041306436119115,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004713555590300513,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.20576956272125244,
|
|
"num_tokens": 40638634.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.398586988449097,
|
|
"epoch": 1.7046109510086456,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004713388170427664,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.20422293990850449,
|
|
"num_tokens": 40651279.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.3229881763458256,
|
|
"epoch": 1.7050912584053795,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004713220704970771,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.21030211001634597,
|
|
"num_tokens": 40662306.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.16081132888794,
|
|
"epoch": 1.7055715658021133,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047130531939337236,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.21790910512208939,
|
|
"num_tokens": 40672290.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.3144501686096195,
|
|
"epoch": 1.7060518731988472,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047128856373204086,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.20315677374601365,
|
|
"num_tokens": 40683447.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.451790618896484,
|
|
"epoch": 1.7065321805955813,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047127180351347184,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.20478653758764268,
|
|
"num_tokens": 40695230.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.303498315811157,
|
|
"epoch": 1.7070124879923152,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004712550387380544,
|
|
"loss": 5.0343,
|
|
"mean_token_accuracy": 0.21020509004592897,
|
|
"num_tokens": 40707311.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.307075834274292,
|
|
"epoch": 1.707492795389049,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004712382694061776,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.2066749796271324,
|
|
"num_tokens": 40717928.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.281927824020386,
|
|
"epoch": 1.707973102785783,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047122149551823096,
|
|
"loss": 5.0759,
|
|
"mean_token_accuracy": 0.20313112288713456,
|
|
"num_tokens": 40730355.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.395219087600708,
|
|
"epoch": 1.7084534101825168,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004712047170746039,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.2031020626425743,
|
|
"num_tokens": 40741412.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.35954794883728,
|
|
"epoch": 1.7089337175792507,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047118793407568586,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.21314165294170379,
|
|
"num_tokens": 40753491.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.2538769245147705,
|
|
"epoch": 1.7094140249759846,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00047117114652186657,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.21228020042181014,
|
|
"num_tokens": 40765209.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.277756023406982,
|
|
"epoch": 1.7098943323727185,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047115435441353573,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.2069747343659401,
|
|
"num_tokens": 40778065.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.334110069274902,
|
|
"epoch": 1.7103746397694524,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047113755775108333,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.20729120671749116,
|
|
"num_tokens": 40789149.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.326713037490845,
|
|
"epoch": 1.7108549471661862,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047112075653489913,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.2176990255713463,
|
|
"num_tokens": 40800340.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.346135520935059,
|
|
"epoch": 1.7113352545629201,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004711039507653734,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.20705350637435913,
|
|
"num_tokens": 40811866.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.311307001113891,
|
|
"epoch": 1.7118155619596542,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004710871404428961,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.1999067947268486,
|
|
"num_tokens": 40825850.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.365236473083496,
|
|
"epoch": 1.7122958693563881,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047107032556785786,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.21244095712900163,
|
|
"num_tokens": 40836688.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.323546648025513,
|
|
"epoch": 1.712776176753122,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047105350614064874,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.20647770017385483,
|
|
"num_tokens": 40847803.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.349510765075683,
|
|
"epoch": 1.7132564841498559,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047103668216165944,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.20778999030590056,
|
|
"num_tokens": 40859099.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.269279336929321,
|
|
"epoch": 1.71373679154659,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047101985363128045,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.21819332391023635,
|
|
"num_tokens": 40870440.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.409398031234741,
|
|
"epoch": 1.7142170989433239,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047100302054990255,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.20270751565694808,
|
|
"num_tokens": 40882329.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.378934669494629,
|
|
"epoch": 1.7146974063400577,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004709861829179165,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.20518776774406433,
|
|
"num_tokens": 40893458.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.240721845626831,
|
|
"epoch": 1.7151777137367916,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047096934073571325,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.21802443414926528,
|
|
"num_tokens": 40904626.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.255499267578125,
|
|
"epoch": 1.7156580211335255,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047095249400368384,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.21889299005270005,
|
|
"num_tokens": 40916005.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.224230051040649,
|
|
"epoch": 1.7161383285302594,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047093564272221927,
|
|
"loss": 4.9737,
|
|
"mean_token_accuracy": 0.21611129343509675,
|
|
"num_tokens": 40927470.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.3256080627441404,
|
|
"epoch": 1.7166186359269933,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00047091878689171105,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.21451909840106964,
|
|
"num_tokens": 40938968.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.261987829208374,
|
|
"epoch": 1.7170989433237271,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004709019265125502,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.21983838677406312,
|
|
"num_tokens": 40952636.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.328075933456421,
|
|
"epoch": 1.717579250720461,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047088506158512837,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.21381329298019408,
|
|
"num_tokens": 40964816.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.340527677536011,
|
|
"epoch": 1.718059558117195,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047086819210983714,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.20692039728164674,
|
|
"num_tokens": 40977152.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.305281305313111,
|
|
"epoch": 1.7185398655139288,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047085131808706813,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.2125907450914383,
|
|
"num_tokens": 40987506.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.367907619476318,
|
|
"epoch": 1.7190201729106627,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004708344395172129,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.2122908964753151,
|
|
"num_tokens": 40998598.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.305727195739746,
|
|
"epoch": 1.7195004803073968,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004708175564006636,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.20104897767305374,
|
|
"num_tokens": 41009644.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.236573028564453,
|
|
"epoch": 1.7199807877041307,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004708006687378121,
|
|
"loss": 4.9692,
|
|
"mean_token_accuracy": 0.21295610964298248,
|
|
"num_tokens": 41021816.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.280929708480835,
|
|
"epoch": 1.7204610951008645,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004707837765290505,
|
|
"loss": 5.0059,
|
|
"mean_token_accuracy": 0.21186857521533967,
|
|
"num_tokens": 41033482.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.30057692527771,
|
|
"epoch": 1.7209414024975984,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004707668797747709,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.21515336781740188,
|
|
"num_tokens": 41043854.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.331161308288574,
|
|
"epoch": 1.7214217098943325,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004707499784753657,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.2023344725370407,
|
|
"num_tokens": 41056956.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.422322130203247,
|
|
"epoch": 1.7219020172910664,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004707330726312273,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.19742469489574432,
|
|
"num_tokens": 41068170.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.318097829818726,
|
|
"epoch": 1.7223823246878003,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047071616224274803,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.2103310763835907,
|
|
"num_tokens": 41079149.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.417683696746826,
|
|
"epoch": 1.7228626320845342,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004706992473103207,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.1980380430817604,
|
|
"num_tokens": 41091039.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.271555089950562,
|
|
"epoch": 1.723342939481268,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047068232783433806,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.2160372868180275,
|
|
"num_tokens": 41103318.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.259493732452393,
|
|
"epoch": 1.723823246878002,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004706654038151927,
|
|
"loss": 4.9712,
|
|
"mean_token_accuracy": 0.21560185104608537,
|
|
"num_tokens": 41114235.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.278785228729248,
|
|
"epoch": 1.7243035542747358,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004706484752532777,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.21142712980508804,
|
|
"num_tokens": 41126008.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.263929319381714,
|
|
"epoch": 1.7247838616714697,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004706315421489861,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.2083493947982788,
|
|
"num_tokens": 41138819.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.356428003311157,
|
|
"epoch": 1.7252641690682036,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004706146045027109,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.215371473133564,
|
|
"num_tokens": 41149389.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.315204095840454,
|
|
"epoch": 1.7257444764649374,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004705976623148455,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.20701196193695068,
|
|
"num_tokens": 41161810.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.315511894226074,
|
|
"epoch": 1.7262247838616713,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047058071558578324,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.20692536383867263,
|
|
"num_tokens": 41172903.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.349471139907837,
|
|
"epoch": 1.7267050912584054,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004705637643159175,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.21324184983968736,
|
|
"num_tokens": 41183905.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.307153272628784,
|
|
"epoch": 1.7271853986551393,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047054680850564185,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.20976769626140596,
|
|
"num_tokens": 41195921.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.225269365310669,
|
|
"epoch": 1.7276657060518732,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004705298481553499,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.2167291209101677,
|
|
"num_tokens": 41208287.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.329636192321777,
|
|
"epoch": 1.728146013448607,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047051288326543553,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.2032470002770424,
|
|
"num_tokens": 41219864.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.301889038085937,
|
|
"epoch": 1.7286263208453412,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047049591383629247,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.2132970929145813,
|
|
"num_tokens": 41230640.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.31260199546814,
|
|
"epoch": 1.729106628242075,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047047893986831493,
|
|
"loss": 5.0768,
|
|
"mean_token_accuracy": 0.21117638498544694,
|
|
"num_tokens": 41242413.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.729106628242075,
|
|
"eval_entropy": 5.162394116995452,
|
|
"eval_loss": 5.144191741943359,
|
|
"eval_mean_token_accuracy": 0.21300156574799833,
|
|
"eval_num_tokens": 41242413.0,
|
|
"eval_runtime": 26.6525,
|
|
"eval_samples_per_second": 1231.217,
|
|
"eval_steps_per_second": 153.907,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.375878143310547,
|
|
"epoch": 1.729586935638809,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047046196136189686,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.20638556480407716,
|
|
"num_tokens": 41254400.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.2834044933319095,
|
|
"epoch": 1.7300672430355428,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004704449783174323,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.20745731443166732,
|
|
"num_tokens": 41266849.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.369462251663208,
|
|
"epoch": 1.7305475504322767,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004704279907353158,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.2061307594180107,
|
|
"num_tokens": 41278179.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.289987993240357,
|
|
"epoch": 1.7310278578290106,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047041099861594167,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.2162061408162117,
|
|
"num_tokens": 41289904.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.396516990661621,
|
|
"epoch": 1.7315081652257445,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004703940019597044,
|
|
"loss": 5.209,
|
|
"mean_token_accuracy": 0.2002636209130287,
|
|
"num_tokens": 41301861.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.356449699401855,
|
|
"epoch": 1.7319884726224783,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047037700076699857,
|
|
"loss": 5.0356,
|
|
"mean_token_accuracy": 0.21397203356027603,
|
|
"num_tokens": 41312420.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.296197175979614,
|
|
"epoch": 1.7324687800192122,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000470359995038219,
|
|
"loss": 5.0391,
|
|
"mean_token_accuracy": 0.214768123626709,
|
|
"num_tokens": 41323264.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.326612567901611,
|
|
"epoch": 1.732949087415946,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004703429847737604,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.20697094798088073,
|
|
"num_tokens": 41335438.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.342278051376343,
|
|
"epoch": 1.73342939481268,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004703259699740177,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.20014867186546326,
|
|
"num_tokens": 41347295.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.325305032730102,
|
|
"epoch": 1.7339097022094139,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00047030895063938607,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.20619941949844361,
|
|
"num_tokens": 41358886.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.280945920944214,
|
|
"epoch": 1.734390009606148,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047029192677026043,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.22012416422367095,
|
|
"num_tokens": 41369402.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.401988935470581,
|
|
"epoch": 1.7348703170028819,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004702748983670363,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.20058303475379943,
|
|
"num_tokens": 41379772.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.412081575393676,
|
|
"epoch": 1.7353506243996157,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004702578654301088,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.20839405208826065,
|
|
"num_tokens": 41389776.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.213947200775147,
|
|
"epoch": 1.7358309317963496,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004702408279598734,
|
|
"loss": 4.955,
|
|
"mean_token_accuracy": 0.20885930806398392,
|
|
"num_tokens": 41400640.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.2511221408844,
|
|
"epoch": 1.7363112391930837,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004702237859567258,
|
|
"loss": 5.0104,
|
|
"mean_token_accuracy": 0.21154440939426422,
|
|
"num_tokens": 41412653.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.434164953231812,
|
|
"epoch": 1.7367915465898176,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004702067394210616,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.20114415735006333,
|
|
"num_tokens": 41423815.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.343595218658447,
|
|
"epoch": 1.7372718539865515,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047018968835327643,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.20111346244812012,
|
|
"num_tokens": 41436016.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.254481220245362,
|
|
"epoch": 1.7377521613832854,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004701726327537664,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.2114243984222412,
|
|
"num_tokens": 41447837.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.326049089431763,
|
|
"epoch": 1.7382324687800192,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004701555726229274,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.20780792385339736,
|
|
"num_tokens": 41459816.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.3183187484741214,
|
|
"epoch": 1.7387127761767531,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004701385079611555,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.20868220180273056,
|
|
"num_tokens": 41471461.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.285730504989624,
|
|
"epoch": 1.739193083573487,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047012143876884677,
|
|
"loss": 5.0012,
|
|
"mean_token_accuracy": 0.21327888816595078,
|
|
"num_tokens": 41481886.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.246136808395386,
|
|
"epoch": 1.739673390970221,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004701043650463977,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.21371365785598756,
|
|
"num_tokens": 41493698.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.265924453735352,
|
|
"epoch": 1.7401536983669548,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004700872867942046,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.22046957165002823,
|
|
"num_tokens": 41504744.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.350367403030395,
|
|
"epoch": 1.7406340057636887,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000470070204012664,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.2149507462978363,
|
|
"num_tokens": 41517129.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.3734253406524655,
|
|
"epoch": 1.7411143131604225,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047005311670217256,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.20061859786510466,
|
|
"num_tokens": 41529969.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.289269590377808,
|
|
"epoch": 1.7415946205571564,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047003602486312687,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.2147039294242859,
|
|
"num_tokens": 41541515.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.268774127960205,
|
|
"epoch": 1.7420749279538905,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004700189284959238,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.20887874960899352,
|
|
"num_tokens": 41553045.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.334945821762085,
|
|
"epoch": 1.7425552353506244,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047000182760096037,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.20638084560632705,
|
|
"num_tokens": 41565376.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.302884483337403,
|
|
"epoch": 1.7430355427473583,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004699847221786335,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.20068811029195785,
|
|
"num_tokens": 41577515.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.2651886463165285,
|
|
"epoch": 1.7435158501440924,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004699676122293403,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.21231616288423538,
|
|
"num_tokens": 41588589.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.36748480796814,
|
|
"epoch": 1.7439961575408263,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004699504977534782,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.2090010091662407,
|
|
"num_tokens": 41600727.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.373867654800415,
|
|
"epoch": 1.7444764649375601,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004699333787514444,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.21372549533843993,
|
|
"num_tokens": 41612177.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.370540904998779,
|
|
"epoch": 1.744956772334294,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004699162552236363,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.21335291713476182,
|
|
"num_tokens": 41623749.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.371150255203247,
|
|
"epoch": 1.745437079731028,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046989912717045165,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.20616011470556259,
|
|
"num_tokens": 41635549.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.31395320892334,
|
|
"epoch": 1.7459173871277618,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046988199459228793,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.20538069307804108,
|
|
"num_tokens": 41647219.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.441364383697509,
|
|
"epoch": 1.7463976945244957,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004698648574895429,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.20694483518600465,
|
|
"num_tokens": 41658850.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.39647536277771,
|
|
"epoch": 1.7468780019212296,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046984771586261465,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.2069239944219589,
|
|
"num_tokens": 41669304.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.318625593185425,
|
|
"epoch": 1.7473583093179634,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000469830569711901,
|
|
"loss": 5.1442,
|
|
"mean_token_accuracy": 0.2104225903749466,
|
|
"num_tokens": 41681652.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.3588056564331055,
|
|
"epoch": 1.7478386167146973,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004698134190377999,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.202828311920166,
|
|
"num_tokens": 41692548.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.320604133605957,
|
|
"epoch": 1.7483189241114312,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00046979626384070983,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.21475785374641418,
|
|
"num_tokens": 41704528.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.286573457717895,
|
|
"epoch": 1.748799231508165,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000469779104121029,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.20668799728155135,
|
|
"num_tokens": 41717314.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.420193910598755,
|
|
"epoch": 1.7492795389048992,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046976193987915553,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.2044479250907898,
|
|
"num_tokens": 41729193.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.326896381378174,
|
|
"epoch": 1.749759846301633,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004697447711154883,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.20906509310007096,
|
|
"num_tokens": 41741208.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.2838029861450195,
|
|
"epoch": 1.750240153698367,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046972759783042576,
|
|
"loss": 5.034,
|
|
"mean_token_accuracy": 0.212690632045269,
|
|
"num_tokens": 41752792.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.36752290725708,
|
|
"epoch": 1.7507204610951008,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004697104200243666,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.21097383499145508,
|
|
"num_tokens": 41763629.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.257845067977906,
|
|
"epoch": 1.751200768491835,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004696932376977096,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.2163722425699234,
|
|
"num_tokens": 41774502.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.305451679229736,
|
|
"epoch": 1.7516810758885688,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004696760508508538,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.2053578093647957,
|
|
"num_tokens": 41785700.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.260090970993042,
|
|
"epoch": 1.7521613832853027,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00046965885948419814,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.20706653445959092,
|
|
"num_tokens": 41797347.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.2378082275390625,
|
|
"epoch": 1.7526416906820366,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004696416635981418,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.2088778421282768,
|
|
"num_tokens": 41810866.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.353393507003784,
|
|
"epoch": 1.7531219980787704,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000469624463193084,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.2086847737431526,
|
|
"num_tokens": 41821786.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.352453517913818,
|
|
"epoch": 1.7536023054755043,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000469607258269424,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.2078515872359276,
|
|
"num_tokens": 41833591.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.274644088745117,
|
|
"epoch": 1.7540826128722382,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004695900488275614,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.21838094741106034,
|
|
"num_tokens": 41844659.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.2514769554138185,
|
|
"epoch": 1.754562920268972,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004695728348678957,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.2122058242559433,
|
|
"num_tokens": 41856378.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.305406093597412,
|
|
"epoch": 1.755043227665706,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004695556163908265,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.20486113876104356,
|
|
"num_tokens": 41867624.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.324618196487426,
|
|
"epoch": 1.7555235350624399,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.0004695383933967536,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.21566205024719237,
|
|
"num_tokens": 41879250.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.30359263420105,
|
|
"epoch": 1.7560038424591737,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046952116588607694,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.2054525539278984,
|
|
"num_tokens": 41890713.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.321026849746704,
|
|
"epoch": 1.7564841498559076,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004695039338591963,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.20902233570814133,
|
|
"num_tokens": 41902924.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.372379398345947,
|
|
"epoch": 1.7569644572526417,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000469486697316512,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20867699831724168,
|
|
"num_tokens": 41914498.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.319398498535156,
|
|
"epoch": 1.7574447646493756,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000469469456258424,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.20919411927461623,
|
|
"num_tokens": 41925258.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.256595754623413,
|
|
"epoch": 1.7579250720461095,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004694522106853327,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.20971318930387498,
|
|
"num_tokens": 41938176.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.294081354141236,
|
|
"epoch": 1.7584053794428436,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046943496059763845,
|
|
"loss": 4.9165,
|
|
"mean_token_accuracy": 0.21901204586029052,
|
|
"num_tokens": 41949160.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.302512311935425,
|
|
"epoch": 1.7588856868395775,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046941770599574176,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.2097326323390007,
|
|
"num_tokens": 41960981.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.267141723632813,
|
|
"epoch": 1.7593659942363113,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004694004468800433,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.20992262214422225,
|
|
"num_tokens": 41971755.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.30947208404541,
|
|
"epoch": 1.7598463016330452,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004693831832509437,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.2120966747403145,
|
|
"num_tokens": 41984337.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.297647333145141,
|
|
"epoch": 1.760326609029779,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046936591510884375,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.21458773016929628,
|
|
"num_tokens": 41995648.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.278610897064209,
|
|
"epoch": 1.760806916426513,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046934864245414443,
|
|
"loss": 5.0035,
|
|
"mean_token_accuracy": 0.21797370165586472,
|
|
"num_tokens": 42006995.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.373203372955322,
|
|
"epoch": 1.7612872238232469,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046933136528724676,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.19573544561862946,
|
|
"num_tokens": 42020074.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.281209564208984,
|
|
"epoch": 1.7617675312199808,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004693140836085518,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.21615249812602996,
|
|
"num_tokens": 42032053.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.219389963150024,
|
|
"epoch": 1.7622478386167146,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046929679741846076,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.21715942323207854,
|
|
"num_tokens": 42042223.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.285732173919678,
|
|
"epoch": 1.7627281460134485,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00046927950671737505,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.21658603996038436,
|
|
"num_tokens": 42053988.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.231212759017945,
|
|
"epoch": 1.7632084534101824,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046926221150569617,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.22064896076917648,
|
|
"num_tokens": 42064451.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.296082067489624,
|
|
"epoch": 1.7636887608069163,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004692449117838255,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.20137674808502198,
|
|
"num_tokens": 42076503.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.326652908325196,
|
|
"epoch": 1.7641690682036504,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004692276075521648,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.20632155239582062,
|
|
"num_tokens": 42088341.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.273596525192261,
|
|
"epoch": 1.7646493756003843,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004692102988111158,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.21236828118562698,
|
|
"num_tokens": 42099862.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.341343069076538,
|
|
"epoch": 1.7651296829971181,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046919298556108023,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.20756177008152008,
|
|
"num_tokens": 42112117.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.363731002807617,
|
|
"epoch": 1.765609990393852,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046917566780246036,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.20858072787523269,
|
|
"num_tokens": 42123093.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.354918909072876,
|
|
"epoch": 1.7660902977905861,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00046915834553565793,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.20462724566459656,
|
|
"num_tokens": 42135266.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.417573308944702,
|
|
"epoch": 1.76657060518732,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004691410187610753,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.20598672181367875,
|
|
"num_tokens": 42145743.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.2935291767120365,
|
|
"epoch": 1.767050912584054,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046912368747911465,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.21832351833581926,
|
|
"num_tokens": 42157604.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.307654142379761,
|
|
"epoch": 1.7675312199807878,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046910635169017845,
|
|
"loss": 4.9936,
|
|
"mean_token_accuracy": 0.2160412460565567,
|
|
"num_tokens": 42168738.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.33832368850708,
|
|
"epoch": 1.7680115273775217,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004690890113946691,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.20279377996921538,
|
|
"num_tokens": 42179699.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.2979357719421385,
|
|
"epoch": 1.7684918347742555,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004690716665929893,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.20393190681934356,
|
|
"num_tokens": 42190512.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.362306404113769,
|
|
"epoch": 1.7689721421709894,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046905431728554164,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.20414434969425202,
|
|
"num_tokens": 42200996.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.26557035446167,
|
|
"epoch": 1.7694524495677233,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00046903696347272894,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.2223775401711464,
|
|
"num_tokens": 42213032.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.32272162437439,
|
|
"epoch": 1.7699327569644572,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046901960515495413,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.20360186994075774,
|
|
"num_tokens": 42224366.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.219755172729492,
|
|
"epoch": 1.770413064361191,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004690022423326202,
|
|
"loss": 4.9726,
|
|
"mean_token_accuracy": 0.2186558574438095,
|
|
"num_tokens": 42235540.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.236265468597412,
|
|
"epoch": 1.770893371757925,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004689848750061303,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.21772620379924773,
|
|
"num_tokens": 42246755.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.300216341018677,
|
|
"epoch": 1.7713736791546588,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004689675031758876,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.20702123939990996,
|
|
"num_tokens": 42259536.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.263544416427612,
|
|
"epoch": 1.771853986551393,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004689501268422954,
|
|
"loss": 5.0132,
|
|
"mean_token_accuracy": 0.209878309071064,
|
|
"num_tokens": 42270813.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.4813127517700195,
|
|
"epoch": 1.7723342939481268,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046893274600575725,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.20322110652923583,
|
|
"num_tokens": 42281953.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.387529993057251,
|
|
"epoch": 1.7728146013448607,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004689153606666765,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.20064026564359666,
|
|
"num_tokens": 42294041.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.287707901000976,
|
|
"epoch": 1.7732949087415946,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000468897970825457,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.21147090047597886,
|
|
"num_tokens": 42305812.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.2912328243255615,
|
|
"epoch": 1.7737752161383287,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046888057648250233,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.2169363185763359,
|
|
"num_tokens": 42317585.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.334371423721313,
|
|
"epoch": 1.7742555235350626,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004688631776382164,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.20652769953012468,
|
|
"num_tokens": 42328723.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.2795311450958256,
|
|
"epoch": 1.7747358309317964,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046884577429300305,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.21517701894044877,
|
|
"num_tokens": 42340741.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.279333257675171,
|
|
"epoch": 1.7752161383285303,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004688283664472665,
|
|
"loss": 5.0807,
|
|
"mean_token_accuracy": 0.2126216173171997,
|
|
"num_tokens": 42351504.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.320878887176514,
|
|
"epoch": 1.7756964457252642,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046881095410141084,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.2124560445547104,
|
|
"num_tokens": 42362920.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.308727264404297,
|
|
"epoch": 1.776176753121998,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046879353725584036,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.21063063889741898,
|
|
"num_tokens": 42374523.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.354165363311767,
|
|
"epoch": 1.776657060518732,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046877611591095923,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.21025790572166442,
|
|
"num_tokens": 42384988.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.204031229019165,
|
|
"epoch": 1.7771373679154658,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046875869006717224,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.2164252519607544,
|
|
"num_tokens": 42396503.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.368519592285156,
|
|
"epoch": 1.7776176753121997,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046874125972488375,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.20592961609363555,
|
|
"num_tokens": 42406877.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.3162883758544925,
|
|
"epoch": 1.7780979827089336,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046872382488449853,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.21315557956695558,
|
|
"num_tokens": 42418010.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.305571365356445,
|
|
"epoch": 1.7785782901056675,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046870638554642133,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.21155026704072952,
|
|
"num_tokens": 42429056.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.232552242279053,
|
|
"epoch": 1.7790585975024016,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046868894171105704,
|
|
"loss": 5.006,
|
|
"mean_token_accuracy": 0.21324759274721145,
|
|
"num_tokens": 42442294.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.316347742080689,
|
|
"epoch": 1.7795389048991355,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004686714933788107,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.20394423305988313,
|
|
"num_tokens": 42454064.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.3199341773986815,
|
|
"epoch": 1.7800192122958693,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004686540405500873,
|
|
"loss": 5.0833,
|
|
"mean_token_accuracy": 0.21551483273506164,
|
|
"num_tokens": 42465289.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.270934677124023,
|
|
"epoch": 1.7804995196926032,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004686365832252922,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.21336443722248077,
|
|
"num_tokens": 42476662.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.309093427658081,
|
|
"epoch": 1.7809798270893373,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046861912140483056,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.21323847025632858,
|
|
"num_tokens": 42486893.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.278469038009644,
|
|
"epoch": 1.7814601344860712,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046860165508910787,
|
|
"loss": 5.0116,
|
|
"mean_token_accuracy": 0.21494197100400925,
|
|
"num_tokens": 42498202.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.186483907699585,
|
|
"epoch": 1.781940441882805,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004685841842785296,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.21994325816631316,
|
|
"num_tokens": 42509378.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.2774481773376465,
|
|
"epoch": 1.782420749279539,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004685667089735014,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.2117509886622429,
|
|
"num_tokens": 42519955.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.356520748138427,
|
|
"epoch": 1.7829010566762729,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046854922917442907,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.20462783724069594,
|
|
"num_tokens": 42531896.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.3385731220245365,
|
|
"epoch": 1.7833813640730067,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004685317448817182,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.21622913479804992,
|
|
"num_tokens": 42542123.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.310177183151245,
|
|
"epoch": 1.7838616714697406,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004685142560957751,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.20571675151586533,
|
|
"num_tokens": 42554034.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.24381275177002,
|
|
"epoch": 1.7843419788664745,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004684967628170054,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.21439653933048247,
|
|
"num_tokens": 42564532.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.239025449752807,
|
|
"epoch": 1.7848222862632084,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046847926504581553,
|
|
"loss": 4.9871,
|
|
"mean_token_accuracy": 0.21178268641233444,
|
|
"num_tokens": 42576864.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.208342838287353,
|
|
"epoch": 1.7853025936599423,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004684617627826116,
|
|
"loss": 4.9845,
|
|
"mean_token_accuracy": 0.2146550327539444,
|
|
"num_tokens": 42588571.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.373462772369384,
|
|
"epoch": 1.7857829010566761,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004684442560278001,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.20294515043497086,
|
|
"num_tokens": 42600912.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.34680027961731,
|
|
"epoch": 1.78626320845341,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046842674478178727,
|
|
"loss": 5.0132,
|
|
"mean_token_accuracy": 0.20976462364196777,
|
|
"num_tokens": 42612929.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.288423013687134,
|
|
"epoch": 1.7867435158501441,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004684092290449798,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.21292086243629454,
|
|
"num_tokens": 42623688.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.348728275299072,
|
|
"epoch": 1.787223823246878,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004683917088177844,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.19969099909067153,
|
|
"num_tokens": 42635773.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.363118600845337,
|
|
"epoch": 1.7877041306436119,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004683741841006077,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.20820394158363342,
|
|
"num_tokens": 42647210.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.2957135200500485,
|
|
"epoch": 1.7881844380403458,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004683566548938567,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.21436642110347748,
|
|
"num_tokens": 42658029.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.281511688232422,
|
|
"epoch": 1.7886647454370799,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004683391211979383,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.21196065098047256,
|
|
"num_tokens": 42669327.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.34220142364502,
|
|
"epoch": 1.7891450528338138,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004683215830132597,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.2188802629709244,
|
|
"num_tokens": 42679794.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.242846202850342,
|
|
"epoch": 1.7896253602305476,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046830404034022786,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.2180158168077469,
|
|
"num_tokens": 42689838.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.303073787689209,
|
|
"epoch": 1.7901056676272815,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004682864931792502,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.2092784285545349,
|
|
"num_tokens": 42700935.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.39800910949707,
|
|
"epoch": 1.7905859750240154,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004682689415307342,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.20201542228460312,
|
|
"num_tokens": 42712533.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.321328973770141,
|
|
"epoch": 1.7910662824207493,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004682513853950872,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.21474273651838302,
|
|
"num_tokens": 42723604.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.297608852386475,
|
|
"epoch": 1.7915465898174832,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000468233824772717,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.2119303196668625,
|
|
"num_tokens": 42735957.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.35692720413208,
|
|
"epoch": 1.792026897214217,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000468216259664031,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.2056288316845894,
|
|
"num_tokens": 42747287.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.266495561599731,
|
|
"epoch": 1.792507204610951,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00046819869006943727,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.21188050806522368,
|
|
"num_tokens": 42759270.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.258999061584473,
|
|
"epoch": 1.7929875120076848,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004681811159893436,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.2143746003508568,
|
|
"num_tokens": 42771955.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.410590505599975,
|
|
"epoch": 1.7934678194044187,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046816353742415814,
|
|
"loss": 5.1672,
|
|
"mean_token_accuracy": 0.20304094552993773,
|
|
"num_tokens": 42784610.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.318156623840332,
|
|
"epoch": 1.7939481268011528,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046814595437428885,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.2163353979587555,
|
|
"num_tokens": 42795221.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.223325252532959,
|
|
"epoch": 1.7944284341978867,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000468128366840144,
|
|
"loss": 5.034,
|
|
"mean_token_accuracy": 0.21059756129980087,
|
|
"num_tokens": 42807475.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.2987884998321535,
|
|
"epoch": 1.7949087415946205,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000468110774822132,
|
|
"loss": 5.037,
|
|
"mean_token_accuracy": 0.2065739005804062,
|
|
"num_tokens": 42819193.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.371966457366943,
|
|
"epoch": 1.7953890489913544,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004680931783206612,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.20849183946847916,
|
|
"num_tokens": 42831267.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.360419225692749,
|
|
"epoch": 1.7958693563880885,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046807557733614014,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.21023551970720292,
|
|
"num_tokens": 42843066.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.2446677684783936,
|
|
"epoch": 1.7963496637848224,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00046805797186897757,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.2143852174282074,
|
|
"num_tokens": 42854630.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.340395784378051,
|
|
"epoch": 1.7968299711815563,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046804036191958206,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.20709908455610276,
|
|
"num_tokens": 42865986.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.403108358383179,
|
|
"epoch": 1.7973102785782902,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00046802274748836267,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.20781438499689103,
|
|
"num_tokens": 42877533.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.2885088443756105,
|
|
"epoch": 1.797790585975024,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004680051285757281,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.21662292629480362,
|
|
"num_tokens": 42889114.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.326693344116211,
|
|
"epoch": 1.798270893371758,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004679875051820877,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.19961099326610565,
|
|
"num_tokens": 42899483.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.28899655342102,
|
|
"epoch": 1.7987512007684918,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004679698773078503,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.21785212457180023,
|
|
"num_tokens": 42910267.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.251875734329223,
|
|
"epoch": 1.7992315081652257,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046795224495342554,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.21858458817005158,
|
|
"num_tokens": 42922440.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.243092632293701,
|
|
"epoch": 1.7997118155619596,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00046793460811922255,
|
|
"loss": 4.9838,
|
|
"mean_token_accuracy": 0.21523887515068055,
|
|
"num_tokens": 42933967.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.32867693901062,
|
|
"epoch": 1.8001921229586935,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00046791696680565075,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.21738191246986388,
|
|
"num_tokens": 42945049.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.355920314788818,
|
|
"epoch": 1.8006724303554273,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046789932101312003,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.20757005959749222,
|
|
"num_tokens": 42956062.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.332795524597168,
|
|
"epoch": 1.8011527377521612,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004678816707420397,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.207767117023468,
|
|
"num_tokens": 42967687.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.359020185470581,
|
|
"epoch": 1.8016330451488953,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004678640159928198,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.19949206411838533,
|
|
"num_tokens": 42979916.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.3449499130249025,
|
|
"epoch": 1.8021133525456292,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004678463567658701,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.2088497132062912,
|
|
"num_tokens": 42991639.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.32305383682251,
|
|
"epoch": 1.802593659942363,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004678286930616006,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.21507826149463655,
|
|
"num_tokens": 43001843.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.244558238983155,
|
|
"epoch": 1.803073967339097,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004678110248804215,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.20870622992515564,
|
|
"num_tokens": 43013249.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.293065071105957,
|
|
"epoch": 1.803554274735831,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046779335222274293,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.2141919657588005,
|
|
"num_tokens": 43025867.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.339227676391602,
|
|
"epoch": 1.804034582132565,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046777567508897515,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.20295823663473128,
|
|
"num_tokens": 43037530.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.306135082244873,
|
|
"epoch": 1.8045148895292988,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046775799347952864,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.2097504824399948,
|
|
"num_tokens": 43048675.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.342991638183594,
|
|
"epoch": 1.8049951969260327,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004677403073948139,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.21053718775510788,
|
|
"num_tokens": 43059592.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.206336641311646,
|
|
"epoch": 1.8054755043227666,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004677226168352416,
|
|
"loss": 4.9258,
|
|
"mean_token_accuracy": 0.21257364451885224,
|
|
"num_tokens": 43071755.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.315927362442016,
|
|
"epoch": 1.8059558117195005,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004677049218012223,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.21041785031557084,
|
|
"num_tokens": 43081801.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.295944547653198,
|
|
"epoch": 1.8064361191162344,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000467687222293167,
|
|
"loss": 5.0048,
|
|
"mean_token_accuracy": 0.21535798013210297,
|
|
"num_tokens": 43094160.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.273276948928833,
|
|
"epoch": 1.8069164265129682,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004676695183114866,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.21261857002973555,
|
|
"num_tokens": 43106082.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.311666440963745,
|
|
"epoch": 1.8073967339097021,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000467651809856592,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.20915350914001465,
|
|
"num_tokens": 43117215.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.385028553009033,
|
|
"epoch": 1.807877041306436,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046763409692889446,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.19711381644010545,
|
|
"num_tokens": 43127858.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.347618865966797,
|
|
"epoch": 1.8083573487031699,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046761637952880516,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.2102242037653923,
|
|
"num_tokens": 43139952.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.274471139907837,
|
|
"epoch": 1.808837656099904,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046759865765673555,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.21754143089056016,
|
|
"num_tokens": 43150900.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.272740411758423,
|
|
"epoch": 1.8093179634966379,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000467580931313097,
|
|
"loss": 5.0104,
|
|
"mean_token_accuracy": 0.21619114875793458,
|
|
"num_tokens": 43163199.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.288625240325928,
|
|
"epoch": 1.8097982708933718,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046756320049830106,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.21029435098171234,
|
|
"num_tokens": 43174147.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.2501262664794925,
|
|
"epoch": 1.8102785782901056,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004675454652127594,
|
|
"loss": 4.9837,
|
|
"mean_token_accuracy": 0.21148480772972106,
|
|
"num_tokens": 43186191.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.383968782424927,
|
|
"epoch": 1.8107588856868397,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046752772545688377,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.20517950803041457,
|
|
"num_tokens": 43197541.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.384000205993653,
|
|
"epoch": 1.8112391930835736,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004675099812310861,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.20675036013126374,
|
|
"num_tokens": 43208792.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.349514722824097,
|
|
"epoch": 1.8117195004803075,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004674922325357782,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.20453467965126038,
|
|
"num_tokens": 43219914.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.219752979278565,
|
|
"epoch": 1.8121998078770414,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046747447937137235,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.21905779987573623,
|
|
"num_tokens": 43232179.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.29947943687439,
|
|
"epoch": 1.8126801152737753,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046745672173828057,
|
|
"loss": 5.008,
|
|
"mean_token_accuracy": 0.20601184219121932,
|
|
"num_tokens": 43243196.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.3494219303131105,
|
|
"epoch": 1.8131604226705091,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004674389596369151,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.2049070864915848,
|
|
"num_tokens": 43255573.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.280105495452881,
|
|
"epoch": 1.813640730067243,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00046742119306768855,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.21012551635503768,
|
|
"num_tokens": 43267679.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.3683164596557615,
|
|
"epoch": 1.814121037463977,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004674034220310132,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.20022495090961456,
|
|
"num_tokens": 43278857.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.335575914382934,
|
|
"epoch": 1.8146013448607108,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046738564652730176,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.21618562042713166,
|
|
"num_tokens": 43291099.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.298767852783203,
|
|
"epoch": 1.8150816522574447,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004673678665569669,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.20872244983911514,
|
|
"num_tokens": 43302863.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.268329048156739,
|
|
"epoch": 1.8155619596541785,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004673500821204213,
|
|
"loss": 5.0012,
|
|
"mean_token_accuracy": 0.2163540855050087,
|
|
"num_tokens": 43314673.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.280411148071289,
|
|
"epoch": 1.8160422670509124,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000467332293218078,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.21632237285375594,
|
|
"num_tokens": 43325927.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.286722993850708,
|
|
"epoch": 1.8165225744476465,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046731449985035,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.2155402883887291,
|
|
"num_tokens": 43337615.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.354308366775513,
|
|
"epoch": 1.8170028818443804,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00046729670201765036,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.2113124206662178,
|
|
"num_tokens": 43349195.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.369007396697998,
|
|
"epoch": 1.8174831892411143,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046727889972039227,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.21113220751285552,
|
|
"num_tokens": 43361274.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.307171249389649,
|
|
"epoch": 1.8179634966378482,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046726109295898904,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.21453823298215866,
|
|
"num_tokens": 43372843.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.275585174560547,
|
|
"epoch": 1.8184438040345823,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004672432817338542,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.21442022323608398,
|
|
"num_tokens": 43383492.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.3099559307098385,
|
|
"epoch": 1.8189241114313162,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046722546604540115,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.20575998425483705,
|
|
"num_tokens": 43395669.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.274599266052246,
|
|
"epoch": 1.81940441882805,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004672076458940436,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.21392346620559693,
|
|
"num_tokens": 43407340.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.276431369781494,
|
|
"epoch": 1.819884726224784,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046718982128019534,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.21228488981723787,
|
|
"num_tokens": 43418607.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.391432666778565,
|
|
"epoch": 1.8203650336215178,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046717199220427003,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.20291971713304519,
|
|
"num_tokens": 43429286.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.256087970733643,
|
|
"epoch": 1.8208453410182517,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046715415866668163,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.209514319896698,
|
|
"num_tokens": 43440794.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.300838375091553,
|
|
"epoch": 1.8213256484149856,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004671363206678443,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.20918649435043335,
|
|
"num_tokens": 43452184.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.262285423278809,
|
|
"epoch": 1.8218059558117194,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046711847820817215,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.21202387660741806,
|
|
"num_tokens": 43463361.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.290587759017944,
|
|
"epoch": 1.8222862632084533,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004671006312880794,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.20747705399990082,
|
|
"num_tokens": 43474802.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.303598403930664,
|
|
"epoch": 1.8227665706051872,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004670827799079805,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.21293377876281738,
|
|
"num_tokens": 43486962.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.345356082916259,
|
|
"epoch": 1.823246878001921,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046706492406828966,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.2134587436914444,
|
|
"num_tokens": 43498761.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.294065713882446,
|
|
"epoch": 1.8237271853986552,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004670470637694217,
|
|
"loss": 5.1013,
|
|
"mean_token_accuracy": 0.21060515493154525,
|
|
"num_tokens": 43511294.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.311513805389405,
|
|
"epoch": 1.824207492795389,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004670291990117912,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.21674739718437194,
|
|
"num_tokens": 43522858.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.345806312561035,
|
|
"epoch": 1.824687800192123,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004670113297958128,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.2094866156578064,
|
|
"num_tokens": 43533453.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.296781826019287,
|
|
"epoch": 1.8251681075888568,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046699345612190155,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.22239327281713486,
|
|
"num_tokens": 43543889.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.217564487457276,
|
|
"epoch": 1.825648414985591,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046697557799047233,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.22035169303417207,
|
|
"num_tokens": 43554815.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.241135168075561,
|
|
"epoch": 1.8261287223823248,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004669576954019403,
|
|
"loss": 4.9086,
|
|
"mean_token_accuracy": 0.21708057224750518,
|
|
"num_tokens": 43565258.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.322254657745361,
|
|
"epoch": 1.8266090297790587,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004669398083567205,
|
|
"loss": 5.0481,
|
|
"mean_token_accuracy": 0.2081855282187462,
|
|
"num_tokens": 43576710.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.298232746124268,
|
|
"epoch": 1.8270893371757926,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004669219168552284,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.21333639621734618,
|
|
"num_tokens": 43587590.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.287563753128052,
|
|
"epoch": 1.8275696445725265,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046690402089787916,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.2084555745124817,
|
|
"num_tokens": 43599675.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.2459495067596436,
|
|
"epoch": 1.8280499519692603,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004668861204850884,
|
|
"loss": 4.9192,
|
|
"mean_token_accuracy": 0.2254490688443184,
|
|
"num_tokens": 43612369.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.2684039115905765,
|
|
"epoch": 1.8285302593659942,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00046686821561727176,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.21850524544715882,
|
|
"num_tokens": 43624807.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.2569328308105465,
|
|
"epoch": 1.829010566762728,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004668503062948449,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.2160832017660141,
|
|
"num_tokens": 43635389.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.318116998672485,
|
|
"epoch": 1.829490874159462,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004668323925182236,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.21130442321300508,
|
|
"num_tokens": 43646807.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.323995447158813,
|
|
"epoch": 1.8299711815561959,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046681447428782377,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.21017789393663405,
|
|
"num_tokens": 43657910.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.243077564239502,
|
|
"epoch": 1.8304514889529298,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004667965516040613,
|
|
"loss": 5.012,
|
|
"mean_token_accuracy": 0.21675102412700653,
|
|
"num_tokens": 43669376.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.235134744644165,
|
|
"epoch": 1.8309317963496636,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004667786244673526,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.2186190217733383,
|
|
"num_tokens": 43681702.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.363132286071777,
|
|
"epoch": 1.8314121037463977,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046676069287811365,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20963902175426483,
|
|
"num_tokens": 43694795.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.394192934036255,
|
|
"epoch": 1.8318924111431316,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004667427568367607,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.20971607714891433,
|
|
"num_tokens": 43707197.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.382369613647461,
|
|
"epoch": 1.8323727185398655,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046672481634371047,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.203464874625206,
|
|
"num_tokens": 43719066.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.322706508636474,
|
|
"epoch": 1.8328530259365994,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046670687139937925,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.2131766766309738,
|
|
"num_tokens": 43731080.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.309553813934326,
|
|
"epoch": 1.8333333333333335,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004666889220041837,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.2093015804886818,
|
|
"num_tokens": 43743048.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.289741849899292,
|
|
"epoch": 1.8338136407300674,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00046667096815854056,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.21031393557786943,
|
|
"num_tokens": 43754701.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.3173316478729244,
|
|
"epoch": 1.8342939481268012,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004666530098628667,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.2106448382139206,
|
|
"num_tokens": 43765696.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.328948068618774,
|
|
"epoch": 1.8347742555235351,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004666350471175791,
|
|
"loss": 5.1509,
|
|
"mean_token_accuracy": 0.20184383690357208,
|
|
"num_tokens": 43777162.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.336687850952148,
|
|
"epoch": 1.835254562920269,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004666170799230947,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.21024733036756516,
|
|
"num_tokens": 43789340.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.259295415878296,
|
|
"epoch": 1.8357348703170029,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004665991082798307,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.22434320002794267,
|
|
"num_tokens": 43800098.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.2719474792480465,
|
|
"epoch": 1.8362151777137368,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004665811321882043,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.21575791388750076,
|
|
"num_tokens": 43811403.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.3646081447601315,
|
|
"epoch": 1.8366954851104706,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046656315164863297,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.21675563603639603,
|
|
"num_tokens": 43821946.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.204444217681885,
|
|
"epoch": 1.8371757925072045,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046654516666153403,
|
|
"loss": 4.9662,
|
|
"mean_token_accuracy": 0.2134495720267296,
|
|
"num_tokens": 43832638.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.2889386177062985,
|
|
"epoch": 1.8376560999039384,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004665271772273251,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.21410137563943862,
|
|
"num_tokens": 43843616.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.3462347984313965,
|
|
"epoch": 1.8381364073006723,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004665091833464239,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.21117831766605377,
|
|
"num_tokens": 43854680.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.270117998123169,
|
|
"epoch": 1.8386167146974062,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046649118501924805,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.2117802917957306,
|
|
"num_tokens": 43866683.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.312960147857666,
|
|
"epoch": 1.8390970220941403,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004664731822462154,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.20460806041955948,
|
|
"num_tokens": 43878080.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.345739126205444,
|
|
"epoch": 1.8395773294908742,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046645517502774415,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.21229581385850907,
|
|
"num_tokens": 43888633.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.385975980758667,
|
|
"epoch": 1.840057636887608,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046643716336425224,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.2096552923321724,
|
|
"num_tokens": 43899678.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.319149541854858,
|
|
"epoch": 1.8405379442843421,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004664191472561578,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.21425844877958297,
|
|
"num_tokens": 43910744.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.316144800186157,
|
|
"epoch": 1.841018251681076,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004664011267038792,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.21197121888399123,
|
|
"num_tokens": 43922467.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.287255716323853,
|
|
"epoch": 1.84149855907781,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046638310170783476,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.221212500333786,
|
|
"num_tokens": 43934919.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.304694938659668,
|
|
"epoch": 1.8419788664745438,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000466365072268443,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.21203170120716094,
|
|
"num_tokens": 43947737.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.2380414485931395,
|
|
"epoch": 1.8424591738712777,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004663470383861225,
|
|
"loss": 4.9876,
|
|
"mean_token_accuracy": 0.21742728650569915,
|
|
"num_tokens": 43959656.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.2955094337463375,
|
|
"epoch": 1.8429394812680115,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000466329000061292,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.21233586817979813,
|
|
"num_tokens": 43970732.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.297198104858398,
|
|
"epoch": 1.8434197886647454,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004663109572943702,
|
|
"loss": 5.0227,
|
|
"mean_token_accuracy": 0.2095019370317459,
|
|
"num_tokens": 43982369.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.380299854278564,
|
|
"epoch": 1.8439000960614793,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000466292910085776,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.21002495139837266,
|
|
"num_tokens": 43993751.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.246116638183594,
|
|
"epoch": 1.8443804034582132,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046627485843592854,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.20889011919498443,
|
|
"num_tokens": 44005021.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.258654308319092,
|
|
"epoch": 1.844860710854947,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046625680234524674,
|
|
"loss": 5.0059,
|
|
"mean_token_accuracy": 0.2132275477051735,
|
|
"num_tokens": 44015571.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.3238959312438965,
|
|
"epoch": 1.845341018251681,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046623874181414993,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.2117968887090683,
|
|
"num_tokens": 44026363.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.278289318084717,
|
|
"epoch": 1.8458213256484148,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004662206768430574,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.22274608463048934,
|
|
"num_tokens": 44038042.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.33193678855896,
|
|
"epoch": 1.846301633045149,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004662026074323886,
|
|
"loss": 5.0593,
|
|
"mean_token_accuracy": 0.20317239165306092,
|
|
"num_tokens": 44049086.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.342093563079834,
|
|
"epoch": 1.8467819404418828,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046618453358256303,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.21497215032577516,
|
|
"num_tokens": 44060816.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.2276939868927,
|
|
"epoch": 1.8472622478386167,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046616645529400026,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.2187034383416176,
|
|
"num_tokens": 44071877.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.291880798339844,
|
|
"epoch": 1.8477425552353506,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004661483725671201,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.2102872386574745,
|
|
"num_tokens": 44082618.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.29580397605896,
|
|
"epoch": 1.8482228626320847,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046613028540234226,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.21812890470027924,
|
|
"num_tokens": 44093411.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.1978058338165285,
|
|
"epoch": 1.8487031700288186,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004661121938000867,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.22793837040662765,
|
|
"num_tokens": 44103595.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.249513483047485,
|
|
"epoch": 1.8491834774255524,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004660940977607736,
|
|
"loss": 5.0162,
|
|
"mean_token_accuracy": 0.22166648507118225,
|
|
"num_tokens": 44114740.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.233553457260132,
|
|
"epoch": 1.8496637848222863,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046607599728482285,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.21845000386238098,
|
|
"num_tokens": 44125415.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.222881650924682,
|
|
"epoch": 1.8501440922190202,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046605789237265496,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.21561665385961531,
|
|
"num_tokens": 44137399.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.261289024353028,
|
|
"epoch": 1.850624399615754,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046603978302469,
|
|
"loss": 4.9475,
|
|
"mean_token_accuracy": 0.21484656780958175,
|
|
"num_tokens": 44148354.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.251283073425293,
|
|
"epoch": 1.851104707012488,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004660216692413486,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.21757749021053313,
|
|
"num_tokens": 44160496.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.312267398834228,
|
|
"epoch": 1.8515850144092219,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004660035510230513,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.21237989962100984,
|
|
"num_tokens": 44171832.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.333335113525391,
|
|
"epoch": 1.8520653218059557,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004659854283702186,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.20841265022754668,
|
|
"num_tokens": 44182850.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.280579471588135,
|
|
"epoch": 1.8525456292026896,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004659673012832715,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.2112398400902748,
|
|
"num_tokens": 44194343.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.383692073822021,
|
|
"epoch": 1.8530259365994235,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004659491697626306,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.20492777824401856,
|
|
"num_tokens": 44206294.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.319229936599731,
|
|
"epoch": 1.8535062439961574,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046593103380871705,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.21396999508142472,
|
|
"num_tokens": 44218576.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.2466192722320555,
|
|
"epoch": 1.8539865513928915,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046591289342195184,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.2100767344236374,
|
|
"num_tokens": 44230480.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.268080615997315,
|
|
"epoch": 1.8544668587896254,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004658947486027562,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.2172798454761505,
|
|
"num_tokens": 44240907.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.289157581329346,
|
|
"epoch": 1.8549471661863592,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046587659935155124,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.20672256648540496,
|
|
"num_tokens": 44251469.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.42198076248169,
|
|
"epoch": 1.8554274735830933,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046585844566875845,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.20549213737249375,
|
|
"num_tokens": 44263875.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.336321687698364,
|
|
"epoch": 1.8559077809798272,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004658402875547993,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.20594169795513154,
|
|
"num_tokens": 44276163.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.257051467895508,
|
|
"epoch": 1.856388088376561,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046582212501009533,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.21042819768190385,
|
|
"num_tokens": 44287985.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.330567264556885,
|
|
"epoch": 1.856868395773295,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046580395803506825,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.2066018834710121,
|
|
"num_tokens": 44299360.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.340612173080444,
|
|
"epoch": 1.8573487031700289,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004657857866301399,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.22131674736738205,
|
|
"num_tokens": 44310459.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.3823638439178465,
|
|
"epoch": 1.8578290105667628,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00046576761079573204,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.20457759350538254,
|
|
"num_tokens": 44321832.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.319523715972901,
|
|
"epoch": 1.8583093179634966,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004657494305322667,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.2121136873960495,
|
|
"num_tokens": 44332829.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.329847192764282,
|
|
"epoch": 1.8587896253602305,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004657312458401661,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.20716656893491744,
|
|
"num_tokens": 44344321.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.394326162338257,
|
|
"epoch": 1.8592699327569644,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004657130567198522,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.20058058053255082,
|
|
"num_tokens": 44357183.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.352883338928223,
|
|
"epoch": 1.8597502401536983,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00046569486317174746,
|
|
"loss": 5.0907,
|
|
"mean_token_accuracy": 0.21475301682949066,
|
|
"num_tokens": 44367118.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.39706654548645,
|
|
"epoch": 1.8602305475504322,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004656766651962742,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.20854970067739487,
|
|
"num_tokens": 44377699.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.314235067367553,
|
|
"epoch": 1.860710854947166,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004656584627938551,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.20115735977888108,
|
|
"num_tokens": 44389457.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.308538866043091,
|
|
"epoch": 1.8611911623439001,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046564025596491254,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.2154830664396286,
|
|
"num_tokens": 44400140.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.245579195022583,
|
|
"epoch": 1.861671469740634,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004656220447098693,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.2269770994782448,
|
|
"num_tokens": 44411088.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.2759928703308105,
|
|
"epoch": 1.862151777137368,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004656038290291483,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.2118873193860054,
|
|
"num_tokens": 44422515.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.226703214645386,
|
|
"epoch": 1.8626320845341018,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004655856089231723,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.2150784030556679,
|
|
"num_tokens": 44433711.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.353952836990357,
|
|
"epoch": 1.8631123919308359,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004655673843923644,
|
|
"loss": 5.0815,
|
|
"mean_token_accuracy": 0.21202225983142853,
|
|
"num_tokens": 44446157.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.396558237075806,
|
|
"epoch": 1.8635926993275698,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004655491554371477,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.20286007821559907,
|
|
"num_tokens": 44457506.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.329527139663696,
|
|
"epoch": 1.8640730067243036,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046553092205794543,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.20376235842704774,
|
|
"num_tokens": 44469572.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.311488914489746,
|
|
"epoch": 1.8645533141210375,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046551268425518096,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.21093759834766387,
|
|
"num_tokens": 44481932.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.2758067607879635,
|
|
"epoch": 1.8650336215177714,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004654944420292776,
|
|
"loss": 4.9648,
|
|
"mean_token_accuracy": 0.21709224581718445,
|
|
"num_tokens": 44493081.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.300523900985718,
|
|
"epoch": 1.8655139289145053,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000465476195380659,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.21586766242980956,
|
|
"num_tokens": 44503919.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.272089719772339,
|
|
"epoch": 1.8659942363112392,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004654579443097487,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.21725130528211595,
|
|
"num_tokens": 44515493.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.37538514137268,
|
|
"epoch": 1.866474543707973,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004654396888169705,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.20654360949993134,
|
|
"num_tokens": 44527432.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.281630134582519,
|
|
"epoch": 1.866954851104707,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046542142890274816,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.211539426445961,
|
|
"num_tokens": 44537634.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.23915843963623,
|
|
"epoch": 1.8674351585014408,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004654031645675057,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.21487823277711868,
|
|
"num_tokens": 44549856.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.275540733337403,
|
|
"epoch": 1.8679154658981747,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004653848958116672,
|
|
"loss": 4.9872,
|
|
"mean_token_accuracy": 0.21462760120630264,
|
|
"num_tokens": 44563214.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.254242753982544,
|
|
"epoch": 1.8683957732949086,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046536662263565667,
|
|
"loss": 5.0029,
|
|
"mean_token_accuracy": 0.20832280665636063,
|
|
"num_tokens": 44572982.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.271893405914307,
|
|
"epoch": 1.8688760806916427,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004653483450398985,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.2224487766623497,
|
|
"num_tokens": 44583664.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.241083383560181,
|
|
"epoch": 1.8693563880883766,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046533006302481694,
|
|
"loss": 4.8771,
|
|
"mean_token_accuracy": 0.22087477445602416,
|
|
"num_tokens": 44594987.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.270383834838867,
|
|
"epoch": 1.8698366954851104,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004653117765908365,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.210374316573143,
|
|
"num_tokens": 44607123.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.313928413391113,
|
|
"epoch": 1.8703170028818443,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004652934857383816,
|
|
"loss": 4.9817,
|
|
"mean_token_accuracy": 0.21184581518173218,
|
|
"num_tokens": 44618736.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.237531948089599,
|
|
"epoch": 1.8707973102785784,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004652751904678772,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.2204627051949501,
|
|
"num_tokens": 44630681.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.27205810546875,
|
|
"epoch": 1.8712776176753123,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046525689077974775,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.21493995636701585,
|
|
"num_tokens": 44641641.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.25797028541565,
|
|
"epoch": 1.8717579250720462,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046523858667441834,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.21460986137390137,
|
|
"num_tokens": 44652489.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.305598592758178,
|
|
"epoch": 1.87223823246878,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004652202781523138,
|
|
"loss": 5.0739,
|
|
"mean_token_accuracy": 0.2093808025121689,
|
|
"num_tokens": 44665659.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.316447305679321,
|
|
"epoch": 1.872718539865514,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004652019652138592,
|
|
"loss": 4.9756,
|
|
"mean_token_accuracy": 0.21787947714328765,
|
|
"num_tokens": 44677300.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.283531284332275,
|
|
"epoch": 1.8731988472622478,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004651836478594798,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.2051348641514778,
|
|
"num_tokens": 44690084.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.257456541061401,
|
|
"epoch": 1.8736791546589817,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004651653260896008,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.22100395262241362,
|
|
"num_tokens": 44701208.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.381862783432007,
|
|
"epoch": 1.8741594620557156,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046514699990464763,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.2041815459728241,
|
|
"num_tokens": 44713546.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.452500629425049,
|
|
"epoch": 1.8746397694524495,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004651286693050458,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.1911044403910637,
|
|
"num_tokens": 44724802.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.320990467071534,
|
|
"epoch": 1.8751200768491834,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004651103342912207,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.2119123473763466,
|
|
"num_tokens": 44736625.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.252282905578613,
|
|
"epoch": 1.8756003842459172,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046509199486359824,
|
|
"loss": 5.0218,
|
|
"mean_token_accuracy": 0.2001339390873909,
|
|
"num_tokens": 44750451.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.260472965240479,
|
|
"epoch": 1.8760806916426513,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046507365102260403,
|
|
"loss": 5.0323,
|
|
"mean_token_accuracy": 0.21169745475053786,
|
|
"num_tokens": 44762043.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.366578483581543,
|
|
"epoch": 1.8765609990393852,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046505530276866417,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.20900458693504334,
|
|
"num_tokens": 44774329.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.361866283416748,
|
|
"epoch": 1.877041306436119,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046503695010220443,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.21322084069252015,
|
|
"num_tokens": 44786352.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.24550838470459,
|
|
"epoch": 1.877521613832853,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000465018593023651,
|
|
"loss": 4.8658,
|
|
"mean_token_accuracy": 0.22650884985923767,
|
|
"num_tokens": 44796829.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.373003244400024,
|
|
"epoch": 1.878001921229587,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004650002315334302,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.20967071652412414,
|
|
"num_tokens": 44808900.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.263217115402222,
|
|
"epoch": 1.878482228626321,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000464981865631968,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.21893709450960158,
|
|
"num_tokens": 44820638.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.220929527282715,
|
|
"epoch": 1.8789625360230549,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004649634953196912,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.216234090924263,
|
|
"num_tokens": 44833370.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.235432863235474,
|
|
"epoch": 1.8794428434197887,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046494512059702605,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.21144747883081436,
|
|
"num_tokens": 44844291.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.271677732467651,
|
|
"epoch": 1.8799231508165226,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004649267414643992,
|
|
"loss": 4.9768,
|
|
"mean_token_accuracy": 0.21793173551559447,
|
|
"num_tokens": 44855303.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.234027528762818,
|
|
"epoch": 1.8804034582132565,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004649083579222374,
|
|
"loss": 4.9165,
|
|
"mean_token_accuracy": 0.2168656751513481,
|
|
"num_tokens": 44866593.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.242999076843262,
|
|
"epoch": 1.8808837656099904,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046488996997096744,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.21799572110176085,
|
|
"num_tokens": 44879124.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.277993822097779,
|
|
"epoch": 1.8813640730067243,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004648715776110162,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.2272763356566429,
|
|
"num_tokens": 44889942.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.223872089385987,
|
|
"epoch": 1.8818443804034581,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004648531808428108,
|
|
"loss": 4.9532,
|
|
"mean_token_accuracy": 0.22176636010408401,
|
|
"num_tokens": 44901002.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.329809474945068,
|
|
"epoch": 1.882324687800192,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004648347796667782,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.20560958683490754,
|
|
"num_tokens": 44913495.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.300788545608521,
|
|
"epoch": 1.882804995196926,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004648163740833458,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.20987547039985657,
|
|
"num_tokens": 44924624.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.314574480056763,
|
|
"epoch": 1.8832853025936598,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046479796409294076,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.2129050686955452,
|
|
"num_tokens": 44935539.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.258442449569702,
|
|
"epoch": 1.8837656099903939,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004647795496959907,
|
|
"loss": 4.9695,
|
|
"mean_token_accuracy": 0.22378882616758347,
|
|
"num_tokens": 44945979.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.2290033340454105,
|
|
"epoch": 1.8842459173871278,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046476113089292286,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.21186195313930511,
|
|
"num_tokens": 44958294.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.33666501045227,
|
|
"epoch": 1.8847262247838616,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004647427076841651,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.2049453616142273,
|
|
"num_tokens": 44970261.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.339979982376098,
|
|
"epoch": 1.8852065321805955,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046472428007014515,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.2119445577263832,
|
|
"num_tokens": 44981515.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.23395791053772,
|
|
"epoch": 1.8856868395773296,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004647058480512907,
|
|
"loss": 4.9488,
|
|
"mean_token_accuracy": 0.22145207971334457,
|
|
"num_tokens": 44992473.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.337176132202148,
|
|
"epoch": 1.8861671469740635,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046468741162802987,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.2080984443426132,
|
|
"num_tokens": 45004264.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.256448888778687,
|
|
"epoch": 1.8866474543707974,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004646689708007905,
|
|
"loss": 4.9538,
|
|
"mean_token_accuracy": 0.2186066374182701,
|
|
"num_tokens": 45015601.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.350739049911499,
|
|
"epoch": 1.8871277617675313,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046465052557000087,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.21176934242248535,
|
|
"num_tokens": 45028044.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.391657066345215,
|
|
"epoch": 1.8876080691642652,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046463207593608916,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.21324148923158645,
|
|
"num_tokens": 45040144.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.382012844085693,
|
|
"epoch": 1.888088376560999,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004646136218994837,
|
|
"loss": 5.148,
|
|
"mean_token_accuracy": 0.20179301202297212,
|
|
"num_tokens": 45051844.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.3287529945373535,
|
|
"epoch": 1.888568683957733,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00046459516346061304,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.20796885788440705,
|
|
"num_tokens": 45062684.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.262111568450928,
|
|
"epoch": 1.8890489913544668,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046457670061990564,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.21314372569322587,
|
|
"num_tokens": 45073327.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.283940172195434,
|
|
"epoch": 1.8895292987512007,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046455823337779024,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.20843502134084702,
|
|
"num_tokens": 45085309.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.4441839218139645,
|
|
"epoch": 1.8900096061479346,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004645397617346954,
|
|
"loss": 5.0952,
|
|
"mean_token_accuracy": 0.2090018332004547,
|
|
"num_tokens": 45095934.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.298432350158691,
|
|
"epoch": 1.8904899135446684,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004645212856910502,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.21931952834129334,
|
|
"num_tokens": 45106220.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.239926481246949,
|
|
"epoch": 1.8909702209414025,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004645028052472835,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.20921881645917892,
|
|
"num_tokens": 45117861.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.2719159603118895,
|
|
"epoch": 1.8914505283381364,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046448432040382444,
|
|
"loss": 4.992,
|
|
"mean_token_accuracy": 0.2219533786177635,
|
|
"num_tokens": 45129248.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.33004789352417,
|
|
"epoch": 1.8919308357348703,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000464465831161102,
|
|
"loss": 5.0291,
|
|
"mean_token_accuracy": 0.2090006649494171,
|
|
"num_tokens": 45140610.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.231512975692749,
|
|
"epoch": 1.8924111431316042,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004644473375195456,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.2223814159631729,
|
|
"num_tokens": 45150697.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.320860433578491,
|
|
"epoch": 1.8928914505283383,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046442883947958466,
|
|
"loss": 5.031,
|
|
"mean_token_accuracy": 0.2136651560664177,
|
|
"num_tokens": 45162627.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.166951131820679,
|
|
"epoch": 1.8933717579250722,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046441033704164845,
|
|
"loss": 4.8262,
|
|
"mean_token_accuracy": 0.23050385117530822,
|
|
"num_tokens": 45173030.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.2749005317687985,
|
|
"epoch": 1.893852065321806,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004643918302061666,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.21386819034814836,
|
|
"num_tokens": 45183588.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.338022184371948,
|
|
"epoch": 1.89433237271854,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004643733189735689,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.2141084536910057,
|
|
"num_tokens": 45195289.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.290249347686768,
|
|
"epoch": 1.8948126801152738,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000464354803344285,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.21618156582117082,
|
|
"num_tokens": 45207001.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.256804609298706,
|
|
"epoch": 1.8952929875120077,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046433628331874496,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.21753165870904922,
|
|
"num_tokens": 45217447.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.34669337272644,
|
|
"epoch": 1.8957732949087416,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004643177588973785,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.21131815612316132,
|
|
"num_tokens": 45227588.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.276452302932739,
|
|
"epoch": 1.8962536023054755,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004642992300806159,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.21444032341241837,
|
|
"num_tokens": 45239969.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.293974590301514,
|
|
"epoch": 1.8967339097022093,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004642806968688873,
|
|
"loss": 4.9936,
|
|
"mean_token_accuracy": 0.21329281926155091,
|
|
"num_tokens": 45250877.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.358693981170655,
|
|
"epoch": 1.8972142170989432,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046426215926262295,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.21325994580984114,
|
|
"num_tokens": 45262846.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.2678405284881595,
|
|
"epoch": 1.897694524495677,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004642436172622532,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.21437106281518936,
|
|
"num_tokens": 45274198.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.240784072875977,
|
|
"epoch": 1.898174831892411,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004642250708682086,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.21538497060537337,
|
|
"num_tokens": 45285803.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.327806854248047,
|
|
"epoch": 1.898655139289145,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046420652008091984,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.20756091177463531,
|
|
"num_tokens": 45298242.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.2653967380523685,
|
|
"epoch": 1.899135446685879,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004641879649008174,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.2164671763777733,
|
|
"num_tokens": 45309567.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.358039999008179,
|
|
"epoch": 1.8996157540826129,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004641694053283323,
|
|
"loss": 5.0989,
|
|
"mean_token_accuracy": 0.21287932097911835,
|
|
"num_tokens": 45321693.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.309349489212036,
|
|
"epoch": 1.9000960614793467,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046415084136389525,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.2116013064980507,
|
|
"num_tokens": 45333094.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.265291786193847,
|
|
"epoch": 1.9005763688760808,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004641322730079374,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.2185659408569336,
|
|
"num_tokens": 45344549.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.355047225952148,
|
|
"epoch": 1.9010566762728147,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004641137002608897,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.20411577820777893,
|
|
"num_tokens": 45356433.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.283747291564941,
|
|
"epoch": 1.9015369836695486,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046409512312318345,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.2138038232922554,
|
|
"num_tokens": 45368224.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.250497341156006,
|
|
"epoch": 1.9020172910662825,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046407654159524994,
|
|
"loss": 4.9511,
|
|
"mean_token_accuracy": 0.21821341067552566,
|
|
"num_tokens": 45379673.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.38646354675293,
|
|
"epoch": 1.9024975984630164,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046405795567752055,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.21010962575674058,
|
|
"num_tokens": 45391613.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.280827617645263,
|
|
"epoch": 1.9029779058597502,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046403936537042686,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.2102092459797859,
|
|
"num_tokens": 45403693.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.29713397026062,
|
|
"epoch": 1.9034582132564841,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046402077067440043,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.20997344702482224,
|
|
"num_tokens": 45416151.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.3275713443756105,
|
|
"epoch": 1.903938520653218,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046400217158987293,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.20300500094890594,
|
|
"num_tokens": 45428276.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.255893898010254,
|
|
"epoch": 1.9044188280499519,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046398356811727626,
|
|
"loss": 4.9734,
|
|
"mean_token_accuracy": 0.219564850628376,
|
|
"num_tokens": 45439877.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.285429191589356,
|
|
"epoch": 1.9048991354466858,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004639649602570423,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.22026070058345795,
|
|
"num_tokens": 45451459.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.1831237316131595,
|
|
"epoch": 1.9053794428434196,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046394634800960314,
|
|
"loss": 4.9281,
|
|
"mean_token_accuracy": 0.2164081260561943,
|
|
"num_tokens": 45463341.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.359205865859986,
|
|
"epoch": 1.9058597502401537,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046392773137539074,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.21270294934511186,
|
|
"num_tokens": 45475585.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.338249683380127,
|
|
"epoch": 1.9063400576368876,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046390911035483744,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.21767494976520538,
|
|
"num_tokens": 45487178.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.3526520252227785,
|
|
"epoch": 1.9068203650336215,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004638904849483756,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.21164452731609346,
|
|
"num_tokens": 45498832.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.322737550735473,
|
|
"epoch": 1.9073006724303554,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046387185515643756,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.20483416616916655,
|
|
"num_tokens": 45511549.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.322851896286011,
|
|
"epoch": 1.9077809798270895,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004638532209794559,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.20940010696649553,
|
|
"num_tokens": 45523421.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.3506194114685055,
|
|
"epoch": 1.9082612872238234,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004638345824178631,
|
|
"loss": 5.0759,
|
|
"mean_token_accuracy": 0.21197763234376907,
|
|
"num_tokens": 45535247.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.222987508773803,
|
|
"epoch": 1.9087415946205573,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046381593947209215,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.22396730184555053,
|
|
"num_tokens": 45546296.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.2605266094207765,
|
|
"epoch": 1.9092219020172911,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004637972921425757,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.2129968836903572,
|
|
"num_tokens": 45557360.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.287890243530273,
|
|
"epoch": 1.909702209414025,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046377864042974675,
|
|
"loss": 5.0218,
|
|
"mean_token_accuracy": 0.2173658162355423,
|
|
"num_tokens": 45568500.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.354616260528564,
|
|
"epoch": 1.910182516810759,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004637599843340384,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.20541017204523088,
|
|
"num_tokens": 45579513.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.317130041122437,
|
|
"epoch": 1.9106628242074928,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046374132385588356,
|
|
"loss": 4.9916,
|
|
"mean_token_accuracy": 0.2211133360862732,
|
|
"num_tokens": 45591144.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.301947927474975,
|
|
"epoch": 1.9111431316042267,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046372265899571576,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.21076801270246506,
|
|
"num_tokens": 45602487.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.354799270629883,
|
|
"epoch": 1.9116234390009605,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046370398975396817,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.20737011283636092,
|
|
"num_tokens": 45614448.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.3074616432189945,
|
|
"epoch": 1.9121037463976944,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004636853161310743,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.2083998814225197,
|
|
"num_tokens": 45625660.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.216388511657715,
|
|
"epoch": 1.9125840537944283,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046366663812746764,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.22452109456062316,
|
|
"num_tokens": 45638602.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.19244499206543,
|
|
"epoch": 1.9130643611911622,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004636479557435818,
|
|
"loss": 4.9186,
|
|
"mean_token_accuracy": 0.22906002253293992,
|
|
"num_tokens": 45649460.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.156311511993408,
|
|
"epoch": 1.9135446685878963,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046362926897985067,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.22199774980545045,
|
|
"num_tokens": 45659995.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.26104416847229,
|
|
"epoch": 1.9140249759846302,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000463610577836708,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.20980933904647828,
|
|
"num_tokens": 45672262.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.26897029876709,
|
|
"epoch": 1.914505283381364,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046359188231458783,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.21302689760923385,
|
|
"num_tokens": 45685210.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.283378314971924,
|
|
"epoch": 1.914985590778098,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046357318241392414,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.21247404366731643,
|
|
"num_tokens": 45696418.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.330809831619263,
|
|
"epoch": 1.915465898174832,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000463554478135151,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.21386393755674363,
|
|
"num_tokens": 45708393.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.347344446182251,
|
|
"epoch": 1.915946205571566,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004635357694787029,
|
|
"loss": 5.0707,
|
|
"mean_token_accuracy": 0.20497565418481828,
|
|
"num_tokens": 45721287.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.215263557434082,
|
|
"epoch": 1.9164265129682998,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000463517056445014,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.22729844152927398,
|
|
"num_tokens": 45732846.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.331226253509522,
|
|
"epoch": 1.9169068203650337,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00046349833903451884,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.2014801248908043,
|
|
"num_tokens": 45743931.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.356312274932861,
|
|
"epoch": 1.9173871277617676,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046347961724765196,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.21668496876955032,
|
|
"num_tokens": 45755512.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.249177074432373,
|
|
"epoch": 1.9178674351585014,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046346089108484806,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.21311326771974565,
|
|
"num_tokens": 45766793.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.286300897598267,
|
|
"epoch": 1.9183477425552353,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046344216054654193,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.21139733195304872,
|
|
"num_tokens": 45778214.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.424818468093872,
|
|
"epoch": 1.9188280499519692,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046342342563316833,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.1983308583498001,
|
|
"num_tokens": 45791255.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.380587387084961,
|
|
"epoch": 1.919308357348703,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046340468634516223,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.2011657178401947,
|
|
"num_tokens": 45803351.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.228133344650269,
|
|
"epoch": 1.919788664745437,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046338594268295884,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.21977782100439072,
|
|
"num_tokens": 45814986.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.206633138656616,
|
|
"epoch": 1.9202689721421708,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004633671946469933,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.2144823268055916,
|
|
"num_tokens": 45827073.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.316590642929077,
|
|
"epoch": 1.920749279538905,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046334844223770076,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.21909478008747102,
|
|
"num_tokens": 45837808.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.241662645339966,
|
|
"epoch": 1.9212295869356388,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046332968545551674,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.21328342854976653,
|
|
"num_tokens": 45849932.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.264273071289063,
|
|
"epoch": 1.9217098943323727,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004633109243008765,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.21284113079309464,
|
|
"num_tokens": 45860961.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.229662084579468,
|
|
"epoch": 1.9221902017291066,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004632921587742159,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.21720025092363357,
|
|
"num_tokens": 45872251.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.385938930511474,
|
|
"epoch": 1.9226705091258407,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046327338887597043,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.21219139844179152,
|
|
"num_tokens": 45883234.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.225459623336792,
|
|
"epoch": 1.9231508165225746,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000463254614606576,
|
|
"loss": 5.0019,
|
|
"mean_token_accuracy": 0.21435252875089644,
|
|
"num_tokens": 45894003.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.202113389968872,
|
|
"epoch": 1.9236311239193085,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004632358359664683,
|
|
"loss": 4.9648,
|
|
"mean_token_accuracy": 0.21713642925024032,
|
|
"num_tokens": 45906109.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.335662126541138,
|
|
"epoch": 1.9241114313160423,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046321705295608356,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.2099107727408409,
|
|
"num_tokens": 45918372.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.346123075485229,
|
|
"epoch": 1.9245917387127762,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046319826557585764,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.20498981326818466,
|
|
"num_tokens": 45928750.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.371047830581665,
|
|
"epoch": 1.92507204610951,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004631794738262269,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.2176031455397606,
|
|
"num_tokens": 45939297.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.290903520584107,
|
|
"epoch": 1.925552353506244,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004631606777076275,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.21438322067260743,
|
|
"num_tokens": 45949986.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.279991817474365,
|
|
"epoch": 1.9260326609029779,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046314187722049587,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.2134560763835907,
|
|
"num_tokens": 45960747.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.326022911071777,
|
|
"epoch": 1.9265129682997117,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046312307236526863,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.2138536050915718,
|
|
"num_tokens": 45972260.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.278458023071289,
|
|
"epoch": 1.9269932756964456,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046310426314238217,
|
|
"loss": 4.949,
|
|
"mean_token_accuracy": 0.21782176494598388,
|
|
"num_tokens": 45983589.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.19992880821228,
|
|
"epoch": 1.9274735830931795,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004630854495522733,
|
|
"loss": 4.964,
|
|
"mean_token_accuracy": 0.2221485272049904,
|
|
"num_tokens": 45994776.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.323886919021606,
|
|
"epoch": 1.9279538904899134,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046306663159537874,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.20774816423654557,
|
|
"num_tokens": 46005530.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.26939435005188,
|
|
"epoch": 1.9284341978866475,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046304780927213554,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.21631258130073547,
|
|
"num_tokens": 46017538.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.290132331848144,
|
|
"epoch": 1.9289145052833814,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046302898258298046,
|
|
"loss": 4.9662,
|
|
"mean_token_accuracy": 0.20990947782993316,
|
|
"num_tokens": 46029011.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.207756519317627,
|
|
"epoch": 1.9293948126801153,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004630101515283509,
|
|
"loss": 4.9873,
|
|
"mean_token_accuracy": 0.2201964035630226,
|
|
"num_tokens": 46040354.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.241646957397461,
|
|
"epoch": 1.9298751200768491,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046299131610868377,
|
|
"loss": 4.9993,
|
|
"mean_token_accuracy": 0.2157585173845291,
|
|
"num_tokens": 46051127.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.283195686340332,
|
|
"epoch": 1.9303554274735832,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004629724763244165,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.22140569239854813,
|
|
"num_tokens": 46062343.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.203181743621826,
|
|
"epoch": 1.9308357348703171,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004629536321759866,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.21446231305599212,
|
|
"num_tokens": 46074193.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.319753885269165,
|
|
"epoch": 1.931316042267051,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046293478366383133,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.2224903091788292,
|
|
"num_tokens": 46085930.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.345250511169434,
|
|
"epoch": 1.9317963496637849,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004629159307883885,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.20437120497226716,
|
|
"num_tokens": 46099759.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.459265565872192,
|
|
"epoch": 1.9322766570605188,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004628970735500958,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.1984418287873268,
|
|
"num_tokens": 46110907.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.271303319931031,
|
|
"epoch": 1.9327569644572526,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046287821194939094,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.21448833793401717,
|
|
"num_tokens": 46122167.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.26546721458435,
|
|
"epoch": 1.9332372718539865,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046285934598671186,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.20495077967643738,
|
|
"num_tokens": 46132948.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.34251856803894,
|
|
"epoch": 1.9337175792507204,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046284047566249665,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.2133988246321678,
|
|
"num_tokens": 46144275.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.280539274215698,
|
|
"epoch": 1.9341978866474543,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046282160097718336,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.21694754362106322,
|
|
"num_tokens": 46156138.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.335160446166992,
|
|
"epoch": 1.9346781940441882,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004628027219312102,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.21081102639436722,
|
|
"num_tokens": 46169437.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.297490358352661,
|
|
"epoch": 1.935158501440922,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004627838385250155,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.21552095264196397,
|
|
"num_tokens": 46182150.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.293683481216431,
|
|
"epoch": 1.9356388088376562,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046276495075903764,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.22149748504161834,
|
|
"num_tokens": 46193945.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.353234481811524,
|
|
"epoch": 1.93611911623439,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046274605863371517,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.2108941987156868,
|
|
"num_tokens": 46206130.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.213943767547607,
|
|
"epoch": 1.936599423631124,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004627271621494868,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.22338226437568665,
|
|
"num_tokens": 46217284.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.243566942214966,
|
|
"epoch": 1.9370797310278578,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000462708261306791,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.21683521717786788,
|
|
"num_tokens": 46227949.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.276575660705566,
|
|
"epoch": 1.937560038424592,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004626893561060669,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.210880346596241,
|
|
"num_tokens": 46239101.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.364283084869385,
|
|
"epoch": 1.9380403458213258,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046267044654775324,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.21061044037342072,
|
|
"num_tokens": 46251272.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.3198998928070065,
|
|
"epoch": 1.9385206532180597,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000462651532632289,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.21092406511306763,
|
|
"num_tokens": 46262603.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.292784595489502,
|
|
"epoch": 1.9390009606147935,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046263261436011344,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.2089035391807556,
|
|
"num_tokens": 46275142.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.271890544891358,
|
|
"epoch": 1.9394812680115274,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004626136917316657,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.2196761980652809,
|
|
"num_tokens": 46286339.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.2611692428588865,
|
|
"epoch": 1.9399615754082613,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046259476474738514,
|
|
"loss": 5.012,
|
|
"mean_token_accuracy": 0.21532711684703826,
|
|
"num_tokens": 46297514.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.238162422180176,
|
|
"epoch": 1.9404418828049952,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046257583340771123,
|
|
"loss": 4.8976,
|
|
"mean_token_accuracy": 0.22167856097221375,
|
|
"num_tokens": 46309249.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.266149234771729,
|
|
"epoch": 1.940922190201729,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004625568977130835,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.20890892893075944,
|
|
"num_tokens": 46320759.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.375870656967163,
|
|
"epoch": 1.941402497598463,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004625379576639414,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.20746563971042634,
|
|
"num_tokens": 46332113.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.319719552993774,
|
|
"epoch": 1.9418828049951968,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046251901326072487,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.2163466051220894,
|
|
"num_tokens": 46342648.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.240574932098388,
|
|
"epoch": 1.9423631123919307,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046250006450387367,
|
|
"loss": 4.9665,
|
|
"mean_token_accuracy": 0.2129060983657837,
|
|
"num_tokens": 46354066.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.315989303588867,
|
|
"epoch": 1.9428434197886646,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004624811113938277,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.20398405194282532,
|
|
"num_tokens": 46366586.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.279525995254517,
|
|
"epoch": 1.9433237271853987,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004624621539310271,
|
|
"loss": 4.9704,
|
|
"mean_token_accuracy": 0.21829787492752076,
|
|
"num_tokens": 46378155.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.285288906097412,
|
|
"epoch": 1.9438040345821326,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046244319211591193,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.21318268924951553,
|
|
"num_tokens": 46389631.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.380673027038574,
|
|
"epoch": 1.9442843419788665,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004624242259489223,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.202990560233593,
|
|
"num_tokens": 46401915.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.380218505859375,
|
|
"epoch": 1.9447646493756003,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046240525543049884,
|
|
"loss": 5.0357,
|
|
"mean_token_accuracy": 0.21355825215578078,
|
|
"num_tokens": 46412396.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.196614837646484,
|
|
"epoch": 1.9452449567723344,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046238628056108176,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.22194779217243193,
|
|
"num_tokens": 46423089.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.33855357170105,
|
|
"epoch": 1.9457252641690683,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046236730134111166,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.2060428187251091,
|
|
"num_tokens": 46434858.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.228152227401734,
|
|
"epoch": 1.9462055715658022,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004623483177710291,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.22168778479099274,
|
|
"num_tokens": 46445628.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.201297998428345,
|
|
"epoch": 1.946685878962536,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004623293298512751,
|
|
"loss": 4.9764,
|
|
"mean_token_accuracy": 0.2200157731771469,
|
|
"num_tokens": 46457382.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.279243421554566,
|
|
"epoch": 1.94716618635927,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046231033758229026,
|
|
"loss": 5.0503,
|
|
"mean_token_accuracy": 0.20789543986320497,
|
|
"num_tokens": 46469765.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.4170982837677,
|
|
"epoch": 1.9476464937560038,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004622913409645154,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.20600515902042388,
|
|
"num_tokens": 46481451.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.293075799942017,
|
|
"epoch": 1.9481268011527377,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004622723399983919,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.2214369773864746,
|
|
"num_tokens": 46491585.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.263570356369018,
|
|
"epoch": 1.9486071085494716,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046225333468436077,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.2032816618680954,
|
|
"num_tokens": 46503789.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.354936933517456,
|
|
"epoch": 1.9490874159462055,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046223432502286323,
|
|
"loss": 5.1226,
|
|
"mean_token_accuracy": 0.2084595963358879,
|
|
"num_tokens": 46516647.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.315009498596192,
|
|
"epoch": 1.9495677233429394,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046221531101434056,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.2063657596707344,
|
|
"num_tokens": 46527432.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.369308853149414,
|
|
"epoch": 1.9500480307396733,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004621962926592343,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.21073827445507048,
|
|
"num_tokens": 46538990.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.297941207885742,
|
|
"epoch": 1.9505283381364071,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000462177269957986,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.2081049293279648,
|
|
"num_tokens": 46551291.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.286041021347046,
|
|
"epoch": 1.9510086455331412,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004621582429110373,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.2186756730079651,
|
|
"num_tokens": 46562415.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.332885265350342,
|
|
"epoch": 1.9514889529298751,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046213921151883,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.21910308450460433,
|
|
"num_tokens": 46572544.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.239902067184448,
|
|
"epoch": 1.951969260326609,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004621201757818059,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.21817909479141234,
|
|
"num_tokens": 46584694.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.332189893722534,
|
|
"epoch": 1.952449567723343,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046210113570040683,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.21691255271434784,
|
|
"num_tokens": 46595086.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.329073572158814,
|
|
"epoch": 1.952929875120077,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000462082091275075,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.21363091170787812,
|
|
"num_tokens": 46606627.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.3048172950744625,
|
|
"epoch": 1.9534101825168109,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004620630425062526,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.20815900415182115,
|
|
"num_tokens": 46618560.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.302272510528565,
|
|
"epoch": 1.9538904899135447,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004620439893943817,
|
|
"loss": 5.006,
|
|
"mean_token_accuracy": 0.21112534403800964,
|
|
"num_tokens": 46630109.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.2717784404754635,
|
|
"epoch": 1.9543707973102786,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004620249319399049,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.2196525901556015,
|
|
"num_tokens": 46642247.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.349028873443603,
|
|
"epoch": 1.9548511047070125,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046200587014326455,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.21144695281982423,
|
|
"num_tokens": 46653119.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.215050268173218,
|
|
"epoch": 1.9553314121037464,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004619868040049031,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.21749130189418792,
|
|
"num_tokens": 46664392.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.215203666687012,
|
|
"epoch": 1.9558117195004803,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004619677335252633,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.22284729331731795,
|
|
"num_tokens": 46674981.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.324275350570678,
|
|
"epoch": 1.9562920268972142,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046194865870478793,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.20696202665567398,
|
|
"num_tokens": 46688692.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.181072092056274,
|
|
"epoch": 1.956772334293948,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046192957954391983,
|
|
"loss": 4.9075,
|
|
"mean_token_accuracy": 0.2238846719264984,
|
|
"num_tokens": 46699799.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.258173131942749,
|
|
"epoch": 1.957252641690682,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000461910496043102,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.2130882576107979,
|
|
"num_tokens": 46711994.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.29259467124939,
|
|
"epoch": 1.9577329490874158,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004618914082027773,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.21425153762102128,
|
|
"num_tokens": 46723247.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.342856740951538,
|
|
"epoch": 1.95821325648415,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046187231602338926,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.20902744084596633,
|
|
"num_tokens": 46732824.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.258202123641968,
|
|
"epoch": 1.9586935638808838,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046185321950538086,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.21736806780099868,
|
|
"num_tokens": 46744640.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.273447751998901,
|
|
"epoch": 1.9591738712776177,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004618341186491955,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.21351933032274245,
|
|
"num_tokens": 46757513.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.246955394744873,
|
|
"epoch": 1.9596541786743515,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004618150134552768,
|
|
"loss": 4.9595,
|
|
"mean_token_accuracy": 0.2220014899969101,
|
|
"num_tokens": 46769021.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.213215732574463,
|
|
"epoch": 1.9601344860710856,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000461795903924068,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.21974156498908998,
|
|
"num_tokens": 46781175.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.225290107727051,
|
|
"epoch": 1.9606147934678195,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046177679005601313,
|
|
"loss": 4.9305,
|
|
"mean_token_accuracy": 0.21803064942359923,
|
|
"num_tokens": 46792256.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.227657651901245,
|
|
"epoch": 1.9610951008645534,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004617576718515558,
|
|
"loss": 4.9354,
|
|
"mean_token_accuracy": 0.22384601086378098,
|
|
"num_tokens": 46803215.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.322060585021973,
|
|
"epoch": 1.9615754082612873,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004617385493111399,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.21494927555322646,
|
|
"num_tokens": 46813770.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.248436117172242,
|
|
"epoch": 1.9620557156580212,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004617194224352093,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.2125754863023758,
|
|
"num_tokens": 46826923.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.2237146377563475,
|
|
"epoch": 1.962536023054755,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004617002912242083,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.2192418396472931,
|
|
"num_tokens": 46837761.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.259875345230102,
|
|
"epoch": 1.963016330451489,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046168115567858084,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.21133572608232498,
|
|
"num_tokens": 46848190.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.190766954421997,
|
|
"epoch": 1.9634966378482228,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046166201579877125,
|
|
"loss": 4.9151,
|
|
"mean_token_accuracy": 0.22336575984954835,
|
|
"num_tokens": 46858643.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.2515746593475345,
|
|
"epoch": 1.9639769452449567,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004616428715852239,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.21630677580833435,
|
|
"num_tokens": 46868711.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.312127304077149,
|
|
"epoch": 1.9644572526416906,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004616237230383833,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.2133081078529358,
|
|
"num_tokens": 46880045.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.271383142471313,
|
|
"epoch": 1.9649375600384245,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046160457015869414,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.2149149939417839,
|
|
"num_tokens": 46890680.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.265486764907837,
|
|
"epoch": 1.9654178674351583,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046158541294660083,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.21194234639406204,
|
|
"num_tokens": 46904807.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.307876634597778,
|
|
"epoch": 1.9658981748318924,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004615662514025483,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.21581350564956664,
|
|
"num_tokens": 46916039.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.261682367324829,
|
|
"epoch": 1.9663784822286263,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046154708552698147,
|
|
"loss": 5.0126,
|
|
"mean_token_accuracy": 0.21343594044446945,
|
|
"num_tokens": 46927175.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.212980318069458,
|
|
"epoch": 1.9668587896253602,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046152791532034517,
|
|
"loss": 4.9026,
|
|
"mean_token_accuracy": 0.22436313778162004,
|
|
"num_tokens": 46938711.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.243221044540405,
|
|
"epoch": 1.967339097022094,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046150874078308463,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.21277956813573837,
|
|
"num_tokens": 46951002.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.37927656173706,
|
|
"epoch": 1.9678194044188282,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004614895619156449,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.20976139456033707,
|
|
"num_tokens": 46962673.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.283319902420044,
|
|
"epoch": 1.968299711815562,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046147037871847125,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.21135011166334153,
|
|
"num_tokens": 46973955.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.3042933464050295,
|
|
"epoch": 1.968780019212296,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004614511911920092,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.20572051852941514,
|
|
"num_tokens": 46985791.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.449639940261841,
|
|
"epoch": 1.9692603266090298,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046143199933670404,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.20105572044849396,
|
|
"num_tokens": 46998437.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.29549560546875,
|
|
"epoch": 1.9697406340057637,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004614128031530015,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.21202209293842317,
|
|
"num_tokens": 47009666.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.346506023406983,
|
|
"epoch": 1.9702209414024976,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046139360264134724,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.20785963386297227,
|
|
"num_tokens": 47021170.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.31040506362915,
|
|
"epoch": 1.9707012487992315,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004613743978021869,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.21787395179271699,
|
|
"num_tokens": 47033077.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.302386808395386,
|
|
"epoch": 1.9711815561959654,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046135518863596654,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.20924610048532485,
|
|
"num_tokens": 47044858.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.3284547328948975,
|
|
"epoch": 1.9716618635926992,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046133597514313204,
|
|
"loss": 5.1204,
|
|
"mean_token_accuracy": 0.20419208258390426,
|
|
"num_tokens": 47057587.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.364740991592408,
|
|
"epoch": 1.9721421709894331,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004613167573241295,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.20179614871740342,
|
|
"num_tokens": 47068690.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.29047155380249,
|
|
"epoch": 1.972622478386167,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004612975351794051,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.21221625208854675,
|
|
"num_tokens": 47081279.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.29954342842102,
|
|
"epoch": 1.973102785782901,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004612783087094051,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.2151889681816101,
|
|
"num_tokens": 47093372.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.398928308486939,
|
|
"epoch": 1.973583093179635,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046125907791457594,
|
|
"loss": 5.1705,
|
|
"mean_token_accuracy": 0.20555868446826936,
|
|
"num_tokens": 47104332.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.373195457458496,
|
|
"epoch": 1.9740634005763689,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046123984279536405,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.2057998701930046,
|
|
"num_tokens": 47116941.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.360964107513428,
|
|
"epoch": 1.9745437079731027,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046122060335221604,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.20736243277788163,
|
|
"num_tokens": 47128473.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.27558970451355,
|
|
"epoch": 1.9750240153698368,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046120135958557855,
|
|
"loss": 5.0238,
|
|
"mean_token_accuracy": 0.208538256585598,
|
|
"num_tokens": 47140586.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.248756074905396,
|
|
"epoch": 1.9755043227665707,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046118211149589843,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.22023916840553284,
|
|
"num_tokens": 47150875.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.253042793273925,
|
|
"epoch": 1.9759846301633046,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004611628590836225,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.2274812176823616,
|
|
"num_tokens": 47162074.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.226053285598755,
|
|
"epoch": 1.9764649375600385,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004611436023491979,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.21748096346855164,
|
|
"num_tokens": 47174544.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.312288665771485,
|
|
"epoch": 1.9769452449567724,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004611243412930714,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.21081341654062272,
|
|
"num_tokens": 47186260.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.293906545639038,
|
|
"epoch": 1.9774255523535063,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046110507591569047,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.21639261692762374,
|
|
"num_tokens": 47198059.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.2578497409820555,
|
|
"epoch": 1.9779058597502401,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004610858062175023,
|
|
"loss": 4.9305,
|
|
"mean_token_accuracy": 0.22250256538391114,
|
|
"num_tokens": 47208300.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.262729454040527,
|
|
"epoch": 1.978386167146974,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046106653219895417,
|
|
"loss": 5.0006,
|
|
"mean_token_accuracy": 0.21817676424980165,
|
|
"num_tokens": 47220135.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.337225341796875,
|
|
"epoch": 1.978866474543708,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004610472538604938,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.20712206214666368,
|
|
"num_tokens": 47230385.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.195694875717163,
|
|
"epoch": 1.9793467819404418,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046102797120256854,
|
|
"loss": 4.9144,
|
|
"mean_token_accuracy": 0.22136950194835664,
|
|
"num_tokens": 47242593.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.33862533569336,
|
|
"epoch": 1.9798270893371757,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004610086842256262,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.2092697098851204,
|
|
"num_tokens": 47254223.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.324244260787964,
|
|
"epoch": 1.9803073967339095,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004609893929301146,
|
|
"loss": 5.0739,
|
|
"mean_token_accuracy": 0.21409593522548676,
|
|
"num_tokens": 47266559.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.313050746917725,
|
|
"epoch": 1.9807877041306436,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004609700973164816,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.21654462069272995,
|
|
"num_tokens": 47276438.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.257084560394287,
|
|
"epoch": 1.9812680115273775,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004609507973851751,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.20667703598737716,
|
|
"num_tokens": 47287791.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.289524221420288,
|
|
"epoch": 1.9817483189241114,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046093149313664316,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.21462836116552353,
|
|
"num_tokens": 47300282.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.38121395111084,
|
|
"epoch": 1.9822286263208453,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004609121845713342,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.21808649897575377,
|
|
"num_tokens": 47310473.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.201325750350952,
|
|
"epoch": 1.9827089337175794,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004608928716896963,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.21268734335899353,
|
|
"num_tokens": 47322245.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.339168739318848,
|
|
"epoch": 1.9831892411143133,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004608735544921778,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.21760564297437668,
|
|
"num_tokens": 47334316.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.363510608673096,
|
|
"epoch": 1.9836695485110472,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046085423297922745,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.21336631029844283,
|
|
"num_tokens": 47344909.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.200469970703125,
|
|
"epoch": 1.984149855907781,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046083490715129367,
|
|
"loss": 4.9438,
|
|
"mean_token_accuracy": 0.2257858023047447,
|
|
"num_tokens": 47356682.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.2342664241790775,
|
|
"epoch": 1.984630163304515,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004608155770088251,
|
|
"loss": 4.9087,
|
|
"mean_token_accuracy": 0.21988777220249175,
|
|
"num_tokens": 47368362.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.3509016036987305,
|
|
"epoch": 1.9851104707012488,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046079624255227066,
|
|
"loss": 5.0154,
|
|
"mean_token_accuracy": 0.21610396206378937,
|
|
"num_tokens": 47379932.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.294203662872315,
|
|
"epoch": 1.9855907780979827,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004607769037820791,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.20623611509799958,
|
|
"num_tokens": 47391244.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.294877338409424,
|
|
"epoch": 1.9860710854947166,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004607575606986995,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.21228047311306,
|
|
"num_tokens": 47404005.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.202724361419678,
|
|
"epoch": 1.9865513928914504,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004607382133025809,
|
|
"loss": 4.925,
|
|
"mean_token_accuracy": 0.22279721796512603,
|
|
"num_tokens": 47414555.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.276439952850342,
|
|
"epoch": 1.9870317002881843,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046071886159417257,
|
|
"loss": 5.0552,
|
|
"mean_token_accuracy": 0.21037745326757432,
|
|
"num_tokens": 47425902.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.18895468711853,
|
|
"epoch": 1.9875120076849182,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004606995055739238,
|
|
"loss": 4.9196,
|
|
"mean_token_accuracy": 0.22099285423755646,
|
|
"num_tokens": 47438068.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.328373813629151,
|
|
"epoch": 1.9879923150816523,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046068014524228374,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.20972843319177628,
|
|
"num_tokens": 47450322.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.273414468765258,
|
|
"epoch": 1.9884726224783862,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046066078059970217,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.21476263403892518,
|
|
"num_tokens": 47462615.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.2627428531646725,
|
|
"epoch": 1.98895292987512,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004606414116466286,
|
|
"loss": 4.9765,
|
|
"mean_token_accuracy": 0.21488141268491745,
|
|
"num_tokens": 47472530.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.2016302108764645,
|
|
"epoch": 1.989433237271854,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046062203838351267,
|
|
"loss": 4.9573,
|
|
"mean_token_accuracy": 0.21786079108715056,
|
|
"num_tokens": 47484217.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.339591836929321,
|
|
"epoch": 1.989913544668588,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046060266081080414,
|
|
"loss": 5.0432,
|
|
"mean_token_accuracy": 0.2119894027709961,
|
|
"num_tokens": 47496365.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.304943418502807,
|
|
"epoch": 1.990393852065322,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004605832789289531,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.22366088181734084,
|
|
"num_tokens": 47509437.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.31752381324768,
|
|
"epoch": 1.9908741594620558,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004605638927384093,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.2052105188369751,
|
|
"num_tokens": 47520913.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.352366924285889,
|
|
"epoch": 1.9913544668587897,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046054450223962284,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.2078831300139427,
|
|
"num_tokens": 47532015.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.367773818969726,
|
|
"epoch": 1.9918347742555236,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046052510743304405,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.2038946196436882,
|
|
"num_tokens": 47543675.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.331734609603882,
|
|
"epoch": 1.9923150816522575,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004605057083191232,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.21390334218740464,
|
|
"num_tokens": 47555757.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.338556480407715,
|
|
"epoch": 1.9927953890489913,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004604863048983106,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.21158306300640106,
|
|
"num_tokens": 47568043.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.249013423919678,
|
|
"epoch": 1.9932756964457252,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004604668971710568,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.21534719169139863,
|
|
"num_tokens": 47577811.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.383232259750367,
|
|
"epoch": 1.993756003842459,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004604474851378124,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.2028462678194046,
|
|
"num_tokens": 47588309.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.484276962280274,
|
|
"epoch": 1.994236311239193,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046042806879902803,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.20325528979301452,
|
|
"num_tokens": 47599814.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.369664144515991,
|
|
"epoch": 1.9947166186359269,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004604086481551546,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.20997765213251113,
|
|
"num_tokens": 47611851.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.245332813262939,
|
|
"epoch": 1.9951969260326607,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004603892232066428,
|
|
"loss": 4.9417,
|
|
"mean_token_accuracy": 0.22030594497919082,
|
|
"num_tokens": 47624056.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.258671426773072,
|
|
"epoch": 1.9956772334293948,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046036979395394374,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.21470014303922652,
|
|
"num_tokens": 47637214.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.286880397796631,
|
|
"epoch": 1.9961575408261287,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004603503603975085,
|
|
"loss": 4.9786,
|
|
"mean_token_accuracy": 0.21744334846735,
|
|
"num_tokens": 47647498.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.294569492340088,
|
|
"epoch": 1.9966378482228626,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004603309225377883,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.21223255395889282,
|
|
"num_tokens": 47659576.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.306166887283325,
|
|
"epoch": 1.9971181556195965,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004603114803752344,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.21052755564451217,
|
|
"num_tokens": 47670631.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.256212377548218,
|
|
"epoch": 1.9975984630163306,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00046029203391029813,
|
|
"loss": 4.9432,
|
|
"mean_token_accuracy": 0.21549466699361802,
|
|
"num_tokens": 47681647.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.254293441772461,
|
|
"epoch": 1.9980787704130645,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046027258314343107,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.21806015223264694,
|
|
"num_tokens": 47694386.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.308084535598755,
|
|
"epoch": 1.9985590778097984,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046025312807508487,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.21000762283802032,
|
|
"num_tokens": 47704897.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.2936032772064205,
|
|
"epoch": 1.9990393852065322,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046023366870571097,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.2117243617773056,
|
|
"num_tokens": 47715771.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.318970680236816,
|
|
"epoch": 1.9995196926032661,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046021420503576145,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.2233315661549568,
|
|
"num_tokens": 47726295.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.181529235839844,
|
|
"epoch": 2.0,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004601947370656879,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.20828320682048798,
|
|
"num_tokens": 47737072.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.287859201431274,
|
|
"epoch": 2.000480307396734,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004601752647959426,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.21192548871040345,
|
|
"num_tokens": 47750379.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.4091148853302,
|
|
"epoch": 2.0009606147934678,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004601557882269775,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.21073902547359466,
|
|
"num_tokens": 47763059.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.280742835998535,
|
|
"epoch": 2.0014409221902016,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004601363073592447,
|
|
"loss": 4.9438,
|
|
"mean_token_accuracy": 0.2172427996993065,
|
|
"num_tokens": 47775513.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.200676345825196,
|
|
"epoch": 2.0019212295869355,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004601168221931967,
|
|
"loss": 4.8686,
|
|
"mean_token_accuracy": 0.22140122354030609,
|
|
"num_tokens": 47786215.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.262446641921997,
|
|
"epoch": 2.0024015369836694,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004600973327292857,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.21607888340950013,
|
|
"num_tokens": 47796894.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.2651200771331785,
|
|
"epoch": 2.0028818443804033,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046007783896796436,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.2138429194688797,
|
|
"num_tokens": 47808505.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.279147386550903,
|
|
"epoch": 2.003362151777137,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004600583409096851,
|
|
"loss": 4.8731,
|
|
"mean_token_accuracy": 0.21986687630414964,
|
|
"num_tokens": 47819617.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.1963951587677,
|
|
"epoch": 2.0038424591738715,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046003883855490066,
|
|
"loss": 4.9069,
|
|
"mean_token_accuracy": 0.22438308745622634,
|
|
"num_tokens": 47830655.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.216381454467774,
|
|
"epoch": 2.0043227665706054,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004600193319040638,
|
|
"loss": 4.857,
|
|
"mean_token_accuracy": 0.22834118604660034,
|
|
"num_tokens": 47842439.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.173571395874023,
|
|
"epoch": 2.0048030739673393,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045999982095762756,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.23359253704547883,
|
|
"num_tokens": 47853327.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.281465339660644,
|
|
"epoch": 2.005283381364073,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045998030571604473,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.21437281668186187,
|
|
"num_tokens": 47867155.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.2730742454528805,
|
|
"epoch": 2.005763688760807,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004599607861797685,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.21622742116451263,
|
|
"num_tokens": 47879641.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.285227680206299,
|
|
"epoch": 2.006243996157541,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045994126234925203,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.21456611007452012,
|
|
"num_tokens": 47890512.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.299113464355469,
|
|
"epoch": 2.006724303554275,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045992173422494865,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.21064408719539643,
|
|
"num_tokens": 47902575.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.2830400466918945,
|
|
"epoch": 2.0072046109510087,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004599022018073117,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.22615595757961274,
|
|
"num_tokens": 47915447.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.246980428695679,
|
|
"epoch": 2.0076849183477425,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 0.0004598826650967946,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.21610080301761628,
|
|
"num_tokens": 47925702.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.272411441802978,
|
|
"epoch": 2.0081652257444764,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045986312409385105,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.22178911417722702,
|
|
"num_tokens": 47936621.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.232845973968506,
|
|
"epoch": 2.0086455331412103,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004598435787989347,
|
|
"loss": 4.8913,
|
|
"mean_token_accuracy": 0.22545901387929917,
|
|
"num_tokens": 47948026.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.311439752578735,
|
|
"epoch": 2.009125840537944,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045982402921249934,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.2120351403951645,
|
|
"num_tokens": 47959976.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.340374183654785,
|
|
"epoch": 2.009606147934678,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004598044753349988,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.20699219554662704,
|
|
"num_tokens": 47972071.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.325219297409058,
|
|
"epoch": 2.010086455331412,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045978491716688706,
|
|
"loss": 4.931,
|
|
"mean_token_accuracy": 0.21753817945718765,
|
|
"num_tokens": 47984789.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.18701024055481,
|
|
"epoch": 2.010566762728146,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004597653547086184,
|
|
"loss": 4.9125,
|
|
"mean_token_accuracy": 0.22455205619335175,
|
|
"num_tokens": 47995661.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.277917814254761,
|
|
"epoch": 2.0110470701248797,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004597457879606467,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.2130712404847145,
|
|
"num_tokens": 48006043.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.3000490188598635,
|
|
"epoch": 2.011527377521614,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045972621692342636,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.21137429028749466,
|
|
"num_tokens": 48016904.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.287079381942749,
|
|
"epoch": 2.012007684918348,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045970664159741186,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.21675706058740615,
|
|
"num_tokens": 48026533.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.226649236679077,
|
|
"epoch": 2.012487992315082,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045968706198305765,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.22501958310604095,
|
|
"num_tokens": 48038280.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.203261756896973,
|
|
"epoch": 2.0129682997118157,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045966747808081824,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.23015830367803575,
|
|
"num_tokens": 48049663.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.273942279815674,
|
|
"epoch": 2.0134486071085496,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004596478898911483,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.217519311606884,
|
|
"num_tokens": 48059826.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.266466665267944,
|
|
"epoch": 2.0139289145052834,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045962829741450265,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.2252273753285408,
|
|
"num_tokens": 48071097.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.260691595077515,
|
|
"epoch": 2.0144092219020173,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004596087006513361,
|
|
"loss": 4.9311,
|
|
"mean_token_accuracy": 0.21815840750932694,
|
|
"num_tokens": 48082297.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.168303060531616,
|
|
"epoch": 2.014889529298751,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045958909960210385,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.2219670832157135,
|
|
"num_tokens": 48092946.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.228477573394775,
|
|
"epoch": 2.015369836695485,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045956949426726075,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.22270985841751098,
|
|
"num_tokens": 48105000.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.228873682022095,
|
|
"epoch": 2.015850144092219,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045954988464726203,
|
|
"loss": 4.9084,
|
|
"mean_token_accuracy": 0.22021305412054062,
|
|
"num_tokens": 48117513.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.338377523422241,
|
|
"epoch": 2.016330451488953,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000459530270742563,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.20176563411951065,
|
|
"num_tokens": 48130895.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.2870564460754395,
|
|
"epoch": 2.0168107588856867,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045951065255361905,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.21117716282606125,
|
|
"num_tokens": 48143348.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.2773353099823,
|
|
"epoch": 2.0172910662824206,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004594910300808856,
|
|
"loss": 4.9438,
|
|
"mean_token_accuracy": 0.22376890182495118,
|
|
"num_tokens": 48154959.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.0172910662824206,
|
|
"eval_entropy": 5.11275166386456,
|
|
"eval_loss": 5.083931922912598,
|
|
"eval_mean_token_accuracy": 0.21917101315816165,
|
|
"eval_num_tokens": 48154959.0,
|
|
"eval_runtime": 26.5083,
|
|
"eval_samples_per_second": 1237.915,
|
|
"eval_steps_per_second": 154.744,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.2027538299560545,
|
|
"epoch": 2.0177713736791545,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004594714033248183,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.22635449469089508,
|
|
"num_tokens": 48165227.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.280473709106445,
|
|
"epoch": 2.0182516810758884,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004594517722858728,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.21184469312429427,
|
|
"num_tokens": 48175133.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.301852178573609,
|
|
"epoch": 2.0187319884726227,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045943213696450475,
|
|
"loss": 4.9543,
|
|
"mean_token_accuracy": 0.21753255426883697,
|
|
"num_tokens": 48187554.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.3010235786437985,
|
|
"epoch": 2.0192122958693566,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045941249736117023,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.2103932172060013,
|
|
"num_tokens": 48199410.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.212014865875244,
|
|
"epoch": 2.0196926032660905,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004593928534763251,
|
|
"loss": 4.9438,
|
|
"mean_token_accuracy": 0.21633480489253998,
|
|
"num_tokens": 48211124.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.240890073776245,
|
|
"epoch": 2.0201729106628243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004593732053104254,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.21971191614866256,
|
|
"num_tokens": 48222690.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.2611490249633786,
|
|
"epoch": 2.020653218059558,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045935355286392735,
|
|
"loss": 4.9107,
|
|
"mean_token_accuracy": 0.2196151167154312,
|
|
"num_tokens": 48235054.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.161662435531616,
|
|
"epoch": 2.021133525456292,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004593338961372873,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.22492327839136123,
|
|
"num_tokens": 48246645.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.182728099822998,
|
|
"epoch": 2.021613832853026,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004593142351309614,
|
|
"loss": 4.8708,
|
|
"mean_token_accuracy": 0.2254963770508766,
|
|
"num_tokens": 48258149.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.29056305885315,
|
|
"epoch": 2.02209414024976,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004592945698454064,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.21572868376970292,
|
|
"num_tokens": 48269892.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.326174736022949,
|
|
"epoch": 2.0225744476464937,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045927490028107866,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.2116445079445839,
|
|
"num_tokens": 48281087.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.2490987300872805,
|
|
"epoch": 2.0230547550432276,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000459255226438435,
|
|
"loss": 4.8522,
|
|
"mean_token_accuracy": 0.23108487576246262,
|
|
"num_tokens": 48292177.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.162690448760986,
|
|
"epoch": 2.0235350624399615,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000459235548317932,
|
|
"loss": 4.9049,
|
|
"mean_token_accuracy": 0.21730162650346757,
|
|
"num_tokens": 48304281.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.226367616653443,
|
|
"epoch": 2.0240153698366954,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00045921586592002667,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.21940454542636872,
|
|
"num_tokens": 48316758.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.367440891265869,
|
|
"epoch": 2.0244956772334293,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000459196179245176,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.2086740866303444,
|
|
"num_tokens": 48327455.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.264489269256591,
|
|
"epoch": 2.024975984630163,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004591764882938369,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.2137674242258072,
|
|
"num_tokens": 48338105.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.283783960342407,
|
|
"epoch": 2.025456292026897,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004591567930664667,
|
|
"loss": 4.9913,
|
|
"mean_token_accuracy": 0.20984267294406891,
|
|
"num_tokens": 48349599.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.299345064163208,
|
|
"epoch": 2.025936599423631,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004591370935635226,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.21096672862768173,
|
|
"num_tokens": 48361488.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.299706935882568,
|
|
"epoch": 2.0264169068203652,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004591173897854619,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.21530982255935668,
|
|
"num_tokens": 48372049.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.2183623790740965,
|
|
"epoch": 2.026897214217099,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004590976817327422,
|
|
"loss": 4.8862,
|
|
"mean_token_accuracy": 0.2228393331170082,
|
|
"num_tokens": 48385599.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.320964097976685,
|
|
"epoch": 2.027377521613833,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004590779694058209,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.21729758083820344,
|
|
"num_tokens": 48397390.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.268738222122193,
|
|
"epoch": 2.027857829010567,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045905825280515586,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.21409812569618225,
|
|
"num_tokens": 48409837.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.194092035293579,
|
|
"epoch": 2.0283381364073008,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00045903853193120464,
|
|
"loss": 4.8427,
|
|
"mean_token_accuracy": 0.22717543095350265,
|
|
"num_tokens": 48420765.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.247415447235108,
|
|
"epoch": 2.0288184438040346,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045901880678442524,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.2214759275317192,
|
|
"num_tokens": 48431939.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.310197496414185,
|
|
"epoch": 2.0292987512007685,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045899907736527556,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.20910764932632447,
|
|
"num_tokens": 48444820.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.244786119461059,
|
|
"epoch": 2.0297790585975024,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045897934367421364,
|
|
"loss": 4.967,
|
|
"mean_token_accuracy": 0.2175592824816704,
|
|
"num_tokens": 48457315.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.322730779647827,
|
|
"epoch": 2.0302593659942363,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004589596057116977,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.2064725250005722,
|
|
"num_tokens": 48468612.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.231360244750976,
|
|
"epoch": 2.03073967339097,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045893986347818593,
|
|
"loss": 4.8868,
|
|
"mean_token_accuracy": 0.22177761048078537,
|
|
"num_tokens": 48479453.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.230742931365967,
|
|
"epoch": 2.031219980787704,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004589201169741368,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.22122501134872435,
|
|
"num_tokens": 48491656.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.216836833953858,
|
|
"epoch": 2.031700288184438,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045890036620000856,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.21144406199455262,
|
|
"num_tokens": 48503431.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.214943981170654,
|
|
"epoch": 2.032180595581172,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045888061115626,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.22472997307777404,
|
|
"num_tokens": 48513922.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.181715679168701,
|
|
"epoch": 2.0326609029779057,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004588608518433496,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.22170526087284087,
|
|
"num_tokens": 48524715.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.287716293334961,
|
|
"epoch": 2.0331412103746396,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004588410882617362,
|
|
"loss": 5.0117,
|
|
"mean_token_accuracy": 0.2117729127407074,
|
|
"num_tokens": 48536696.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.366511583328247,
|
|
"epoch": 2.0336215177713735,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004588213204118786,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.2078629493713379,
|
|
"num_tokens": 48550290.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.295836734771728,
|
|
"epoch": 2.034101825168108,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045880154829423586,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.21997810751199723,
|
|
"num_tokens": 48561047.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.135164976119995,
|
|
"epoch": 2.0345821325648417,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004587817719092668,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.23468807935714722,
|
|
"num_tokens": 48571268.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.189264631271362,
|
|
"epoch": 2.0350624399615755,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045876199125743087,
|
|
"loss": 4.896,
|
|
"mean_token_accuracy": 0.2153346598148346,
|
|
"num_tokens": 48583158.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.3050695896148685,
|
|
"epoch": 2.0355427473583094,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004587422063391871,
|
|
"loss": 4.9552,
|
|
"mean_token_accuracy": 0.2212915003299713,
|
|
"num_tokens": 48593419.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.301788806915283,
|
|
"epoch": 2.0360230547550433,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004587224171549949,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.21935103833675385,
|
|
"num_tokens": 48605845.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.247403621673584,
|
|
"epoch": 2.036503362151777,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045870262370531376,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.22075793147087097,
|
|
"num_tokens": 48616503.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.27436146736145,
|
|
"epoch": 2.036983669548511,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045868282599060314,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.21397918611764907,
|
|
"num_tokens": 48628410.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.2414017677307125,
|
|
"epoch": 2.037463976945245,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004586630240113227,
|
|
"loss": 4.9134,
|
|
"mean_token_accuracy": 0.21863891929388046,
|
|
"num_tokens": 48639457.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.237280035018921,
|
|
"epoch": 2.037944284341979,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004586432177679322,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.2200344294309616,
|
|
"num_tokens": 48652250.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.237525510787964,
|
|
"epoch": 2.0384245917387127,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045862340726089153,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.21231539100408553,
|
|
"num_tokens": 48663386.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.317520570755005,
|
|
"epoch": 2.0389048991354466,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004586035924906606,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.213177952170372,
|
|
"num_tokens": 48675111.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.230409145355225,
|
|
"epoch": 2.0393852065321805,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045858377345769946,
|
|
"loss": 4.8888,
|
|
"mean_token_accuracy": 0.2234511375427246,
|
|
"num_tokens": 48686264.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.224790811538696,
|
|
"epoch": 2.0398655139289144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004585639501624682,
|
|
"loss": 4.9364,
|
|
"mean_token_accuracy": 0.2124020963907242,
|
|
"num_tokens": 48697249.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.206356811523437,
|
|
"epoch": 2.0403458213256482,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000458544122605427,
|
|
"loss": 4.8925,
|
|
"mean_token_accuracy": 0.21740953624248505,
|
|
"num_tokens": 48708808.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.307266759872436,
|
|
"epoch": 2.040826128722382,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045852429078703646,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.21207872331142424,
|
|
"num_tokens": 48719879.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.324212169647216,
|
|
"epoch": 2.0413064361191164,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045850445470775673,
|
|
"loss": 4.9876,
|
|
"mean_token_accuracy": 0.22012442648410796,
|
|
"num_tokens": 48731110.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.221066427230835,
|
|
"epoch": 2.0417867435158503,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004584846143680485,
|
|
"loss": 4.9303,
|
|
"mean_token_accuracy": 0.22004867643117904,
|
|
"num_tokens": 48742799.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.388209342956543,
|
|
"epoch": 2.042267050912584,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004584647697683723,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.20960856527090072,
|
|
"num_tokens": 48753773.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.286432409286499,
|
|
"epoch": 2.042747358309318,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045844492090918904,
|
|
"loss": 4.925,
|
|
"mean_token_accuracy": 0.22115902751684188,
|
|
"num_tokens": 48764561.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.20129714012146,
|
|
"epoch": 2.043227665706052,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045842506779095936,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.2182600602507591,
|
|
"num_tokens": 48775319.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.340674543380738,
|
|
"epoch": 2.043707973102786,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004584052104141443,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.20243048369884492,
|
|
"num_tokens": 48787595.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.34336576461792,
|
|
"epoch": 2.0441882804995197,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004583853487792048,
|
|
"loss": 4.9638,
|
|
"mean_token_accuracy": 0.21147483736276626,
|
|
"num_tokens": 48800015.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.310475921630859,
|
|
"epoch": 2.0446685878962536,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004583654828866021,
|
|
"loss": 4.9641,
|
|
"mean_token_accuracy": 0.21119226664304733,
|
|
"num_tokens": 48811651.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.271849775314331,
|
|
"epoch": 2.0451488952929875,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004583456127367973,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.22147364318370819,
|
|
"num_tokens": 48823561.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.236146259307861,
|
|
"epoch": 2.0456292026897214,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004583257383302519,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.21249209344387054,
|
|
"num_tokens": 48835385.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.329408836364746,
|
|
"epoch": 2.0461095100864553,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004583058596674271,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.21209967881441116,
|
|
"num_tokens": 48846899.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.268584585189819,
|
|
"epoch": 2.046589817483189,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004582859767487846,
|
|
"loss": 4.9429,
|
|
"mean_token_accuracy": 0.22087372988462448,
|
|
"num_tokens": 48857850.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.206199884414673,
|
|
"epoch": 2.047070124879923,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045826608957478604,
|
|
"loss": 4.9261,
|
|
"mean_token_accuracy": 0.21753964573144913,
|
|
"num_tokens": 48869192.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.2248228073120115,
|
|
"epoch": 2.047550432276657,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045824619814589297,
|
|
"loss": 4.9084,
|
|
"mean_token_accuracy": 0.22176061868667601,
|
|
"num_tokens": 48881314.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.213526248931885,
|
|
"epoch": 2.0480307396733908,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004582263024625674,
|
|
"loss": 4.9774,
|
|
"mean_token_accuracy": 0.2159250944852829,
|
|
"num_tokens": 48893292.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.254723739624024,
|
|
"epoch": 2.048511047070125,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004582064025252711,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.21298140436410903,
|
|
"num_tokens": 48905607.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.306242609024048,
|
|
"epoch": 2.048991354466859,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004581864983344661,
|
|
"loss": 4.9396,
|
|
"mean_token_accuracy": 0.2207736998796463,
|
|
"num_tokens": 48916194.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.281847906112671,
|
|
"epoch": 2.049471661863593,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004581665898906147,
|
|
"loss": 4.9281,
|
|
"mean_token_accuracy": 0.21871140748262405,
|
|
"num_tokens": 48927560.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.168967866897583,
|
|
"epoch": 2.0499519692603267,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045814667719417887,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.22662024945020676,
|
|
"num_tokens": 48938284.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.230234432220459,
|
|
"epoch": 2.0504322766570606,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000458126760245621,
|
|
"loss": 4.9195,
|
|
"mean_token_accuracy": 0.22285306751728057,
|
|
"num_tokens": 48948325.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.254767751693725,
|
|
"epoch": 2.0509125840537945,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004581068390454036,
|
|
"loss": 4.929,
|
|
"mean_token_accuracy": 0.21972954273223877,
|
|
"num_tokens": 48960020.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.203447914123535,
|
|
"epoch": 2.0513928914505284,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045808691359398905,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.2253645732998848,
|
|
"num_tokens": 48970833.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.211418104171753,
|
|
"epoch": 2.0518731988472623,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004580669838918401,
|
|
"loss": 4.9288,
|
|
"mean_token_accuracy": 0.22642400860786438,
|
|
"num_tokens": 48981821.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.279809284210205,
|
|
"epoch": 2.052353506243996,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045804704993941935,
|
|
"loss": 4.9361,
|
|
"mean_token_accuracy": 0.21800605803728104,
|
|
"num_tokens": 48992341.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.243301820755005,
|
|
"epoch": 2.05283381364073,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00045802711173718966,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.21032867282629014,
|
|
"num_tokens": 49003063.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.278737306594849,
|
|
"epoch": 2.053314121037464,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004580071692856138,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.22039274573326112,
|
|
"num_tokens": 49015353.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.196951675415039,
|
|
"epoch": 2.053794428434198,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045798722258515504,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.22632651031017303,
|
|
"num_tokens": 49026405.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.261710691452026,
|
|
"epoch": 2.0542747358309317,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045796727163627623,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.2100438266992569,
|
|
"num_tokens": 49038433.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.177416753768921,
|
|
"epoch": 2.0547550432276656,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004579473164394408,
|
|
"loss": 4.8545,
|
|
"mean_token_accuracy": 0.22608156651258468,
|
|
"num_tokens": 49049463.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.154839277267456,
|
|
"epoch": 2.0552353506243994,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045792735699511176,
|
|
"loss": 4.8202,
|
|
"mean_token_accuracy": 0.22489213347434997,
|
|
"num_tokens": 49061607.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.277562093734741,
|
|
"epoch": 2.0557156580211333,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045790739330375276,
|
|
"loss": 4.9959,
|
|
"mean_token_accuracy": 0.21473717242479323,
|
|
"num_tokens": 49074687.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.243634939193726,
|
|
"epoch": 2.0561959654178676,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045788742536582717,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.2219685807824135,
|
|
"num_tokens": 49086151.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.2228984355926515,
|
|
"epoch": 2.0566762728146015,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045786745318179866,
|
|
"loss": 4.9837,
|
|
"mean_token_accuracy": 0.20988998115062713,
|
|
"num_tokens": 49097418.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.205038547515869,
|
|
"epoch": 2.0571565802113354,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004578474767521309,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.2265104427933693,
|
|
"num_tokens": 49108570.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.196998977661133,
|
|
"epoch": 2.0576368876080693,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045782749607728765,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.2117031365633011,
|
|
"num_tokens": 49120906.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.2364967346191404,
|
|
"epoch": 2.058117195004803,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045780751115773286,
|
|
"loss": 4.8724,
|
|
"mean_token_accuracy": 0.22467209696769713,
|
|
"num_tokens": 49132040.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.2600781440734865,
|
|
"epoch": 2.058597502401537,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004577875219939304,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.22256723493337632,
|
|
"num_tokens": 49143427.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.288342428207398,
|
|
"epoch": 2.059077809798271,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004577675285863446,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.21680564880371095,
|
|
"num_tokens": 49155351.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.291520404815674,
|
|
"epoch": 2.059558117195005,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045774753093543943,
|
|
"loss": 4.9833,
|
|
"mean_token_accuracy": 0.21490877270698547,
|
|
"num_tokens": 49167898.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.219863700866699,
|
|
"epoch": 2.0600384245917387,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004577275290416791,
|
|
"loss": 4.9619,
|
|
"mean_token_accuracy": 0.21499780863523482,
|
|
"num_tokens": 49179209.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.240249300003052,
|
|
"epoch": 2.0605187319884726,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004577075229055283,
|
|
"loss": 4.9045,
|
|
"mean_token_accuracy": 0.22095047533512116,
|
|
"num_tokens": 49190382.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.1985594749450685,
|
|
"epoch": 2.0609990393852065,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045768751252745133,
|
|
"loss": 4.9548,
|
|
"mean_token_accuracy": 0.21915296763181685,
|
|
"num_tokens": 49203511.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.3150331497192385,
|
|
"epoch": 2.0614793467819403,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045766749790791274,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.21533906906843187,
|
|
"num_tokens": 49214276.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.129332494735718,
|
|
"epoch": 2.061959654178674,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004576474790473773,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.23126184791326523,
|
|
"num_tokens": 49225803.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.231499052047729,
|
|
"epoch": 2.062439961575408,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045762745594630973,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.2151098594069481,
|
|
"num_tokens": 49237187.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.373307895660401,
|
|
"epoch": 2.062920268972142,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004576074286051749,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.2148006647825241,
|
|
"num_tokens": 49250151.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.175782585144043,
|
|
"epoch": 2.063400576368876,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045758739702443787,
|
|
"loss": 4.8491,
|
|
"mean_token_accuracy": 0.2294616237282753,
|
|
"num_tokens": 49261970.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.210483121871948,
|
|
"epoch": 2.06388088376561,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004575673612045636,
|
|
"loss": 4.9108,
|
|
"mean_token_accuracy": 0.22683330476284028,
|
|
"num_tokens": 49271427.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.222397661209106,
|
|
"epoch": 2.064361191162344,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004575473211460173,
|
|
"loss": 4.9735,
|
|
"mean_token_accuracy": 0.22199309915304183,
|
|
"num_tokens": 49285102.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.250132036209107,
|
|
"epoch": 2.064841498559078,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004575272768492644,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.21586863696575165,
|
|
"num_tokens": 49297569.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.250937032699585,
|
|
"epoch": 2.065321805955812,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045750722831476993,
|
|
"loss": 4.8732,
|
|
"mean_token_accuracy": 0.22487862855196,
|
|
"num_tokens": 49308795.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.2914670467376705,
|
|
"epoch": 2.0658021133525457,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045748717554299964,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.21868394017219545,
|
|
"num_tokens": 49320971.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.289001035690307,
|
|
"epoch": 2.0662824207492796,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000457467118534419,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.20740963220596315,
|
|
"num_tokens": 49333624.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.352980613708496,
|
|
"epoch": 2.0667627281460135,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004574470572894938,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.20980596393346787,
|
|
"num_tokens": 49344863.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.284479331970215,
|
|
"epoch": 2.0672430355427474,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004574269918086895,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.21921409368515016,
|
|
"num_tokens": 49355501.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.270954561233521,
|
|
"epoch": 2.0677233429394812,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004574069220924722,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.22562674432992935,
|
|
"num_tokens": 49366384.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.3324095726013185,
|
|
"epoch": 2.068203650336215,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004573868481413079,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.2021533265709877,
|
|
"num_tokens": 49378670.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.268502044677734,
|
|
"epoch": 2.068683957732949,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045736676995566244,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.21646809428930283,
|
|
"num_tokens": 49390273.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.279264450073242,
|
|
"epoch": 2.069164265129683,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045734668753600217,
|
|
"loss": 4.9817,
|
|
"mean_token_accuracy": 0.21377656906843184,
|
|
"num_tokens": 49402503.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.243313646316528,
|
|
"epoch": 2.0696445725264168,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045732660088279326,
|
|
"loss": 4.927,
|
|
"mean_token_accuracy": 0.2152409479022026,
|
|
"num_tokens": 49413948.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.243001556396484,
|
|
"epoch": 2.0701248799231506,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045730650999650216,
|
|
"loss": 4.8928,
|
|
"mean_token_accuracy": 0.22510455548763275,
|
|
"num_tokens": 49424164.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.297632217407227,
|
|
"epoch": 2.0706051873198845,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045728641487759506,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.20737979114055632,
|
|
"num_tokens": 49435102.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.237615299224854,
|
|
"epoch": 2.071085494716619,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004572663155265388,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.22458921521902084,
|
|
"num_tokens": 49445445.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.262486696243286,
|
|
"epoch": 2.0715658021133527,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004572462119437999,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.21930481791496276,
|
|
"num_tokens": 49457578.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.219423246383667,
|
|
"epoch": 2.0720461095100866,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045722610412984513,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.2215749815106392,
|
|
"num_tokens": 49470253.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.3034075736999515,
|
|
"epoch": 2.0725264169068205,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004572059920851412,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.21402154266834258,
|
|
"num_tokens": 49481854.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.310453748703003,
|
|
"epoch": 2.0730067243035544,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045718587581015534,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.20961796939373017,
|
|
"num_tokens": 49494311.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.277214431762696,
|
|
"epoch": 2.0734870317002883,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004571657553053544,
|
|
"loss": 4.9324,
|
|
"mean_token_accuracy": 0.2263311669230461,
|
|
"num_tokens": 49506186.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.234983253479004,
|
|
"epoch": 2.073967339097022,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004571456305712055,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.21566364020109177,
|
|
"num_tokens": 49517841.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.218552350997925,
|
|
"epoch": 2.074447646493756,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004571255016081759,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.2209479570388794,
|
|
"num_tokens": 49529260.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.233576774597168,
|
|
"epoch": 2.07492795389049,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000457105368416733,
|
|
"loss": 4.9165,
|
|
"mean_token_accuracy": 0.22552942484617233,
|
|
"num_tokens": 49540892.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.339231824874878,
|
|
"epoch": 2.0754082612872238,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045708523099734417,
|
|
"loss": 4.9464,
|
|
"mean_token_accuracy": 0.21950782388448714,
|
|
"num_tokens": 49550924.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.277345418930054,
|
|
"epoch": 2.0758885686839577,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045706508935047693,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.21657910495996474,
|
|
"num_tokens": 49562424.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.189773416519165,
|
|
"epoch": 2.0763688760806915,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000457044943476599,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.22581999599933625,
|
|
"num_tokens": 49573341.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.299385261535645,
|
|
"epoch": 2.0768491834774254,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045702479337617795,
|
|
"loss": 4.8867,
|
|
"mean_token_accuracy": 0.21989830434322358,
|
|
"num_tokens": 49584047.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.1923572540283205,
|
|
"epoch": 2.0773294908741593,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004570046390496818,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.21853299885988237,
|
|
"num_tokens": 49595898.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.2347509384155275,
|
|
"epoch": 2.077809798270893,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004569844804975783,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.2188993364572525,
|
|
"num_tokens": 49607865.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.361542797088623,
|
|
"epoch": 2.0782901056676275,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004569643177203356,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.21685645431280137,
|
|
"num_tokens": 49619513.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.259656381607056,
|
|
"epoch": 2.0787704130643614,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004569441507184218,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.22725088000297547,
|
|
"num_tokens": 49631232.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.2362034797668455,
|
|
"epoch": 2.0792507204610953,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045692397949230495,
|
|
"loss": 4.9224,
|
|
"mean_token_accuracy": 0.2199809283018112,
|
|
"num_tokens": 49642653.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.204314851760865,
|
|
"epoch": 2.079731027857829,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045690380404245364,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.22270667403936387,
|
|
"num_tokens": 49654479.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.219990921020508,
|
|
"epoch": 2.080211335254563,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045688362436933607,
|
|
"loss": 4.9526,
|
|
"mean_token_accuracy": 0.21552058905363083,
|
|
"num_tokens": 49666461.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.232997179031372,
|
|
"epoch": 2.080691642651297,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004568634404734208,
|
|
"loss": 4.9803,
|
|
"mean_token_accuracy": 0.2188989609479904,
|
|
"num_tokens": 49676602.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.241682815551758,
|
|
"epoch": 2.081171950048031,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004568432523551765,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.2229257971048355,
|
|
"num_tokens": 49689225.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.216572523117065,
|
|
"epoch": 2.0816522574447647,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004568230600150718,
|
|
"loss": 4.9349,
|
|
"mean_token_accuracy": 0.21686665415763856,
|
|
"num_tokens": 49700827.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.247020292282104,
|
|
"epoch": 2.0821325648414986,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004568028634535757,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.21866553872823716,
|
|
"num_tokens": 49712777.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.249493551254273,
|
|
"epoch": 2.0826128722382324,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004567826626711568,
|
|
"loss": 4.9441,
|
|
"mean_token_accuracy": 0.22222511917352678,
|
|
"num_tokens": 49725234.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.2132128238677975,
|
|
"epoch": 2.0830931796349663,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004567624576682843,
|
|
"loss": 4.8908,
|
|
"mean_token_accuracy": 0.22294116467237474,
|
|
"num_tokens": 49736933.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.3070220947265625,
|
|
"epoch": 2.0835734870317,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004567422484454273,
|
|
"loss": 5.0012,
|
|
"mean_token_accuracy": 0.213498555123806,
|
|
"num_tokens": 49748279.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.193960857391358,
|
|
"epoch": 2.084053794428434,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00045672203500305493,
|
|
"loss": 4.9271,
|
|
"mean_token_accuracy": 0.22419319152832032,
|
|
"num_tokens": 49760874.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.205493211746216,
|
|
"epoch": 2.084534101825168,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045670181734163654,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.2242891013622284,
|
|
"num_tokens": 49772520.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.205278825759888,
|
|
"epoch": 2.085014409221902,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004566815954616414,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.22533990144729615,
|
|
"num_tokens": 49783019.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.161827230453492,
|
|
"epoch": 2.0854947166186357,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00045666136936353913,
|
|
"loss": 4.9074,
|
|
"mean_token_accuracy": 0.22436399459838868,
|
|
"num_tokens": 49795111.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.199182033538818,
|
|
"epoch": 2.08597502401537,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004566411390477993,
|
|
"loss": 4.8636,
|
|
"mean_token_accuracy": 0.22760812938213348,
|
|
"num_tokens": 49807022.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.29057035446167,
|
|
"epoch": 2.086455331412104,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045662090451489156,
|
|
"loss": 4.9711,
|
|
"mean_token_accuracy": 0.2121961385011673,
|
|
"num_tokens": 49819225.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.257859802246093,
|
|
"epoch": 2.086935638808838,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045660066576528577,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.22650564163923265,
|
|
"num_tokens": 49830989.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.2521013736724855,
|
|
"epoch": 2.0874159462055717,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004565804227994518,
|
|
"loss": 4.9234,
|
|
"mean_token_accuracy": 0.21800258308649062,
|
|
"num_tokens": 49841618.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.138695859909058,
|
|
"epoch": 2.0878962536023056,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004565601756178595,
|
|
"loss": 4.7658,
|
|
"mean_token_accuracy": 0.23876622319221497,
|
|
"num_tokens": 49851985.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.1859376430511475,
|
|
"epoch": 2.0883765609990395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004565399242209791,
|
|
"loss": 4.9778,
|
|
"mean_token_accuracy": 0.2125781461596489,
|
|
"num_tokens": 49863383.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.30908899307251,
|
|
"epoch": 2.0888568683957733,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004565196686092807,
|
|
"loss": 4.9536,
|
|
"mean_token_accuracy": 0.2221081331372261,
|
|
"num_tokens": 49875757.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.237438917160034,
|
|
"epoch": 2.089337175792507,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004564994087832346,
|
|
"loss": 4.8841,
|
|
"mean_token_accuracy": 0.22846302539110183,
|
|
"num_tokens": 49888419.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.241913890838623,
|
|
"epoch": 2.089817483189241,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045647914474331123,
|
|
"loss": 4.9737,
|
|
"mean_token_accuracy": 0.21643905192613602,
|
|
"num_tokens": 49899629.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.340927505493164,
|
|
"epoch": 2.090297790585975,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045645887648998094,
|
|
"loss": 4.9561,
|
|
"mean_token_accuracy": 0.2175733044743538,
|
|
"num_tokens": 49909858.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.1432350158691404,
|
|
"epoch": 2.090778097982709,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045643860402371433,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.2205786243081093,
|
|
"num_tokens": 49921305.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.251908588409424,
|
|
"epoch": 2.0912584053794427,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004564183273449821,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.21779208183288573,
|
|
"num_tokens": 49931966.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.225549125671387,
|
|
"epoch": 2.0917387127761766,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004563980464542551,
|
|
"loss": 4.884,
|
|
"mean_token_accuracy": 0.22089003920555114,
|
|
"num_tokens": 49943781.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.2632543563842775,
|
|
"epoch": 2.0922190201729105,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045637776135200406,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.22308011204004288,
|
|
"num_tokens": 49954149.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.291943740844727,
|
|
"epoch": 2.0926993275696444,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004563574720386999,
|
|
"loss": 4.9766,
|
|
"mean_token_accuracy": 0.21584233045578002,
|
|
"num_tokens": 49965542.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.238829183578491,
|
|
"epoch": 2.0931796349663783,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004563371785148139,
|
|
"loss": 4.903,
|
|
"mean_token_accuracy": 0.21663109213113785,
|
|
"num_tokens": 49977444.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.211457872390747,
|
|
"epoch": 2.0936599423631126,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045631688078081695,
|
|
"loss": 4.8933,
|
|
"mean_token_accuracy": 0.21973369121551514,
|
|
"num_tokens": 49988409.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.246695852279663,
|
|
"epoch": 2.0941402497598465,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004562965788371805,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.22022804617881775,
|
|
"num_tokens": 49999639.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.2278814792633055,
|
|
"epoch": 2.0946205571565804,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004562762726843758,
|
|
"loss": 4.9142,
|
|
"mean_token_accuracy": 0.2166602835059166,
|
|
"num_tokens": 50010964.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.35602912902832,
|
|
"epoch": 2.0951008645533142,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00045625596232287436,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.20688475668430328,
|
|
"num_tokens": 50024487.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.385723114013672,
|
|
"epoch": 2.095581171950048,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004562356477531477,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.20613116025924683,
|
|
"num_tokens": 50037202.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.205229377746582,
|
|
"epoch": 2.096061479346782,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004562153289756674,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.22819455564022065,
|
|
"num_tokens": 50048520.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.28936882019043,
|
|
"epoch": 2.096541786743516,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004561950059909053,
|
|
"loss": 4.9515,
|
|
"mean_token_accuracy": 0.21316723823547362,
|
|
"num_tokens": 50058523.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.285438203811646,
|
|
"epoch": 2.0970220941402498,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004561746787993332,
|
|
"loss": 4.9562,
|
|
"mean_token_accuracy": 0.21497801393270494,
|
|
"num_tokens": 50070241.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.237221908569336,
|
|
"epoch": 2.0975024015369836,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045615434740142307,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.21914665400981903,
|
|
"num_tokens": 50081326.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.20652666091919,
|
|
"epoch": 2.0979827089337175,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045613401179764686,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.22618957310914994,
|
|
"num_tokens": 50091767.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.2268013000488285,
|
|
"epoch": 2.0984630163304514,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045611367198847676,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.2183104544878006,
|
|
"num_tokens": 50103435.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.247589206695556,
|
|
"epoch": 2.0989433237271853,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000456093327974385,
|
|
"loss": 4.933,
|
|
"mean_token_accuracy": 0.21992123872041702,
|
|
"num_tokens": 50114127.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.26792802810669,
|
|
"epoch": 2.099423631123919,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004560729797558438,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.22583342641592025,
|
|
"num_tokens": 50126328.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.2811915397644045,
|
|
"epoch": 2.099903938520653,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004560526273333259,
|
|
"loss": 4.934,
|
|
"mean_token_accuracy": 0.2222449228167534,
|
|
"num_tokens": 50137600.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.296525526046753,
|
|
"epoch": 2.100384245917387,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045603227070730346,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.21520761251449586,
|
|
"num_tokens": 50148711.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.214939308166504,
|
|
"epoch": 2.1008645533141213,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045601190987824933,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.21014345288276673,
|
|
"num_tokens": 50161141.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.261022472381592,
|
|
"epoch": 2.101344860710855,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045599154484663606,
|
|
"loss": 4.9875,
|
|
"mean_token_accuracy": 0.21928945183753967,
|
|
"num_tokens": 50173145.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.27135705947876,
|
|
"epoch": 2.101825168107589,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045597117561293663,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.22249473184347152,
|
|
"num_tokens": 50184074.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.426916980743409,
|
|
"epoch": 2.102305475504323,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004559508021776238,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.2014644294977188,
|
|
"num_tokens": 50195004.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.21240005493164,
|
|
"epoch": 2.1027857829010568,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004559304245411707,
|
|
"loss": 4.9011,
|
|
"mean_token_accuracy": 0.22109040170907973,
|
|
"num_tokens": 50205329.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.326483249664307,
|
|
"epoch": 2.1032660902977907,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045591004270405044,
|
|
"loss": 4.9737,
|
|
"mean_token_accuracy": 0.2157845288515091,
|
|
"num_tokens": 50218346.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.2481683731079105,
|
|
"epoch": 2.1037463976945245,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004558896566667361,
|
|
"loss": 4.9435,
|
|
"mean_token_accuracy": 0.22151225656270981,
|
|
"num_tokens": 50229790.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.347575664520264,
|
|
"epoch": 2.1042267050912584,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045586926642970113,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.20791198760271073,
|
|
"num_tokens": 50240547.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.26989164352417,
|
|
"epoch": 2.1047070124879923,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004558488719934188,
|
|
"loss": 4.9061,
|
|
"mean_token_accuracy": 0.22638799399137496,
|
|
"num_tokens": 50251889.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.214649868011475,
|
|
"epoch": 2.105187319884726,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004558284733583627,
|
|
"loss": 4.9751,
|
|
"mean_token_accuracy": 0.21044729501008988,
|
|
"num_tokens": 50263599.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.287359428405762,
|
|
"epoch": 2.10566762728146,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045580807052500645,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.21516743004322053,
|
|
"num_tokens": 50275645.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.24601936340332,
|
|
"epoch": 2.106147934678194,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004557876634938236,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.2212132453918457,
|
|
"num_tokens": 50287640.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.282949733734131,
|
|
"epoch": 2.106628242074928,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004557672522652881,
|
|
"loss": 4.9887,
|
|
"mean_token_accuracy": 0.21193009316921235,
|
|
"num_tokens": 50299119.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.257583713531494,
|
|
"epoch": 2.1071085494716617,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004557468368398738,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.2134413927793503,
|
|
"num_tokens": 50311377.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.251482820510864,
|
|
"epoch": 2.1075888568683956,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004557264172180546,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.21805716156959534,
|
|
"num_tokens": 50323185.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.292876863479615,
|
|
"epoch": 2.1080691642651295,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004557059934003046,
|
|
"loss": 5.0227,
|
|
"mean_token_accuracy": 0.22077461332082748,
|
|
"num_tokens": 50333992.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.35239543914795,
|
|
"epoch": 2.108549471661864,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004556855653870981,
|
|
"loss": 5.0043,
|
|
"mean_token_accuracy": 0.21347902864217758,
|
|
"num_tokens": 50346087.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.289971876144409,
|
|
"epoch": 2.1090297790585977,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004556651331789092,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.2140049159526825,
|
|
"num_tokens": 50358274.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.257817363739013,
|
|
"epoch": 2.1095100864553316,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004556446967762125,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.22272191643714906,
|
|
"num_tokens": 50367784.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.302308750152588,
|
|
"epoch": 2.1099903938520654,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045562425617948226,
|
|
"loss": 5.0246,
|
|
"mean_token_accuracy": 0.21476725339889527,
|
|
"num_tokens": 50377877.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.2485435009002686,
|
|
"epoch": 2.1104707012487993,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045560381138919315,
|
|
"loss": 5.0184,
|
|
"mean_token_accuracy": 0.2220246523618698,
|
|
"num_tokens": 50391023.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.306030035018921,
|
|
"epoch": 2.110951008645533,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045558336240581984,
|
|
"loss": 4.9764,
|
|
"mean_token_accuracy": 0.2111206591129303,
|
|
"num_tokens": 50404417.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.287727975845337,
|
|
"epoch": 2.111431316042267,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045556290922983705,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.2161542445421219,
|
|
"num_tokens": 50416153.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.200957345962524,
|
|
"epoch": 2.111911623439001,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004555424518617197,
|
|
"loss": 4.9172,
|
|
"mean_token_accuracy": 0.22658466696739196,
|
|
"num_tokens": 50426860.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.230398082733155,
|
|
"epoch": 2.112391930835735,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045552199030194274,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.23127394020557404,
|
|
"num_tokens": 50437262.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.23589301109314,
|
|
"epoch": 2.1128722382324687,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045550152455098113,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.2267778515815735,
|
|
"num_tokens": 50448564.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.223162460327148,
|
|
"epoch": 2.1133525456292026,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004554810546093102,
|
|
"loss": 4.8797,
|
|
"mean_token_accuracy": 0.23406689912080764,
|
|
"num_tokens": 50459416.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.27290415763855,
|
|
"epoch": 2.1138328530259365,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000455460580477405,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.22122398167848586,
|
|
"num_tokens": 50470934.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.347412538528443,
|
|
"epoch": 2.1143131604226704,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000455440102155741,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.21570696085691451,
|
|
"num_tokens": 50483050.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.251918888092041,
|
|
"epoch": 2.1147934678194042,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004554196196447937,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.21043399423360826,
|
|
"num_tokens": 50494655.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.28315577507019,
|
|
"epoch": 2.115273775216138,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004553991329450385,
|
|
"loss": 4.9361,
|
|
"mean_token_accuracy": 0.21858337372541428,
|
|
"num_tokens": 50506302.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.3222850322723385,
|
|
"epoch": 2.115754082612872,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045537864205695116,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.21680360585451125,
|
|
"num_tokens": 50517979.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.277181243896484,
|
|
"epoch": 2.1162343900096063,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004553581469810073,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.2105120912194252,
|
|
"num_tokens": 50530054.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.238501358032226,
|
|
"epoch": 2.11671469740634,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045533764771768287,
|
|
"loss": 4.9192,
|
|
"mean_token_accuracy": 0.2150655746459961,
|
|
"num_tokens": 50540664.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.278092765808106,
|
|
"epoch": 2.117195004803074,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045531714426745373,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.2107803478837013,
|
|
"num_tokens": 50551444.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.226173639297485,
|
|
"epoch": 2.117675312199808,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004552966366307959,
|
|
"loss": 4.9148,
|
|
"mean_token_accuracy": 0.2215001568198204,
|
|
"num_tokens": 50562371.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.213501214981079,
|
|
"epoch": 2.118155619596542,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004552761248081856,
|
|
"loss": 4.8983,
|
|
"mean_token_accuracy": 0.22296253293752671,
|
|
"num_tokens": 50573545.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.306918144226074,
|
|
"epoch": 2.1186359269932757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000455255608800099,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.21261774748563766,
|
|
"num_tokens": 50584799.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.324064779281616,
|
|
"epoch": 2.1191162343900096,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045523508860701237,
|
|
"loss": 4.9682,
|
|
"mean_token_accuracy": 0.21340103447437286,
|
|
"num_tokens": 50596435.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.225666856765747,
|
|
"epoch": 2.1195965417867435,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004552145642294021,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.2261168211698532,
|
|
"num_tokens": 50606921.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.245547771453857,
|
|
"epoch": 2.1200768491834774,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045519403566774493,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.20972804576158524,
|
|
"num_tokens": 50618107.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.272660207748413,
|
|
"epoch": 2.1205571565802113,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004551735029225172,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.21494301408529282,
|
|
"num_tokens": 50628958.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.2711282730102536,
|
|
"epoch": 2.121037463976945,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045515296599419583,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.2203969120979309,
|
|
"num_tokens": 50640557.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.264281368255615,
|
|
"epoch": 2.121517771373679,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004551324248832574,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.22236818969249725,
|
|
"num_tokens": 50652699.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.253987598419189,
|
|
"epoch": 2.121998078770413,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004551118795901791,
|
|
"loss": 4.849,
|
|
"mean_token_accuracy": 0.21966277211904525,
|
|
"num_tokens": 50663735.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.227318859100341,
|
|
"epoch": 2.122478386167147,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004550913301154376,
|
|
"loss": 4.9442,
|
|
"mean_token_accuracy": 0.22112540304660797,
|
|
"num_tokens": 50676384.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.259908437728882,
|
|
"epoch": 2.1229586935638807,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004550707764595103,
|
|
"loss": 4.9634,
|
|
"mean_token_accuracy": 0.2132906973361969,
|
|
"num_tokens": 50687775.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.288627958297729,
|
|
"epoch": 2.123439000960615,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045505021862287434,
|
|
"loss": 5.0234,
|
|
"mean_token_accuracy": 0.21428995579481125,
|
|
"num_tokens": 50698522.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.233067655563355,
|
|
"epoch": 2.123919308357349,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045502965660600684,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.22154076397418976,
|
|
"num_tokens": 50709994.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.192929983139038,
|
|
"epoch": 2.1243996157540828,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004550090904093853,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.22015739530324935,
|
|
"num_tokens": 50720777.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.236693811416626,
|
|
"epoch": 2.1248799231508166,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004549885200334872,
|
|
"loss": 4.9007,
|
|
"mean_token_accuracy": 0.2200877621769905,
|
|
"num_tokens": 50732836.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.25096697807312,
|
|
"epoch": 2.1253602305475505,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004549679454787901,
|
|
"loss": 4.9304,
|
|
"mean_token_accuracy": 0.22793377339839935,
|
|
"num_tokens": 50743854.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.179960107803344,
|
|
"epoch": 2.1258405379442844,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045494736674577175,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.22310005575418473,
|
|
"num_tokens": 50755524.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.261144495010376,
|
|
"epoch": 2.1263208453410183,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004549267838349099,
|
|
"loss": 4.9091,
|
|
"mean_token_accuracy": 0.2206063836812973,
|
|
"num_tokens": 50766909.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.2205415725708,
|
|
"epoch": 2.126801152737752,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004549061967466823,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.22576962858438493,
|
|
"num_tokens": 50778065.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.253192901611328,
|
|
"epoch": 2.127281460134486,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004548856054815671,
|
|
"loss": 4.9625,
|
|
"mean_token_accuracy": 0.21876341253519058,
|
|
"num_tokens": 50790122.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.188257503509521,
|
|
"epoch": 2.12776176753122,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045486501004004225,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.2113481193780899,
|
|
"num_tokens": 50802661.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.308226490020752,
|
|
"epoch": 2.128242074927954,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000454844410422586,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.22067127376794815,
|
|
"num_tokens": 50814279.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.188221502304077,
|
|
"epoch": 2.1287223823246877,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045482380662967655,
|
|
"loss": 4.84,
|
|
"mean_token_accuracy": 0.22477750480175018,
|
|
"num_tokens": 50826186.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.2884622573852536,
|
|
"epoch": 2.1292026897214216,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004548031986617923,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.21065690517425537,
|
|
"num_tokens": 50838185.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.191874837875366,
|
|
"epoch": 2.1296829971181555,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004547825865194117,
|
|
"loss": 4.9072,
|
|
"mean_token_accuracy": 0.22308651059865953,
|
|
"num_tokens": 50850461.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.252447557449341,
|
|
"epoch": 2.1301633045148893,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045476197020301323,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.21486645936965942,
|
|
"num_tokens": 50861859.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.263146591186524,
|
|
"epoch": 2.1306436119116237,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045474134971307554,
|
|
"loss": 4.8959,
|
|
"mean_token_accuracy": 0.22305061370134355,
|
|
"num_tokens": 50872776.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.227983808517456,
|
|
"epoch": 2.1311239193083575,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004547207250500775,
|
|
"loss": 4.9199,
|
|
"mean_token_accuracy": 0.21705229729413986,
|
|
"num_tokens": 50885333.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.249975681304932,
|
|
"epoch": 2.1316042267050914,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000454700096214498,
|
|
"loss": 4.9237,
|
|
"mean_token_accuracy": 0.21599429100751877,
|
|
"num_tokens": 50897256.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.211497831344604,
|
|
"epoch": 2.1320845341018253,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045467946320681567,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.2195196658372879,
|
|
"num_tokens": 50909558.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.2566441059112545,
|
|
"epoch": 2.132564841498559,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004546588260275098,
|
|
"loss": 4.9391,
|
|
"mean_token_accuracy": 0.22384905070066452,
|
|
"num_tokens": 50920617.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.2283834457397464,
|
|
"epoch": 2.133045148895293,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045463818467705955,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.22179386764764786,
|
|
"num_tokens": 50931323.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.2085308074951175,
|
|
"epoch": 2.133525456292027,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000454617539155944,
|
|
"loss": 4.8251,
|
|
"mean_token_accuracy": 0.2322506606578827,
|
|
"num_tokens": 50942798.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.153916549682617,
|
|
"epoch": 2.134005763688761,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045459688946464255,
|
|
"loss": 4.7946,
|
|
"mean_token_accuracy": 0.22434925884008408,
|
|
"num_tokens": 50954877.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.314891672134399,
|
|
"epoch": 2.1344860710854947,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004545762356036346,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.22138840705156326,
|
|
"num_tokens": 50966133.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.293141222000122,
|
|
"epoch": 2.1349663784822286,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004545555775733998,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.22959452569484712,
|
|
"num_tokens": 50977334.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.216661643981934,
|
|
"epoch": 2.1354466858789625,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045453491537441747,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.21278008669614792,
|
|
"num_tokens": 50988743.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.236453008651734,
|
|
"epoch": 2.1359269932756964,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045451424900716763,
|
|
"loss": 4.9119,
|
|
"mean_token_accuracy": 0.22209604382514953,
|
|
"num_tokens": 51000591.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.318597745895386,
|
|
"epoch": 2.1364073006724302,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045449357847212994,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.21482229381799697,
|
|
"num_tokens": 51011565.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.255195760726929,
|
|
"epoch": 2.136887608069164,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004544729037697844,
|
|
"loss": 4.9679,
|
|
"mean_token_accuracy": 0.2178390368819237,
|
|
"num_tokens": 51022755.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.277530670166016,
|
|
"epoch": 2.137367915465898,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045445222490061093,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.21380429863929748,
|
|
"num_tokens": 51032839.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.235503435134888,
|
|
"epoch": 2.1378482228626323,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004544315418650897,
|
|
"loss": 4.9511,
|
|
"mean_token_accuracy": 0.2256665498018265,
|
|
"num_tokens": 51045020.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.224499845504761,
|
|
"epoch": 2.138328530259366,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004544108546637008,
|
|
"loss": 4.8497,
|
|
"mean_token_accuracy": 0.2290714219212532,
|
|
"num_tokens": 51056765.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.174235677719116,
|
|
"epoch": 2.1388088376561,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004543901632969247,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.22232733964920043,
|
|
"num_tokens": 51069559.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.235898017883301,
|
|
"epoch": 2.139289145052834,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045436946776524157,
|
|
"loss": 4.9064,
|
|
"mean_token_accuracy": 0.21977081149816513,
|
|
"num_tokens": 51080972.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.212474393844604,
|
|
"epoch": 2.139769452449568,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045434876806913204,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.22594887018203735,
|
|
"num_tokens": 51092101.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.296600484848023,
|
|
"epoch": 2.1402497598463017,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004543280642090767,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.21887072771787644,
|
|
"num_tokens": 51103372.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.252919149398804,
|
|
"epoch": 2.1407300672430356,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004543073561855562,
|
|
"loss": 4.9517,
|
|
"mean_token_accuracy": 0.2146154373884201,
|
|
"num_tokens": 51114856.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.351844263076782,
|
|
"epoch": 2.1412103746397695,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004542866439990513,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.21180437058210372,
|
|
"num_tokens": 51126354.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.299754858016968,
|
|
"epoch": 2.1416906820365034,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004542659276500429,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.21567759811878204,
|
|
"num_tokens": 51138341.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.187322568893433,
|
|
"epoch": 2.1421709894332372,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00045424520713901204,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.22690129429101943,
|
|
"num_tokens": 51150969.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.198380041122436,
|
|
"epoch": 2.142651296829971,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004542244824664396,
|
|
"loss": 4.8885,
|
|
"mean_token_accuracy": 0.21748742759227752,
|
|
"num_tokens": 51162199.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.218799877166748,
|
|
"epoch": 2.143131604226705,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045420375363280696,
|
|
"loss": 4.9554,
|
|
"mean_token_accuracy": 0.21481606364250183,
|
|
"num_tokens": 51173129.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.173846864700318,
|
|
"epoch": 2.143611911623439,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045418302063859526,
|
|
"loss": 4.8773,
|
|
"mean_token_accuracy": 0.22298049032688141,
|
|
"num_tokens": 51184593.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.238423299789429,
|
|
"epoch": 2.1440922190201728,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045416228348428583,
|
|
"loss": 4.9224,
|
|
"mean_token_accuracy": 0.2200753942131996,
|
|
"num_tokens": 51196524.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.2689262390136715,
|
|
"epoch": 2.1445725264169067,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045414154217036023,
|
|
"loss": 5.0068,
|
|
"mean_token_accuracy": 0.21674133688211442,
|
|
"num_tokens": 51209307.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.178395414352417,
|
|
"epoch": 2.1450528338136405,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045412079669730006,
|
|
"loss": 4.8909,
|
|
"mean_token_accuracy": 0.22972644120454788,
|
|
"num_tokens": 51220919.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.2160851001739506,
|
|
"epoch": 2.1455331412103744,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004541000470655867,
|
|
"loss": 4.8563,
|
|
"mean_token_accuracy": 0.22898981720209122,
|
|
"num_tokens": 51232930.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.179632091522217,
|
|
"epoch": 2.1460134486071087,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045407929327570215,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.2206220492720604,
|
|
"num_tokens": 51244697.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.2147516250610355,
|
|
"epoch": 2.1464937560038426,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004540585353281282,
|
|
"loss": 4.9182,
|
|
"mean_token_accuracy": 0.22836984544992447,
|
|
"num_tokens": 51255333.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.2982964515686035,
|
|
"epoch": 2.1469740634005765,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004540377732233467,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.21904638707637786,
|
|
"num_tokens": 51267649.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.269833087921143,
|
|
"epoch": 2.1474543707973104,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004540170069618397,
|
|
"loss": 4.8598,
|
|
"mean_token_accuracy": 0.22135900110006332,
|
|
"num_tokens": 51279576.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.275000476837159,
|
|
"epoch": 2.1479346781940443,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00045399623654408946,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.2167386457324028,
|
|
"num_tokens": 51290974.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.337709093093872,
|
|
"epoch": 2.148414985590778,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000453975461970578,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.21745382696390153,
|
|
"num_tokens": 51301405.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.307269763946533,
|
|
"epoch": 2.148895292987512,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004539546832417879,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.21165120154619216,
|
|
"num_tokens": 51313158.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.240895223617554,
|
|
"epoch": 2.149375600384246,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045393390035820136,
|
|
"loss": 4.9291,
|
|
"mean_token_accuracy": 0.22643761038780214,
|
|
"num_tokens": 51323789.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.204812812805176,
|
|
"epoch": 2.14985590778098,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000453913113320301,
|
|
"loss": 4.9441,
|
|
"mean_token_accuracy": 0.22136794179677963,
|
|
"num_tokens": 51334864.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.300289678573608,
|
|
"epoch": 2.1503362151777137,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004538923221285694,
|
|
"loss": 4.8441,
|
|
"mean_token_accuracy": 0.2188943848013878,
|
|
"num_tokens": 51345473.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.28816590309143,
|
|
"epoch": 2.1508165225744476,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004538715267834893,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.21605681478977204,
|
|
"num_tokens": 51356755.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.102611112594604,
|
|
"epoch": 2.1512968299711814,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004538507272855434,
|
|
"loss": 4.8301,
|
|
"mean_token_accuracy": 0.22608031779527665,
|
|
"num_tokens": 51368351.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.30010290145874,
|
|
"epoch": 2.1517771373679153,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045382992363521486,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.21167968958616257,
|
|
"num_tokens": 51379144.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.224101114273071,
|
|
"epoch": 2.152257444764649,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045380911583298633,
|
|
"loss": 4.9002,
|
|
"mean_token_accuracy": 0.22291434407234192,
|
|
"num_tokens": 51390732.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.184118795394897,
|
|
"epoch": 2.152737752161383,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045378830387934123,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.22457861602306367,
|
|
"num_tokens": 51401185.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.272035360336304,
|
|
"epoch": 2.1532180595581174,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004537674877747626,
|
|
"loss": 4.9648,
|
|
"mean_token_accuracy": 0.21384980380535126,
|
|
"num_tokens": 51412598.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.2545332431793215,
|
|
"epoch": 2.1536983669548513,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045374666751973365,
|
|
"loss": 4.8513,
|
|
"mean_token_accuracy": 0.2247536897659302,
|
|
"num_tokens": 51423248.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.127745246887207,
|
|
"epoch": 2.154178674351585,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045372584311473784,
|
|
"loss": 4.8171,
|
|
"mean_token_accuracy": 0.2325787752866745,
|
|
"num_tokens": 51433862.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.173068428039551,
|
|
"epoch": 2.154658981748319,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004537050145602587,
|
|
"loss": 4.932,
|
|
"mean_token_accuracy": 0.21991967111825944,
|
|
"num_tokens": 51445311.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.18431396484375,
|
|
"epoch": 2.155139289145053,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004536841818567798,
|
|
"loss": 4.8147,
|
|
"mean_token_accuracy": 0.22875108271837236,
|
|
"num_tokens": 51456550.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.280763387680054,
|
|
"epoch": 2.155619596541787,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004536633450047847,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.2210303798317909,
|
|
"num_tokens": 51467645.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.242958498001099,
|
|
"epoch": 2.1560999039385207,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045364250400475734,
|
|
"loss": 4.9008,
|
|
"mean_token_accuracy": 0.22655384987592697,
|
|
"num_tokens": 51478275.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.177510118484497,
|
|
"epoch": 2.1565802113352546,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004536216588571814,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.22532253265380858,
|
|
"num_tokens": 51489634.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.202427768707276,
|
|
"epoch": 2.1570605187319885,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000453600809562541,
|
|
"loss": 4.9014,
|
|
"mean_token_accuracy": 0.22713358402252198,
|
|
"num_tokens": 51500245.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.237389373779297,
|
|
"epoch": 2.1575408261287223,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004535799561213202,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.2236206978559494,
|
|
"num_tokens": 51511996.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.1922194480896,
|
|
"epoch": 2.158021133525456,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000453559098534003,
|
|
"loss": 4.8689,
|
|
"mean_token_accuracy": 0.22763263434171677,
|
|
"num_tokens": 51523522.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.239442205429077,
|
|
"epoch": 2.15850144092219,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004535382368010738,
|
|
"loss": 4.9405,
|
|
"mean_token_accuracy": 0.21928779035806656,
|
|
"num_tokens": 51535261.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.171402454376221,
|
|
"epoch": 2.158981748318924,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045351737092301676,
|
|
"loss": 4.8411,
|
|
"mean_token_accuracy": 0.223861201107502,
|
|
"num_tokens": 51546965.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.258289861679077,
|
|
"epoch": 2.159462055715658,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004534965009003165,
|
|
"loss": 4.8759,
|
|
"mean_token_accuracy": 0.2301410049200058,
|
|
"num_tokens": 51558976.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.3020354270935055,
|
|
"epoch": 2.1599423631123917,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004534756267334576,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.2110905721783638,
|
|
"num_tokens": 51571625.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.310091114044189,
|
|
"epoch": 2.160422670509126,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045345474842292455,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.21696867793798447,
|
|
"num_tokens": 51582732.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.214520502090454,
|
|
"epoch": 2.16090297790586,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004534338659692022,
|
|
"loss": 4.9146,
|
|
"mean_token_accuracy": 0.22015979439020156,
|
|
"num_tokens": 51594346.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.205715703964233,
|
|
"epoch": 2.161383285302594,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004534129793727753,
|
|
"loss": 4.927,
|
|
"mean_token_accuracy": 0.22009027749300003,
|
|
"num_tokens": 51606909.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.194458293914795,
|
|
"epoch": 2.1618635926993277,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004533920886341288,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.23020835369825363,
|
|
"num_tokens": 51617596.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.172086238861084,
|
|
"epoch": 2.1623439000960616,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004533711937537477,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.22715438902378082,
|
|
"num_tokens": 51627573.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.169159460067749,
|
|
"epoch": 2.1628242074927955,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004533502947321171,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.21557381749153137,
|
|
"num_tokens": 51640070.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.277215528488159,
|
|
"epoch": 2.1633045148895294,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004533293915697223,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.22319093942642212,
|
|
"num_tokens": 51651139.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.299956560134888,
|
|
"epoch": 2.1637848222862632,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045330848426704853,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.21669793277978897,
|
|
"num_tokens": 51661893.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.191579294204712,
|
|
"epoch": 2.164265129682997,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004532875728245813,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.21583209186792374,
|
|
"num_tokens": 51674266.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.236484861373901,
|
|
"epoch": 2.164745437079731,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045326665724280594,
|
|
"loss": 4.939,
|
|
"mean_token_accuracy": 0.227231003344059,
|
|
"num_tokens": 51685450.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.285590076446534,
|
|
"epoch": 2.165225744476465,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045324573752220814,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.2208284020423889,
|
|
"num_tokens": 51696779.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.296401309967041,
|
|
"epoch": 2.1657060518731988,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045322481366327365,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.22035850286483766,
|
|
"num_tokens": 51709387.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.207496690750122,
|
|
"epoch": 2.1661863592699326,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004532038856664882,
|
|
"loss": 4.9309,
|
|
"mean_token_accuracy": 0.2197367876768112,
|
|
"num_tokens": 51720978.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.357200765609742,
|
|
"epoch": 2.1666666666666665,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004531829535323376,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.21402827203273772,
|
|
"num_tokens": 51733510.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.205407381057739,
|
|
"epoch": 2.1671469740634004,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000453162017261308,
|
|
"loss": 4.8362,
|
|
"mean_token_accuracy": 0.23514433950185776,
|
|
"num_tokens": 51743660.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.188913822174072,
|
|
"epoch": 2.1676272814601343,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004531410768538854,
|
|
"loss": 4.867,
|
|
"mean_token_accuracy": 0.22894510626792908,
|
|
"num_tokens": 51754592.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.210267972946167,
|
|
"epoch": 2.168107588856868,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045312013231055596,
|
|
"loss": 4.8758,
|
|
"mean_token_accuracy": 0.22838261723518372,
|
|
"num_tokens": 51766241.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.2357497215271,
|
|
"epoch": 2.1685878962536025,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045309918363180593,
|
|
"loss": 4.8987,
|
|
"mean_token_accuracy": 0.22273167222738266,
|
|
"num_tokens": 51777718.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.1206896781921385,
|
|
"epoch": 2.1690682036503364,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045307823081812166,
|
|
"loss": 4.7922,
|
|
"mean_token_accuracy": 0.2332197204232216,
|
|
"num_tokens": 51788290.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.201221084594726,
|
|
"epoch": 2.1695485110470702,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045305727386998977,
|
|
"loss": 4.8629,
|
|
"mean_token_accuracy": 0.22485717684030532,
|
|
"num_tokens": 51800080.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.260825204849243,
|
|
"epoch": 2.170028818443804,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004530363127878966,
|
|
"loss": 4.9046,
|
|
"mean_token_accuracy": 0.2268513485789299,
|
|
"num_tokens": 51810155.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.271351957321167,
|
|
"epoch": 2.170509125840538,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045301534757232885,
|
|
"loss": 4.9462,
|
|
"mean_token_accuracy": 0.22163198739290238,
|
|
"num_tokens": 51823082.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.245570135116577,
|
|
"epoch": 2.170989433237272,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004529943782237735,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.21988258510828018,
|
|
"num_tokens": 51833280.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.269007587432862,
|
|
"epoch": 2.1714697406340058,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045297340474271717,
|
|
"loss": 4.9061,
|
|
"mean_token_accuracy": 0.21949662417173385,
|
|
"num_tokens": 51845105.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.2727649211883545,
|
|
"epoch": 2.1719500480307397,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004529524271296468,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.22909463495016097,
|
|
"num_tokens": 51856232.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.202229976654053,
|
|
"epoch": 2.1724303554274735,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045293144538504943,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.225759881734848,
|
|
"num_tokens": 51866218.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.214396715164185,
|
|
"epoch": 2.1729106628242074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004529104595094124,
|
|
"loss": 4.9211,
|
|
"mean_token_accuracy": 0.21892580687999724,
|
|
"num_tokens": 51877425.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.257857751846314,
|
|
"epoch": 2.1733909702209413,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045288946950322264,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.2222224533557892,
|
|
"num_tokens": 51888818.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.238804721832276,
|
|
"epoch": 2.173871277617675,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004528684753669677,
|
|
"loss": 4.8964,
|
|
"mean_token_accuracy": 0.21965697407722473,
|
|
"num_tokens": 51899875.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.224397468566894,
|
|
"epoch": 2.174351585014409,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004528474771011349,
|
|
"loss": 4.8661,
|
|
"mean_token_accuracy": 0.22874379456043242,
|
|
"num_tokens": 51911084.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.18680853843689,
|
|
"epoch": 2.174831892411143,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045282647470621176,
|
|
"loss": 4.9146,
|
|
"mean_token_accuracy": 0.22288999557495118,
|
|
"num_tokens": 51922165.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.266115474700928,
|
|
"epoch": 2.175312199807877,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045280546818268595,
|
|
"loss": 4.9204,
|
|
"mean_token_accuracy": 0.2226560026407242,
|
|
"num_tokens": 51934827.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.304421854019165,
|
|
"epoch": 2.175792507204611,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004527844575310452,
|
|
"loss": 4.956,
|
|
"mean_token_accuracy": 0.21439751535654067,
|
|
"num_tokens": 51947997.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.2355047225952145,
|
|
"epoch": 2.176272814601345,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045276344275177715,
|
|
"loss": 4.9731,
|
|
"mean_token_accuracy": 0.21997680962085725,
|
|
"num_tokens": 51959639.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.285352659225464,
|
|
"epoch": 2.176753121998079,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045274242384536984,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.21708685010671616,
|
|
"num_tokens": 51970716.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.254370880126953,
|
|
"epoch": 2.177233429394813,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004527214008123113,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.2273054078221321,
|
|
"num_tokens": 51982556.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.2755364894866945,
|
|
"epoch": 2.1777137367915467,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004527003736530895,
|
|
"loss": 4.9115,
|
|
"mean_token_accuracy": 0.22606787979602813,
|
|
"num_tokens": 51994894.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.234649610519409,
|
|
"epoch": 2.1781940441882806,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045267934236819265,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.21434174627065658,
|
|
"num_tokens": 52007128.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.242549657821655,
|
|
"epoch": 2.1786743515850144,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004526583069581091,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.21804459095001222,
|
|
"num_tokens": 52019598.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.326955986022949,
|
|
"epoch": 2.1791546589817483,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004526372674233272,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.22259819954633714,
|
|
"num_tokens": 52031445.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.342922258377075,
|
|
"epoch": 2.179634966378482,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045261622376433543,
|
|
"loss": 4.9759,
|
|
"mean_token_accuracy": 0.21814302653074263,
|
|
"num_tokens": 52042548.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.187623929977417,
|
|
"epoch": 2.180115273775216,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045259517598162237,
|
|
"loss": 4.8961,
|
|
"mean_token_accuracy": 0.22332047671079636,
|
|
"num_tokens": 52054147.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.172680854797363,
|
|
"epoch": 2.18059558117195,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004525741240756766,
|
|
"loss": 4.8547,
|
|
"mean_token_accuracy": 0.2289947122335434,
|
|
"num_tokens": 52065556.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.299084997177124,
|
|
"epoch": 2.181075888568684,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004525530680469871,
|
|
"loss": 4.973,
|
|
"mean_token_accuracy": 0.21607443392276765,
|
|
"num_tokens": 52077543.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.232616949081421,
|
|
"epoch": 2.1815561959654177,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045253200789604245,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.2274976596236229,
|
|
"num_tokens": 52088376.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.2030308723449705,
|
|
"epoch": 2.1820365033621516,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045251094362333186,
|
|
"loss": 4.9078,
|
|
"mean_token_accuracy": 0.22106473445892333,
|
|
"num_tokens": 52100019.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.183649015426636,
|
|
"epoch": 2.1825168107588855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004524898752293441,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.2243225544691086,
|
|
"num_tokens": 52110643.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.154497241973877,
|
|
"epoch": 2.18299711815562,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045246880271456857,
|
|
"loss": 4.8414,
|
|
"mean_token_accuracy": 0.22926569432020188,
|
|
"num_tokens": 52123092.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.34030179977417,
|
|
"epoch": 2.1834774255523537,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004524477260794944,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.21903387159109117,
|
|
"num_tokens": 52135371.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.2770391464233395,
|
|
"epoch": 2.1839577329490876,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045242664532461094,
|
|
"loss": 4.8741,
|
|
"mean_token_accuracy": 0.22888119667768478,
|
|
"num_tokens": 52145877.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.159749364852905,
|
|
"epoch": 2.1844380403458215,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045240556045040767,
|
|
"loss": 4.9299,
|
|
"mean_token_accuracy": 0.21984486579895018,
|
|
"num_tokens": 52158228.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.3361584663391115,
|
|
"epoch": 2.1849183477425553,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045238447145737397,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.20893794298171997,
|
|
"num_tokens": 52169515.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.288297319412232,
|
|
"epoch": 2.185398655139289,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045236337834599966,
|
|
"loss": 4.9505,
|
|
"mean_token_accuracy": 0.22106326818466188,
|
|
"num_tokens": 52179846.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.096581745147705,
|
|
"epoch": 2.185878962536023,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045234228111677434,
|
|
"loss": 4.8076,
|
|
"mean_token_accuracy": 0.22514103949069977,
|
|
"num_tokens": 52191095.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.276009464263916,
|
|
"epoch": 2.186359269932757,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004523211797701878,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.21564510613679885,
|
|
"num_tokens": 52202289.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.182168197631836,
|
|
"epoch": 2.186839577329491,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045230007430673014,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.22776093035936357,
|
|
"num_tokens": 52214424.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.283871746063232,
|
|
"epoch": 2.1873198847262247,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004522789647268911,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.21634564846754073,
|
|
"num_tokens": 52225446.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.228879165649414,
|
|
"epoch": 2.1878001921229586,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004522578510311609,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.22041349112987518,
|
|
"num_tokens": 52236063.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.178937768936157,
|
|
"epoch": 2.1882804995196925,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045223673322002984,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.22366690039634704,
|
|
"num_tokens": 52248618.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.271890926361084,
|
|
"epoch": 2.1887608069164264,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045221561129398804,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.2122838854789734,
|
|
"num_tokens": 52261913.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.283578205108642,
|
|
"epoch": 2.1892411143131603,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000452194485253526,
|
|
"loss": 4.8875,
|
|
"mean_token_accuracy": 0.22256312221288682,
|
|
"num_tokens": 52273838.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.215548038482666,
|
|
"epoch": 2.189721421709894,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004521733550991342,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.22570301592350006,
|
|
"num_tokens": 52285464.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.192488813400269,
|
|
"epoch": 2.1902017291066285,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045215222083130316,
|
|
"loss": 4.8684,
|
|
"mean_token_accuracy": 0.22632960230112076,
|
|
"num_tokens": 52295800.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.304665517807007,
|
|
"epoch": 2.1906820365033624,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004521310824505236,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.2182232066988945,
|
|
"num_tokens": 52307243.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.246120262145996,
|
|
"epoch": 2.1911623439000962,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045210993995728623,
|
|
"loss": 4.8787,
|
|
"mean_token_accuracy": 0.22787655293941497,
|
|
"num_tokens": 52317065.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.2058783054351805,
|
|
"epoch": 2.19164265129683,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000452088793352082,
|
|
"loss": 4.9258,
|
|
"mean_token_accuracy": 0.21657868325710297,
|
|
"num_tokens": 52328385.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.138287305831909,
|
|
"epoch": 2.192122958693564,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004520676426354018,
|
|
"loss": 4.8603,
|
|
"mean_token_accuracy": 0.2266307458281517,
|
|
"num_tokens": 52340046.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.176139831542969,
|
|
"epoch": 2.192603266090298,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004520464878077368,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.22773883044719695,
|
|
"num_tokens": 52352071.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.352715015411377,
|
|
"epoch": 2.1930835734870318,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045202532886957805,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.2174594819545746,
|
|
"num_tokens": 52364173.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.182467889785767,
|
|
"epoch": 2.1935638808837656,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045200416582141676,
|
|
"loss": 4.8251,
|
|
"mean_token_accuracy": 0.22713367640972137,
|
|
"num_tokens": 52374690.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.300544548034668,
|
|
"epoch": 2.1940441882804995,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004519829986637444,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.21584999412298203,
|
|
"num_tokens": 52385661.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.263431453704834,
|
|
"epoch": 2.1945244956772334,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004519618273970523,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.21880888491868972,
|
|
"num_tokens": 52396759.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.3286796569824215,
|
|
"epoch": 2.1950048030739673,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045194065202183205,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.21353908032178878,
|
|
"num_tokens": 52409122.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.3805742263793945,
|
|
"epoch": 2.195485110470701,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004519194725385752,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.20878787487745284,
|
|
"num_tokens": 52421318.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.158284664154053,
|
|
"epoch": 2.195965417867435,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045189828894777364,
|
|
"loss": 4.8772,
|
|
"mean_token_accuracy": 0.22732447683811188,
|
|
"num_tokens": 52432595.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.175820922851562,
|
|
"epoch": 2.196445725264169,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00045187710124991904,
|
|
"loss": 4.9066,
|
|
"mean_token_accuracy": 0.22221854329109192,
|
|
"num_tokens": 52444423.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.286258554458618,
|
|
"epoch": 2.196926032660903,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004518559094455034,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.21861122995615007,
|
|
"num_tokens": 52457183.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.313595533370972,
|
|
"epoch": 2.1974063400576367,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004518347135350187,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.22122288644313812,
|
|
"num_tokens": 52469624.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.286441707611084,
|
|
"epoch": 2.1978866474543706,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045181351351895703,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.21261027455329895,
|
|
"num_tokens": 52481369.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.228226947784424,
|
|
"epoch": 2.198366954851105,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004517923093978106,
|
|
"loss": 4.861,
|
|
"mean_token_accuracy": 0.22298421263694762,
|
|
"num_tokens": 52493315.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.225436782836914,
|
|
"epoch": 2.1988472622478388,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004517711011720717,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.2231158509850502,
|
|
"num_tokens": 52504929.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.236334657669067,
|
|
"epoch": 2.1993275696445727,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004517498888422327,
|
|
"loss": 4.8708,
|
|
"mean_token_accuracy": 0.21546072512865067,
|
|
"num_tokens": 52518364.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.260016298294067,
|
|
"epoch": 2.1998078770413065,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004517286724087862,
|
|
"loss": 4.9054,
|
|
"mean_token_accuracy": 0.22055712938308716,
|
|
"num_tokens": 52530359.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.190277051925659,
|
|
"epoch": 2.2002881844380404,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004517074518722247,
|
|
"loss": 4.9251,
|
|
"mean_token_accuracy": 0.225760580599308,
|
|
"num_tokens": 52542242.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.2708031177520756,
|
|
"epoch": 2.2007684918347743,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045168622723304084,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.21671066135168077,
|
|
"num_tokens": 52552838.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.256677532196045,
|
|
"epoch": 2.201248799231508,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004516649984917274,
|
|
"loss": 4.9013,
|
|
"mean_token_accuracy": 0.21981012672185898,
|
|
"num_tokens": 52564568.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.281131839752197,
|
|
"epoch": 2.201729106628242,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045164376564877734,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.21524348109960556,
|
|
"num_tokens": 52577563.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.288108158111572,
|
|
"epoch": 2.202209414024976,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045162252870468354,
|
|
"loss": 4.979,
|
|
"mean_token_accuracy": 0.21375205665826796,
|
|
"num_tokens": 52590295.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.276605796813965,
|
|
"epoch": 2.20268972142171,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004516012876599391,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.2303829610347748,
|
|
"num_tokens": 52602727.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.1466817378997805,
|
|
"epoch": 2.2031700288184437,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045158004251503715,
|
|
"loss": 4.8232,
|
|
"mean_token_accuracy": 0.22775801420211791,
|
|
"num_tokens": 52613422.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.152949666976928,
|
|
"epoch": 2.2036503362151776,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045155879327047087,
|
|
"loss": 4.8601,
|
|
"mean_token_accuracy": 0.2296785831451416,
|
|
"num_tokens": 52624907.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.2883429527282715,
|
|
"epoch": 2.2041306436119115,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004515375399267338,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.21764634400606156,
|
|
"num_tokens": 52635864.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.248695278167725,
|
|
"epoch": 2.2046109510086453,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045151628248431925,
|
|
"loss": 5.0213,
|
|
"mean_token_accuracy": 0.2167029023170471,
|
|
"num_tokens": 52647023.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.251709222793579,
|
|
"epoch": 2.2050912584053792,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045149502094372077,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.22109463512897493,
|
|
"num_tokens": 52658846.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.213857650756836,
|
|
"epoch": 2.2055715658021136,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045147375530543195,
|
|
"loss": 4.7848,
|
|
"mean_token_accuracy": 0.23528305143117906,
|
|
"num_tokens": 52671363.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.271751165390015,
|
|
"epoch": 2.2060518731988474,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045145248556994653,
|
|
"loss": 4.9923,
|
|
"mean_token_accuracy": 0.2126673325896263,
|
|
"num_tokens": 52682734.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.217284393310547,
|
|
"epoch": 2.2065321805955813,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004514312117377584,
|
|
"loss": 4.8648,
|
|
"mean_token_accuracy": 0.22582547664642333,
|
|
"num_tokens": 52693272.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.205141687393189,
|
|
"epoch": 2.207012487992315,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004514099338093613,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.22323437333106994,
|
|
"num_tokens": 52703395.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.215268278121949,
|
|
"epoch": 2.207492795389049,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004513886517852496,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.22344650328159332,
|
|
"num_tokens": 52715870.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.264265251159668,
|
|
"epoch": 2.207973102785783,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000451367365665917,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.22354543805122376,
|
|
"num_tokens": 52726922.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.2249833106994625,
|
|
"epoch": 2.208453410182517,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045134607545185785,
|
|
"loss": 4.926,
|
|
"mean_token_accuracy": 0.21970305889844893,
|
|
"num_tokens": 52738211.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.258601331710816,
|
|
"epoch": 2.2089337175792507,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004513247811435666,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.22683105617761612,
|
|
"num_tokens": 52749267.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.168635368347168,
|
|
"epoch": 2.2094140249759846,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045130348274153735,
|
|
"loss": 4.8855,
|
|
"mean_token_accuracy": 0.22028826773166657,
|
|
"num_tokens": 52760520.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.244860219955444,
|
|
"epoch": 2.2098943323727185,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045128218024626486,
|
|
"loss": 4.862,
|
|
"mean_token_accuracy": 0.23352981656789779,
|
|
"num_tokens": 52772865.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.21704216003418,
|
|
"epoch": 2.2103746397694524,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004512608736582436,
|
|
"loss": 4.9207,
|
|
"mean_token_accuracy": 0.22517919540405273,
|
|
"num_tokens": 52783935.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.1268397808074955,
|
|
"epoch": 2.2108549471661862,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004512395629779682,
|
|
"loss": 4.8456,
|
|
"mean_token_accuracy": 0.2286387249827385,
|
|
"num_tokens": 52794980.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.289114284515381,
|
|
"epoch": 2.21133525456292,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004512182482059335,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.2077925056219101,
|
|
"num_tokens": 52806426.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.178171920776367,
|
|
"epoch": 2.211815561959654,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004511969293426343,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.22590079307556152,
|
|
"num_tokens": 52816832.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.266859722137451,
|
|
"epoch": 2.212295869356388,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045117560638856567,
|
|
"loss": 4.9072,
|
|
"mean_token_accuracy": 0.22513401955366136,
|
|
"num_tokens": 52829913.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.262035655975342,
|
|
"epoch": 2.212776176753122,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004511542793442225,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.222748039662838,
|
|
"num_tokens": 52841300.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.183122205734253,
|
|
"epoch": 2.213256484149856,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004511329482101001,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.22153398990631104,
|
|
"num_tokens": 52852862.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.240936803817749,
|
|
"epoch": 2.21373679154659,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004511116129866936,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.2213187038898468,
|
|
"num_tokens": 52863499.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.267353963851929,
|
|
"epoch": 2.214217098943324,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045109027367449845,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.22631914913654327,
|
|
"num_tokens": 52875459.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.215583276748657,
|
|
"epoch": 2.2146974063400577,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045106893027400995,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.22024632394313812,
|
|
"num_tokens": 52886758.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.208404541015625,
|
|
"epoch": 2.2151777137367916,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045104758278572375,
|
|
"loss": 4.8669,
|
|
"mean_token_accuracy": 0.2232646554708481,
|
|
"num_tokens": 52898703.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.295749950408935,
|
|
"epoch": 2.2156580211335255,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004510262312101355,
|
|
"loss": 4.9291,
|
|
"mean_token_accuracy": 0.21496911346912384,
|
|
"num_tokens": 52910455.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.161748552322388,
|
|
"epoch": 2.2161383285302594,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004510048755477407,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.22383417189121246,
|
|
"num_tokens": 52921992.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.216359853744507,
|
|
"epoch": 2.2166186359269933,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004509835157990354,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.21846764236688615,
|
|
"num_tokens": 52934994.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.2688497543334964,
|
|
"epoch": 2.217098943323727,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045096215196451547,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.2133615031838417,
|
|
"num_tokens": 52945745.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.287591886520386,
|
|
"epoch": 2.217579250720461,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045094078404467683,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.21574087291955948,
|
|
"num_tokens": 52957470.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.331320905685425,
|
|
"epoch": 2.218059558117195,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045091941204001564,
|
|
"loss": 4.9324,
|
|
"mean_token_accuracy": 0.22360492497682571,
|
|
"num_tokens": 52968584.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.2488502025604244,
|
|
"epoch": 2.218539865513929,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000450898035951028,
|
|
"loss": 4.9293,
|
|
"mean_token_accuracy": 0.2189251810312271,
|
|
"num_tokens": 52980187.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.203431749343872,
|
|
"epoch": 2.2190201729106627,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045087665577821034,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.23209090381860734,
|
|
"num_tokens": 52990478.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.2402088165283205,
|
|
"epoch": 2.2195004803073966,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000450855271522059,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.210091695189476,
|
|
"num_tokens": 53001130.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.318418741226196,
|
|
"epoch": 2.219980787704131,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045083388318307044,
|
|
"loss": 4.9842,
|
|
"mean_token_accuracy": 0.21856217384338378,
|
|
"num_tokens": 53013057.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.304359292984008,
|
|
"epoch": 2.2204610951008648,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004508124907617411,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.2191627189517021,
|
|
"num_tokens": 53024333.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.197845935821533,
|
|
"epoch": 2.2209414024975986,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004507910942585679,
|
|
"loss": 4.931,
|
|
"mean_token_accuracy": 0.21633582413196564,
|
|
"num_tokens": 53036723.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.30280442237854,
|
|
"epoch": 2.2214217098943325,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004507696936740475,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.2237219586968422,
|
|
"num_tokens": 53048183.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.218694496154785,
|
|
"epoch": 2.2219020172910664,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004507482890086767,
|
|
"loss": 4.9325,
|
|
"mean_token_accuracy": 0.22400079518556595,
|
|
"num_tokens": 53061467.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.203434801101684,
|
|
"epoch": 2.2223823246878003,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004507268802629525,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.22330165654420853,
|
|
"num_tokens": 53072833.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.27309832572937,
|
|
"epoch": 2.222862632084534,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004507054674373719,
|
|
"loss": 4.89,
|
|
"mean_token_accuracy": 0.2176015168428421,
|
|
"num_tokens": 53084109.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.246954774856567,
|
|
"epoch": 2.223342939481268,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045068405053243216,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.22333049178123474,
|
|
"num_tokens": 53095997.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.164844274520874,
|
|
"epoch": 2.223823246878002,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004506626295486304,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.23420249968767165,
|
|
"num_tokens": 53107518.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.202484273910523,
|
|
"epoch": 2.224303554274736,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00045064120448646405,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.22586372792720794,
|
|
"num_tokens": 53118908.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.24341516494751,
|
|
"epoch": 2.2247838616714697,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004506197753464304,
|
|
"loss": 4.897,
|
|
"mean_token_accuracy": 0.22881498783826829,
|
|
"num_tokens": 53129404.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.2722066879272464,
|
|
"epoch": 2.2252641690682036,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045059834212902707,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.21661216169595718,
|
|
"num_tokens": 53141364.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.273164415359497,
|
|
"epoch": 2.2257444764649374,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045057690483475167,
|
|
"loss": 4.9047,
|
|
"mean_token_accuracy": 0.22450898438692093,
|
|
"num_tokens": 53153617.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.238543605804443,
|
|
"epoch": 2.2262247838616713,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004505554634641019,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.21454287469387054,
|
|
"num_tokens": 53166537.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.231886291503907,
|
|
"epoch": 2.226705091258405,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045053401801757554,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.2216634452342987,
|
|
"num_tokens": 53178979.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.252911233901978,
|
|
"epoch": 2.227185398655139,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00045051256849567054,
|
|
"loss": 4.9499,
|
|
"mean_token_accuracy": 0.22578862756490709,
|
|
"num_tokens": 53190177.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.263202714920044,
|
|
"epoch": 2.227665706051873,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045049111489888486,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.22687104046344758,
|
|
"num_tokens": 53201398.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.279418849945069,
|
|
"epoch": 2.2281460134486073,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004504696572277165,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.2181571513414383,
|
|
"num_tokens": 53213795.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.224297952651978,
|
|
"epoch": 2.228626320845341,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045044819548266385,
|
|
"loss": 4.9907,
|
|
"mean_token_accuracy": 0.21408381313085556,
|
|
"num_tokens": 53226831.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.302975225448608,
|
|
"epoch": 2.229106628242075,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045042672966422506,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.21956822723150254,
|
|
"num_tokens": 53238558.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.253889179229736,
|
|
"epoch": 2.229586935638809,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045040525977289847,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.22294055074453353,
|
|
"num_tokens": 53250376.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.275496912002564,
|
|
"epoch": 2.230067243035543,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004503837858091826,
|
|
"loss": 4.8789,
|
|
"mean_token_accuracy": 0.22562482655048371,
|
|
"num_tokens": 53260872.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.191474294662475,
|
|
"epoch": 2.2305475504322767,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045036230777357604,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.2241663381457329,
|
|
"num_tokens": 53271363.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.276864624023437,
|
|
"epoch": 2.2310278578290106,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004503408256665774,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.21531836986541747,
|
|
"num_tokens": 53282356.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.269224166870117,
|
|
"epoch": 2.2315081652257445,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045031933948868545,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.2195221409201622,
|
|
"num_tokens": 53293675.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.237408542633057,
|
|
"epoch": 2.2319884726224783,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045029784924039903,
|
|
"loss": 4.8492,
|
|
"mean_token_accuracy": 0.23161215782165528,
|
|
"num_tokens": 53305193.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.207571601867675,
|
|
"epoch": 2.2324687800192122,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045027635492221716,
|
|
"loss": 4.8324,
|
|
"mean_token_accuracy": 0.23122619837522507,
|
|
"num_tokens": 53315729.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.1768323421478275,
|
|
"epoch": 2.232949087415946,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045025485653463866,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.2209918439388275,
|
|
"num_tokens": 53327220.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.192916679382324,
|
|
"epoch": 2.23342939481268,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004502333540781628,
|
|
"loss": 4.9484,
|
|
"mean_token_accuracy": 0.2170170873403549,
|
|
"num_tokens": 53337565.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.281071901321411,
|
|
"epoch": 2.233909702209414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004502118475532888,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.22289046496152878,
|
|
"num_tokens": 53348791.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.193204307556153,
|
|
"epoch": 2.2343900096061478,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000450190336960516,
|
|
"loss": 4.8809,
|
|
"mean_token_accuracy": 0.22458298057317733,
|
|
"num_tokens": 53361341.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.210828638076782,
|
|
"epoch": 2.2348703170028816,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004501688223003438,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.21663014739751815,
|
|
"num_tokens": 53372085.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.214933013916015,
|
|
"epoch": 2.235350624399616,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004501473035732717,
|
|
"loss": 4.91,
|
|
"mean_token_accuracy": 0.22296539545059205,
|
|
"num_tokens": 53383665.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.232224607467652,
|
|
"epoch": 2.23583093179635,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004501257807797993,
|
|
"loss": 4.9026,
|
|
"mean_token_accuracy": 0.21829243004322052,
|
|
"num_tokens": 53394697.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.193957185745239,
|
|
"epoch": 2.2363112391930837,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045010425392042624,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.2201283097267151,
|
|
"num_tokens": 53405538.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.319758510589599,
|
|
"epoch": 2.2367915465898176,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004500827229956524,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.21682668328285218,
|
|
"num_tokens": 53416515.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.262248229980469,
|
|
"epoch": 2.2372718539865515,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045006118800597757,
|
|
"loss": 4.8674,
|
|
"mean_token_accuracy": 0.22055206298828126,
|
|
"num_tokens": 53426530.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.261639070510864,
|
|
"epoch": 2.2377521613832854,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045003964895190177,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.21776846647262574,
|
|
"num_tokens": 53438514.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.144234371185303,
|
|
"epoch": 2.2382324687800192,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004500181058339251,
|
|
"loss": 4.8341,
|
|
"mean_token_accuracy": 0.23479900509119034,
|
|
"num_tokens": 53448845.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.227501630783081,
|
|
"epoch": 2.238712776176753,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004499965586525478,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.216687373816967,
|
|
"num_tokens": 53460526.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.393211412429809,
|
|
"epoch": 2.239193083573487,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044997500740826993,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.22088383436203002,
|
|
"num_tokens": 53471997.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.201370000839233,
|
|
"epoch": 2.239673390970221,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000449953452101592,
|
|
"loss": 4.9644,
|
|
"mean_token_accuracy": 0.22097888737916946,
|
|
"num_tokens": 53483097.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.177021503448486,
|
|
"epoch": 2.2401536983669548,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044993189273301445,
|
|
"loss": 4.8778,
|
|
"mean_token_accuracy": 0.23279569745063783,
|
|
"num_tokens": 53494877.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.236870908737183,
|
|
"epoch": 2.2406340057636887,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004499103293030377,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.22707222253084183,
|
|
"num_tokens": 53507065.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.296442651748658,
|
|
"epoch": 2.2411143131604225,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004498887618121625,
|
|
"loss": 4.9392,
|
|
"mean_token_accuracy": 0.2242847666144371,
|
|
"num_tokens": 53518188.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.17414288520813,
|
|
"epoch": 2.2415946205571564,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004498671902608897,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.22386835664510726,
|
|
"num_tokens": 53529872.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.2397924900054935,
|
|
"epoch": 2.2420749279538903,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004498456146497198,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.2207154244184494,
|
|
"num_tokens": 53540175.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.204226684570313,
|
|
"epoch": 2.2425552353506246,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044982403497915405,
|
|
"loss": 4.8174,
|
|
"mean_token_accuracy": 0.22311179637908934,
|
|
"num_tokens": 53552520.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.223599195480347,
|
|
"epoch": 2.2430355427473585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044980245124969333,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.22039095908403397,
|
|
"num_tokens": 53563937.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.20012526512146,
|
|
"epoch": 2.2435158501440924,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004497808634618386,
|
|
"loss": 4.8821,
|
|
"mean_token_accuracy": 0.21693841367959976,
|
|
"num_tokens": 53574654.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.238617038726806,
|
|
"epoch": 2.2439961575408263,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004497592716160913,
|
|
"loss": 4.9539,
|
|
"mean_token_accuracy": 0.21787745356559754,
|
|
"num_tokens": 53586848.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.2392950534820555,
|
|
"epoch": 2.24447646493756,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044973767571295273,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.22257062792778015,
|
|
"num_tokens": 53598200.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.213217687606812,
|
|
"epoch": 2.244956772334294,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004497160757529241,
|
|
"loss": 4.8637,
|
|
"mean_token_accuracy": 0.22870618402957915,
|
|
"num_tokens": 53609957.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.240585660934448,
|
|
"epoch": 2.245437079731028,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044969447173650695,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.22619887739419936,
|
|
"num_tokens": 53621029.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.22138819694519,
|
|
"epoch": 2.245917387127762,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000449672863664203,
|
|
"loss": 4.9032,
|
|
"mean_token_accuracy": 0.22272591888904572,
|
|
"num_tokens": 53633279.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.226912212371826,
|
|
"epoch": 2.2463976945244957,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044965125153651375,
|
|
"loss": 4.9151,
|
|
"mean_token_accuracy": 0.22267891019582747,
|
|
"num_tokens": 53643959.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.22492618560791,
|
|
"epoch": 2.2468780019212296,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004496296353539411,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.22243613749742508,
|
|
"num_tokens": 53655215.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.269690704345703,
|
|
"epoch": 2.2473583093179634,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004496080151169869,
|
|
"loss": 4.8995,
|
|
"mean_token_accuracy": 0.22779991030693053,
|
|
"num_tokens": 53666557.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.2492719173431395,
|
|
"epoch": 2.2478386167146973,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044958639082615294,
|
|
"loss": 4.9781,
|
|
"mean_token_accuracy": 0.2191444978117943,
|
|
"num_tokens": 53679626.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.207081699371338,
|
|
"epoch": 2.248318924111431,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004495647624819415,
|
|
"loss": 4.9078,
|
|
"mean_token_accuracy": 0.22337686121463776,
|
|
"num_tokens": 53691681.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.257059526443482,
|
|
"epoch": 2.248799231508165,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044954313008485457,
|
|
"loss": 4.8685,
|
|
"mean_token_accuracy": 0.22803826183080672,
|
|
"num_tokens": 53703320.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.182119703292846,
|
|
"epoch": 2.249279538904899,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044952149363539453,
|
|
"loss": 4.8375,
|
|
"mean_token_accuracy": 0.22561087161302568,
|
|
"num_tokens": 53714867.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.200799036026001,
|
|
"epoch": 2.249759846301633,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004494998531340635,
|
|
"loss": 4.9561,
|
|
"mean_token_accuracy": 0.22113188356161118,
|
|
"num_tokens": 53726121.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.271017551422119,
|
|
"epoch": 2.2502401536983667,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004494782085813641,
|
|
"loss": 4.9686,
|
|
"mean_token_accuracy": 0.2199683666229248,
|
|
"num_tokens": 53736966.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.199404954910278,
|
|
"epoch": 2.250720461095101,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004494565599777988,
|
|
"loss": 4.8396,
|
|
"mean_token_accuracy": 0.23492411226034166,
|
|
"num_tokens": 53747446.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.212501382827758,
|
|
"epoch": 2.251200768491835,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044943490732387025,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.21281190365552902,
|
|
"num_tokens": 53759588.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.26312575340271,
|
|
"epoch": 2.251681075888569,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004494132506200811,
|
|
"loss": 4.9489,
|
|
"mean_token_accuracy": 0.22048983126878738,
|
|
"num_tokens": 53770314.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.227333116531372,
|
|
"epoch": 2.2521613832853027,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004493915898669341,
|
|
"loss": 4.8713,
|
|
"mean_token_accuracy": 0.22812264859676362,
|
|
"num_tokens": 53781251.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.273406934738159,
|
|
"epoch": 2.2526416906820366,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004493699250649323,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.21574821025133134,
|
|
"num_tokens": 53792676.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.298877906799317,
|
|
"epoch": 2.2531219980787704,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004493482562145786,
|
|
"loss": 4.9729,
|
|
"mean_token_accuracy": 0.21859216839075088,
|
|
"num_tokens": 53802714.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.210111904144287,
|
|
"epoch": 2.2536023054755043,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044932658331637605,
|
|
"loss": 4.9524,
|
|
"mean_token_accuracy": 0.21759840995073318,
|
|
"num_tokens": 53815043.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.253601741790772,
|
|
"epoch": 2.254082612872238,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004493049063708279,
|
|
"loss": 4.9249,
|
|
"mean_token_accuracy": 0.21183123141527177,
|
|
"num_tokens": 53827903.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.3312122344970705,
|
|
"epoch": 2.254562920268972,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044928322537843746,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.22155788391828538,
|
|
"num_tokens": 53839574.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.244658660888672,
|
|
"epoch": 2.255043227665706,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044926154033970793,
|
|
"loss": 4.8553,
|
|
"mean_token_accuracy": 0.23106950968503953,
|
|
"num_tokens": 53850488.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.252710247039795,
|
|
"epoch": 2.25552353506244,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000449239851255143,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.2240070581436157,
|
|
"num_tokens": 53860766.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.15909857749939,
|
|
"epoch": 2.2560038424591737,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044921815812524606,
|
|
"loss": 4.8868,
|
|
"mean_token_accuracy": 0.21882531344890593,
|
|
"num_tokens": 53872088.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.250496912002563,
|
|
"epoch": 2.2564841498559076,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044919646095052077,
|
|
"loss": 4.9402,
|
|
"mean_token_accuracy": 0.222981233894825,
|
|
"num_tokens": 53883302.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.168660020828247,
|
|
"epoch": 2.2569644572526415,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000449174759731471,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.23599445819854736,
|
|
"num_tokens": 53894310.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.264799547195435,
|
|
"epoch": 2.2574447646493754,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044915305446860046,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.21157455444335938,
|
|
"num_tokens": 53906760.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.232786846160889,
|
|
"epoch": 2.2579250720461097,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00044913134516241305,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.22032948285341264,
|
|
"num_tokens": 53918758.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.164526700973511,
|
|
"epoch": 2.2584053794428436,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004491096318134129,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.22525731921195985,
|
|
"num_tokens": 53932574.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.265543651580811,
|
|
"epoch": 2.2588856868395775,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004490879144221042,
|
|
"loss": 4.9509,
|
|
"mean_token_accuracy": 0.2242477983236313,
|
|
"num_tokens": 53943801.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.205193710327149,
|
|
"epoch": 2.2593659942363113,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044906619298899097,
|
|
"loss": 4.8931,
|
|
"mean_token_accuracy": 0.23412103205919266,
|
|
"num_tokens": 53955458.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.273860311508178,
|
|
"epoch": 2.2598463016330452,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004490444675145777,
|
|
"loss": 4.9276,
|
|
"mean_token_accuracy": 0.21761668771505355,
|
|
"num_tokens": 53967242.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.209068346023559,
|
|
"epoch": 2.260326609029779,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004490227379993686,
|
|
"loss": 4.9484,
|
|
"mean_token_accuracy": 0.2239930048584938,
|
|
"num_tokens": 53978953.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.279601287841797,
|
|
"epoch": 2.260806916426513,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004490010044438683,
|
|
"loss": 4.9423,
|
|
"mean_token_accuracy": 0.22479574680328368,
|
|
"num_tokens": 53990553.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.224512767791748,
|
|
"epoch": 2.261287223823247,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044897926684858133,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.22252236157655716,
|
|
"num_tokens": 54002187.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.261300849914551,
|
|
"epoch": 2.2617675312199808,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044895752521401246,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.21945257782936095,
|
|
"num_tokens": 54014202.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.238504838943482,
|
|
"epoch": 2.2622478386167146,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004489357795406663,
|
|
"loss": 4.9217,
|
|
"mean_token_accuracy": 0.22414778620004655,
|
|
"num_tokens": 54026286.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.253145980834961,
|
|
"epoch": 2.2627281460134485,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004489140298290479,
|
|
"loss": 4.9333,
|
|
"mean_token_accuracy": 0.21986344307661057,
|
|
"num_tokens": 54038845.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.3395427703857425,
|
|
"epoch": 2.2632084534101824,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044889227607966217,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.21541474759578705,
|
|
"num_tokens": 54049991.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.201151609420776,
|
|
"epoch": 2.2636887608069163,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044887051829301406,
|
|
"loss": 4.8795,
|
|
"mean_token_accuracy": 0.22167337387800218,
|
|
"num_tokens": 54061408.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.2071412086486815,
|
|
"epoch": 2.26416906820365,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044884875646960886,
|
|
"loss": 4.8882,
|
|
"mean_token_accuracy": 0.22650287598371505,
|
|
"num_tokens": 54072670.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.260703706741333,
|
|
"epoch": 2.264649375600384,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044882699060995175,
|
|
"loss": 4.9098,
|
|
"mean_token_accuracy": 0.22213997691869736,
|
|
"num_tokens": 54084555.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.153254652023316,
|
|
"epoch": 2.2651296829971184,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004488052207145481,
|
|
"loss": 4.8539,
|
|
"mean_token_accuracy": 0.22797705084085465,
|
|
"num_tokens": 54096764.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.33255443572998,
|
|
"epoch": 2.2656099903938522,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044878344678390324,
|
|
"loss": 4.9824,
|
|
"mean_token_accuracy": 0.2196044757962227,
|
|
"num_tokens": 54109101.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.31586766242981,
|
|
"epoch": 2.266090297790586,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044876166881852286,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.2165826216340065,
|
|
"num_tokens": 54120217.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.248987674713135,
|
|
"epoch": 2.26657060518732,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004487398868189125,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.22168087661266328,
|
|
"num_tokens": 54132059.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.3229883193969725,
|
|
"epoch": 2.267050912584054,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044871810078557777,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.21555239111185073,
|
|
"num_tokens": 54141928.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.276185846328735,
|
|
"epoch": 2.2675312199807878,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004486963107190247,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.21850961595773696,
|
|
"num_tokens": 54153052.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.335283660888672,
|
|
"epoch": 2.2680115273775217,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044867451661975894,
|
|
"loss": 4.94,
|
|
"mean_token_accuracy": 0.21467501819133758,
|
|
"num_tokens": 54163539.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.177802419662475,
|
|
"epoch": 2.2684918347742555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044865271848828673,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.2255900487303734,
|
|
"num_tokens": 54176313.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.2648321151733395,
|
|
"epoch": 2.2689721421709894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000448630916325114,
|
|
"loss": 4.9731,
|
|
"mean_token_accuracy": 0.21404950469732284,
|
|
"num_tokens": 54187080.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.261587047576905,
|
|
"epoch": 2.2694524495677233,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000448609110130747,
|
|
"loss": 4.9431,
|
|
"mean_token_accuracy": 0.2215867593884468,
|
|
"num_tokens": 54197856.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.279731941223145,
|
|
"epoch": 2.269932756964457,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044858729990569193,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.21835249215364455,
|
|
"num_tokens": 54210865.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.215116930007935,
|
|
"epoch": 2.270413064361191,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044856548565045523,
|
|
"loss": 4.839,
|
|
"mean_token_accuracy": 0.22448943555355072,
|
|
"num_tokens": 54222719.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.258306312561035,
|
|
"epoch": 2.270893371757925,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044854366736554323,
|
|
"loss": 4.8861,
|
|
"mean_token_accuracy": 0.22772839814424514,
|
|
"num_tokens": 54233874.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.15136981010437,
|
|
"epoch": 2.271373679154659,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044852184505146274,
|
|
"loss": 4.7991,
|
|
"mean_token_accuracy": 0.22663939148187637,
|
|
"num_tokens": 54245966.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.218375730514526,
|
|
"epoch": 2.2718539865513927,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004485000187087202,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.22408788204193114,
|
|
"num_tokens": 54256468.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.1800073146820065,
|
|
"epoch": 2.272334293948127,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004484781883378224,
|
|
"loss": 4.8231,
|
|
"mean_token_accuracy": 0.2214045464992523,
|
|
"num_tokens": 54266362.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.232305479049683,
|
|
"epoch": 2.2728146013448605,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044845635393927623,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.21472273170948028,
|
|
"num_tokens": 54278365.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.298816156387329,
|
|
"epoch": 2.273294908741595,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004484345155135886,
|
|
"loss": 5.0044,
|
|
"mean_token_accuracy": 0.21872389912605286,
|
|
"num_tokens": 54289310.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.203012990951538,
|
|
"epoch": 2.2737752161383287,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004484126730612664,
|
|
"loss": 4.8586,
|
|
"mean_token_accuracy": 0.22349931299686432,
|
|
"num_tokens": 54300421.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.177694940567017,
|
|
"epoch": 2.2742555235350626,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000448390826582817,
|
|
"loss": 4.9352,
|
|
"mean_token_accuracy": 0.22294449359178542,
|
|
"num_tokens": 54312803.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.277594995498657,
|
|
"epoch": 2.2747358309317964,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044836897607874744,
|
|
"loss": 4.9485,
|
|
"mean_token_accuracy": 0.22241282165050508,
|
|
"num_tokens": 54324651.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.232652091979981,
|
|
"epoch": 2.2752161383285303,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000448347121549565,
|
|
"loss": 4.841,
|
|
"mean_token_accuracy": 0.2349979281425476,
|
|
"num_tokens": 54334841.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.237567138671875,
|
|
"epoch": 2.275696445725264,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004483252629957771,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.2218261882662773,
|
|
"num_tokens": 54346685.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.17869553565979,
|
|
"epoch": 2.276176753121998,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044830340041789133,
|
|
"loss": 4.9768,
|
|
"mean_token_accuracy": 0.21565035879611968,
|
|
"num_tokens": 54358710.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.208660221099853,
|
|
"epoch": 2.276657060518732,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004482815338164152,
|
|
"loss": 4.946,
|
|
"mean_token_accuracy": 0.2238724410533905,
|
|
"num_tokens": 54369695.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.242773103713989,
|
|
"epoch": 2.277137367915466,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004482596631918564,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.2224190577864647,
|
|
"num_tokens": 54381605.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.25229229927063,
|
|
"epoch": 2.2776176753121997,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044823778854472267,
|
|
"loss": 4.9069,
|
|
"mean_token_accuracy": 0.2248014271259308,
|
|
"num_tokens": 54392309.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.232637119293213,
|
|
"epoch": 2.2780979827089336,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004482159098755219,
|
|
"loss": 4.9333,
|
|
"mean_token_accuracy": 0.22155639231204988,
|
|
"num_tokens": 54403195.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.183228445053101,
|
|
"epoch": 2.2785782901056675,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004481940271847621,
|
|
"loss": 4.8859,
|
|
"mean_token_accuracy": 0.22822879999876022,
|
|
"num_tokens": 54415105.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.218152379989624,
|
|
"epoch": 2.2790585975024014,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004481721404729513,
|
|
"loss": 4.9185,
|
|
"mean_token_accuracy": 0.22222390472888948,
|
|
"num_tokens": 54425798.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.26456036567688,
|
|
"epoch": 2.2795389048991357,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004481502497405975,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.2221813678741455,
|
|
"num_tokens": 54437254.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.244229412078857,
|
|
"epoch": 2.280019212295869,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004481283549882091,
|
|
"loss": 4.9071,
|
|
"mean_token_accuracy": 0.21715707778930665,
|
|
"num_tokens": 54448152.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.2216572761535645,
|
|
"epoch": 2.2804995196926034,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044810645621629443,
|
|
"loss": 4.9406,
|
|
"mean_token_accuracy": 0.2179849550127983,
|
|
"num_tokens": 54460066.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.284715032577514,
|
|
"epoch": 2.2809798270893373,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044808455342536176,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.2206544429063797,
|
|
"num_tokens": 54471769.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.189642524719238,
|
|
"epoch": 2.281460134486071,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044806264661591976,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.2408903196454048,
|
|
"num_tokens": 54483630.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.220715141296386,
|
|
"epoch": 2.281940441882805,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004480407357884771,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.21938869655132293,
|
|
"num_tokens": 54495696.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.219896841049194,
|
|
"epoch": 2.282420749279539,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044801882094354226,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.2246438130736351,
|
|
"num_tokens": 54507153.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.292820978164673,
|
|
"epoch": 2.282901056676273,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004479969020816242,
|
|
"loss": 4.9922,
|
|
"mean_token_accuracy": 0.21575176864862441,
|
|
"num_tokens": 54519922.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.206247425079345,
|
|
"epoch": 2.2833813640730067,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044797497920323175,
|
|
"loss": 4.8781,
|
|
"mean_token_accuracy": 0.22886064350605012,
|
|
"num_tokens": 54531857.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.246527862548828,
|
|
"epoch": 2.2838616714697406,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004479530523088739,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.22666315585374833,
|
|
"num_tokens": 54542079.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.143339920043945,
|
|
"epoch": 2.2843419788664745,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004479311213990598,
|
|
"loss": 4.8638,
|
|
"mean_token_accuracy": 0.22403869777917862,
|
|
"num_tokens": 54552722.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.133920907974243,
|
|
"epoch": 2.2848222862632084,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044790918647429854,
|
|
"loss": 4.8635,
|
|
"mean_token_accuracy": 0.226280876994133,
|
|
"num_tokens": 54564224.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.231433629989624,
|
|
"epoch": 2.2853025936599423,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044788724753509935,
|
|
"loss": 4.8546,
|
|
"mean_token_accuracy": 0.22928415536880492,
|
|
"num_tokens": 54575553.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.2662605285644535,
|
|
"epoch": 2.285782901056676,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004478653045819717,
|
|
"loss": 5.0268,
|
|
"mean_token_accuracy": 0.21615772545337678,
|
|
"num_tokens": 54587315.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.320351791381836,
|
|
"epoch": 2.28626320845341,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004478433576154249,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.2280268445611,
|
|
"num_tokens": 54598776.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.289631080627442,
|
|
"epoch": 2.286743515850144,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004478214066359687,
|
|
"loss": 5.0056,
|
|
"mean_token_accuracy": 0.20825899839401246,
|
|
"num_tokens": 54610272.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.250975847244263,
|
|
"epoch": 2.287223823246878,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044779945164411254,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.2201616182923317,
|
|
"num_tokens": 54622105.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.25731840133667,
|
|
"epoch": 2.287704130643612,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004477774926403662,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.2249108374118805,
|
|
"num_tokens": 54631771.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.213026142120361,
|
|
"epoch": 2.288184438040346,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004477555296252396,
|
|
"loss": 4.843,
|
|
"mean_token_accuracy": 0.23351151198148729,
|
|
"num_tokens": 54642724.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.187056398391723,
|
|
"epoch": 2.28866474543708,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044773356259924255,
|
|
"loss": 4.8721,
|
|
"mean_token_accuracy": 0.22333118170499802,
|
|
"num_tokens": 54655126.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.149639558792114,
|
|
"epoch": 2.2891450528338138,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044771159156288505,
|
|
"loss": 4.8142,
|
|
"mean_token_accuracy": 0.23281800597906113,
|
|
"num_tokens": 54665334.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.205320930480957,
|
|
"epoch": 2.2896253602305476,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004476896165166772,
|
|
"loss": 4.8375,
|
|
"mean_token_accuracy": 0.2263697162270546,
|
|
"num_tokens": 54676205.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.258168411254883,
|
|
"epoch": 2.2901056676272815,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044766763746112936,
|
|
"loss": 4.9155,
|
|
"mean_token_accuracy": 0.2210956871509552,
|
|
"num_tokens": 54686586.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.2312976837158205,
|
|
"epoch": 2.2905859750240154,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004476456543967517,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.22116924226284027,
|
|
"num_tokens": 54698879.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.180245780944825,
|
|
"epoch": 2.2910662824207493,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044762366732405454,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.2266719624400139,
|
|
"num_tokens": 54710140.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.191117525100708,
|
|
"epoch": 2.291546589817483,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004476016762435484,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.23437079638242722,
|
|
"num_tokens": 54721317.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.290325450897217,
|
|
"epoch": 2.292026897214217,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004475796811557439,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.21243244409561157,
|
|
"num_tokens": 54733329.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.280664396286011,
|
|
"epoch": 2.292507204610951,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044755768206115155,
|
|
"loss": 4.9486,
|
|
"mean_token_accuracy": 0.214385461807251,
|
|
"num_tokens": 54745230.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.206203842163086,
|
|
"epoch": 2.292987512007685,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004475356789602823,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.22001769840717317,
|
|
"num_tokens": 54757428.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.180565929412841,
|
|
"epoch": 2.2934678194044187,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044751367185364696,
|
|
"loss": 4.8059,
|
|
"mean_token_accuracy": 0.23064171075820922,
|
|
"num_tokens": 54768886.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.32332215309143,
|
|
"epoch": 2.2939481268011526,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044749166074175634,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.21338929533958434,
|
|
"num_tokens": 54780243.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.207958221435547,
|
|
"epoch": 2.2944284341978864,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044746964562512154,
|
|
"loss": 4.8083,
|
|
"mean_token_accuracy": 0.22638397216796874,
|
|
"num_tokens": 54792462.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.256507062911988,
|
|
"epoch": 2.2949087415946208,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044744762650425376,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.21686498075723648,
|
|
"num_tokens": 54804412.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.213009548187256,
|
|
"epoch": 2.2953890489913547,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044742560337966415,
|
|
"loss": 4.8982,
|
|
"mean_token_accuracy": 0.2261689454317093,
|
|
"num_tokens": 54814910.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.22779860496521,
|
|
"epoch": 2.2958693563880885,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000447403576251864,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.221656134724617,
|
|
"num_tokens": 54826500.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.208161449432373,
|
|
"epoch": 2.2963496637848224,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004473815451213648,
|
|
"loss": 4.9041,
|
|
"mean_token_accuracy": 0.21826696246862412,
|
|
"num_tokens": 54837682.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.182793045043946,
|
|
"epoch": 2.2968299711815563,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004473595099886779,
|
|
"loss": 4.8417,
|
|
"mean_token_accuracy": 0.22775577008724213,
|
|
"num_tokens": 54848937.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.222349739074707,
|
|
"epoch": 2.29731027857829,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004473374708543151,
|
|
"loss": 4.8135,
|
|
"mean_token_accuracy": 0.23454341441392898,
|
|
"num_tokens": 54859384.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.1442375659942625,
|
|
"epoch": 2.297790585975024,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004473154277187878,
|
|
"loss": 4.8231,
|
|
"mean_token_accuracy": 0.23754313439130784,
|
|
"num_tokens": 54871280.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.169858360290528,
|
|
"epoch": 2.298270893371758,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044729338058260805,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.23080163598060607,
|
|
"num_tokens": 54882699.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.288290119171142,
|
|
"epoch": 2.298751200768492,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004472713294462876,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.22179173529148102,
|
|
"num_tokens": 54894041.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.249594736099243,
|
|
"epoch": 2.2992315081652257,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044724927431033843,
|
|
"loss": 4.9413,
|
|
"mean_token_accuracy": 0.215796160697937,
|
|
"num_tokens": 54905007.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.278767538070679,
|
|
"epoch": 2.2997118155619596,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004472272151752725,
|
|
"loss": 4.9398,
|
|
"mean_token_accuracy": 0.22011374086141586,
|
|
"num_tokens": 54915735.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.120993328094483,
|
|
"epoch": 2.3001921229586935,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004472051520416022,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.2329139307141304,
|
|
"num_tokens": 54926350.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.197820138931275,
|
|
"epoch": 2.3006724303554273,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004471830849098395,
|
|
"loss": 4.9299,
|
|
"mean_token_accuracy": 0.21876053661108016,
|
|
"num_tokens": 54938354.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.273369312286377,
|
|
"epoch": 2.3011527377521612,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044716101378049683,
|
|
"loss": 4.9188,
|
|
"mean_token_accuracy": 0.21954952031373978,
|
|
"num_tokens": 54949440.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.261082363128662,
|
|
"epoch": 2.301633045148895,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044713893865408667,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.22168788760900499,
|
|
"num_tokens": 54961751.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.295437431335449,
|
|
"epoch": 2.3021133525456294,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004471168595311215,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.2049001380801201,
|
|
"num_tokens": 54975415.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.266733837127686,
|
|
"epoch": 2.302593659942363,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044709477641211395,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.22817655205726622,
|
|
"num_tokens": 54986599.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.2040468692779545,
|
|
"epoch": 2.303073967339097,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004470726892975767,
|
|
"loss": 4.8737,
|
|
"mean_token_accuracy": 0.2236848622560501,
|
|
"num_tokens": 54997428.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.23274040222168,
|
|
"epoch": 2.303554274735831,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044705059818802255,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.21156636327505113,
|
|
"num_tokens": 55008434.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.185987520217895,
|
|
"epoch": 2.304034582132565,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004470285030839644,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.2264905571937561,
|
|
"num_tokens": 55019834.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.208951568603515,
|
|
"epoch": 2.304514889529299,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044700640398591526,
|
|
"loss": 4.8577,
|
|
"mean_token_accuracy": 0.2258513480424881,
|
|
"num_tokens": 55030432.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.284347629547119,
|
|
"epoch": 2.3049951969260327,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004469843008943881,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.22620719373226167,
|
|
"num_tokens": 55041482.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.157518434524536,
|
|
"epoch": 2.3054755043227666,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004469621938098962,
|
|
"loss": 4.8067,
|
|
"mean_token_accuracy": 0.23129467368125917,
|
|
"num_tokens": 55051894.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.3054755043227666,
|
|
"eval_entropy": 4.983469216664322,
|
|
"eval_loss": 5.023782730102539,
|
|
"eval_mean_token_accuracy": 0.22586363242682103,
|
|
"eval_num_tokens": 55051894.0,
|
|
"eval_runtime": 26.4763,
|
|
"eval_samples_per_second": 1239.412,
|
|
"eval_steps_per_second": 154.931,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 5.212243843078613,
|
|
"epoch": 2.3059558117195005,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004469400827329528,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.225038380920887,
|
|
"num_tokens": 55063907.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 5.248084497451782,
|
|
"epoch": 2.3064361191162344,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004469179676640712,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.21650101989507675,
|
|
"num_tokens": 55076004.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 5.144097232818604,
|
|
"epoch": 2.3069164265129682,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004468958486037649,
|
|
"loss": 4.82,
|
|
"mean_token_accuracy": 0.23969807624816894,
|
|
"num_tokens": 55087506.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 5.185698556900024,
|
|
"epoch": 2.307396733909702,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004468737255525474,
|
|
"loss": 4.9069,
|
|
"mean_token_accuracy": 0.21914512813091278,
|
|
"num_tokens": 55099406.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 5.31342453956604,
|
|
"epoch": 2.307877041306436,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004468515985109324,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.21403180807828903,
|
|
"num_tokens": 55111733.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 5.245559024810791,
|
|
"epoch": 2.30835734870317,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004468294674794335,
|
|
"loss": 4.8873,
|
|
"mean_token_accuracy": 0.21877354234457017,
|
|
"num_tokens": 55123455.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 5.237900876998902,
|
|
"epoch": 2.3088376560999038,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004468073324585647,
|
|
"loss": 4.8998,
|
|
"mean_token_accuracy": 0.22092512249946594,
|
|
"num_tokens": 55134284.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 5.256622219085694,
|
|
"epoch": 2.309317963496638,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004467851934488398,
|
|
"loss": 4.9339,
|
|
"mean_token_accuracy": 0.2219757318496704,
|
|
"num_tokens": 55147224.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 5.165453767776489,
|
|
"epoch": 2.3097982708933715,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004467630504507727,
|
|
"loss": 4.8551,
|
|
"mean_token_accuracy": 0.2193499282002449,
|
|
"num_tokens": 55158144.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 5.191117000579834,
|
|
"epoch": 2.310278578290106,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004467409034648776,
|
|
"loss": 4.9813,
|
|
"mean_token_accuracy": 0.22474952787160873,
|
|
"num_tokens": 55171522.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 5.273671865463257,
|
|
"epoch": 2.3107588856868397,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004467187524916688,
|
|
"loss": 4.8987,
|
|
"mean_token_accuracy": 0.22583427876234055,
|
|
"num_tokens": 55182097.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 5.262166595458984,
|
|
"epoch": 2.3112391930835736,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004466965975316604,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.21749716997146606,
|
|
"num_tokens": 55192287.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 5.2329747676849365,
|
|
"epoch": 2.3117195004803075,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044667443858536685,
|
|
"loss": 4.9726,
|
|
"mean_token_accuracy": 0.22167059928178787,
|
|
"num_tokens": 55204049.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 5.166873455047607,
|
|
"epoch": 2.3121998078770414,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004466522756533026,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.2359093725681305,
|
|
"num_tokens": 55214969.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 5.268103885650635,
|
|
"epoch": 2.3126801152737753,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004466301087359822,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.22150795459747313,
|
|
"num_tokens": 55226362.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 5.310860252380371,
|
|
"epoch": 2.313160422670509,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044660793783392035,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.21925863325595857,
|
|
"num_tokens": 55237345.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 5.253285074234009,
|
|
"epoch": 2.313640730067243,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004465857629476317,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.21841876655817033,
|
|
"num_tokens": 55248426.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 5.193467664718628,
|
|
"epoch": 2.314121037463977,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004465635840776312,
|
|
"loss": 4.933,
|
|
"mean_token_accuracy": 0.2225531280040741,
|
|
"num_tokens": 55259017.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 5.316436243057251,
|
|
"epoch": 2.314601344860711,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044654140122443373,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.21906349807977676,
|
|
"num_tokens": 55270074.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 5.224502897262573,
|
|
"epoch": 2.3150816522574447,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004465192143885542,
|
|
"loss": 4.898,
|
|
"mean_token_accuracy": 0.2253411054611206,
|
|
"num_tokens": 55282291.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 5.277665901184082,
|
|
"epoch": 2.3155619596541785,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044649702357050787,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.22103088349103928,
|
|
"num_tokens": 55293113.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 5.246498060226441,
|
|
"epoch": 2.3160422670509124,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004464748287708099,
|
|
"loss": 4.9427,
|
|
"mean_token_accuracy": 0.2212749347090721,
|
|
"num_tokens": 55304182.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 5.25442328453064,
|
|
"epoch": 2.3165225744476463,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044645262998997557,
|
|
"loss": 4.8626,
|
|
"mean_token_accuracy": 0.23167835175991058,
|
|
"num_tokens": 55315292.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 5.224245166778564,
|
|
"epoch": 2.31700288184438,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044643042722852024,
|
|
"loss": 4.8728,
|
|
"mean_token_accuracy": 0.22347933799028397,
|
|
"num_tokens": 55327000.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 5.1607870101928714,
|
|
"epoch": 2.3174831892411145,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004464082204869595,
|
|
"loss": 4.8241,
|
|
"mean_token_accuracy": 0.23552655726671218,
|
|
"num_tokens": 55337506.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 5.135497379302978,
|
|
"epoch": 2.3179634966378484,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004463860097658088,
|
|
"loss": 4.7975,
|
|
"mean_token_accuracy": 0.23028502315282823,
|
|
"num_tokens": 55348538.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 5.271769428253174,
|
|
"epoch": 2.3184438040345823,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004463637950655839,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.21677158772945404,
|
|
"num_tokens": 55360501.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 5.23710618019104,
|
|
"epoch": 2.318924111431316,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044634157638680054,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.2260874792933464,
|
|
"num_tokens": 55371616.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 5.243774700164795,
|
|
"epoch": 2.31940441882805,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044631935372997455,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.21698538661003114,
|
|
"num_tokens": 55382702.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 5.221590232849121,
|
|
"epoch": 2.319884726224784,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004462971270956219,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.2246563971042633,
|
|
"num_tokens": 55394826.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 5.167381429672242,
|
|
"epoch": 2.320365033621518,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004462748964842586,
|
|
"loss": 4.8184,
|
|
"mean_token_accuracy": 0.23962229788303374,
|
|
"num_tokens": 55406584.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 5.221317958831787,
|
|
"epoch": 2.3208453410182517,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004462526618964008,
|
|
"loss": 4.9545,
|
|
"mean_token_accuracy": 0.22290830612182616,
|
|
"num_tokens": 55419640.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 5.187234687805176,
|
|
"epoch": 2.3213256484149856,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004462304233325647,
|
|
"loss": 4.8737,
|
|
"mean_token_accuracy": 0.23158129155635834,
|
|
"num_tokens": 55430197.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 5.225841331481933,
|
|
"epoch": 2.3218059558117194,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004462081807932666,
|
|
"loss": 4.9196,
|
|
"mean_token_accuracy": 0.22220309674739838,
|
|
"num_tokens": 55441832.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 5.172810840606689,
|
|
"epoch": 2.3222862632084533,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004461859342790229,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.23048628717660904,
|
|
"num_tokens": 55452656.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 5.0808509349822994,
|
|
"epoch": 2.322766570605187,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004461636837903501,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.23106198906898498,
|
|
"num_tokens": 55463936.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 5.262548732757568,
|
|
"epoch": 2.323246878001921,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004461414293277649,
|
|
"loss": 4.967,
|
|
"mean_token_accuracy": 0.2266307443380356,
|
|
"num_tokens": 55475885.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 5.237647867202758,
|
|
"epoch": 2.323727185398655,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004461191708917839,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.22261820286512374,
|
|
"num_tokens": 55489022.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 5.1863147735595705,
|
|
"epoch": 2.324207492795389,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044609690848292376,
|
|
"loss": 4.8662,
|
|
"mean_token_accuracy": 0.22367933094501496,
|
|
"num_tokens": 55500008.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 5.23619909286499,
|
|
"epoch": 2.324687800192123,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004460746421017016,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.2119087755680084,
|
|
"num_tokens": 55511024.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 5.289441871643066,
|
|
"epoch": 2.325168107588857,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044605237174863405,
|
|
"loss": 4.9093,
|
|
"mean_token_accuracy": 0.22212362736463548,
|
|
"num_tokens": 55522199.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 5.236349248886109,
|
|
"epoch": 2.325648414985591,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004460300974242386,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.2256661042571068,
|
|
"num_tokens": 55533197.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 5.202176141738891,
|
|
"epoch": 2.326128722382325,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004460078191290319,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.2212807759642601,
|
|
"num_tokens": 55544317.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 5.228208351135254,
|
|
"epoch": 2.3266090297790587,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044598553686353153,
|
|
"loss": 4.9418,
|
|
"mean_token_accuracy": 0.21934096813201903,
|
|
"num_tokens": 55555388.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 5.262100505828857,
|
|
"epoch": 2.3270893371757926,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044596325062825476,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.22275560349225998,
|
|
"num_tokens": 55566189.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 5.148277759552002,
|
|
"epoch": 2.3275696445725265,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004459409604237189,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.23741742968559265,
|
|
"num_tokens": 55578235.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 5.118755722045899,
|
|
"epoch": 2.3280499519692603,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044591866625044154,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.22996907085180282,
|
|
"num_tokens": 55590300.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 5.287404537200928,
|
|
"epoch": 2.3285302593659942,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004458963681089403,
|
|
"loss": 4.9128,
|
|
"mean_token_accuracy": 0.22585478127002717,
|
|
"num_tokens": 55601017.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 5.260603380203247,
|
|
"epoch": 2.329010566762728,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004458740659997328,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.22283689677715302,
|
|
"num_tokens": 55612411.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 5.265006351470947,
|
|
"epoch": 2.329490874159462,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004458517599233369,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.2229331374168396,
|
|
"num_tokens": 55623872.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 5.291339778900147,
|
|
"epoch": 2.329971181556196,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004458294498802706,
|
|
"loss": 4.9696,
|
|
"mean_token_accuracy": 0.21295732855796815,
|
|
"num_tokens": 55634887.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 5.241194581985473,
|
|
"epoch": 2.3304514889529298,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004458071358710516,
|
|
"loss": 4.9109,
|
|
"mean_token_accuracy": 0.22206103503704072,
|
|
"num_tokens": 55646286.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 5.226214742660522,
|
|
"epoch": 2.3309317963496636,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004457848178961981,
|
|
"loss": 4.9086,
|
|
"mean_token_accuracy": 0.225031478703022,
|
|
"num_tokens": 55657647.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 5.196869516372681,
|
|
"epoch": 2.3314121037463975,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044576249595622833,
|
|
"loss": 4.8793,
|
|
"mean_token_accuracy": 0.22696656584739686,
|
|
"num_tokens": 55669000.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 5.257259845733643,
|
|
"epoch": 2.331892411143132,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004457401700516603,
|
|
"loss": 4.8931,
|
|
"mean_token_accuracy": 0.22085844874382018,
|
|
"num_tokens": 55680678.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 5.238944721221924,
|
|
"epoch": 2.3323727185398653,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044571784018301267,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.2235509932041168,
|
|
"num_tokens": 55692429.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 5.230943584442139,
|
|
"epoch": 2.3328530259365996,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044569550635080365,
|
|
"loss": 4.9734,
|
|
"mean_token_accuracy": 0.219959057867527,
|
|
"num_tokens": 55704659.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 5.122937393188477,
|
|
"epoch": 2.3333333333333335,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044567316855555184,
|
|
"loss": 4.7699,
|
|
"mean_token_accuracy": 0.23464687913656235,
|
|
"num_tokens": 55715584.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 5.262300157546997,
|
|
"epoch": 2.3338136407300674,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004456508267977759,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.217544387280941,
|
|
"num_tokens": 55726715.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 5.162510776519776,
|
|
"epoch": 2.3342939481268012,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044562848107799444,
|
|
"loss": 4.8649,
|
|
"mean_token_accuracy": 0.2290295109152794,
|
|
"num_tokens": 55737069.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 5.194169616699218,
|
|
"epoch": 2.334774255523535,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044560613139672627,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.2346920222043991,
|
|
"num_tokens": 55747774.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 5.20966911315918,
|
|
"epoch": 2.335254562920269,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044558377775449036,
|
|
"loss": 4.8908,
|
|
"mean_token_accuracy": 0.23112610280513762,
|
|
"num_tokens": 55758209.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 5.295125961303711,
|
|
"epoch": 2.335734870317003,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044556142015180573,
|
|
"loss": 4.9236,
|
|
"mean_token_accuracy": 0.21760222613811492,
|
|
"num_tokens": 55768668.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 5.37776780128479,
|
|
"epoch": 2.3362151777137368,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044553905858919134,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.21401102393865584,
|
|
"num_tokens": 55780254.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 5.223437261581421,
|
|
"epoch": 2.3366954851104706,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004455166930671664,
|
|
"loss": 4.9029,
|
|
"mean_token_accuracy": 0.22644427716732024,
|
|
"num_tokens": 55790241.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 5.253385305404663,
|
|
"epoch": 2.3371757925072045,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044549432358625014,
|
|
"loss": 5.017,
|
|
"mean_token_accuracy": 0.21737547367811202,
|
|
"num_tokens": 55802040.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 5.273345470428467,
|
|
"epoch": 2.3376560999039384,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000445471950146962,
|
|
"loss": 4.9143,
|
|
"mean_token_accuracy": 0.22337866425514222,
|
|
"num_tokens": 55813926.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 5.2523167610168455,
|
|
"epoch": 2.3381364073006723,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004454495727498214,
|
|
"loss": 4.8832,
|
|
"mean_token_accuracy": 0.2248215675354004,
|
|
"num_tokens": 55825281.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 5.176073789596558,
|
|
"epoch": 2.338616714697406,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004454271913953478,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.2266184076666832,
|
|
"num_tokens": 55836295.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 5.182536220550537,
|
|
"epoch": 2.3390970220941405,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044540480608406093,
|
|
"loss": 4.8594,
|
|
"mean_token_accuracy": 0.23386203050613402,
|
|
"num_tokens": 55847150.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 5.242807245254516,
|
|
"epoch": 2.339577329490874,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004453824168164804,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.22257349044084548,
|
|
"num_tokens": 55858135.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 5.318433046340942,
|
|
"epoch": 2.3400576368876083,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004453600235931261,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.22205506414175033,
|
|
"num_tokens": 55869319.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 5.255600833892823,
|
|
"epoch": 2.340537944284342,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000445337626414518,
|
|
"loss": 4.9641,
|
|
"mean_token_accuracy": 0.22021288573741912,
|
|
"num_tokens": 55881383.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 5.215582990646363,
|
|
"epoch": 2.341018251681076,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044531522528117593,
|
|
"loss": 4.8907,
|
|
"mean_token_accuracy": 0.22597514986991882,
|
|
"num_tokens": 55893726.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 5.265971612930298,
|
|
"epoch": 2.34149855907781,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044529282019362007,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.22994812279939653,
|
|
"num_tokens": 55905260.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 5.247964715957641,
|
|
"epoch": 2.341978866474544,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044527041115237056,
|
|
"loss": 4.9338,
|
|
"mean_token_accuracy": 0.22742531895637513,
|
|
"num_tokens": 55915404.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 5.191548299789429,
|
|
"epoch": 2.3424591738712777,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004452479981579477,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.22897960096597672,
|
|
"num_tokens": 55925972.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 5.186753225326538,
|
|
"epoch": 2.3429394812680115,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004452255812108719,
|
|
"loss": 4.8773,
|
|
"mean_token_accuracy": 0.22110798060894013,
|
|
"num_tokens": 55937545.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 5.149283742904663,
|
|
"epoch": 2.3434197886647454,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004452031603116636,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.23623964339494705,
|
|
"num_tokens": 55949934.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 5.23052191734314,
|
|
"epoch": 2.3439000960614793,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044518073546084326,
|
|
"loss": 4.9241,
|
|
"mean_token_accuracy": 0.22815946340560914,
|
|
"num_tokens": 55960414.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 5.167893791198731,
|
|
"epoch": 2.344380403458213,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004451583066589316,
|
|
"loss": 4.8565,
|
|
"mean_token_accuracy": 0.2227165788412094,
|
|
"num_tokens": 55970999.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 5.230942630767823,
|
|
"epoch": 2.344860710854947,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044513587390644925,
|
|
"loss": 4.885,
|
|
"mean_token_accuracy": 0.22906312197446824,
|
|
"num_tokens": 55982801.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 5.327472305297851,
|
|
"epoch": 2.345341018251681,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044511343720391724,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.21972613632678986,
|
|
"num_tokens": 55995143.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 5.186668729782104,
|
|
"epoch": 2.345821325648415,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004450909965518563,
|
|
"loss": 4.9342,
|
|
"mean_token_accuracy": 0.22271201610565186,
|
|
"num_tokens": 56006368.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 5.247733068466187,
|
|
"epoch": 2.3463016330451487,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044506855195078755,
|
|
"loss": 4.9837,
|
|
"mean_token_accuracy": 0.22265852987766266,
|
|
"num_tokens": 56019245.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 5.278822040557861,
|
|
"epoch": 2.3467819404418826,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044504610340123185,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.21181004643440246,
|
|
"num_tokens": 56030982.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 5.229121398925781,
|
|
"epoch": 2.347262247838617,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044502365090371066,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.22116327732801438,
|
|
"num_tokens": 56042871.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 5.276763010025024,
|
|
"epoch": 2.347742555235351,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004450011944587452,
|
|
"loss": 4.9475,
|
|
"mean_token_accuracy": 0.2212435021996498,
|
|
"num_tokens": 56054099.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 5.159561967849731,
|
|
"epoch": 2.3482228626320847,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044497873406685673,
|
|
"loss": 4.8569,
|
|
"mean_token_accuracy": 0.221847203373909,
|
|
"num_tokens": 56064315.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 5.15967960357666,
|
|
"epoch": 2.3487031700288186,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004449562697285669,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.22397716492414474,
|
|
"num_tokens": 56076446.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 5.323082351684571,
|
|
"epoch": 2.3491834774255524,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044493380144439707,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.21478139758110046,
|
|
"num_tokens": 56089356.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 5.269741487503052,
|
|
"epoch": 2.3496637848222863,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000444911329214869,
|
|
"loss": 4.9826,
|
|
"mean_token_accuracy": 0.21790652722120285,
|
|
"num_tokens": 56101245.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 5.146304559707642,
|
|
"epoch": 2.35014409221902,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044488885304050434,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.23224153369665146,
|
|
"num_tokens": 56112756.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 5.2401570796966555,
|
|
"epoch": 2.350624399615754,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000444866372921825,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.22134802341461182,
|
|
"num_tokens": 56124316.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 5.16593828201294,
|
|
"epoch": 2.351104707012488,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044484388885935287,
|
|
"loss": 4.8465,
|
|
"mean_token_accuracy": 0.2352960303425789,
|
|
"num_tokens": 56135972.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 5.282983255386353,
|
|
"epoch": 2.351585014409222,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044482140085361005,
|
|
"loss": 4.9323,
|
|
"mean_token_accuracy": 0.22338353395462035,
|
|
"num_tokens": 56147335.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 5.175797080993652,
|
|
"epoch": 2.3520653218059557,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044479890890511853,
|
|
"loss": 4.8362,
|
|
"mean_token_accuracy": 0.23055289834737777,
|
|
"num_tokens": 56158294.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 5.167487573623657,
|
|
"epoch": 2.3525456292026896,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044477641301440054,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.2348927617073059,
|
|
"num_tokens": 56169468.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 5.236497974395752,
|
|
"epoch": 2.3530259365994235,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004447539131819784,
|
|
"loss": 4.8678,
|
|
"mean_token_accuracy": 0.21870579421520234,
|
|
"num_tokens": 56180112.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 5.250787782669067,
|
|
"epoch": 2.3535062439961574,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044473140940837436,
|
|
"loss": 4.9362,
|
|
"mean_token_accuracy": 0.22629490494728088,
|
|
"num_tokens": 56191290.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 5.27094292640686,
|
|
"epoch": 2.3539865513928913,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044470890169411107,
|
|
"loss": 4.9944,
|
|
"mean_token_accuracy": 0.21979201585054398,
|
|
"num_tokens": 56202447.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 5.291543292999267,
|
|
"epoch": 2.3544668587896256,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000444686390039711,
|
|
"loss": 4.967,
|
|
"mean_token_accuracy": 0.21210471242666246,
|
|
"num_tokens": 56213802.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 5.219963026046753,
|
|
"epoch": 2.3549471661863595,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004446638744456968,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.22364912331104278,
|
|
"num_tokens": 56225243.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 5.27596526145935,
|
|
"epoch": 2.3554274735830933,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044464135491259135,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.22718398571014403,
|
|
"num_tokens": 56235116.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 5.218603134155273,
|
|
"epoch": 2.3559077809798272,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004446188314409172,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.22307237833738328,
|
|
"num_tokens": 56246654.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 5.250893402099609,
|
|
"epoch": 2.356388088376561,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004445963040311975,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.2271270841360092,
|
|
"num_tokens": 56257787.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 5.13486328125,
|
|
"epoch": 2.356868395773295,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044457377268395526,
|
|
"loss": 4.8071,
|
|
"mean_token_accuracy": 0.230245903134346,
|
|
"num_tokens": 56268881.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 5.103006601333618,
|
|
"epoch": 2.357348703170029,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044455123739971355,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.23094092607498168,
|
|
"num_tokens": 56281515.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 5.155858373641967,
|
|
"epoch": 2.3578290105667628,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044452869817899554,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.22983989417552947,
|
|
"num_tokens": 56293226.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 5.227748870849609,
|
|
"epoch": 2.3583093179634966,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004445061550223246,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.22704354524612427,
|
|
"num_tokens": 56303408.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 5.219588327407837,
|
|
"epoch": 2.3587896253602305,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044448360793022403,
|
|
"loss": 4.8757,
|
|
"mean_token_accuracy": 0.2238838255405426,
|
|
"num_tokens": 56315379.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 5.2138762950897215,
|
|
"epoch": 2.3592699327569644,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004444610569032174,
|
|
"loss": 4.9063,
|
|
"mean_token_accuracy": 0.22513810843229293,
|
|
"num_tokens": 56326496.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 5.138730478286743,
|
|
"epoch": 2.3597502401536983,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004444385019418281,
|
|
"loss": 4.8494,
|
|
"mean_token_accuracy": 0.2273797243833542,
|
|
"num_tokens": 56339416.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 5.271489763259888,
|
|
"epoch": 2.360230547550432,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044441594304658004,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.2213674768805504,
|
|
"num_tokens": 56352305.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 5.201544618606567,
|
|
"epoch": 2.360710854947166,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004443933802179968,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.22358070462942123,
|
|
"num_tokens": 56364598.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 5.211123657226563,
|
|
"epoch": 2.3611911623439,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044437081345660224,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.21109369546175002,
|
|
"num_tokens": 56376651.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 5.226035833358765,
|
|
"epoch": 2.3616714697406342,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004443482427629204,
|
|
"loss": 4.8503,
|
|
"mean_token_accuracy": 0.2266779884696007,
|
|
"num_tokens": 56388038.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 5.238267993927002,
|
|
"epoch": 2.3621517771373677,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004443256681374751,
|
|
"loss": 4.8755,
|
|
"mean_token_accuracy": 0.22779489010572435,
|
|
"num_tokens": 56398889.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 5.168354749679565,
|
|
"epoch": 2.362632084534102,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004443030895807907,
|
|
"loss": 4.9286,
|
|
"mean_token_accuracy": 0.22425079941749573,
|
|
"num_tokens": 56411548.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 5.235644865036011,
|
|
"epoch": 2.363112391930836,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044428050709339117,
|
|
"loss": 4.7983,
|
|
"mean_token_accuracy": 0.22844240963459014,
|
|
"num_tokens": 56423292.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 5.133938789367676,
|
|
"epoch": 2.3635926993275698,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000444257920675801,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.23171754479408263,
|
|
"num_tokens": 56434834.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 5.164880895614624,
|
|
"epoch": 2.3640730067243036,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044423533032854454,
|
|
"loss": 4.9244,
|
|
"mean_token_accuracy": 0.22366227954626083,
|
|
"num_tokens": 56445554.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 5.208892202377319,
|
|
"epoch": 2.3645533141210375,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004442127360521462,
|
|
"loss": 4.8775,
|
|
"mean_token_accuracy": 0.23426975607872008,
|
|
"num_tokens": 56457748.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 5.1802726745605465,
|
|
"epoch": 2.3650336215177714,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004441901378471306,
|
|
"loss": 4.8091,
|
|
"mean_token_accuracy": 0.2356065645813942,
|
|
"num_tokens": 56469650.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 5.162552452087402,
|
|
"epoch": 2.3655139289145053,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044416753571402233,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.22896739840507507,
|
|
"num_tokens": 56482061.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 5.253963899612427,
|
|
"epoch": 2.365994236311239,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004441449296533462,
|
|
"loss": 4.9296,
|
|
"mean_token_accuracy": 0.22412364333868026,
|
|
"num_tokens": 56493599.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 5.2636407852172855,
|
|
"epoch": 2.366474543707973,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044412231966562717,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.21843173056840898,
|
|
"num_tokens": 56505842.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 5.177345228195191,
|
|
"epoch": 2.366954851104707,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044409970575139,
|
|
"loss": 4.8398,
|
|
"mean_token_accuracy": 0.23218178004026413,
|
|
"num_tokens": 56517688.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 5.2336808204650875,
|
|
"epoch": 2.367435158501441,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004440770879111598,
|
|
"loss": 4.8873,
|
|
"mean_token_accuracy": 0.22954965382814407,
|
|
"num_tokens": 56528665.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 5.118437004089356,
|
|
"epoch": 2.3679154658981747,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044405446614546163,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.2274254560470581,
|
|
"num_tokens": 56539097.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 5.266106605529785,
|
|
"epoch": 2.3683957732949086,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004440318404548208,
|
|
"loss": 4.9595,
|
|
"mean_token_accuracy": 0.22808630615472794,
|
|
"num_tokens": 56550373.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 5.24993896484375,
|
|
"epoch": 2.3688760806916425,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044400921083976246,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.21978272050619124,
|
|
"num_tokens": 56561289.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 5.226989984512329,
|
|
"epoch": 2.3693563880883763,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004439865773008122,
|
|
"loss": 4.9543,
|
|
"mean_token_accuracy": 0.2243264451622963,
|
|
"num_tokens": 56572331.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 5.18682017326355,
|
|
"epoch": 2.3698366954851107,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004439639398384953,
|
|
"loss": 4.8248,
|
|
"mean_token_accuracy": 0.23234686106443406,
|
|
"num_tokens": 56584375.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 5.1593992710113525,
|
|
"epoch": 2.3703170028818445,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044394129845333756,
|
|
"loss": 4.8522,
|
|
"mean_token_accuracy": 0.219572551548481,
|
|
"num_tokens": 56595825.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 5.235120964050293,
|
|
"epoch": 2.3707973102785784,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004439186531458645,
|
|
"loss": 4.955,
|
|
"mean_token_accuracy": 0.23091911822557448,
|
|
"num_tokens": 56607842.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 5.264122819900512,
|
|
"epoch": 2.3712776176753123,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044389600391660185,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.22286438345909118,
|
|
"num_tokens": 56618509.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 5.184954833984375,
|
|
"epoch": 2.371757925072046,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044387335076607554,
|
|
"loss": 4.8367,
|
|
"mean_token_accuracy": 0.22866396903991698,
|
|
"num_tokens": 56630293.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 5.294245338439941,
|
|
"epoch": 2.37223823246878,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004438506936948115,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.21462903022766114,
|
|
"num_tokens": 56641852.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 5.346317100524902,
|
|
"epoch": 2.372718539865514,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044382803270333565,
|
|
"loss": 4.9696,
|
|
"mean_token_accuracy": 0.2203134074807167,
|
|
"num_tokens": 56654409.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 5.206334018707276,
|
|
"epoch": 2.373198847262248,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004438053677921743,
|
|
"loss": 4.8759,
|
|
"mean_token_accuracy": 0.22651425153017044,
|
|
"num_tokens": 56665227.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 5.213127183914184,
|
|
"epoch": 2.3736791546589817,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044378269896185344,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.2225804254412651,
|
|
"num_tokens": 56677924.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 5.192664098739624,
|
|
"epoch": 2.3741594620557156,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004437600262128996,
|
|
"loss": 4.8294,
|
|
"mean_token_accuracy": 0.2277800738811493,
|
|
"num_tokens": 56689789.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 5.261063098907471,
|
|
"epoch": 2.3746397694524495,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000443737349545839,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.22295571118593216,
|
|
"num_tokens": 56700595.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 5.281785869598389,
|
|
"epoch": 2.3751200768491834,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044371466896119823,
|
|
"loss": 4.9826,
|
|
"mean_token_accuracy": 0.21971645802259446,
|
|
"num_tokens": 56712554.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 5.254749822616577,
|
|
"epoch": 2.3756003842459172,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044369198445950384,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.22578625679016112,
|
|
"num_tokens": 56723698.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 5.2321408748626705,
|
|
"epoch": 2.376080691642651,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004436692960412824,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.23372157216072081,
|
|
"num_tokens": 56734660.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 5.210962343215942,
|
|
"epoch": 2.376560999039385,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004436466037070608,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.22521074414253234,
|
|
"num_tokens": 56746150.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 5.3114574432373045,
|
|
"epoch": 2.3770413064361193,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044362390745736585,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.2168632686138153,
|
|
"num_tokens": 56758018.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 5.193136405944824,
|
|
"epoch": 2.377521613832853,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004436012072927245,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.2260827139019966,
|
|
"num_tokens": 56769129.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 5.228445386886596,
|
|
"epoch": 2.378001921229587,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044357850321366375,
|
|
"loss": 4.909,
|
|
"mean_token_accuracy": 0.2250712439417839,
|
|
"num_tokens": 56780445.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 5.205980491638184,
|
|
"epoch": 2.378482228626321,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004435557952207107,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.22750670313835145,
|
|
"num_tokens": 56792338.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 5.214509534835815,
|
|
"epoch": 2.378962536023055,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044353308331439257,
|
|
"loss": 4.899,
|
|
"mean_token_accuracy": 0.2292829394340515,
|
|
"num_tokens": 56802345.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 5.288167667388916,
|
|
"epoch": 2.3794428434197887,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004435103674952367,
|
|
"loss": 4.9548,
|
|
"mean_token_accuracy": 0.2233438014984131,
|
|
"num_tokens": 56813865.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 5.16458306312561,
|
|
"epoch": 2.3799231508165226,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044348764776377047,
|
|
"loss": 4.8181,
|
|
"mean_token_accuracy": 0.22966080605983735,
|
|
"num_tokens": 56824135.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 5.181768989562988,
|
|
"epoch": 2.3804034582132565,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004434649241205214,
|
|
"loss": 4.8719,
|
|
"mean_token_accuracy": 0.22802967429161072,
|
|
"num_tokens": 56836104.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 5.204383802413941,
|
|
"epoch": 2.3808837656099904,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044344219656601704,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.23223182410001755,
|
|
"num_tokens": 56848308.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 5.193201637268066,
|
|
"epoch": 2.3813640730067243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000443419465100785,
|
|
"loss": 4.8863,
|
|
"mean_token_accuracy": 0.22914159893989564,
|
|
"num_tokens": 56859351.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 5.222154235839843,
|
|
"epoch": 2.381844380403458,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004433967297253531,
|
|
"loss": 4.9253,
|
|
"mean_token_accuracy": 0.21997396051883697,
|
|
"num_tokens": 56870645.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 5.193235778808594,
|
|
"epoch": 2.382324687800192,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044337399044024924,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.22724822163581848,
|
|
"num_tokens": 56881246.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 5.194839763641357,
|
|
"epoch": 2.382804995196926,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004433512472460012,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.22909946888685226,
|
|
"num_tokens": 56893477.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 5.179016065597534,
|
|
"epoch": 2.38328530259366,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044332850014313713,
|
|
"loss": 4.8908,
|
|
"mean_token_accuracy": 0.22824471592903137,
|
|
"num_tokens": 56904813.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 5.176292800903321,
|
|
"epoch": 2.3837656099903937,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004433057491321851,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.2223691910505295,
|
|
"num_tokens": 56916160.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 5.187251281738281,
|
|
"epoch": 2.384245917387128,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044328299421367333,
|
|
"loss": 4.8655,
|
|
"mean_token_accuracy": 0.23168368488550187,
|
|
"num_tokens": 56927791.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 5.233174276351929,
|
|
"epoch": 2.3847262247838614,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004432602353881302,
|
|
"loss": 4.9064,
|
|
"mean_token_accuracy": 0.22714092433452607,
|
|
"num_tokens": 56938848.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 5.202776575088501,
|
|
"epoch": 2.3852065321805958,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044323747265608395,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.22784914672374726,
|
|
"num_tokens": 56950116.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 5.230696392059326,
|
|
"epoch": 2.3856868395773296,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004432147060180632,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.22764678448438644,
|
|
"num_tokens": 56961911.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 5.267803287506103,
|
|
"epoch": 2.3861671469740635,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044319193547459645,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.209423066675663,
|
|
"num_tokens": 56974105.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 5.174156951904297,
|
|
"epoch": 2.3866474543707974,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004431691610262124,
|
|
"loss": 4.8722,
|
|
"mean_token_accuracy": 0.228171606361866,
|
|
"num_tokens": 56985564.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 5.224444389343262,
|
|
"epoch": 2.3871277617675313,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044314638267343976,
|
|
"loss": 4.8209,
|
|
"mean_token_accuracy": 0.2397466465830803,
|
|
"num_tokens": 56995835.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 5.102242374420166,
|
|
"epoch": 2.387608069164265,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004431236004168075,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.2295714035630226,
|
|
"num_tokens": 57008114.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 5.120087337493897,
|
|
"epoch": 2.388088376560999,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004431008142568444,
|
|
"loss": 4.8502,
|
|
"mean_token_accuracy": 0.23239296823740005,
|
|
"num_tokens": 57018968.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 5.187870788574219,
|
|
"epoch": 2.388568683957733,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044307802419407954,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.2316372126340866,
|
|
"num_tokens": 57031297.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 5.228634548187256,
|
|
"epoch": 2.389048991354467,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004430552302290421,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.22399379760026933,
|
|
"num_tokens": 57043457.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 5.1815338134765625,
|
|
"epoch": 2.3895292987512007,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004430324323622611,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.22715217918157576,
|
|
"num_tokens": 57054474.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 5.170245933532715,
|
|
"epoch": 2.3900096061479346,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044300963059426605,
|
|
"loss": 4.8901,
|
|
"mean_token_accuracy": 0.22443275153636932,
|
|
"num_tokens": 57065120.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 5.164962816238403,
|
|
"epoch": 2.3904899135446684,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044298682492558637,
|
|
"loss": 4.8684,
|
|
"mean_token_accuracy": 0.22450555860996246,
|
|
"num_tokens": 57076712.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 5.316261148452758,
|
|
"epoch": 2.3909702209414023,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044296401535675136,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.2207703948020935,
|
|
"num_tokens": 57087894.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 5.307439613342285,
|
|
"epoch": 2.3914505283381366,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044294120188829056,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.21402352452278137,
|
|
"num_tokens": 57101029.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 5.279623365402221,
|
|
"epoch": 2.39193083573487,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004429183845207339,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.21904916316270828,
|
|
"num_tokens": 57112893.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 5.225486469268799,
|
|
"epoch": 2.3924111431316044,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004428955632546108,
|
|
"loss": 4.9435,
|
|
"mean_token_accuracy": 0.22552342265844344,
|
|
"num_tokens": 57123899.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 5.1828710556030275,
|
|
"epoch": 2.3928914505283383,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004428727380904514,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.22242086827754975,
|
|
"num_tokens": 57134896.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 5.098242521286011,
|
|
"epoch": 2.393371757925072,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00044284990902878545,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.23411538004875182,
|
|
"num_tokens": 57146278.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 5.211308097839355,
|
|
"epoch": 2.393852065321806,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044282707607014304,
|
|
"loss": 4.8707,
|
|
"mean_token_accuracy": 0.22824101895093918,
|
|
"num_tokens": 57157663.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 5.211515331268311,
|
|
"epoch": 2.39433237271854,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044280423921505427,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.23192256689071655,
|
|
"num_tokens": 57169131.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 5.189872360229492,
|
|
"epoch": 2.394812680115274,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004427813984640493,
|
|
"loss": 4.8709,
|
|
"mean_token_accuracy": 0.22394271194934845,
|
|
"num_tokens": 57181653.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 5.163410806655884,
|
|
"epoch": 2.3952929875120077,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004427585538176585,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.2333957001566887,
|
|
"num_tokens": 57192817.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 5.230109977722168,
|
|
"epoch": 2.3957732949087416,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044273570527641223,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.21981339752674103,
|
|
"num_tokens": 57203570.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 5.179500675201416,
|
|
"epoch": 2.3962536023054755,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044271285284084097,
|
|
"loss": 4.8004,
|
|
"mean_token_accuracy": 0.2282325193285942,
|
|
"num_tokens": 57214388.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 5.227189636230468,
|
|
"epoch": 2.3967339097022093,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004426899965114752,
|
|
"loss": 4.9234,
|
|
"mean_token_accuracy": 0.22090783566236497,
|
|
"num_tokens": 57225004.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 5.166911792755127,
|
|
"epoch": 2.3972142170989432,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044266713628884566,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.2320847690105438,
|
|
"num_tokens": 57236643.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 5.176105690002442,
|
|
"epoch": 2.397694524495677,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044264427217348315,
|
|
"loss": 4.859,
|
|
"mean_token_accuracy": 0.22422920316457748,
|
|
"num_tokens": 57247502.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 5.270990085601807,
|
|
"epoch": 2.398174831892411,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004426214041659184,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.216754749417305,
|
|
"num_tokens": 57259539.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 5.361375617980957,
|
|
"epoch": 2.398655139289145,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004425985322666824,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.21734236031770707,
|
|
"num_tokens": 57270946.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 5.253762197494507,
|
|
"epoch": 2.3991354466858787,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004425756564763061,
|
|
"loss": 4.9371,
|
|
"mean_token_accuracy": 0.2218172013759613,
|
|
"num_tokens": 57282855.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 5.232973670959472,
|
|
"epoch": 2.399615754082613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044255277679532075,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.21835512071847915,
|
|
"num_tokens": 57292638.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 5.2621687889099125,
|
|
"epoch": 2.400096061479347,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044252989322425735,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.22608459293842315,
|
|
"num_tokens": 57304088.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 5.297831296920776,
|
|
"epoch": 2.400576368876081,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044250700576364734,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.23010066896677017,
|
|
"num_tokens": 57314534.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 5.219142770767212,
|
|
"epoch": 2.4010566762728147,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000442484114414022,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.21779891550540925,
|
|
"num_tokens": 57326787.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 5.166839122772217,
|
|
"epoch": 2.4015369836695486,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004424612191759129,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.2221489742398262,
|
|
"num_tokens": 57338935.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 5.297084951400757,
|
|
"epoch": 2.4020172910662825,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004424383200498515,
|
|
"loss": 4.9107,
|
|
"mean_token_accuracy": 0.22600928246974944,
|
|
"num_tokens": 57349963.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 5.173072576522827,
|
|
"epoch": 2.4024975984630164,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004424154170363696,
|
|
"loss": 4.888,
|
|
"mean_token_accuracy": 0.23014439940452575,
|
|
"num_tokens": 57361305.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 5.1501274585723875,
|
|
"epoch": 2.4029779058597502,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004423925101359987,
|
|
"loss": 4.8463,
|
|
"mean_token_accuracy": 0.2254084974527359,
|
|
"num_tokens": 57371582.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 5.223374843597412,
|
|
"epoch": 2.403458213256484,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004423695993492709,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.22989859580993652,
|
|
"num_tokens": 57382222.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 5.223973655700684,
|
|
"epoch": 2.403938520653218,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004423466846767179,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.22674113959074021,
|
|
"num_tokens": 57393939.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 5.179949760437012,
|
|
"epoch": 2.404418828049952,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044232376611887185,
|
|
"loss": 4.8509,
|
|
"mean_token_accuracy": 0.2267923042178154,
|
|
"num_tokens": 57404889.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 5.234487628936767,
|
|
"epoch": 2.4048991354466858,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044230084367626477,
|
|
"loss": 4.9442,
|
|
"mean_token_accuracy": 0.22466535568237306,
|
|
"num_tokens": 57416296.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 5.178449106216431,
|
|
"epoch": 2.4053794428434196,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004422779173494288,
|
|
"loss": 4.9059,
|
|
"mean_token_accuracy": 0.2241778090596199,
|
|
"num_tokens": 57427926.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 5.239514684677124,
|
|
"epoch": 2.4058597502401535,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004422549871388965,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.22753166258335114,
|
|
"num_tokens": 57439397.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 5.263103866577149,
|
|
"epoch": 2.4063400576368874,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044223205304519994,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.22574831396341324,
|
|
"num_tokens": 57449976.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 5.253390502929688,
|
|
"epoch": 2.4068203650336217,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004422091150688717,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.21822086572647095,
|
|
"num_tokens": 57461578.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 5.21581802368164,
|
|
"epoch": 2.4073006724303556,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004421861732104443,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.22185304909944534,
|
|
"num_tokens": 57471832.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 5.256034326553345,
|
|
"epoch": 2.4077809798270895,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004421632274704504,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.22242865711450577,
|
|
"num_tokens": 57482854.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 5.267632389068604,
|
|
"epoch": 2.4082612872238234,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004421402778494227,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.21565067321062087,
|
|
"num_tokens": 57494243.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 5.243531274795532,
|
|
"epoch": 2.4087415946205573,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004421173243478941,
|
|
"loss": 4.8524,
|
|
"mean_token_accuracy": 0.2258637309074402,
|
|
"num_tokens": 57506185.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 5.244460344314575,
|
|
"epoch": 2.409221902017291,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044209436696639745,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.2306853637099266,
|
|
"num_tokens": 57517980.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 5.123124647140503,
|
|
"epoch": 2.409702209414025,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044207140570546574,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.2323068842291832,
|
|
"num_tokens": 57529331.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 5.201483488082886,
|
|
"epoch": 2.410182516810759,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044204844056563216,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.22603220939636232,
|
|
"num_tokens": 57540463.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 5.235255193710327,
|
|
"epoch": 2.410662824207493,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004420254715474297,
|
|
"loss": 4.9944,
|
|
"mean_token_accuracy": 0.21758652627468109,
|
|
"num_tokens": 57550896.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 5.19186544418335,
|
|
"epoch": 2.4111431316042267,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044200249865139187,
|
|
"loss": 4.8713,
|
|
"mean_token_accuracy": 0.23060999065637589,
|
|
"num_tokens": 57562041.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 5.333061981201172,
|
|
"epoch": 2.4116234390009605,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044197952187805185,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.21766868531703948,
|
|
"num_tokens": 57573771.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 5.241616821289062,
|
|
"epoch": 2.4121037463976944,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044195654122794324,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.22339505702257156,
|
|
"num_tokens": 57585651.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 5.139295482635498,
|
|
"epoch": 2.4125840537944283,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004419335567015994,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.23031686544418334,
|
|
"num_tokens": 57596328.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 5.139455890655517,
|
|
"epoch": 2.413064361191162,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004419105682995542,
|
|
"loss": 4.7846,
|
|
"mean_token_accuracy": 0.22876114696264266,
|
|
"num_tokens": 57608012.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 5.277891349792481,
|
|
"epoch": 2.413544668587896,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004418875760223411,
|
|
"loss": 4.8922,
|
|
"mean_token_accuracy": 0.22445854395627976,
|
|
"num_tokens": 57619711.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 5.189095067977905,
|
|
"epoch": 2.4140249759846304,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044186457987049405,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.2315531402826309,
|
|
"num_tokens": 57630263.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 5.176491737365723,
|
|
"epoch": 2.414505283381364,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000441841579844547,
|
|
"loss": 4.8598,
|
|
"mean_token_accuracy": 0.22859848737716676,
|
|
"num_tokens": 57640973.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 5.2230637550354,
|
|
"epoch": 2.414985590778098,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004418185759450338,
|
|
"loss": 4.8364,
|
|
"mean_token_accuracy": 0.22329819500446318,
|
|
"num_tokens": 57651698.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 5.169799947738648,
|
|
"epoch": 2.415465898174832,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004417955681724887,
|
|
"loss": 4.8455,
|
|
"mean_token_accuracy": 0.22904650419950484,
|
|
"num_tokens": 57662547.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 5.263559198379516,
|
|
"epoch": 2.415946205571566,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044177255652744576,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.2160400003194809,
|
|
"num_tokens": 57675665.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 5.179860782623291,
|
|
"epoch": 2.4164265129683,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044174954101043926,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.23287280797958373,
|
|
"num_tokens": 57687765.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 5.2169633388519285,
|
|
"epoch": 2.4169068203650337,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044172652162200354,
|
|
"loss": 4.9243,
|
|
"mean_token_accuracy": 0.21703041791915895,
|
|
"num_tokens": 57699575.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 5.269207000732422,
|
|
"epoch": 2.4173871277617676,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004417034983626731,
|
|
"loss": 4.9389,
|
|
"mean_token_accuracy": 0.22806538492441178,
|
|
"num_tokens": 57710014.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 5.150432777404785,
|
|
"epoch": 2.4178674351585014,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004416804712329825,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.24168164879083634,
|
|
"num_tokens": 57720763.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 5.230108451843262,
|
|
"epoch": 2.4183477425552353,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044165744023346614,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.22139157503843307,
|
|
"num_tokens": 57731581.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 5.26843490600586,
|
|
"epoch": 2.418828049951969,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044163440536465904,
|
|
"loss": 4.9735,
|
|
"mean_token_accuracy": 0.2259112685918808,
|
|
"num_tokens": 57742473.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 5.271869277954101,
|
|
"epoch": 2.419308357348703,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044161136662709577,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.22139864265918732,
|
|
"num_tokens": 57754317.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 5.2010307788848875,
|
|
"epoch": 2.419788664745437,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044158832402131133,
|
|
"loss": 4.8845,
|
|
"mean_token_accuracy": 0.22685072422027588,
|
|
"num_tokens": 57765882.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 5.235776090621949,
|
|
"epoch": 2.420268972142171,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044156527754784066,
|
|
"loss": 4.8441,
|
|
"mean_token_accuracy": 0.2280900776386261,
|
|
"num_tokens": 57776977.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 5.254271221160889,
|
|
"epoch": 2.4207492795389047,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044154222720721887,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.22626640796661376,
|
|
"num_tokens": 57788652.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 5.282021951675415,
|
|
"epoch": 2.421229586935639,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000441519172999981,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.2212475061416626,
|
|
"num_tokens": 57799660.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 5.251865339279175,
|
|
"epoch": 2.4217098943323725,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004414961149266625,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.21594949811697006,
|
|
"num_tokens": 57811754.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 5.2524528980255125,
|
|
"epoch": 2.422190201729107,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044147305298779856,
|
|
"loss": 4.9191,
|
|
"mean_token_accuracy": 0.2255387306213379,
|
|
"num_tokens": 57823470.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 5.322222757339477,
|
|
"epoch": 2.4226705091258407,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004414499871839247,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.21818740367889405,
|
|
"num_tokens": 57834917.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 5.199805021286011,
|
|
"epoch": 2.4231508165225746,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004414269175155763,
|
|
"loss": 4.9041,
|
|
"mean_token_accuracy": 0.22060853540897368,
|
|
"num_tokens": 57844655.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 5.25324239730835,
|
|
"epoch": 2.4236311239193085,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004414038439832891,
|
|
"loss": 4.9228,
|
|
"mean_token_accuracy": 0.22314024865627288,
|
|
"num_tokens": 57856019.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 5.230134916305542,
|
|
"epoch": 2.4241114313160423,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004413807665875988,
|
|
"loss": 4.8781,
|
|
"mean_token_accuracy": 0.22628380954265595,
|
|
"num_tokens": 57867661.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 5.2106297492980955,
|
|
"epoch": 2.4245917387127762,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044135768532904104,
|
|
"loss": 4.8982,
|
|
"mean_token_accuracy": 0.2206370413303375,
|
|
"num_tokens": 57879899.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 5.274259901046753,
|
|
"epoch": 2.42507204610951,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000441334600208152,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.21578627973794937,
|
|
"num_tokens": 57891168.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 5.250477695465088,
|
|
"epoch": 2.425552353506244,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044131151122546724,
|
|
"loss": 4.8342,
|
|
"mean_token_accuracy": 0.22099458575248718,
|
|
"num_tokens": 57901997.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 5.181818914413452,
|
|
"epoch": 2.426032660902978,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044128841838152313,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.2288301482796669,
|
|
"num_tokens": 57913380.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 5.139718723297119,
|
|
"epoch": 2.4265129682997117,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004412653216768558,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.23259792178869249,
|
|
"num_tokens": 57923675.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 5.236892366409302,
|
|
"epoch": 2.4269932756964456,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004412422211120013,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.22489610314369202,
|
|
"num_tokens": 57935885.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 5.1973601341247555,
|
|
"epoch": 2.4274735830931795,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004412191166874961,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.2244529128074646,
|
|
"num_tokens": 57946551.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 5.1602576732635494,
|
|
"epoch": 2.4279538904899134,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004411960084038766,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.2356921538710594,
|
|
"num_tokens": 57957778.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 5.188169717788696,
|
|
"epoch": 2.4284341978866473,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044117289626167917,
|
|
"loss": 4.9247,
|
|
"mean_token_accuracy": 0.22755209654569625,
|
|
"num_tokens": 57969256.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 5.248109912872314,
|
|
"epoch": 2.428914505283381,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004411497802614406,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.2281348541378975,
|
|
"num_tokens": 57981368.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 5.1910905838012695,
|
|
"epoch": 2.4293948126801155,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004411266604036975,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.21979343444108962,
|
|
"num_tokens": 57992862.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 5.139862394332885,
|
|
"epoch": 2.4298751200768494,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044110353668898674,
|
|
"loss": 4.7629,
|
|
"mean_token_accuracy": 0.23600274920463563,
|
|
"num_tokens": 58003492.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 5.165081882476807,
|
|
"epoch": 2.4303554274735832,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004410804091178449,
|
|
"loss": 4.7853,
|
|
"mean_token_accuracy": 0.230222749710083,
|
|
"num_tokens": 58014623.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 5.262546396255493,
|
|
"epoch": 2.430835734870317,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004410572776908092,
|
|
"loss": 4.9649,
|
|
"mean_token_accuracy": 0.22391248494386673,
|
|
"num_tokens": 58024886.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 5.267395973205566,
|
|
"epoch": 2.431316042267051,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044103414240841664,
|
|
"loss": 4.9485,
|
|
"mean_token_accuracy": 0.22300166189670562,
|
|
"num_tokens": 58035998.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 5.23329005241394,
|
|
"epoch": 2.431796349663785,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004410110032712043,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.23294074982404708,
|
|
"num_tokens": 58046577.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 5.131019401550293,
|
|
"epoch": 2.4322766570605188,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004409878602797094,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.23105624467134475,
|
|
"num_tokens": 58057711.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 5.218229627609253,
|
|
"epoch": 2.4327569644572526,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044096471343446923,
|
|
"loss": 4.8318,
|
|
"mean_token_accuracy": 0.22555720508098603,
|
|
"num_tokens": 58069657.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 5.213239049911499,
|
|
"epoch": 2.4332372718539865,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004409415627360213,
|
|
"loss": 4.8914,
|
|
"mean_token_accuracy": 0.22425956428050994,
|
|
"num_tokens": 58081081.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 5.231668090820312,
|
|
"epoch": 2.4337175792507204,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044091840818490303,
|
|
"loss": 4.8486,
|
|
"mean_token_accuracy": 0.22137889117002488,
|
|
"num_tokens": 58091561.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 5.140351009368897,
|
|
"epoch": 2.4341978866474543,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044089524978165197,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.2295369178056717,
|
|
"num_tokens": 58102640.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 5.214110422134399,
|
|
"epoch": 2.434678194044188,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044087208752680577,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.2182653069496155,
|
|
"num_tokens": 58113356.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 5.316407823562622,
|
|
"epoch": 2.435158501440922,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004408489214209023,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.2138427749276161,
|
|
"num_tokens": 58125437.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 5.313144540786743,
|
|
"epoch": 2.435638808837656,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004408257514644793,
|
|
"loss": 4.9619,
|
|
"mean_token_accuracy": 0.2259225443005562,
|
|
"num_tokens": 58138491.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 5.198267698287964,
|
|
"epoch": 2.43611911623439,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044080257765807476,
|
|
"loss": 4.8901,
|
|
"mean_token_accuracy": 0.22022671550512313,
|
|
"num_tokens": 58150200.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 5.234851884841919,
|
|
"epoch": 2.436599423631124,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004407794000022267,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.2261577308177948,
|
|
"num_tokens": 58162467.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 5.2887969493865965,
|
|
"epoch": 2.437079731027858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004407562184974732,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.21410568654537201,
|
|
"num_tokens": 58175052.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 5.230691528320312,
|
|
"epoch": 2.437560038424592,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004407330331443526,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.22584464102983476,
|
|
"num_tokens": 58186999.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 5.169686985015869,
|
|
"epoch": 2.438040345821326,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000440709843943403,
|
|
"loss": 4.7945,
|
|
"mean_token_accuracy": 0.23003166913986206,
|
|
"num_tokens": 58197811.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 5.28399133682251,
|
|
"epoch": 2.4385206532180597,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000440686650895163,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.22162880897521972,
|
|
"num_tokens": 58209545.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 5.187944984436035,
|
|
"epoch": 2.4390009606147935,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044066345400017084,
|
|
"loss": 4.8018,
|
|
"mean_token_accuracy": 0.23151367902755737,
|
|
"num_tokens": 58220994.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 5.157350254058838,
|
|
"epoch": 2.4394812680115274,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044064025325896524,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.2407313197851181,
|
|
"num_tokens": 58232778.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 5.241579866409301,
|
|
"epoch": 2.4399615754082613,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044061704867208484,
|
|
"loss": 4.9434,
|
|
"mean_token_accuracy": 0.23176864236593248,
|
|
"num_tokens": 58243889.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 5.151588106155396,
|
|
"epoch": 2.440441882804995,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044059384024006825,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.23006897270679474,
|
|
"num_tokens": 58256144.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 5.19352011680603,
|
|
"epoch": 2.440922190201729,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004405706279634545,
|
|
"loss": 4.8783,
|
|
"mean_token_accuracy": 0.22763650864362717,
|
|
"num_tokens": 58267509.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 5.157356834411621,
|
|
"epoch": 2.441402497598463,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044054741184278243,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.23887556046247482,
|
|
"num_tokens": 58278880.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 5.261596012115478,
|
|
"epoch": 2.441882804995197,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044052419187859095,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.2266361951828003,
|
|
"num_tokens": 58290046.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 5.128321170806885,
|
|
"epoch": 2.4423631123919307,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004405009680714193,
|
|
"loss": 4.7322,
|
|
"mean_token_accuracy": 0.23758183270692826,
|
|
"num_tokens": 58301406.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 5.158086681365967,
|
|
"epoch": 2.4428434197886646,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004404777404218065,
|
|
"loss": 4.8309,
|
|
"mean_token_accuracy": 0.2338385373353958,
|
|
"num_tokens": 58313064.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 5.1991739749908445,
|
|
"epoch": 2.4433237271853985,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000440454508930292,
|
|
"loss": 4.9493,
|
|
"mean_token_accuracy": 0.21538980901241303,
|
|
"num_tokens": 58324779.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 5.265347099304199,
|
|
"epoch": 2.443804034582133,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004404312735974152,
|
|
"loss": 4.9347,
|
|
"mean_token_accuracy": 0.21975625455379486,
|
|
"num_tokens": 58336064.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 5.140418148040771,
|
|
"epoch": 2.4442843419788662,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044040803442371533,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.2320781469345093,
|
|
"num_tokens": 58347497.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 5.09449028968811,
|
|
"epoch": 2.4447646493756006,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004403847914097321,
|
|
"loss": 4.7796,
|
|
"mean_token_accuracy": 0.23621957004070282,
|
|
"num_tokens": 58357716.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 5.222089719772339,
|
|
"epoch": 2.4452449567723344,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044036154455600517,
|
|
"loss": 4.9193,
|
|
"mean_token_accuracy": 0.2228131577372551,
|
|
"num_tokens": 58368451.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 5.244800138473511,
|
|
"epoch": 2.4457252641690683,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004403382938630741,
|
|
"loss": 4.8976,
|
|
"mean_token_accuracy": 0.22186142802238465,
|
|
"num_tokens": 58378915.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 5.164390802383423,
|
|
"epoch": 2.446205571565802,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044031503933147887,
|
|
"loss": 4.8078,
|
|
"mean_token_accuracy": 0.23915001899003982,
|
|
"num_tokens": 58390251.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 5.154802322387695,
|
|
"epoch": 2.446685878962536,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044029178096175934,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.22764649540185927,
|
|
"num_tokens": 58401390.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 5.211530494689941,
|
|
"epoch": 2.44716618635927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004402685187544554,
|
|
"loss": 4.8585,
|
|
"mean_token_accuracy": 0.2355824813246727,
|
|
"num_tokens": 58412530.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 5.276695823669433,
|
|
"epoch": 2.447646493756004,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004402452527101072,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.22193204015493392,
|
|
"num_tokens": 58424437.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 5.265928649902344,
|
|
"epoch": 2.4481268011527377,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004402219828292549,
|
|
"loss": 4.926,
|
|
"mean_token_accuracy": 0.2205255925655365,
|
|
"num_tokens": 58435661.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 5.253306913375854,
|
|
"epoch": 2.4486071085494716,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004401987091124388,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.21383630931377412,
|
|
"num_tokens": 58445840.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 5.265986013412475,
|
|
"epoch": 2.4490874159462055,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004401754315601992,
|
|
"loss": 4.9548,
|
|
"mean_token_accuracy": 0.2156996473670006,
|
|
"num_tokens": 58460160.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 5.203715896606445,
|
|
"epoch": 2.4495677233429394,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004401521501730765,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.2368559271097183,
|
|
"num_tokens": 58471257.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 5.074607467651367,
|
|
"epoch": 2.4500480307396733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044012886495161144,
|
|
"loss": 4.815,
|
|
"mean_token_accuracy": 0.22909512668848037,
|
|
"num_tokens": 58482830.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 5.170804071426391,
|
|
"epoch": 2.450528338136407,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004401055758963443,
|
|
"loss": 4.8522,
|
|
"mean_token_accuracy": 0.2343411400914192,
|
|
"num_tokens": 58494278.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 5.189333391189575,
|
|
"epoch": 2.451008645533141,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000440082283007816,
|
|
"loss": 4.837,
|
|
"mean_token_accuracy": 0.2262153819203377,
|
|
"num_tokens": 58505653.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 5.232948255538941,
|
|
"epoch": 2.451488952929875,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044005898628656734,
|
|
"loss": 4.8716,
|
|
"mean_token_accuracy": 0.2259698361158371,
|
|
"num_tokens": 58516906.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 5.210148286819458,
|
|
"epoch": 2.4519692603266092,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000440035685733139,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.23256392031908035,
|
|
"num_tokens": 58527326.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 5.176090240478516,
|
|
"epoch": 2.452449567723343,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004400123813480722,
|
|
"loss": 4.8266,
|
|
"mean_token_accuracy": 0.2337269440293312,
|
|
"num_tokens": 58537749.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 5.1960090637207035,
|
|
"epoch": 2.452929875120077,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043998907313190787,
|
|
"loss": 4.869,
|
|
"mean_token_accuracy": 0.222178553044796,
|
|
"num_tokens": 58549479.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 5.17247896194458,
|
|
"epoch": 2.453410182516811,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004399657610851873,
|
|
"loss": 4.8676,
|
|
"mean_token_accuracy": 0.22597639858722687,
|
|
"num_tokens": 58561051.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 5.2352594375610355,
|
|
"epoch": 2.4538904899135447,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043994244520845146,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.22388723194599153,
|
|
"num_tokens": 58571482.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 5.26043004989624,
|
|
"epoch": 2.4543707973102786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004399191255022418,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.22735117226839066,
|
|
"num_tokens": 58584369.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 5.1891649723052975,
|
|
"epoch": 2.4548511047070125,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004398958019670998,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.23053499907255173,
|
|
"num_tokens": 58595786.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 5.110941791534424,
|
|
"epoch": 2.4553314121037464,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043987247460356696,
|
|
"loss": 4.8385,
|
|
"mean_token_accuracy": 0.22803280055522918,
|
|
"num_tokens": 58608536.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 5.116344308853149,
|
|
"epoch": 2.4558117195004803,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004398491434121847,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.23657913357019425,
|
|
"num_tokens": 58620981.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 5.287122678756714,
|
|
"epoch": 2.456292026897214,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000439825808393495,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.22614310681819916,
|
|
"num_tokens": 58632802.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 5.204078578948975,
|
|
"epoch": 2.456772334293948,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004398024695480394,
|
|
"loss": 4.9351,
|
|
"mean_token_accuracy": 0.2246805652976036,
|
|
"num_tokens": 58644577.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 5.185160446166992,
|
|
"epoch": 2.457252641690682,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004397791268763598,
|
|
"loss": 4.8465,
|
|
"mean_token_accuracy": 0.2259562537074089,
|
|
"num_tokens": 58654970.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 5.238499736785888,
|
|
"epoch": 2.457732949087416,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043975578037899814,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.22465014606714248,
|
|
"num_tokens": 58666534.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 5.209278154373169,
|
|
"epoch": 2.4582132564841497,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004397324300564966,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.23106938302516938,
|
|
"num_tokens": 58677451.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 5.218133878707886,
|
|
"epoch": 2.4586935638808836,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004397090759093971,
|
|
"loss": 4.8628,
|
|
"mean_token_accuracy": 0.22905149012804032,
|
|
"num_tokens": 58689179.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 5.2045083999633786,
|
|
"epoch": 2.459173871277618,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043968571793824194,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.22696552574634551,
|
|
"num_tokens": 58701939.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 5.116093301773072,
|
|
"epoch": 2.4596541786743518,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004396623561435734,
|
|
"loss": 4.7441,
|
|
"mean_token_accuracy": 0.23915455341339112,
|
|
"num_tokens": 58714302.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 5.1824627876281735,
|
|
"epoch": 2.4601344860710856,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004396389905259339,
|
|
"loss": 4.8771,
|
|
"mean_token_accuracy": 0.2229331687092781,
|
|
"num_tokens": 58727619.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 5.245010709762573,
|
|
"epoch": 2.4606147934678195,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043961562108586603,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.2225929692387581,
|
|
"num_tokens": 58738929.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 5.3145300388336185,
|
|
"epoch": 2.4610951008645534,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043959224782391215,
|
|
"loss": 4.9453,
|
|
"mean_token_accuracy": 0.22718310207128525,
|
|
"num_tokens": 58751771.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 5.112285327911377,
|
|
"epoch": 2.4615754082612873,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000439568870740615,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.24369789510965348,
|
|
"num_tokens": 58762304.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 5.153982543945313,
|
|
"epoch": 2.462055715658021,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004395454898365174,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.22670551836490632,
|
|
"num_tokens": 58775222.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 5.1145439624786375,
|
|
"epoch": 2.462536023054755,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043952210511216205,
|
|
"loss": 4.8326,
|
|
"mean_token_accuracy": 0.23248003870248796,
|
|
"num_tokens": 58785904.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 5.151872730255127,
|
|
"epoch": 2.463016330451489,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043949871656809205,
|
|
"loss": 4.8542,
|
|
"mean_token_accuracy": 0.2355274200439453,
|
|
"num_tokens": 58796186.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 5.251420640945435,
|
|
"epoch": 2.463496637848223,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043947532420485024,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.2284131705760956,
|
|
"num_tokens": 58807317.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 5.264280652999878,
|
|
"epoch": 2.4639769452449567,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004394519280229798,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.22030002772808074,
|
|
"num_tokens": 58819108.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 5.188389492034912,
|
|
"epoch": 2.4644572526416906,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043942852802302397,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.22286704629659654,
|
|
"num_tokens": 58830962.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 5.305834817886352,
|
|
"epoch": 2.4649375600384245,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004394051242055259,
|
|
"loss": 4.9985,
|
|
"mean_token_accuracy": 0.21513222008943558,
|
|
"num_tokens": 58843236.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 5.223780155181885,
|
|
"epoch": 2.4654178674351583,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004393817165710291,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.2308872386813164,
|
|
"num_tokens": 58853995.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 5.1409666538238525,
|
|
"epoch": 2.465898174831892,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043935830512007687,
|
|
"loss": 4.8273,
|
|
"mean_token_accuracy": 0.2375153660774231,
|
|
"num_tokens": 58866563.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 5.25864200592041,
|
|
"epoch": 2.4663784822286265,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00043933488985321286,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.22389023900032043,
|
|
"num_tokens": 58878660.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 5.162670993804932,
|
|
"epoch": 2.46685878962536,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004393114707709807,
|
|
"loss": 4.8021,
|
|
"mean_token_accuracy": 0.23180255442857742,
|
|
"num_tokens": 58890332.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 5.176639986038208,
|
|
"epoch": 2.4673390970220943,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004392880478739241,
|
|
"loss": 4.9041,
|
|
"mean_token_accuracy": 0.2236527755856514,
|
|
"num_tokens": 58902228.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 5.239907073974609,
|
|
"epoch": 2.467819404418828,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004392646211625869,
|
|
"loss": 4.8987,
|
|
"mean_token_accuracy": 0.2288254275918007,
|
|
"num_tokens": 58914452.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 5.227190589904785,
|
|
"epoch": 2.468299711815562,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004392411906375129,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.2304124042391777,
|
|
"num_tokens": 58926079.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 5.1803946018219,
|
|
"epoch": 2.468780019212296,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043921775629924615,
|
|
"loss": 4.8417,
|
|
"mean_token_accuracy": 0.23379115462303163,
|
|
"num_tokens": 58937292.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 5.225245475769043,
|
|
"epoch": 2.46926032660903,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043919431814833077,
|
|
"loss": 4.9221,
|
|
"mean_token_accuracy": 0.22617134749889373,
|
|
"num_tokens": 58949425.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 5.257068109512329,
|
|
"epoch": 2.4697406340057637,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043917087618531084,
|
|
"loss": 4.9025,
|
|
"mean_token_accuracy": 0.2290273740887642,
|
|
"num_tokens": 58961620.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 5.207181406021118,
|
|
"epoch": 2.4702209414024976,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004391474304107307,
|
|
"loss": 4.8178,
|
|
"mean_token_accuracy": 0.23515239357948303,
|
|
"num_tokens": 58973043.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 5.2330728530883786,
|
|
"epoch": 2.4707012487992315,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043912398082513463,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.21320909410715103,
|
|
"num_tokens": 58984516.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 5.195977354049683,
|
|
"epoch": 2.4711815561959654,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000439100527429067,
|
|
"loss": 4.8184,
|
|
"mean_token_accuracy": 0.23230622857809066,
|
|
"num_tokens": 58996473.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 5.204995441436767,
|
|
"epoch": 2.4716618635926992,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043907707022307243,
|
|
"loss": 4.8224,
|
|
"mean_token_accuracy": 0.22680118530988694,
|
|
"num_tokens": 59009001.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 5.253498840332031,
|
|
"epoch": 2.472142170989433,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043905360920769553,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.2272225484251976,
|
|
"num_tokens": 59021238.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 5.266614007949829,
|
|
"epoch": 2.472622478386167,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000439030144383481,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.2293246015906334,
|
|
"num_tokens": 59031311.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 5.208481168746948,
|
|
"epoch": 2.473102785782901,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00043900667575097355,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.23100287467241287,
|
|
"num_tokens": 59043151.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 5.257993888854981,
|
|
"epoch": 2.473583093179635,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004389832033107181,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.23043064922094345,
|
|
"num_tokens": 59054513.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 5.207402944564819,
|
|
"epoch": 2.4740634005763686,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043895972706325953,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.2284642681479454,
|
|
"num_tokens": 59064909.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 5.126880264282226,
|
|
"epoch": 2.474543707973103,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000438936247009143,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.2228294536471367,
|
|
"num_tokens": 59077089.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 5.2196098327636715,
|
|
"epoch": 2.475024015369837,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043891276314891365,
|
|
"loss": 4.8425,
|
|
"mean_token_accuracy": 0.23198142945766448,
|
|
"num_tokens": 59089188.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 5.270108699798584,
|
|
"epoch": 2.4755043227665707,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004388892754831166,
|
|
"loss": 4.9411,
|
|
"mean_token_accuracy": 0.21596890836954116,
|
|
"num_tokens": 59101384.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 5.222210168838501,
|
|
"epoch": 2.4759846301633046,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004388657840122973,
|
|
"loss": 4.8628,
|
|
"mean_token_accuracy": 0.22167568057775497,
|
|
"num_tokens": 59112327.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 5.195142555236816,
|
|
"epoch": 2.4764649375600385,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000438842288737001,
|
|
"loss": 4.9137,
|
|
"mean_token_accuracy": 0.2251543492078781,
|
|
"num_tokens": 59123577.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 5.167669868469238,
|
|
"epoch": 2.4769452449567724,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043881878965777325,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.23836146295070648,
|
|
"num_tokens": 59135359.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 5.1654869556427006,
|
|
"epoch": 2.4774255523535063,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043879528677515973,
|
|
"loss": 4.7441,
|
|
"mean_token_accuracy": 0.23456114828586577,
|
|
"num_tokens": 59146679.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 5.184736490249634,
|
|
"epoch": 2.47790585975024,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043877178008970596,
|
|
"loss": 4.9048,
|
|
"mean_token_accuracy": 0.22214162796735765,
|
|
"num_tokens": 59159893.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 5.131521224975586,
|
|
"epoch": 2.478386167146974,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004387482696019578,
|
|
"loss": 4.8261,
|
|
"mean_token_accuracy": 0.23487259894609452,
|
|
"num_tokens": 59172592.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 5.2063422203063965,
|
|
"epoch": 2.478866474543708,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043872475531246105,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.23245082050561905,
|
|
"num_tokens": 59183650.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 5.214326429367065,
|
|
"epoch": 2.479346781940442,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043870123722176166,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.23253731727600097,
|
|
"num_tokens": 59195423.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 5.208007717132569,
|
|
"epoch": 2.4798270893371757,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004386777153304056,
|
|
"loss": 4.9045,
|
|
"mean_token_accuracy": 0.22776261270046233,
|
|
"num_tokens": 59208486.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 5.166433429718017,
|
|
"epoch": 2.4803073967339095,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043865418963893896,
|
|
"loss": 4.8675,
|
|
"mean_token_accuracy": 0.2265192300081253,
|
|
"num_tokens": 59220230.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 5.211950302124023,
|
|
"epoch": 2.4807877041306434,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004386306601479081,
|
|
"loss": 4.8827,
|
|
"mean_token_accuracy": 0.22820105999708176,
|
|
"num_tokens": 59231524.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 5.201438856124878,
|
|
"epoch": 2.4812680115273773,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004386071268578591,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.21870680004358292,
|
|
"num_tokens": 59243525.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 5.239387702941895,
|
|
"epoch": 2.4817483189241116,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043858358976933844,
|
|
"loss": 4.8021,
|
|
"mean_token_accuracy": 0.23269596546888352,
|
|
"num_tokens": 59253774.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 5.22696328163147,
|
|
"epoch": 2.4822286263208455,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043856004888289264,
|
|
"loss": 4.8555,
|
|
"mean_token_accuracy": 0.23037521094083785,
|
|
"num_tokens": 59265640.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 5.132445764541626,
|
|
"epoch": 2.4827089337175794,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004385365041990681,
|
|
"loss": 4.9244,
|
|
"mean_token_accuracy": 0.22420456111431122,
|
|
"num_tokens": 59277513.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 5.291885328292847,
|
|
"epoch": 2.4831892411143133,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004385129557184116,
|
|
"loss": 4.8872,
|
|
"mean_token_accuracy": 0.2293332949280739,
|
|
"num_tokens": 59289446.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 5.245462465286255,
|
|
"epoch": 2.483669548511047,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043848940344146976,
|
|
"loss": 4.9225,
|
|
"mean_token_accuracy": 0.22950903028249742,
|
|
"num_tokens": 59300156.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 5.154501867294312,
|
|
"epoch": 2.484149855907781,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004384658473687894,
|
|
"loss": 4.8574,
|
|
"mean_token_accuracy": 0.22609752416610718,
|
|
"num_tokens": 59311500.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 5.256465005874634,
|
|
"epoch": 2.484630163304515,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004384422875009176,
|
|
"loss": 4.9873,
|
|
"mean_token_accuracy": 0.21660172045230866,
|
|
"num_tokens": 59323299.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 5.2440385818481445,
|
|
"epoch": 2.485110470701249,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004384187238384011,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.22462350726127625,
|
|
"num_tokens": 59335955.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 5.1502495288848875,
|
|
"epoch": 2.4855907780979827,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004383951563817871,
|
|
"loss": 4.7779,
|
|
"mean_token_accuracy": 0.23437274396419525,
|
|
"num_tokens": 59347571.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 5.202844715118408,
|
|
"epoch": 2.4860710854947166,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004383715851316227,
|
|
"loss": 4.8706,
|
|
"mean_token_accuracy": 0.22834547311067582,
|
|
"num_tokens": 59358932.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 5.134037828445434,
|
|
"epoch": 2.4865513928914504,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043834801008845527,
|
|
"loss": 4.7895,
|
|
"mean_token_accuracy": 0.23271507620811463,
|
|
"num_tokens": 59371425.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 5.1503074169158936,
|
|
"epoch": 2.4870317002881843,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004383244312528321,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.22916982620954512,
|
|
"num_tokens": 59382917.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 5.246347427368164,
|
|
"epoch": 2.487512007684918,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004383008486253006,
|
|
"loss": 4.9371,
|
|
"mean_token_accuracy": 0.21969374865293503,
|
|
"num_tokens": 59395014.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 5.252179288864136,
|
|
"epoch": 2.487992315081652,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043827726220640827,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.22833629697561264,
|
|
"num_tokens": 59407115.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 5.315743541717529,
|
|
"epoch": 2.488472622478386,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00043825367199670274,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.21695873886346817,
|
|
"num_tokens": 59418744.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 5.1482078552246096,
|
|
"epoch": 2.4889529298751203,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004382300779967318,
|
|
"loss": 4.8041,
|
|
"mean_token_accuracy": 0.23728216737508773,
|
|
"num_tokens": 59429950.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 5.190100479125976,
|
|
"epoch": 2.489433237271854,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043820648020704303,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.22555991560220717,
|
|
"num_tokens": 59441335.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 5.244925689697266,
|
|
"epoch": 2.489913544668588,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043818287862818444,
|
|
"loss": 4.8714,
|
|
"mean_token_accuracy": 0.229472778737545,
|
|
"num_tokens": 59452325.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 5.265477418899536,
|
|
"epoch": 2.490393852065322,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000438159273260704,
|
|
"loss": 4.9645,
|
|
"mean_token_accuracy": 0.22538191229104995,
|
|
"num_tokens": 59464352.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 5.198654270172119,
|
|
"epoch": 2.490874159462056,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004381356641051497,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.23185565769672395,
|
|
"num_tokens": 59476048.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 5.23712797164917,
|
|
"epoch": 2.4913544668587897,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004381120511620697,
|
|
"loss": 4.9201,
|
|
"mean_token_accuracy": 0.2238827958703041,
|
|
"num_tokens": 59488139.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 5.202022504806519,
|
|
"epoch": 2.4918347742555236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043808843443201217,
|
|
"loss": 4.9432,
|
|
"mean_token_accuracy": 0.22086574286222457,
|
|
"num_tokens": 59498279.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 5.251803064346314,
|
|
"epoch": 2.4923150816522575,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004380648139155255,
|
|
"loss": 4.8773,
|
|
"mean_token_accuracy": 0.22228545397520066,
|
|
"num_tokens": 59509914.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 5.300123262405395,
|
|
"epoch": 2.4927953890489913,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004380411896131581,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.211761674284935,
|
|
"num_tokens": 59521441.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 5.255803060531616,
|
|
"epoch": 2.493275696445725,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043801756152545836,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.2243537038564682,
|
|
"num_tokens": 59533086.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 5.261987113952637,
|
|
"epoch": 2.493756003842459,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043799392965297496,
|
|
"loss": 4.9346,
|
|
"mean_token_accuracy": 0.22422681152820587,
|
|
"num_tokens": 59545165.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 5.198247909545898,
|
|
"epoch": 2.494236311239193,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004379702939962564,
|
|
"loss": 4.91,
|
|
"mean_token_accuracy": 0.21606962829828263,
|
|
"num_tokens": 59556016.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 5.21985182762146,
|
|
"epoch": 2.494716618635927,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004379466545558516,
|
|
"loss": 4.8814,
|
|
"mean_token_accuracy": 0.224064439535141,
|
|
"num_tokens": 59566431.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 5.268839645385742,
|
|
"epoch": 2.4951969260326607,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043792301133230933,
|
|
"loss": 4.951,
|
|
"mean_token_accuracy": 0.22136590331792833,
|
|
"num_tokens": 59579371.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 5.225128698348999,
|
|
"epoch": 2.4956772334293946,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004378993643261785,
|
|
"loss": 4.8352,
|
|
"mean_token_accuracy": 0.23383774012327194,
|
|
"num_tokens": 59590088.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 5.132566928863525,
|
|
"epoch": 2.496157540826129,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043787571353800814,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.24080482572317125,
|
|
"num_tokens": 59600973.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 5.181383895874023,
|
|
"epoch": 2.4966378482228624,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004378520589683475,
|
|
"loss": 4.8552,
|
|
"mean_token_accuracy": 0.22504758834838867,
|
|
"num_tokens": 59613194.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 5.209079933166504,
|
|
"epoch": 2.4971181556195967,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043782840061774544,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.2261744663119316,
|
|
"num_tokens": 59623932.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 5.240095710754394,
|
|
"epoch": 2.4975984630163306,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00043780473848675143,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.22142927050590516,
|
|
"num_tokens": 59635095.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 5.186735773086548,
|
|
"epoch": 2.4980787704130645,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004377810725759149,
|
|
"loss": 4.873,
|
|
"mean_token_accuracy": 0.22643351405858994,
|
|
"num_tokens": 59646930.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 5.169314861297607,
|
|
"epoch": 2.4985590778097984,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043775740288578516,
|
|
"loss": 4.8176,
|
|
"mean_token_accuracy": 0.22937406450510026,
|
|
"num_tokens": 59658729.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 5.1796341896057125,
|
|
"epoch": 2.4990393852065322,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004377337294169118,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.22223479747772218,
|
|
"num_tokens": 59670619.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 5.272053527832031,
|
|
"epoch": 2.499519692603266,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043771005216984457,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.2223030984401703,
|
|
"num_tokens": 59682307.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 5.235784816741943,
|
|
"epoch": 2.5,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000437686371145133,
|
|
"loss": 4.8563,
|
|
"mean_token_accuracy": 0.22961792051792146,
|
|
"num_tokens": 59693515.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 5.216558790206909,
|
|
"epoch": 2.500480307396734,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000437662686343327,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.223285311460495,
|
|
"num_tokens": 59705012.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 5.269689083099365,
|
|
"epoch": 2.5009606147934678,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004376389977649764,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.22304858565330504,
|
|
"num_tokens": 59716776.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 5.156000423431396,
|
|
"epoch": 2.5014409221902016,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004376153054106313,
|
|
"loss": 4.8864,
|
|
"mean_token_accuracy": 0.22826462239027023,
|
|
"num_tokens": 59727526.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 5.1989658832550045,
|
|
"epoch": 2.5019212295869355,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004375916092808416,
|
|
"loss": 4.8419,
|
|
"mean_token_accuracy": 0.23048499077558518,
|
|
"num_tokens": 59738861.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 5.363444137573242,
|
|
"epoch": 2.5024015369836694,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004375679093761575,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.20983866602182388,
|
|
"num_tokens": 59751019.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 5.251155042648316,
|
|
"epoch": 2.5028818443804033,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043754420569712925,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.2304222986102104,
|
|
"num_tokens": 59762936.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 5.198634195327759,
|
|
"epoch": 2.5033621517771376,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043752049824430736,
|
|
"loss": 4.8245,
|
|
"mean_token_accuracy": 0.23067770302295684,
|
|
"num_tokens": 59772909.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 5.113176155090332,
|
|
"epoch": 2.503842459173871,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00043749678701824197,
|
|
"loss": 4.7945,
|
|
"mean_token_accuracy": 0.2337280735373497,
|
|
"num_tokens": 59784003.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 5.205815267562866,
|
|
"epoch": 2.5043227665706054,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004374730720194837,
|
|
"loss": 4.9384,
|
|
"mean_token_accuracy": 0.22225023955106735,
|
|
"num_tokens": 59796200.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 5.20936803817749,
|
|
"epoch": 2.5048030739673393,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004374493532485832,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.23061748892068862,
|
|
"num_tokens": 59807559.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 5.233620595932007,
|
|
"epoch": 2.505283381364073,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000437425630706091,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.22272586971521377,
|
|
"num_tokens": 59818213.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 5.181348657608032,
|
|
"epoch": 2.505763688760807,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000437401904392558,
|
|
"loss": 4.9087,
|
|
"mean_token_accuracy": 0.2221958428621292,
|
|
"num_tokens": 59829485.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 5.195496368408203,
|
|
"epoch": 2.506243996157541,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043737817430853504,
|
|
"loss": 4.965,
|
|
"mean_token_accuracy": 0.2299943670630455,
|
|
"num_tokens": 59842187.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 5.3420977115631105,
|
|
"epoch": 2.506724303554275,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043735444045457303,
|
|
"loss": 5.0045,
|
|
"mean_token_accuracy": 0.21608218997716905,
|
|
"num_tokens": 59852783.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 5.240023231506347,
|
|
"epoch": 2.5072046109510087,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043733070283122306,
|
|
"loss": 4.8508,
|
|
"mean_token_accuracy": 0.22762778252363206,
|
|
"num_tokens": 59863661.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 5.1736329078674315,
|
|
"epoch": 2.5076849183477425,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043730696143903607,
|
|
"loss": 4.8621,
|
|
"mean_token_accuracy": 0.2274973839521408,
|
|
"num_tokens": 59876109.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 5.139631986618042,
|
|
"epoch": 2.5081652257444764,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004372832162785635,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.24049385786056518,
|
|
"num_tokens": 59886322.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 5.131896591186523,
|
|
"epoch": 2.5086455331412103,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004372594673503565,
|
|
"loss": 4.8275,
|
|
"mean_token_accuracy": 0.22950201034545897,
|
|
"num_tokens": 59897307.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 5.1426825523376465,
|
|
"epoch": 2.509125840537944,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004372357146549664,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.2317928358912468,
|
|
"num_tokens": 59908709.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 5.163176870346069,
|
|
"epoch": 2.509606147934678,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043721195819294487,
|
|
"loss": 4.8241,
|
|
"mean_token_accuracy": 0.24064693599939346,
|
|
"num_tokens": 59920082.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 5.156716775894165,
|
|
"epoch": 2.510086455331412,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004371881979648433,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.2240738719701767,
|
|
"num_tokens": 59931632.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 5.126112604141236,
|
|
"epoch": 2.5105667627281463,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004371644339712133,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.2325238436460495,
|
|
"num_tokens": 59944093.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 5.147172451019287,
|
|
"epoch": 2.5110470701248797,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004371406662126067,
|
|
"loss": 4.8444,
|
|
"mean_token_accuracy": 0.22427631467580794,
|
|
"num_tokens": 59954879.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 5.183293151855469,
|
|
"epoch": 2.511527377521614,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043711689468957534,
|
|
"loss": 4.8705,
|
|
"mean_token_accuracy": 0.2256565883755684,
|
|
"num_tokens": 59967074.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 5.306117820739746,
|
|
"epoch": 2.5120076849183475,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043709311940267107,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.2239045023918152,
|
|
"num_tokens": 59978939.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 5.232266855239868,
|
|
"epoch": 2.512487992315082,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004370693403524458,
|
|
"loss": 4.8812,
|
|
"mean_token_accuracy": 0.2271528035402298,
|
|
"num_tokens": 59989251.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 5.160184144973755,
|
|
"epoch": 2.5129682997118157,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004370455575394518,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.23063498586416245,
|
|
"num_tokens": 60000267.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 5.251547861099243,
|
|
"epoch": 2.5134486071085496,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004370217709642411,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.2236742928624153,
|
|
"num_tokens": 60011190.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 5.254093170166016,
|
|
"epoch": 2.5139289145052834,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000436997980627366,
|
|
"loss": 4.9409,
|
|
"mean_token_accuracy": 0.21911938935518266,
|
|
"num_tokens": 60023496.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 5.29413251876831,
|
|
"epoch": 2.5144092219020173,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043697418652937877,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.2222231447696686,
|
|
"num_tokens": 60034585.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 5.236820363998413,
|
|
"epoch": 2.514889529298751,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004369503886708319,
|
|
"loss": 4.9506,
|
|
"mean_token_accuracy": 0.21905994564294815,
|
|
"num_tokens": 60046333.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 5.2200305461883545,
|
|
"epoch": 2.515369836695485,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043692658705227796,
|
|
"loss": 4.9323,
|
|
"mean_token_accuracy": 0.22598293721675872,
|
|
"num_tokens": 60058744.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 5.328441905975342,
|
|
"epoch": 2.515850144092219,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043690278167426945,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.2218186154961586,
|
|
"num_tokens": 60069303.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 5.180104207992554,
|
|
"epoch": 2.516330451488953,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004368789725373591,
|
|
"loss": 4.8209,
|
|
"mean_token_accuracy": 0.23170508891344072,
|
|
"num_tokens": 60080604.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 5.2201268672943115,
|
|
"epoch": 2.5168107588856867,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043685515964209977,
|
|
"loss": 4.8482,
|
|
"mean_token_accuracy": 0.22993848323822022,
|
|
"num_tokens": 60090151.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 5.263975667953491,
|
|
"epoch": 2.5172910662824206,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004368313429890441,
|
|
"loss": 4.9993,
|
|
"mean_token_accuracy": 0.22278196215629578,
|
|
"num_tokens": 60102528.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 5.176841878890992,
|
|
"epoch": 2.517771373679155,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004368075225787453,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.23322963565587998,
|
|
"num_tokens": 60113078.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 5.126330995559693,
|
|
"epoch": 2.5182516810758884,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004367836984117562,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.23144018799066543,
|
|
"num_tokens": 60124728.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 5.113933038711548,
|
|
"epoch": 2.5187319884726227,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043675987048863,
|
|
"loss": 4.7984,
|
|
"mean_token_accuracy": 0.2329600363969803,
|
|
"num_tokens": 60136224.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 5.25955810546875,
|
|
"epoch": 2.519212295869356,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004367360388099201,
|
|
"loss": 4.9452,
|
|
"mean_token_accuracy": 0.2199702799320221,
|
|
"num_tokens": 60148654.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 5.370873212814331,
|
|
"epoch": 2.5196926032660905,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004367122033761796,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.21936780363321304,
|
|
"num_tokens": 60159740.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 5.2100776672363285,
|
|
"epoch": 2.5201729106628243,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004366883641879618,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.22242576479911805,
|
|
"num_tokens": 60171387.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 5.1347455978393555,
|
|
"epoch": 2.520653218059558,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043666452124582034,
|
|
"loss": 4.812,
|
|
"mean_token_accuracy": 0.23790554702281952,
|
|
"num_tokens": 60181562.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 5.098042011260986,
|
|
"epoch": 2.521133525456292,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004366406745503088,
|
|
"loss": 4.76,
|
|
"mean_token_accuracy": 0.2346281185746193,
|
|
"num_tokens": 60191187.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 5.112291669845581,
|
|
"epoch": 2.521613832853026,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004366168241019807,
|
|
"loss": 4.827,
|
|
"mean_token_accuracy": 0.2326110303401947,
|
|
"num_tokens": 60203792.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 5.291718816757202,
|
|
"epoch": 2.52209414024976,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004365929699013899,
|
|
"loss": 4.8904,
|
|
"mean_token_accuracy": 0.23028724044561386,
|
|
"num_tokens": 60215523.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 5.245113515853882,
|
|
"epoch": 2.5225744476464937,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004365691119490902,
|
|
"loss": 4.939,
|
|
"mean_token_accuracy": 0.22394480258226396,
|
|
"num_tokens": 60226113.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 5.263897371292114,
|
|
"epoch": 2.5230547550432276,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004365452502456354,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.21666356325149536,
|
|
"num_tokens": 60238521.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 5.1314982891082765,
|
|
"epoch": 2.5235350624399615,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004365213847915796,
|
|
"loss": 4.7554,
|
|
"mean_token_accuracy": 0.23539794683456422,
|
|
"num_tokens": 60249717.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 5.261186695098877,
|
|
"epoch": 2.5240153698366954,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043649751558747695,
|
|
"loss": 4.9623,
|
|
"mean_token_accuracy": 0.21756114959716796,
|
|
"num_tokens": 60261749.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 5.244775724411011,
|
|
"epoch": 2.5244956772334293,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043647364263388143,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.2217550531029701,
|
|
"num_tokens": 60272925.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 5.196218729019165,
|
|
"epoch": 2.524975984630163,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004364497659313475,
|
|
"loss": 4.9016,
|
|
"mean_token_accuracy": 0.22420225143432618,
|
|
"num_tokens": 60285081.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 5.254171133041382,
|
|
"epoch": 2.525456292026897,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004364258854804294,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.2319134443998337,
|
|
"num_tokens": 60296796.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 5.2314105987548825,
|
|
"epoch": 2.5259365994236314,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004364020012816815,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.22727528363466262,
|
|
"num_tokens": 60308600.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 5.185413837432861,
|
|
"epoch": 2.526416906820365,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004363781133356584,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.229492124915123,
|
|
"num_tokens": 60319188.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 5.298202419281006,
|
|
"epoch": 2.526897214217099,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004363542216429147,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.2267363265156746,
|
|
"num_tokens": 60329912.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 5.261073446273803,
|
|
"epoch": 2.527377521613833,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004363303262040051,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.2244286894798279,
|
|
"num_tokens": 60339760.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 5.081413221359253,
|
|
"epoch": 2.527857829010567,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043630642701948446,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.24080440551042556,
|
|
"num_tokens": 60349947.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 5.216693162918091,
|
|
"epoch": 2.5283381364073008,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00043628252408990756,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.22117610424757003,
|
|
"num_tokens": 60362620.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 5.277050161361695,
|
|
"epoch": 2.5288184438040346,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043625861741582926,
|
|
"loss": 4.9142,
|
|
"mean_token_accuracy": 0.22711616307497023,
|
|
"num_tokens": 60373729.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 5.236779403686524,
|
|
"epoch": 2.5292987512007685,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043623470699780483,
|
|
"loss": 4.8721,
|
|
"mean_token_accuracy": 0.22636013180017472,
|
|
"num_tokens": 60386423.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 5.1991040229797365,
|
|
"epoch": 2.5297790585975024,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004362107928363892,
|
|
"loss": 4.8895,
|
|
"mean_token_accuracy": 0.22605448365211486,
|
|
"num_tokens": 60398364.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 5.189363670349121,
|
|
"epoch": 2.5302593659942363,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004361868749321377,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.22923046350479126,
|
|
"num_tokens": 60408423.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 5.273103046417236,
|
|
"epoch": 2.53073967339097,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004361629532856055,
|
|
"loss": 4.9456,
|
|
"mean_token_accuracy": 0.22094983607530594,
|
|
"num_tokens": 60420229.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 5.307610368728637,
|
|
"epoch": 2.531219980787704,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043613902789734816,
|
|
"loss": 4.9791,
|
|
"mean_token_accuracy": 0.22327430695295333,
|
|
"num_tokens": 60430711.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 5.269787359237671,
|
|
"epoch": 2.531700288184438,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000436115098767921,
|
|
"loss": 4.9561,
|
|
"mean_token_accuracy": 0.21856672912836075,
|
|
"num_tokens": 60442293.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 5.174128293991089,
|
|
"epoch": 2.532180595581172,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043609116589787974,
|
|
"loss": 4.8414,
|
|
"mean_token_accuracy": 0.22696544229984283,
|
|
"num_tokens": 60452616.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 5.1906884670257565,
|
|
"epoch": 2.5326609029779057,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004360672292877799,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.2244404748082161,
|
|
"num_tokens": 60463254.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 5.196820259094238,
|
|
"epoch": 2.53314121037464,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043604328893817726,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.23258469849824906,
|
|
"num_tokens": 60473725.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 5.223887491226196,
|
|
"epoch": 2.5336215177713735,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043601934484962775,
|
|
"loss": 4.9021,
|
|
"mean_token_accuracy": 0.23032606095075608,
|
|
"num_tokens": 60484502.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 5.1533040523529055,
|
|
"epoch": 2.534101825168108,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004359953970226871,
|
|
"loss": 4.844,
|
|
"mean_token_accuracy": 0.23413677960634233,
|
|
"num_tokens": 60496134.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 5.2166290283203125,
|
|
"epoch": 2.5345821325648417,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043597144545791134,
|
|
"loss": 4.9296,
|
|
"mean_token_accuracy": 0.23193558305501938,
|
|
"num_tokens": 60507236.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 5.184367561340332,
|
|
"epoch": 2.5350624399615755,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004359474901558567,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.23327660113573073,
|
|
"num_tokens": 60517499.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 5.254463481903076,
|
|
"epoch": 2.5355427473583094,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004359235311170792,
|
|
"loss": 4.9365,
|
|
"mean_token_accuracy": 0.21636133939027785,
|
|
"num_tokens": 60529434.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 5.300494813919068,
|
|
"epoch": 2.5360230547550433,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004358995683421352,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.2232494607567787,
|
|
"num_tokens": 60542571.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 5.177821111679077,
|
|
"epoch": 2.536503362151777,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043587560183158095,
|
|
"loss": 4.8278,
|
|
"mean_token_accuracy": 0.22569537907838821,
|
|
"num_tokens": 60553826.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 5.152345991134643,
|
|
"epoch": 2.536983669548511,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000435851631585973,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.22723005563020707,
|
|
"num_tokens": 60565173.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 5.185355234146118,
|
|
"epoch": 2.537463976945245,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004358276576058677,
|
|
"loss": 4.8378,
|
|
"mean_token_accuracy": 0.23175583630800248,
|
|
"num_tokens": 60577267.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 5.218684339523316,
|
|
"epoch": 2.537944284341979,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004358036798918218,
|
|
"loss": 4.8843,
|
|
"mean_token_accuracy": 0.2239573121070862,
|
|
"num_tokens": 60587441.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 5.25899486541748,
|
|
"epoch": 2.5384245917387127,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004357796984443919,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.22650626301765442,
|
|
"num_tokens": 60597173.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 5.16945104598999,
|
|
"epoch": 2.5389048991354466,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043575571326413484,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.22527746111154556,
|
|
"num_tokens": 60608299.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 5.312683963775635,
|
|
"epoch": 2.5393852065321805,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004357317243516075,
|
|
"loss": 4.9923,
|
|
"mean_token_accuracy": 0.2236280396580696,
|
|
"num_tokens": 60619106.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 5.194765567779541,
|
|
"epoch": 2.5398655139289144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043570773170736676,
|
|
"loss": 4.7738,
|
|
"mean_token_accuracy": 0.23785741180181502,
|
|
"num_tokens": 60629339.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 5.167845916748047,
|
|
"epoch": 2.5403458213256487,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043568373533196976,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.23500405848026276,
|
|
"num_tokens": 60640162.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 5.158766889572144,
|
|
"epoch": 2.540826128722382,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043565973522597344,
|
|
"loss": 4.833,
|
|
"mean_token_accuracy": 0.22426412105560303,
|
|
"num_tokens": 60652529.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 5.167701768875122,
|
|
"epoch": 2.5413064361191164,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043563573138993524,
|
|
"loss": 4.7825,
|
|
"mean_token_accuracy": 0.2290465235710144,
|
|
"num_tokens": 60663035.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 5.158677959442139,
|
|
"epoch": 2.54178674351585,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004356117238244123,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.23152656555175782,
|
|
"num_tokens": 60674430.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 5.1779335021972654,
|
|
"epoch": 2.542267050912584,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043558771252996204,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.23553578108549117,
|
|
"num_tokens": 60685923.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 5.170600557327271,
|
|
"epoch": 2.542747358309318,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000435563697507142,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.2320768028497696,
|
|
"num_tokens": 60696344.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 5.211849546432495,
|
|
"epoch": 2.543227665706052,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004355396787565096,
|
|
"loss": 4.8857,
|
|
"mean_token_accuracy": 0.2280934765934944,
|
|
"num_tokens": 60709941.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 5.211927890777588,
|
|
"epoch": 2.543707973102786,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043551565627862257,
|
|
"loss": 4.8466,
|
|
"mean_token_accuracy": 0.22800153940916063,
|
|
"num_tokens": 60721245.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 5.185878086090088,
|
|
"epoch": 2.5441882804995197,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004354916300740387,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.2270375221967697,
|
|
"num_tokens": 60732763.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 5.118517875671387,
|
|
"epoch": 2.5446685878962536,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004354676001433157,
|
|
"loss": 4.8345,
|
|
"mean_token_accuracy": 0.2323276236653328,
|
|
"num_tokens": 60743192.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 5.087047386169433,
|
|
"epoch": 2.5451488952929875,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004354435664870116,
|
|
"loss": 4.7389,
|
|
"mean_token_accuracy": 0.23856834024190904,
|
|
"num_tokens": 60754115.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 5.253400802612305,
|
|
"epoch": 2.5456292026897214,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043541952910568417,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.2296978935599327,
|
|
"num_tokens": 60765516.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 5.22387728691101,
|
|
"epoch": 2.5461095100864553,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004353954879998916,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.22842017263174058,
|
|
"num_tokens": 60776206.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 5.15810751914978,
|
|
"epoch": 2.546589817483189,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004353714431701922,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.22883677631616592,
|
|
"num_tokens": 60786992.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 5.202462863922119,
|
|
"epoch": 2.547070124879923,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004353473946171441,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.22204888015985488,
|
|
"num_tokens": 60797765.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 5.236706686019898,
|
|
"epoch": 2.547550432276657,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043532334234130547,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.21511630117893218,
|
|
"num_tokens": 60808873.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 5.287065553665161,
|
|
"epoch": 2.5480307396733908,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043529928634323503,
|
|
"loss": 4.9249,
|
|
"mean_token_accuracy": 0.22242189347743987,
|
|
"num_tokens": 60820245.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 5.200459098815918,
|
|
"epoch": 2.548511047070125,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043527522662349113,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.2292040094733238,
|
|
"num_tokens": 60832159.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 5.210034370422363,
|
|
"epoch": 2.5489913544668585,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004352511631826324,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.22805323749780654,
|
|
"num_tokens": 60842957.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 5.1573648929595945,
|
|
"epoch": 2.549471661863593,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004352270960212175,
|
|
"loss": 4.8344,
|
|
"mean_token_accuracy": 0.23503851294517517,
|
|
"num_tokens": 60852537.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 5.2850724220275875,
|
|
"epoch": 2.5499519692603267,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004352030251398052,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.216036619246006,
|
|
"num_tokens": 60865761.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 5.283509206771851,
|
|
"epoch": 2.5504322766570606,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043517895053895434,
|
|
"loss": 4.888,
|
|
"mean_token_accuracy": 0.22830187231302262,
|
|
"num_tokens": 60877805.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 5.208657455444336,
|
|
"epoch": 2.5509125840537945,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004351548722192239,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.22477088421583175,
|
|
"num_tokens": 60889868.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 5.167305755615234,
|
|
"epoch": 2.5513928914505284,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004351307901811729,
|
|
"loss": 4.8694,
|
|
"mean_token_accuracy": 0.23218984156847,
|
|
"num_tokens": 60902046.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 5.230257987976074,
|
|
"epoch": 2.5518731988472623,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004351067044253605,
|
|
"loss": 4.8668,
|
|
"mean_token_accuracy": 0.22085123360157013,
|
|
"num_tokens": 60913447.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 5.228398704528809,
|
|
"epoch": 2.552353506243996,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043508261495234577,
|
|
"loss": 4.8514,
|
|
"mean_token_accuracy": 0.23458220511674882,
|
|
"num_tokens": 60924920.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 5.143043470382691,
|
|
"epoch": 2.55283381364073,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000435058521762688,
|
|
"loss": 4.7928,
|
|
"mean_token_accuracy": 0.23681768476963044,
|
|
"num_tokens": 60936937.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 5.163158845901489,
|
|
"epoch": 2.553314121037464,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004350344248569467,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.24210432767868043,
|
|
"num_tokens": 60947836.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 5.182175159454346,
|
|
"epoch": 2.553794428434198,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004350103242356813,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.22445462346076966,
|
|
"num_tokens": 60959380.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 5.283533143997192,
|
|
"epoch": 2.5542747358309317,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004349862198994513,
|
|
"loss": 4.9123,
|
|
"mean_token_accuracy": 0.22324459850788117,
|
|
"num_tokens": 60970148.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 5.219712972640991,
|
|
"epoch": 2.5547550432276656,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004349621118488163,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.23842350244522095,
|
|
"num_tokens": 60981139.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 5.118231773376465,
|
|
"epoch": 2.5552353506243994,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004349380000843361,
|
|
"loss": 4.8259,
|
|
"mean_token_accuracy": 0.23181494027376176,
|
|
"num_tokens": 60992204.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 5.179120683670044,
|
|
"epoch": 2.5557156580211338,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004349138846065704,
|
|
"loss": 4.8204,
|
|
"mean_token_accuracy": 0.23277657032012938,
|
|
"num_tokens": 61002198.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 5.254082536697387,
|
|
"epoch": 2.556195965417867,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004348897654160791,
|
|
"loss": 4.9359,
|
|
"mean_token_accuracy": 0.22718619257211686,
|
|
"num_tokens": 61012987.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 5.160164546966553,
|
|
"epoch": 2.5566762728146015,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004348656425134223,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.23781875669956207,
|
|
"num_tokens": 61023668.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 5.20031476020813,
|
|
"epoch": 2.5571565802113354,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043484151589916,
|
|
"loss": 4.7809,
|
|
"mean_token_accuracy": 0.23556509017944335,
|
|
"num_tokens": 61034375.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 5.185934019088745,
|
|
"epoch": 2.5576368876080693,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004348173855738523,
|
|
"loss": 4.8716,
|
|
"mean_token_accuracy": 0.22354686707258226,
|
|
"num_tokens": 61045625.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 5.203153467178344,
|
|
"epoch": 2.558117195004803,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004347932515380595,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.2320193737745285,
|
|
"num_tokens": 61056359.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 5.195769548416138,
|
|
"epoch": 2.558597502401537,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004347691137923418,
|
|
"loss": 4.8426,
|
|
"mean_token_accuracy": 0.2307454079389572,
|
|
"num_tokens": 61067194.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 5.282229280471801,
|
|
"epoch": 2.559077809798271,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004347449723372598,
|
|
"loss": 4.9313,
|
|
"mean_token_accuracy": 0.22139095067977904,
|
|
"num_tokens": 61079341.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 5.243840551376342,
|
|
"epoch": 2.559558117195005,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004347208271733738,
|
|
"loss": 4.9348,
|
|
"mean_token_accuracy": 0.226503948867321,
|
|
"num_tokens": 61090843.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 5.170305299758911,
|
|
"epoch": 2.5600384245917387,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004346966783012445,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.22859929800033568,
|
|
"num_tokens": 61101780.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 5.213365983963013,
|
|
"epoch": 2.5605187319884726,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043467252572143247,
|
|
"loss": 4.8978,
|
|
"mean_token_accuracy": 0.23099792152643203,
|
|
"num_tokens": 61113026.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 5.225868034362793,
|
|
"epoch": 2.5609990393852065,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00043464836943449866,
|
|
"loss": 4.8759,
|
|
"mean_token_accuracy": 0.2289099007844925,
|
|
"num_tokens": 61124772.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 5.216859245300293,
|
|
"epoch": 2.5614793467819403,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004346242094410036,
|
|
"loss": 4.8899,
|
|
"mean_token_accuracy": 0.22909623831510545,
|
|
"num_tokens": 61136683.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 5.206309413909912,
|
|
"epoch": 2.561959654178674,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004346000457415085,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.23523251414299012,
|
|
"num_tokens": 61148047.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 5.17175989151001,
|
|
"epoch": 2.562439961575408,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00043457587833657424,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.2322452187538147,
|
|
"num_tokens": 61160680.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 5.22050142288208,
|
|
"epoch": 2.5629202689721424,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043455170722676194,
|
|
"loss": 4.8781,
|
|
"mean_token_accuracy": 0.22574893087148667,
|
|
"num_tokens": 61172624.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 5.135837507247925,
|
|
"epoch": 2.563400576368876,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004345275324126328,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.23528261184692384,
|
|
"num_tokens": 61183971.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 5.175984191894531,
|
|
"epoch": 2.56388088376561,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043450335389474796,
|
|
"loss": 4.7732,
|
|
"mean_token_accuracy": 0.23712784498929979,
|
|
"num_tokens": 61194511.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 5.163534259796142,
|
|
"epoch": 2.5643611911623436,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004344791716736689,
|
|
"loss": 4.7905,
|
|
"mean_token_accuracy": 0.23134261071681977,
|
|
"num_tokens": 61205235.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 5.10134539604187,
|
|
"epoch": 2.564841498559078,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043445498574995705,
|
|
"loss": 4.8203,
|
|
"mean_token_accuracy": 0.23617089092731475,
|
|
"num_tokens": 61217460.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 5.218317174911499,
|
|
"epoch": 2.565321805955812,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043443079612417394,
|
|
"loss": 4.8287,
|
|
"mean_token_accuracy": 0.22889280915260315,
|
|
"num_tokens": 61229917.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 5.27015438079834,
|
|
"epoch": 2.5658021133525457,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004344066027968812,
|
|
"loss": 4.9774,
|
|
"mean_token_accuracy": 0.21463661789894103,
|
|
"num_tokens": 61241826.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 5.281561756134034,
|
|
"epoch": 2.5662824207492796,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043438240576864034,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.2252814695239067,
|
|
"num_tokens": 61254095.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 5.2078498840332035,
|
|
"epoch": 2.5667627281460135,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004343582050400134,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.23003289103507996,
|
|
"num_tokens": 61266114.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 5.172713899612427,
|
|
"epoch": 2.5672430355427474,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004343340006115621,
|
|
"loss": 4.8396,
|
|
"mean_token_accuracy": 0.2381330370903015,
|
|
"num_tokens": 61277289.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 5.310648632049561,
|
|
"epoch": 2.5677233429394812,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004343097924838483,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.22249739170074462,
|
|
"num_tokens": 61289424.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 5.26606936454773,
|
|
"epoch": 2.568203650336215,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004342855806574344,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.22756934762001038,
|
|
"num_tokens": 61300821.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 5.197086668014526,
|
|
"epoch": 2.568683957732949,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004342613651328822,
|
|
"loss": 4.8454,
|
|
"mean_token_accuracy": 0.23240066766738893,
|
|
"num_tokens": 61312097.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 5.122616910934449,
|
|
"epoch": 2.569164265129683,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000434237145910754,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.2323356419801712,
|
|
"num_tokens": 61324144.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 5.1948850631713865,
|
|
"epoch": 2.5696445725264168,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00043421292299161213,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.2292586997151375,
|
|
"num_tokens": 61335809.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 5.235209178924561,
|
|
"epoch": 2.570124879923151,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043418869637601887,
|
|
"loss": 4.8428,
|
|
"mean_token_accuracy": 0.2288612961769104,
|
|
"num_tokens": 61346980.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 5.263842439651489,
|
|
"epoch": 2.5706051873198845,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043416446606453686,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.2269706666469574,
|
|
"num_tokens": 61358401.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 5.154978895187378,
|
|
"epoch": 2.571085494716619,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004341402320577285,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.229957315325737,
|
|
"num_tokens": 61369383.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 5.286456680297851,
|
|
"epoch": 2.5715658021133523,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004341159943561566,
|
|
"loss": 4.8726,
|
|
"mean_token_accuracy": 0.22624915987253189,
|
|
"num_tokens": 61380439.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 5.198639965057373,
|
|
"epoch": 2.5720461095100866,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004340917529603837,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.23699888288974763,
|
|
"num_tokens": 61391218.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 5.153933668136597,
|
|
"epoch": 2.5725264169068205,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004340675078709728,
|
|
"loss": 4.7971,
|
|
"mean_token_accuracy": 0.22926707118749617,
|
|
"num_tokens": 61402715.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 5.251871490478516,
|
|
"epoch": 2.5730067243035544,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004340432590884866,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.22303646355867385,
|
|
"num_tokens": 61414361.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 5.21401162147522,
|
|
"epoch": 2.5734870317002883,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043401900661348825,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.23437957018613814,
|
|
"num_tokens": 61426817.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 5.128950214385986,
|
|
"epoch": 2.573967339097022,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043399475044654073,
|
|
"loss": 4.8327,
|
|
"mean_token_accuracy": 0.22799860686063766,
|
|
"num_tokens": 61438142.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 5.204029893875122,
|
|
"epoch": 2.574447646493756,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043397049058820726,
|
|
"loss": 4.8951,
|
|
"mean_token_accuracy": 0.22633402347564696,
|
|
"num_tokens": 61450708.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 5.254377651214599,
|
|
"epoch": 2.57492795389049,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000433946227039051,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.2289728567004204,
|
|
"num_tokens": 61462266.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 5.195062351226807,
|
|
"epoch": 2.5754082612872238,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004339219597996353,
|
|
"loss": 4.8745,
|
|
"mean_token_accuracy": 0.22702620327472686,
|
|
"num_tokens": 61473690.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 5.110820245742798,
|
|
"epoch": 2.5758885686839577,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004338976888705236,
|
|
"loss": 4.7432,
|
|
"mean_token_accuracy": 0.23836125582456588,
|
|
"num_tokens": 61484997.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 5.120053482055664,
|
|
"epoch": 2.5763688760806915,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043387341425227944,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.22603914588689805,
|
|
"num_tokens": 61497792.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 5.1905780792236325,
|
|
"epoch": 2.5768491834774254,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004338491359454664,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.23427007645368575,
|
|
"num_tokens": 61509060.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 5.218004131317139,
|
|
"epoch": 2.5773294908741593,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043382485395064796,
|
|
"loss": 4.8929,
|
|
"mean_token_accuracy": 0.23781045228242875,
|
|
"num_tokens": 61519577.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 5.15456109046936,
|
|
"epoch": 2.577809798270893,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004338005682683881,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.23275409638881683,
|
|
"num_tokens": 61531956.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 5.250078010559082,
|
|
"epoch": 2.5782901056676275,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043377627889925057,
|
|
"loss": 4.9058,
|
|
"mean_token_accuracy": 0.22944066822528839,
|
|
"num_tokens": 61543801.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 5.252503681182861,
|
|
"epoch": 2.578770413064361,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004337519858437994,
|
|
"loss": 4.929,
|
|
"mean_token_accuracy": 0.2200077936053276,
|
|
"num_tokens": 61555899.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 5.125127267837525,
|
|
"epoch": 2.5792507204610953,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004337276891025984,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.24053539335727692,
|
|
"num_tokens": 61567280.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 5.159241533279419,
|
|
"epoch": 2.579731027857829,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043370338867621184,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.22567370682954788,
|
|
"num_tokens": 61578026.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 5.230853843688965,
|
|
"epoch": 2.580211335254563,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043367908456520387,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.22501195818185807,
|
|
"num_tokens": 61589399.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 5.216916513442993,
|
|
"epoch": 2.580691642651297,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004336547767701387,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.2249898672103882,
|
|
"num_tokens": 61601025.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 5.257025241851807,
|
|
"epoch": 2.581171950048031,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043363046529158077,
|
|
"loss": 4.9813,
|
|
"mean_token_accuracy": 0.22317082285881043,
|
|
"num_tokens": 61612529.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 5.231204509735107,
|
|
"epoch": 2.5816522574447647,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004336061501300944,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.22551472932100297,
|
|
"num_tokens": 61624423.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 5.302283048629761,
|
|
"epoch": 2.5821325648414986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004335818312862442,
|
|
"loss": 4.9368,
|
|
"mean_token_accuracy": 0.2295331820845604,
|
|
"num_tokens": 61635002.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 5.176891851425171,
|
|
"epoch": 2.5826128722382324,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043355750876059485,
|
|
"loss": 4.7952,
|
|
"mean_token_accuracy": 0.23718696534633638,
|
|
"num_tokens": 61645911.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 5.1852353572845455,
|
|
"epoch": 2.5830931796349663,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043353318255371086,
|
|
"loss": 4.8569,
|
|
"mean_token_accuracy": 0.2320757269859314,
|
|
"num_tokens": 61657545.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 5.266826009750366,
|
|
"epoch": 2.5835734870317,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004335088526661571,
|
|
"loss": 4.9274,
|
|
"mean_token_accuracy": 0.22197365760803223,
|
|
"num_tokens": 61669567.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 5.291628837585449,
|
|
"epoch": 2.584053794428434,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043348451909849855,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.22891746163368226,
|
|
"num_tokens": 61681725.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 5.240240669250488,
|
|
"epoch": 2.584534101825168,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043346018185130006,
|
|
"loss": 4.9182,
|
|
"mean_token_accuracy": 0.2320317804813385,
|
|
"num_tokens": 61692503.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 5.148536109924317,
|
|
"epoch": 2.585014409221902,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043343584092512665,
|
|
"loss": 4.8018,
|
|
"mean_token_accuracy": 0.23633200526237488,
|
|
"num_tokens": 61704567.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 5.1899388313293455,
|
|
"epoch": 2.585494716618636,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004334114963205435,
|
|
"loss": 4.8227,
|
|
"mean_token_accuracy": 0.23456315845251083,
|
|
"num_tokens": 61716155.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 5.211306381225586,
|
|
"epoch": 2.5859750240153696,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004333871480381158,
|
|
"loss": 4.9233,
|
|
"mean_token_accuracy": 0.2255728855729103,
|
|
"num_tokens": 61727489.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 5.209018182754517,
|
|
"epoch": 2.586455331412104,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004333627960784088,
|
|
"loss": 4.8725,
|
|
"mean_token_accuracy": 0.23084848374128342,
|
|
"num_tokens": 61739792.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 5.208897304534912,
|
|
"epoch": 2.586935638808838,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004333384404419879,
|
|
"loss": 4.8724,
|
|
"mean_token_accuracy": 0.22543371766805648,
|
|
"num_tokens": 61750891.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 5.183165836334228,
|
|
"epoch": 2.5874159462055717,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004333140811294186,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.23736967593431474,
|
|
"num_tokens": 61761691.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 5.196360969543457,
|
|
"epoch": 2.5878962536023056,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004332897181412664,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.22977162450551986,
|
|
"num_tokens": 61772371.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 5.1619565963745115,
|
|
"epoch": 2.5883765609990395,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00043326535147809696,
|
|
"loss": 4.8222,
|
|
"mean_token_accuracy": 0.23367271721363067,
|
|
"num_tokens": 61784908.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 5.229061079025269,
|
|
"epoch": 2.5888568683957733,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043324098114047604,
|
|
"loss": 4.9183,
|
|
"mean_token_accuracy": 0.2251209869980812,
|
|
"num_tokens": 61795948.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 5.266927671432495,
|
|
"epoch": 2.589337175792507,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004332166071289695,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.22218109518289567,
|
|
"num_tokens": 61807528.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 5.181930923461914,
|
|
"epoch": 2.589817483189241,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043319222944414304,
|
|
"loss": 4.8349,
|
|
"mean_token_accuracy": 0.23566761314868928,
|
|
"num_tokens": 61819971.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 5.120153331756592,
|
|
"epoch": 2.590297790585975,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043316784808656276,
|
|
"loss": 4.801,
|
|
"mean_token_accuracy": 0.2360517680644989,
|
|
"num_tokens": 61832284.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 5.238914871215821,
|
|
"epoch": 2.590778097982709,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043314346305679477,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.22581387013196946,
|
|
"num_tokens": 61844350.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 5.240818071365356,
|
|
"epoch": 2.5912584053794427,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043311907435540517,
|
|
"loss": 4.8456,
|
|
"mean_token_accuracy": 0.24016914069652556,
|
|
"num_tokens": 61855180.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 5.16663384437561,
|
|
"epoch": 2.5917387127761766,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004330946819829601,
|
|
"loss": 4.9011,
|
|
"mean_token_accuracy": 0.21983635127544404,
|
|
"num_tokens": 61866963.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 5.242919158935547,
|
|
"epoch": 2.5922190201729105,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043307028594002597,
|
|
"loss": 4.9296,
|
|
"mean_token_accuracy": 0.226530821621418,
|
|
"num_tokens": 61877503.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 5.190473127365112,
|
|
"epoch": 2.592699327569645,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00043304588622716924,
|
|
"loss": 4.7997,
|
|
"mean_token_accuracy": 0.2441087156534195,
|
|
"num_tokens": 61888426.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 5.204941320419311,
|
|
"epoch": 2.5931796349663783,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004330214828449563,
|
|
"loss": 4.8241,
|
|
"mean_token_accuracy": 0.2280264288187027,
|
|
"num_tokens": 61899952.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 5.127698564529419,
|
|
"epoch": 2.5936599423631126,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043299707579395365,
|
|
"loss": 4.8342,
|
|
"mean_token_accuracy": 0.23342197984457017,
|
|
"num_tokens": 61911956.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 2.5936599423631126,
|
|
"eval_entropy": 4.971726975401456,
|
|
"eval_loss": 4.953742504119873,
|
|
"eval_mean_token_accuracy": 0.23280154529873595,
|
|
"eval_num_tokens": 61911956.0,
|
|
"eval_runtime": 26.5648,
|
|
"eval_samples_per_second": 1235.281,
|
|
"eval_steps_per_second": 154.415,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"entropy": 5.152721977233886,
|
|
"epoch": 2.594140249759846,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004329726650747282,
|
|
"loss": 4.8415,
|
|
"mean_token_accuracy": 0.2280100926756859,
|
|
"num_tokens": 61922916.0,
|
|
"step": 27005
|
|
},
|
|
{
|
|
"entropy": 5.261081886291504,
|
|
"epoch": 2.5946205571565804,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004329482506878465,
|
|
"loss": 4.9021,
|
|
"mean_token_accuracy": 0.22608393132686616,
|
|
"num_tokens": 61933683.0,
|
|
"step": 27010
|
|
},
|
|
{
|
|
"entropy": 5.162463760375976,
|
|
"epoch": 2.5951008645533142,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043292383263387536,
|
|
"loss": 4.9035,
|
|
"mean_token_accuracy": 0.2323944926261902,
|
|
"num_tokens": 61945063.0,
|
|
"step": 27015
|
|
},
|
|
{
|
|
"entropy": 5.188848876953125,
|
|
"epoch": 2.595581171950048,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043289941091338187,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.2271340772509575,
|
|
"num_tokens": 61955919.0,
|
|
"step": 27020
|
|
},
|
|
{
|
|
"entropy": 5.355915594100952,
|
|
"epoch": 2.596061479346782,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004328749855269329,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.21829874962568283,
|
|
"num_tokens": 61967083.0,
|
|
"step": 27025
|
|
},
|
|
{
|
|
"entropy": 5.196405982971191,
|
|
"epoch": 2.596541786743516,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004328505564750955,
|
|
"loss": 4.7905,
|
|
"mean_token_accuracy": 0.23799231201410292,
|
|
"num_tokens": 61978659.0,
|
|
"step": 27030
|
|
},
|
|
{
|
|
"entropy": 5.163998460769653,
|
|
"epoch": 2.5970220941402498,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000432826123758437,
|
|
"loss": 4.8017,
|
|
"mean_token_accuracy": 0.23585939556360244,
|
|
"num_tokens": 61990966.0,
|
|
"step": 27035
|
|
},
|
|
{
|
|
"entropy": 5.159018182754517,
|
|
"epoch": 2.5975024015369836,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004328016873775244,
|
|
"loss": 4.8016,
|
|
"mean_token_accuracy": 0.23381449282169342,
|
|
"num_tokens": 62002417.0,
|
|
"step": 27040
|
|
},
|
|
{
|
|
"entropy": 5.223142290115357,
|
|
"epoch": 2.5979827089337175,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043277724733292527,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.22680740803480148,
|
|
"num_tokens": 62014698.0,
|
|
"step": 27045
|
|
},
|
|
{
|
|
"entropy": 5.128479480743408,
|
|
"epoch": 2.5984630163304514,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004327528036252071,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.2404017984867096,
|
|
"num_tokens": 62025298.0,
|
|
"step": 27050
|
|
},
|
|
{
|
|
"entropy": 5.107566595077515,
|
|
"epoch": 2.5989433237271853,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004327283562549371,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.23713478147983552,
|
|
"num_tokens": 62036419.0,
|
|
"step": 27055
|
|
},
|
|
{
|
|
"entropy": 5.245788812637329,
|
|
"epoch": 2.599423631123919,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000432703905222683,
|
|
"loss": 4.9072,
|
|
"mean_token_accuracy": 0.22745972871780396,
|
|
"num_tokens": 62046800.0,
|
|
"step": 27060
|
|
},
|
|
{
|
|
"entropy": 5.203386974334717,
|
|
"epoch": 2.5999039385206535,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043267945052901264,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.22951792627573014,
|
|
"num_tokens": 62058519.0,
|
|
"step": 27065
|
|
},
|
|
{
|
|
"entropy": 5.207656764984131,
|
|
"epoch": 2.600384245917387,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004326549921744935,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.23097579181194305,
|
|
"num_tokens": 62070445.0,
|
|
"step": 27070
|
|
},
|
|
{
|
|
"entropy": 5.260202884674072,
|
|
"epoch": 2.6008645533141213,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004326305301596937,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.2261493057012558,
|
|
"num_tokens": 62083084.0,
|
|
"step": 27075
|
|
},
|
|
{
|
|
"entropy": 5.206742525100708,
|
|
"epoch": 2.6013448607108547,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043260606448518096,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.2287858560681343,
|
|
"num_tokens": 62094334.0,
|
|
"step": 27080
|
|
},
|
|
{
|
|
"entropy": 5.152456378936767,
|
|
"epoch": 2.601825168107589,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043258159515152347,
|
|
"loss": 4.8407,
|
|
"mean_token_accuracy": 0.23031281530857087,
|
|
"num_tokens": 62105065.0,
|
|
"step": 27085
|
|
},
|
|
{
|
|
"entropy": 5.2465033531188965,
|
|
"epoch": 2.602305475504323,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004325571221592892,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.22328371852636336,
|
|
"num_tokens": 62116990.0,
|
|
"step": 27090
|
|
},
|
|
{
|
|
"entropy": 5.16760630607605,
|
|
"epoch": 2.6027857829010568,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043253264550904646,
|
|
"loss": 4.7751,
|
|
"mean_token_accuracy": 0.2339330717921257,
|
|
"num_tokens": 62128096.0,
|
|
"step": 27095
|
|
},
|
|
{
|
|
"entropy": 5.306564712524414,
|
|
"epoch": 2.6032660902977907,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004325081652013635,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.21923603862524033,
|
|
"num_tokens": 62141139.0,
|
|
"step": 27100
|
|
},
|
|
{
|
|
"entropy": 5.130558872222901,
|
|
"epoch": 2.6037463976945245,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043248368123680855,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.2355847492814064,
|
|
"num_tokens": 62152522.0,
|
|
"step": 27105
|
|
},
|
|
{
|
|
"entropy": 5.094349670410156,
|
|
"epoch": 2.6042267050912584,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043245919361595026,
|
|
"loss": 4.8009,
|
|
"mean_token_accuracy": 0.23692144453525543,
|
|
"num_tokens": 62162919.0,
|
|
"step": 27110
|
|
},
|
|
{
|
|
"entropy": 5.1954817295074465,
|
|
"epoch": 2.6047070124879923,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043243470233935696,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.23212538063526153,
|
|
"num_tokens": 62174936.0,
|
|
"step": 27115
|
|
},
|
|
{
|
|
"entropy": 5.253101539611817,
|
|
"epoch": 2.605187319884726,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004324102074075973,
|
|
"loss": 4.8864,
|
|
"mean_token_accuracy": 0.22848013937473297,
|
|
"num_tokens": 62186260.0,
|
|
"step": 27120
|
|
},
|
|
{
|
|
"entropy": 5.20013017654419,
|
|
"epoch": 2.60566762728146,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004323857088212402,
|
|
"loss": 4.7941,
|
|
"mean_token_accuracy": 0.2366043359041214,
|
|
"num_tokens": 62198616.0,
|
|
"step": 27125
|
|
},
|
|
{
|
|
"entropy": 5.1456972599029545,
|
|
"epoch": 2.606147934678194,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004323612065808541,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.23585746437311172,
|
|
"num_tokens": 62209318.0,
|
|
"step": 27130
|
|
},
|
|
{
|
|
"entropy": 5.245513486862182,
|
|
"epoch": 2.606628242074928,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043233670068700827,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.22211128771305083,
|
|
"num_tokens": 62220510.0,
|
|
"step": 27135
|
|
},
|
|
{
|
|
"entropy": 5.2810427188873295,
|
|
"epoch": 2.6071085494716617,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004323121911402713,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.21819155514240265,
|
|
"num_tokens": 62233676.0,
|
|
"step": 27140
|
|
},
|
|
{
|
|
"entropy": 5.250755786895752,
|
|
"epoch": 2.6075888568683956,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043228767794121245,
|
|
"loss": 4.8602,
|
|
"mean_token_accuracy": 0.22793488800525666,
|
|
"num_tokens": 62244604.0,
|
|
"step": 27145
|
|
},
|
|
{
|
|
"entropy": 5.167405986785889,
|
|
"epoch": 2.60806916426513,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004322631610904006,
|
|
"loss": 4.881,
|
|
"mean_token_accuracy": 0.22692146003246308,
|
|
"num_tokens": 62255431.0,
|
|
"step": 27150
|
|
},
|
|
{
|
|
"entropy": 5.322629737854004,
|
|
"epoch": 2.6085494716618634,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043223864058840534,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.2157856911420822,
|
|
"num_tokens": 62267050.0,
|
|
"step": 27155
|
|
},
|
|
{
|
|
"entropy": 5.239490509033203,
|
|
"epoch": 2.6090297790585977,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00043221411643579557,
|
|
"loss": 4.9126,
|
|
"mean_token_accuracy": 0.22611448168754578,
|
|
"num_tokens": 62278939.0,
|
|
"step": 27160
|
|
},
|
|
{
|
|
"entropy": 5.158590030670166,
|
|
"epoch": 2.6095100864553316,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043218958863314096,
|
|
"loss": 4.8517,
|
|
"mean_token_accuracy": 0.2241947755217552,
|
|
"num_tokens": 62291275.0,
|
|
"step": 27165
|
|
},
|
|
{
|
|
"entropy": 5.138450813293457,
|
|
"epoch": 2.6099903938520654,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004321650571810109,
|
|
"loss": 4.786,
|
|
"mean_token_accuracy": 0.2351975232362747,
|
|
"num_tokens": 62302191.0,
|
|
"step": 27170
|
|
},
|
|
{
|
|
"entropy": 5.205291032791138,
|
|
"epoch": 2.6104707012487993,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004321405220799747,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.23339645564556122,
|
|
"num_tokens": 62313678.0,
|
|
"step": 27175
|
|
},
|
|
{
|
|
"entropy": 5.148307800292969,
|
|
"epoch": 2.610951008645533,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004321159833306024,
|
|
"loss": 4.8109,
|
|
"mean_token_accuracy": 0.23103210628032683,
|
|
"num_tokens": 62324324.0,
|
|
"step": 27180
|
|
},
|
|
{
|
|
"entropy": 5.205150699615478,
|
|
"epoch": 2.611431316042267,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004320914409334634,
|
|
"loss": 4.972,
|
|
"mean_token_accuracy": 0.2266403317451477,
|
|
"num_tokens": 62335385.0,
|
|
"step": 27185
|
|
},
|
|
{
|
|
"entropy": 5.20397367477417,
|
|
"epoch": 2.611911623439001,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004320668948891276,
|
|
"loss": 4.9096,
|
|
"mean_token_accuracy": 0.22184415012598038,
|
|
"num_tokens": 62346733.0,
|
|
"step": 27190
|
|
},
|
|
{
|
|
"entropy": 5.283486986160279,
|
|
"epoch": 2.612391930835735,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043204234519816486,
|
|
"loss": 4.8987,
|
|
"mean_token_accuracy": 0.22763701826333999,
|
|
"num_tokens": 62358674.0,
|
|
"step": 27195
|
|
},
|
|
{
|
|
"entropy": 5.196029281616211,
|
|
"epoch": 2.6128722382324687,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004320177918611453,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.23064724504947662,
|
|
"num_tokens": 62370431.0,
|
|
"step": 27200
|
|
},
|
|
{
|
|
"entropy": 5.1340490818023685,
|
|
"epoch": 2.6133525456292026,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043199323487863876,
|
|
"loss": 4.7905,
|
|
"mean_token_accuracy": 0.23448858857154847,
|
|
"num_tokens": 62381098.0,
|
|
"step": 27205
|
|
},
|
|
{
|
|
"entropy": 5.208865833282471,
|
|
"epoch": 2.6138328530259365,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043196867425121554,
|
|
"loss": 4.827,
|
|
"mean_token_accuracy": 0.22983212620019913,
|
|
"num_tokens": 62393446.0,
|
|
"step": 27210
|
|
},
|
|
{
|
|
"entropy": 5.215778350830078,
|
|
"epoch": 2.6143131604226704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043194410997944577,
|
|
"loss": 4.9069,
|
|
"mean_token_accuracy": 0.2254984647035599,
|
|
"num_tokens": 62406581.0,
|
|
"step": 27215
|
|
},
|
|
{
|
|
"entropy": 5.2368989944458,
|
|
"epoch": 2.6147934678194042,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00043191954206389985,
|
|
"loss": 4.9297,
|
|
"mean_token_accuracy": 0.22366953343153,
|
|
"num_tokens": 62419516.0,
|
|
"step": 27220
|
|
},
|
|
{
|
|
"entropy": 5.179166460037232,
|
|
"epoch": 2.6152737752161386,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004318949705051481,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.22740765213966369,
|
|
"num_tokens": 62431577.0,
|
|
"step": 27225
|
|
},
|
|
{
|
|
"entropy": 5.129627799987793,
|
|
"epoch": 2.615754082612872,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004318703953037609,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.23104438930749893,
|
|
"num_tokens": 62444507.0,
|
|
"step": 27230
|
|
},
|
|
{
|
|
"entropy": 5.162756156921387,
|
|
"epoch": 2.6162343900096063,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004318458164603091,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.22707800716161727,
|
|
"num_tokens": 62455692.0,
|
|
"step": 27235
|
|
},
|
|
{
|
|
"entropy": 5.2872577667236325,
|
|
"epoch": 2.61671469740634,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004318212339753631,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.22351700961589813,
|
|
"num_tokens": 62467215.0,
|
|
"step": 27240
|
|
},
|
|
{
|
|
"entropy": 5.2005753993988035,
|
|
"epoch": 2.617195004803074,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00043179664784949375,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.222824589908123,
|
|
"num_tokens": 62480016.0,
|
|
"step": 27245
|
|
},
|
|
{
|
|
"entropy": 5.2212320327758786,
|
|
"epoch": 2.617675312199808,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004317720580832717,
|
|
"loss": 4.9258,
|
|
"mean_token_accuracy": 0.23424352705478668,
|
|
"num_tokens": 62491088.0,
|
|
"step": 27250
|
|
},
|
|
{
|
|
"entropy": 5.2412927627563475,
|
|
"epoch": 2.618155619596542,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004317474646772681,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.2282996729016304,
|
|
"num_tokens": 62502405.0,
|
|
"step": 27255
|
|
},
|
|
{
|
|
"entropy": 5.228611612319947,
|
|
"epoch": 2.6186359269932757,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004317228676320539,
|
|
"loss": 4.8577,
|
|
"mean_token_accuracy": 0.22894774824380876,
|
|
"num_tokens": 62512968.0,
|
|
"step": 27260
|
|
},
|
|
{
|
|
"entropy": 5.153527069091797,
|
|
"epoch": 2.6191162343900096,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00043169826694819987,
|
|
"loss": 4.7305,
|
|
"mean_token_accuracy": 0.23782391250133514,
|
|
"num_tokens": 62524242.0,
|
|
"step": 27265
|
|
},
|
|
{
|
|
"entropy": 5.252042531967163,
|
|
"epoch": 2.6195965417867435,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004316736626262775,
|
|
"loss": 4.9128,
|
|
"mean_token_accuracy": 0.22663568407297136,
|
|
"num_tokens": 62536556.0,
|
|
"step": 27270
|
|
},
|
|
{
|
|
"entropy": 5.2535071849823,
|
|
"epoch": 2.6200768491834774,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004316490546668579,
|
|
"loss": 4.8835,
|
|
"mean_token_accuracy": 0.2301328510046005,
|
|
"num_tokens": 62547897.0,
|
|
"step": 27275
|
|
},
|
|
{
|
|
"entropy": 5.216599082946777,
|
|
"epoch": 2.6205571565802113,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004316244430705124,
|
|
"loss": 4.8918,
|
|
"mean_token_accuracy": 0.22067732065916063,
|
|
"num_tokens": 62560190.0,
|
|
"step": 27280
|
|
},
|
|
{
|
|
"entropy": 5.202698230743408,
|
|
"epoch": 2.621037463976945,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004315998278378123,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.21775836646556854,
|
|
"num_tokens": 62571885.0,
|
|
"step": 27285
|
|
},
|
|
{
|
|
"entropy": 5.215139579772949,
|
|
"epoch": 2.621517771373679,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043157520896932943,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.2284093201160431,
|
|
"num_tokens": 62583698.0,
|
|
"step": 27290
|
|
},
|
|
{
|
|
"entropy": 5.2959339141845705,
|
|
"epoch": 2.621998078770413,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000431550586465635,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.22847890108823776,
|
|
"num_tokens": 62594813.0,
|
|
"step": 27295
|
|
},
|
|
{
|
|
"entropy": 5.1417797088623045,
|
|
"epoch": 2.6224783861671472,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043152596032730085,
|
|
"loss": 4.702,
|
|
"mean_token_accuracy": 0.24149904549121856,
|
|
"num_tokens": 62604868.0,
|
|
"step": 27300
|
|
},
|
|
{
|
|
"entropy": 5.119030857086182,
|
|
"epoch": 2.6229586935638807,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043150133055489865,
|
|
"loss": 4.7827,
|
|
"mean_token_accuracy": 0.23350350856781005,
|
|
"num_tokens": 62616553.0,
|
|
"step": 27305
|
|
},
|
|
{
|
|
"entropy": 5.204604911804199,
|
|
"epoch": 2.623439000960615,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004314766971490003,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.2337656021118164,
|
|
"num_tokens": 62627468.0,
|
|
"step": 27310
|
|
},
|
|
{
|
|
"entropy": 5.182678985595703,
|
|
"epoch": 2.6239193083573484,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004314520601101776,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.2262950286269188,
|
|
"num_tokens": 62639255.0,
|
|
"step": 27315
|
|
},
|
|
{
|
|
"entropy": 5.158666372299194,
|
|
"epoch": 2.6243996157540828,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043142741943900275,
|
|
"loss": 4.8232,
|
|
"mean_token_accuracy": 0.2252733126282692,
|
|
"num_tokens": 62650553.0,
|
|
"step": 27320
|
|
},
|
|
{
|
|
"entropy": 5.227890396118164,
|
|
"epoch": 2.6248799231508166,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043140277513604763,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.22100803554058074,
|
|
"num_tokens": 62662653.0,
|
|
"step": 27325
|
|
},
|
|
{
|
|
"entropy": 5.175113391876221,
|
|
"epoch": 2.6253602305475505,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004313781272018845,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.23325150460004807,
|
|
"num_tokens": 62673618.0,
|
|
"step": 27330
|
|
},
|
|
{
|
|
"entropy": 5.207998037338257,
|
|
"epoch": 2.6258405379442844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004313534756370857,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.231086827814579,
|
|
"num_tokens": 62685221.0,
|
|
"step": 27335
|
|
},
|
|
{
|
|
"entropy": 5.1659204959869385,
|
|
"epoch": 2.6263208453410183,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043132882044222336,
|
|
"loss": 4.7219,
|
|
"mean_token_accuracy": 0.2428169772028923,
|
|
"num_tokens": 62695544.0,
|
|
"step": 27340
|
|
},
|
|
{
|
|
"entropy": 5.0635816097259525,
|
|
"epoch": 2.626801152737752,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00043130416161787005,
|
|
"loss": 4.6686,
|
|
"mean_token_accuracy": 0.24327061772346498,
|
|
"num_tokens": 62706945.0,
|
|
"step": 27345
|
|
},
|
|
{
|
|
"entropy": 5.187275123596192,
|
|
"epoch": 2.627281460134486,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043127949916459823,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.22867840826511382,
|
|
"num_tokens": 62717821.0,
|
|
"step": 27350
|
|
},
|
|
{
|
|
"entropy": 5.1544352054595945,
|
|
"epoch": 2.62776176753122,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00043125483308298053,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.23613744229078293,
|
|
"num_tokens": 62730477.0,
|
|
"step": 27355
|
|
},
|
|
{
|
|
"entropy": 5.188195371627808,
|
|
"epoch": 2.628242074927954,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004312301633735895,
|
|
"loss": 4.8278,
|
|
"mean_token_accuracy": 0.23259933590888976,
|
|
"num_tokens": 62741725.0,
|
|
"step": 27360
|
|
},
|
|
{
|
|
"entropy": 5.191578340530396,
|
|
"epoch": 2.6287223823246877,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004312054900369981,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.22230452597141265,
|
|
"num_tokens": 62753600.0,
|
|
"step": 27365
|
|
},
|
|
{
|
|
"entropy": 5.195092678070068,
|
|
"epoch": 2.6292026897214216,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000431180813073779,
|
|
"loss": 4.9391,
|
|
"mean_token_accuracy": 0.2256601184606552,
|
|
"num_tokens": 62766218.0,
|
|
"step": 27370
|
|
},
|
|
{
|
|
"entropy": 5.171886253356933,
|
|
"epoch": 2.629682997118156,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004311561324845051,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.2331762358546257,
|
|
"num_tokens": 62777723.0,
|
|
"step": 27375
|
|
},
|
|
{
|
|
"entropy": 5.271885108947754,
|
|
"epoch": 2.6301633045148893,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004311314482697496,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.22328080981969833,
|
|
"num_tokens": 62789711.0,
|
|
"step": 27380
|
|
},
|
|
{
|
|
"entropy": 5.148415803909302,
|
|
"epoch": 2.6306436119116237,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004311067604300855,
|
|
"loss": 4.8158,
|
|
"mean_token_accuracy": 0.23404400795698166,
|
|
"num_tokens": 62800600.0,
|
|
"step": 27385
|
|
},
|
|
{
|
|
"entropy": 5.231881427764892,
|
|
"epoch": 2.631123919308357,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004310820689660859,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.23089914470911027,
|
|
"num_tokens": 62811872.0,
|
|
"step": 27390
|
|
},
|
|
{
|
|
"entropy": 5.2011195659637455,
|
|
"epoch": 2.6316042267050914,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004310573738783242,
|
|
"loss": 4.8606,
|
|
"mean_token_accuracy": 0.23284119367599487,
|
|
"num_tokens": 62822886.0,
|
|
"step": 27395
|
|
},
|
|
{
|
|
"entropy": 5.153226137161255,
|
|
"epoch": 2.6320845341018253,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004310326751673736,
|
|
"loss": 4.785,
|
|
"mean_token_accuracy": 0.23082454949617387,
|
|
"num_tokens": 62833911.0,
|
|
"step": 27400
|
|
},
|
|
{
|
|
"entropy": 5.153330659866333,
|
|
"epoch": 2.632564841498559,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043100797283380756,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.23956239372491836,
|
|
"num_tokens": 62844756.0,
|
|
"step": 27405
|
|
},
|
|
{
|
|
"entropy": 5.1705320358276365,
|
|
"epoch": 2.633045148895293,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043098326687819973,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.2332485184073448,
|
|
"num_tokens": 62856072.0,
|
|
"step": 27410
|
|
},
|
|
{
|
|
"entropy": 5.281047725677491,
|
|
"epoch": 2.633525456292027,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004309585573011236,
|
|
"loss": 4.917,
|
|
"mean_token_accuracy": 0.22401714473962783,
|
|
"num_tokens": 62868334.0,
|
|
"step": 27415
|
|
},
|
|
{
|
|
"entropy": 5.169274997711182,
|
|
"epoch": 2.634005763688761,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004309338441031528,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.23925271332263948,
|
|
"num_tokens": 62879459.0,
|
|
"step": 27420
|
|
},
|
|
{
|
|
"entropy": 5.052501583099366,
|
|
"epoch": 2.6344860710854947,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043090912728486135,
|
|
"loss": 4.7143,
|
|
"mean_token_accuracy": 0.24202261567115785,
|
|
"num_tokens": 62890137.0,
|
|
"step": 27425
|
|
},
|
|
{
|
|
"entropy": 5.2056995868682865,
|
|
"epoch": 2.6349663784822286,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004308844068468228,
|
|
"loss": 4.8699,
|
|
"mean_token_accuracy": 0.22178313732147217,
|
|
"num_tokens": 62902688.0,
|
|
"step": 27430
|
|
},
|
|
{
|
|
"entropy": 5.1345458984375,
|
|
"epoch": 2.6354466858789625,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043085968278961116,
|
|
"loss": 4.8417,
|
|
"mean_token_accuracy": 0.23213982880115508,
|
|
"num_tokens": 62913008.0,
|
|
"step": 27435
|
|
},
|
|
{
|
|
"entropy": 5.199015808105469,
|
|
"epoch": 2.6359269932756964,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043083495511380055,
|
|
"loss": 4.872,
|
|
"mean_token_accuracy": 0.22539333999156952,
|
|
"num_tokens": 62924894.0,
|
|
"step": 27440
|
|
},
|
|
{
|
|
"entropy": 5.153941679000854,
|
|
"epoch": 2.6364073006724302,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043081022381996506,
|
|
"loss": 4.6824,
|
|
"mean_token_accuracy": 0.25251459777355195,
|
|
"num_tokens": 62935709.0,
|
|
"step": 27445
|
|
},
|
|
{
|
|
"entropy": 5.234029722213745,
|
|
"epoch": 2.636887608069164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004307854889086787,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.23030474185943603,
|
|
"num_tokens": 62947122.0,
|
|
"step": 27450
|
|
},
|
|
{
|
|
"entropy": 5.183029079437256,
|
|
"epoch": 2.637367915465898,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043076075038051605,
|
|
"loss": 4.7912,
|
|
"mean_token_accuracy": 0.23229042291641236,
|
|
"num_tokens": 62957993.0,
|
|
"step": 27455
|
|
},
|
|
{
|
|
"entropy": 5.268702459335327,
|
|
"epoch": 2.6378482228626323,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004307360082360512,
|
|
"loss": 4.9127,
|
|
"mean_token_accuracy": 0.227476042509079,
|
|
"num_tokens": 62969645.0,
|
|
"step": 27460
|
|
},
|
|
{
|
|
"entropy": 5.191092491149902,
|
|
"epoch": 2.6383285302593658,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043071126247585866,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.23462135940790177,
|
|
"num_tokens": 62980770.0,
|
|
"step": 27465
|
|
},
|
|
{
|
|
"entropy": 5.126678085327148,
|
|
"epoch": 2.6388088376561,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000430686513100513,
|
|
"loss": 4.7251,
|
|
"mean_token_accuracy": 0.2452177509665489,
|
|
"num_tokens": 62991418.0,
|
|
"step": 27470
|
|
},
|
|
{
|
|
"entropy": 5.101024532318116,
|
|
"epoch": 2.639289145052834,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043066176011058877,
|
|
"loss": 4.7539,
|
|
"mean_token_accuracy": 0.2378368556499481,
|
|
"num_tokens": 63002228.0,
|
|
"step": 27475
|
|
},
|
|
{
|
|
"entropy": 5.144393682479858,
|
|
"epoch": 2.639769452449568,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043063700350666066,
|
|
"loss": 4.8369,
|
|
"mean_token_accuracy": 0.22726211547851563,
|
|
"num_tokens": 63013502.0,
|
|
"step": 27480
|
|
},
|
|
{
|
|
"entropy": 5.2337103366851805,
|
|
"epoch": 2.6402497598463017,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004306122432893036,
|
|
"loss": 4.9342,
|
|
"mean_token_accuracy": 0.22789040356874465,
|
|
"num_tokens": 63024530.0,
|
|
"step": 27485
|
|
},
|
|
{
|
|
"entropy": 5.160613298416138,
|
|
"epoch": 2.6407300672430356,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043058747945909224,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.23891457319259643,
|
|
"num_tokens": 63035668.0,
|
|
"step": 27490
|
|
},
|
|
{
|
|
"entropy": 5.204391860961914,
|
|
"epoch": 2.6412103746397695,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043056271201660166,
|
|
"loss": 4.8174,
|
|
"mean_token_accuracy": 0.2343011200428009,
|
|
"num_tokens": 63048020.0,
|
|
"step": 27495
|
|
},
|
|
{
|
|
"entropy": 5.209877443313599,
|
|
"epoch": 2.6416906820365034,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004305379409624068,
|
|
"loss": 4.8267,
|
|
"mean_token_accuracy": 0.23098521381616594,
|
|
"num_tokens": 63060019.0,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"entropy": 5.09333438873291,
|
|
"epoch": 2.6421709894332372,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004305131662970827,
|
|
"loss": 4.7748,
|
|
"mean_token_accuracy": 0.23339166194200517,
|
|
"num_tokens": 63070151.0,
|
|
"step": 27505
|
|
},
|
|
{
|
|
"entropy": 5.159240961074829,
|
|
"epoch": 2.642651296829971,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004304883880212048,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.23358498960733415,
|
|
"num_tokens": 63082174.0,
|
|
"step": 27510
|
|
},
|
|
{
|
|
"entropy": 5.132683324813843,
|
|
"epoch": 2.643131604226705,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004304636061353482,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.23761930763721467,
|
|
"num_tokens": 63093478.0,
|
|
"step": 27515
|
|
},
|
|
{
|
|
"entropy": 5.099394130706787,
|
|
"epoch": 2.643611911623439,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004304388206400883,
|
|
"loss": 4.7196,
|
|
"mean_token_accuracy": 0.24211880415678025,
|
|
"num_tokens": 63104153.0,
|
|
"step": 27520
|
|
},
|
|
{
|
|
"entropy": 5.101822757720948,
|
|
"epoch": 2.6440922190201728,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004304140315360005,
|
|
"loss": 4.7176,
|
|
"mean_token_accuracy": 0.24736980795860292,
|
|
"num_tokens": 63115469.0,
|
|
"step": 27525
|
|
},
|
|
{
|
|
"entropy": 5.11777925491333,
|
|
"epoch": 2.6445725264169067,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004303892388236604,
|
|
"loss": 4.8807,
|
|
"mean_token_accuracy": 0.22332934588193892,
|
|
"num_tokens": 63126917.0,
|
|
"step": 27530
|
|
},
|
|
{
|
|
"entropy": 5.163936948776245,
|
|
"epoch": 2.645052833813641,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004303644425036436,
|
|
"loss": 4.8494,
|
|
"mean_token_accuracy": 0.23337552100419998,
|
|
"num_tokens": 63138865.0,
|
|
"step": 27535
|
|
},
|
|
{
|
|
"entropy": 5.1171165943145756,
|
|
"epoch": 2.6455331412103744,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043033964257652575,
|
|
"loss": 4.6529,
|
|
"mean_token_accuracy": 0.24751077741384506,
|
|
"num_tokens": 63148937.0,
|
|
"step": 27540
|
|
},
|
|
{
|
|
"entropy": 5.092058897018433,
|
|
"epoch": 2.6460134486071087,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004303148390428827,
|
|
"loss": 4.7618,
|
|
"mean_token_accuracy": 0.2331083044409752,
|
|
"num_tokens": 63160850.0,
|
|
"step": 27545
|
|
},
|
|
{
|
|
"entropy": 5.1973330020904545,
|
|
"epoch": 2.6464937560038426,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043029003190329023,
|
|
"loss": 4.8713,
|
|
"mean_token_accuracy": 0.23061523884534835,
|
|
"num_tokens": 63171660.0,
|
|
"step": 27550
|
|
},
|
|
{
|
|
"entropy": 5.207761144638061,
|
|
"epoch": 2.6469740634005765,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004302652211583244,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.22784758508205413,
|
|
"num_tokens": 63182291.0,
|
|
"step": 27555
|
|
},
|
|
{
|
|
"entropy": 5.1609760284423825,
|
|
"epoch": 2.6474543707973104,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004302404068085612,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.23762747943401336,
|
|
"num_tokens": 63193646.0,
|
|
"step": 27560
|
|
},
|
|
{
|
|
"entropy": 5.128122997283936,
|
|
"epoch": 2.6479346781940443,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004302155888545766,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.22400487959384918,
|
|
"num_tokens": 63205021.0,
|
|
"step": 27565
|
|
},
|
|
{
|
|
"entropy": 5.180052423477173,
|
|
"epoch": 2.648414985590778,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000430190767296947,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.2286435842514038,
|
|
"num_tokens": 63217315.0,
|
|
"step": 27570
|
|
},
|
|
{
|
|
"entropy": 5.2360217571258545,
|
|
"epoch": 2.648895292987512,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004301659421362486,
|
|
"loss": 4.8494,
|
|
"mean_token_accuracy": 0.23242759257555007,
|
|
"num_tokens": 63229082.0,
|
|
"step": 27575
|
|
},
|
|
{
|
|
"entropy": 5.272447490692139,
|
|
"epoch": 2.649375600384246,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004301411133730578,
|
|
"loss": 4.9427,
|
|
"mean_token_accuracy": 0.22899051010608673,
|
|
"num_tokens": 63240498.0,
|
|
"step": 27580
|
|
},
|
|
{
|
|
"entropy": 5.238081693649292,
|
|
"epoch": 2.64985590778098,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043011628100795093,
|
|
"loss": 4.9128,
|
|
"mean_token_accuracy": 0.22598650455474853,
|
|
"num_tokens": 63251149.0,
|
|
"step": 27585
|
|
},
|
|
{
|
|
"entropy": 5.297263097763062,
|
|
"epoch": 2.6503362151777137,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004300914450415047,
|
|
"loss": 4.9119,
|
|
"mean_token_accuracy": 0.23284189105033876,
|
|
"num_tokens": 63261903.0,
|
|
"step": 27590
|
|
},
|
|
{
|
|
"entropy": 5.135991048812866,
|
|
"epoch": 2.6508165225744476,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043006660547429565,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.23185640573501587,
|
|
"num_tokens": 63274281.0,
|
|
"step": 27595
|
|
},
|
|
{
|
|
"entropy": 5.104227828979492,
|
|
"epoch": 2.6512968299711814,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004300417623069005,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.24787989854812623,
|
|
"num_tokens": 63285421.0,
|
|
"step": 27600
|
|
},
|
|
{
|
|
"entropy": 5.181985187530517,
|
|
"epoch": 2.6517771373679153,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004300169155398959,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.2386231765151024,
|
|
"num_tokens": 63296828.0,
|
|
"step": 27605
|
|
},
|
|
{
|
|
"entropy": 5.260995626449585,
|
|
"epoch": 2.6522574447646496,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042999206517385885,
|
|
"loss": 4.8887,
|
|
"mean_token_accuracy": 0.22497848123311998,
|
|
"num_tokens": 63307132.0,
|
|
"step": 27610
|
|
},
|
|
{
|
|
"entropy": 5.228298377990723,
|
|
"epoch": 2.652737752161383,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004299672112093663,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.22996958196163178,
|
|
"num_tokens": 63318911.0,
|
|
"step": 27615
|
|
},
|
|
{
|
|
"entropy": 5.236276245117187,
|
|
"epoch": 2.6532180595581174,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042994235364699526,
|
|
"loss": 4.9242,
|
|
"mean_token_accuracy": 0.22470122426748276,
|
|
"num_tokens": 63329973.0,
|
|
"step": 27620
|
|
},
|
|
{
|
|
"entropy": 5.187528371810913,
|
|
"epoch": 2.653698366954851,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004299174924873229,
|
|
"loss": 4.8573,
|
|
"mean_token_accuracy": 0.2300560712814331,
|
|
"num_tokens": 63341576.0,
|
|
"step": 27625
|
|
},
|
|
{
|
|
"entropy": 5.154596138000488,
|
|
"epoch": 2.654178674351585,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004298926277309263,
|
|
"loss": 4.8623,
|
|
"mean_token_accuracy": 0.2319568693637848,
|
|
"num_tokens": 63353988.0,
|
|
"step": 27630
|
|
},
|
|
{
|
|
"entropy": 5.245839977264405,
|
|
"epoch": 2.654658981748319,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042986775937838283,
|
|
"loss": 4.8617,
|
|
"mean_token_accuracy": 0.22823255360126496,
|
|
"num_tokens": 63364746.0,
|
|
"step": 27635
|
|
},
|
|
{
|
|
"entropy": 5.268437671661377,
|
|
"epoch": 2.655139289145053,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004298428874302699,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.2227187380194664,
|
|
"num_tokens": 63375608.0,
|
|
"step": 27640
|
|
},
|
|
{
|
|
"entropy": 5.116877126693725,
|
|
"epoch": 2.655619596541787,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004298180118871649,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.2365681618452072,
|
|
"num_tokens": 63386581.0,
|
|
"step": 27645
|
|
},
|
|
{
|
|
"entropy": 5.1612354755401615,
|
|
"epoch": 2.6560999039385207,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042979313274964535,
|
|
"loss": 4.8707,
|
|
"mean_token_accuracy": 0.22894826531410217,
|
|
"num_tokens": 63398844.0,
|
|
"step": 27650
|
|
},
|
|
{
|
|
"entropy": 5.231775236129761,
|
|
"epoch": 2.6565802113352546,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00042976825001828897,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.23284294009208678,
|
|
"num_tokens": 63409972.0,
|
|
"step": 27655
|
|
},
|
|
{
|
|
"entropy": 5.16971869468689,
|
|
"epoch": 2.6570605187319885,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042974336369367333,
|
|
"loss": 4.7636,
|
|
"mean_token_accuracy": 0.2409840926527977,
|
|
"num_tokens": 63420598.0,
|
|
"step": 27660
|
|
},
|
|
{
|
|
"entropy": 5.2458573341369625,
|
|
"epoch": 2.6575408261287223,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004297184737763763,
|
|
"loss": 4.9335,
|
|
"mean_token_accuracy": 0.2263625219464302,
|
|
"num_tokens": 63431943.0,
|
|
"step": 27665
|
|
},
|
|
{
|
|
"entropy": 5.151793098449707,
|
|
"epoch": 2.658021133525456,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042969358026697567,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.23809369504451752,
|
|
"num_tokens": 63442539.0,
|
|
"step": 27670
|
|
},
|
|
{
|
|
"entropy": 5.1287431716918945,
|
|
"epoch": 2.65850144092219,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004296686831660495,
|
|
"loss": 4.7642,
|
|
"mean_token_accuracy": 0.2348925143480301,
|
|
"num_tokens": 63453100.0,
|
|
"step": 27675
|
|
},
|
|
{
|
|
"entropy": 5.151091480255127,
|
|
"epoch": 2.658981748318924,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004296437824741758,
|
|
"loss": 4.8809,
|
|
"mean_token_accuracy": 0.22888348996639252,
|
|
"num_tokens": 63464226.0,
|
|
"step": 27680
|
|
},
|
|
{
|
|
"entropy": 5.207557821273804,
|
|
"epoch": 2.659462055715658,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042961887819193263,
|
|
"loss": 4.778,
|
|
"mean_token_accuracy": 0.24056252539157869,
|
|
"num_tokens": 63475159.0,
|
|
"step": 27685
|
|
},
|
|
{
|
|
"entropy": 5.271911573410034,
|
|
"epoch": 2.6599423631123917,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004295939703198983,
|
|
"loss": 5.0046,
|
|
"mean_token_accuracy": 0.21641286760568618,
|
|
"num_tokens": 63488015.0,
|
|
"step": 27690
|
|
},
|
|
{
|
|
"entropy": 5.174448728561401,
|
|
"epoch": 2.660422670509126,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000429569058858651,
|
|
"loss": 4.8273,
|
|
"mean_token_accuracy": 0.23401379585266113,
|
|
"num_tokens": 63501216.0,
|
|
"step": 27695
|
|
},
|
|
{
|
|
"entropy": 5.258895397186279,
|
|
"epoch": 2.6609029779058595,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042954414380876906,
|
|
"loss": 4.8997,
|
|
"mean_token_accuracy": 0.22875845730304717,
|
|
"num_tokens": 63511560.0,
|
|
"step": 27700
|
|
},
|
|
{
|
|
"entropy": 5.249605131149292,
|
|
"epoch": 2.661383285302594,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042951922517083104,
|
|
"loss": 4.9944,
|
|
"mean_token_accuracy": 0.22239305078983307,
|
|
"num_tokens": 63522762.0,
|
|
"step": 27705
|
|
},
|
|
{
|
|
"entropy": 5.217506551742554,
|
|
"epoch": 2.6618635926993277,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004294943029454155,
|
|
"loss": 4.902,
|
|
"mean_token_accuracy": 0.23289986550807953,
|
|
"num_tokens": 63535095.0,
|
|
"step": 27710
|
|
},
|
|
{
|
|
"entropy": 5.159198999404907,
|
|
"epoch": 2.6623439000960616,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042946937713310093,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.2396216094493866,
|
|
"num_tokens": 63545256.0,
|
|
"step": 27715
|
|
},
|
|
{
|
|
"entropy": 5.180679655075073,
|
|
"epoch": 2.6628242074927955,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004294444477344661,
|
|
"loss": 4.8499,
|
|
"mean_token_accuracy": 0.22510923594236373,
|
|
"num_tokens": 63557269.0,
|
|
"step": 27720
|
|
},
|
|
{
|
|
"entropy": 5.062251043319702,
|
|
"epoch": 2.6633045148895294,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004294195147500898,
|
|
"loss": 4.7206,
|
|
"mean_token_accuracy": 0.24250949919223785,
|
|
"num_tokens": 63568452.0,
|
|
"step": 27725
|
|
},
|
|
{
|
|
"entropy": 5.198007249832154,
|
|
"epoch": 2.6637848222862632,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00042939457818055095,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.22160856425762177,
|
|
"num_tokens": 63581653.0,
|
|
"step": 27730
|
|
},
|
|
{
|
|
"entropy": 5.1763834953308105,
|
|
"epoch": 2.664265129682997,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042936963802642843,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.23229695856571198,
|
|
"num_tokens": 63592862.0,
|
|
"step": 27735
|
|
},
|
|
{
|
|
"entropy": 5.219204664230347,
|
|
"epoch": 2.664745437079731,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004293446942883013,
|
|
"loss": 4.8899,
|
|
"mean_token_accuracy": 0.2244829311966896,
|
|
"num_tokens": 63603306.0,
|
|
"step": 27740
|
|
},
|
|
{
|
|
"entropy": 5.243879890441894,
|
|
"epoch": 2.665225744476465,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042931974696674866,
|
|
"loss": 4.8823,
|
|
"mean_token_accuracy": 0.2242935299873352,
|
|
"num_tokens": 63615031.0,
|
|
"step": 27745
|
|
},
|
|
{
|
|
"entropy": 5.241208124160766,
|
|
"epoch": 2.6657060518731988,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004292947960623497,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.22447613924741744,
|
|
"num_tokens": 63627004.0,
|
|
"step": 27750
|
|
},
|
|
{
|
|
"entropy": 5.207187747955322,
|
|
"epoch": 2.6661863592699326,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042926984157568384,
|
|
"loss": 4.8592,
|
|
"mean_token_accuracy": 0.23122096806764603,
|
|
"num_tokens": 63637712.0,
|
|
"step": 27755
|
|
},
|
|
{
|
|
"entropy": 5.185144233703613,
|
|
"epoch": 2.6666666666666665,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00042924488350733024,
|
|
"loss": 4.8855,
|
|
"mean_token_accuracy": 0.23308789879083633,
|
|
"num_tokens": 63649631.0,
|
|
"step": 27760
|
|
},
|
|
{
|
|
"entropy": 5.268042659759521,
|
|
"epoch": 2.6671469740634004,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042921992185786847,
|
|
"loss": 4.8285,
|
|
"mean_token_accuracy": 0.22803637385368347,
|
|
"num_tokens": 63661929.0,
|
|
"step": 27765
|
|
},
|
|
{
|
|
"entropy": 5.232502174377442,
|
|
"epoch": 2.6676272814601347,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042919495662787813,
|
|
"loss": 4.915,
|
|
"mean_token_accuracy": 0.22262402921915053,
|
|
"num_tokens": 63674411.0,
|
|
"step": 27770
|
|
},
|
|
{
|
|
"entropy": 5.180151128768921,
|
|
"epoch": 2.668107588856868,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004291699878179387,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.23348522335290908,
|
|
"num_tokens": 63685182.0,
|
|
"step": 27775
|
|
},
|
|
{
|
|
"entropy": 5.174935340881348,
|
|
"epoch": 2.6685878962536025,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004291450154286299,
|
|
"loss": 4.8672,
|
|
"mean_token_accuracy": 0.22604048103094102,
|
|
"num_tokens": 63696374.0,
|
|
"step": 27780
|
|
},
|
|
{
|
|
"entropy": 5.142121839523315,
|
|
"epoch": 2.6690682036503364,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004291200394605317,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.2302960216999054,
|
|
"num_tokens": 63708092.0,
|
|
"step": 27785
|
|
},
|
|
{
|
|
"entropy": 5.178969955444336,
|
|
"epoch": 2.6695485110470702,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004290950599142237,
|
|
"loss": 4.7764,
|
|
"mean_token_accuracy": 0.2343618780374527,
|
|
"num_tokens": 63721143.0,
|
|
"step": 27790
|
|
},
|
|
{
|
|
"entropy": 5.232968997955322,
|
|
"epoch": 2.670028818443804,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000429070076790286,
|
|
"loss": 4.8757,
|
|
"mean_token_accuracy": 0.2276745095849037,
|
|
"num_tokens": 63732346.0,
|
|
"step": 27795
|
|
},
|
|
{
|
|
"entropy": 5.119388771057129,
|
|
"epoch": 2.670509125840538,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042904509008929873,
|
|
"loss": 4.767,
|
|
"mean_token_accuracy": 0.242314675450325,
|
|
"num_tokens": 63744008.0,
|
|
"step": 27800
|
|
},
|
|
{
|
|
"entropy": 5.202625513076782,
|
|
"epoch": 2.670989433237272,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004290200998118417,
|
|
"loss": 4.8128,
|
|
"mean_token_accuracy": 0.24221161901950836,
|
|
"num_tokens": 63754792.0,
|
|
"step": 27805
|
|
},
|
|
{
|
|
"entropy": 5.150046920776367,
|
|
"epoch": 2.6714697406340058,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042899510595849544,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.2332458898425102,
|
|
"num_tokens": 63767194.0,
|
|
"step": 27810
|
|
},
|
|
{
|
|
"entropy": 5.1137552738189695,
|
|
"epoch": 2.6719500480307397,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042897010852984004,
|
|
"loss": 4.8039,
|
|
"mean_token_accuracy": 0.23455947786569595,
|
|
"num_tokens": 63778641.0,
|
|
"step": 27815
|
|
},
|
|
{
|
|
"entropy": 5.219489336013794,
|
|
"epoch": 2.6724303554274735,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042894510752645586,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.22774797230958937,
|
|
"num_tokens": 63791447.0,
|
|
"step": 27820
|
|
},
|
|
{
|
|
"entropy": 5.264297914505005,
|
|
"epoch": 2.6729106628242074,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004289201029489235,
|
|
"loss": 4.9209,
|
|
"mean_token_accuracy": 0.22484225928783416,
|
|
"num_tokens": 63802162.0,
|
|
"step": 27825
|
|
},
|
|
{
|
|
"entropy": 5.21282811164856,
|
|
"epoch": 2.6733909702209413,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004288950947978234,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.2367763951420784,
|
|
"num_tokens": 63812689.0,
|
|
"step": 27830
|
|
},
|
|
{
|
|
"entropy": 5.2203638553619385,
|
|
"epoch": 2.673871277617675,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004288700830737361,
|
|
"loss": 4.8909,
|
|
"mean_token_accuracy": 0.22986862063407898,
|
|
"num_tokens": 63822915.0,
|
|
"step": 27835
|
|
},
|
|
{
|
|
"entropy": 5.1155437469482425,
|
|
"epoch": 2.674351585014409,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042884506777724244,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.23504654616117476,
|
|
"num_tokens": 63834350.0,
|
|
"step": 27840
|
|
},
|
|
{
|
|
"entropy": 5.094002676010132,
|
|
"epoch": 2.6748318924111434,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004288200489089231,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.23420720994472505,
|
|
"num_tokens": 63846150.0,
|
|
"step": 27845
|
|
},
|
|
{
|
|
"entropy": 5.260430812835693,
|
|
"epoch": 2.675312199807877,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000428795026469359,
|
|
"loss": 4.8252,
|
|
"mean_token_accuracy": 0.23089017421007157,
|
|
"num_tokens": 63857675.0,
|
|
"step": 27850
|
|
},
|
|
{
|
|
"entropy": 5.253284931182861,
|
|
"epoch": 2.675792507204611,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000428770000459131,
|
|
"loss": 4.949,
|
|
"mean_token_accuracy": 0.22029553949832917,
|
|
"num_tokens": 63868073.0,
|
|
"step": 27855
|
|
},
|
|
{
|
|
"entropy": 5.244732475280761,
|
|
"epoch": 2.6762728146013446,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004287449708788202,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.23723480850458145,
|
|
"num_tokens": 63879085.0,
|
|
"step": 27860
|
|
},
|
|
{
|
|
"entropy": 5.168757772445678,
|
|
"epoch": 2.676753121998079,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004287199377290077,
|
|
"loss": 4.7603,
|
|
"mean_token_accuracy": 0.23694878369569777,
|
|
"num_tokens": 63890885.0,
|
|
"step": 27865
|
|
},
|
|
{
|
|
"entropy": 5.185235214233399,
|
|
"epoch": 2.677233429394813,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004286949010102748,
|
|
"loss": 4.8152,
|
|
"mean_token_accuracy": 0.23158994764089585,
|
|
"num_tokens": 63902421.0,
|
|
"step": 27870
|
|
},
|
|
{
|
|
"entropy": 5.1730719089508055,
|
|
"epoch": 2.6777137367915467,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004286698607232026,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.23317931592464447,
|
|
"num_tokens": 63913845.0,
|
|
"step": 27875
|
|
},
|
|
{
|
|
"entropy": 5.1030433177948,
|
|
"epoch": 2.6781940441882806,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00042864481686837253,
|
|
"loss": 4.7133,
|
|
"mean_token_accuracy": 0.23619545996189117,
|
|
"num_tokens": 63925429.0,
|
|
"step": 27880
|
|
},
|
|
{
|
|
"entropy": 5.139955615997314,
|
|
"epoch": 2.6786743515850144,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00042861976944636604,
|
|
"loss": 4.844,
|
|
"mean_token_accuracy": 0.2322927951812744,
|
|
"num_tokens": 63939451.0,
|
|
"step": 27885
|
|
},
|
|
{
|
|
"entropy": 5.31072587966919,
|
|
"epoch": 2.6791546589817483,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004285947184577647,
|
|
"loss": 4.915,
|
|
"mean_token_accuracy": 0.22780710607767105,
|
|
"num_tokens": 63949077.0,
|
|
"step": 27890
|
|
},
|
|
{
|
|
"entropy": 5.195921993255615,
|
|
"epoch": 2.679634966378482,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042856966390315013,
|
|
"loss": 4.8589,
|
|
"mean_token_accuracy": 0.2308130070567131,
|
|
"num_tokens": 63960553.0,
|
|
"step": 27895
|
|
},
|
|
{
|
|
"entropy": 5.205868339538574,
|
|
"epoch": 2.680115273775216,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004285446057831039,
|
|
"loss": 4.9006,
|
|
"mean_token_accuracy": 0.22142658084630967,
|
|
"num_tokens": 63973086.0,
|
|
"step": 27900
|
|
},
|
|
{
|
|
"entropy": 5.210314607620239,
|
|
"epoch": 2.68059558117195,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004285195440982078,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.22569691389799118,
|
|
"num_tokens": 63983933.0,
|
|
"step": 27905
|
|
},
|
|
{
|
|
"entropy": 5.107872152328492,
|
|
"epoch": 2.681075888568684,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004284944788490439,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.24298178553581237,
|
|
"num_tokens": 63994557.0,
|
|
"step": 27910
|
|
},
|
|
{
|
|
"entropy": 5.224168825149536,
|
|
"epoch": 2.6815561959654177,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004284694100361938,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.22345736771821975,
|
|
"num_tokens": 64006368.0,
|
|
"step": 27915
|
|
},
|
|
{
|
|
"entropy": 5.205152130126953,
|
|
"epoch": 2.682036503362152,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004284443376602398,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.23565101027488708,
|
|
"num_tokens": 64018336.0,
|
|
"step": 27920
|
|
},
|
|
{
|
|
"entropy": 5.249040317535401,
|
|
"epoch": 2.6825168107588855,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004284192617217639,
|
|
"loss": 4.9207,
|
|
"mean_token_accuracy": 0.22711430490016937,
|
|
"num_tokens": 64030329.0,
|
|
"step": 27925
|
|
},
|
|
{
|
|
"entropy": 5.178670358657837,
|
|
"epoch": 2.68299711815562,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004283941822213484,
|
|
"loss": 4.8544,
|
|
"mean_token_accuracy": 0.23148019462823868,
|
|
"num_tokens": 64042502.0,
|
|
"step": 27930
|
|
},
|
|
{
|
|
"entropy": 5.161762666702271,
|
|
"epoch": 2.6834774255523532,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004283690991595754,
|
|
"loss": 4.8353,
|
|
"mean_token_accuracy": 0.23213352411985397,
|
|
"num_tokens": 64054217.0,
|
|
"step": 27935
|
|
},
|
|
{
|
|
"entropy": 5.310577392578125,
|
|
"epoch": 2.6839577329490876,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042834401253702734,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.23024509251117706,
|
|
"num_tokens": 64065019.0,
|
|
"step": 27940
|
|
},
|
|
{
|
|
"entropy": 5.170102596282959,
|
|
"epoch": 2.6844380403458215,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004283189223542866,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.23371675610542297,
|
|
"num_tokens": 64076251.0,
|
|
"step": 27945
|
|
},
|
|
{
|
|
"entropy": 5.154329061508179,
|
|
"epoch": 2.6849183477425553,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042829382861193585,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.23572148829698564,
|
|
"num_tokens": 64087257.0,
|
|
"step": 27950
|
|
},
|
|
{
|
|
"entropy": 5.120529651641846,
|
|
"epoch": 2.685398655139289,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004282687313105575,
|
|
"loss": 4.8552,
|
|
"mean_token_accuracy": 0.22527171820402145,
|
|
"num_tokens": 64098304.0,
|
|
"step": 27955
|
|
},
|
|
{
|
|
"entropy": 5.191087770462036,
|
|
"epoch": 2.685878962536023,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042824363045073434,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.23601422905921937,
|
|
"num_tokens": 64108839.0,
|
|
"step": 27960
|
|
},
|
|
{
|
|
"entropy": 5.259613561630249,
|
|
"epoch": 2.686359269932757,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004282185260330491,
|
|
"loss": 4.9193,
|
|
"mean_token_accuracy": 0.2259707748889923,
|
|
"num_tokens": 64121579.0,
|
|
"step": 27965
|
|
},
|
|
{
|
|
"entropy": 5.0611982345581055,
|
|
"epoch": 2.686839577329491,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042819341805808473,
|
|
"loss": 4.7495,
|
|
"mean_token_accuracy": 0.24356246143579482,
|
|
"num_tokens": 64132220.0,
|
|
"step": 27970
|
|
},
|
|
{
|
|
"entropy": 5.141791152954101,
|
|
"epoch": 2.6873198847262247,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042816830652642396,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.227760973572731,
|
|
"num_tokens": 64143580.0,
|
|
"step": 27975
|
|
},
|
|
{
|
|
"entropy": 5.178323221206665,
|
|
"epoch": 2.6878001921229586,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004281431914386501,
|
|
"loss": 4.8245,
|
|
"mean_token_accuracy": 0.2310981497168541,
|
|
"num_tokens": 64155042.0,
|
|
"step": 27980
|
|
},
|
|
{
|
|
"entropy": 5.293927574157715,
|
|
"epoch": 2.6882804995196925,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000428118072795346,
|
|
"loss": 4.9351,
|
|
"mean_token_accuracy": 0.22535859942436218,
|
|
"num_tokens": 64167755.0,
|
|
"step": 27985
|
|
},
|
|
{
|
|
"entropy": 5.221910429000855,
|
|
"epoch": 2.6887608069164264,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042809295059709483,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.22541654258966445,
|
|
"num_tokens": 64180930.0,
|
|
"step": 27990
|
|
},
|
|
{
|
|
"entropy": 5.212127780914306,
|
|
"epoch": 2.6892411143131603,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00042806782484448,
|
|
"loss": 4.8796,
|
|
"mean_token_accuracy": 0.22960123866796495,
|
|
"num_tokens": 64192994.0,
|
|
"step": 27995
|
|
},
|
|
{
|
|
"entropy": 5.238705635070801,
|
|
"epoch": 2.689721421709894,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004280426955380848,
|
|
"loss": 4.8725,
|
|
"mean_token_accuracy": 0.23027896881103516,
|
|
"num_tokens": 64204572.0,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"entropy": 5.150877189636231,
|
|
"epoch": 2.6902017291066285,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042801756267849266,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.23782838582992555,
|
|
"num_tokens": 64216361.0,
|
|
"step": 28005
|
|
},
|
|
{
|
|
"entropy": 5.135192394256592,
|
|
"epoch": 2.690682036503362,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004279924262662871,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.2389463111758232,
|
|
"num_tokens": 64227074.0,
|
|
"step": 28010
|
|
},
|
|
{
|
|
"entropy": 5.122286081314087,
|
|
"epoch": 2.6911623439000962,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004279672863020517,
|
|
"loss": 4.7827,
|
|
"mean_token_accuracy": 0.2373646765947342,
|
|
"num_tokens": 64239507.0,
|
|
"step": 28015
|
|
},
|
|
{
|
|
"entropy": 5.1969521045684814,
|
|
"epoch": 2.69164265129683,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042794214278637013,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.22729186713695526,
|
|
"num_tokens": 64251307.0,
|
|
"step": 28020
|
|
},
|
|
{
|
|
"entropy": 5.18192048072815,
|
|
"epoch": 2.692122958693564,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00042791699571982606,
|
|
"loss": 4.8834,
|
|
"mean_token_accuracy": 0.2318079560995102,
|
|
"num_tokens": 64263988.0,
|
|
"step": 28025
|
|
},
|
|
{
|
|
"entropy": 5.2305042266845705,
|
|
"epoch": 2.692603266090298,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004278918451030035,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.22560014724731445,
|
|
"num_tokens": 64275311.0,
|
|
"step": 28030
|
|
},
|
|
{
|
|
"entropy": 5.232147645950318,
|
|
"epoch": 2.6930835734870318,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004278666909364863,
|
|
"loss": 4.8983,
|
|
"mean_token_accuracy": 0.22650158554315566,
|
|
"num_tokens": 64286055.0,
|
|
"step": 28035
|
|
},
|
|
{
|
|
"entropy": 5.179013109207153,
|
|
"epoch": 2.6935638808837656,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004278415332208584,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.23664935380220414,
|
|
"num_tokens": 64297286.0,
|
|
"step": 28040
|
|
},
|
|
{
|
|
"entropy": 5.189198017120361,
|
|
"epoch": 2.6940441882804995,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042781637195670396,
|
|
"loss": 4.8759,
|
|
"mean_token_accuracy": 0.22985631376504898,
|
|
"num_tokens": 64308277.0,
|
|
"step": 28045
|
|
},
|
|
{
|
|
"entropy": 5.309024333953857,
|
|
"epoch": 2.6945244956772334,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004277912071446072,
|
|
"loss": 5.026,
|
|
"mean_token_accuracy": 0.21211127787828446,
|
|
"num_tokens": 64319260.0,
|
|
"step": 28050
|
|
},
|
|
{
|
|
"entropy": 5.310612344741822,
|
|
"epoch": 2.6950048030739673,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004277660387851522,
|
|
"loss": 4.9296,
|
|
"mean_token_accuracy": 0.22532116025686263,
|
|
"num_tokens": 64329840.0,
|
|
"step": 28055
|
|
},
|
|
{
|
|
"entropy": 5.331455278396606,
|
|
"epoch": 2.695485110470701,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004277408668789235,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.22230236679315568,
|
|
"num_tokens": 64342375.0,
|
|
"step": 28060
|
|
},
|
|
{
|
|
"entropy": 5.094805002212524,
|
|
"epoch": 2.695965417867435,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004277156914265054,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.24227969199419022,
|
|
"num_tokens": 64353396.0,
|
|
"step": 28065
|
|
},
|
|
{
|
|
"entropy": 5.2387580394744875,
|
|
"epoch": 2.696445725264169,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004276905124284824,
|
|
"loss": 4.9039,
|
|
"mean_token_accuracy": 0.23009640127420425,
|
|
"num_tokens": 64364802.0,
|
|
"step": 28070
|
|
},
|
|
{
|
|
"entropy": 5.2554676055908205,
|
|
"epoch": 2.696926032660903,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004276653298854391,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.22195184528827666,
|
|
"num_tokens": 64376379.0,
|
|
"step": 28075
|
|
},
|
|
{
|
|
"entropy": 5.206753444671631,
|
|
"epoch": 2.697406340057637,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004276401437979601,
|
|
"loss": 4.881,
|
|
"mean_token_accuracy": 0.22750166952610015,
|
|
"num_tokens": 64388039.0,
|
|
"step": 28080
|
|
},
|
|
{
|
|
"entropy": 5.210115957260132,
|
|
"epoch": 2.6978866474543706,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004276149541666303,
|
|
"loss": 4.8374,
|
|
"mean_token_accuracy": 0.2312204733490944,
|
|
"num_tokens": 64401288.0,
|
|
"step": 28085
|
|
},
|
|
{
|
|
"entropy": 5.197222423553467,
|
|
"epoch": 2.698366954851105,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042758976099203444,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.2386190414428711,
|
|
"num_tokens": 64411392.0,
|
|
"step": 28090
|
|
},
|
|
{
|
|
"entropy": 5.212723445892334,
|
|
"epoch": 2.6988472622478388,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042756456427475736,
|
|
"loss": 4.9091,
|
|
"mean_token_accuracy": 0.22774529904127122,
|
|
"num_tokens": 64421955.0,
|
|
"step": 28095
|
|
},
|
|
{
|
|
"entropy": 5.146440649032593,
|
|
"epoch": 2.6993275696445727,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004275393640153842,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.23396213203668595,
|
|
"num_tokens": 64434365.0,
|
|
"step": 28100
|
|
},
|
|
{
|
|
"entropy": 5.150233793258667,
|
|
"epoch": 2.6998078770413065,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042751416021449986,
|
|
"loss": 4.7847,
|
|
"mean_token_accuracy": 0.2335128203034401,
|
|
"num_tokens": 64444846.0,
|
|
"step": 28105
|
|
},
|
|
{
|
|
"entropy": 5.169606256484985,
|
|
"epoch": 2.7002881844380404,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004274889528726896,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.23514352589845658,
|
|
"num_tokens": 64455215.0,
|
|
"step": 28110
|
|
},
|
|
{
|
|
"entropy": 5.223955488204956,
|
|
"epoch": 2.7007684918347743,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004274637419905388,
|
|
"loss": 4.8154,
|
|
"mean_token_accuracy": 0.23629673421382905,
|
|
"num_tokens": 64465810.0,
|
|
"step": 28115
|
|
},
|
|
{
|
|
"entropy": 5.1208837032318115,
|
|
"epoch": 2.701248799231508,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042743852756863253,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.23602539896965027,
|
|
"num_tokens": 64476615.0,
|
|
"step": 28120
|
|
},
|
|
{
|
|
"entropy": 5.181634473800659,
|
|
"epoch": 2.701729106628242,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004274133096075563,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.23326804488897324,
|
|
"num_tokens": 64490137.0,
|
|
"step": 28125
|
|
},
|
|
{
|
|
"entropy": 5.175612735748291,
|
|
"epoch": 2.702209414024976,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004273880881078956,
|
|
"loss": 4.8245,
|
|
"mean_token_accuracy": 0.2372938722372055,
|
|
"num_tokens": 64501357.0,
|
|
"step": 28130
|
|
},
|
|
{
|
|
"entropy": 5.058705806732178,
|
|
"epoch": 2.70268972142171,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004273628630702359,
|
|
"loss": 4.6561,
|
|
"mean_token_accuracy": 0.24705255627632142,
|
|
"num_tokens": 64512784.0,
|
|
"step": 28135
|
|
},
|
|
{
|
|
"entropy": 5.148261404037475,
|
|
"epoch": 2.7031700288184437,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042733763449516313,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.24202821403741837,
|
|
"num_tokens": 64523800.0,
|
|
"step": 28140
|
|
},
|
|
{
|
|
"entropy": 5.206783056259155,
|
|
"epoch": 2.7036503362151776,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00042731240238326273,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.2358396530151367,
|
|
"num_tokens": 64535551.0,
|
|
"step": 28145
|
|
},
|
|
{
|
|
"entropy": 5.172128391265869,
|
|
"epoch": 2.7041306436119115,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00042728716673512065,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.2390364497900009,
|
|
"num_tokens": 64547892.0,
|
|
"step": 28150
|
|
},
|
|
{
|
|
"entropy": 5.092237186431885,
|
|
"epoch": 2.704610951008646,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00042726192755132276,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.2419498696923256,
|
|
"num_tokens": 64559687.0,
|
|
"step": 28155
|
|
},
|
|
{
|
|
"entropy": 5.133261346817017,
|
|
"epoch": 2.7050912584053792,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042723668483245496,
|
|
"loss": 4.7245,
|
|
"mean_token_accuracy": 0.23577760607004167,
|
|
"num_tokens": 64571691.0,
|
|
"step": 28160
|
|
},
|
|
{
|
|
"entropy": 5.203524398803711,
|
|
"epoch": 2.7055715658021136,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004272114385791035,
|
|
"loss": 4.8712,
|
|
"mean_token_accuracy": 0.23016779273748397,
|
|
"num_tokens": 64582570.0,
|
|
"step": 28165
|
|
},
|
|
{
|
|
"entropy": 5.238841581344604,
|
|
"epoch": 2.706051873198847,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042718618879185435,
|
|
"loss": 4.8385,
|
|
"mean_token_accuracy": 0.23446483612060548,
|
|
"num_tokens": 64593610.0,
|
|
"step": 28170
|
|
},
|
|
{
|
|
"entropy": 5.174103450775147,
|
|
"epoch": 2.7065321805955813,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004271609354712938,
|
|
"loss": 4.7694,
|
|
"mean_token_accuracy": 0.24304006546735762,
|
|
"num_tokens": 64604802.0,
|
|
"step": 28175
|
|
},
|
|
{
|
|
"entropy": 5.151589202880859,
|
|
"epoch": 2.707012487992315,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004271356786180082,
|
|
"loss": 4.7868,
|
|
"mean_token_accuracy": 0.22423326671123506,
|
|
"num_tokens": 64615816.0,
|
|
"step": 28180
|
|
},
|
|
{
|
|
"entropy": 5.107933044433594,
|
|
"epoch": 2.707492795389049,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004271104182325838,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.23281594067811967,
|
|
"num_tokens": 64628890.0,
|
|
"step": 28185
|
|
},
|
|
{
|
|
"entropy": 5.154287719726563,
|
|
"epoch": 2.707973102785783,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042708515431560723,
|
|
"loss": 4.7779,
|
|
"mean_token_accuracy": 0.2395346701145172,
|
|
"num_tokens": 64639494.0,
|
|
"step": 28190
|
|
},
|
|
{
|
|
"entropy": 5.286838579177856,
|
|
"epoch": 2.708453410182517,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000427059886867665,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.22195273041725158,
|
|
"num_tokens": 64651235.0,
|
|
"step": 28195
|
|
},
|
|
{
|
|
"entropy": 5.180114221572876,
|
|
"epoch": 2.7089337175792507,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004270346158893436,
|
|
"loss": 4.8414,
|
|
"mean_token_accuracy": 0.23215432614088058,
|
|
"num_tokens": 64662517.0,
|
|
"step": 28200
|
|
},
|
|
{
|
|
"entropy": 5.205938768386841,
|
|
"epoch": 2.7094140249759846,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00042700934138123004,
|
|
"loss": 4.9154,
|
|
"mean_token_accuracy": 0.22002994120121003,
|
|
"num_tokens": 64674521.0,
|
|
"step": 28205
|
|
},
|
|
{
|
|
"entropy": 5.269718885421753,
|
|
"epoch": 2.7098943323727185,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042698406334391084,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.21864506602287292,
|
|
"num_tokens": 64686894.0,
|
|
"step": 28210
|
|
},
|
|
{
|
|
"entropy": 5.262466907501221,
|
|
"epoch": 2.7103746397694524,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000426958781777973,
|
|
"loss": 4.9257,
|
|
"mean_token_accuracy": 0.23662377744913102,
|
|
"num_tokens": 64697948.0,
|
|
"step": 28215
|
|
},
|
|
{
|
|
"entropy": 5.227351665496826,
|
|
"epoch": 2.7108549471661862,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004269334966840035,
|
|
"loss": 4.807,
|
|
"mean_token_accuracy": 0.23347826004028321,
|
|
"num_tokens": 64709429.0,
|
|
"step": 28220
|
|
},
|
|
{
|
|
"entropy": 5.182429456710816,
|
|
"epoch": 2.71133525456292,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042690820806258933,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.2390466883778572,
|
|
"num_tokens": 64720529.0,
|
|
"step": 28225
|
|
},
|
|
{
|
|
"entropy": 5.096969318389893,
|
|
"epoch": 2.7118155619596545,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004268829159143176,
|
|
"loss": 4.7492,
|
|
"mean_token_accuracy": 0.24123973548412322,
|
|
"num_tokens": 64731602.0,
|
|
"step": 28230
|
|
},
|
|
{
|
|
"entropy": 5.249237108230591,
|
|
"epoch": 2.712295869356388,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004268576202397757,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.23285702764987945,
|
|
"num_tokens": 64742746.0,
|
|
"step": 28235
|
|
},
|
|
{
|
|
"entropy": 5.185017204284668,
|
|
"epoch": 2.712776176753122,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004268323210395506,
|
|
"loss": 4.8355,
|
|
"mean_token_accuracy": 0.2366800367832184,
|
|
"num_tokens": 64754643.0,
|
|
"step": 28240
|
|
},
|
|
{
|
|
"entropy": 5.273546886444092,
|
|
"epoch": 2.7132564841498557,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042680701831423004,
|
|
"loss": 4.9116,
|
|
"mean_token_accuracy": 0.2259516566991806,
|
|
"num_tokens": 64766349.0,
|
|
"step": 28245
|
|
},
|
|
{
|
|
"entropy": 5.129106760025024,
|
|
"epoch": 2.71373679154659,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004267817120644012,
|
|
"loss": 4.8003,
|
|
"mean_token_accuracy": 0.23647269904613494,
|
|
"num_tokens": 64777645.0,
|
|
"step": 28250
|
|
},
|
|
{
|
|
"entropy": 5.197730350494385,
|
|
"epoch": 2.714217098943324,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042675640229065167,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.22385105043649672,
|
|
"num_tokens": 64788065.0,
|
|
"step": 28255
|
|
},
|
|
{
|
|
"entropy": 5.234056043624878,
|
|
"epoch": 2.7146974063400577,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00042673108899356915,
|
|
"loss": 4.815,
|
|
"mean_token_accuracy": 0.23539386838674545,
|
|
"num_tokens": 64798938.0,
|
|
"step": 28260
|
|
},
|
|
{
|
|
"entropy": 5.148052644729614,
|
|
"epoch": 2.7151777137367916,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004267057721737413,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.23131294697523117,
|
|
"num_tokens": 64810572.0,
|
|
"step": 28265
|
|
},
|
|
{
|
|
"entropy": 5.121906852722168,
|
|
"epoch": 2.7156580211335255,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004266804518317559,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.23754575103521347,
|
|
"num_tokens": 64821877.0,
|
|
"step": 28270
|
|
},
|
|
{
|
|
"entropy": 5.203670406341553,
|
|
"epoch": 2.7161383285302594,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004266551279682008,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.23785802274942397,
|
|
"num_tokens": 64832737.0,
|
|
"step": 28275
|
|
},
|
|
{
|
|
"entropy": 5.164348125457764,
|
|
"epoch": 2.7166186359269933,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004266298005836639,
|
|
"loss": 4.8377,
|
|
"mean_token_accuracy": 0.22582447826862334,
|
|
"num_tokens": 64844713.0,
|
|
"step": 28280
|
|
},
|
|
{
|
|
"entropy": 5.184296178817749,
|
|
"epoch": 2.717098943323727,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042660446967873327,
|
|
"loss": 4.8404,
|
|
"mean_token_accuracy": 0.23406440019607544,
|
|
"num_tokens": 64855896.0,
|
|
"step": 28285
|
|
},
|
|
{
|
|
"entropy": 5.2128662109375,
|
|
"epoch": 2.717579250720461,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042657913525399703,
|
|
"loss": 4.904,
|
|
"mean_token_accuracy": 0.2227015107870102,
|
|
"num_tokens": 64866529.0,
|
|
"step": 28290
|
|
},
|
|
{
|
|
"entropy": 5.170451021194458,
|
|
"epoch": 2.718059558117195,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004265537973100435,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.23102509826421738,
|
|
"num_tokens": 64876691.0,
|
|
"step": 28295
|
|
},
|
|
{
|
|
"entropy": 5.1440938949584964,
|
|
"epoch": 2.718539865513929,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004265284558474607,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.23001815676689147,
|
|
"num_tokens": 64887271.0,
|
|
"step": 28300
|
|
},
|
|
{
|
|
"entropy": 5.173931980133057,
|
|
"epoch": 2.7190201729106627,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00042650311086683715,
|
|
"loss": 4.9018,
|
|
"mean_token_accuracy": 0.22500599622726442,
|
|
"num_tokens": 64900698.0,
|
|
"step": 28305
|
|
},
|
|
{
|
|
"entropy": 5.211280727386475,
|
|
"epoch": 2.7195004803073966,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004264777623687612,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.22957205027341843,
|
|
"num_tokens": 64911349.0,
|
|
"step": 28310
|
|
},
|
|
{
|
|
"entropy": 5.171284818649292,
|
|
"epoch": 2.719980787704131,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004264524103538214,
|
|
"loss": 4.8357,
|
|
"mean_token_accuracy": 0.23712946772575377,
|
|
"num_tokens": 64922522.0,
|
|
"step": 28315
|
|
},
|
|
{
|
|
"entropy": 5.2240636348724365,
|
|
"epoch": 2.7204610951008643,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004264270548226064,
|
|
"loss": 4.8588,
|
|
"mean_token_accuracy": 0.23265839219093323,
|
|
"num_tokens": 64934796.0,
|
|
"step": 28320
|
|
},
|
|
{
|
|
"entropy": 5.181234979629517,
|
|
"epoch": 2.7209414024975986,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004264016957757048,
|
|
"loss": 4.8378,
|
|
"mean_token_accuracy": 0.23910980373620988,
|
|
"num_tokens": 64946717.0,
|
|
"step": 28325
|
|
},
|
|
{
|
|
"entropy": 5.222444295883179,
|
|
"epoch": 2.7214217098943325,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00042637633321370545,
|
|
"loss": 4.9206,
|
|
"mean_token_accuracy": 0.22515794187784194,
|
|
"num_tokens": 64958818.0,
|
|
"step": 28330
|
|
},
|
|
{
|
|
"entropy": 5.201200866699219,
|
|
"epoch": 2.7219020172910664,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004263509671371971,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.22637580037117006,
|
|
"num_tokens": 64968974.0,
|
|
"step": 28335
|
|
},
|
|
{
|
|
"entropy": 5.203151035308838,
|
|
"epoch": 2.7223823246878003,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042632559754676865,
|
|
"loss": 4.8395,
|
|
"mean_token_accuracy": 0.22997038513422013,
|
|
"num_tokens": 64980347.0,
|
|
"step": 28340
|
|
},
|
|
{
|
|
"entropy": 5.2181721210479735,
|
|
"epoch": 2.722862632084534,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004263002244430092,
|
|
"loss": 4.8274,
|
|
"mean_token_accuracy": 0.23339779078960418,
|
|
"num_tokens": 64992916.0,
|
|
"step": 28345
|
|
},
|
|
{
|
|
"entropy": 5.148798418045044,
|
|
"epoch": 2.723342939481268,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004262748478265078,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.23074301928281785,
|
|
"num_tokens": 65003382.0,
|
|
"step": 28350
|
|
},
|
|
{
|
|
"entropy": 5.109139060974121,
|
|
"epoch": 2.723823246878002,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004262494676978537,
|
|
"loss": 4.6547,
|
|
"mean_token_accuracy": 0.24407210648059846,
|
|
"num_tokens": 65014064.0,
|
|
"step": 28355
|
|
},
|
|
{
|
|
"entropy": 5.242486190795899,
|
|
"epoch": 2.724303554274736,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042622408405763607,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.22838118821382522,
|
|
"num_tokens": 65025701.0,
|
|
"step": 28360
|
|
},
|
|
{
|
|
"entropy": 5.212172412872315,
|
|
"epoch": 2.7247838616714697,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004261986969064442,
|
|
"loss": 4.8604,
|
|
"mean_token_accuracy": 0.2290143758058548,
|
|
"num_tokens": 65038270.0,
|
|
"step": 28365
|
|
},
|
|
{
|
|
"entropy": 5.1744218349456785,
|
|
"epoch": 2.7252641690682036,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042617330624486753,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.23613883852958678,
|
|
"num_tokens": 65049453.0,
|
|
"step": 28370
|
|
},
|
|
{
|
|
"entropy": 5.0397655963897705,
|
|
"epoch": 2.7257444764649374,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004261479120734956,
|
|
"loss": 4.6554,
|
|
"mean_token_accuracy": 0.2517122715711594,
|
|
"num_tokens": 65061211.0,
|
|
"step": 28375
|
|
},
|
|
{
|
|
"entropy": 5.127121448516846,
|
|
"epoch": 2.7262247838616713,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000426122514392918,
|
|
"loss": 4.7315,
|
|
"mean_token_accuracy": 0.2393806204199791,
|
|
"num_tokens": 65073073.0,
|
|
"step": 28380
|
|
},
|
|
{
|
|
"entropy": 5.171558094024658,
|
|
"epoch": 2.726705091258405,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042609711320372435,
|
|
"loss": 4.8129,
|
|
"mean_token_accuracy": 0.23908934444189073,
|
|
"num_tokens": 65084647.0,
|
|
"step": 28385
|
|
},
|
|
{
|
|
"entropy": 5.1742026805877686,
|
|
"epoch": 2.7271853986551395,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004260717085065045,
|
|
"loss": 4.7798,
|
|
"mean_token_accuracy": 0.2419736534357071,
|
|
"num_tokens": 65095405.0,
|
|
"step": 28390
|
|
},
|
|
{
|
|
"entropy": 5.174307346343994,
|
|
"epoch": 2.727665706051873,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042604630030184797,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.23463867604732513,
|
|
"num_tokens": 65106981.0,
|
|
"step": 28395
|
|
},
|
|
{
|
|
"entropy": 5.2671952724456785,
|
|
"epoch": 2.7281460134486073,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000426020888590345,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.2246756970882416,
|
|
"num_tokens": 65118957.0,
|
|
"step": 28400
|
|
},
|
|
{
|
|
"entropy": 5.210568237304687,
|
|
"epoch": 2.728626320845341,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042599547337258536,
|
|
"loss": 4.832,
|
|
"mean_token_accuracy": 0.2337906613945961,
|
|
"num_tokens": 65130897.0,
|
|
"step": 28405
|
|
},
|
|
{
|
|
"entropy": 5.0450834274292,
|
|
"epoch": 2.729106628242075,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042597005464915924,
|
|
"loss": 4.6381,
|
|
"mean_token_accuracy": 0.24746651351451873,
|
|
"num_tokens": 65142828.0,
|
|
"step": 28410
|
|
},
|
|
{
|
|
"entropy": 5.071255779266357,
|
|
"epoch": 2.729586935638809,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042594463242065674,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.2390845999121666,
|
|
"num_tokens": 65154787.0,
|
|
"step": 28415
|
|
},
|
|
{
|
|
"entropy": 5.176388883590699,
|
|
"epoch": 2.730067243035543,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004259192066876681,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.23821723461151123,
|
|
"num_tokens": 65165530.0,
|
|
"step": 28420
|
|
},
|
|
{
|
|
"entropy": 5.275805187225342,
|
|
"epoch": 2.7305475504322767,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042589377745078354,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.2273118704557419,
|
|
"num_tokens": 65176809.0,
|
|
"step": 28425
|
|
},
|
|
{
|
|
"entropy": 5.272503805160523,
|
|
"epoch": 2.7310278578290106,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042586834471059366,
|
|
"loss": 4.9276,
|
|
"mean_token_accuracy": 0.2223840594291687,
|
|
"num_tokens": 65189251.0,
|
|
"step": 28430
|
|
},
|
|
{
|
|
"entropy": 5.10967493057251,
|
|
"epoch": 2.7315081652257445,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042584290846768867,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.24204944670200348,
|
|
"num_tokens": 65200918.0,
|
|
"step": 28435
|
|
},
|
|
{
|
|
"entropy": 5.21996545791626,
|
|
"epoch": 2.7319884726224783,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004258174687226593,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.22968358993530275,
|
|
"num_tokens": 65213283.0,
|
|
"step": 28440
|
|
},
|
|
{
|
|
"entropy": 5.233068513870239,
|
|
"epoch": 2.7324687800192122,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004257920254760962,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.2387236088514328,
|
|
"num_tokens": 65223680.0,
|
|
"step": 28445
|
|
},
|
|
{
|
|
"entropy": 5.192857122421264,
|
|
"epoch": 2.732949087415946,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004257665787285899,
|
|
"loss": 4.8341,
|
|
"mean_token_accuracy": 0.23467975854873657,
|
|
"num_tokens": 65234570.0,
|
|
"step": 28450
|
|
},
|
|
{
|
|
"entropy": 5.205500793457031,
|
|
"epoch": 2.73342939481268,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00042574112848073147,
|
|
"loss": 4.7948,
|
|
"mean_token_accuracy": 0.23396794945001603,
|
|
"num_tokens": 65246616.0,
|
|
"step": 28455
|
|
},
|
|
{
|
|
"entropy": 5.147635984420776,
|
|
"epoch": 2.733909702209414,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042571567473311157,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.23425666838884354,
|
|
"num_tokens": 65257853.0,
|
|
"step": 28460
|
|
},
|
|
{
|
|
"entropy": 5.199933910369873,
|
|
"epoch": 2.734390009606148,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004256902174863213,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.23456081748008728,
|
|
"num_tokens": 65268843.0,
|
|
"step": 28465
|
|
},
|
|
{
|
|
"entropy": 5.279987621307373,
|
|
"epoch": 2.7348703170028816,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042566475674095155,
|
|
"loss": 4.9454,
|
|
"mean_token_accuracy": 0.2208731636404991,
|
|
"num_tokens": 65279824.0,
|
|
"step": 28470
|
|
},
|
|
{
|
|
"entropy": 5.13037428855896,
|
|
"epoch": 2.735350624399616,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004256392924975936,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.2332715943455696,
|
|
"num_tokens": 65291318.0,
|
|
"step": 28475
|
|
},
|
|
{
|
|
"entropy": 5.132266473770142,
|
|
"epoch": 2.7358309317963494,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042561382475683854,
|
|
"loss": 4.7958,
|
|
"mean_token_accuracy": 0.23510153740644454,
|
|
"num_tokens": 65302997.0,
|
|
"step": 28480
|
|
},
|
|
{
|
|
"entropy": 5.150341367721557,
|
|
"epoch": 2.7363112391930837,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004255883535192777,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.24443507194519043,
|
|
"num_tokens": 65314336.0,
|
|
"step": 28485
|
|
},
|
|
{
|
|
"entropy": 5.215194654464722,
|
|
"epoch": 2.7367915465898176,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004255628787855025,
|
|
"loss": 4.8521,
|
|
"mean_token_accuracy": 0.22965503185987474,
|
|
"num_tokens": 65325138.0,
|
|
"step": 28490
|
|
},
|
|
{
|
|
"entropy": 5.241517686843872,
|
|
"epoch": 2.7372718539865515,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004255374005561043,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.23489790856838227,
|
|
"num_tokens": 65337067.0,
|
|
"step": 28495
|
|
},
|
|
{
|
|
"entropy": 5.216712522506714,
|
|
"epoch": 2.7377521613832854,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042551191883167464,
|
|
"loss": 4.8441,
|
|
"mean_token_accuracy": 0.2348305657505989,
|
|
"num_tokens": 65349598.0,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"entropy": 5.234872722625733,
|
|
"epoch": 2.7382324687800192,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004254864336128052,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.22190768420696258,
|
|
"num_tokens": 65361052.0,
|
|
"step": 28505
|
|
},
|
|
{
|
|
"entropy": 5.250554180145263,
|
|
"epoch": 2.738712776176753,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00042546094490008765,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.228818379342556,
|
|
"num_tokens": 65373246.0,
|
|
"step": 28510
|
|
},
|
|
{
|
|
"entropy": 5.182133579254151,
|
|
"epoch": 2.739193083573487,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004254354526941136,
|
|
"loss": 4.7809,
|
|
"mean_token_accuracy": 0.23750449866056442,
|
|
"num_tokens": 65384349.0,
|
|
"step": 28515
|
|
},
|
|
{
|
|
"entropy": 5.056044292449951,
|
|
"epoch": 2.739673390970221,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004254099569954751,
|
|
"loss": 4.7889,
|
|
"mean_token_accuracy": 0.2316688746213913,
|
|
"num_tokens": 65396241.0,
|
|
"step": 28520
|
|
},
|
|
{
|
|
"entropy": 5.126723861694336,
|
|
"epoch": 2.7401536983669548,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004253844578047641,
|
|
"loss": 4.8465,
|
|
"mean_token_accuracy": 0.22697652280330657,
|
|
"num_tokens": 65408583.0,
|
|
"step": 28525
|
|
},
|
|
{
|
|
"entropy": 5.226612281799317,
|
|
"epoch": 2.7406340057636887,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004253589551225725,
|
|
"loss": 4.7691,
|
|
"mean_token_accuracy": 0.23954339772462846,
|
|
"num_tokens": 65419845.0,
|
|
"step": 28530
|
|
},
|
|
{
|
|
"entropy": 5.2245604515075685,
|
|
"epoch": 2.7411143131604225,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00042533344894949245,
|
|
"loss": 4.8362,
|
|
"mean_token_accuracy": 0.22538719475269317,
|
|
"num_tokens": 65433790.0,
|
|
"step": 28535
|
|
},
|
|
{
|
|
"entropy": 5.215486812591553,
|
|
"epoch": 2.7415946205571564,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00042530793928611605,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.23281408697366715,
|
|
"num_tokens": 65445958.0,
|
|
"step": 28540
|
|
},
|
|
{
|
|
"entropy": 5.196478843688965,
|
|
"epoch": 2.7420749279538903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004252824261330357,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.23344589322805404,
|
|
"num_tokens": 65457973.0,
|
|
"step": 28545
|
|
},
|
|
{
|
|
"entropy": 5.158015966415405,
|
|
"epoch": 2.7425552353506246,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042525690949084364,
|
|
"loss": 4.8476,
|
|
"mean_token_accuracy": 0.23760845959186555,
|
|
"num_tokens": 65470245.0,
|
|
"step": 28550
|
|
},
|
|
{
|
|
"entropy": 5.092483568191528,
|
|
"epoch": 2.743035542747358,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042523138936013233,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.23889800161123276,
|
|
"num_tokens": 65482541.0,
|
|
"step": 28555
|
|
},
|
|
{
|
|
"entropy": 5.277427625656128,
|
|
"epoch": 2.7435158501440924,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042520586574149423,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.22581302672624587,
|
|
"num_tokens": 65494499.0,
|
|
"step": 28560
|
|
},
|
|
{
|
|
"entropy": 5.300054025650025,
|
|
"epoch": 2.7439961575408263,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042518033863552185,
|
|
"loss": 4.9455,
|
|
"mean_token_accuracy": 0.2195411205291748,
|
|
"num_tokens": 65506377.0,
|
|
"step": 28565
|
|
},
|
|
{
|
|
"entropy": 5.25525279045105,
|
|
"epoch": 2.74447646493756,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004251548080428081,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.2302788943052292,
|
|
"num_tokens": 65517476.0,
|
|
"step": 28570
|
|
},
|
|
{
|
|
"entropy": 5.229835367202758,
|
|
"epoch": 2.744956772334294,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004251292739639455,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.22834286838769913,
|
|
"num_tokens": 65529829.0,
|
|
"step": 28575
|
|
},
|
|
{
|
|
"entropy": 5.080589008331299,
|
|
"epoch": 2.745437079731028,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042510373639952694,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.2401255339384079,
|
|
"num_tokens": 65541030.0,
|
|
"step": 28580
|
|
},
|
|
{
|
|
"entropy": 5.151509618759155,
|
|
"epoch": 2.745917387127762,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042507819535014547,
|
|
"loss": 4.8129,
|
|
"mean_token_accuracy": 0.23415353298187255,
|
|
"num_tokens": 65551727.0,
|
|
"step": 28585
|
|
},
|
|
{
|
|
"entropy": 5.1256636619567875,
|
|
"epoch": 2.7463976945244957,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042505265081639376,
|
|
"loss": 4.7868,
|
|
"mean_token_accuracy": 0.24492108672857285,
|
|
"num_tokens": 65563085.0,
|
|
"step": 28590
|
|
},
|
|
{
|
|
"entropy": 5.202720212936401,
|
|
"epoch": 2.7468780019212296,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004250271027988652,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.23484785109758377,
|
|
"num_tokens": 65574909.0,
|
|
"step": 28595
|
|
},
|
|
{
|
|
"entropy": 5.149930810928344,
|
|
"epoch": 2.7473583093179634,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042500155129815274,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.23937614113092423,
|
|
"num_tokens": 65585515.0,
|
|
"step": 28600
|
|
},
|
|
{
|
|
"entropy": 5.115460729598999,
|
|
"epoch": 2.7478386167146973,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00042497599631484965,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.23045914620161057,
|
|
"num_tokens": 65598160.0,
|
|
"step": 28605
|
|
},
|
|
{
|
|
"entropy": 5.205484437942505,
|
|
"epoch": 2.748318924111431,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042495043784954926,
|
|
"loss": 4.8486,
|
|
"mean_token_accuracy": 0.23076659739017485,
|
|
"num_tokens": 65609886.0,
|
|
"step": 28610
|
|
},
|
|
{
|
|
"entropy": 5.171898651123047,
|
|
"epoch": 2.748799231508165,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000424924875902845,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.2305467575788498,
|
|
"num_tokens": 65620256.0,
|
|
"step": 28615
|
|
},
|
|
{
|
|
"entropy": 5.214147520065308,
|
|
"epoch": 2.749279538904899,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004248993104753303,
|
|
"loss": 4.8428,
|
|
"mean_token_accuracy": 0.23412125408649445,
|
|
"num_tokens": 65631108.0,
|
|
"step": 28620
|
|
},
|
|
{
|
|
"entropy": 5.201419258117676,
|
|
"epoch": 2.7497598463016333,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004248737415675987,
|
|
"loss": 4.84,
|
|
"mean_token_accuracy": 0.23336447179317474,
|
|
"num_tokens": 65642423.0,
|
|
"step": 28625
|
|
},
|
|
{
|
|
"entropy": 5.137066888809204,
|
|
"epoch": 2.7502401536983667,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004248481691802439,
|
|
"loss": 4.8284,
|
|
"mean_token_accuracy": 0.23191688060760499,
|
|
"num_tokens": 65654105.0,
|
|
"step": 28630
|
|
},
|
|
{
|
|
"entropy": 5.244405841827392,
|
|
"epoch": 2.750720461095101,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004248225933138595,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.23556040227413177,
|
|
"num_tokens": 65664738.0,
|
|
"step": 28635
|
|
},
|
|
{
|
|
"entropy": 5.127702617645264,
|
|
"epoch": 2.751200768491835,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00042479701396903945,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.23257231265306472,
|
|
"num_tokens": 65676815.0,
|
|
"step": 28640
|
|
},
|
|
{
|
|
"entropy": 5.229048204421997,
|
|
"epoch": 2.751681075888569,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004247714311463775,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.2349789023399353,
|
|
"num_tokens": 65687234.0,
|
|
"step": 28645
|
|
},
|
|
{
|
|
"entropy": 5.2477076053619385,
|
|
"epoch": 2.7521613832853027,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042474584484646766,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.22508900761604309,
|
|
"num_tokens": 65700356.0,
|
|
"step": 28650
|
|
},
|
|
{
|
|
"entropy": 5.123367977142334,
|
|
"epoch": 2.7526416906820366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004247202550699039,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.24651813209056855,
|
|
"num_tokens": 65711320.0,
|
|
"step": 28655
|
|
},
|
|
{
|
|
"entropy": 5.149107646942139,
|
|
"epoch": 2.7531219980787704,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004246946618172805,
|
|
"loss": 4.8544,
|
|
"mean_token_accuracy": 0.23756307363510132,
|
|
"num_tokens": 65722461.0,
|
|
"step": 28660
|
|
},
|
|
{
|
|
"entropy": 5.104007577896118,
|
|
"epoch": 2.7536023054755043,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004246690650891915,
|
|
"loss": 4.6989,
|
|
"mean_token_accuracy": 0.2395123854279518,
|
|
"num_tokens": 65732311.0,
|
|
"step": 28665
|
|
},
|
|
{
|
|
"entropy": 5.20537371635437,
|
|
"epoch": 2.754082612872238,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004246434648862312,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.23841604292392732,
|
|
"num_tokens": 65743830.0,
|
|
"step": 28670
|
|
},
|
|
{
|
|
"entropy": 5.2420063495635985,
|
|
"epoch": 2.754562920268972,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004246178612089941,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.22409306913614274,
|
|
"num_tokens": 65754851.0,
|
|
"step": 28675
|
|
},
|
|
{
|
|
"entropy": 5.257897520065308,
|
|
"epoch": 2.755043227665706,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004245922540580744,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.23178064227104186,
|
|
"num_tokens": 65765228.0,
|
|
"step": 28680
|
|
},
|
|
{
|
|
"entropy": 5.197315216064453,
|
|
"epoch": 2.75552353506244,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004245666434340668,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.22607577890157698,
|
|
"num_tokens": 65775334.0,
|
|
"step": 28685
|
|
},
|
|
{
|
|
"entropy": 5.074616527557373,
|
|
"epoch": 2.7560038424591737,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004245410293375659,
|
|
"loss": 4.7287,
|
|
"mean_token_accuracy": 0.24869603365659715,
|
|
"num_tokens": 65786256.0,
|
|
"step": 28690
|
|
},
|
|
{
|
|
"entropy": 5.2244542121887205,
|
|
"epoch": 2.7564841498559076,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004245154117691664,
|
|
"loss": 4.7962,
|
|
"mean_token_accuracy": 0.23492054641246796,
|
|
"num_tokens": 65798831.0,
|
|
"step": 28695
|
|
},
|
|
{
|
|
"entropy": 5.146289443969726,
|
|
"epoch": 2.756964457252642,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004244897907294628,
|
|
"loss": 4.8322,
|
|
"mean_token_accuracy": 0.2300187438726425,
|
|
"num_tokens": 65810256.0,
|
|
"step": 28700
|
|
},
|
|
{
|
|
"entropy": 5.296774435043335,
|
|
"epoch": 2.7574447646493754,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004244641662190504,
|
|
"loss": 4.9954,
|
|
"mean_token_accuracy": 0.22646482139825821,
|
|
"num_tokens": 65821752.0,
|
|
"step": 28705
|
|
},
|
|
{
|
|
"entropy": 5.267191934585571,
|
|
"epoch": 2.7579250720461097,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00042443853823852376,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.22688525915145874,
|
|
"num_tokens": 65833056.0,
|
|
"step": 28710
|
|
},
|
|
{
|
|
"entropy": 5.169261121749878,
|
|
"epoch": 2.7584053794428436,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000424412906788478,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.23523123413324357,
|
|
"num_tokens": 65845081.0,
|
|
"step": 28715
|
|
},
|
|
{
|
|
"entropy": 5.190327501296997,
|
|
"epoch": 2.7588856868395775,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004243872718695082,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.22960716485977173,
|
|
"num_tokens": 65856024.0,
|
|
"step": 28720
|
|
},
|
|
{
|
|
"entropy": 5.180902814865112,
|
|
"epoch": 2.7593659942363113,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042436163348220956,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.24180546551942825,
|
|
"num_tokens": 65868282.0,
|
|
"step": 28725
|
|
},
|
|
{
|
|
"entropy": 5.097864246368408,
|
|
"epoch": 2.7598463016330452,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004243359916271773,
|
|
"loss": 4.7905,
|
|
"mean_token_accuracy": 0.23399871438741685,
|
|
"num_tokens": 65879835.0,
|
|
"step": 28730
|
|
},
|
|
{
|
|
"entropy": 5.087635612487793,
|
|
"epoch": 2.760326609029779,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004243103463050067,
|
|
"loss": 4.7495,
|
|
"mean_token_accuracy": 0.24111883342266083,
|
|
"num_tokens": 65890916.0,
|
|
"step": 28735
|
|
},
|
|
{
|
|
"entropy": 5.233701610565186,
|
|
"epoch": 2.760806916426513,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004242846975162933,
|
|
"loss": 4.8427,
|
|
"mean_token_accuracy": 0.23293771147727965,
|
|
"num_tokens": 65901716.0,
|
|
"step": 28740
|
|
},
|
|
{
|
|
"entropy": 5.232057380676269,
|
|
"epoch": 2.761287223823247,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00042425904526163246,
|
|
"loss": 4.8996,
|
|
"mean_token_accuracy": 0.23139912784099578,
|
|
"num_tokens": 65914366.0,
|
|
"step": 28745
|
|
},
|
|
{
|
|
"entropy": 5.290376091003418,
|
|
"epoch": 2.7617675312199808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004242333895416198,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.21852268278598785,
|
|
"num_tokens": 65926396.0,
|
|
"step": 28750
|
|
},
|
|
{
|
|
"entropy": 5.2108588218688965,
|
|
"epoch": 2.7622478386167146,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000424207730356851,
|
|
"loss": 4.8473,
|
|
"mean_token_accuracy": 0.23336768746376038,
|
|
"num_tokens": 65939200.0,
|
|
"step": 28755
|
|
},
|
|
{
|
|
"entropy": 5.232928037643433,
|
|
"epoch": 2.7627281460134485,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004241820677079218,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.23247775584459304,
|
|
"num_tokens": 65948978.0,
|
|
"step": 28760
|
|
},
|
|
{
|
|
"entropy": 5.197577476501465,
|
|
"epoch": 2.7632084534101824,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042415640159542783,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.24156941771507262,
|
|
"num_tokens": 65959661.0,
|
|
"step": 28765
|
|
},
|
|
{
|
|
"entropy": 5.101096725463867,
|
|
"epoch": 2.7636887608069163,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004241307320199652,
|
|
"loss": 4.6949,
|
|
"mean_token_accuracy": 0.2492607519030571,
|
|
"num_tokens": 65970208.0,
|
|
"step": 28770
|
|
},
|
|
{
|
|
"entropy": 5.190475225448608,
|
|
"epoch": 2.7641690682036506,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004241050589821298,
|
|
"loss": 4.84,
|
|
"mean_token_accuracy": 0.23569898754358293,
|
|
"num_tokens": 65982606.0,
|
|
"step": 28775
|
|
},
|
|
{
|
|
"entropy": 5.125509262084961,
|
|
"epoch": 2.764649375600384,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004240793824825177,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.23865172863006592,
|
|
"num_tokens": 65993984.0,
|
|
"step": 28780
|
|
},
|
|
{
|
|
"entropy": 5.192023372650146,
|
|
"epoch": 2.7651296829971184,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042405370252172496,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.23705016374588012,
|
|
"num_tokens": 66004740.0,
|
|
"step": 28785
|
|
},
|
|
{
|
|
"entropy": 5.182515573501587,
|
|
"epoch": 2.765609990393852,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004240280191003479,
|
|
"loss": 4.8929,
|
|
"mean_token_accuracy": 0.23030879944562913,
|
|
"num_tokens": 66019265.0,
|
|
"step": 28790
|
|
},
|
|
{
|
|
"entropy": 5.182042217254638,
|
|
"epoch": 2.766090297790586,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004240023322189828,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.23610274195671083,
|
|
"num_tokens": 66030434.0,
|
|
"step": 28795
|
|
},
|
|
{
|
|
"entropy": 5.221289014816284,
|
|
"epoch": 2.76657060518732,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004239766418782258,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.23007163554430007,
|
|
"num_tokens": 66041100.0,
|
|
"step": 28800
|
|
},
|
|
{
|
|
"entropy": 5.128480005264282,
|
|
"epoch": 2.767050912584054,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004239509480786737,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.23054350465536116,
|
|
"num_tokens": 66053046.0,
|
|
"step": 28805
|
|
},
|
|
{
|
|
"entropy": 5.285182857513428,
|
|
"epoch": 2.7675312199807878,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042392525082092286,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.22453473061323165,
|
|
"num_tokens": 66063508.0,
|
|
"step": 28810
|
|
},
|
|
{
|
|
"entropy": 5.232703065872192,
|
|
"epoch": 2.7680115273775217,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004238995501055699,
|
|
"loss": 4.9472,
|
|
"mean_token_accuracy": 0.22483011931180955,
|
|
"num_tokens": 66076135.0,
|
|
"step": 28815
|
|
},
|
|
{
|
|
"entropy": 5.209732294082642,
|
|
"epoch": 2.7684918347742555,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004238738459332115,
|
|
"loss": 4.8845,
|
|
"mean_token_accuracy": 0.22509629875421525,
|
|
"num_tokens": 66087565.0,
|
|
"step": 28820
|
|
},
|
|
{
|
|
"entropy": 5.217461729049683,
|
|
"epoch": 2.7689721421709894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004238481383044445,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.23616244941949843,
|
|
"num_tokens": 66099430.0,
|
|
"step": 28825
|
|
},
|
|
{
|
|
"entropy": 5.1824564933776855,
|
|
"epoch": 2.7694524495677233,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00042382242721986573,
|
|
"loss": 4.7703,
|
|
"mean_token_accuracy": 0.23234223425388337,
|
|
"num_tokens": 66111060.0,
|
|
"step": 28830
|
|
},
|
|
{
|
|
"entropy": 5.051599311828613,
|
|
"epoch": 2.769932756964457,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00042379671268007207,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.24910002201795578,
|
|
"num_tokens": 66123367.0,
|
|
"step": 28835
|
|
},
|
|
{
|
|
"entropy": 5.154538202285766,
|
|
"epoch": 2.770413064361191,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004237709946856607,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.24736195504665376,
|
|
"num_tokens": 66134198.0,
|
|
"step": 28840
|
|
},
|
|
{
|
|
"entropy": 5.2061018466949465,
|
|
"epoch": 2.770893371757925,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042374527323722836,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.2325848400592804,
|
|
"num_tokens": 66145991.0,
|
|
"step": 28845
|
|
},
|
|
{
|
|
"entropy": 5.2241462707519535,
|
|
"epoch": 2.771373679154659,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00042371954833537263,
|
|
"loss": 4.8667,
|
|
"mean_token_accuracy": 0.22938113808631896,
|
|
"num_tokens": 66157447.0,
|
|
"step": 28850
|
|
},
|
|
{
|
|
"entropy": 5.14521164894104,
|
|
"epoch": 2.7718539865513927,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00042369381998069055,
|
|
"loss": 4.8769,
|
|
"mean_token_accuracy": 0.23516334146261214,
|
|
"num_tokens": 66169259.0,
|
|
"step": 28855
|
|
},
|
|
{
|
|
"entropy": 5.162340831756592,
|
|
"epoch": 2.772334293948127,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004236680881737795,
|
|
"loss": 4.8065,
|
|
"mean_token_accuracy": 0.23693802952766418,
|
|
"num_tokens": 66181221.0,
|
|
"step": 28860
|
|
},
|
|
{
|
|
"entropy": 5.216310596466064,
|
|
"epoch": 2.7728146013448605,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004236423529152369,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.22620050758123397,
|
|
"num_tokens": 66193513.0,
|
|
"step": 28865
|
|
},
|
|
{
|
|
"entropy": 5.170178937911987,
|
|
"epoch": 2.773294908741595,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004236166142056602,
|
|
"loss": 4.7125,
|
|
"mean_token_accuracy": 0.2429742470383644,
|
|
"num_tokens": 66204951.0,
|
|
"step": 28870
|
|
},
|
|
{
|
|
"entropy": 5.12581148147583,
|
|
"epoch": 2.7737752161383287,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004235908720456471,
|
|
"loss": 4.8015,
|
|
"mean_token_accuracy": 0.23830191195011138,
|
|
"num_tokens": 66215845.0,
|
|
"step": 28875
|
|
},
|
|
{
|
|
"entropy": 5.218148851394654,
|
|
"epoch": 2.7742555235350626,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004235651264357951,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.2239104390144348,
|
|
"num_tokens": 66226510.0,
|
|
"step": 28880
|
|
},
|
|
{
|
|
"entropy": 5.1949684619903564,
|
|
"epoch": 2.7747358309317964,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042353937737670206,
|
|
"loss": 4.8358,
|
|
"mean_token_accuracy": 0.23480041027069093,
|
|
"num_tokens": 66238134.0,
|
|
"step": 28885
|
|
},
|
|
{
|
|
"entropy": 5.194104337692261,
|
|
"epoch": 2.7752161383285303,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004235136248689658,
|
|
"loss": 4.8329,
|
|
"mean_token_accuracy": 0.22693195939064026,
|
|
"num_tokens": 66250526.0,
|
|
"step": 28890
|
|
},
|
|
{
|
|
"entropy": 5.277641105651855,
|
|
"epoch": 2.775696445725264,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004234878689131841,
|
|
"loss": 4.8741,
|
|
"mean_token_accuracy": 0.22503982335329056,
|
|
"num_tokens": 66262144.0,
|
|
"step": 28895
|
|
},
|
|
{
|
|
"entropy": 5.280882024765015,
|
|
"epoch": 2.776176753121998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000423462109509955,
|
|
"loss": 4.8886,
|
|
"mean_token_accuracy": 0.2226797178387642,
|
|
"num_tokens": 66273262.0,
|
|
"step": 28900
|
|
},
|
|
{
|
|
"entropy": 5.134186315536499,
|
|
"epoch": 2.776657060518732,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004234363466598765,
|
|
"loss": 4.7759,
|
|
"mean_token_accuracy": 0.24325188100337983,
|
|
"num_tokens": 66284127.0,
|
|
"step": 28905
|
|
},
|
|
{
|
|
"entropy": 5.1410914897918705,
|
|
"epoch": 2.777137367915466,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042341058036354687,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.22835943847894669,
|
|
"num_tokens": 66295092.0,
|
|
"step": 28910
|
|
},
|
|
{
|
|
"entropy": 5.089054775238037,
|
|
"epoch": 2.7776176753121997,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042338481062156424,
|
|
"loss": 4.6737,
|
|
"mean_token_accuracy": 0.24352877140045165,
|
|
"num_tokens": 66306050.0,
|
|
"step": 28915
|
|
},
|
|
{
|
|
"entropy": 5.080532503128052,
|
|
"epoch": 2.7780979827089336,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00042335903743452694,
|
|
"loss": 4.7481,
|
|
"mean_token_accuracy": 0.23705018311738968,
|
|
"num_tokens": 66317186.0,
|
|
"step": 28920
|
|
},
|
|
{
|
|
"entropy": 5.1849480152130125,
|
|
"epoch": 2.7785782901056675,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004233332608030333,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.2305371046066284,
|
|
"num_tokens": 66328486.0,
|
|
"step": 28925
|
|
},
|
|
{
|
|
"entropy": 5.1660661697387695,
|
|
"epoch": 2.7790585975024014,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042330748072768183,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.2436986356973648,
|
|
"num_tokens": 66340649.0,
|
|
"step": 28930
|
|
},
|
|
{
|
|
"entropy": 5.203633737564087,
|
|
"epoch": 2.7795389048991357,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000423281697209071,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.22657889872789383,
|
|
"num_tokens": 66353555.0,
|
|
"step": 28935
|
|
},
|
|
{
|
|
"entropy": 5.270776224136353,
|
|
"epoch": 2.780019212295869,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004232559102477995,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.2240600034594536,
|
|
"num_tokens": 66365445.0,
|
|
"step": 28940
|
|
},
|
|
{
|
|
"entropy": 5.1181457996368405,
|
|
"epoch": 2.7804995196926034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000423230119844466,
|
|
"loss": 4.7387,
|
|
"mean_token_accuracy": 0.24119946211576462,
|
|
"num_tokens": 66377203.0,
|
|
"step": 28945
|
|
},
|
|
{
|
|
"entropy": 5.1762158393859865,
|
|
"epoch": 2.7809798270893373,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004232043259996692,
|
|
"loss": 4.8745,
|
|
"mean_token_accuracy": 0.22531818300485612,
|
|
"num_tokens": 66388637.0,
|
|
"step": 28950
|
|
},
|
|
{
|
|
"entropy": 5.213599395751953,
|
|
"epoch": 2.781460134486071,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004231785287140081,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.2258870095014572,
|
|
"num_tokens": 66400470.0,
|
|
"step": 28955
|
|
},
|
|
{
|
|
"entropy": 5.252213716506958,
|
|
"epoch": 2.781940441882805,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004231527279880816,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.24084632843732834,
|
|
"num_tokens": 66411079.0,
|
|
"step": 28960
|
|
},
|
|
{
|
|
"entropy": 5.180575895309448,
|
|
"epoch": 2.782420749279539,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004231269238224885,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.23096949011087417,
|
|
"num_tokens": 66423706.0,
|
|
"step": 28965
|
|
},
|
|
{
|
|
"entropy": 5.0858009338378904,
|
|
"epoch": 2.782901056676273,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004231011162178282,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.23899709731340407,
|
|
"num_tokens": 66434994.0,
|
|
"step": 28970
|
|
},
|
|
{
|
|
"entropy": 5.143140125274658,
|
|
"epoch": 2.7833813640730067,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004230753051746998,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.24622179120779036,
|
|
"num_tokens": 66446474.0,
|
|
"step": 28975
|
|
},
|
|
{
|
|
"entropy": 5.169672584533691,
|
|
"epoch": 2.7838616714697406,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00042304949069370246,
|
|
"loss": 4.7867,
|
|
"mean_token_accuracy": 0.23226576745510102,
|
|
"num_tokens": 66457633.0,
|
|
"step": 28980
|
|
},
|
|
{
|
|
"entropy": 5.157308292388916,
|
|
"epoch": 2.7843419788664745,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042302367277543553,
|
|
"loss": 4.8108,
|
|
"mean_token_accuracy": 0.23454979062080383,
|
|
"num_tokens": 66468160.0,
|
|
"step": 28985
|
|
},
|
|
{
|
|
"entropy": 5.167266798019409,
|
|
"epoch": 2.7848222862632084,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042299785142049855,
|
|
"loss": 4.8056,
|
|
"mean_token_accuracy": 0.23236972242593765,
|
|
"num_tokens": 66478609.0,
|
|
"step": 28990
|
|
},
|
|
{
|
|
"entropy": 5.18048586845398,
|
|
"epoch": 2.7853025936599423,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004229720266294908,
|
|
"loss": 4.8538,
|
|
"mean_token_accuracy": 0.2298724964261055,
|
|
"num_tokens": 66489992.0,
|
|
"step": 28995
|
|
},
|
|
{
|
|
"entropy": 5.291350650787353,
|
|
"epoch": 2.785782901056676,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000422946198403012,
|
|
"loss": 4.8961,
|
|
"mean_token_accuracy": 0.23051506727933885,
|
|
"num_tokens": 66501331.0,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"entropy": 5.25571985244751,
|
|
"epoch": 2.78626320845341,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004229203667416619,
|
|
"loss": 4.8848,
|
|
"mean_token_accuracy": 0.2300382599234581,
|
|
"num_tokens": 66513336.0,
|
|
"step": 29005
|
|
},
|
|
{
|
|
"entropy": 5.125155353546143,
|
|
"epoch": 2.7867435158501443,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042289453164604,
|
|
"loss": 4.7382,
|
|
"mean_token_accuracy": 0.24149680882692337,
|
|
"num_tokens": 66523577.0,
|
|
"step": 29010
|
|
},
|
|
{
|
|
"entropy": 5.119342184066772,
|
|
"epoch": 2.787223823246878,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004228686931167463,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.22789237946271895,
|
|
"num_tokens": 66536181.0,
|
|
"step": 29015
|
|
},
|
|
{
|
|
"entropy": 5.173925828933716,
|
|
"epoch": 2.787704130643612,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004228428511543806,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.23282485753297805,
|
|
"num_tokens": 66546881.0,
|
|
"step": 29020
|
|
},
|
|
{
|
|
"entropy": 5.2764482498168945,
|
|
"epoch": 2.7881844380403455,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00042281700575954283,
|
|
"loss": 4.9346,
|
|
"mean_token_accuracy": 0.23111527115106584,
|
|
"num_tokens": 66559091.0,
|
|
"step": 29025
|
|
},
|
|
{
|
|
"entropy": 5.219338750839233,
|
|
"epoch": 2.78866474543708,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004227911569328332,
|
|
"loss": 4.8967,
|
|
"mean_token_accuracy": 0.22899060994386672,
|
|
"num_tokens": 66570584.0,
|
|
"step": 29030
|
|
},
|
|
{
|
|
"entropy": 5.181474590301514,
|
|
"epoch": 2.7891450528338138,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004227653046748517,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.23474400639533996,
|
|
"num_tokens": 66581921.0,
|
|
"step": 29035
|
|
},
|
|
{
|
|
"entropy": 5.192089319229126,
|
|
"epoch": 2.7896253602305476,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00042273944898619864,
|
|
"loss": 4.9202,
|
|
"mean_token_accuracy": 0.2281627058982849,
|
|
"num_tokens": 66595132.0,
|
|
"step": 29040
|
|
},
|
|
{
|
|
"entropy": 5.267633962631225,
|
|
"epoch": 2.7901056676272815,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00042271358986747427,
|
|
"loss": 4.8777,
|
|
"mean_token_accuracy": 0.23232050985097885,
|
|
"num_tokens": 66607212.0,
|
|
"step": 29045
|
|
},
|
|
{
|
|
"entropy": 5.224773979187011,
|
|
"epoch": 2.7905859750240154,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00042268772731927895,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.2352380007505417,
|
|
"num_tokens": 66619502.0,
|
|
"step": 29050
|
|
},
|
|
{
|
|
"entropy": 5.1985632419586185,
|
|
"epoch": 2.7910662824207493,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00042266186134221317,
|
|
"loss": 4.8642,
|
|
"mean_token_accuracy": 0.2256588891148567,
|
|
"num_tokens": 66631813.0,
|
|
"step": 29055
|
|
},
|
|
{
|
|
"entropy": 5.245607233047485,
|
|
"epoch": 2.791546589817483,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004226359919368774,
|
|
"loss": 4.9253,
|
|
"mean_token_accuracy": 0.22619607895612717,
|
|
"num_tokens": 66643879.0,
|
|
"step": 29060
|
|
},
|
|
{
|
|
"entropy": 5.268108129501343,
|
|
"epoch": 2.792026897214217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042261011910387224,
|
|
"loss": 4.9032,
|
|
"mean_token_accuracy": 0.2283453583717346,
|
|
"num_tokens": 66656819.0,
|
|
"step": 29065
|
|
},
|
|
{
|
|
"entropy": 5.173039245605469,
|
|
"epoch": 2.792507204610951,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004225842428437985,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.2389233574271202,
|
|
"num_tokens": 66668745.0,
|
|
"step": 29070
|
|
},
|
|
{
|
|
"entropy": 5.158986520767212,
|
|
"epoch": 2.792987512007685,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00042255836315725694,
|
|
"loss": 4.7949,
|
|
"mean_token_accuracy": 0.23683004528284074,
|
|
"num_tokens": 66681620.0,
|
|
"step": 29075
|
|
},
|
|
{
|
|
"entropy": 5.166063451766968,
|
|
"epoch": 2.7934678194044187,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004225324800448483,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.23349505215883254,
|
|
"num_tokens": 66692232.0,
|
|
"step": 29080
|
|
},
|
|
{
|
|
"entropy": 5.121240568161011,
|
|
"epoch": 2.793948126801153,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042250659350717343,
|
|
"loss": 4.774,
|
|
"mean_token_accuracy": 0.2392616391181946,
|
|
"num_tokens": 66703401.0,
|
|
"step": 29085
|
|
},
|
|
{
|
|
"entropy": 5.080190658569336,
|
|
"epoch": 2.7944284341978864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042248070354483354,
|
|
"loss": 4.7075,
|
|
"mean_token_accuracy": 0.24377245604991912,
|
|
"num_tokens": 66714066.0,
|
|
"step": 29090
|
|
},
|
|
{
|
|
"entropy": 5.063272190093994,
|
|
"epoch": 2.7949087415946208,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004224548101584297,
|
|
"loss": 4.6592,
|
|
"mean_token_accuracy": 0.24460198879241943,
|
|
"num_tokens": 66724504.0,
|
|
"step": 29095
|
|
},
|
|
{
|
|
"entropy": 5.193750238418579,
|
|
"epoch": 2.795389048991354,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000422428913348563,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.22496250867843628,
|
|
"num_tokens": 66735772.0,
|
|
"step": 29100
|
|
},
|
|
{
|
|
"entropy": 5.235979604721069,
|
|
"epoch": 2.7958693563880885,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004224030131158346,
|
|
"loss": 4.833,
|
|
"mean_token_accuracy": 0.2319996774196625,
|
|
"num_tokens": 66747956.0,
|
|
"step": 29105
|
|
},
|
|
{
|
|
"entropy": 5.186209583282471,
|
|
"epoch": 2.7963496637848224,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004223771094608461,
|
|
"loss": 4.8713,
|
|
"mean_token_accuracy": 0.233525450527668,
|
|
"num_tokens": 66759112.0,
|
|
"step": 29110
|
|
},
|
|
{
|
|
"entropy": 5.1546190738677975,
|
|
"epoch": 2.7968299711815563,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004223512023841986,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.2340550094842911,
|
|
"num_tokens": 66770927.0,
|
|
"step": 29115
|
|
},
|
|
{
|
|
"entropy": 5.2133277416229244,
|
|
"epoch": 2.79731027857829,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042232529188649374,
|
|
"loss": 4.9035,
|
|
"mean_token_accuracy": 0.23018668889999389,
|
|
"num_tokens": 66781809.0,
|
|
"step": 29120
|
|
},
|
|
{
|
|
"entropy": 5.148280000686645,
|
|
"epoch": 2.797790585975024,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004222993779683331,
|
|
"loss": 4.7903,
|
|
"mean_token_accuracy": 0.23572079092264175,
|
|
"num_tokens": 66793495.0,
|
|
"step": 29125
|
|
},
|
|
{
|
|
"entropy": 5.166997766494751,
|
|
"epoch": 2.798270893371758,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042227346063031837,
|
|
"loss": 4.8063,
|
|
"mean_token_accuracy": 0.23262088745832443,
|
|
"num_tokens": 66804568.0,
|
|
"step": 29130
|
|
},
|
|
{
|
|
"entropy": 5.151519441604615,
|
|
"epoch": 2.798751200768492,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004222475398730511,
|
|
"loss": 4.7637,
|
|
"mean_token_accuracy": 0.2374839887022972,
|
|
"num_tokens": 66816698.0,
|
|
"step": 29135
|
|
},
|
|
{
|
|
"entropy": 5.195838260650635,
|
|
"epoch": 2.7992315081652257,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004222216156971332,
|
|
"loss": 4.8723,
|
|
"mean_token_accuracy": 0.2270650953054428,
|
|
"num_tokens": 66829299.0,
|
|
"step": 29140
|
|
},
|
|
{
|
|
"entropy": 5.0609259605407715,
|
|
"epoch": 2.7997118155619596,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00042219568810316656,
|
|
"loss": 4.6681,
|
|
"mean_token_accuracy": 0.2392285019159317,
|
|
"num_tokens": 66839871.0,
|
|
"step": 29145
|
|
},
|
|
{
|
|
"entropy": 5.267725038528442,
|
|
"epoch": 2.8001921229586935,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004221697570917531,
|
|
"loss": 4.8579,
|
|
"mean_token_accuracy": 0.22908653914928437,
|
|
"num_tokens": 66850368.0,
|
|
"step": 29150
|
|
},
|
|
{
|
|
"entropy": 5.230708599090576,
|
|
"epoch": 2.8006724303554273,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000422143822663495,
|
|
"loss": 4.859,
|
|
"mean_token_accuracy": 0.23203782588243485,
|
|
"num_tokens": 66861067.0,
|
|
"step": 29155
|
|
},
|
|
{
|
|
"entropy": 5.1903173446655275,
|
|
"epoch": 2.8011527377521612,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004221178848189941,
|
|
"loss": 4.9204,
|
|
"mean_token_accuracy": 0.22449685633182526,
|
|
"num_tokens": 66873841.0,
|
|
"step": 29160
|
|
},
|
|
{
|
|
"entropy": 5.2023890018463135,
|
|
"epoch": 2.801633045148895,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042209194355885283,
|
|
"loss": 4.8585,
|
|
"mean_token_accuracy": 0.22427234649658204,
|
|
"num_tokens": 66885042.0,
|
|
"step": 29165
|
|
},
|
|
{
|
|
"entropy": 5.233118677139283,
|
|
"epoch": 2.8021133525456294,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004220659988836734,
|
|
"loss": 4.8385,
|
|
"mean_token_accuracy": 0.23338743597269057,
|
|
"num_tokens": 66897076.0,
|
|
"step": 29170
|
|
},
|
|
{
|
|
"entropy": 5.151754856109619,
|
|
"epoch": 2.802593659942363,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004220400507940582,
|
|
"loss": 4.736,
|
|
"mean_token_accuracy": 0.23444971293210984,
|
|
"num_tokens": 66907879.0,
|
|
"step": 29175
|
|
},
|
|
{
|
|
"entropy": 5.212942314147949,
|
|
"epoch": 2.803073967339097,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042201409929060955,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.22691737860441208,
|
|
"num_tokens": 66920801.0,
|
|
"step": 29180
|
|
},
|
|
{
|
|
"entropy": 5.196306228637695,
|
|
"epoch": 2.803554274735831,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004219881443739301,
|
|
"loss": 4.7555,
|
|
"mean_token_accuracy": 0.23265449702739716,
|
|
"num_tokens": 66931411.0,
|
|
"step": 29185
|
|
},
|
|
{
|
|
"entropy": 5.186198759078979,
|
|
"epoch": 2.804034582132565,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004219621860446225,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.2347521409392357,
|
|
"num_tokens": 66942122.0,
|
|
"step": 29190
|
|
},
|
|
{
|
|
"entropy": 5.168083763122558,
|
|
"epoch": 2.804514889529299,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004219362243032892,
|
|
"loss": 4.8673,
|
|
"mean_token_accuracy": 0.22934019714593887,
|
|
"num_tokens": 66954096.0,
|
|
"step": 29195
|
|
},
|
|
{
|
|
"entropy": 5.228646516799927,
|
|
"epoch": 2.8049951969260327,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00042191025915053323,
|
|
"loss": 4.8959,
|
|
"mean_token_accuracy": 0.2222140535712242,
|
|
"num_tokens": 66965729.0,
|
|
"step": 29200
|
|
},
|
|
{
|
|
"entropy": 5.2434803485870365,
|
|
"epoch": 2.8054755043227666,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042188429058695714,
|
|
"loss": 4.8393,
|
|
"mean_token_accuracy": 0.22501797527074813,
|
|
"num_tokens": 66975819.0,
|
|
"step": 29205
|
|
},
|
|
{
|
|
"entropy": 5.133837032318115,
|
|
"epoch": 2.8059558117195005,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042185831861316406,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.24244081377983093,
|
|
"num_tokens": 66987150.0,
|
|
"step": 29210
|
|
},
|
|
{
|
|
"entropy": 5.1696384906768795,
|
|
"epoch": 2.8064361191162344,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004218323432297568,
|
|
"loss": 4.7835,
|
|
"mean_token_accuracy": 0.22723722606897354,
|
|
"num_tokens": 66999449.0,
|
|
"step": 29215
|
|
},
|
|
{
|
|
"entropy": 5.145774269104004,
|
|
"epoch": 2.8069164265129682,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042180636443733864,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.23628346621990204,
|
|
"num_tokens": 67011256.0,
|
|
"step": 29220
|
|
},
|
|
{
|
|
"entropy": 5.018343544006347,
|
|
"epoch": 2.807396733909702,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042178038223651253,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.24668887108564377,
|
|
"num_tokens": 67021878.0,
|
|
"step": 29225
|
|
},
|
|
{
|
|
"entropy": 5.182019758224487,
|
|
"epoch": 2.807877041306436,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042175439662788195,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.22428189367055892,
|
|
"num_tokens": 67032544.0,
|
|
"step": 29230
|
|
},
|
|
{
|
|
"entropy": 5.167021608352661,
|
|
"epoch": 2.80835734870317,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042172840761204986,
|
|
"loss": 4.8214,
|
|
"mean_token_accuracy": 0.23494331240653993,
|
|
"num_tokens": 67042119.0,
|
|
"step": 29235
|
|
},
|
|
{
|
|
"entropy": 5.204580354690552,
|
|
"epoch": 2.8088376560999038,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004217024151896199,
|
|
"loss": 4.8355,
|
|
"mean_token_accuracy": 0.2394632503390312,
|
|
"num_tokens": 67053126.0,
|
|
"step": 29240
|
|
},
|
|
{
|
|
"entropy": 5.261954402923584,
|
|
"epoch": 2.809317963496638,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042167641936119557,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.22860609740018845,
|
|
"num_tokens": 67063818.0,
|
|
"step": 29245
|
|
},
|
|
{
|
|
"entropy": 5.130444145202636,
|
|
"epoch": 2.8097982708933715,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004216504201273802,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.23639896214008332,
|
|
"num_tokens": 67074477.0,
|
|
"step": 29250
|
|
},
|
|
{
|
|
"entropy": 5.205992412567139,
|
|
"epoch": 2.810278578290106,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004216244174887776,
|
|
"loss": 4.8355,
|
|
"mean_token_accuracy": 0.23213216811418533,
|
|
"num_tokens": 67085920.0,
|
|
"step": 29255
|
|
},
|
|
{
|
|
"entropy": 5.201680612564087,
|
|
"epoch": 2.8107588856868397,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042159841144599145,
|
|
"loss": 4.8748,
|
|
"mean_token_accuracy": 0.23148876428604126,
|
|
"num_tokens": 67097542.0,
|
|
"step": 29260
|
|
},
|
|
{
|
|
"entropy": 5.221301317214966,
|
|
"epoch": 2.8112391930835736,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042157240199962537,
|
|
"loss": 4.8651,
|
|
"mean_token_accuracy": 0.23045103251934052,
|
|
"num_tokens": 67108514.0,
|
|
"step": 29265
|
|
},
|
|
{
|
|
"entropy": 5.17786660194397,
|
|
"epoch": 2.8117195004803075,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004215463891502834,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.24088787734508516,
|
|
"num_tokens": 67120263.0,
|
|
"step": 29270
|
|
},
|
|
{
|
|
"entropy": 5.207084465026855,
|
|
"epoch": 2.8121998078770414,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042152037289856954,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.23551466912031174,
|
|
"num_tokens": 67133607.0,
|
|
"step": 29275
|
|
},
|
|
{
|
|
"entropy": 5.1634971618652346,
|
|
"epoch": 2.8126801152737753,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042149435324508755,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.2358095020055771,
|
|
"num_tokens": 67145452.0,
|
|
"step": 29280
|
|
},
|
|
{
|
|
"entropy": 5.124683952331543,
|
|
"epoch": 2.813160422670509,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004214683301904417,
|
|
"loss": 4.82,
|
|
"mean_token_accuracy": 0.23980697840452195,
|
|
"num_tokens": 67159178.0,
|
|
"step": 29285
|
|
},
|
|
{
|
|
"entropy": 5.292401647567749,
|
|
"epoch": 2.813640730067243,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00042144230373523624,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.2251375809311867,
|
|
"num_tokens": 67171652.0,
|
|
"step": 29290
|
|
},
|
|
{
|
|
"entropy": 5.208017587661743,
|
|
"epoch": 2.814121037463977,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004214162738800753,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.23400747925043106,
|
|
"num_tokens": 67181844.0,
|
|
"step": 29295
|
|
},
|
|
{
|
|
"entropy": 5.156892871856689,
|
|
"epoch": 2.814601344860711,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004213902406255632,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.23549882769584657,
|
|
"num_tokens": 67193156.0,
|
|
"step": 29300
|
|
},
|
|
{
|
|
"entropy": 5.174534463882447,
|
|
"epoch": 2.8150816522574447,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004213642039723044,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.2338573694229126,
|
|
"num_tokens": 67205447.0,
|
|
"step": 29305
|
|
},
|
|
{
|
|
"entropy": 5.2757514953613285,
|
|
"epoch": 2.8155619596541785,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00042133816392090343,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.22771316766738892,
|
|
"num_tokens": 67216101.0,
|
|
"step": 29310
|
|
},
|
|
{
|
|
"entropy": 5.10218997001648,
|
|
"epoch": 2.8160422670509124,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042131212047196484,
|
|
"loss": 4.6288,
|
|
"mean_token_accuracy": 0.24741031974554062,
|
|
"num_tokens": 67226972.0,
|
|
"step": 29315
|
|
},
|
|
{
|
|
"entropy": 5.128326034545898,
|
|
"epoch": 2.8165225744476468,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00042128607362609317,
|
|
"loss": 4.7885,
|
|
"mean_token_accuracy": 0.24051540046930314,
|
|
"num_tokens": 67237968.0,
|
|
"step": 29320
|
|
},
|
|
{
|
|
"entropy": 5.204262161254883,
|
|
"epoch": 2.81700288184438,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042126002338389336,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.22809554934501647,
|
|
"num_tokens": 67250817.0,
|
|
"step": 29325
|
|
},
|
|
{
|
|
"entropy": 5.240609931945801,
|
|
"epoch": 2.8174831892411145,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00042123396974597007,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.23540127873420716,
|
|
"num_tokens": 67261491.0,
|
|
"step": 29330
|
|
},
|
|
{
|
|
"entropy": 5.164694309234619,
|
|
"epoch": 2.817963496637848,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042120791271292823,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.23878257870674133,
|
|
"num_tokens": 67272684.0,
|
|
"step": 29335
|
|
},
|
|
{
|
|
"entropy": 5.163634824752807,
|
|
"epoch": 2.8184438040345823,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042118185228537283,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.23465764671564102,
|
|
"num_tokens": 67284070.0,
|
|
"step": 29340
|
|
},
|
|
{
|
|
"entropy": 5.220658922195435,
|
|
"epoch": 2.818924111431316,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042115578846390884,
|
|
"loss": 4.8956,
|
|
"mean_token_accuracy": 0.22487250715494156,
|
|
"num_tokens": 67296302.0,
|
|
"step": 29345
|
|
},
|
|
{
|
|
"entropy": 5.224685144424439,
|
|
"epoch": 2.81940441882805,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004211297212491414,
|
|
"loss": 4.8451,
|
|
"mean_token_accuracy": 0.23317534625530242,
|
|
"num_tokens": 67307123.0,
|
|
"step": 29350
|
|
},
|
|
{
|
|
"entropy": 5.207588338851929,
|
|
"epoch": 2.819884726224784,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004211036506416759,
|
|
"loss": 4.8288,
|
|
"mean_token_accuracy": 0.23392244726419448,
|
|
"num_tokens": 67318832.0,
|
|
"step": 29355
|
|
},
|
|
{
|
|
"entropy": 5.200908470153808,
|
|
"epoch": 2.820365033621518,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004210775766421173,
|
|
"loss": 4.9063,
|
|
"mean_token_accuracy": 0.23047011494636535,
|
|
"num_tokens": 67329821.0,
|
|
"step": 29360
|
|
},
|
|
{
|
|
"entropy": 5.181852769851685,
|
|
"epoch": 2.8208453410182517,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004210514992510713,
|
|
"loss": 4.7921,
|
|
"mean_token_accuracy": 0.2327391728758812,
|
|
"num_tokens": 67341569.0,
|
|
"step": 29365
|
|
},
|
|
{
|
|
"entropy": 5.24842324256897,
|
|
"epoch": 2.8213256484149856,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004210254184691431,
|
|
"loss": 4.898,
|
|
"mean_token_accuracy": 0.2291034832596779,
|
|
"num_tokens": 67352499.0,
|
|
"step": 29370
|
|
},
|
|
{
|
|
"entropy": 5.149331045150757,
|
|
"epoch": 2.8218059558117194,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042099933429693814,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.23056584298610688,
|
|
"num_tokens": 67363810.0,
|
|
"step": 29375
|
|
},
|
|
{
|
|
"entropy": 5.221974897384643,
|
|
"epoch": 2.8222862632084533,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004209732467350624,
|
|
"loss": 4.893,
|
|
"mean_token_accuracy": 0.23935315310955046,
|
|
"num_tokens": 67374690.0,
|
|
"step": 29380
|
|
},
|
|
{
|
|
"entropy": 5.174096393585205,
|
|
"epoch": 2.822766570605187,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004209471557841212,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.23628099709749223,
|
|
"num_tokens": 67386297.0,
|
|
"step": 29385
|
|
},
|
|
{
|
|
"entropy": 5.143737649917602,
|
|
"epoch": 2.823246878001921,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004209210614447204,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.23394383639097213,
|
|
"num_tokens": 67397544.0,
|
|
"step": 29390
|
|
},
|
|
{
|
|
"entropy": 5.198327589035034,
|
|
"epoch": 2.8237271853986554,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000420894963717466,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.2374086707830429,
|
|
"num_tokens": 67408609.0,
|
|
"step": 29395
|
|
},
|
|
{
|
|
"entropy": 5.204296541213989,
|
|
"epoch": 2.824207492795389,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004208688626029636,
|
|
"loss": 4.8134,
|
|
"mean_token_accuracy": 0.23053475022315978,
|
|
"num_tokens": 67421091.0,
|
|
"step": 29400
|
|
},
|
|
{
|
|
"entropy": 5.202216291427613,
|
|
"epoch": 2.824687800192123,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004208427581018194,
|
|
"loss": 4.8454,
|
|
"mean_token_accuracy": 0.23336973339319228,
|
|
"num_tokens": 67433141.0,
|
|
"step": 29405
|
|
},
|
|
{
|
|
"entropy": 5.250060749053955,
|
|
"epoch": 2.8251681075888566,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004208166502146394,
|
|
"loss": 4.8956,
|
|
"mean_token_accuracy": 0.22568774968385696,
|
|
"num_tokens": 67443646.0,
|
|
"step": 29410
|
|
},
|
|
{
|
|
"entropy": 5.240336322784424,
|
|
"epoch": 2.825648414985591,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042079053894202977,
|
|
"loss": 4.8475,
|
|
"mean_token_accuracy": 0.2344028726220131,
|
|
"num_tokens": 67455783.0,
|
|
"step": 29415
|
|
},
|
|
{
|
|
"entropy": 5.2108134746551515,
|
|
"epoch": 2.826128722382325,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004207644242845968,
|
|
"loss": 4.8145,
|
|
"mean_token_accuracy": 0.23825474530458451,
|
|
"num_tokens": 67467185.0,
|
|
"step": 29420
|
|
},
|
|
{
|
|
"entropy": 5.168216562271118,
|
|
"epoch": 2.8266090297790587,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004207383062429467,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.23379736244678498,
|
|
"num_tokens": 67478740.0,
|
|
"step": 29425
|
|
},
|
|
{
|
|
"entropy": 5.127014207839966,
|
|
"epoch": 2.8270893371757926,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004207121848176858,
|
|
"loss": 4.7837,
|
|
"mean_token_accuracy": 0.24002098739147187,
|
|
"num_tokens": 67490492.0,
|
|
"step": 29430
|
|
},
|
|
{
|
|
"entropy": 5.110888290405273,
|
|
"epoch": 2.8275696445725265,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042068606000942075,
|
|
"loss": 4.7326,
|
|
"mean_token_accuracy": 0.24014897346496583,
|
|
"num_tokens": 67500861.0,
|
|
"step": 29435
|
|
},
|
|
{
|
|
"entropy": 5.178278160095215,
|
|
"epoch": 2.8280499519692603,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042065993181875794,
|
|
"loss": 4.8065,
|
|
"mean_token_accuracy": 0.23329720348119737,
|
|
"num_tokens": 67513577.0,
|
|
"step": 29440
|
|
},
|
|
{
|
|
"entropy": 5.1689847946167,
|
|
"epoch": 2.8285302593659942,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000420633800246304,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.23505962044000625,
|
|
"num_tokens": 67525147.0,
|
|
"step": 29445
|
|
},
|
|
{
|
|
"entropy": 5.17341160774231,
|
|
"epoch": 2.829010566762728,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042060766529266577,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.2325803220272064,
|
|
"num_tokens": 67536183.0,
|
|
"step": 29450
|
|
},
|
|
{
|
|
"entropy": 5.239758491516113,
|
|
"epoch": 2.829490874159462,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042058152695844986,
|
|
"loss": 4.8214,
|
|
"mean_token_accuracy": 0.23572734445333482,
|
|
"num_tokens": 67546868.0,
|
|
"step": 29455
|
|
},
|
|
{
|
|
"entropy": 5.136063194274902,
|
|
"epoch": 2.829971181556196,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042055538524426317,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.2383239284157753,
|
|
"num_tokens": 67557243.0,
|
|
"step": 29460
|
|
},
|
|
{
|
|
"entropy": 5.134432697296143,
|
|
"epoch": 2.8304514889529298,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004205292401507127,
|
|
"loss": 4.8255,
|
|
"mean_token_accuracy": 0.22940812408924102,
|
|
"num_tokens": 67568977.0,
|
|
"step": 29465
|
|
},
|
|
{
|
|
"entropy": 5.147130537033081,
|
|
"epoch": 2.8309317963496636,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004205030916784053,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.23655905276536943,
|
|
"num_tokens": 67581318.0,
|
|
"step": 29470
|
|
},
|
|
{
|
|
"entropy": 5.145619916915893,
|
|
"epoch": 2.8314121037463975,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00042047693982794824,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.2408261626958847,
|
|
"num_tokens": 67592707.0,
|
|
"step": 29475
|
|
},
|
|
{
|
|
"entropy": 5.168356084823609,
|
|
"epoch": 2.831892411143132,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042045078459994854,
|
|
"loss": 4.8041,
|
|
"mean_token_accuracy": 0.23368020802736283,
|
|
"num_tokens": 67602929.0,
|
|
"step": 29480
|
|
},
|
|
{
|
|
"entropy": 5.188101720809937,
|
|
"epoch": 2.8323727185398653,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004204246259950136,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.24091022908687593,
|
|
"num_tokens": 67613049.0,
|
|
"step": 29485
|
|
},
|
|
{
|
|
"entropy": 5.314469575881958,
|
|
"epoch": 2.8328530259365996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042039846401375065,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.22329942286014556,
|
|
"num_tokens": 67623355.0,
|
|
"step": 29490
|
|
},
|
|
{
|
|
"entropy": 5.284983158111572,
|
|
"epoch": 2.8333333333333335,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00042037229865676714,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.23200126141309738,
|
|
"num_tokens": 67634607.0,
|
|
"step": 29495
|
|
},
|
|
{
|
|
"entropy": 5.139189529418945,
|
|
"epoch": 2.8338136407300674,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042034612992467046,
|
|
"loss": 4.7826,
|
|
"mean_token_accuracy": 0.23978570103645325,
|
|
"num_tokens": 67646549.0,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"entropy": 5.087915468215942,
|
|
"epoch": 2.8342939481268012,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004203199578180683,
|
|
"loss": 4.6988,
|
|
"mean_token_accuracy": 0.24484056383371353,
|
|
"num_tokens": 67657785.0,
|
|
"step": 29505
|
|
},
|
|
{
|
|
"entropy": 5.182913589477539,
|
|
"epoch": 2.834774255523535,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004202937823375682,
|
|
"loss": 4.8064,
|
|
"mean_token_accuracy": 0.2382264643907547,
|
|
"num_tokens": 67670415.0,
|
|
"step": 29510
|
|
},
|
|
{
|
|
"entropy": 5.199419832229614,
|
|
"epoch": 2.835254562920269,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004202676034837779,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.2339713916182518,
|
|
"num_tokens": 67682815.0,
|
|
"step": 29515
|
|
},
|
|
{
|
|
"entropy": 5.15564374923706,
|
|
"epoch": 2.835734870317003,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004202414212573052,
|
|
"loss": 4.8077,
|
|
"mean_token_accuracy": 0.23243783116340638,
|
|
"num_tokens": 67693820.0,
|
|
"step": 29520
|
|
},
|
|
{
|
|
"entropy": 5.142180585861206,
|
|
"epoch": 2.8362151777137368,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042021523565875796,
|
|
"loss": 4.8095,
|
|
"mean_token_accuracy": 0.22797807902097703,
|
|
"num_tokens": 67705375.0,
|
|
"step": 29525
|
|
},
|
|
{
|
|
"entropy": 5.238217353820801,
|
|
"epoch": 2.8366954851104706,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004201890466887442,
|
|
"loss": 4.8474,
|
|
"mean_token_accuracy": 0.23222972005605697,
|
|
"num_tokens": 67717549.0,
|
|
"step": 29530
|
|
},
|
|
{
|
|
"entropy": 5.158635377883911,
|
|
"epoch": 2.8371757925072045,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004201628543478718,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.23775016516447067,
|
|
"num_tokens": 67727462.0,
|
|
"step": 29535
|
|
},
|
|
{
|
|
"entropy": 5.147439479827881,
|
|
"epoch": 2.8376560999039384,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000420136658636749,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.2360961690545082,
|
|
"num_tokens": 67740059.0,
|
|
"step": 29540
|
|
},
|
|
{
|
|
"entropy": 5.2256265640258786,
|
|
"epoch": 2.8381364073006723,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004201104595559841,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.23211814761161803,
|
|
"num_tokens": 67751010.0,
|
|
"step": 29545
|
|
},
|
|
{
|
|
"entropy": 5.17496657371521,
|
|
"epoch": 2.838616714697406,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00042008425710618507,
|
|
"loss": 4.8267,
|
|
"mean_token_accuracy": 0.2320425480604172,
|
|
"num_tokens": 67762131.0,
|
|
"step": 29550
|
|
},
|
|
{
|
|
"entropy": 5.183457660675049,
|
|
"epoch": 2.8390970220941405,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00042005805128796043,
|
|
"loss": 4.8592,
|
|
"mean_token_accuracy": 0.24222930669784545,
|
|
"num_tokens": 67773759.0,
|
|
"step": 29555
|
|
},
|
|
{
|
|
"entropy": 5.148909282684326,
|
|
"epoch": 2.839577329490874,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004200318421019186,
|
|
"loss": 4.7367,
|
|
"mean_token_accuracy": 0.239158533513546,
|
|
"num_tokens": 67785009.0,
|
|
"step": 29560
|
|
},
|
|
{
|
|
"entropy": 5.203579950332641,
|
|
"epoch": 2.8400576368876083,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000420005629548668,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.23062448650598527,
|
|
"num_tokens": 67796588.0,
|
|
"step": 29565
|
|
},
|
|
{
|
|
"entropy": 5.187649488449097,
|
|
"epoch": 2.840537944284342,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041997941362881735,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.23429526537656784,
|
|
"num_tokens": 67808777.0,
|
|
"step": 29570
|
|
},
|
|
{
|
|
"entropy": 5.187471532821656,
|
|
"epoch": 2.841018251681076,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004199531943429752,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.23380483388900758,
|
|
"num_tokens": 67818562.0,
|
|
"step": 29575
|
|
},
|
|
{
|
|
"entropy": 5.139521074295044,
|
|
"epoch": 2.84149855907781,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004199269716917502,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.24815360009670256,
|
|
"num_tokens": 67829938.0,
|
|
"step": 29580
|
|
},
|
|
{
|
|
"entropy": 5.200087976455689,
|
|
"epoch": 2.841978866474544,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004199007456757513,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.23218883872032164,
|
|
"num_tokens": 67841735.0,
|
|
"step": 29585
|
|
},
|
|
{
|
|
"entropy": 5.114977121353149,
|
|
"epoch": 2.8424591738712777,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041987451629558743,
|
|
"loss": 4.7493,
|
|
"mean_token_accuracy": 0.239524744451046,
|
|
"num_tokens": 67853545.0,
|
|
"step": 29590
|
|
},
|
|
{
|
|
"entropy": 5.155912303924561,
|
|
"epoch": 2.8429394812680115,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004198482835518674,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.24302093386650087,
|
|
"num_tokens": 67864763.0,
|
|
"step": 29595
|
|
},
|
|
{
|
|
"entropy": 5.222896146774292,
|
|
"epoch": 2.8434197886647454,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004198220474452004,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.23355889320373535,
|
|
"num_tokens": 67875837.0,
|
|
"step": 29600
|
|
},
|
|
{
|
|
"entropy": 5.1685840606689455,
|
|
"epoch": 2.8439000960614793,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004197958079761954,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.23322296440601348,
|
|
"num_tokens": 67887623.0,
|
|
"step": 29605
|
|
},
|
|
{
|
|
"entropy": 5.1443273544311525,
|
|
"epoch": 2.844380403458213,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041976956514546185,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.23964384347200393,
|
|
"num_tokens": 67898883.0,
|
|
"step": 29610
|
|
},
|
|
{
|
|
"entropy": 5.195193099975586,
|
|
"epoch": 2.844860710854947,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041974331895360873,
|
|
"loss": 4.7774,
|
|
"mean_token_accuracy": 0.2446065589785576,
|
|
"num_tokens": 67908871.0,
|
|
"step": 29615
|
|
},
|
|
{
|
|
"entropy": 5.120523262023926,
|
|
"epoch": 2.845341018251681,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004197170694012456,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.23221398442983626,
|
|
"num_tokens": 67920812.0,
|
|
"step": 29620
|
|
},
|
|
{
|
|
"entropy": 5.11143307685852,
|
|
"epoch": 2.845821325648415,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004196908164889818,
|
|
"loss": 4.7603,
|
|
"mean_token_accuracy": 0.23783626705408095,
|
|
"num_tokens": 67931703.0,
|
|
"step": 29625
|
|
},
|
|
{
|
|
"entropy": 5.24814510345459,
|
|
"epoch": 2.846301633045149,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004196645602174269,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.23154794722795485,
|
|
"num_tokens": 67943423.0,
|
|
"step": 29630
|
|
},
|
|
{
|
|
"entropy": 5.221248388290405,
|
|
"epoch": 2.8467819404418826,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00041963830058719046,
|
|
"loss": 4.8538,
|
|
"mean_token_accuracy": 0.22761624604463576,
|
|
"num_tokens": 67954047.0,
|
|
"step": 29635
|
|
},
|
|
{
|
|
"entropy": 5.179180669784546,
|
|
"epoch": 2.847262247838617,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004196120375988822,
|
|
"loss": 4.8209,
|
|
"mean_token_accuracy": 0.23901690691709518,
|
|
"num_tokens": 67964833.0,
|
|
"step": 29640
|
|
},
|
|
{
|
|
"entropy": 5.199791479110718,
|
|
"epoch": 2.8477425552353504,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004195857712531119,
|
|
"loss": 4.8754,
|
|
"mean_token_accuracy": 0.23546901047229768,
|
|
"num_tokens": 67977370.0,
|
|
"step": 29645
|
|
},
|
|
{
|
|
"entropy": 5.227806520462036,
|
|
"epoch": 2.8482228626320847,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004195595015504892,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.23133730739355088,
|
|
"num_tokens": 67988680.0,
|
|
"step": 29650
|
|
},
|
|
{
|
|
"entropy": 5.195487594604492,
|
|
"epoch": 2.8487031700288186,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041953322849162415,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.23242061138153075,
|
|
"num_tokens": 67999927.0,
|
|
"step": 29655
|
|
},
|
|
{
|
|
"entropy": 5.172872638702392,
|
|
"epoch": 2.8491834774255524,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004195069520771268,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.22833628654479982,
|
|
"num_tokens": 68012176.0,
|
|
"step": 29660
|
|
},
|
|
{
|
|
"entropy": 5.232370138168335,
|
|
"epoch": 2.8496637848222863,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041948067230760706,
|
|
"loss": 4.8021,
|
|
"mean_token_accuracy": 0.2348121225833893,
|
|
"num_tokens": 68023561.0,
|
|
"step": 29665
|
|
},
|
|
{
|
|
"entropy": 5.231816959381104,
|
|
"epoch": 2.85014409221902,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041945438918367513,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.22434342801570892,
|
|
"num_tokens": 68035768.0,
|
|
"step": 29670
|
|
},
|
|
{
|
|
"entropy": 5.303016614913941,
|
|
"epoch": 2.850624399615754,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00041942810270594115,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.22487583458423616,
|
|
"num_tokens": 68049414.0,
|
|
"step": 29675
|
|
},
|
|
{
|
|
"entropy": 5.131979703903198,
|
|
"epoch": 2.851104707012488,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004194018128750157,
|
|
"loss": 4.7201,
|
|
"mean_token_accuracy": 0.24324170500040054,
|
|
"num_tokens": 68060743.0,
|
|
"step": 29680
|
|
},
|
|
{
|
|
"entropy": 5.1362629413604735,
|
|
"epoch": 2.851585014409222,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00041937551969150873,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.2356897458434105,
|
|
"num_tokens": 68070525.0,
|
|
"step": 29685
|
|
},
|
|
{
|
|
"entropy": 5.21532974243164,
|
|
"epoch": 2.8520653218059557,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000419349223156031,
|
|
"loss": 4.8422,
|
|
"mean_token_accuracy": 0.23682369142770768,
|
|
"num_tokens": 68082160.0,
|
|
"step": 29690
|
|
},
|
|
{
|
|
"entropy": 5.133152437210083,
|
|
"epoch": 2.8525456292026896,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004193229232691929,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.23625955283641814,
|
|
"num_tokens": 68092473.0,
|
|
"step": 29695
|
|
},
|
|
{
|
|
"entropy": 5.071276044845581,
|
|
"epoch": 2.8530259365994235,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041929662003160504,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.24477774798870086,
|
|
"num_tokens": 68103820.0,
|
|
"step": 29700
|
|
},
|
|
{
|
|
"entropy": 5.107974100112915,
|
|
"epoch": 2.8535062439961574,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041927031344387824,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.2522130623459816,
|
|
"num_tokens": 68116364.0,
|
|
"step": 29705
|
|
},
|
|
{
|
|
"entropy": 5.056685161590576,
|
|
"epoch": 2.8539865513928913,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041924400350662304,
|
|
"loss": 4.6527,
|
|
"mean_token_accuracy": 0.24882728904485701,
|
|
"num_tokens": 68127970.0,
|
|
"step": 29710
|
|
},
|
|
{
|
|
"entropy": 5.1824322700500485,
|
|
"epoch": 2.8544668587896256,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041921769022045045,
|
|
"loss": 4.8587,
|
|
"mean_token_accuracy": 0.2246397078037262,
|
|
"num_tokens": 68139433.0,
|
|
"step": 29715
|
|
},
|
|
{
|
|
"entropy": 5.138696765899658,
|
|
"epoch": 2.854947166186359,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00041919137358597137,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.22812839299440385,
|
|
"num_tokens": 68153169.0,
|
|
"step": 29720
|
|
},
|
|
{
|
|
"entropy": 5.225804805755615,
|
|
"epoch": 2.8554274735830933,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004191650536037967,
|
|
"loss": 4.883,
|
|
"mean_token_accuracy": 0.22738188356161118,
|
|
"num_tokens": 68163899.0,
|
|
"step": 29725
|
|
},
|
|
{
|
|
"entropy": 5.151185607910156,
|
|
"epoch": 2.8559077809798272,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041913873027453756,
|
|
"loss": 4.7071,
|
|
"mean_token_accuracy": 0.2375916287302971,
|
|
"num_tokens": 68175342.0,
|
|
"step": 29730
|
|
},
|
|
{
|
|
"entropy": 5.190003871917725,
|
|
"epoch": 2.856388088376561,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041911240359880517,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.23149916529655457,
|
|
"num_tokens": 68186646.0,
|
|
"step": 29735
|
|
},
|
|
{
|
|
"entropy": 5.098492574691773,
|
|
"epoch": 2.856868395773295,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041908607357721067,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.2388230800628662,
|
|
"num_tokens": 68197464.0,
|
|
"step": 29740
|
|
},
|
|
{
|
|
"entropy": 5.023563098907471,
|
|
"epoch": 2.857348703170029,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041905974021036533,
|
|
"loss": 4.6814,
|
|
"mean_token_accuracy": 0.24572536051273347,
|
|
"num_tokens": 68208846.0,
|
|
"step": 29745
|
|
},
|
|
{
|
|
"entropy": 5.27423505783081,
|
|
"epoch": 2.8578290105667628,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041903340349888065,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.23345862776041032,
|
|
"num_tokens": 68220273.0,
|
|
"step": 29750
|
|
},
|
|
{
|
|
"entropy": 5.2818865299224855,
|
|
"epoch": 2.8583093179634966,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000419007063443368,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.2194827139377594,
|
|
"num_tokens": 68233871.0,
|
|
"step": 29755
|
|
},
|
|
{
|
|
"entropy": 5.173515558242798,
|
|
"epoch": 2.8587896253602305,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041898072004443906,
|
|
"loss": 4.8102,
|
|
"mean_token_accuracy": 0.23273237347602843,
|
|
"num_tokens": 68246155.0,
|
|
"step": 29760
|
|
},
|
|
{
|
|
"entropy": 5.20906925201416,
|
|
"epoch": 2.8592699327569644,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004189543733027052,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.24504492282867432,
|
|
"num_tokens": 68258201.0,
|
|
"step": 29765
|
|
},
|
|
{
|
|
"entropy": 5.1216411113739015,
|
|
"epoch": 2.8597502401536983,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004189280232187783,
|
|
"loss": 4.7318,
|
|
"mean_token_accuracy": 0.23869947344064713,
|
|
"num_tokens": 68270106.0,
|
|
"step": 29770
|
|
},
|
|
{
|
|
"entropy": 5.121942758560181,
|
|
"epoch": 2.860230547550432,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004189016697932701,
|
|
"loss": 4.775,
|
|
"mean_token_accuracy": 0.24146050810813904,
|
|
"num_tokens": 68282549.0,
|
|
"step": 29775
|
|
},
|
|
{
|
|
"entropy": 5.187877130508423,
|
|
"epoch": 2.860710854947166,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004188753130267924,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.23726793229579926,
|
|
"num_tokens": 68294141.0,
|
|
"step": 29780
|
|
},
|
|
{
|
|
"entropy": 5.206736850738525,
|
|
"epoch": 2.8611911623439,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004188489529199572,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.24003143310546876,
|
|
"num_tokens": 68305520.0,
|
|
"step": 29785
|
|
},
|
|
{
|
|
"entropy": 5.142758369445801,
|
|
"epoch": 2.8616714697406342,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00041882258947337637,
|
|
"loss": 4.8267,
|
|
"mean_token_accuracy": 0.23611582368612288,
|
|
"num_tokens": 68317906.0,
|
|
"step": 29790
|
|
},
|
|
{
|
|
"entropy": 5.2088587284088135,
|
|
"epoch": 2.8621517771373677,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041879622268766207,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.23173179030418395,
|
|
"num_tokens": 68328998.0,
|
|
"step": 29795
|
|
},
|
|
{
|
|
"entropy": 5.157630252838135,
|
|
"epoch": 2.862632084534102,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004187698525634266,
|
|
"loss": 4.8082,
|
|
"mean_token_accuracy": 0.23457202166318894,
|
|
"num_tokens": 68341329.0,
|
|
"step": 29800
|
|
},
|
|
{
|
|
"entropy": 5.176769399642945,
|
|
"epoch": 2.863112391930836,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00041874347910128193,
|
|
"loss": 4.8674,
|
|
"mean_token_accuracy": 0.23059642016887666,
|
|
"num_tokens": 68353791.0,
|
|
"step": 29805
|
|
},
|
|
{
|
|
"entropy": 5.178373670578003,
|
|
"epoch": 2.8635926993275698,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004187171023018406,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.23793018460273743,
|
|
"num_tokens": 68365493.0,
|
|
"step": 29810
|
|
},
|
|
{
|
|
"entropy": 5.11832447052002,
|
|
"epoch": 2.8640730067243036,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00041869072216571486,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.24513938277959824,
|
|
"num_tokens": 68377658.0,
|
|
"step": 29815
|
|
},
|
|
{
|
|
"entropy": 5.174359893798828,
|
|
"epoch": 2.8645533141210375,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041866433869351715,
|
|
"loss": 4.7434,
|
|
"mean_token_accuracy": 0.24205548465251922,
|
|
"num_tokens": 68387710.0,
|
|
"step": 29820
|
|
},
|
|
{
|
|
"entropy": 5.262865924835205,
|
|
"epoch": 2.8650336215177714,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004186379518858602,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.2294479489326477,
|
|
"num_tokens": 68400726.0,
|
|
"step": 29825
|
|
},
|
|
{
|
|
"entropy": 5.29531683921814,
|
|
"epoch": 2.8655139289145053,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004186115617433565,
|
|
"loss": 4.977,
|
|
"mean_token_accuracy": 0.2221130073070526,
|
|
"num_tokens": 68413414.0,
|
|
"step": 29830
|
|
},
|
|
{
|
|
"entropy": 5.123077774047852,
|
|
"epoch": 2.865994236311239,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041858516826661876,
|
|
"loss": 4.706,
|
|
"mean_token_accuracy": 0.2431061312556267,
|
|
"num_tokens": 68424834.0,
|
|
"step": 29835
|
|
},
|
|
{
|
|
"entropy": 5.079287433624268,
|
|
"epoch": 2.866474543707973,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00041855877145625974,
|
|
"loss": 4.6765,
|
|
"mean_token_accuracy": 0.2486606240272522,
|
|
"num_tokens": 68437220.0,
|
|
"step": 29840
|
|
},
|
|
{
|
|
"entropy": 5.161103296279907,
|
|
"epoch": 2.866954851104707,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004185323713128924,
|
|
"loss": 4.8847,
|
|
"mean_token_accuracy": 0.23171633780002593,
|
|
"num_tokens": 68449571.0,
|
|
"step": 29845
|
|
},
|
|
{
|
|
"entropy": 5.175662231445313,
|
|
"epoch": 2.867435158501441,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041850596783712956,
|
|
"loss": 4.7495,
|
|
"mean_token_accuracy": 0.233902271091938,
|
|
"num_tokens": 68460592.0,
|
|
"step": 29850
|
|
},
|
|
{
|
|
"entropy": 5.17169680595398,
|
|
"epoch": 2.8679154658981747,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004184795610295843,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.24266376346349716,
|
|
"num_tokens": 68472268.0,
|
|
"step": 29855
|
|
},
|
|
{
|
|
"entropy": 5.1788770198822025,
|
|
"epoch": 2.8683957732949086,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004184531508908697,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.23015254437923433,
|
|
"num_tokens": 68483382.0,
|
|
"step": 29860
|
|
},
|
|
{
|
|
"entropy": 5.175738191604614,
|
|
"epoch": 2.868876080691643,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004184267374215989,
|
|
"loss": 4.824,
|
|
"mean_token_accuracy": 0.24083784222602844,
|
|
"num_tokens": 68494421.0,
|
|
"step": 29865
|
|
},
|
|
{
|
|
"entropy": 5.208910846710205,
|
|
"epoch": 2.8693563880883763,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000418400320622385,
|
|
"loss": 4.8377,
|
|
"mean_token_accuracy": 0.2311741143465042,
|
|
"num_tokens": 68505810.0,
|
|
"step": 29870
|
|
},
|
|
{
|
|
"entropy": 5.048247480392456,
|
|
"epoch": 2.8698366954851107,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004183739004938416,
|
|
"loss": 4.6276,
|
|
"mean_token_accuracy": 0.25459652543067934,
|
|
"num_tokens": 68515632.0,
|
|
"step": 29875
|
|
},
|
|
{
|
|
"entropy": 5.157012939453125,
|
|
"epoch": 2.870317002881844,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000418347477036582,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.23148462325334548,
|
|
"num_tokens": 68526930.0,
|
|
"step": 29880
|
|
},
|
|
{
|
|
"entropy": 5.150242757797241,
|
|
"epoch": 2.8707973102785784,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00041832105025121956,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.24134798645973204,
|
|
"num_tokens": 68537381.0,
|
|
"step": 29885
|
|
},
|
|
{
|
|
"entropy": 5.075560426712036,
|
|
"epoch": 2.8712776176753123,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004182946201383679,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.24558991938829422,
|
|
"num_tokens": 68548982.0,
|
|
"step": 29890
|
|
},
|
|
{
|
|
"entropy": 5.083462142944336,
|
|
"epoch": 2.871757925072046,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004182681866986407,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.23644600957632064,
|
|
"num_tokens": 68560572.0,
|
|
"step": 29895
|
|
},
|
|
{
|
|
"entropy": 5.218330669403076,
|
|
"epoch": 2.87223823246878,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041824174993265165,
|
|
"loss": 4.8117,
|
|
"mean_token_accuracy": 0.2335023209452629,
|
|
"num_tokens": 68572080.0,
|
|
"step": 29900
|
|
},
|
|
{
|
|
"entropy": 5.138706159591675,
|
|
"epoch": 2.872718539865514,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041821530984101444,
|
|
"loss": 4.767,
|
|
"mean_token_accuracy": 0.23450050354003907,
|
|
"num_tokens": 68584481.0,
|
|
"step": 29905
|
|
},
|
|
{
|
|
"entropy": 5.10101637840271,
|
|
"epoch": 2.873198847262248,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000418188866424343,
|
|
"loss": 4.7834,
|
|
"mean_token_accuracy": 0.24725605696439742,
|
|
"num_tokens": 68595673.0,
|
|
"step": 29910
|
|
},
|
|
{
|
|
"entropy": 5.224434328079224,
|
|
"epoch": 2.8736791546589817,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004181624196832513,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.23292853087186813,
|
|
"num_tokens": 68607310.0,
|
|
"step": 29915
|
|
},
|
|
{
|
|
"entropy": 5.153542470932007,
|
|
"epoch": 2.8741594620557156,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041813596961835336,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.2392282724380493,
|
|
"num_tokens": 68618579.0,
|
|
"step": 29920
|
|
},
|
|
{
|
|
"entropy": 5.096701908111572,
|
|
"epoch": 2.8746397694524495,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041810951623026313,
|
|
"loss": 4.6599,
|
|
"mean_token_accuracy": 0.2500207856297493,
|
|
"num_tokens": 68629977.0,
|
|
"step": 29925
|
|
},
|
|
{
|
|
"entropy": 5.187709045410156,
|
|
"epoch": 2.8751200768491834,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041808305951959496,
|
|
"loss": 4.8725,
|
|
"mean_token_accuracy": 0.23013727962970734,
|
|
"num_tokens": 68641740.0,
|
|
"step": 29930
|
|
},
|
|
{
|
|
"entropy": 5.1547736644744875,
|
|
"epoch": 2.8756003842459172,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000418056599486963,
|
|
"loss": 4.8378,
|
|
"mean_token_accuracy": 0.23775057643651962,
|
|
"num_tokens": 68653171.0,
|
|
"step": 29935
|
|
},
|
|
{
|
|
"entropy": 5.182088994979859,
|
|
"epoch": 2.8760806916426516,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004180301361329816,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.23664649277925492,
|
|
"num_tokens": 68664658.0,
|
|
"step": 29940
|
|
},
|
|
{
|
|
"entropy": 5.187310123443604,
|
|
"epoch": 2.876560999039385,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004180036694582651,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.23906238824129106,
|
|
"num_tokens": 68675912.0,
|
|
"step": 29945
|
|
},
|
|
{
|
|
"entropy": 5.137335586547851,
|
|
"epoch": 2.8770413064361193,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041797719946342813,
|
|
"loss": 4.7669,
|
|
"mean_token_accuracy": 0.2431119501590729,
|
|
"num_tokens": 68686586.0,
|
|
"step": 29950
|
|
},
|
|
{
|
|
"entropy": 5.155202102661133,
|
|
"epoch": 2.8775216138328528,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041795072614908503,
|
|
"loss": 4.8194,
|
|
"mean_token_accuracy": 0.22975114732980728,
|
|
"num_tokens": 68698280.0,
|
|
"step": 29955
|
|
},
|
|
{
|
|
"entropy": 5.18602294921875,
|
|
"epoch": 2.878001921229587,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041792424951585055,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.24384418576955796,
|
|
"num_tokens": 68709424.0,
|
|
"step": 29960
|
|
},
|
|
{
|
|
"entropy": 5.215112686157227,
|
|
"epoch": 2.878482228626321,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00041789776956433947,
|
|
"loss": 4.8359,
|
|
"mean_token_accuracy": 0.23994921147823334,
|
|
"num_tokens": 68720785.0,
|
|
"step": 29965
|
|
},
|
|
{
|
|
"entropy": 5.098268747329712,
|
|
"epoch": 2.878962536023055,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041787128629516645,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.23841240704059602,
|
|
"num_tokens": 68732157.0,
|
|
"step": 29970
|
|
},
|
|
{
|
|
"entropy": 5.1257652759552,
|
|
"epoch": 2.8794428434197887,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004178447997089464,
|
|
"loss": 4.8081,
|
|
"mean_token_accuracy": 0.2381267637014389,
|
|
"num_tokens": 68743604.0,
|
|
"step": 29975
|
|
},
|
|
{
|
|
"entropy": 5.172803115844727,
|
|
"epoch": 2.8799231508165226,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004178183098062943,
|
|
"loss": 4.8283,
|
|
"mean_token_accuracy": 0.23289570361375808,
|
|
"num_tokens": 68755056.0,
|
|
"step": 29980
|
|
},
|
|
{
|
|
"entropy": 5.159684753417968,
|
|
"epoch": 2.8804034582132565,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004177918165878251,
|
|
"loss": 4.8295,
|
|
"mean_token_accuracy": 0.2349122568964958,
|
|
"num_tokens": 68766390.0,
|
|
"step": 29985
|
|
},
|
|
{
|
|
"entropy": 5.187057828903198,
|
|
"epoch": 2.8808837656099904,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004177653200541539,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.23430467694997786,
|
|
"num_tokens": 68778780.0,
|
|
"step": 29990
|
|
},
|
|
{
|
|
"entropy": 5.164732122421265,
|
|
"epoch": 2.8813640730067243,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000417738820205896,
|
|
"loss": 4.6989,
|
|
"mean_token_accuracy": 0.24214354753494263,
|
|
"num_tokens": 68789545.0,
|
|
"step": 29995
|
|
},
|
|
{
|
|
"entropy": 5.156518793106079,
|
|
"epoch": 2.881844380403458,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004177123170436665,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.24230390638113022,
|
|
"num_tokens": 68802231.0,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 2.881844380403458,
|
|
"eval_entropy": 5.006742579480139,
|
|
"eval_loss": 4.8893842697143555,
|
|
"eval_mean_token_accuracy": 0.2394054177639936,
|
|
"eval_num_tokens": 68802231.0,
|
|
"eval_runtime": 26.6642,
|
|
"eval_samples_per_second": 1230.674,
|
|
"eval_steps_per_second": 153.839,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"entropy": 5.258435010910034,
|
|
"epoch": 2.882324687800192,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004176858105680807,
|
|
"loss": 4.8814,
|
|
"mean_token_accuracy": 0.2366894081234932,
|
|
"num_tokens": 68812424.0,
|
|
"step": 30005
|
|
},
|
|
{
|
|
"entropy": 5.201403045654297,
|
|
"epoch": 2.882804995196926,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041765930077975415,
|
|
"loss": 4.7509,
|
|
"mean_token_accuracy": 0.23799735605716704,
|
|
"num_tokens": 68823770.0,
|
|
"step": 30010
|
|
},
|
|
{
|
|
"entropy": 5.19072527885437,
|
|
"epoch": 2.88328530259366,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041763278767930213,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.23785564452409744,
|
|
"num_tokens": 68835007.0,
|
|
"step": 30015
|
|
},
|
|
{
|
|
"entropy": 5.088462924957275,
|
|
"epoch": 2.8837656099903937,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004176062712673404,
|
|
"loss": 4.7068,
|
|
"mean_token_accuracy": 0.23358033895492553,
|
|
"num_tokens": 68847070.0,
|
|
"step": 30020
|
|
},
|
|
{
|
|
"entropy": 5.129257869720459,
|
|
"epoch": 2.884245917387128,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004175797515444845,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.23816866129636766,
|
|
"num_tokens": 68857197.0,
|
|
"step": 30025
|
|
},
|
|
{
|
|
"entropy": 5.188799095153809,
|
|
"epoch": 2.8847262247838614,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004175532285113501,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.23118826150894164,
|
|
"num_tokens": 68869719.0,
|
|
"step": 30030
|
|
},
|
|
{
|
|
"entropy": 5.142208051681519,
|
|
"epoch": 2.8852065321805958,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004175267021685531,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.24073195606470107,
|
|
"num_tokens": 68880300.0,
|
|
"step": 30035
|
|
},
|
|
{
|
|
"entropy": 5.114072179794311,
|
|
"epoch": 2.8856868395773296,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00041750017251670926,
|
|
"loss": 4.7484,
|
|
"mean_token_accuracy": 0.23665061593055725,
|
|
"num_tokens": 68892616.0,
|
|
"step": 30040
|
|
},
|
|
{
|
|
"entropy": 5.239190292358399,
|
|
"epoch": 2.8861671469740635,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004174736395564345,
|
|
"loss": 4.9429,
|
|
"mean_token_accuracy": 0.22259667962789537,
|
|
"num_tokens": 68904595.0,
|
|
"step": 30045
|
|
},
|
|
{
|
|
"entropy": 5.192397594451904,
|
|
"epoch": 2.8866474543707974,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041744710328834493,
|
|
"loss": 4.7883,
|
|
"mean_token_accuracy": 0.23803483694791794,
|
|
"num_tokens": 68917036.0,
|
|
"step": 30050
|
|
},
|
|
{
|
|
"entropy": 5.133788776397705,
|
|
"epoch": 2.8871277617675313,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041742056371305665,
|
|
"loss": 4.7758,
|
|
"mean_token_accuracy": 0.23673144578933716,
|
|
"num_tokens": 68928216.0,
|
|
"step": 30055
|
|
},
|
|
{
|
|
"entropy": 5.11666431427002,
|
|
"epoch": 2.887608069164265,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041739402083118576,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.2353200599551201,
|
|
"num_tokens": 68939806.0,
|
|
"step": 30060
|
|
},
|
|
{
|
|
"entropy": 5.13999981880188,
|
|
"epoch": 2.888088376560999,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004173674746433485,
|
|
"loss": 4.7247,
|
|
"mean_token_accuracy": 0.24341085702180862,
|
|
"num_tokens": 68950402.0,
|
|
"step": 30065
|
|
},
|
|
{
|
|
"entropy": 5.172867965698242,
|
|
"epoch": 2.888568683957733,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041734092515016127,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.23447870165109636,
|
|
"num_tokens": 68961472.0,
|
|
"step": 30070
|
|
},
|
|
{
|
|
"entropy": 5.218281650543213,
|
|
"epoch": 2.889048991354467,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00041731437235224036,
|
|
"loss": 4.8869,
|
|
"mean_token_accuracy": 0.23008674383163452,
|
|
"num_tokens": 68972844.0,
|
|
"step": 30075
|
|
},
|
|
{
|
|
"entropy": 5.195930767059326,
|
|
"epoch": 2.8895292987512007,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004172878162502023,
|
|
"loss": 4.877,
|
|
"mean_token_accuracy": 0.22779064029455184,
|
|
"num_tokens": 68985219.0,
|
|
"step": 30080
|
|
},
|
|
{
|
|
"entropy": 5.207902526855468,
|
|
"epoch": 2.8900096061479346,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041726125684466374,
|
|
"loss": 4.8386,
|
|
"mean_token_accuracy": 0.2358989432454109,
|
|
"num_tokens": 68997243.0,
|
|
"step": 30085
|
|
},
|
|
{
|
|
"entropy": 5.27184157371521,
|
|
"epoch": 2.8904899135446684,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004172346941362412,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.23142354488372802,
|
|
"num_tokens": 69008325.0,
|
|
"step": 30090
|
|
},
|
|
{
|
|
"entropy": 5.287092876434326,
|
|
"epoch": 2.8909702209414023,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041720812812555137,
|
|
"loss": 4.9253,
|
|
"mean_token_accuracy": 0.2261146515607834,
|
|
"num_tokens": 69020203.0,
|
|
"step": 30095
|
|
},
|
|
{
|
|
"entropy": 5.119634008407592,
|
|
"epoch": 2.8914505283381366,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004171815588132111,
|
|
"loss": 4.7794,
|
|
"mean_token_accuracy": 0.23745028674602509,
|
|
"num_tokens": 69032538.0,
|
|
"step": 30100
|
|
},
|
|
{
|
|
"entropy": 5.1183020114898685,
|
|
"epoch": 2.89193083573487,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004171549861998372,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.23886434286832808,
|
|
"num_tokens": 69045106.0,
|
|
"step": 30105
|
|
},
|
|
{
|
|
"entropy": 5.1623523235321045,
|
|
"epoch": 2.8924111431316044,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004171284102860467,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.23960015773773194,
|
|
"num_tokens": 69056526.0,
|
|
"step": 30110
|
|
},
|
|
{
|
|
"entropy": 5.187011957168579,
|
|
"epoch": 2.8928914505283383,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004171018310724565,
|
|
"loss": 4.7801,
|
|
"mean_token_accuracy": 0.24208479076623918,
|
|
"num_tokens": 69067497.0,
|
|
"step": 30115
|
|
},
|
|
{
|
|
"entropy": 5.230628824234008,
|
|
"epoch": 2.893371757925072,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004170752485596838,
|
|
"loss": 4.758,
|
|
"mean_token_accuracy": 0.23628327250480652,
|
|
"num_tokens": 69078114.0,
|
|
"step": 30120
|
|
},
|
|
{
|
|
"entropy": 5.111222410202027,
|
|
"epoch": 2.893852065321806,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041704866274834557,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.2363072454929352,
|
|
"num_tokens": 69089329.0,
|
|
"step": 30125
|
|
},
|
|
{
|
|
"entropy": 5.229241275787354,
|
|
"epoch": 2.89433237271854,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00041702207363905933,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.2219257041811943,
|
|
"num_tokens": 69101487.0,
|
|
"step": 30130
|
|
},
|
|
{
|
|
"entropy": 5.16022253036499,
|
|
"epoch": 2.894812680115274,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00041699548123244216,
|
|
"loss": 4.7486,
|
|
"mean_token_accuracy": 0.24018481820821763,
|
|
"num_tokens": 69112297.0,
|
|
"step": 30135
|
|
},
|
|
{
|
|
"entropy": 5.221384572982788,
|
|
"epoch": 2.8952929875120077,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004169688855291116,
|
|
"loss": 4.8783,
|
|
"mean_token_accuracy": 0.23446361273527144,
|
|
"num_tokens": 69123628.0,
|
|
"step": 30140
|
|
},
|
|
{
|
|
"entropy": 5.0424031734466555,
|
|
"epoch": 2.8957732949087416,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004169422865296851,
|
|
"loss": 4.6739,
|
|
"mean_token_accuracy": 0.2424796774983406,
|
|
"num_tokens": 69135040.0,
|
|
"step": 30145
|
|
},
|
|
{
|
|
"entropy": 5.260599279403687,
|
|
"epoch": 2.8962536023054755,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004169156842347802,
|
|
"loss": 4.9125,
|
|
"mean_token_accuracy": 0.22545577585697174,
|
|
"num_tokens": 69146251.0,
|
|
"step": 30150
|
|
},
|
|
{
|
|
"entropy": 5.259523916244507,
|
|
"epoch": 2.8967339097022093,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004168890786450144,
|
|
"loss": 4.9022,
|
|
"mean_token_accuracy": 0.22952253967523575,
|
|
"num_tokens": 69157040.0,
|
|
"step": 30155
|
|
},
|
|
{
|
|
"entropy": 5.20241756439209,
|
|
"epoch": 2.8972142170989432,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004168624697610056,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.24074947386980056,
|
|
"num_tokens": 69167330.0,
|
|
"step": 30160
|
|
},
|
|
{
|
|
"entropy": 5.095981168746948,
|
|
"epoch": 2.897694524495677,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041683585758337156,
|
|
"loss": 4.7097,
|
|
"mean_token_accuracy": 0.24774350672960282,
|
|
"num_tokens": 69177903.0,
|
|
"step": 30165
|
|
},
|
|
{
|
|
"entropy": 5.070072650909424,
|
|
"epoch": 2.898174831892411,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004168092421127299,
|
|
"loss": 4.7443,
|
|
"mean_token_accuracy": 0.23679446280002595,
|
|
"num_tokens": 69189946.0,
|
|
"step": 30170
|
|
},
|
|
{
|
|
"entropy": 5.0753203392028805,
|
|
"epoch": 2.8986551392891453,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004167826233496989,
|
|
"loss": 4.6867,
|
|
"mean_token_accuracy": 0.24961072951555252,
|
|
"num_tokens": 69201393.0,
|
|
"step": 30175
|
|
},
|
|
{
|
|
"entropy": 5.180638408660888,
|
|
"epoch": 2.8991354466858787,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004167560012948963,
|
|
"loss": 4.8562,
|
|
"mean_token_accuracy": 0.22634712010622024,
|
|
"num_tokens": 69213894.0,
|
|
"step": 30180
|
|
},
|
|
{
|
|
"entropy": 5.201881551742554,
|
|
"epoch": 2.899615754082613,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00041672937594894034,
|
|
"loss": 4.8171,
|
|
"mean_token_accuracy": 0.23564327359199524,
|
|
"num_tokens": 69224798.0,
|
|
"step": 30185
|
|
},
|
|
{
|
|
"entropy": 5.207663488388062,
|
|
"epoch": 2.9000960614793465,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041670274731244903,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.23682291209697723,
|
|
"num_tokens": 69235893.0,
|
|
"step": 30190
|
|
},
|
|
{
|
|
"entropy": 5.085102081298828,
|
|
"epoch": 2.900576368876081,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004166761153860408,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.24710213541984558,
|
|
"num_tokens": 69246554.0,
|
|
"step": 30195
|
|
},
|
|
{
|
|
"entropy": 5.117585325241089,
|
|
"epoch": 2.9010566762728147,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00041664948017033383,
|
|
"loss": 4.7729,
|
|
"mean_token_accuracy": 0.24210695028305054,
|
|
"num_tokens": 69259232.0,
|
|
"step": 30200
|
|
},
|
|
{
|
|
"entropy": 5.128939294815064,
|
|
"epoch": 2.9015369836695486,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004166228416659465,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.24386627674102784,
|
|
"num_tokens": 69270143.0,
|
|
"step": 30205
|
|
},
|
|
{
|
|
"entropy": 5.168006420135498,
|
|
"epoch": 2.9020172910662825,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041659619987349734,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.24158162921667098,
|
|
"num_tokens": 69280702.0,
|
|
"step": 30210
|
|
},
|
|
{
|
|
"entropy": 5.197195053100586,
|
|
"epoch": 2.9024975984630164,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041656955479360487,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.23452521115541458,
|
|
"num_tokens": 69292605.0,
|
|
"step": 30215
|
|
},
|
|
{
|
|
"entropy": 5.122607564926147,
|
|
"epoch": 2.9029779058597502,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004165429064268877,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.23719628155231476,
|
|
"num_tokens": 69303243.0,
|
|
"step": 30220
|
|
},
|
|
{
|
|
"entropy": 5.166919326782226,
|
|
"epoch": 2.903458213256484,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004165162547739646,
|
|
"loss": 4.8394,
|
|
"mean_token_accuracy": 0.23166919499635696,
|
|
"num_tokens": 69315059.0,
|
|
"step": 30225
|
|
},
|
|
{
|
|
"entropy": 5.197614002227783,
|
|
"epoch": 2.903938520653218,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004164895998354542,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.23075097799301147,
|
|
"num_tokens": 69327338.0,
|
|
"step": 30230
|
|
},
|
|
{
|
|
"entropy": 5.212221384048462,
|
|
"epoch": 2.904418828049952,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004164629416119755,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.23588002771139144,
|
|
"num_tokens": 69339955.0,
|
|
"step": 30235
|
|
},
|
|
{
|
|
"entropy": 5.21528263092041,
|
|
"epoch": 2.9048991354466858,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041643628010414735,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.2338453158736229,
|
|
"num_tokens": 69350847.0,
|
|
"step": 30240
|
|
},
|
|
{
|
|
"entropy": 5.163480472564697,
|
|
"epoch": 2.9053794428434196,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041640961531258877,
|
|
"loss": 4.7712,
|
|
"mean_token_accuracy": 0.23499837517738342,
|
|
"num_tokens": 69362066.0,
|
|
"step": 30245
|
|
},
|
|
{
|
|
"entropy": 5.09740571975708,
|
|
"epoch": 2.905859750240154,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004163829472379187,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.23670259565114976,
|
|
"num_tokens": 69373239.0,
|
|
"step": 30250
|
|
},
|
|
{
|
|
"entropy": 5.159323692321777,
|
|
"epoch": 2.9063400576368874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041635627588075655,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.23854222446680068,
|
|
"num_tokens": 69384094.0,
|
|
"step": 30255
|
|
},
|
|
{
|
|
"entropy": 5.118864631652832,
|
|
"epoch": 2.9068203650336217,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004163296012417213,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.2403934493660927,
|
|
"num_tokens": 69394667.0,
|
|
"step": 30260
|
|
},
|
|
{
|
|
"entropy": 5.171692371368408,
|
|
"epoch": 2.907300672430355,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041630292332143245,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.23907336741685867,
|
|
"num_tokens": 69405146.0,
|
|
"step": 30265
|
|
},
|
|
{
|
|
"entropy": 5.19437050819397,
|
|
"epoch": 2.9077809798270895,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004162762421205093,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.2365285724401474,
|
|
"num_tokens": 69416147.0,
|
|
"step": 30270
|
|
},
|
|
{
|
|
"entropy": 5.166696214675904,
|
|
"epoch": 2.9082612872238234,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041624955763957134,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.24138064235448836,
|
|
"num_tokens": 69426065.0,
|
|
"step": 30275
|
|
},
|
|
{
|
|
"entropy": 5.100807332992554,
|
|
"epoch": 2.9087415946205573,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004162228698792381,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.24514464884996415,
|
|
"num_tokens": 69437266.0,
|
|
"step": 30280
|
|
},
|
|
{
|
|
"entropy": 5.180440950393677,
|
|
"epoch": 2.909221902017291,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041619617884012904,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.24235093593597412,
|
|
"num_tokens": 69449539.0,
|
|
"step": 30285
|
|
},
|
|
{
|
|
"entropy": 5.22049765586853,
|
|
"epoch": 2.909702209414025,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004161694845228641,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.23226125538349152,
|
|
"num_tokens": 69460515.0,
|
|
"step": 30290
|
|
},
|
|
{
|
|
"entropy": 5.224125051498413,
|
|
"epoch": 2.910182516810759,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004161427869280628,
|
|
"loss": 4.9151,
|
|
"mean_token_accuracy": 0.23495280295610427,
|
|
"num_tokens": 69472997.0,
|
|
"step": 30295
|
|
},
|
|
{
|
|
"entropy": 5.222141218185425,
|
|
"epoch": 2.910662824207493,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00041611608605634517,
|
|
"loss": 4.8673,
|
|
"mean_token_accuracy": 0.2303227648139,
|
|
"num_tokens": 69485118.0,
|
|
"step": 30300
|
|
},
|
|
{
|
|
"entropy": 5.161869907379151,
|
|
"epoch": 2.9111431316042267,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000416089381908331,
|
|
"loss": 4.7991,
|
|
"mean_token_accuracy": 0.23488334715366363,
|
|
"num_tokens": 69495696.0,
|
|
"step": 30305
|
|
},
|
|
{
|
|
"entropy": 5.109068584442139,
|
|
"epoch": 2.9116234390009605,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004160626744846404,
|
|
"loss": 4.6581,
|
|
"mean_token_accuracy": 0.24787424206733705,
|
|
"num_tokens": 69507832.0,
|
|
"step": 30310
|
|
},
|
|
{
|
|
"entropy": 5.181776094436645,
|
|
"epoch": 2.9121037463976944,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004160359637858933,
|
|
"loss": 4.8692,
|
|
"mean_token_accuracy": 0.227865569293499,
|
|
"num_tokens": 69520180.0,
|
|
"step": 30315
|
|
},
|
|
{
|
|
"entropy": 5.132340764999389,
|
|
"epoch": 2.9125840537944283,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041600924981270997,
|
|
"loss": 4.7453,
|
|
"mean_token_accuracy": 0.24370963871479034,
|
|
"num_tokens": 69531201.0,
|
|
"step": 30320
|
|
},
|
|
{
|
|
"entropy": 5.211927032470703,
|
|
"epoch": 2.913064361191162,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00041598253256571057,
|
|
"loss": 4.8359,
|
|
"mean_token_accuracy": 0.23639008551836013,
|
|
"num_tokens": 69542552.0,
|
|
"step": 30325
|
|
},
|
|
{
|
|
"entropy": 5.182415103912353,
|
|
"epoch": 2.913544668587896,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004159558120455154,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.23729271292686463,
|
|
"num_tokens": 69554424.0,
|
|
"step": 30330
|
|
},
|
|
{
|
|
"entropy": 5.045497417449951,
|
|
"epoch": 2.9140249759846304,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004159290882527448,
|
|
"loss": 4.6371,
|
|
"mean_token_accuracy": 0.2521500289440155,
|
|
"num_tokens": 69565043.0,
|
|
"step": 30335
|
|
},
|
|
{
|
|
"entropy": 5.127642869949341,
|
|
"epoch": 2.914505283381364,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004159023611880192,
|
|
"loss": 4.7767,
|
|
"mean_token_accuracy": 0.23553356677293777,
|
|
"num_tokens": 69576734.0,
|
|
"step": 30340
|
|
},
|
|
{
|
|
"entropy": 5.208169603347779,
|
|
"epoch": 2.914985590778098,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004158756308519592,
|
|
"loss": 4.7949,
|
|
"mean_token_accuracy": 0.23422856032848358,
|
|
"num_tokens": 69588565.0,
|
|
"step": 30345
|
|
},
|
|
{
|
|
"entropy": 5.176501750946045,
|
|
"epoch": 2.915465898174832,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00041584889724518545,
|
|
"loss": 4.8095,
|
|
"mean_token_accuracy": 0.2432440146803856,
|
|
"num_tokens": 69600595.0,
|
|
"step": 30350
|
|
},
|
|
{
|
|
"entropy": 5.103567600250244,
|
|
"epoch": 2.915946205571566,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00041582216036831844,
|
|
"loss": 4.6855,
|
|
"mean_token_accuracy": 0.249041286110878,
|
|
"num_tokens": 69611091.0,
|
|
"step": 30355
|
|
},
|
|
{
|
|
"entropy": 5.23740782737732,
|
|
"epoch": 2.9164265129683,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000415795420221979,
|
|
"loss": 4.861,
|
|
"mean_token_accuracy": 0.23419079929590225,
|
|
"num_tokens": 69621882.0,
|
|
"step": 30360
|
|
},
|
|
{
|
|
"entropy": 5.222881269454956,
|
|
"epoch": 2.9169068203650337,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041576867680678803,
|
|
"loss": 4.7869,
|
|
"mean_token_accuracy": 0.23136445134878159,
|
|
"num_tokens": 69634673.0,
|
|
"step": 30365
|
|
},
|
|
{
|
|
"entropy": 5.150103902816772,
|
|
"epoch": 2.9173871277617676,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004157419301233664,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.23304531574249268,
|
|
"num_tokens": 69644950.0,
|
|
"step": 30370
|
|
},
|
|
{
|
|
"entropy": 5.154030752182007,
|
|
"epoch": 2.9178674351585014,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041571518017233505,
|
|
"loss": 4.8016,
|
|
"mean_token_accuracy": 0.23984937816858293,
|
|
"num_tokens": 69656750.0,
|
|
"step": 30375
|
|
},
|
|
{
|
|
"entropy": 5.229638624191284,
|
|
"epoch": 2.9183477425552353,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004156884269543151,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.2426661878824234,
|
|
"num_tokens": 69667945.0,
|
|
"step": 30380
|
|
},
|
|
{
|
|
"entropy": 5.180156803131103,
|
|
"epoch": 2.918828049951969,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004156616704699275,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.23562555760145187,
|
|
"num_tokens": 69679995.0,
|
|
"step": 30385
|
|
},
|
|
{
|
|
"entropy": 5.119556617736817,
|
|
"epoch": 2.919308357348703,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041563491071979375,
|
|
"loss": 4.7761,
|
|
"mean_token_accuracy": 0.24115033745765685,
|
|
"num_tokens": 69691029.0,
|
|
"step": 30390
|
|
},
|
|
{
|
|
"entropy": 5.142963504791259,
|
|
"epoch": 2.919788664745437,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00041560814770453495,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.24253900945186616,
|
|
"num_tokens": 69702497.0,
|
|
"step": 30395
|
|
},
|
|
{
|
|
"entropy": 5.1728040218353275,
|
|
"epoch": 2.920268972142171,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041558138142477235,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.23208773732185364,
|
|
"num_tokens": 69713127.0,
|
|
"step": 30400
|
|
},
|
|
{
|
|
"entropy": 5.18835129737854,
|
|
"epoch": 2.9207492795389047,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041555461188112763,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.23705886900424958,
|
|
"num_tokens": 69725314.0,
|
|
"step": 30405
|
|
},
|
|
{
|
|
"entropy": 5.090746259689331,
|
|
"epoch": 2.921229586935639,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041552783907422217,
|
|
"loss": 4.6929,
|
|
"mean_token_accuracy": 0.24249991476535798,
|
|
"num_tokens": 69736696.0,
|
|
"step": 30410
|
|
},
|
|
{
|
|
"entropy": 5.1320164680480955,
|
|
"epoch": 2.9217098943323725,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004155010630046775,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.2386457785964012,
|
|
"num_tokens": 69748639.0,
|
|
"step": 30415
|
|
},
|
|
{
|
|
"entropy": 5.206455183029175,
|
|
"epoch": 2.922190201729107,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004154742836731155,
|
|
"loss": 4.8554,
|
|
"mean_token_accuracy": 0.23460814356803894,
|
|
"num_tokens": 69760124.0,
|
|
"step": 30420
|
|
},
|
|
{
|
|
"entropy": 5.136847496032715,
|
|
"epoch": 2.9226705091258407,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004154475010801576,
|
|
"loss": 4.7973,
|
|
"mean_token_accuracy": 0.2423509582877159,
|
|
"num_tokens": 69772280.0,
|
|
"step": 30425
|
|
},
|
|
{
|
|
"entropy": 5.159572505950928,
|
|
"epoch": 2.9231508165225746,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041542071522642583,
|
|
"loss": 4.792,
|
|
"mean_token_accuracy": 0.23335715979337693,
|
|
"num_tokens": 69784308.0,
|
|
"step": 30430
|
|
},
|
|
{
|
|
"entropy": 5.191873788833618,
|
|
"epoch": 2.9236311239193085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004153939261125421,
|
|
"loss": 4.8368,
|
|
"mean_token_accuracy": 0.23065870702266694,
|
|
"num_tokens": 69795761.0,
|
|
"step": 30435
|
|
},
|
|
{
|
|
"entropy": 5.107944440841675,
|
|
"epoch": 2.9241114313160423,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004153671337391281,
|
|
"loss": 4.6666,
|
|
"mean_token_accuracy": 0.25203706622123717,
|
|
"num_tokens": 69805581.0,
|
|
"step": 30440
|
|
},
|
|
{
|
|
"entropy": 5.150821018218994,
|
|
"epoch": 2.9245917387127762,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004153403381068062,
|
|
"loss": 4.7839,
|
|
"mean_token_accuracy": 0.23631372451782226,
|
|
"num_tokens": 69816593.0,
|
|
"step": 30445
|
|
},
|
|
{
|
|
"entropy": 5.124134922027588,
|
|
"epoch": 2.92507204610951,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041531353921619833,
|
|
"loss": 4.7821,
|
|
"mean_token_accuracy": 0.23950306177139283,
|
|
"num_tokens": 69828424.0,
|
|
"step": 30450
|
|
},
|
|
{
|
|
"entropy": 5.17933030128479,
|
|
"epoch": 2.925552353506244,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004152867370679267,
|
|
"loss": 4.749,
|
|
"mean_token_accuracy": 0.23682328760623933,
|
|
"num_tokens": 69839250.0,
|
|
"step": 30455
|
|
},
|
|
{
|
|
"entropy": 5.137775516510009,
|
|
"epoch": 2.926032660902978,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041525993166261366,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.2440867841243744,
|
|
"num_tokens": 69850910.0,
|
|
"step": 30460
|
|
},
|
|
{
|
|
"entropy": 5.155823802947998,
|
|
"epoch": 2.9265129682997117,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004152331230008814,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.23658701330423354,
|
|
"num_tokens": 69863048.0,
|
|
"step": 30465
|
|
},
|
|
{
|
|
"entropy": 5.205382776260376,
|
|
"epoch": 2.9269932756964456,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041520631108335254,
|
|
"loss": 4.8352,
|
|
"mean_token_accuracy": 0.23379142731428146,
|
|
"num_tokens": 69873512.0,
|
|
"step": 30470
|
|
},
|
|
{
|
|
"entropy": 5.251008081436157,
|
|
"epoch": 2.9274735830931795,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004151794959106494,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.22680544555187226,
|
|
"num_tokens": 69884813.0,
|
|
"step": 30475
|
|
},
|
|
{
|
|
"entropy": 5.171332550048828,
|
|
"epoch": 2.9279538904899134,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004151526774833947,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.24088313728570937,
|
|
"num_tokens": 69896832.0,
|
|
"step": 30480
|
|
},
|
|
{
|
|
"entropy": 5.158399391174316,
|
|
"epoch": 2.9284341978866477,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00041512585580221086,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.24667361825704576,
|
|
"num_tokens": 69908181.0,
|
|
"step": 30485
|
|
},
|
|
{
|
|
"entropy": 5.1982346534729,
|
|
"epoch": 2.928914505283381,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004150990308677208,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.23165930807590485,
|
|
"num_tokens": 69918839.0,
|
|
"step": 30490
|
|
},
|
|
{
|
|
"entropy": 5.210438013076782,
|
|
"epoch": 2.9293948126801155,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041507220268054737,
|
|
"loss": 4.8709,
|
|
"mean_token_accuracy": 0.23225441426038743,
|
|
"num_tokens": 69929637.0,
|
|
"step": 30495
|
|
},
|
|
{
|
|
"entropy": 5.19804048538208,
|
|
"epoch": 2.929875120076849,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004150453712413131,
|
|
"loss": 4.8119,
|
|
"mean_token_accuracy": 0.23361691683530808,
|
|
"num_tokens": 69940202.0,
|
|
"step": 30500
|
|
},
|
|
{
|
|
"entropy": 5.2022068977355955,
|
|
"epoch": 2.9303554274735832,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041501853655064134,
|
|
"loss": 4.7475,
|
|
"mean_token_accuracy": 0.23508015722036363,
|
|
"num_tokens": 69951049.0,
|
|
"step": 30505
|
|
},
|
|
{
|
|
"entropy": 5.138336563110352,
|
|
"epoch": 2.930835734870317,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004149916986091548,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.23355031311511992,
|
|
"num_tokens": 69962950.0,
|
|
"step": 30510
|
|
},
|
|
{
|
|
"entropy": 5.18893084526062,
|
|
"epoch": 2.931316042267051,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004149648574174768,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.23119191825389862,
|
|
"num_tokens": 69974961.0,
|
|
"step": 30515
|
|
},
|
|
{
|
|
"entropy": 5.246787643432617,
|
|
"epoch": 2.931796349663785,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004149380129762304,
|
|
"loss": 4.7699,
|
|
"mean_token_accuracy": 0.24275948703289033,
|
|
"num_tokens": 69985184.0,
|
|
"step": 30520
|
|
},
|
|
{
|
|
"entropy": 5.060419225692749,
|
|
"epoch": 2.9322766570605188,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004149111652860389,
|
|
"loss": 4.6735,
|
|
"mean_token_accuracy": 0.24692427664995192,
|
|
"num_tokens": 69996773.0,
|
|
"step": 30525
|
|
},
|
|
{
|
|
"entropy": 5.226261949539184,
|
|
"epoch": 2.9327569644572526,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004148843143475255,
|
|
"loss": 4.7969,
|
|
"mean_token_accuracy": 0.23626272827386857,
|
|
"num_tokens": 70008834.0,
|
|
"step": 30530
|
|
},
|
|
{
|
|
"entropy": 5.164511585235596,
|
|
"epoch": 2.9332372718539865,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004148574601613137,
|
|
"loss": 4.7381,
|
|
"mean_token_accuracy": 0.23919579833745958,
|
|
"num_tokens": 70019708.0,
|
|
"step": 30535
|
|
},
|
|
{
|
|
"entropy": 5.244851207733154,
|
|
"epoch": 2.9337175792507204,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004148306027280271,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.22539777904748917,
|
|
"num_tokens": 70029680.0,
|
|
"step": 30540
|
|
},
|
|
{
|
|
"entropy": 5.099228572845459,
|
|
"epoch": 2.9341978866474543,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00041480374204828896,
|
|
"loss": 4.7278,
|
|
"mean_token_accuracy": 0.24278710931539535,
|
|
"num_tokens": 70041473.0,
|
|
"step": 30545
|
|
},
|
|
{
|
|
"entropy": 5.194138717651367,
|
|
"epoch": 2.934678194044188,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041477687812272314,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.2346867337822914,
|
|
"num_tokens": 70051646.0,
|
|
"step": 30550
|
|
},
|
|
{
|
|
"entropy": 5.216246891021728,
|
|
"epoch": 2.935158501440922,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041475001095195324,
|
|
"loss": 4.8288,
|
|
"mean_token_accuracy": 0.22900230884552003,
|
|
"num_tokens": 70063795.0,
|
|
"step": 30555
|
|
},
|
|
{
|
|
"entropy": 5.207636737823487,
|
|
"epoch": 2.9356388088376564,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004147231405366031,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.2389038994908333,
|
|
"num_tokens": 70074481.0,
|
|
"step": 30560
|
|
},
|
|
{
|
|
"entropy": 5.107990169525147,
|
|
"epoch": 2.93611911623439,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004146962668772965,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.24161197394132614,
|
|
"num_tokens": 70085939.0,
|
|
"step": 30565
|
|
},
|
|
{
|
|
"entropy": 5.15210542678833,
|
|
"epoch": 2.936599423631124,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00041466938997465744,
|
|
"loss": 4.8226,
|
|
"mean_token_accuracy": 0.23923008292913436,
|
|
"num_tokens": 70097466.0,
|
|
"step": 30570
|
|
},
|
|
{
|
|
"entropy": 5.1324913024902346,
|
|
"epoch": 2.9370797310278576,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041464250982930974,
|
|
"loss": 4.728,
|
|
"mean_token_accuracy": 0.2411188080906868,
|
|
"num_tokens": 70109720.0,
|
|
"step": 30575
|
|
},
|
|
{
|
|
"entropy": 5.25372314453125,
|
|
"epoch": 2.937560038424592,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041461562644187777,
|
|
"loss": 4.8931,
|
|
"mean_token_accuracy": 0.23464643210172653,
|
|
"num_tokens": 70121101.0,
|
|
"step": 30580
|
|
},
|
|
{
|
|
"entropy": 5.213743257522583,
|
|
"epoch": 2.938040345821326,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041458873981298547,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.24090914726257323,
|
|
"num_tokens": 70131512.0,
|
|
"step": 30585
|
|
},
|
|
{
|
|
"entropy": 5.191576623916626,
|
|
"epoch": 2.9385206532180597,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041456184994325714,
|
|
"loss": 4.8791,
|
|
"mean_token_accuracy": 0.23130532801151277,
|
|
"num_tokens": 70142873.0,
|
|
"step": 30590
|
|
},
|
|
{
|
|
"entropy": 5.2010252475738525,
|
|
"epoch": 2.9390009606147935,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041453495683331694,
|
|
"loss": 4.8271,
|
|
"mean_token_accuracy": 0.23024224638938903,
|
|
"num_tokens": 70154476.0,
|
|
"step": 30595
|
|
},
|
|
{
|
|
"entropy": 5.278477716445923,
|
|
"epoch": 2.9394812680115274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041450806048378954,
|
|
"loss": 4.8498,
|
|
"mean_token_accuracy": 0.23563790768384935,
|
|
"num_tokens": 70165439.0,
|
|
"step": 30600
|
|
},
|
|
{
|
|
"entropy": 5.174014854431152,
|
|
"epoch": 2.9399615754082613,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004144811608952992,
|
|
"loss": 4.801,
|
|
"mean_token_accuracy": 0.2327744573354721,
|
|
"num_tokens": 70176515.0,
|
|
"step": 30605
|
|
},
|
|
{
|
|
"entropy": 5.136973428726196,
|
|
"epoch": 2.940441882804995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041445425806847043,
|
|
"loss": 4.7683,
|
|
"mean_token_accuracy": 0.239946411550045,
|
|
"num_tokens": 70189064.0,
|
|
"step": 30610
|
|
},
|
|
{
|
|
"entropy": 5.110017585754394,
|
|
"epoch": 2.940922190201729,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041442735200392783,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.23538936525583268,
|
|
"num_tokens": 70200984.0,
|
|
"step": 30615
|
|
},
|
|
{
|
|
"entropy": 5.0751220703125,
|
|
"epoch": 2.941402497598463,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004144004427022962,
|
|
"loss": 4.7547,
|
|
"mean_token_accuracy": 0.23452960848808288,
|
|
"num_tokens": 70212071.0,
|
|
"step": 30620
|
|
},
|
|
{
|
|
"entropy": 5.218735599517823,
|
|
"epoch": 2.941882804995197,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041437353016420025,
|
|
"loss": 4.872,
|
|
"mean_token_accuracy": 0.23390315622091293,
|
|
"num_tokens": 70223395.0,
|
|
"step": 30625
|
|
},
|
|
{
|
|
"entropy": 5.176876544952393,
|
|
"epoch": 2.9423631123919307,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004143466143902648,
|
|
"loss": 4.6793,
|
|
"mean_token_accuracy": 0.2430490419268608,
|
|
"num_tokens": 70233130.0,
|
|
"step": 30630
|
|
},
|
|
{
|
|
"entropy": 5.16585955619812,
|
|
"epoch": 2.9428434197886646,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041431969538111463,
|
|
"loss": 4.8603,
|
|
"mean_token_accuracy": 0.2301809936761856,
|
|
"num_tokens": 70245227.0,
|
|
"step": 30635
|
|
},
|
|
{
|
|
"entropy": 5.176884174346924,
|
|
"epoch": 2.9433237271853985,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004142927731373749,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.2385750398039818,
|
|
"num_tokens": 70256483.0,
|
|
"step": 30640
|
|
},
|
|
{
|
|
"entropy": 5.1823101997375485,
|
|
"epoch": 2.943804034582133,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004142658476596706,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.23545114398002626,
|
|
"num_tokens": 70267484.0,
|
|
"step": 30645
|
|
},
|
|
{
|
|
"entropy": 5.251696681976318,
|
|
"epoch": 2.9442843419788662,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041423891894862687,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.2259354069828987,
|
|
"num_tokens": 70278137.0,
|
|
"step": 30650
|
|
},
|
|
{
|
|
"entropy": 5.168307447433472,
|
|
"epoch": 2.9447646493756006,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004142119870048689,
|
|
"loss": 4.7834,
|
|
"mean_token_accuracy": 0.23308769911527633,
|
|
"num_tokens": 70289255.0,
|
|
"step": 30655
|
|
},
|
|
{
|
|
"entropy": 5.199542808532715,
|
|
"epoch": 2.9452449567723344,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004141850518290219,
|
|
"loss": 4.8504,
|
|
"mean_token_accuracy": 0.2379837766289711,
|
|
"num_tokens": 70300672.0,
|
|
"step": 30660
|
|
},
|
|
{
|
|
"entropy": 5.17111029624939,
|
|
"epoch": 2.9457252641690683,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041415811342171134,
|
|
"loss": 4.7794,
|
|
"mean_token_accuracy": 0.23771178126335143,
|
|
"num_tokens": 70311964.0,
|
|
"step": 30665
|
|
},
|
|
{
|
|
"entropy": 5.133658313751221,
|
|
"epoch": 2.946205571565802,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004141311717835625,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.23811358511447905,
|
|
"num_tokens": 70323354.0,
|
|
"step": 30670
|
|
},
|
|
{
|
|
"entropy": 5.209849262237549,
|
|
"epoch": 2.946685878962536,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041410422691520114,
|
|
"loss": 4.8841,
|
|
"mean_token_accuracy": 0.2224256157875061,
|
|
"num_tokens": 70335432.0,
|
|
"step": 30675
|
|
},
|
|
{
|
|
"entropy": 5.216767978668213,
|
|
"epoch": 2.94716618635927,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041407727881725265,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.23387747555971145,
|
|
"num_tokens": 70347012.0,
|
|
"step": 30680
|
|
},
|
|
{
|
|
"entropy": 5.156971073150634,
|
|
"epoch": 2.947646493756004,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004140503274903426,
|
|
"loss": 4.7722,
|
|
"mean_token_accuracy": 0.23932261914014816,
|
|
"num_tokens": 70358680.0,
|
|
"step": 30685
|
|
},
|
|
{
|
|
"entropy": 5.106101131439209,
|
|
"epoch": 2.9481268011527377,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000414023372935097,
|
|
"loss": 4.6588,
|
|
"mean_token_accuracy": 0.2501971572637558,
|
|
"num_tokens": 70369081.0,
|
|
"step": 30690
|
|
},
|
|
{
|
|
"entropy": 5.160896492004395,
|
|
"epoch": 2.9486071085494716,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041399641515214137,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.23057452738285064,
|
|
"num_tokens": 70380831.0,
|
|
"step": 30695
|
|
},
|
|
{
|
|
"entropy": 5.147576236724854,
|
|
"epoch": 2.9490874159462055,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004139694541421018,
|
|
"loss": 4.7748,
|
|
"mean_token_accuracy": 0.24427331238985062,
|
|
"num_tokens": 70392403.0,
|
|
"step": 30700
|
|
},
|
|
{
|
|
"entropy": 5.195247220993042,
|
|
"epoch": 2.9495677233429394,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004139424899056042,
|
|
"loss": 4.8692,
|
|
"mean_token_accuracy": 0.23495137840509414,
|
|
"num_tokens": 70404332.0,
|
|
"step": 30705
|
|
},
|
|
{
|
|
"entropy": 5.185168695449829,
|
|
"epoch": 2.9500480307396733,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00041391552244327446,
|
|
"loss": 4.7686,
|
|
"mean_token_accuracy": 0.2401106834411621,
|
|
"num_tokens": 70416119.0,
|
|
"step": 30710
|
|
},
|
|
{
|
|
"entropy": 5.235811376571656,
|
|
"epoch": 2.950528338136407,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004138885517557387,
|
|
"loss": 4.8296,
|
|
"mean_token_accuracy": 0.2301781192421913,
|
|
"num_tokens": 70425874.0,
|
|
"step": 30715
|
|
},
|
|
{
|
|
"entropy": 5.195336103439331,
|
|
"epoch": 2.9510086455331415,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004138615778436234,
|
|
"loss": 4.8759,
|
|
"mean_token_accuracy": 0.23271079659461974,
|
|
"num_tokens": 70435755.0,
|
|
"step": 30720
|
|
},
|
|
{
|
|
"entropy": 5.066377735137939,
|
|
"epoch": 2.951488952929875,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041383460070755447,
|
|
"loss": 4.6589,
|
|
"mean_token_accuracy": 0.24372947514057158,
|
|
"num_tokens": 70446764.0,
|
|
"step": 30725
|
|
},
|
|
{
|
|
"entropy": 5.146914482116699,
|
|
"epoch": 2.9519692603266092,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041380762034815834,
|
|
"loss": 4.6942,
|
|
"mean_token_accuracy": 0.24833110421895982,
|
|
"num_tokens": 70457635.0,
|
|
"step": 30730
|
|
},
|
|
{
|
|
"entropy": 5.2182841300964355,
|
|
"epoch": 2.952449567723343,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041378063676606147,
|
|
"loss": 4.8716,
|
|
"mean_token_accuracy": 0.22970163077116013,
|
|
"num_tokens": 70469082.0,
|
|
"step": 30735
|
|
},
|
|
{
|
|
"entropy": 5.156048202514649,
|
|
"epoch": 2.952929875120077,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00041375364996189035,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.24063003063201904,
|
|
"num_tokens": 70481634.0,
|
|
"step": 30740
|
|
},
|
|
{
|
|
"entropy": 5.217213726043701,
|
|
"epoch": 2.953410182516811,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00041372665993627143,
|
|
"loss": 4.8569,
|
|
"mean_token_accuracy": 0.23506666719913483,
|
|
"num_tokens": 70493320.0,
|
|
"step": 30745
|
|
},
|
|
{
|
|
"entropy": 5.198023843765259,
|
|
"epoch": 2.9538904899135447,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041369966668983144,
|
|
"loss": 4.7555,
|
|
"mean_token_accuracy": 0.23958168923854828,
|
|
"num_tokens": 70504998.0,
|
|
"step": 30750
|
|
},
|
|
{
|
|
"entropy": 5.215562391281128,
|
|
"epoch": 2.9543707973102786,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041367267022319706,
|
|
"loss": 4.7761,
|
|
"mean_token_accuracy": 0.24050793796777725,
|
|
"num_tokens": 70516096.0,
|
|
"step": 30755
|
|
},
|
|
{
|
|
"entropy": 5.143350076675415,
|
|
"epoch": 2.9548511047070125,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000413645670536995,
|
|
"loss": 4.8578,
|
|
"mean_token_accuracy": 0.237970070540905,
|
|
"num_tokens": 70527193.0,
|
|
"step": 30760
|
|
},
|
|
{
|
|
"entropy": 5.261097526550293,
|
|
"epoch": 2.9553314121037464,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004136186676318522,
|
|
"loss": 4.8933,
|
|
"mean_token_accuracy": 0.22514180690050126,
|
|
"num_tokens": 70538733.0,
|
|
"step": 30765
|
|
},
|
|
{
|
|
"entropy": 5.216279125213623,
|
|
"epoch": 2.9558117195004803,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004135916615083956,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.23702714890241622,
|
|
"num_tokens": 70549381.0,
|
|
"step": 30770
|
|
},
|
|
{
|
|
"entropy": 5.152738189697265,
|
|
"epoch": 2.956292026897214,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00041356465216725195,
|
|
"loss": 4.7976,
|
|
"mean_token_accuracy": 0.23515752851963043,
|
|
"num_tokens": 70560576.0,
|
|
"step": 30775
|
|
},
|
|
{
|
|
"entropy": 5.135280561447144,
|
|
"epoch": 2.956772334293948,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041353763960904873,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.23375997692346573,
|
|
"num_tokens": 70572093.0,
|
|
"step": 30780
|
|
},
|
|
{
|
|
"entropy": 5.189914512634277,
|
|
"epoch": 2.957252641690682,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041351062383441286,
|
|
"loss": 4.7636,
|
|
"mean_token_accuracy": 0.23868095129728317,
|
|
"num_tokens": 70581567.0,
|
|
"step": 30785
|
|
},
|
|
{
|
|
"entropy": 5.150408840179443,
|
|
"epoch": 2.957732949087416,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004134836048439716,
|
|
"loss": 4.7815,
|
|
"mean_token_accuracy": 0.24508727490901946,
|
|
"num_tokens": 70593729.0,
|
|
"step": 30790
|
|
},
|
|
{
|
|
"entropy": 5.168519926071167,
|
|
"epoch": 2.95821325648415,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041345658263835215,
|
|
"loss": 4.7883,
|
|
"mean_token_accuracy": 0.24051970690488816,
|
|
"num_tokens": 70605816.0,
|
|
"step": 30795
|
|
},
|
|
{
|
|
"entropy": 5.196683406829834,
|
|
"epoch": 2.9586935638808836,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041342955721818207,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.23381567001342773,
|
|
"num_tokens": 70618310.0,
|
|
"step": 30800
|
|
},
|
|
{
|
|
"entropy": 5.147897815704345,
|
|
"epoch": 2.959173871277618,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00041340252858408866,
|
|
"loss": 4.7958,
|
|
"mean_token_accuracy": 0.23893490582704544,
|
|
"num_tokens": 70629842.0,
|
|
"step": 30805
|
|
},
|
|
{
|
|
"entropy": 5.174610328674317,
|
|
"epoch": 2.9596541786743513,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00041337549673669963,
|
|
"loss": 4.9011,
|
|
"mean_token_accuracy": 0.2302386686205864,
|
|
"num_tokens": 70642564.0,
|
|
"step": 30810
|
|
},
|
|
{
|
|
"entropy": 5.272196435928345,
|
|
"epoch": 2.9601344860710856,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004133484616766423,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.23572280257940292,
|
|
"num_tokens": 70653225.0,
|
|
"step": 30815
|
|
},
|
|
{
|
|
"entropy": 5.245864820480347,
|
|
"epoch": 2.9606147934678195,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041332142340454463,
|
|
"loss": 4.8353,
|
|
"mean_token_accuracy": 0.23133866041898726,
|
|
"num_tokens": 70665428.0,
|
|
"step": 30820
|
|
},
|
|
{
|
|
"entropy": 5.177904176712036,
|
|
"epoch": 2.9610951008645534,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004132943819210342,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.23393570482730866,
|
|
"num_tokens": 70676441.0,
|
|
"step": 30825
|
|
},
|
|
{
|
|
"entropy": 5.080386686325073,
|
|
"epoch": 2.9615754082612873,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041326733722673876,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.25193150490522387,
|
|
"num_tokens": 70687561.0,
|
|
"step": 30830
|
|
},
|
|
{
|
|
"entropy": 5.198447036743164,
|
|
"epoch": 2.962055715658021,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041324028932228645,
|
|
"loss": 4.8339,
|
|
"mean_token_accuracy": 0.2367920011281967,
|
|
"num_tokens": 70699949.0,
|
|
"step": 30835
|
|
},
|
|
{
|
|
"entropy": 5.134621334075928,
|
|
"epoch": 2.962536023054755,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004132132382083051,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.2480901688337326,
|
|
"num_tokens": 70711176.0,
|
|
"step": 30840
|
|
},
|
|
{
|
|
"entropy": 5.264098882675171,
|
|
"epoch": 2.963016330451489,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041318618388542274,
|
|
"loss": 4.8012,
|
|
"mean_token_accuracy": 0.23000501096248627,
|
|
"num_tokens": 70722974.0,
|
|
"step": 30845
|
|
},
|
|
{
|
|
"entropy": 5.0708336353302,
|
|
"epoch": 2.963496637848223,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004131591263542675,
|
|
"loss": 4.6401,
|
|
"mean_token_accuracy": 0.25042801201343534,
|
|
"num_tokens": 70735158.0,
|
|
"step": 30850
|
|
},
|
|
{
|
|
"entropy": 5.125586700439453,
|
|
"epoch": 2.9639769452449567,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004131320656154676,
|
|
"loss": 4.7792,
|
|
"mean_token_accuracy": 0.23748330026865005,
|
|
"num_tokens": 70746444.0,
|
|
"step": 30855
|
|
},
|
|
{
|
|
"entropy": 5.2541872501373295,
|
|
"epoch": 2.9644572526416906,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004131050016696514,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.2372214287519455,
|
|
"num_tokens": 70757985.0,
|
|
"step": 30860
|
|
},
|
|
{
|
|
"entropy": 5.226123046875,
|
|
"epoch": 2.9649375600384245,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000413077934517447,
|
|
"loss": 4.8183,
|
|
"mean_token_accuracy": 0.23436143398284912,
|
|
"num_tokens": 70769867.0,
|
|
"step": 30865
|
|
},
|
|
{
|
|
"entropy": 5.1643108367919925,
|
|
"epoch": 2.9654178674351583,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004130508641594831,
|
|
"loss": 4.8507,
|
|
"mean_token_accuracy": 0.23198235630989075,
|
|
"num_tokens": 70781610.0,
|
|
"step": 30870
|
|
},
|
|
{
|
|
"entropy": 5.1911492347717285,
|
|
"epoch": 2.965898174831892,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041302379059638794,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.24012200236320497,
|
|
"num_tokens": 70793336.0,
|
|
"step": 30875
|
|
},
|
|
{
|
|
"entropy": 5.1375412940979,
|
|
"epoch": 2.9663784822286265,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041299671382879024,
|
|
"loss": 4.7626,
|
|
"mean_token_accuracy": 0.23730559796094894,
|
|
"num_tokens": 70802714.0,
|
|
"step": 30880
|
|
},
|
|
{
|
|
"entropy": 5.277142763137817,
|
|
"epoch": 2.96685878962536,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004129696338573187,
|
|
"loss": 4.903,
|
|
"mean_token_accuracy": 0.22657340914011,
|
|
"num_tokens": 70813300.0,
|
|
"step": 30885
|
|
},
|
|
{
|
|
"entropy": 5.252987670898437,
|
|
"epoch": 2.9673390970220943,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004129425506826019,
|
|
"loss": 4.9257,
|
|
"mean_token_accuracy": 0.22725864201784135,
|
|
"num_tokens": 70824828.0,
|
|
"step": 30890
|
|
},
|
|
{
|
|
"entropy": 5.163870620727539,
|
|
"epoch": 2.967819404418828,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00041291546430526863,
|
|
"loss": 4.8286,
|
|
"mean_token_accuracy": 0.24259574860334396,
|
|
"num_tokens": 70836788.0,
|
|
"step": 30895
|
|
},
|
|
{
|
|
"entropy": 5.216791820526123,
|
|
"epoch": 2.968299711815562,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004128883747259478,
|
|
"loss": 4.7785,
|
|
"mean_token_accuracy": 0.24038069248199462,
|
|
"num_tokens": 70849308.0,
|
|
"step": 30900
|
|
},
|
|
{
|
|
"entropy": 5.330492115020752,
|
|
"epoch": 2.968780019212296,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004128612819452684,
|
|
"loss": 4.9228,
|
|
"mean_token_accuracy": 0.22431219071149827,
|
|
"num_tokens": 70859987.0,
|
|
"step": 30905
|
|
},
|
|
{
|
|
"entropy": 5.278654527664185,
|
|
"epoch": 2.96926032660903,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041283418596385944,
|
|
"loss": 4.8497,
|
|
"mean_token_accuracy": 0.2417091190814972,
|
|
"num_tokens": 70872096.0,
|
|
"step": 30910
|
|
},
|
|
{
|
|
"entropy": 5.1265160083770756,
|
|
"epoch": 2.9697406340057637,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004128070867823499,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.2430032953619957,
|
|
"num_tokens": 70884336.0,
|
|
"step": 30915
|
|
},
|
|
{
|
|
"entropy": 5.127111434936523,
|
|
"epoch": 2.9702209414024976,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000412779984401369,
|
|
"loss": 4.7263,
|
|
"mean_token_accuracy": 0.24674725234508516,
|
|
"num_tokens": 70894707.0,
|
|
"step": 30920
|
|
},
|
|
{
|
|
"entropy": 5.220841693878174,
|
|
"epoch": 2.9707012487992315,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000412752878821546,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.2324744924902916,
|
|
"num_tokens": 70906461.0,
|
|
"step": 30925
|
|
},
|
|
{
|
|
"entropy": 5.146343755722046,
|
|
"epoch": 2.9711815561959654,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041272577004351026,
|
|
"loss": 4.6983,
|
|
"mean_token_accuracy": 0.24336091428995132,
|
|
"num_tokens": 70917282.0,
|
|
"step": 30930
|
|
},
|
|
{
|
|
"entropy": 5.152488803863525,
|
|
"epoch": 2.9716618635926992,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041269865806789095,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.24513566493988037,
|
|
"num_tokens": 70928253.0,
|
|
"step": 30935
|
|
},
|
|
{
|
|
"entropy": 5.136491489410401,
|
|
"epoch": 2.972142170989433,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004126715428953178,
|
|
"loss": 4.7496,
|
|
"mean_token_accuracy": 0.23434931486845018,
|
|
"num_tokens": 70939089.0,
|
|
"step": 30940
|
|
},
|
|
{
|
|
"entropy": 5.157656145095825,
|
|
"epoch": 2.972622478386167,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004126444245264202,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.2387981593608856,
|
|
"num_tokens": 70949533.0,
|
|
"step": 30945
|
|
},
|
|
{
|
|
"entropy": 5.162232780456543,
|
|
"epoch": 2.973102785782901,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004126173029618278,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.23166611790657043,
|
|
"num_tokens": 70961449.0,
|
|
"step": 30950
|
|
},
|
|
{
|
|
"entropy": 5.143775177001953,
|
|
"epoch": 2.973583093179635,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004125901782021702,
|
|
"loss": 4.7666,
|
|
"mean_token_accuracy": 0.23952997028827666,
|
|
"num_tokens": 70973008.0,
|
|
"step": 30955
|
|
},
|
|
{
|
|
"entropy": 5.125874996185303,
|
|
"epoch": 2.9740634005763686,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004125630502480773,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.24207810908555985,
|
|
"num_tokens": 70984170.0,
|
|
"step": 30960
|
|
},
|
|
{
|
|
"entropy": 5.207072305679321,
|
|
"epoch": 2.974543707973103,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004125359191001788,
|
|
"loss": 4.8286,
|
|
"mean_token_accuracy": 0.23180654793977737,
|
|
"num_tokens": 70994900.0,
|
|
"step": 30965
|
|
},
|
|
{
|
|
"entropy": 5.201153087615967,
|
|
"epoch": 2.975024015369837,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004125087847591047,
|
|
"loss": 4.794,
|
|
"mean_token_accuracy": 0.23852715790271758,
|
|
"num_tokens": 71007430.0,
|
|
"step": 30970
|
|
},
|
|
{
|
|
"entropy": 5.195294189453125,
|
|
"epoch": 2.9755043227665707,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00041248164722548493,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.23601623475551606,
|
|
"num_tokens": 71020306.0,
|
|
"step": 30975
|
|
},
|
|
{
|
|
"entropy": 5.1599750995635985,
|
|
"epoch": 2.9759846301633046,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004124545064999495,
|
|
"loss": 4.7206,
|
|
"mean_token_accuracy": 0.2428874120116234,
|
|
"num_tokens": 71031114.0,
|
|
"step": 30980
|
|
},
|
|
{
|
|
"entropy": 5.071662712097168,
|
|
"epoch": 2.9764649375600385,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041242736258312866,
|
|
"loss": 4.7212,
|
|
"mean_token_accuracy": 0.24512513875961303,
|
|
"num_tokens": 71043289.0,
|
|
"step": 30985
|
|
},
|
|
{
|
|
"entropy": 5.146754121780395,
|
|
"epoch": 2.9769452449567724,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004124002154756525,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.24860253930091858,
|
|
"num_tokens": 71055163.0,
|
|
"step": 30990
|
|
},
|
|
{
|
|
"entropy": 5.132520723342895,
|
|
"epoch": 2.9774255523535063,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041237306517815124,
|
|
"loss": 4.7128,
|
|
"mean_token_accuracy": 0.24269575327634813,
|
|
"num_tokens": 71067830.0,
|
|
"step": 30995
|
|
},
|
|
{
|
|
"entropy": 5.108531379699707,
|
|
"epoch": 2.97790585975024,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004123459116912554,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.24747138172388078,
|
|
"num_tokens": 71079242.0,
|
|
"step": 31000
|
|
},
|
|
{
|
|
"entropy": 5.163477802276612,
|
|
"epoch": 2.978386167146974,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041231875501559535,
|
|
"loss": 4.8135,
|
|
"mean_token_accuracy": 0.2346956729888916,
|
|
"num_tokens": 71091076.0,
|
|
"step": 31005
|
|
},
|
|
{
|
|
"entropy": 5.206032228469849,
|
|
"epoch": 2.978866474543708,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041229159515180155,
|
|
"loss": 4.726,
|
|
"mean_token_accuracy": 0.2431800216436386,
|
|
"num_tokens": 71101226.0,
|
|
"step": 31010
|
|
},
|
|
{
|
|
"entropy": 5.172221946716308,
|
|
"epoch": 2.979346781940442,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004122644321005046,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.24683685451745987,
|
|
"num_tokens": 71112689.0,
|
|
"step": 31015
|
|
},
|
|
{
|
|
"entropy": 5.138100814819336,
|
|
"epoch": 2.9798270893371757,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041223726586233505,
|
|
"loss": 4.8189,
|
|
"mean_token_accuracy": 0.2319454476237297,
|
|
"num_tokens": 71124256.0,
|
|
"step": 31020
|
|
},
|
|
{
|
|
"entropy": 5.15993709564209,
|
|
"epoch": 2.9803073967339095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041221009643792377,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.2395955115556717,
|
|
"num_tokens": 71134636.0,
|
|
"step": 31025
|
|
},
|
|
{
|
|
"entropy": 5.136376523971558,
|
|
"epoch": 2.980787704130644,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004121829238279014,
|
|
"loss": 4.6816,
|
|
"mean_token_accuracy": 0.24070947766304016,
|
|
"num_tokens": 71145969.0,
|
|
"step": 31030
|
|
},
|
|
{
|
|
"entropy": 5.142029476165772,
|
|
"epoch": 2.9812680115273773,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00041215574803289896,
|
|
"loss": 4.7779,
|
|
"mean_token_accuracy": 0.238448166847229,
|
|
"num_tokens": 71157491.0,
|
|
"step": 31035
|
|
},
|
|
{
|
|
"entropy": 5.143434619903564,
|
|
"epoch": 2.9817483189241116,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004121285690535473,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.2386000096797943,
|
|
"num_tokens": 71169325.0,
|
|
"step": 31040
|
|
},
|
|
{
|
|
"entropy": 5.141952991485596,
|
|
"epoch": 2.982228626320845,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00041210138689047745,
|
|
"loss": 4.7833,
|
|
"mean_token_accuracy": 0.2373145952820778,
|
|
"num_tokens": 71181179.0,
|
|
"step": 31045
|
|
},
|
|
{
|
|
"entropy": 5.150288343429565,
|
|
"epoch": 2.9827089337175794,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004120742015443206,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.23803836554288865,
|
|
"num_tokens": 71193250.0,
|
|
"step": 31050
|
|
},
|
|
{
|
|
"entropy": 5.09924635887146,
|
|
"epoch": 2.9831892411143133,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004120470130157077,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.24932236671447755,
|
|
"num_tokens": 71207544.0,
|
|
"step": 31055
|
|
},
|
|
{
|
|
"entropy": 5.193252325057983,
|
|
"epoch": 2.983669548511047,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00041201982130527006,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.23842172920703888,
|
|
"num_tokens": 71219989.0,
|
|
"step": 31060
|
|
},
|
|
{
|
|
"entropy": 5.1847187042236325,
|
|
"epoch": 2.984149855907781,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00041199262641363914,
|
|
"loss": 4.7774,
|
|
"mean_token_accuracy": 0.23416979163885115,
|
|
"num_tokens": 71232455.0,
|
|
"step": 31065
|
|
},
|
|
{
|
|
"entropy": 5.153942966461182,
|
|
"epoch": 2.984630163304515,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00041196542834144617,
|
|
"loss": 4.6978,
|
|
"mean_token_accuracy": 0.24455562829971314,
|
|
"num_tokens": 71244179.0,
|
|
"step": 31070
|
|
},
|
|
{
|
|
"entropy": 5.125854635238648,
|
|
"epoch": 2.985110470701249,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041193822708932265,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.23852642327547074,
|
|
"num_tokens": 71255468.0,
|
|
"step": 31075
|
|
},
|
|
{
|
|
"entropy": 5.167898368835449,
|
|
"epoch": 2.9855907780979827,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004119110226579002,
|
|
"loss": 4.8012,
|
|
"mean_token_accuracy": 0.23694975823163986,
|
|
"num_tokens": 71266192.0,
|
|
"step": 31080
|
|
},
|
|
{
|
|
"entropy": 5.0936503410339355,
|
|
"epoch": 2.9860710854947166,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041188381504781026,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.2413354516029358,
|
|
"num_tokens": 71277166.0,
|
|
"step": 31085
|
|
},
|
|
{
|
|
"entropy": 5.159340763092041,
|
|
"epoch": 2.9865513928914504,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004118566042596846,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.23888649940490722,
|
|
"num_tokens": 71288077.0,
|
|
"step": 31090
|
|
},
|
|
{
|
|
"entropy": 5.061277246475219,
|
|
"epoch": 2.9870317002881843,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000411829390294155,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.2518033146858215,
|
|
"num_tokens": 71300423.0,
|
|
"step": 31095
|
|
},
|
|
{
|
|
"entropy": 5.155814123153687,
|
|
"epoch": 2.987512007684918,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041180217315185333,
|
|
"loss": 4.7241,
|
|
"mean_token_accuracy": 0.2375679224729538,
|
|
"num_tokens": 71312265.0,
|
|
"step": 31100
|
|
},
|
|
{
|
|
"entropy": 5.119020891189575,
|
|
"epoch": 2.9879923150816525,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00041177495283341124,
|
|
"loss": 4.7014,
|
|
"mean_token_accuracy": 0.2432352989912033,
|
|
"num_tokens": 71323369.0,
|
|
"step": 31105
|
|
},
|
|
{
|
|
"entropy": 5.172815227508545,
|
|
"epoch": 2.988472622478386,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000411747729339461,
|
|
"loss": 4.7582,
|
|
"mean_token_accuracy": 0.24694153368473054,
|
|
"num_tokens": 71333977.0,
|
|
"step": 31110
|
|
},
|
|
{
|
|
"entropy": 5.126711225509643,
|
|
"epoch": 2.9889529298751203,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004117205026706345,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.24455465823411943,
|
|
"num_tokens": 71345176.0,
|
|
"step": 31115
|
|
},
|
|
{
|
|
"entropy": 5.189213418960572,
|
|
"epoch": 2.9894332372718537,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041169327282756396,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.2366039663553238,
|
|
"num_tokens": 71357310.0,
|
|
"step": 31120
|
|
},
|
|
{
|
|
"entropy": 5.272304058074951,
|
|
"epoch": 2.989913544668588,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004116660398108815,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.22920242697000504,
|
|
"num_tokens": 71369610.0,
|
|
"step": 31125
|
|
},
|
|
{
|
|
"entropy": 5.208366250991821,
|
|
"epoch": 2.990393852065322,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004116388036212194,
|
|
"loss": 4.9021,
|
|
"mean_token_accuracy": 0.23218174427747726,
|
|
"num_tokens": 71381973.0,
|
|
"step": 31130
|
|
},
|
|
{
|
|
"entropy": 5.099828243255615,
|
|
"epoch": 2.990874159462056,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041161156425921004,
|
|
"loss": 4.7661,
|
|
"mean_token_accuracy": 0.23609502762556075,
|
|
"num_tokens": 71393739.0,
|
|
"step": 31135
|
|
},
|
|
{
|
|
"entropy": 5.211916780471801,
|
|
"epoch": 2.9913544668587897,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041158432172548577,
|
|
"loss": 4.8442,
|
|
"mean_token_accuracy": 0.23362098038196563,
|
|
"num_tokens": 71405205.0,
|
|
"step": 31140
|
|
},
|
|
{
|
|
"entropy": 5.16189489364624,
|
|
"epoch": 2.9918347742555236,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00041155707602067923,
|
|
"loss": 4.6943,
|
|
"mean_token_accuracy": 0.2425771802663803,
|
|
"num_tokens": 71416645.0,
|
|
"step": 31145
|
|
},
|
|
{
|
|
"entropy": 5.188506937026977,
|
|
"epoch": 2.9923150816522575,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004115298271454227,
|
|
"loss": 4.8274,
|
|
"mean_token_accuracy": 0.23068844079971312,
|
|
"num_tokens": 71428854.0,
|
|
"step": 31150
|
|
},
|
|
{
|
|
"entropy": 5.156141185760498,
|
|
"epoch": 2.9927953890489913,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004115025751003491,
|
|
"loss": 4.752,
|
|
"mean_token_accuracy": 0.2445857122540474,
|
|
"num_tokens": 71439950.0,
|
|
"step": 31155
|
|
},
|
|
{
|
|
"entropy": 5.127729701995849,
|
|
"epoch": 2.993275696445725,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000411475319886091,
|
|
"loss": 4.749,
|
|
"mean_token_accuracy": 0.24213937520980836,
|
|
"num_tokens": 71451901.0,
|
|
"step": 31160
|
|
},
|
|
{
|
|
"entropy": 5.272598791122436,
|
|
"epoch": 2.993756003842459,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041144806150328117,
|
|
"loss": 4.8952,
|
|
"mean_token_accuracy": 0.23578106462955475,
|
|
"num_tokens": 71463688.0,
|
|
"step": 31165
|
|
},
|
|
{
|
|
"entropy": 5.284673643112183,
|
|
"epoch": 2.994236311239193,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004114207999525527,
|
|
"loss": 4.8651,
|
|
"mean_token_accuracy": 0.23249777257442475,
|
|
"num_tokens": 71475392.0,
|
|
"step": 31170
|
|
},
|
|
{
|
|
"entropy": 5.156809854507446,
|
|
"epoch": 2.994716618635927,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00041139353523453814,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.24214831441640855,
|
|
"num_tokens": 71486004.0,
|
|
"step": 31175
|
|
},
|
|
{
|
|
"entropy": 5.215101003646851,
|
|
"epoch": 2.9951969260326607,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004113662673498708,
|
|
"loss": 4.8983,
|
|
"mean_token_accuracy": 0.23020508289337158,
|
|
"num_tokens": 71497850.0,
|
|
"step": 31180
|
|
},
|
|
{
|
|
"entropy": 5.2085676193237305,
|
|
"epoch": 2.9956772334293946,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041133899629918364,
|
|
"loss": 4.7454,
|
|
"mean_token_accuracy": 0.2462710753083229,
|
|
"num_tokens": 71507778.0,
|
|
"step": 31185
|
|
},
|
|
{
|
|
"entropy": 5.182804155349731,
|
|
"epoch": 2.996157540826129,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00041131172208310986,
|
|
"loss": 4.8046,
|
|
"mean_token_accuracy": 0.23487781435251237,
|
|
"num_tokens": 71519506.0,
|
|
"step": 31190
|
|
},
|
|
{
|
|
"entropy": 5.1288127422332765,
|
|
"epoch": 2.9966378482228624,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041128444470228253,
|
|
"loss": 4.7352,
|
|
"mean_token_accuracy": 0.24270397424697876,
|
|
"num_tokens": 71530523.0,
|
|
"step": 31195
|
|
},
|
|
{
|
|
"entropy": 5.191748094558716,
|
|
"epoch": 2.9971181556195967,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041125716415733524,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.22983711510896682,
|
|
"num_tokens": 71541473.0,
|
|
"step": 31200
|
|
},
|
|
{
|
|
"entropy": 5.152352666854858,
|
|
"epoch": 2.9975984630163306,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004112298804489011,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.2453027695417404,
|
|
"num_tokens": 71552012.0,
|
|
"step": 31205
|
|
},
|
|
{
|
|
"entropy": 5.18847804069519,
|
|
"epoch": 2.9980787704130645,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004112025935776137,
|
|
"loss": 4.7899,
|
|
"mean_token_accuracy": 0.23447803258895875,
|
|
"num_tokens": 71562239.0,
|
|
"step": 31210
|
|
},
|
|
{
|
|
"entropy": 5.14770359992981,
|
|
"epoch": 2.9985590778097984,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041117530354410647,
|
|
"loss": 4.6978,
|
|
"mean_token_accuracy": 0.2415661484003067,
|
|
"num_tokens": 71573296.0,
|
|
"step": 31215
|
|
},
|
|
{
|
|
"entropy": 5.1880346775054935,
|
|
"epoch": 2.9990393852065322,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004111480103490131,
|
|
"loss": 4.8505,
|
|
"mean_token_accuracy": 0.23558012694120406,
|
|
"num_tokens": 71584659.0,
|
|
"step": 31220
|
|
},
|
|
{
|
|
"entropy": 5.152195978164673,
|
|
"epoch": 2.999519692603266,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041112071399296724,
|
|
"loss": 4.7488,
|
|
"mean_token_accuracy": 0.24320499151945113,
|
|
"num_tokens": 71595672.0,
|
|
"step": 31225
|
|
},
|
|
{
|
|
"entropy": 5.117705821990967,
|
|
"epoch": 3.0,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004110934144766025,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.2541891232132912,
|
|
"num_tokens": 71605608.0,
|
|
"step": 31230
|
|
},
|
|
{
|
|
"entropy": 5.146771955490112,
|
|
"epoch": 3.000480307396734,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041106611180055284,
|
|
"loss": 4.7651,
|
|
"mean_token_accuracy": 0.2350709095597267,
|
|
"num_tokens": 71617542.0,
|
|
"step": 31235
|
|
},
|
|
{
|
|
"entropy": 5.1232363224029545,
|
|
"epoch": 3.0009606147934678,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041103880596545206,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.24445026665925979,
|
|
"num_tokens": 71629087.0,
|
|
"step": 31240
|
|
},
|
|
{
|
|
"entropy": 5.203413105010986,
|
|
"epoch": 3.0014409221902016,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004110114969719342,
|
|
"loss": 4.7415,
|
|
"mean_token_accuracy": 0.24606202095746993,
|
|
"num_tokens": 71640929.0,
|
|
"step": 31245
|
|
},
|
|
{
|
|
"entropy": 5.165411186218262,
|
|
"epoch": 3.0019212295869355,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004109841848206333,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.24100087732076644,
|
|
"num_tokens": 71652641.0,
|
|
"step": 31250
|
|
},
|
|
{
|
|
"entropy": 5.135177946090698,
|
|
"epoch": 3.0024015369836694,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004109568695121833,
|
|
"loss": 4.6784,
|
|
"mean_token_accuracy": 0.24453205466270447,
|
|
"num_tokens": 71664482.0,
|
|
"step": 31255
|
|
},
|
|
{
|
|
"entropy": 5.070644855499268,
|
|
"epoch": 3.0028818443804033,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004109295510472186,
|
|
"loss": 4.5951,
|
|
"mean_token_accuracy": 0.2492346629500389,
|
|
"num_tokens": 71675568.0,
|
|
"step": 31260
|
|
},
|
|
{
|
|
"entropy": 5.174136066436768,
|
|
"epoch": 3.003362151777137,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041090222942637323,
|
|
"loss": 4.7679,
|
|
"mean_token_accuracy": 0.2345506563782692,
|
|
"num_tokens": 71685731.0,
|
|
"step": 31265
|
|
},
|
|
{
|
|
"entropy": 5.219728755950928,
|
|
"epoch": 3.0038424591738715,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041087490465028175,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.23498520702123643,
|
|
"num_tokens": 71697212.0,
|
|
"step": 31270
|
|
},
|
|
{
|
|
"entropy": 5.097744989395141,
|
|
"epoch": 3.0043227665706054,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041084757671957844,
|
|
"loss": 4.6653,
|
|
"mean_token_accuracy": 0.2444755181670189,
|
|
"num_tokens": 71708444.0,
|
|
"step": 31275
|
|
},
|
|
{
|
|
"entropy": 5.176333332061768,
|
|
"epoch": 3.0048030739673393,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041082024563489773,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.2449917569756508,
|
|
"num_tokens": 71718645.0,
|
|
"step": 31280
|
|
},
|
|
{
|
|
"entropy": 5.1255146026611325,
|
|
"epoch": 3.005283381364073,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004107929113968743,
|
|
"loss": 4.6608,
|
|
"mean_token_accuracy": 0.2428463101387024,
|
|
"num_tokens": 71728798.0,
|
|
"step": 31285
|
|
},
|
|
{
|
|
"entropy": 5.180874443054199,
|
|
"epoch": 3.005763688760807,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004107655740061427,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.23136376291513444,
|
|
"num_tokens": 71741237.0,
|
|
"step": 31290
|
|
},
|
|
{
|
|
"entropy": 5.195070457458496,
|
|
"epoch": 3.006243996157541,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004107382334633375,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.24106893092393875,
|
|
"num_tokens": 71753755.0,
|
|
"step": 31295
|
|
},
|
|
{
|
|
"entropy": 5.236195373535156,
|
|
"epoch": 3.006724303554275,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004107108897690936,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.24224750697612762,
|
|
"num_tokens": 71765447.0,
|
|
"step": 31300
|
|
},
|
|
{
|
|
"entropy": 5.174728298187256,
|
|
"epoch": 3.0072046109510087,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004106835429240458,
|
|
"loss": 4.7579,
|
|
"mean_token_accuracy": 0.23930587917566298,
|
|
"num_tokens": 71777106.0,
|
|
"step": 31305
|
|
},
|
|
{
|
|
"entropy": 5.096037817001343,
|
|
"epoch": 3.0076849183477425,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004106561929288292,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.24493644684553145,
|
|
"num_tokens": 71789226.0,
|
|
"step": 31310
|
|
},
|
|
{
|
|
"entropy": 5.182675838470459,
|
|
"epoch": 3.0081652257444764,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041062883978407844,
|
|
"loss": 4.7554,
|
|
"mean_token_accuracy": 0.23883342742919922,
|
|
"num_tokens": 71800754.0,
|
|
"step": 31315
|
|
},
|
|
{
|
|
"entropy": 5.163075017929077,
|
|
"epoch": 3.0086455331412103,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041060148349042876,
|
|
"loss": 4.7848,
|
|
"mean_token_accuracy": 0.2427433267235756,
|
|
"num_tokens": 71812107.0,
|
|
"step": 31320
|
|
},
|
|
{
|
|
"entropy": 5.146941900253296,
|
|
"epoch": 3.009125840537944,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041057412404851536,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.24387964010238647,
|
|
"num_tokens": 71822031.0,
|
|
"step": 31325
|
|
},
|
|
{
|
|
"entropy": 5.160187768936157,
|
|
"epoch": 3.009606147934678,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004105467614589734,
|
|
"loss": 4.7127,
|
|
"mean_token_accuracy": 0.2386588379740715,
|
|
"num_tokens": 71833744.0,
|
|
"step": 31330
|
|
},
|
|
{
|
|
"entropy": 5.203341627120972,
|
|
"epoch": 3.010086455331412,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004105193957224381,
|
|
"loss": 4.6685,
|
|
"mean_token_accuracy": 0.24855976402759553,
|
|
"num_tokens": 71845385.0,
|
|
"step": 31335
|
|
},
|
|
{
|
|
"entropy": 5.1044059753417965,
|
|
"epoch": 3.010566762728146,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00041049202683954473,
|
|
"loss": 4.596,
|
|
"mean_token_accuracy": 0.2563145950436592,
|
|
"num_tokens": 71858065.0,
|
|
"step": 31340
|
|
},
|
|
{
|
|
"entropy": 5.069129943847656,
|
|
"epoch": 3.0110470701248797,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041046465481092893,
|
|
"loss": 4.6631,
|
|
"mean_token_accuracy": 0.24348257333040238,
|
|
"num_tokens": 71869553.0,
|
|
"step": 31345
|
|
},
|
|
{
|
|
"entropy": 5.124128961563111,
|
|
"epoch": 3.011527377521614,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00041043727963722607,
|
|
"loss": 4.7091,
|
|
"mean_token_accuracy": 0.24277879744768144,
|
|
"num_tokens": 71881196.0,
|
|
"step": 31350
|
|
},
|
|
{
|
|
"entropy": 5.13468565940857,
|
|
"epoch": 3.012007684918348,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004104099013190718,
|
|
"loss": 4.737,
|
|
"mean_token_accuracy": 0.23197893649339676,
|
|
"num_tokens": 71893323.0,
|
|
"step": 31355
|
|
},
|
|
{
|
|
"entropy": 5.1484674453735355,
|
|
"epoch": 3.012487992315082,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00041038251985710164,
|
|
"loss": 4.6626,
|
|
"mean_token_accuracy": 0.24603164494037627,
|
|
"num_tokens": 71904679.0,
|
|
"step": 31360
|
|
},
|
|
{
|
|
"entropy": 5.093578195571899,
|
|
"epoch": 3.0129682997118157,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004103551352519514,
|
|
"loss": 4.7559,
|
|
"mean_token_accuracy": 0.25139800310134885,
|
|
"num_tokens": 71916478.0,
|
|
"step": 31365
|
|
},
|
|
{
|
|
"entropy": 5.164360046386719,
|
|
"epoch": 3.0134486071085496,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041032774750425683,
|
|
"loss": 4.7445,
|
|
"mean_token_accuracy": 0.24580314457416536,
|
|
"num_tokens": 71928203.0,
|
|
"step": 31370
|
|
},
|
|
{
|
|
"entropy": 5.180453824996948,
|
|
"epoch": 3.0139289145052834,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004103003566146538,
|
|
"loss": 4.6541,
|
|
"mean_token_accuracy": 0.24307194948196412,
|
|
"num_tokens": 71939118.0,
|
|
"step": 31375
|
|
},
|
|
{
|
|
"entropy": 5.172709274291992,
|
|
"epoch": 3.0144092219020173,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004102729625837782,
|
|
"loss": 4.7814,
|
|
"mean_token_accuracy": 0.23412666469812393,
|
|
"num_tokens": 71950964.0,
|
|
"step": 31380
|
|
},
|
|
{
|
|
"entropy": 5.084878778457641,
|
|
"epoch": 3.014889529298751,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004102455654122662,
|
|
"loss": 4.6225,
|
|
"mean_token_accuracy": 0.254323935508728,
|
|
"num_tokens": 71960587.0,
|
|
"step": 31385
|
|
},
|
|
{
|
|
"entropy": 5.142302751541138,
|
|
"epoch": 3.015369836695485,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041021816510075366,
|
|
"loss": 4.666,
|
|
"mean_token_accuracy": 0.24275851547718047,
|
|
"num_tokens": 71972014.0,
|
|
"step": 31390
|
|
},
|
|
{
|
|
"entropy": 5.191846513748169,
|
|
"epoch": 3.015850144092219,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041019076164987696,
|
|
"loss": 4.7236,
|
|
"mean_token_accuracy": 0.2443491831421852,
|
|
"num_tokens": 71982842.0,
|
|
"step": 31395
|
|
},
|
|
{
|
|
"entropy": 5.156191301345825,
|
|
"epoch": 3.016330451488953,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004101633550602721,
|
|
"loss": 4.6551,
|
|
"mean_token_accuracy": 0.24115131944417953,
|
|
"num_tokens": 71994450.0,
|
|
"step": 31400
|
|
},
|
|
{
|
|
"entropy": 5.09965500831604,
|
|
"epoch": 3.0168107588856867,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004101359453325755,
|
|
"loss": 4.6143,
|
|
"mean_token_accuracy": 0.24458208829164504,
|
|
"num_tokens": 72005490.0,
|
|
"step": 31405
|
|
},
|
|
{
|
|
"entropy": 5.146286535263061,
|
|
"epoch": 3.0172910662824206,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041010853246742357,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.24111726582050325,
|
|
"num_tokens": 72016723.0,
|
|
"step": 31410
|
|
},
|
|
{
|
|
"entropy": 5.069475412368774,
|
|
"epoch": 3.0177713736791545,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004100811164654527,
|
|
"loss": 4.6297,
|
|
"mean_token_accuracy": 0.25136281698942187,
|
|
"num_tokens": 72027189.0,
|
|
"step": 31415
|
|
},
|
|
{
|
|
"entropy": 5.183282804489136,
|
|
"epoch": 3.0182516810758884,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004100536973272994,
|
|
"loss": 4.7984,
|
|
"mean_token_accuracy": 0.23466323018074037,
|
|
"num_tokens": 72039662.0,
|
|
"step": 31420
|
|
},
|
|
{
|
|
"entropy": 5.157060623168945,
|
|
"epoch": 3.0187319884726227,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004100262750536003,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.2388945385813713,
|
|
"num_tokens": 72050769.0,
|
|
"step": 31425
|
|
},
|
|
{
|
|
"entropy": 5.153368854522705,
|
|
"epoch": 3.0192122958693566,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00040999884964499196,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.24322872906923293,
|
|
"num_tokens": 72062657.0,
|
|
"step": 31430
|
|
},
|
|
{
|
|
"entropy": 5.119635200500488,
|
|
"epoch": 3.0196926032660905,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00040997142110211127,
|
|
"loss": 4.6978,
|
|
"mean_token_accuracy": 0.24458848387002946,
|
|
"num_tokens": 72074805.0,
|
|
"step": 31435
|
|
},
|
|
{
|
|
"entropy": 5.100884437561035,
|
|
"epoch": 3.0201729106628243,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00040994398942559496,
|
|
"loss": 4.6818,
|
|
"mean_token_accuracy": 0.2542981833219528,
|
|
"num_tokens": 72085842.0,
|
|
"step": 31440
|
|
},
|
|
{
|
|
"entropy": 5.22122368812561,
|
|
"epoch": 3.020653218059558,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004099165546160799,
|
|
"loss": 4.792,
|
|
"mean_token_accuracy": 0.23209169805049895,
|
|
"num_tokens": 72096750.0,
|
|
"step": 31445
|
|
},
|
|
{
|
|
"entropy": 5.1298408031463625,
|
|
"epoch": 3.021133525456292,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040988911667420305,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.23611252754926682,
|
|
"num_tokens": 72108842.0,
|
|
"step": 31450
|
|
},
|
|
{
|
|
"entropy": 5.170259141921997,
|
|
"epoch": 3.021613832853026,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004098616756006015,
|
|
"loss": 4.7825,
|
|
"mean_token_accuracy": 0.23583701401948928,
|
|
"num_tokens": 72119582.0,
|
|
"step": 31455
|
|
},
|
|
{
|
|
"entropy": 5.220218086242676,
|
|
"epoch": 3.02209414024976,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004098342313959122,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.24251906722784042,
|
|
"num_tokens": 72129984.0,
|
|
"step": 31460
|
|
},
|
|
{
|
|
"entropy": 5.221495962142944,
|
|
"epoch": 3.0225744476464937,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004098067840607725,
|
|
"loss": 4.7508,
|
|
"mean_token_accuracy": 0.23580859154462813,
|
|
"num_tokens": 72142160.0,
|
|
"step": 31465
|
|
},
|
|
{
|
|
"entropy": 5.2523853302001955,
|
|
"epoch": 3.0230547550432276,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004097793335958195,
|
|
"loss": 4.8273,
|
|
"mean_token_accuracy": 0.23073551505804063,
|
|
"num_tokens": 72153691.0,
|
|
"step": 31470
|
|
},
|
|
{
|
|
"entropy": 5.17963433265686,
|
|
"epoch": 3.0235350624399615,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00040975188000169074,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.24246465265750886,
|
|
"num_tokens": 72165123.0,
|
|
"step": 31475
|
|
},
|
|
{
|
|
"entropy": 5.136645221710205,
|
|
"epoch": 3.0240153698366954,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040972442327902325,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.23861626982688905,
|
|
"num_tokens": 72177006.0,
|
|
"step": 31480
|
|
},
|
|
{
|
|
"entropy": 5.234075212478638,
|
|
"epoch": 3.0244956772334293,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004096969634284549,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.24114799201488496,
|
|
"num_tokens": 72189185.0,
|
|
"step": 31485
|
|
},
|
|
{
|
|
"entropy": 5.162556838989258,
|
|
"epoch": 3.024975984630163,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004096695004506229,
|
|
"loss": 4.7519,
|
|
"mean_token_accuracy": 0.24072834700345994,
|
|
"num_tokens": 72201530.0,
|
|
"step": 31490
|
|
},
|
|
{
|
|
"entropy": 5.131984090805053,
|
|
"epoch": 3.025456292026897,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00040964203434616496,
|
|
"loss": 4.6981,
|
|
"mean_token_accuracy": 0.25074725449085233,
|
|
"num_tokens": 72213514.0,
|
|
"step": 31495
|
|
},
|
|
{
|
|
"entropy": 5.123308086395264,
|
|
"epoch": 3.025936599423631,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004096145651157189,
|
|
"loss": 4.6721,
|
|
"mean_token_accuracy": 0.23987617641687392,
|
|
"num_tokens": 72224811.0,
|
|
"step": 31500
|
|
},
|
|
{
|
|
"entropy": 5.19174222946167,
|
|
"epoch": 3.0264169068203652,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004095870927599223,
|
|
"loss": 4.8105,
|
|
"mean_token_accuracy": 0.23840675950050355,
|
|
"num_tokens": 72236201.0,
|
|
"step": 31505
|
|
},
|
|
{
|
|
"entropy": 5.26389446258545,
|
|
"epoch": 3.026897214217099,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040955961727941306,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.23337478041648865,
|
|
"num_tokens": 72248963.0,
|
|
"step": 31510
|
|
},
|
|
{
|
|
"entropy": 5.198200750350952,
|
|
"epoch": 3.027377521613833,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004095321386748291,
|
|
"loss": 4.7703,
|
|
"mean_token_accuracy": 0.24041935056447983,
|
|
"num_tokens": 72259489.0,
|
|
"step": 31515
|
|
},
|
|
{
|
|
"entropy": 5.105219554901123,
|
|
"epoch": 3.027857829010567,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040950465694680825,
|
|
"loss": 4.7325,
|
|
"mean_token_accuracy": 0.24216355234384537,
|
|
"num_tokens": 72271124.0,
|
|
"step": 31520
|
|
},
|
|
{
|
|
"entropy": 5.219186401367187,
|
|
"epoch": 3.0283381364073008,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040947717209598877,
|
|
"loss": 4.7606,
|
|
"mean_token_accuracy": 0.2418152630329132,
|
|
"num_tokens": 72281144.0,
|
|
"step": 31525
|
|
},
|
|
{
|
|
"entropy": 5.123046493530273,
|
|
"epoch": 3.0288184438040346,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040944968412300867,
|
|
"loss": 4.7107,
|
|
"mean_token_accuracy": 0.24515776485204696,
|
|
"num_tokens": 72293422.0,
|
|
"step": 31530
|
|
},
|
|
{
|
|
"entropy": 5.181326913833618,
|
|
"epoch": 3.0292987512007685,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040942219302850605,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.24202222377061844,
|
|
"num_tokens": 72304450.0,
|
|
"step": 31535
|
|
},
|
|
{
|
|
"entropy": 5.157929754257202,
|
|
"epoch": 3.0297790585975024,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004093946988131193,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.2483867436647415,
|
|
"num_tokens": 72315000.0,
|
|
"step": 31540
|
|
},
|
|
{
|
|
"entropy": 5.167289447784424,
|
|
"epoch": 3.0302593659942363,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004093672014774868,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.23515065163373947,
|
|
"num_tokens": 72327268.0,
|
|
"step": 31545
|
|
},
|
|
{
|
|
"entropy": 5.1457513809204105,
|
|
"epoch": 3.03073967339097,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040933970102224675,
|
|
"loss": 4.6666,
|
|
"mean_token_accuracy": 0.24879975467920304,
|
|
"num_tokens": 72338371.0,
|
|
"step": 31550
|
|
},
|
|
{
|
|
"entropy": 5.198610019683838,
|
|
"epoch": 3.031219980787704,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040931219744803774,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.2453204557299614,
|
|
"num_tokens": 72349211.0,
|
|
"step": 31555
|
|
},
|
|
{
|
|
"entropy": 5.2092443943023685,
|
|
"epoch": 3.031700288184438,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004092846907554985,
|
|
"loss": 4.7806,
|
|
"mean_token_accuracy": 0.23937484472990037,
|
|
"num_tokens": 72361634.0,
|
|
"step": 31560
|
|
},
|
|
{
|
|
"entropy": 5.1265764236450195,
|
|
"epoch": 3.032180595581172,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040925718094526724,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.24192465096712112,
|
|
"num_tokens": 72374071.0,
|
|
"step": 31565
|
|
},
|
|
{
|
|
"entropy": 5.248894882202149,
|
|
"epoch": 3.0326609029779057,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040922966801798305,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.23453231900930405,
|
|
"num_tokens": 72386272.0,
|
|
"step": 31570
|
|
},
|
|
{
|
|
"entropy": 5.208275938034058,
|
|
"epoch": 3.0331412103746396,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00040920215197428456,
|
|
"loss": 4.7144,
|
|
"mean_token_accuracy": 0.24018343538045883,
|
|
"num_tokens": 72398832.0,
|
|
"step": 31575
|
|
},
|
|
{
|
|
"entropy": 5.233211421966553,
|
|
"epoch": 3.0336215177713735,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00040917463281481053,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.23224434703588487,
|
|
"num_tokens": 72409970.0,
|
|
"step": 31580
|
|
},
|
|
{
|
|
"entropy": 5.1359302520751955,
|
|
"epoch": 3.034101825168108,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004091471105402,
|
|
"loss": 4.6938,
|
|
"mean_token_accuracy": 0.24955242574214936,
|
|
"num_tokens": 72420640.0,
|
|
"step": 31585
|
|
},
|
|
{
|
|
"entropy": 5.184348201751709,
|
|
"epoch": 3.0345821325648417,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004091195851510918,
|
|
"loss": 4.7772,
|
|
"mean_token_accuracy": 0.24144320636987687,
|
|
"num_tokens": 72432111.0,
|
|
"step": 31590
|
|
},
|
|
{
|
|
"entropy": 5.115200424194336,
|
|
"epoch": 3.0350624399615755,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004090920566481252,
|
|
"loss": 4.6699,
|
|
"mean_token_accuracy": 0.24572039097547532,
|
|
"num_tokens": 72444427.0,
|
|
"step": 31595
|
|
},
|
|
{
|
|
"entropy": 5.202545070648194,
|
|
"epoch": 3.0355427473583094,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004090645250319392,
|
|
"loss": 4.7895,
|
|
"mean_token_accuracy": 0.2369418978691101,
|
|
"num_tokens": 72454955.0,
|
|
"step": 31600
|
|
},
|
|
{
|
|
"entropy": 5.10728440284729,
|
|
"epoch": 3.0360230547550433,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000409036990303173,
|
|
"loss": 4.6249,
|
|
"mean_token_accuracy": 0.25243430584669113,
|
|
"num_tokens": 72464914.0,
|
|
"step": 31605
|
|
},
|
|
{
|
|
"entropy": 5.134739208221435,
|
|
"epoch": 3.036503362151777,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004090094524624658,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.2425854980945587,
|
|
"num_tokens": 72476379.0,
|
|
"step": 31610
|
|
},
|
|
{
|
|
"entropy": 5.214470767974854,
|
|
"epoch": 3.036983669548511,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040898191151045717,
|
|
"loss": 4.734,
|
|
"mean_token_accuracy": 0.24410388618707657,
|
|
"num_tokens": 72488249.0,
|
|
"step": 31615
|
|
},
|
|
{
|
|
"entropy": 5.164141416549683,
|
|
"epoch": 3.037463976945245,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004089543674477864,
|
|
"loss": 4.6995,
|
|
"mean_token_accuracy": 0.24072018563747405,
|
|
"num_tokens": 72499365.0,
|
|
"step": 31620
|
|
},
|
|
{
|
|
"entropy": 5.12713737487793,
|
|
"epoch": 3.037944284341979,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004089268202750929,
|
|
"loss": 4.7028,
|
|
"mean_token_accuracy": 0.2410147786140442,
|
|
"num_tokens": 72511231.0,
|
|
"step": 31625
|
|
},
|
|
{
|
|
"entropy": 5.126743936538697,
|
|
"epoch": 3.0384245917387127,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040889926999301634,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.24600735157728196,
|
|
"num_tokens": 72524357.0,
|
|
"step": 31630
|
|
},
|
|
{
|
|
"entropy": 5.212428331375122,
|
|
"epoch": 3.0389048991354466,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004088717166021964,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.23906245529651643,
|
|
"num_tokens": 72537170.0,
|
|
"step": 31635
|
|
},
|
|
{
|
|
"entropy": 5.11562933921814,
|
|
"epoch": 3.0393852065321805,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004088441601032727,
|
|
"loss": 4.6596,
|
|
"mean_token_accuracy": 0.24886415302753448,
|
|
"num_tokens": 72548631.0,
|
|
"step": 31640
|
|
},
|
|
{
|
|
"entropy": 5.10996150970459,
|
|
"epoch": 3.0398655139289144,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004088166004968849,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.24465307146310805,
|
|
"num_tokens": 72561787.0,
|
|
"step": 31645
|
|
},
|
|
{
|
|
"entropy": 5.148533821105957,
|
|
"epoch": 3.0403458213256482,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040878903778367317,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.24226536452770234,
|
|
"num_tokens": 72572480.0,
|
|
"step": 31650
|
|
},
|
|
{
|
|
"entropy": 5.160731220245362,
|
|
"epoch": 3.040826128722382,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004087614719642772,
|
|
"loss": 4.7525,
|
|
"mean_token_accuracy": 0.23278530985116958,
|
|
"num_tokens": 72584636.0,
|
|
"step": 31655
|
|
},
|
|
{
|
|
"entropy": 5.202339029312133,
|
|
"epoch": 3.0413064361191164,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040873390303933693,
|
|
"loss": 4.7805,
|
|
"mean_token_accuracy": 0.24051880985498428,
|
|
"num_tokens": 72595425.0,
|
|
"step": 31660
|
|
},
|
|
{
|
|
"entropy": 5.245622634887695,
|
|
"epoch": 3.0417867435158503,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00040870633100949266,
|
|
"loss": 4.761,
|
|
"mean_token_accuracy": 0.24231055080890657,
|
|
"num_tokens": 72607344.0,
|
|
"step": 31665
|
|
},
|
|
{
|
|
"entropy": 5.153373670578003,
|
|
"epoch": 3.042267050912584,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00040867875587538436,
|
|
"loss": 4.7781,
|
|
"mean_token_accuracy": 0.24159275144338607,
|
|
"num_tokens": 72619704.0,
|
|
"step": 31670
|
|
},
|
|
{
|
|
"entropy": 5.1373241424560545,
|
|
"epoch": 3.042747358309318,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004086511776376523,
|
|
"loss": 4.6801,
|
|
"mean_token_accuracy": 0.24895088523626327,
|
|
"num_tokens": 72632143.0,
|
|
"step": 31675
|
|
},
|
|
{
|
|
"entropy": 5.171732187271118,
|
|
"epoch": 3.043227665706052,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00040862359629693684,
|
|
"loss": 4.701,
|
|
"mean_token_accuracy": 0.24072470217943193,
|
|
"num_tokens": 72644581.0,
|
|
"step": 31680
|
|
},
|
|
{
|
|
"entropy": 5.2045488357543945,
|
|
"epoch": 3.043707973102786,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004085960118538781,
|
|
"loss": 4.7713,
|
|
"mean_token_accuracy": 0.23900470286607742,
|
|
"num_tokens": 72656309.0,
|
|
"step": 31685
|
|
},
|
|
{
|
|
"entropy": 5.187387704849243,
|
|
"epoch": 3.0441882804995197,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004085684243091168,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.23844507932662964,
|
|
"num_tokens": 72668347.0,
|
|
"step": 31690
|
|
},
|
|
{
|
|
"entropy": 5.07761287689209,
|
|
"epoch": 3.0446685878962536,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004085408336632933,
|
|
"loss": 4.6584,
|
|
"mean_token_accuracy": 0.24468964636325835,
|
|
"num_tokens": 72679375.0,
|
|
"step": 31695
|
|
},
|
|
{
|
|
"entropy": 5.145705938339233,
|
|
"epoch": 3.0451488952929875,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00040851323991704803,
|
|
"loss": 4.7192,
|
|
"mean_token_accuracy": 0.24448172003030777,
|
|
"num_tokens": 72691020.0,
|
|
"step": 31700
|
|
},
|
|
{
|
|
"entropy": 5.166021728515625,
|
|
"epoch": 3.0456292026897214,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004084856430710219,
|
|
"loss": 4.6794,
|
|
"mean_token_accuracy": 0.24286409914493562,
|
|
"num_tokens": 72703215.0,
|
|
"step": 31705
|
|
},
|
|
{
|
|
"entropy": 5.1739555358886715,
|
|
"epoch": 3.0461095100864553,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004084580431258555,
|
|
"loss": 4.7061,
|
|
"mean_token_accuracy": 0.23954640775918962,
|
|
"num_tokens": 72715107.0,
|
|
"step": 31710
|
|
},
|
|
{
|
|
"entropy": 5.169467926025391,
|
|
"epoch": 3.046589817483189,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004084304400821896,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.237743479013443,
|
|
"num_tokens": 72726301.0,
|
|
"step": 31715
|
|
},
|
|
{
|
|
"entropy": 5.128793430328369,
|
|
"epoch": 3.047070124879923,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004084028339406651,
|
|
"loss": 4.7138,
|
|
"mean_token_accuracy": 0.24522869288921356,
|
|
"num_tokens": 72738102.0,
|
|
"step": 31720
|
|
},
|
|
{
|
|
"entropy": 5.142139148712158,
|
|
"epoch": 3.047550432276657,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040837522470192297,
|
|
"loss": 4.7611,
|
|
"mean_token_accuracy": 0.24218156635761262,
|
|
"num_tokens": 72748840.0,
|
|
"step": 31725
|
|
},
|
|
{
|
|
"entropy": 5.065821552276612,
|
|
"epoch": 3.0480307396733908,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004083476123666041,
|
|
"loss": 4.5885,
|
|
"mean_token_accuracy": 0.26222154349088667,
|
|
"num_tokens": 72760480.0,
|
|
"step": 31730
|
|
},
|
|
{
|
|
"entropy": 5.1367809772491455,
|
|
"epoch": 3.048511047070125,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004083199969353496,
|
|
"loss": 4.6683,
|
|
"mean_token_accuracy": 0.25184184312820435,
|
|
"num_tokens": 72770446.0,
|
|
"step": 31735
|
|
},
|
|
{
|
|
"entropy": 5.109501743316651,
|
|
"epoch": 3.048991354466859,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00040829237840880075,
|
|
"loss": 4.6981,
|
|
"mean_token_accuracy": 0.2409219816327095,
|
|
"num_tokens": 72782262.0,
|
|
"step": 31740
|
|
},
|
|
{
|
|
"entropy": 5.152459144592285,
|
|
"epoch": 3.049471661863593,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040826475678759855,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.24652656316757202,
|
|
"num_tokens": 72793857.0,
|
|
"step": 31745
|
|
},
|
|
{
|
|
"entropy": 5.1566078662872314,
|
|
"epoch": 3.0499519692603267,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004082371320723845,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.2347189486026764,
|
|
"num_tokens": 72805396.0,
|
|
"step": 31750
|
|
},
|
|
{
|
|
"entropy": 5.199008989334106,
|
|
"epoch": 3.0504322766570606,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040820950426379986,
|
|
"loss": 4.7757,
|
|
"mean_token_accuracy": 0.2438274472951889,
|
|
"num_tokens": 72816946.0,
|
|
"step": 31755
|
|
},
|
|
{
|
|
"entropy": 5.133043813705444,
|
|
"epoch": 3.0509125840537945,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004081818733624861,
|
|
"loss": 4.6366,
|
|
"mean_token_accuracy": 0.2532357797026634,
|
|
"num_tokens": 72827589.0,
|
|
"step": 31760
|
|
},
|
|
{
|
|
"entropy": 5.106831645965576,
|
|
"epoch": 3.0513928914505284,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004081542393690847,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.2464718371629715,
|
|
"num_tokens": 72838333.0,
|
|
"step": 31765
|
|
},
|
|
{
|
|
"entropy": 5.1430987358093265,
|
|
"epoch": 3.0518731988472623,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004081266022842372,
|
|
"loss": 4.6825,
|
|
"mean_token_accuracy": 0.24736190736293792,
|
|
"num_tokens": 72850212.0,
|
|
"step": 31770
|
|
},
|
|
{
|
|
"entropy": 5.180472993850708,
|
|
"epoch": 3.052353506243996,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00040809896210858537,
|
|
"loss": 4.6396,
|
|
"mean_token_accuracy": 0.24312705248594285,
|
|
"num_tokens": 72861406.0,
|
|
"step": 31775
|
|
},
|
|
{
|
|
"entropy": 5.14213809967041,
|
|
"epoch": 3.05283381364073,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040807131884277085,
|
|
"loss": 4.7278,
|
|
"mean_token_accuracy": 0.25352590084075927,
|
|
"num_tokens": 72872563.0,
|
|
"step": 31780
|
|
},
|
|
{
|
|
"entropy": 5.210968971252441,
|
|
"epoch": 3.053314121037464,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004080436724874354,
|
|
"loss": 4.769,
|
|
"mean_token_accuracy": 0.24007954597473144,
|
|
"num_tokens": 72883718.0,
|
|
"step": 31785
|
|
},
|
|
{
|
|
"entropy": 5.216419982910156,
|
|
"epoch": 3.053794428434198,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00040801602304322095,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.23996955752372742,
|
|
"num_tokens": 72896423.0,
|
|
"step": 31790
|
|
},
|
|
{
|
|
"entropy": 5.257101726531983,
|
|
"epoch": 3.0542747358309317,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040798837051076944,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.22880117744207382,
|
|
"num_tokens": 72907681.0,
|
|
"step": 31795
|
|
},
|
|
{
|
|
"entropy": 5.100228357315063,
|
|
"epoch": 3.0547550432276656,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040796071489072286,
|
|
"loss": 4.6109,
|
|
"mean_token_accuracy": 0.24865949004888535,
|
|
"num_tokens": 72919782.0,
|
|
"step": 31800
|
|
},
|
|
{
|
|
"entropy": 5.10189118385315,
|
|
"epoch": 3.0552353506243994,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004079330561837233,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.2455490931868553,
|
|
"num_tokens": 72931458.0,
|
|
"step": 31805
|
|
},
|
|
{
|
|
"entropy": 5.179701232910157,
|
|
"epoch": 3.0557156580211333,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040790539439041287,
|
|
"loss": 4.776,
|
|
"mean_token_accuracy": 0.23518899381160735,
|
|
"num_tokens": 72942415.0,
|
|
"step": 31810
|
|
},
|
|
{
|
|
"entropy": 5.106736135482788,
|
|
"epoch": 3.0561959654178676,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00040787772951143386,
|
|
"loss": 4.5336,
|
|
"mean_token_accuracy": 0.2576321944594383,
|
|
"num_tokens": 72953134.0,
|
|
"step": 31815
|
|
},
|
|
{
|
|
"entropy": 5.09008526802063,
|
|
"epoch": 3.0566762728146015,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004078500615474285,
|
|
"loss": 4.6689,
|
|
"mean_token_accuracy": 0.24289832264184952,
|
|
"num_tokens": 72964390.0,
|
|
"step": 31820
|
|
},
|
|
{
|
|
"entropy": 5.101112985610962,
|
|
"epoch": 3.0571565802113354,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040782239049903926,
|
|
"loss": 4.7085,
|
|
"mean_token_accuracy": 0.24442487508058547,
|
|
"num_tokens": 72976899.0,
|
|
"step": 31825
|
|
},
|
|
{
|
|
"entropy": 5.188674259185791,
|
|
"epoch": 3.0576368876080693,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040779471636690845,
|
|
"loss": 4.7838,
|
|
"mean_token_accuracy": 0.2470595955848694,
|
|
"num_tokens": 72989074.0,
|
|
"step": 31830
|
|
},
|
|
{
|
|
"entropy": 5.159616374969483,
|
|
"epoch": 3.058117195004803,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040776703915167866,
|
|
"loss": 4.7187,
|
|
"mean_token_accuracy": 0.2418240264058113,
|
|
"num_tokens": 73000434.0,
|
|
"step": 31835
|
|
},
|
|
{
|
|
"entropy": 5.1052977561950685,
|
|
"epoch": 3.058597502401537,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040773935885399254,
|
|
"loss": 4.6986,
|
|
"mean_token_accuracy": 0.24390469044446944,
|
|
"num_tokens": 73011902.0,
|
|
"step": 31840
|
|
},
|
|
{
|
|
"entropy": 5.225247383117676,
|
|
"epoch": 3.059077809798271,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004077116754744926,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.23881346434354783,
|
|
"num_tokens": 73022349.0,
|
|
"step": 31845
|
|
},
|
|
{
|
|
"entropy": 5.1109534740448,
|
|
"epoch": 3.059558117195005,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040768398901382157,
|
|
"loss": 4.6413,
|
|
"mean_token_accuracy": 0.25469513833522794,
|
|
"num_tokens": 73033958.0,
|
|
"step": 31850
|
|
},
|
|
{
|
|
"entropy": 5.093298101425171,
|
|
"epoch": 3.0600384245917387,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004076562994726223,
|
|
"loss": 4.6332,
|
|
"mean_token_accuracy": 0.2549673616886139,
|
|
"num_tokens": 73045807.0,
|
|
"step": 31855
|
|
},
|
|
{
|
|
"entropy": 5.1706451892852785,
|
|
"epoch": 3.0605187319884726,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004076286068515378,
|
|
"loss": 4.6629,
|
|
"mean_token_accuracy": 0.24987491220235825,
|
|
"num_tokens": 73056883.0,
|
|
"step": 31860
|
|
},
|
|
{
|
|
"entropy": 5.175310850143433,
|
|
"epoch": 3.0609990393852065,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004076009111512108,
|
|
"loss": 4.6733,
|
|
"mean_token_accuracy": 0.24765457957983017,
|
|
"num_tokens": 73067924.0,
|
|
"step": 31865
|
|
},
|
|
{
|
|
"entropy": 5.130523157119751,
|
|
"epoch": 3.0614793467819403,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004075732123722844,
|
|
"loss": 4.7123,
|
|
"mean_token_accuracy": 0.23919830322265626,
|
|
"num_tokens": 73079965.0,
|
|
"step": 31870
|
|
},
|
|
{
|
|
"entropy": 5.142838859558106,
|
|
"epoch": 3.061959654178674,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004075455105154016,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.2420002669095993,
|
|
"num_tokens": 73091986.0,
|
|
"step": 31875
|
|
},
|
|
{
|
|
"entropy": 5.234872674942016,
|
|
"epoch": 3.062439961575408,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00040751780558120573,
|
|
"loss": 4.7568,
|
|
"mean_token_accuracy": 0.23690957129001616,
|
|
"num_tokens": 73102445.0,
|
|
"step": 31880
|
|
},
|
|
{
|
|
"entropy": 5.179855489730835,
|
|
"epoch": 3.062920268972142,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004074900975703398,
|
|
"loss": 4.6635,
|
|
"mean_token_accuracy": 0.24575208276510238,
|
|
"num_tokens": 73112921.0,
|
|
"step": 31885
|
|
},
|
|
{
|
|
"entropy": 5.174446868896484,
|
|
"epoch": 3.063400576368876,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004074623864834473,
|
|
"loss": 4.7067,
|
|
"mean_token_accuracy": 0.2418326035141945,
|
|
"num_tokens": 73123653.0,
|
|
"step": 31890
|
|
},
|
|
{
|
|
"entropy": 5.157104396820069,
|
|
"epoch": 3.06388088376561,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004074346723211715,
|
|
"loss": 4.7001,
|
|
"mean_token_accuracy": 0.25098772197961805,
|
|
"num_tokens": 73135568.0,
|
|
"step": 31895
|
|
},
|
|
{
|
|
"entropy": 5.057322311401367,
|
|
"epoch": 3.064361191162344,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00040740695508415583,
|
|
"loss": 4.6604,
|
|
"mean_token_accuracy": 0.24758532792329788,
|
|
"num_tokens": 73145964.0,
|
|
"step": 31900
|
|
},
|
|
{
|
|
"entropy": 5.052099561691284,
|
|
"epoch": 3.064841498559078,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040737923477304386,
|
|
"loss": 4.6103,
|
|
"mean_token_accuracy": 0.2509263813495636,
|
|
"num_tokens": 73156941.0,
|
|
"step": 31905
|
|
},
|
|
{
|
|
"entropy": 5.148358631134033,
|
|
"epoch": 3.065321805955812,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040735151138847917,
|
|
"loss": 4.6302,
|
|
"mean_token_accuracy": 0.24455084949731826,
|
|
"num_tokens": 73167928.0,
|
|
"step": 31910
|
|
},
|
|
{
|
|
"entropy": 5.102109336853028,
|
|
"epoch": 3.0658021133525457,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004073237849311053,
|
|
"loss": 4.6318,
|
|
"mean_token_accuracy": 0.2494472473859787,
|
|
"num_tokens": 73179861.0,
|
|
"step": 31915
|
|
},
|
|
{
|
|
"entropy": 5.153822660446167,
|
|
"epoch": 3.0662824207492796,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004072960554015661,
|
|
"loss": 4.769,
|
|
"mean_token_accuracy": 0.24231611043214799,
|
|
"num_tokens": 73191152.0,
|
|
"step": 31920
|
|
},
|
|
{
|
|
"entropy": 5.12549729347229,
|
|
"epoch": 3.0667627281460135,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004072683228005055,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.24864929914474487,
|
|
"num_tokens": 73202952.0,
|
|
"step": 31925
|
|
},
|
|
{
|
|
"entropy": 5.081151056289673,
|
|
"epoch": 3.0672430355427474,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040724058712856697,
|
|
"loss": 4.6205,
|
|
"mean_token_accuracy": 0.24818470627069472,
|
|
"num_tokens": 73214899.0,
|
|
"step": 31930
|
|
},
|
|
{
|
|
"entropy": 5.114001798629761,
|
|
"epoch": 3.0677233429394812,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004072128483863948,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.24307787418365479,
|
|
"num_tokens": 73226599.0,
|
|
"step": 31935
|
|
},
|
|
{
|
|
"entropy": 5.107784032821655,
|
|
"epoch": 3.068203650336215,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004071851065746328,
|
|
"loss": 4.6162,
|
|
"mean_token_accuracy": 0.2462075799703598,
|
|
"num_tokens": 73238588.0,
|
|
"step": 31940
|
|
},
|
|
{
|
|
"entropy": 5.199315738677979,
|
|
"epoch": 3.068683957732949,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004071573616939252,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.24113891124725342,
|
|
"num_tokens": 73250727.0,
|
|
"step": 31945
|
|
},
|
|
{
|
|
"entropy": 5.119432497024536,
|
|
"epoch": 3.069164265129683,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004071296137449161,
|
|
"loss": 4.641,
|
|
"mean_token_accuracy": 0.25550548285245894,
|
|
"num_tokens": 73261937.0,
|
|
"step": 31950
|
|
},
|
|
{
|
|
"entropy": 5.069135141372681,
|
|
"epoch": 3.0696445725264168,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040710186272824967,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.2424317106604576,
|
|
"num_tokens": 73274853.0,
|
|
"step": 31955
|
|
},
|
|
{
|
|
"entropy": 5.157767581939697,
|
|
"epoch": 3.0701248799231506,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004070741086445703,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.23910710513591765,
|
|
"num_tokens": 73284901.0,
|
|
"step": 31960
|
|
},
|
|
{
|
|
"entropy": 5.120964050292969,
|
|
"epoch": 3.0706051873198845,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040704635149452223,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.24439673870801926,
|
|
"num_tokens": 73295989.0,
|
|
"step": 31965
|
|
},
|
|
{
|
|
"entropy": 5.208907175064087,
|
|
"epoch": 3.071085494716619,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040701859127875,
|
|
"loss": 4.7926,
|
|
"mean_token_accuracy": 0.23286982327699662,
|
|
"num_tokens": 73306661.0,
|
|
"step": 31970
|
|
},
|
|
{
|
|
"entropy": 5.2452332973480225,
|
|
"epoch": 3.0715658021133527,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040699082799789814,
|
|
"loss": 4.776,
|
|
"mean_token_accuracy": 0.2342320427298546,
|
|
"num_tokens": 73318456.0,
|
|
"step": 31975
|
|
},
|
|
{
|
|
"entropy": 5.225047159194946,
|
|
"epoch": 3.0720461095100866,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00040696306165261117,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.2379014104604721,
|
|
"num_tokens": 73330577.0,
|
|
"step": 31980
|
|
},
|
|
{
|
|
"entropy": 5.162475681304931,
|
|
"epoch": 3.0725264169068205,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004069352922435337,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.2462288871407509,
|
|
"num_tokens": 73341682.0,
|
|
"step": 31985
|
|
},
|
|
{
|
|
"entropy": 5.154619407653809,
|
|
"epoch": 3.0730067243035544,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004069075197713106,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.24385349452495575,
|
|
"num_tokens": 73352924.0,
|
|
"step": 31990
|
|
},
|
|
{
|
|
"entropy": 5.149204397201538,
|
|
"epoch": 3.0734870317002883,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040687974423658655,
|
|
"loss": 4.7344,
|
|
"mean_token_accuracy": 0.24540336579084396,
|
|
"num_tokens": 73364904.0,
|
|
"step": 31995
|
|
},
|
|
{
|
|
"entropy": 5.168240690231324,
|
|
"epoch": 3.073967339097022,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040685196564000644,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.24216135889291762,
|
|
"num_tokens": 73376680.0,
|
|
"step": 32000
|
|
},
|
|
{
|
|
"entropy": 5.12242169380188,
|
|
"epoch": 3.074447646493756,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00040682418398221517,
|
|
"loss": 4.6641,
|
|
"mean_token_accuracy": 0.24870889037847518,
|
|
"num_tokens": 73388631.0,
|
|
"step": 32005
|
|
},
|
|
{
|
|
"entropy": 5.119266510009766,
|
|
"epoch": 3.07492795389049,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040679639926385783,
|
|
"loss": 4.6757,
|
|
"mean_token_accuracy": 0.2475368469953537,
|
|
"num_tokens": 73400953.0,
|
|
"step": 32010
|
|
},
|
|
{
|
|
"entropy": 5.133496332168579,
|
|
"epoch": 3.0754082612872238,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004067686114855794,
|
|
"loss": 4.5995,
|
|
"mean_token_accuracy": 0.25181301683187485,
|
|
"num_tokens": 73411167.0,
|
|
"step": 32015
|
|
},
|
|
{
|
|
"entropy": 5.0052581310272215,
|
|
"epoch": 3.0758885686839577,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040674082064802507,
|
|
"loss": 4.6405,
|
|
"mean_token_accuracy": 0.2517711102962494,
|
|
"num_tokens": 73422434.0,
|
|
"step": 32020
|
|
},
|
|
{
|
|
"entropy": 5.215702772140503,
|
|
"epoch": 3.0763688760806915,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004067130267518401,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.23716977536678313,
|
|
"num_tokens": 73433543.0,
|
|
"step": 32025
|
|
},
|
|
{
|
|
"entropy": 5.253855991363525,
|
|
"epoch": 3.0768491834774254,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004066852297976698,
|
|
"loss": 4.9024,
|
|
"mean_token_accuracy": 0.2286639541387558,
|
|
"num_tokens": 73444624.0,
|
|
"step": 32030
|
|
},
|
|
{
|
|
"entropy": 5.144961357116699,
|
|
"epoch": 3.0773294908741593,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004066574297861595,
|
|
"loss": 4.7004,
|
|
"mean_token_accuracy": 0.24410452097654342,
|
|
"num_tokens": 73454446.0,
|
|
"step": 32035
|
|
},
|
|
{
|
|
"entropy": 5.137217855453491,
|
|
"epoch": 3.077809798270893,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00040662962671795454,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.23579273521900176,
|
|
"num_tokens": 73465557.0,
|
|
"step": 32040
|
|
},
|
|
{
|
|
"entropy": 5.198558378219604,
|
|
"epoch": 3.0782901056676275,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004066018205937006,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.24388012290000916,
|
|
"num_tokens": 73477939.0,
|
|
"step": 32045
|
|
},
|
|
{
|
|
"entropy": 5.127918481826782,
|
|
"epoch": 3.0787704130643614,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004065740114140431,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.24430853575468064,
|
|
"num_tokens": 73490715.0,
|
|
"step": 32050
|
|
},
|
|
{
|
|
"entropy": 5.120150423049926,
|
|
"epoch": 3.0792507204610953,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00040654619917962774,
|
|
"loss": 4.6672,
|
|
"mean_token_accuracy": 0.2441734105348587,
|
|
"num_tokens": 73503147.0,
|
|
"step": 32055
|
|
},
|
|
{
|
|
"entropy": 5.208631229400635,
|
|
"epoch": 3.079731027857829,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004065183838911003,
|
|
"loss": 4.7351,
|
|
"mean_token_accuracy": 0.2407555639743805,
|
|
"num_tokens": 73514750.0,
|
|
"step": 32060
|
|
},
|
|
{
|
|
"entropy": 5.129000997543335,
|
|
"epoch": 3.080211335254563,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004064905655491065,
|
|
"loss": 4.7055,
|
|
"mean_token_accuracy": 0.247677943110466,
|
|
"num_tokens": 73525845.0,
|
|
"step": 32065
|
|
},
|
|
{
|
|
"entropy": 5.211631822586059,
|
|
"epoch": 3.080691642651297,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00040646274415429224,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.23824138194322586,
|
|
"num_tokens": 73537086.0,
|
|
"step": 32070
|
|
},
|
|
{
|
|
"entropy": 5.10782527923584,
|
|
"epoch": 3.081171950048031,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004064349197073033,
|
|
"loss": 4.6553,
|
|
"mean_token_accuracy": 0.2502602204680443,
|
|
"num_tokens": 73548708.0,
|
|
"step": 32075
|
|
},
|
|
{
|
|
"entropy": 5.208362674713134,
|
|
"epoch": 3.0816522574447647,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004064070922087859,
|
|
"loss": 4.7432,
|
|
"mean_token_accuracy": 0.23852650970220565,
|
|
"num_tokens": 73559703.0,
|
|
"step": 32080
|
|
},
|
|
{
|
|
"entropy": 5.124740362167358,
|
|
"epoch": 3.0821325648414986,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040637926165938606,
|
|
"loss": 4.6325,
|
|
"mean_token_accuracy": 0.24807916581630707,
|
|
"num_tokens": 73570858.0,
|
|
"step": 32085
|
|
},
|
|
{
|
|
"entropy": 5.110561418533325,
|
|
"epoch": 3.0826128722382324,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040635142805974986,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.24499464631080628,
|
|
"num_tokens": 73583442.0,
|
|
"step": 32090
|
|
},
|
|
{
|
|
"entropy": 5.139330101013184,
|
|
"epoch": 3.0830931796349663,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004063235914105235,
|
|
"loss": 4.7378,
|
|
"mean_token_accuracy": 0.24056018888950348,
|
|
"num_tokens": 73595336.0,
|
|
"step": 32095
|
|
},
|
|
{
|
|
"entropy": 5.092437076568603,
|
|
"epoch": 3.0835734870317,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040629575171235327,
|
|
"loss": 4.7241,
|
|
"mean_token_accuracy": 0.2335670217871666,
|
|
"num_tokens": 73606582.0,
|
|
"step": 32100
|
|
},
|
|
{
|
|
"entropy": 5.192134189605713,
|
|
"epoch": 3.084053794428434,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004062679089658856,
|
|
"loss": 4.738,
|
|
"mean_token_accuracy": 0.24586152285337448,
|
|
"num_tokens": 73618432.0,
|
|
"step": 32105
|
|
},
|
|
{
|
|
"entropy": 5.133797979354858,
|
|
"epoch": 3.084534101825168,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00040624006317176685,
|
|
"loss": 4.6025,
|
|
"mean_token_accuracy": 0.2502001851797104,
|
|
"num_tokens": 73628880.0,
|
|
"step": 32110
|
|
},
|
|
{
|
|
"entropy": 5.121675586700439,
|
|
"epoch": 3.085014409221902,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040621221433064354,
|
|
"loss": 4.7054,
|
|
"mean_token_accuracy": 0.24323211312294007,
|
|
"num_tokens": 73639813.0,
|
|
"step": 32115
|
|
},
|
|
{
|
|
"entropy": 5.25922155380249,
|
|
"epoch": 3.0854947166186357,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004061843624431623,
|
|
"loss": 4.8776,
|
|
"mean_token_accuracy": 0.23531562089920044,
|
|
"num_tokens": 73651276.0,
|
|
"step": 32120
|
|
},
|
|
{
|
|
"entropy": 5.158939599990845,
|
|
"epoch": 3.08597502401537,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00040615650750996956,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.24756043255329133,
|
|
"num_tokens": 73663869.0,
|
|
"step": 32125
|
|
},
|
|
{
|
|
"entropy": 5.149884462356567,
|
|
"epoch": 3.086455331412104,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040612864953171223,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.2363823175430298,
|
|
"num_tokens": 73676089.0,
|
|
"step": 32130
|
|
},
|
|
{
|
|
"entropy": 5.154263067245483,
|
|
"epoch": 3.086935638808838,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040610078850903715,
|
|
"loss": 4.7103,
|
|
"mean_token_accuracy": 0.24147648215293885,
|
|
"num_tokens": 73688718.0,
|
|
"step": 32135
|
|
},
|
|
{
|
|
"entropy": 5.106658124923706,
|
|
"epoch": 3.0874159462055717,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040607292444259094,
|
|
"loss": 4.6496,
|
|
"mean_token_accuracy": 0.2482113465666771,
|
|
"num_tokens": 73700363.0,
|
|
"step": 32140
|
|
},
|
|
{
|
|
"entropy": 5.036934232711792,
|
|
"epoch": 3.0878962536023056,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004060450573330206,
|
|
"loss": 4.563,
|
|
"mean_token_accuracy": 0.24979182928800583,
|
|
"num_tokens": 73711873.0,
|
|
"step": 32145
|
|
},
|
|
{
|
|
"entropy": 5.11496901512146,
|
|
"epoch": 3.0883765609990395,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040601718718097325,
|
|
"loss": 4.6211,
|
|
"mean_token_accuracy": 0.24438033550977706,
|
|
"num_tokens": 73722466.0,
|
|
"step": 32150
|
|
},
|
|
{
|
|
"entropy": 5.134246921539306,
|
|
"epoch": 3.0888568683957733,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00040598931398709576,
|
|
"loss": 4.6854,
|
|
"mean_token_accuracy": 0.24802180975675583,
|
|
"num_tokens": 73734712.0,
|
|
"step": 32155
|
|
},
|
|
{
|
|
"entropy": 5.276463270187378,
|
|
"epoch": 3.089337175792507,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040596143775203534,
|
|
"loss": 4.8887,
|
|
"mean_token_accuracy": 0.2306375741958618,
|
|
"num_tokens": 73746367.0,
|
|
"step": 32160
|
|
},
|
|
{
|
|
"entropy": 5.1193047046661375,
|
|
"epoch": 3.089817483189241,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040593355847643933,
|
|
"loss": 4.6372,
|
|
"mean_token_accuracy": 0.255756139755249,
|
|
"num_tokens": 73758223.0,
|
|
"step": 32165
|
|
},
|
|
{
|
|
"entropy": 5.168850994110107,
|
|
"epoch": 3.090297790585975,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004059056761609548,
|
|
"loss": 4.7449,
|
|
"mean_token_accuracy": 0.23836323767900466,
|
|
"num_tokens": 73769278.0,
|
|
"step": 32170
|
|
},
|
|
{
|
|
"entropy": 5.138795042037964,
|
|
"epoch": 3.090778097982709,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004058777908062292,
|
|
"loss": 4.6786,
|
|
"mean_token_accuracy": 0.24323378056287764,
|
|
"num_tokens": 73778999.0,
|
|
"step": 32175
|
|
},
|
|
{
|
|
"entropy": 5.152171468734741,
|
|
"epoch": 3.0912584053794427,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004058499024129099,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.2410280004143715,
|
|
"num_tokens": 73789556.0,
|
|
"step": 32180
|
|
},
|
|
{
|
|
"entropy": 5.146829080581665,
|
|
"epoch": 3.0917387127761766,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040582201098164443,
|
|
"loss": 4.7075,
|
|
"mean_token_accuracy": 0.2453271821141243,
|
|
"num_tokens": 73800691.0,
|
|
"step": 32185
|
|
},
|
|
{
|
|
"entropy": 5.161119556427002,
|
|
"epoch": 3.0922190201729105,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040579411651308034,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.2411967098712921,
|
|
"num_tokens": 73811353.0,
|
|
"step": 32190
|
|
},
|
|
{
|
|
"entropy": 5.131231117248535,
|
|
"epoch": 3.0926993275696444,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00040576621900786523,
|
|
"loss": 4.6939,
|
|
"mean_token_accuracy": 0.24530881345272065,
|
|
"num_tokens": 73822531.0,
|
|
"step": 32195
|
|
},
|
|
{
|
|
"entropy": 5.176963138580322,
|
|
"epoch": 3.0931796349663783,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004057383184666468,
|
|
"loss": 4.757,
|
|
"mean_token_accuracy": 0.2357767105102539,
|
|
"num_tokens": 73833857.0,
|
|
"step": 32200
|
|
},
|
|
{
|
|
"entropy": 5.164080810546875,
|
|
"epoch": 3.0936599423631126,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040571041489007286,
|
|
"loss": 4.722,
|
|
"mean_token_accuracy": 0.24238646179437637,
|
|
"num_tokens": 73845664.0,
|
|
"step": 32205
|
|
},
|
|
{
|
|
"entropy": 5.124571895599365,
|
|
"epoch": 3.0941402497598465,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00040568250827879127,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.25469831973314283,
|
|
"num_tokens": 73856860.0,
|
|
"step": 32210
|
|
},
|
|
{
|
|
"entropy": 5.105336332321167,
|
|
"epoch": 3.0946205571565804,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004056545986334497,
|
|
"loss": 4.7329,
|
|
"mean_token_accuracy": 0.2452879801392555,
|
|
"num_tokens": 73867532.0,
|
|
"step": 32215
|
|
},
|
|
{
|
|
"entropy": 5.154278755187988,
|
|
"epoch": 3.0951008645533142,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004056266859546965,
|
|
"loss": 4.7454,
|
|
"mean_token_accuracy": 0.2387353762984276,
|
|
"num_tokens": 73880458.0,
|
|
"step": 32220
|
|
},
|
|
{
|
|
"entropy": 5.213191270828247,
|
|
"epoch": 3.095581171950048,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004055987702431795,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.2394198790192604,
|
|
"num_tokens": 73892842.0,
|
|
"step": 32225
|
|
},
|
|
{
|
|
"entropy": 5.155652809143066,
|
|
"epoch": 3.096061479346782,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040557085149954677,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.24252513200044631,
|
|
"num_tokens": 73903491.0,
|
|
"step": 32230
|
|
},
|
|
{
|
|
"entropy": 5.082308912277222,
|
|
"epoch": 3.096541786743516,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040554292972444663,
|
|
"loss": 4.6725,
|
|
"mean_token_accuracy": 0.24383601993322374,
|
|
"num_tokens": 73915255.0,
|
|
"step": 32235
|
|
},
|
|
{
|
|
"entropy": 5.101403522491455,
|
|
"epoch": 3.0970220941402498,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00040551500491852735,
|
|
"loss": 4.5839,
|
|
"mean_token_accuracy": 0.25664661824703217,
|
|
"num_tokens": 73925571.0,
|
|
"step": 32240
|
|
},
|
|
{
|
|
"entropy": 5.198448896408081,
|
|
"epoch": 3.0975024015369836,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004054870770824371,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.23730039596557617,
|
|
"num_tokens": 73936957.0,
|
|
"step": 32245
|
|
},
|
|
{
|
|
"entropy": 5.209801244735718,
|
|
"epoch": 3.0979827089337175,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040545914621682445,
|
|
"loss": 4.6537,
|
|
"mean_token_accuracy": 0.2525388687849045,
|
|
"num_tokens": 73948018.0,
|
|
"step": 32250
|
|
},
|
|
{
|
|
"entropy": 5.130172348022461,
|
|
"epoch": 3.0984630163304514,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004054312123223378,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.23772261142730713,
|
|
"num_tokens": 73958713.0,
|
|
"step": 32255
|
|
},
|
|
{
|
|
"entropy": 5.150218725204468,
|
|
"epoch": 3.0989433237271853,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040540327539962567,
|
|
"loss": 4.7715,
|
|
"mean_token_accuracy": 0.24261657148599625,
|
|
"num_tokens": 73969299.0,
|
|
"step": 32260
|
|
},
|
|
{
|
|
"entropy": 5.306479167938233,
|
|
"epoch": 3.099423631123919,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040537533544933674,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.2280011311173439,
|
|
"num_tokens": 73980149.0,
|
|
"step": 32265
|
|
},
|
|
{
|
|
"entropy": 5.171335315704345,
|
|
"epoch": 3.099903938520653,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004053473924721197,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.2434567466378212,
|
|
"num_tokens": 73991462.0,
|
|
"step": 32270
|
|
},
|
|
{
|
|
"entropy": 5.1976728439331055,
|
|
"epoch": 3.100384245917387,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004053194464686232,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.2330326870083809,
|
|
"num_tokens": 74003442.0,
|
|
"step": 32275
|
|
},
|
|
{
|
|
"entropy": 5.029257106781006,
|
|
"epoch": 3.1008645533141213,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004052914974394961,
|
|
"loss": 4.554,
|
|
"mean_token_accuracy": 0.2550989240407944,
|
|
"num_tokens": 74014394.0,
|
|
"step": 32280
|
|
},
|
|
{
|
|
"entropy": 5.227604246139526,
|
|
"epoch": 3.101344860710855,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040526354538538735,
|
|
"loss": 4.8234,
|
|
"mean_token_accuracy": 0.23796732425689698,
|
|
"num_tokens": 74025377.0,
|
|
"step": 32285
|
|
},
|
|
{
|
|
"entropy": 5.153126239776611,
|
|
"epoch": 3.101825168107589,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004052355903069459,
|
|
"loss": 4.6551,
|
|
"mean_token_accuracy": 0.24834902137517928,
|
|
"num_tokens": 74037094.0,
|
|
"step": 32290
|
|
},
|
|
{
|
|
"entropy": 5.061073684692383,
|
|
"epoch": 3.102305475504323,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004052076322048207,
|
|
"loss": 4.558,
|
|
"mean_token_accuracy": 0.2561584174633026,
|
|
"num_tokens": 74048043.0,
|
|
"step": 32295
|
|
},
|
|
{
|
|
"entropy": 5.1111555099487305,
|
|
"epoch": 3.1027857829010568,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00040517967107966095,
|
|
"loss": 4.7435,
|
|
"mean_token_accuracy": 0.23631277829408645,
|
|
"num_tokens": 74061026.0,
|
|
"step": 32300
|
|
},
|
|
{
|
|
"entropy": 5.177499532699585,
|
|
"epoch": 3.1032660902977907,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040515170693211584,
|
|
"loss": 4.7876,
|
|
"mean_token_accuracy": 0.23866722881793975,
|
|
"num_tokens": 74072930.0,
|
|
"step": 32305
|
|
},
|
|
{
|
|
"entropy": 5.173421239852905,
|
|
"epoch": 3.1037463976945245,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004051237397628345,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.24377389401197433,
|
|
"num_tokens": 74083847.0,
|
|
"step": 32310
|
|
},
|
|
{
|
|
"entropy": 5.205827236175537,
|
|
"epoch": 3.1042267050912584,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004050957695724663,
|
|
"loss": 4.7098,
|
|
"mean_token_accuracy": 0.24134963154792785,
|
|
"num_tokens": 74096187.0,
|
|
"step": 32315
|
|
},
|
|
{
|
|
"entropy": 5.121522331237793,
|
|
"epoch": 3.1047070124879923,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004050677963616607,
|
|
"loss": 4.6929,
|
|
"mean_token_accuracy": 0.2458855465054512,
|
|
"num_tokens": 74108894.0,
|
|
"step": 32320
|
|
},
|
|
{
|
|
"entropy": 5.093410301208496,
|
|
"epoch": 3.105187319884726,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040503982013106706,
|
|
"loss": 4.7668,
|
|
"mean_token_accuracy": 0.23979612141847612,
|
|
"num_tokens": 74119941.0,
|
|
"step": 32325
|
|
},
|
|
{
|
|
"entropy": 5.142340803146363,
|
|
"epoch": 3.10566762728146,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000405011840881335,
|
|
"loss": 4.6818,
|
|
"mean_token_accuracy": 0.24870577156543733,
|
|
"num_tokens": 74131550.0,
|
|
"step": 32330
|
|
},
|
|
{
|
|
"entropy": 5.122891235351562,
|
|
"epoch": 3.106147934678194,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004049838586131139,
|
|
"loss": 4.6131,
|
|
"mean_token_accuracy": 0.2519130870699883,
|
|
"num_tokens": 74142530.0,
|
|
"step": 32335
|
|
},
|
|
{
|
|
"entropy": 5.11582317352295,
|
|
"epoch": 3.106628242074928,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004049558733270537,
|
|
"loss": 4.7101,
|
|
"mean_token_accuracy": 0.23965898752212525,
|
|
"num_tokens": 74155117.0,
|
|
"step": 32340
|
|
},
|
|
{
|
|
"entropy": 5.20378851890564,
|
|
"epoch": 3.1071085494716617,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000404927885023804,
|
|
"loss": 4.8119,
|
|
"mean_token_accuracy": 0.23491472601890565,
|
|
"num_tokens": 74165880.0,
|
|
"step": 32345
|
|
},
|
|
{
|
|
"entropy": 5.0146870613098145,
|
|
"epoch": 3.1075888568683956,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040489989370401456,
|
|
"loss": 4.4977,
|
|
"mean_token_accuracy": 0.2599795043468475,
|
|
"num_tokens": 74175777.0,
|
|
"step": 32350
|
|
},
|
|
{
|
|
"entropy": 5.107920122146607,
|
|
"epoch": 3.1080691642651295,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004048718993683353,
|
|
"loss": 4.6818,
|
|
"mean_token_accuracy": 0.24574484676122665,
|
|
"num_tokens": 74187745.0,
|
|
"step": 32355
|
|
},
|
|
{
|
|
"entropy": 5.149761962890625,
|
|
"epoch": 3.108549471661864,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040484390201741627,
|
|
"loss": 4.6862,
|
|
"mean_token_accuracy": 0.2379585713148117,
|
|
"num_tokens": 74198606.0,
|
|
"step": 32360
|
|
},
|
|
{
|
|
"entropy": 5.262574815750122,
|
|
"epoch": 3.1090297790585977,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004048159016519073,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.22890110611915587,
|
|
"num_tokens": 74210530.0,
|
|
"step": 32365
|
|
},
|
|
{
|
|
"entropy": 5.086649799346924,
|
|
"epoch": 3.1095100864553316,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004047878982724586,
|
|
"loss": 4.658,
|
|
"mean_token_accuracy": 0.24405039995908737,
|
|
"num_tokens": 74222155.0,
|
|
"step": 32370
|
|
},
|
|
{
|
|
"entropy": 5.295310592651367,
|
|
"epoch": 3.1099903938520654,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040475989187972034,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.23490164577960967,
|
|
"num_tokens": 74233003.0,
|
|
"step": 32375
|
|
},
|
|
{
|
|
"entropy": 5.151399755477906,
|
|
"epoch": 3.1104707012487993,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040473188247434265,
|
|
"loss": 4.6196,
|
|
"mean_token_accuracy": 0.25154550820589067,
|
|
"num_tokens": 74244013.0,
|
|
"step": 32380
|
|
},
|
|
{
|
|
"entropy": 5.1276086330413815,
|
|
"epoch": 3.110951008645533,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00040470387005697587,
|
|
"loss": 4.7009,
|
|
"mean_token_accuracy": 0.24285753518342973,
|
|
"num_tokens": 74256010.0,
|
|
"step": 32385
|
|
},
|
|
{
|
|
"entropy": 5.251143741607666,
|
|
"epoch": 3.111431316042267,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004046758546282704,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.2368951603770256,
|
|
"num_tokens": 74268680.0,
|
|
"step": 32390
|
|
},
|
|
{
|
|
"entropy": 5.236994791030884,
|
|
"epoch": 3.111911623439001,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004046478361888766,
|
|
"loss": 4.8287,
|
|
"mean_token_accuracy": 0.23313190042972565,
|
|
"num_tokens": 74280807.0,
|
|
"step": 32395
|
|
},
|
|
{
|
|
"entropy": 5.148218393325806,
|
|
"epoch": 3.112391930835735,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000404619814739445,
|
|
"loss": 4.7534,
|
|
"mean_token_accuracy": 0.2393534943461418,
|
|
"num_tokens": 74292076.0,
|
|
"step": 32400
|
|
},
|
|
{
|
|
"entropy": 5.199115180969239,
|
|
"epoch": 3.1128722382324687,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004045917902806263,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.2437075972557068,
|
|
"num_tokens": 74303965.0,
|
|
"step": 32405
|
|
},
|
|
{
|
|
"entropy": 5.0533061027526855,
|
|
"epoch": 3.1133525456292026,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000404563762813071,
|
|
"loss": 4.6222,
|
|
"mean_token_accuracy": 0.2484365552663803,
|
|
"num_tokens": 74315774.0,
|
|
"step": 32410
|
|
},
|
|
{
|
|
"entropy": 5.115778255462646,
|
|
"epoch": 3.1138328530259365,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004045357323374298,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.24629587084054946,
|
|
"num_tokens": 74326624.0,
|
|
"step": 32415
|
|
},
|
|
{
|
|
"entropy": 5.162211561203003,
|
|
"epoch": 3.1143131604226704,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040450769885435364,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.23849097788333892,
|
|
"num_tokens": 74337595.0,
|
|
"step": 32420
|
|
},
|
|
{
|
|
"entropy": 5.18556170463562,
|
|
"epoch": 3.1147934678194042,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040447966236449313,
|
|
"loss": 4.6944,
|
|
"mean_token_accuracy": 0.24664094150066376,
|
|
"num_tokens": 74347695.0,
|
|
"step": 32425
|
|
},
|
|
{
|
|
"entropy": 5.071398687362671,
|
|
"epoch": 3.115273775216138,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00040445162286849935,
|
|
"loss": 4.6058,
|
|
"mean_token_accuracy": 0.2557909652590752,
|
|
"num_tokens": 74358491.0,
|
|
"step": 32430
|
|
},
|
|
{
|
|
"entropy": 5.172908592224121,
|
|
"epoch": 3.115754082612872,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040442358036702343,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.23958386480808258,
|
|
"num_tokens": 74371038.0,
|
|
"step": 32435
|
|
},
|
|
{
|
|
"entropy": 5.156137609481812,
|
|
"epoch": 3.1162343900096063,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004043955348607161,
|
|
"loss": 4.7216,
|
|
"mean_token_accuracy": 0.24851551055908203,
|
|
"num_tokens": 74381449.0,
|
|
"step": 32440
|
|
},
|
|
{
|
|
"entropy": 5.149456405639649,
|
|
"epoch": 3.11671469740634,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004043674863502288,
|
|
"loss": 4.6732,
|
|
"mean_token_accuracy": 0.24743663519620895,
|
|
"num_tokens": 74392970.0,
|
|
"step": 32445
|
|
},
|
|
{
|
|
"entropy": 5.105837106704712,
|
|
"epoch": 3.117195004803074,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00040433943483621253,
|
|
"loss": 4.612,
|
|
"mean_token_accuracy": 0.2466822311282158,
|
|
"num_tokens": 74404243.0,
|
|
"step": 32450
|
|
},
|
|
{
|
|
"entropy": 5.182582712173462,
|
|
"epoch": 3.117675312199808,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004043113803193187,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.24027082175016404,
|
|
"num_tokens": 74415546.0,
|
|
"step": 32455
|
|
},
|
|
{
|
|
"entropy": 5.098617792129517,
|
|
"epoch": 3.118155619596542,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040428332280019864,
|
|
"loss": 4.6788,
|
|
"mean_token_accuracy": 0.24867632389068603,
|
|
"num_tokens": 74427138.0,
|
|
"step": 32460
|
|
},
|
|
{
|
|
"entropy": 5.130516767501831,
|
|
"epoch": 3.1186359269932757,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004042552622795036,
|
|
"loss": 4.6143,
|
|
"mean_token_accuracy": 0.2443312019109726,
|
|
"num_tokens": 74438088.0,
|
|
"step": 32465
|
|
},
|
|
{
|
|
"entropy": 5.163979959487915,
|
|
"epoch": 3.1191162343900096,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004042271987578852,
|
|
"loss": 4.7661,
|
|
"mean_token_accuracy": 0.23883019834756852,
|
|
"num_tokens": 74450310.0,
|
|
"step": 32470
|
|
},
|
|
{
|
|
"entropy": 5.163835763931274,
|
|
"epoch": 3.1195965417867435,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040419913223599505,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.24487913846969606,
|
|
"num_tokens": 74461128.0,
|
|
"step": 32475
|
|
},
|
|
{
|
|
"entropy": 5.166586017608642,
|
|
"epoch": 3.1200768491834774,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040417106271448464,
|
|
"loss": 4.7346,
|
|
"mean_token_accuracy": 0.24654660671949385,
|
|
"num_tokens": 74472459.0,
|
|
"step": 32480
|
|
},
|
|
{
|
|
"entropy": 5.075335264205933,
|
|
"epoch": 3.1205571565802113,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004041429901940057,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.2491409435868263,
|
|
"num_tokens": 74485257.0,
|
|
"step": 32485
|
|
},
|
|
{
|
|
"entropy": 5.067234992980957,
|
|
"epoch": 3.121037463976945,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040411491467521,
|
|
"loss": 4.6284,
|
|
"mean_token_accuracy": 0.24726552218198777,
|
|
"num_tokens": 74496277.0,
|
|
"step": 32490
|
|
},
|
|
{
|
|
"entropy": 5.166469240188599,
|
|
"epoch": 3.121517771373679,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004040868361587494,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.24053015261888505,
|
|
"num_tokens": 74508083.0,
|
|
"step": 32495
|
|
},
|
|
{
|
|
"entropy": 5.245715856552124,
|
|
"epoch": 3.121998078770413,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004040587546452758,
|
|
"loss": 4.8796,
|
|
"mean_token_accuracy": 0.23144406974315643,
|
|
"num_tokens": 74520403.0,
|
|
"step": 32500
|
|
},
|
|
{
|
|
"entropy": 5.177587556838989,
|
|
"epoch": 3.122478386167147,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040403067013544116,
|
|
"loss": 4.7176,
|
|
"mean_token_accuracy": 0.24398790597915648,
|
|
"num_tokens": 74531657.0,
|
|
"step": 32505
|
|
},
|
|
{
|
|
"entropy": 5.168539333343506,
|
|
"epoch": 3.1229586935638807,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040400258262989744,
|
|
"loss": 4.6912,
|
|
"mean_token_accuracy": 0.24525805413722992,
|
|
"num_tokens": 74541841.0,
|
|
"step": 32510
|
|
},
|
|
{
|
|
"entropy": 5.225370407104492,
|
|
"epoch": 3.123439000960615,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00040397449212929676,
|
|
"loss": 4.7868,
|
|
"mean_token_accuracy": 0.23809233903884888,
|
|
"num_tokens": 74553312.0,
|
|
"step": 32515
|
|
},
|
|
{
|
|
"entropy": 5.172553825378418,
|
|
"epoch": 3.123919308357349,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004039463986342914,
|
|
"loss": 4.7535,
|
|
"mean_token_accuracy": 0.23972778171300888,
|
|
"num_tokens": 74564470.0,
|
|
"step": 32520
|
|
},
|
|
{
|
|
"entropy": 5.171434450149536,
|
|
"epoch": 3.1243996157540828,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040391830214553365,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.24201394468545914,
|
|
"num_tokens": 74575548.0,
|
|
"step": 32525
|
|
},
|
|
{
|
|
"entropy": 5.171947193145752,
|
|
"epoch": 3.1248799231508166,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004038902026636756,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.24629668593406678,
|
|
"num_tokens": 74587470.0,
|
|
"step": 32530
|
|
},
|
|
{
|
|
"entropy": 5.152751874923706,
|
|
"epoch": 3.1253602305475505,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004038621001893698,
|
|
"loss": 4.6478,
|
|
"mean_token_accuracy": 0.2490006536245346,
|
|
"num_tokens": 74598743.0,
|
|
"step": 32535
|
|
},
|
|
{
|
|
"entropy": 5.149413442611694,
|
|
"epoch": 3.1258405379442844,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040383399472326874,
|
|
"loss": 4.6982,
|
|
"mean_token_accuracy": 0.24384602904319763,
|
|
"num_tokens": 74609057.0,
|
|
"step": 32540
|
|
},
|
|
{
|
|
"entropy": 5.204260921478271,
|
|
"epoch": 3.1263208453410183,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00040380588626602484,
|
|
"loss": 4.7878,
|
|
"mean_token_accuracy": 0.236150424182415,
|
|
"num_tokens": 74620938.0,
|
|
"step": 32545
|
|
},
|
|
{
|
|
"entropy": 5.152799081802368,
|
|
"epoch": 3.126801152737752,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004037777748182907,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.2505915552377701,
|
|
"num_tokens": 74631877.0,
|
|
"step": 32550
|
|
},
|
|
{
|
|
"entropy": 5.169199991226196,
|
|
"epoch": 3.127281460134486,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004037496603807191,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.24417367130517958,
|
|
"num_tokens": 74641921.0,
|
|
"step": 32555
|
|
},
|
|
{
|
|
"entropy": 5.08069863319397,
|
|
"epoch": 3.12776176753122,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004037215429539626,
|
|
"loss": 4.6621,
|
|
"mean_token_accuracy": 0.24941371977329255,
|
|
"num_tokens": 74652950.0,
|
|
"step": 32560
|
|
},
|
|
{
|
|
"entropy": 5.1653283596038815,
|
|
"epoch": 3.128242074927954,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040369342253867413,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.24635832011699677,
|
|
"num_tokens": 74665512.0,
|
|
"step": 32565
|
|
},
|
|
{
|
|
"entropy": 5.18185601234436,
|
|
"epoch": 3.1287223823246877,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004036652991355066,
|
|
"loss": 4.7046,
|
|
"mean_token_accuracy": 0.25003670156002045,
|
|
"num_tokens": 74675833.0,
|
|
"step": 32570
|
|
},
|
|
{
|
|
"entropy": 5.043581295013428,
|
|
"epoch": 3.1292026897214216,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004036371727451128,
|
|
"loss": 4.6154,
|
|
"mean_token_accuracy": 0.2499663218855858,
|
|
"num_tokens": 74688356.0,
|
|
"step": 32575
|
|
},
|
|
{
|
|
"entropy": 5.064912033081055,
|
|
"epoch": 3.1296829971181555,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040360904336814586,
|
|
"loss": 4.652,
|
|
"mean_token_accuracy": 0.2477026805281639,
|
|
"num_tokens": 74699617.0,
|
|
"step": 32580
|
|
},
|
|
{
|
|
"entropy": 5.052552986145019,
|
|
"epoch": 3.1301633045148893,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004035809110052588,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.250621896982193,
|
|
"num_tokens": 74711319.0,
|
|
"step": 32585
|
|
},
|
|
{
|
|
"entropy": 5.068495225906372,
|
|
"epoch": 3.1306436119116237,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004035527756571048,
|
|
"loss": 4.6574,
|
|
"mean_token_accuracy": 0.24842144399881363,
|
|
"num_tokens": 74723378.0,
|
|
"step": 32590
|
|
},
|
|
{
|
|
"entropy": 5.126441478729248,
|
|
"epoch": 3.1311239193083575,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00040352463732433707,
|
|
"loss": 4.7069,
|
|
"mean_token_accuracy": 0.24138143360614778,
|
|
"num_tokens": 74734011.0,
|
|
"step": 32595
|
|
},
|
|
{
|
|
"entropy": 5.133939027786255,
|
|
"epoch": 3.1316042267050914,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040349649600760894,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.2508859381079674,
|
|
"num_tokens": 74745534.0,
|
|
"step": 32600
|
|
},
|
|
{
|
|
"entropy": 5.184495973587036,
|
|
"epoch": 3.1320845341018253,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004034683517075737,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.2478151649236679,
|
|
"num_tokens": 74757288.0,
|
|
"step": 32605
|
|
},
|
|
{
|
|
"entropy": 5.1084681987762455,
|
|
"epoch": 3.132564841498559,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040344020442488476,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.2413388356566429,
|
|
"num_tokens": 74770520.0,
|
|
"step": 32610
|
|
},
|
|
{
|
|
"entropy": 5.089059257507325,
|
|
"epoch": 3.133045148895293,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040341205416019577,
|
|
"loss": 4.6526,
|
|
"mean_token_accuracy": 0.25263812839984895,
|
|
"num_tokens": 74781967.0,
|
|
"step": 32615
|
|
},
|
|
{
|
|
"entropy": 5.155272483825684,
|
|
"epoch": 3.133525456292027,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004033839009141601,
|
|
"loss": 4.7021,
|
|
"mean_token_accuracy": 0.2411336064338684,
|
|
"num_tokens": 74793022.0,
|
|
"step": 32620
|
|
},
|
|
{
|
|
"entropy": 5.139456415176392,
|
|
"epoch": 3.134005763688761,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00040335574468743145,
|
|
"loss": 4.6916,
|
|
"mean_token_accuracy": 0.25057646781206133,
|
|
"num_tokens": 74805165.0,
|
|
"step": 32625
|
|
},
|
|
{
|
|
"entropy": 5.118796443939209,
|
|
"epoch": 3.1344860710854947,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004033275854806636,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.24398700147867203,
|
|
"num_tokens": 74816607.0,
|
|
"step": 32630
|
|
},
|
|
{
|
|
"entropy": 5.117525386810303,
|
|
"epoch": 3.1349663784822286,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004032994232945103,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.24472275227308274,
|
|
"num_tokens": 74827606.0,
|
|
"step": 32635
|
|
},
|
|
{
|
|
"entropy": 5.126372575759888,
|
|
"epoch": 3.1354466858789625,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004032712581296253,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.24891693741083146,
|
|
"num_tokens": 74837507.0,
|
|
"step": 32640
|
|
},
|
|
{
|
|
"entropy": 5.160611724853515,
|
|
"epoch": 3.1359269932756964,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040324308998666267,
|
|
"loss": 4.7496,
|
|
"mean_token_accuracy": 0.2412009507417679,
|
|
"num_tokens": 74848164.0,
|
|
"step": 32645
|
|
},
|
|
{
|
|
"entropy": 5.167444562911987,
|
|
"epoch": 3.1364073006724302,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040321491886627614,
|
|
"loss": 4.6759,
|
|
"mean_token_accuracy": 0.2472422093153,
|
|
"num_tokens": 74858010.0,
|
|
"step": 32650
|
|
},
|
|
{
|
|
"entropy": 5.12895245552063,
|
|
"epoch": 3.136887608069164,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040318674476912006,
|
|
"loss": 4.6471,
|
|
"mean_token_accuracy": 0.2461197629570961,
|
|
"num_tokens": 74868654.0,
|
|
"step": 32655
|
|
},
|
|
{
|
|
"entropy": 5.197067213058472,
|
|
"epoch": 3.137367915465898,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004031585676958483,
|
|
"loss": 4.794,
|
|
"mean_token_accuracy": 0.2406579241156578,
|
|
"num_tokens": 74879751.0,
|
|
"step": 32660
|
|
},
|
|
{
|
|
"entropy": 5.158984136581421,
|
|
"epoch": 3.1378482228626323,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040313038764711517,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.24261709898710251,
|
|
"num_tokens": 74890569.0,
|
|
"step": 32665
|
|
},
|
|
{
|
|
"entropy": 5.20735239982605,
|
|
"epoch": 3.138328530259366,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00040310220462357494,
|
|
"loss": 4.7421,
|
|
"mean_token_accuracy": 0.2353273242712021,
|
|
"num_tokens": 74902078.0,
|
|
"step": 32670
|
|
},
|
|
{
|
|
"entropy": 5.1584573745727536,
|
|
"epoch": 3.1388088376561,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004030740186258819,
|
|
"loss": 4.7158,
|
|
"mean_token_accuracy": 0.24077963680028916,
|
|
"num_tokens": 74913228.0,
|
|
"step": 32675
|
|
},
|
|
{
|
|
"entropy": 5.147527408599854,
|
|
"epoch": 3.139289145052834,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004030458296546905,
|
|
"loss": 4.7138,
|
|
"mean_token_accuracy": 0.24514165371656418,
|
|
"num_tokens": 74925419.0,
|
|
"step": 32680
|
|
},
|
|
{
|
|
"entropy": 5.185752630233765,
|
|
"epoch": 3.139769452449568,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00040301763771065504,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.24120572209358215,
|
|
"num_tokens": 74936219.0,
|
|
"step": 32685
|
|
},
|
|
{
|
|
"entropy": 5.109808921813965,
|
|
"epoch": 3.1402497598463017,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004029894427944302,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.2499714121222496,
|
|
"num_tokens": 74948015.0,
|
|
"step": 32690
|
|
},
|
|
{
|
|
"entropy": 5.137356567382812,
|
|
"epoch": 3.1407300672430356,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040296124490667065,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.24607135504484176,
|
|
"num_tokens": 74959753.0,
|
|
"step": 32695
|
|
},
|
|
{
|
|
"entropy": 5.1185520648956295,
|
|
"epoch": 3.1412103746397695,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004029330440480308,
|
|
"loss": 4.6391,
|
|
"mean_token_accuracy": 0.2513972744345665,
|
|
"num_tokens": 74970696.0,
|
|
"step": 32700
|
|
},
|
|
{
|
|
"entropy": 5.170540523529053,
|
|
"epoch": 3.1416906820365034,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004029048402191656,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.24417130649089813,
|
|
"num_tokens": 74982070.0,
|
|
"step": 32705
|
|
},
|
|
{
|
|
"entropy": 5.130312824249268,
|
|
"epoch": 3.1421709894332372,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004028766334207299,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.2459976464509964,
|
|
"num_tokens": 74992823.0,
|
|
"step": 32710
|
|
},
|
|
{
|
|
"entropy": 5.034432601928711,
|
|
"epoch": 3.142651296829971,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004028484236533784,
|
|
"loss": 4.5928,
|
|
"mean_token_accuracy": 0.2498169869184494,
|
|
"num_tokens": 75004456.0,
|
|
"step": 32715
|
|
},
|
|
{
|
|
"entropy": 5.220001745223999,
|
|
"epoch": 3.143131604226705,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00040282021091776624,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.22986337095499038,
|
|
"num_tokens": 75017039.0,
|
|
"step": 32720
|
|
},
|
|
{
|
|
"entropy": 5.124684524536133,
|
|
"epoch": 3.143611911623439,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004027919952145482,
|
|
"loss": 4.654,
|
|
"mean_token_accuracy": 0.24679243415594102,
|
|
"num_tokens": 75028155.0,
|
|
"step": 32725
|
|
},
|
|
{
|
|
"entropy": 5.127170085906982,
|
|
"epoch": 3.1440922190201728,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004027637765443795,
|
|
"loss": 4.7059,
|
|
"mean_token_accuracy": 0.2420048251748085,
|
|
"num_tokens": 75039529.0,
|
|
"step": 32730
|
|
},
|
|
{
|
|
"entropy": 5.152038812637329,
|
|
"epoch": 3.1445725264169067,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00040273555490791534,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.238873091340065,
|
|
"num_tokens": 75051205.0,
|
|
"step": 32735
|
|
},
|
|
{
|
|
"entropy": 5.198554468154907,
|
|
"epoch": 3.1450528338136405,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004027073303058109,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.24600255340337754,
|
|
"num_tokens": 75063379.0,
|
|
"step": 32740
|
|
},
|
|
{
|
|
"entropy": 5.151837539672852,
|
|
"epoch": 3.1455331412103744,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004026791027387214,
|
|
"loss": 4.7001,
|
|
"mean_token_accuracy": 0.2443821758031845,
|
|
"num_tokens": 75074034.0,
|
|
"step": 32745
|
|
},
|
|
{
|
|
"entropy": 5.176320362091064,
|
|
"epoch": 3.1460134486071087,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004026508722073024,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.23652040511369704,
|
|
"num_tokens": 75087004.0,
|
|
"step": 32750
|
|
},
|
|
{
|
|
"entropy": 5.193984127044677,
|
|
"epoch": 3.1464937560038426,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040262263871220904,
|
|
"loss": 4.764,
|
|
"mean_token_accuracy": 0.24067216515541076,
|
|
"num_tokens": 75100270.0,
|
|
"step": 32755
|
|
},
|
|
{
|
|
"entropy": 5.110241651535034,
|
|
"epoch": 3.1469740634005765,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004025944022540971,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.2505010232329369,
|
|
"num_tokens": 75113116.0,
|
|
"step": 32760
|
|
},
|
|
{
|
|
"entropy": 5.180291604995728,
|
|
"epoch": 3.1474543707973104,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040256616283362195,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.24061424136161805,
|
|
"num_tokens": 75124225.0,
|
|
"step": 32765
|
|
},
|
|
{
|
|
"entropy": 5.102535009384155,
|
|
"epoch": 3.1479346781940443,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040253792045143926,
|
|
"loss": 4.6369,
|
|
"mean_token_accuracy": 0.254263611137867,
|
|
"num_tokens": 75135859.0,
|
|
"step": 32770
|
|
},
|
|
{
|
|
"entropy": 5.255549430847168,
|
|
"epoch": 3.148414985590778,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004025096751082048,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.24022137522697448,
|
|
"num_tokens": 75148626.0,
|
|
"step": 32775
|
|
},
|
|
{
|
|
"entropy": 5.188140201568603,
|
|
"epoch": 3.148895292987512,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004024814268045743,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.23972190618515016,
|
|
"num_tokens": 75159539.0,
|
|
"step": 32780
|
|
},
|
|
{
|
|
"entropy": 5.114200639724731,
|
|
"epoch": 3.149375600384246,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00040245317554120363,
|
|
"loss": 4.6895,
|
|
"mean_token_accuracy": 0.24664783030748366,
|
|
"num_tokens": 75172393.0,
|
|
"step": 32785
|
|
},
|
|
{
|
|
"entropy": 5.182809448242187,
|
|
"epoch": 3.14985590778098,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004024249213187487,
|
|
"loss": 4.7447,
|
|
"mean_token_accuracy": 0.2434307098388672,
|
|
"num_tokens": 75183777.0,
|
|
"step": 32790
|
|
},
|
|
{
|
|
"entropy": 5.08672685623169,
|
|
"epoch": 3.1503362151777137,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004023966641378655,
|
|
"loss": 4.648,
|
|
"mean_token_accuracy": 0.2511796608567238,
|
|
"num_tokens": 75194976.0,
|
|
"step": 32795
|
|
},
|
|
{
|
|
"entropy": 5.088904523849488,
|
|
"epoch": 3.1508165225744476,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00040236840399920996,
|
|
"loss": 4.6522,
|
|
"mean_token_accuracy": 0.24821109622716903,
|
|
"num_tokens": 75207709.0,
|
|
"step": 32800
|
|
},
|
|
{
|
|
"entropy": 5.081234312057495,
|
|
"epoch": 3.1512968299711814,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00040234014090343833,
|
|
"loss": 4.5902,
|
|
"mean_token_accuracy": 0.250691781938076,
|
|
"num_tokens": 75217848.0,
|
|
"step": 32805
|
|
},
|
|
{
|
|
"entropy": 5.208475399017334,
|
|
"epoch": 3.1517771373679153,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004023118748512068,
|
|
"loss": 4.7702,
|
|
"mean_token_accuracy": 0.2396462380886078,
|
|
"num_tokens": 75229670.0,
|
|
"step": 32810
|
|
},
|
|
{
|
|
"entropy": 5.076343536376953,
|
|
"epoch": 3.152257444764649,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004022836058431715,
|
|
"loss": 4.6532,
|
|
"mean_token_accuracy": 0.24948821514844893,
|
|
"num_tokens": 75241752.0,
|
|
"step": 32815
|
|
},
|
|
{
|
|
"entropy": 5.101542901992798,
|
|
"epoch": 3.152737752161383,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00040225533387998883,
|
|
"loss": 4.6697,
|
|
"mean_token_accuracy": 0.24313783645629883,
|
|
"num_tokens": 75252818.0,
|
|
"step": 32820
|
|
},
|
|
{
|
|
"entropy": 5.130284833908081,
|
|
"epoch": 3.1532180595581174,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004022270589623152,
|
|
"loss": 4.6856,
|
|
"mean_token_accuracy": 0.24589302837848664,
|
|
"num_tokens": 75264076.0,
|
|
"step": 32825
|
|
},
|
|
{
|
|
"entropy": 5.174988174438477,
|
|
"epoch": 3.1536983669548513,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000402198781090807,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.243490307033062,
|
|
"num_tokens": 75275281.0,
|
|
"step": 32830
|
|
},
|
|
{
|
|
"entropy": 5.089195251464844,
|
|
"epoch": 3.154178674351585,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004021705002661208,
|
|
"loss": 4.6767,
|
|
"mean_token_accuracy": 0.2439264789223671,
|
|
"num_tokens": 75287443.0,
|
|
"step": 32835
|
|
},
|
|
{
|
|
"entropy": 5.131635522842407,
|
|
"epoch": 3.154658981748319,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004021422164889133,
|
|
"loss": 4.7,
|
|
"mean_token_accuracy": 0.24109155982732772,
|
|
"num_tokens": 75299256.0,
|
|
"step": 32840
|
|
},
|
|
{
|
|
"entropy": 5.198635244369507,
|
|
"epoch": 3.155139289145053,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000402113929759841,
|
|
"loss": 4.7254,
|
|
"mean_token_accuracy": 0.2459749311208725,
|
|
"num_tokens": 75310485.0,
|
|
"step": 32845
|
|
},
|
|
{
|
|
"entropy": 5.180550622940063,
|
|
"epoch": 3.155619596541787,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040208564007956075,
|
|
"loss": 4.7033,
|
|
"mean_token_accuracy": 0.24295693039894103,
|
|
"num_tokens": 75322826.0,
|
|
"step": 32850
|
|
},
|
|
{
|
|
"entropy": 5.124126434326172,
|
|
"epoch": 3.1560999039385207,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004020573474487293,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.2520866051316261,
|
|
"num_tokens": 75334826.0,
|
|
"step": 32855
|
|
},
|
|
{
|
|
"entropy": 5.067382192611694,
|
|
"epoch": 3.1565802113352546,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00040202905186800347,
|
|
"loss": 4.6373,
|
|
"mean_token_accuracy": 0.2515884816646576,
|
|
"num_tokens": 75345997.0,
|
|
"step": 32860
|
|
},
|
|
{
|
|
"entropy": 5.195913648605346,
|
|
"epoch": 3.1570605187319885,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004020007533380403,
|
|
"loss": 4.6944,
|
|
"mean_token_accuracy": 0.23151724487543107,
|
|
"num_tokens": 75357018.0,
|
|
"step": 32865
|
|
},
|
|
{
|
|
"entropy": 5.09669942855835,
|
|
"epoch": 3.1575408261287223,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004019724518594967,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.2454105719923973,
|
|
"num_tokens": 75368190.0,
|
|
"step": 32870
|
|
},
|
|
{
|
|
"entropy": 5.110709095001221,
|
|
"epoch": 3.158021133525456,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004019441474330298,
|
|
"loss": 4.6538,
|
|
"mean_token_accuracy": 0.24637721478939056,
|
|
"num_tokens": 75380284.0,
|
|
"step": 32875
|
|
},
|
|
{
|
|
"entropy": 5.083511781692505,
|
|
"epoch": 3.15850144092219,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040191584005929684,
|
|
"loss": 4.6751,
|
|
"mean_token_accuracy": 0.25053894370794294,
|
|
"num_tokens": 75392543.0,
|
|
"step": 32880
|
|
},
|
|
{
|
|
"entropy": 5.116760730743408,
|
|
"epoch": 3.158981748318924,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004018875297389549,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.24313436895608903,
|
|
"num_tokens": 75404883.0,
|
|
"step": 32885
|
|
},
|
|
{
|
|
"entropy": 5.193080806732178,
|
|
"epoch": 3.159462055715658,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00040185921647266126,
|
|
"loss": 4.7483,
|
|
"mean_token_accuracy": 0.24138785600662233,
|
|
"num_tokens": 75416717.0,
|
|
"step": 32890
|
|
},
|
|
{
|
|
"entropy": 5.132291984558106,
|
|
"epoch": 3.1599423631123917,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040183090026107326,
|
|
"loss": 4.6389,
|
|
"mean_token_accuracy": 0.25611883997917173,
|
|
"num_tokens": 75428103.0,
|
|
"step": 32895
|
|
},
|
|
{
|
|
"entropy": 5.054528379440308,
|
|
"epoch": 3.160422670509126,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040180258110484847,
|
|
"loss": 4.6109,
|
|
"mean_token_accuracy": 0.2548226326704025,
|
|
"num_tokens": 75438333.0,
|
|
"step": 32900
|
|
},
|
|
{
|
|
"entropy": 5.168835926055908,
|
|
"epoch": 3.16090297790586,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004017742590046442,
|
|
"loss": 4.7074,
|
|
"mean_token_accuracy": 0.24765390157699585,
|
|
"num_tokens": 75450023.0,
|
|
"step": 32905
|
|
},
|
|
{
|
|
"entropy": 5.127561759948731,
|
|
"epoch": 3.161383285302594,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040174593396111814,
|
|
"loss": 4.6751,
|
|
"mean_token_accuracy": 0.24903755635023117,
|
|
"num_tokens": 75460724.0,
|
|
"step": 32910
|
|
},
|
|
{
|
|
"entropy": 5.1111256122589115,
|
|
"epoch": 3.1618635926993277,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040171760597492785,
|
|
"loss": 4.6948,
|
|
"mean_token_accuracy": 0.24684537202119827,
|
|
"num_tokens": 75471752.0,
|
|
"step": 32915
|
|
},
|
|
{
|
|
"entropy": 5.05853796005249,
|
|
"epoch": 3.1623439000960616,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040168927504673094,
|
|
"loss": 4.6226,
|
|
"mean_token_accuracy": 0.24693062007427216,
|
|
"num_tokens": 75483748.0,
|
|
"step": 32920
|
|
},
|
|
{
|
|
"entropy": 5.156345796585083,
|
|
"epoch": 3.1628242074927955,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004016609411771853,
|
|
"loss": 4.7872,
|
|
"mean_token_accuracy": 0.2400098130106926,
|
|
"num_tokens": 75495497.0,
|
|
"step": 32925
|
|
},
|
|
{
|
|
"entropy": 5.196905469894409,
|
|
"epoch": 3.1633045148895294,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040163260436694876,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.24081387668848037,
|
|
"num_tokens": 75506852.0,
|
|
"step": 32930
|
|
},
|
|
{
|
|
"entropy": 5.178798198699951,
|
|
"epoch": 3.1637848222862632,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004016042646166791,
|
|
"loss": 4.6983,
|
|
"mean_token_accuracy": 0.25021115988492965,
|
|
"num_tokens": 75518633.0,
|
|
"step": 32935
|
|
},
|
|
{
|
|
"entropy": 5.114012289047241,
|
|
"epoch": 3.164265129682997,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004015759219270344,
|
|
"loss": 4.6518,
|
|
"mean_token_accuracy": 0.24705173075199127,
|
|
"num_tokens": 75529668.0,
|
|
"step": 32940
|
|
},
|
|
{
|
|
"entropy": 5.157095003128052,
|
|
"epoch": 3.164745437079731,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004015475762986726,
|
|
"loss": 4.7114,
|
|
"mean_token_accuracy": 0.24954354465007783,
|
|
"num_tokens": 75541603.0,
|
|
"step": 32945
|
|
},
|
|
{
|
|
"entropy": 5.175605630874633,
|
|
"epoch": 3.165225744476465,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040151922773225187,
|
|
"loss": 4.7241,
|
|
"mean_token_accuracy": 0.2444535806775093,
|
|
"num_tokens": 75553489.0,
|
|
"step": 32950
|
|
},
|
|
{
|
|
"entropy": 5.109271287918091,
|
|
"epoch": 3.1657060518731988,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004014908762284303,
|
|
"loss": 4.6775,
|
|
"mean_token_accuracy": 0.24114330261945724,
|
|
"num_tokens": 75564809.0,
|
|
"step": 32955
|
|
},
|
|
{
|
|
"entropy": 5.157461833953858,
|
|
"epoch": 3.1661863592699326,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040146252178786633,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.24130633175373079,
|
|
"num_tokens": 75575886.0,
|
|
"step": 32960
|
|
},
|
|
{
|
|
"entropy": 5.146005296707154,
|
|
"epoch": 3.1666666666666665,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000401434164411218,
|
|
"loss": 4.6933,
|
|
"mean_token_accuracy": 0.23717365115880967,
|
|
"num_tokens": 75586518.0,
|
|
"step": 32965
|
|
},
|
|
{
|
|
"entropy": 5.072914123535156,
|
|
"epoch": 3.1671469740634004,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00040140580409914385,
|
|
"loss": 4.5542,
|
|
"mean_token_accuracy": 0.2539627686142921,
|
|
"num_tokens": 75598819.0,
|
|
"step": 32970
|
|
},
|
|
{
|
|
"entropy": 5.140855121612549,
|
|
"epoch": 3.1676272814601343,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040137744085230227,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.2443515196442604,
|
|
"num_tokens": 75610319.0,
|
|
"step": 32975
|
|
},
|
|
{
|
|
"entropy": 5.29808349609375,
|
|
"epoch": 3.168107588856868,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004013490746713518,
|
|
"loss": 4.833,
|
|
"mean_token_accuracy": 0.23608228266239167,
|
|
"num_tokens": 75622479.0,
|
|
"step": 32980
|
|
},
|
|
{
|
|
"entropy": 5.16813645362854,
|
|
"epoch": 3.1685878962536025,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00040132070555695096,
|
|
"loss": 4.6946,
|
|
"mean_token_accuracy": 0.24547169953584672,
|
|
"num_tokens": 75634114.0,
|
|
"step": 32985
|
|
},
|
|
{
|
|
"entropy": 5.132023000717163,
|
|
"epoch": 3.1690682036503364,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00040129233350975847,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.23569009751081466,
|
|
"num_tokens": 75645828.0,
|
|
"step": 32990
|
|
},
|
|
{
|
|
"entropy": 5.120276069641113,
|
|
"epoch": 3.1695485110470702,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00040126395853043293,
|
|
"loss": 4.7129,
|
|
"mean_token_accuracy": 0.2450796216726303,
|
|
"num_tokens": 75657335.0,
|
|
"step": 32995
|
|
},
|
|
{
|
|
"entropy": 5.144857549667359,
|
|
"epoch": 3.170028818443804,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004012355806196332,
|
|
"loss": 4.6492,
|
|
"mean_token_accuracy": 0.2448412224650383,
|
|
"num_tokens": 75668886.0,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"epoch": 3.170028818443804,
|
|
"eval_entropy": 4.95432301034932,
|
|
"eval_loss": 4.844753742218018,
|
|
"eval_mean_token_accuracy": 0.2450723909350182,
|
|
"eval_num_tokens": 75668886.0,
|
|
"eval_runtime": 27.4484,
|
|
"eval_samples_per_second": 1195.516,
|
|
"eval_steps_per_second": 149.444,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"entropy": 5.2193684577941895,
|
|
"epoch": 3.170509125840538,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040120719977801823,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.23755639791488647,
|
|
"num_tokens": 75679392.0,
|
|
"step": 33005
|
|
},
|
|
{
|
|
"entropy": 5.227935314178467,
|
|
"epoch": 3.170989433237272,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040117881600624676,
|
|
"loss": 4.7912,
|
|
"mean_token_accuracy": 0.238484987616539,
|
|
"num_tokens": 75692028.0,
|
|
"step": 33010
|
|
},
|
|
{
|
|
"entropy": 5.118623304367065,
|
|
"epoch": 3.1714697406340058,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040115042930497787,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.2402774453163147,
|
|
"num_tokens": 75702879.0,
|
|
"step": 33015
|
|
},
|
|
{
|
|
"entropy": 5.180615615844727,
|
|
"epoch": 3.1719500480307397,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040112203967487066,
|
|
"loss": 4.6774,
|
|
"mean_token_accuracy": 0.24163737446069716,
|
|
"num_tokens": 75713564.0,
|
|
"step": 33020
|
|
},
|
|
{
|
|
"entropy": 5.067767477035522,
|
|
"epoch": 3.1724303554274735,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00040109364711658416,
|
|
"loss": 4.643,
|
|
"mean_token_accuracy": 0.2456322953104973,
|
|
"num_tokens": 75724577.0,
|
|
"step": 33025
|
|
},
|
|
{
|
|
"entropy": 5.150070142745972,
|
|
"epoch": 3.1729106628242074,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040106525163077756,
|
|
"loss": 4.709,
|
|
"mean_token_accuracy": 0.2511893197894096,
|
|
"num_tokens": 75736349.0,
|
|
"step": 33030
|
|
},
|
|
{
|
|
"entropy": 5.124058628082276,
|
|
"epoch": 3.1733909702209413,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004010368532181102,
|
|
"loss": 4.7188,
|
|
"mean_token_accuracy": 0.24050048738718033,
|
|
"num_tokens": 75747465.0,
|
|
"step": 33035
|
|
},
|
|
{
|
|
"entropy": 5.2701012134552006,
|
|
"epoch": 3.173871277617675,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004010084518792413,
|
|
"loss": 4.8312,
|
|
"mean_token_accuracy": 0.236104553937912,
|
|
"num_tokens": 75759014.0,
|
|
"step": 33040
|
|
},
|
|
{
|
|
"entropy": 5.116722536087036,
|
|
"epoch": 3.174351585014409,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040098004761483037,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.2435469850897789,
|
|
"num_tokens": 75770354.0,
|
|
"step": 33045
|
|
},
|
|
{
|
|
"entropy": 5.206272029876709,
|
|
"epoch": 3.174831892411143,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004009516404255368,
|
|
"loss": 4.7782,
|
|
"mean_token_accuracy": 0.23953821659088134,
|
|
"num_tokens": 75781530.0,
|
|
"step": 33050
|
|
},
|
|
{
|
|
"entropy": 5.157583904266358,
|
|
"epoch": 3.175312199807877,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004009232303120202,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.24363791048526764,
|
|
"num_tokens": 75792751.0,
|
|
"step": 33055
|
|
},
|
|
{
|
|
"entropy": 5.108658361434936,
|
|
"epoch": 3.175792507204611,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00040089481727494,
|
|
"loss": 4.6159,
|
|
"mean_token_accuracy": 0.25298918336629866,
|
|
"num_tokens": 75804882.0,
|
|
"step": 33060
|
|
},
|
|
{
|
|
"entropy": 5.059522914886474,
|
|
"epoch": 3.176272814601345,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000400866401314956,
|
|
"loss": 4.6441,
|
|
"mean_token_accuracy": 0.2488788530230522,
|
|
"num_tokens": 75816207.0,
|
|
"step": 33065
|
|
},
|
|
{
|
|
"entropy": 5.152594041824341,
|
|
"epoch": 3.176753121998079,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040083798243272797,
|
|
"loss": 4.8191,
|
|
"mean_token_accuracy": 0.23993035554885864,
|
|
"num_tokens": 75827957.0,
|
|
"step": 33070
|
|
},
|
|
{
|
|
"entropy": 5.207097148895263,
|
|
"epoch": 3.177233429394813,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00040080956062891554,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.2446106940507889,
|
|
"num_tokens": 75839227.0,
|
|
"step": 33075
|
|
},
|
|
{
|
|
"entropy": 5.213340616226196,
|
|
"epoch": 3.1777137367915467,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040078113590417887,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.24470304995775222,
|
|
"num_tokens": 75849831.0,
|
|
"step": 33080
|
|
},
|
|
{
|
|
"entropy": 5.084146451950073,
|
|
"epoch": 3.1781940441882806,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040075270825917753,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.2486659273505211,
|
|
"num_tokens": 75860617.0,
|
|
"step": 33085
|
|
},
|
|
{
|
|
"entropy": 5.143074989318848,
|
|
"epoch": 3.1786743515850144,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004007242776945718,
|
|
"loss": 4.7462,
|
|
"mean_token_accuracy": 0.2419470265507698,
|
|
"num_tokens": 75872193.0,
|
|
"step": 33090
|
|
},
|
|
{
|
|
"entropy": 5.161079168319702,
|
|
"epoch": 3.1791546589817483,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00040069584421102174,
|
|
"loss": 4.7427,
|
|
"mean_token_accuracy": 0.24876087605953218,
|
|
"num_tokens": 75885536.0,
|
|
"step": 33095
|
|
},
|
|
{
|
|
"entropy": 5.224838018417358,
|
|
"epoch": 3.179634966378482,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040066740780918725,
|
|
"loss": 4.7576,
|
|
"mean_token_accuracy": 0.24105380326509476,
|
|
"num_tokens": 75897325.0,
|
|
"step": 33100
|
|
},
|
|
{
|
|
"entropy": 5.156337022781372,
|
|
"epoch": 3.180115273775216,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004006389684897288,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.24369630366563796,
|
|
"num_tokens": 75908353.0,
|
|
"step": 33105
|
|
},
|
|
{
|
|
"entropy": 5.165036058425903,
|
|
"epoch": 3.18059558117195,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004006105262533066,
|
|
"loss": 4.7538,
|
|
"mean_token_accuracy": 0.2433931440114975,
|
|
"num_tokens": 75919862.0,
|
|
"step": 33110
|
|
},
|
|
{
|
|
"entropy": 5.1237273693084715,
|
|
"epoch": 3.181075888568684,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004005820811005809,
|
|
"loss": 4.6458,
|
|
"mean_token_accuracy": 0.2562327325344086,
|
|
"num_tokens": 75930971.0,
|
|
"step": 33115
|
|
},
|
|
{
|
|
"entropy": 5.165366697311401,
|
|
"epoch": 3.1815561959654177,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040055363303221226,
|
|
"loss": 4.6177,
|
|
"mean_token_accuracy": 0.25857568085193633,
|
|
"num_tokens": 75941124.0,
|
|
"step": 33120
|
|
},
|
|
{
|
|
"entropy": 5.1656044006347654,
|
|
"epoch": 3.1820365033621516,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000400525182048861,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.24396208822727203,
|
|
"num_tokens": 75953040.0,
|
|
"step": 33125
|
|
},
|
|
{
|
|
"entropy": 5.1531729221344,
|
|
"epoch": 3.1825168107588855,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040049672815118775,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.23352790027856826,
|
|
"num_tokens": 75965122.0,
|
|
"step": 33130
|
|
},
|
|
{
|
|
"entropy": 5.201599073410034,
|
|
"epoch": 3.18299711815562,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040046827133985316,
|
|
"loss": 4.6576,
|
|
"mean_token_accuracy": 0.24749863892793655,
|
|
"num_tokens": 75975360.0,
|
|
"step": 33135
|
|
},
|
|
{
|
|
"entropy": 5.130577325820923,
|
|
"epoch": 3.1834774255523537,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040043981161551784,
|
|
"loss": 4.6137,
|
|
"mean_token_accuracy": 0.2476016104221344,
|
|
"num_tokens": 75985592.0,
|
|
"step": 33140
|
|
},
|
|
{
|
|
"entropy": 5.05172963142395,
|
|
"epoch": 3.1839577329490876,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004004113489788426,
|
|
"loss": 4.6948,
|
|
"mean_token_accuracy": 0.24390236139297486,
|
|
"num_tokens": 75997429.0,
|
|
"step": 33145
|
|
},
|
|
{
|
|
"entropy": 5.205761861801148,
|
|
"epoch": 3.1844380403458215,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040038288343048823,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.23377538621425628,
|
|
"num_tokens": 76008785.0,
|
|
"step": 33150
|
|
},
|
|
{
|
|
"entropy": 5.2940820217132565,
|
|
"epoch": 3.1849183477425553,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00040035441497111564,
|
|
"loss": 4.835,
|
|
"mean_token_accuracy": 0.23924779295921325,
|
|
"num_tokens": 76020773.0,
|
|
"step": 33155
|
|
},
|
|
{
|
|
"entropy": 5.157857513427734,
|
|
"epoch": 3.185398655139289,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040032594360138576,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.24934963136911392,
|
|
"num_tokens": 76033300.0,
|
|
"step": 33160
|
|
},
|
|
{
|
|
"entropy": 5.084401321411133,
|
|
"epoch": 3.185878962536023,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004002974693219595,
|
|
"loss": 4.5983,
|
|
"mean_token_accuracy": 0.24583688378334045,
|
|
"num_tokens": 76043443.0,
|
|
"step": 33165
|
|
},
|
|
{
|
|
"entropy": 5.157472705841064,
|
|
"epoch": 3.186359269932757,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040026899213349814,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.2446027457714081,
|
|
"num_tokens": 76055417.0,
|
|
"step": 33170
|
|
},
|
|
{
|
|
"entropy": 5.231717252731324,
|
|
"epoch": 3.186839577329491,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004002405120366628,
|
|
"loss": 4.7008,
|
|
"mean_token_accuracy": 0.24618784189224244,
|
|
"num_tokens": 76067259.0,
|
|
"step": 33175
|
|
},
|
|
{
|
|
"entropy": 5.159530735015869,
|
|
"epoch": 3.1873198847262247,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00040021202903211454,
|
|
"loss": 4.689,
|
|
"mean_token_accuracy": 0.24541291296482087,
|
|
"num_tokens": 76079827.0,
|
|
"step": 33180
|
|
},
|
|
{
|
|
"entropy": 5.167980432510376,
|
|
"epoch": 3.1878001921229586,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004001835431205149,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.23902440965175628,
|
|
"num_tokens": 76092068.0,
|
|
"step": 33185
|
|
},
|
|
{
|
|
"entropy": 5.204587459564209,
|
|
"epoch": 3.1882804995196925,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040015505430252506,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.23885730057954788,
|
|
"num_tokens": 76102046.0,
|
|
"step": 33190
|
|
},
|
|
{
|
|
"entropy": 5.100633335113526,
|
|
"epoch": 3.1887608069164264,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040012656257880645,
|
|
"loss": 4.6757,
|
|
"mean_token_accuracy": 0.24515202790498733,
|
|
"num_tokens": 76113629.0,
|
|
"step": 33195
|
|
},
|
|
{
|
|
"entropy": 5.102912378311157,
|
|
"epoch": 3.1892411143131603,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040009806795002076,
|
|
"loss": 4.6276,
|
|
"mean_token_accuracy": 0.2536490514874458,
|
|
"num_tokens": 76124593.0,
|
|
"step": 33200
|
|
},
|
|
{
|
|
"entropy": 5.288735198974609,
|
|
"epoch": 3.189721421709894,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004000695704168292,
|
|
"loss": 4.8881,
|
|
"mean_token_accuracy": 0.22736235857009887,
|
|
"num_tokens": 76135177.0,
|
|
"step": 33205
|
|
},
|
|
{
|
|
"entropy": 5.170682001113891,
|
|
"epoch": 3.1902017291066285,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004000410699798937,
|
|
"loss": 4.6801,
|
|
"mean_token_accuracy": 0.24451248943805695,
|
|
"num_tokens": 76148998.0,
|
|
"step": 33210
|
|
},
|
|
{
|
|
"entropy": 5.065028476715088,
|
|
"epoch": 3.1906820365033624,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00040001256663987585,
|
|
"loss": 4.7008,
|
|
"mean_token_accuracy": 0.2494421899318695,
|
|
"num_tokens": 76161224.0,
|
|
"step": 33215
|
|
},
|
|
{
|
|
"entropy": 5.107192277908325,
|
|
"epoch": 3.1911623439000962,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039998406039743736,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.24373262226581574,
|
|
"num_tokens": 76172577.0,
|
|
"step": 33220
|
|
},
|
|
{
|
|
"entropy": 5.117644596099853,
|
|
"epoch": 3.19164265129683,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003999555512532401,
|
|
"loss": 4.6599,
|
|
"mean_token_accuracy": 0.25143107771873474,
|
|
"num_tokens": 76184135.0,
|
|
"step": 33225
|
|
},
|
|
{
|
|
"entropy": 5.1663634300231935,
|
|
"epoch": 3.192122958693564,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003999270392079461,
|
|
"loss": 4.7299,
|
|
"mean_token_accuracy": 0.24233764111995698,
|
|
"num_tokens": 76195831.0,
|
|
"step": 33230
|
|
},
|
|
{
|
|
"entropy": 5.212095594406128,
|
|
"epoch": 3.192603266090298,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003998985242622171,
|
|
"loss": 4.7444,
|
|
"mean_token_accuracy": 0.2401751011610031,
|
|
"num_tokens": 76208914.0,
|
|
"step": 33235
|
|
},
|
|
{
|
|
"entropy": 5.127374696731567,
|
|
"epoch": 3.1930835734870318,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003998700064167153,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.23909802287817,
|
|
"num_tokens": 76220599.0,
|
|
"step": 33240
|
|
},
|
|
{
|
|
"entropy": 5.170952415466308,
|
|
"epoch": 3.1935638808837656,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003998414856721027,
|
|
"loss": 4.7104,
|
|
"mean_token_accuracy": 0.24359094500541686,
|
|
"num_tokens": 76232897.0,
|
|
"step": 33245
|
|
},
|
|
{
|
|
"entropy": 5.221544361114502,
|
|
"epoch": 3.1940441882804995,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003998129620290415,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.24689700007438659,
|
|
"num_tokens": 76245948.0,
|
|
"step": 33250
|
|
},
|
|
{
|
|
"entropy": 5.13859453201294,
|
|
"epoch": 3.1945244956772334,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039978443548819393,
|
|
"loss": 4.6937,
|
|
"mean_token_accuracy": 0.24782951772212983,
|
|
"num_tokens": 76257223.0,
|
|
"step": 33255
|
|
},
|
|
{
|
|
"entropy": 5.0693024635314945,
|
|
"epoch": 3.1950048030739673,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0003997559060502224,
|
|
"loss": 4.6143,
|
|
"mean_token_accuracy": 0.25600714385509493,
|
|
"num_tokens": 76267606.0,
|
|
"step": 33260
|
|
},
|
|
{
|
|
"entropy": 5.104847574234009,
|
|
"epoch": 3.195485110470701,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003997273737157891,
|
|
"loss": 4.7021,
|
|
"mean_token_accuracy": 0.2443031921982765,
|
|
"num_tokens": 76280430.0,
|
|
"step": 33265
|
|
},
|
|
{
|
|
"entropy": 5.2144325256347654,
|
|
"epoch": 3.195965417867435,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039969883848555647,
|
|
"loss": 4.7399,
|
|
"mean_token_accuracy": 0.24136941879987717,
|
|
"num_tokens": 76293089.0,
|
|
"step": 33270
|
|
},
|
|
{
|
|
"entropy": 5.171425199508667,
|
|
"epoch": 3.196445725264169,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003996703003601872,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.2465455248951912,
|
|
"num_tokens": 76304936.0,
|
|
"step": 33275
|
|
},
|
|
{
|
|
"entropy": 5.075675773620605,
|
|
"epoch": 3.196926032660903,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00039964175934034375,
|
|
"loss": 4.5128,
|
|
"mean_token_accuracy": 0.26054380387067794,
|
|
"num_tokens": 76316195.0,
|
|
"step": 33280
|
|
},
|
|
{
|
|
"entropy": 5.076376819610596,
|
|
"epoch": 3.1974063400576367,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0003996132154266887,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.25281447917222977,
|
|
"num_tokens": 76328128.0,
|
|
"step": 33285
|
|
},
|
|
{
|
|
"entropy": 5.091669511795044,
|
|
"epoch": 3.1978866474543706,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003995846686198849,
|
|
"loss": 4.6181,
|
|
"mean_token_accuracy": 0.2508593872189522,
|
|
"num_tokens": 76338596.0,
|
|
"step": 33290
|
|
},
|
|
{
|
|
"entropy": 5.135903549194336,
|
|
"epoch": 3.198366954851105,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003995561189205949,
|
|
"loss": 4.7091,
|
|
"mean_token_accuracy": 0.24293019324541093,
|
|
"num_tokens": 76350479.0,
|
|
"step": 33295
|
|
},
|
|
{
|
|
"entropy": 5.134489345550537,
|
|
"epoch": 3.1988472622478388,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003995275663294818,
|
|
"loss": 4.7269,
|
|
"mean_token_accuracy": 0.2415492445230484,
|
|
"num_tokens": 76363433.0,
|
|
"step": 33300
|
|
},
|
|
{
|
|
"entropy": 5.061918306350708,
|
|
"epoch": 3.1993275696445727,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003994990108472084,
|
|
"loss": 4.6179,
|
|
"mean_token_accuracy": 0.25157475024461745,
|
|
"num_tokens": 76374000.0,
|
|
"step": 33305
|
|
},
|
|
{
|
|
"entropy": 5.085454988479614,
|
|
"epoch": 3.1998078770413065,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00039947045247443755,
|
|
"loss": 4.6323,
|
|
"mean_token_accuracy": 0.2470325455069542,
|
|
"num_tokens": 76384192.0,
|
|
"step": 33310
|
|
},
|
|
{
|
|
"entropy": 5.214585971832276,
|
|
"epoch": 3.2002881844380404,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039944189121183247,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.23712409138679505,
|
|
"num_tokens": 76396641.0,
|
|
"step": 33315
|
|
},
|
|
{
|
|
"entropy": 5.061916017532349,
|
|
"epoch": 3.2007684918347743,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039941332706005617,
|
|
"loss": 4.576,
|
|
"mean_token_accuracy": 0.25115514546632767,
|
|
"num_tokens": 76407954.0,
|
|
"step": 33320
|
|
},
|
|
{
|
|
"entropy": 5.126073884963989,
|
|
"epoch": 3.201248799231508,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00039938476001977175,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.24591198414564133,
|
|
"num_tokens": 76419024.0,
|
|
"step": 33325
|
|
},
|
|
{
|
|
"entropy": 5.160331296920776,
|
|
"epoch": 3.201729106628242,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039935619009164264,
|
|
"loss": 4.7042,
|
|
"mean_token_accuracy": 0.2389150634407997,
|
|
"num_tokens": 76429786.0,
|
|
"step": 33330
|
|
},
|
|
{
|
|
"entropy": 5.065987634658813,
|
|
"epoch": 3.202209414024976,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003993276172763321,
|
|
"loss": 4.5648,
|
|
"mean_token_accuracy": 0.2553159222006798,
|
|
"num_tokens": 76440439.0,
|
|
"step": 33335
|
|
},
|
|
{
|
|
"entropy": 5.13554162979126,
|
|
"epoch": 3.20268972142171,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039929904157450343,
|
|
"loss": 4.7244,
|
|
"mean_token_accuracy": 0.24429527968168258,
|
|
"num_tokens": 76451855.0,
|
|
"step": 33340
|
|
},
|
|
{
|
|
"entropy": 5.0750159740448,
|
|
"epoch": 3.2031700288184437,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039927046298682007,
|
|
"loss": 4.6324,
|
|
"mean_token_accuracy": 0.25223221331834794,
|
|
"num_tokens": 76463662.0,
|
|
"step": 33345
|
|
},
|
|
{
|
|
"entropy": 5.133476829528808,
|
|
"epoch": 3.2036503362151776,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003992418815139456,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.24523995369672774,
|
|
"num_tokens": 76476273.0,
|
|
"step": 33350
|
|
},
|
|
{
|
|
"entropy": 5.24965991973877,
|
|
"epoch": 3.2041306436119115,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00039921329715654355,
|
|
"loss": 4.7686,
|
|
"mean_token_accuracy": 0.23413299769163132,
|
|
"num_tokens": 76488958.0,
|
|
"step": 33355
|
|
},
|
|
{
|
|
"entropy": 5.074213123321533,
|
|
"epoch": 3.2046109510086453,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003991847099152775,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.25028275698423386,
|
|
"num_tokens": 76499606.0,
|
|
"step": 33360
|
|
},
|
|
{
|
|
"entropy": 5.205523157119751,
|
|
"epoch": 3.2050912584053792,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003991561197908114,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.2312649041414261,
|
|
"num_tokens": 76510953.0,
|
|
"step": 33365
|
|
},
|
|
{
|
|
"entropy": 5.1596921443939205,
|
|
"epoch": 3.2055715658021136,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003991275267838088,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.24612627923488617,
|
|
"num_tokens": 76522420.0,
|
|
"step": 33370
|
|
},
|
|
{
|
|
"entropy": 5.122861003875732,
|
|
"epoch": 3.2060518731988474,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039909893089493353,
|
|
"loss": 4.6943,
|
|
"mean_token_accuracy": 0.25263547897338867,
|
|
"num_tokens": 76533748.0,
|
|
"step": 33375
|
|
},
|
|
{
|
|
"entropy": 5.135891437530518,
|
|
"epoch": 3.2065321805955813,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039907033212484966,
|
|
"loss": 4.6548,
|
|
"mean_token_accuracy": 0.250062520802021,
|
|
"num_tokens": 76544831.0,
|
|
"step": 33380
|
|
},
|
|
{
|
|
"entropy": 5.125119924545288,
|
|
"epoch": 3.207012487992315,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003990417304742211,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.24605010598897933,
|
|
"num_tokens": 76558048.0,
|
|
"step": 33385
|
|
},
|
|
{
|
|
"entropy": 5.168108510971069,
|
|
"epoch": 3.207492795389049,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003990131259437119,
|
|
"loss": 4.732,
|
|
"mean_token_accuracy": 0.2493499308824539,
|
|
"num_tokens": 76568461.0,
|
|
"step": 33390
|
|
},
|
|
{
|
|
"entropy": 5.126466083526611,
|
|
"epoch": 3.207973102785783,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003989845185339861,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.24626142382621766,
|
|
"num_tokens": 76580191.0,
|
|
"step": 33395
|
|
},
|
|
{
|
|
"entropy": 5.145447731018066,
|
|
"epoch": 3.208453410182517,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003989559082457079,
|
|
"loss": 4.6557,
|
|
"mean_token_accuracy": 0.24432076662778854,
|
|
"num_tokens": 76591846.0,
|
|
"step": 33400
|
|
},
|
|
{
|
|
"entropy": 5.110228824615478,
|
|
"epoch": 3.2089337175792507,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00039892729507954173,
|
|
"loss": 4.6236,
|
|
"mean_token_accuracy": 0.2503491297364235,
|
|
"num_tokens": 76602301.0,
|
|
"step": 33405
|
|
},
|
|
{
|
|
"entropy": 5.137456607818604,
|
|
"epoch": 3.2094140249759846,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039889867903615165,
|
|
"loss": 4.6739,
|
|
"mean_token_accuracy": 0.2462332859635353,
|
|
"num_tokens": 76613299.0,
|
|
"step": 33410
|
|
},
|
|
{
|
|
"entropy": 5.175840187072754,
|
|
"epoch": 3.2098943323727185,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00039887006011620217,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.2438751071691513,
|
|
"num_tokens": 76625022.0,
|
|
"step": 33415
|
|
},
|
|
{
|
|
"entropy": 5.089872026443482,
|
|
"epoch": 3.2103746397694524,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039884143832035775,
|
|
"loss": 4.6625,
|
|
"mean_token_accuracy": 0.24801980406045915,
|
|
"num_tokens": 76636393.0,
|
|
"step": 33420
|
|
},
|
|
{
|
|
"entropy": 5.174492406845093,
|
|
"epoch": 3.2108549471661862,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003988128136492828,
|
|
"loss": 4.692,
|
|
"mean_token_accuracy": 0.24343761354684829,
|
|
"num_tokens": 76648953.0,
|
|
"step": 33425
|
|
},
|
|
{
|
|
"entropy": 5.115954732894897,
|
|
"epoch": 3.21133525456292,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000398784186103642,
|
|
"loss": 4.6929,
|
|
"mean_token_accuracy": 0.2402750015258789,
|
|
"num_tokens": 76660843.0,
|
|
"step": 33430
|
|
},
|
|
{
|
|
"entropy": 5.132492017745972,
|
|
"epoch": 3.211815561959654,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039875555568409996,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.25010610222816465,
|
|
"num_tokens": 76671745.0,
|
|
"step": 33435
|
|
},
|
|
{
|
|
"entropy": 5.122971487045288,
|
|
"epoch": 3.212295869356388,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003987269223913214,
|
|
"loss": 4.6573,
|
|
"mean_token_accuracy": 0.24037795662879943,
|
|
"num_tokens": 76684386.0,
|
|
"step": 33440
|
|
},
|
|
{
|
|
"entropy": 5.124348497390747,
|
|
"epoch": 3.212776176753122,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039869828622597105,
|
|
"loss": 4.649,
|
|
"mean_token_accuracy": 0.24940857738256456,
|
|
"num_tokens": 76694670.0,
|
|
"step": 33445
|
|
},
|
|
{
|
|
"entropy": 5.030927467346191,
|
|
"epoch": 3.213256484149856,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039866964718871385,
|
|
"loss": 4.6931,
|
|
"mean_token_accuracy": 0.25175226628780367,
|
|
"num_tokens": 76705567.0,
|
|
"step": 33450
|
|
},
|
|
{
|
|
"entropy": 5.094576025009156,
|
|
"epoch": 3.21373679154659,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003986410052802146,
|
|
"loss": 4.6451,
|
|
"mean_token_accuracy": 0.24675157368183137,
|
|
"num_tokens": 76717211.0,
|
|
"step": 33455
|
|
},
|
|
{
|
|
"entropy": 5.243278312683105,
|
|
"epoch": 3.214217098943324,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039861236050113845,
|
|
"loss": 4.7528,
|
|
"mean_token_accuracy": 0.23681883066892623,
|
|
"num_tokens": 76728414.0,
|
|
"step": 33460
|
|
},
|
|
{
|
|
"entropy": 5.053638744354248,
|
|
"epoch": 3.2146974063400577,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003985837128521503,
|
|
"loss": 4.6058,
|
|
"mean_token_accuracy": 0.25625320374965666,
|
|
"num_tokens": 76739790.0,
|
|
"step": 33465
|
|
},
|
|
{
|
|
"entropy": 5.139553833007812,
|
|
"epoch": 3.2151777137367916,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003985550623339153,
|
|
"loss": 4.7213,
|
|
"mean_token_accuracy": 0.24293430298566818,
|
|
"num_tokens": 76751558.0,
|
|
"step": 33470
|
|
},
|
|
{
|
|
"entropy": 5.221442079544067,
|
|
"epoch": 3.2156580211335255,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003985264089470987,
|
|
"loss": 4.8591,
|
|
"mean_token_accuracy": 0.23465726971626283,
|
|
"num_tokens": 76763004.0,
|
|
"step": 33475
|
|
},
|
|
{
|
|
"entropy": 5.148220491409302,
|
|
"epoch": 3.2161383285302594,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039849775269236556,
|
|
"loss": 4.7298,
|
|
"mean_token_accuracy": 0.24634650647640227,
|
|
"num_tokens": 76773625.0,
|
|
"step": 33480
|
|
},
|
|
{
|
|
"entropy": 5.1978209018707275,
|
|
"epoch": 3.2166186359269933,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00039846909357038135,
|
|
"loss": 4.759,
|
|
"mean_token_accuracy": 0.2396638035774231,
|
|
"num_tokens": 76786351.0,
|
|
"step": 33485
|
|
},
|
|
{
|
|
"entropy": 5.168853092193603,
|
|
"epoch": 3.217098943323727,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003984404315818115,
|
|
"loss": 4.6461,
|
|
"mean_token_accuracy": 0.24769550263881684,
|
|
"num_tokens": 76796997.0,
|
|
"step": 33490
|
|
},
|
|
{
|
|
"entropy": 5.181208515167237,
|
|
"epoch": 3.217579250720461,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039841176672732127,
|
|
"loss": 4.75,
|
|
"mean_token_accuracy": 0.24197126924991608,
|
|
"num_tokens": 76809690.0,
|
|
"step": 33495
|
|
},
|
|
{
|
|
"entropy": 5.103465223312378,
|
|
"epoch": 3.218059558117195,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003983830990075763,
|
|
"loss": 4.6154,
|
|
"mean_token_accuracy": 0.2474225178360939,
|
|
"num_tokens": 76820387.0,
|
|
"step": 33500
|
|
},
|
|
{
|
|
"entropy": 5.179717636108398,
|
|
"epoch": 3.218539865513929,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039835442842324216,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.2359391763806343,
|
|
"num_tokens": 76833261.0,
|
|
"step": 33505
|
|
},
|
|
{
|
|
"entropy": 5.087058019638062,
|
|
"epoch": 3.2190201729106627,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00039832575497498454,
|
|
"loss": 4.6309,
|
|
"mean_token_accuracy": 0.2452571853995323,
|
|
"num_tokens": 76844952.0,
|
|
"step": 33510
|
|
},
|
|
{
|
|
"entropy": 5.171843719482422,
|
|
"epoch": 3.2195004803073966,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00039829707866346895,
|
|
"loss": 4.6894,
|
|
"mean_token_accuracy": 0.2459503635764122,
|
|
"num_tokens": 76856076.0,
|
|
"step": 33515
|
|
},
|
|
{
|
|
"entropy": 5.237038087844849,
|
|
"epoch": 3.219980787704131,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003982683994893614,
|
|
"loss": 4.8708,
|
|
"mean_token_accuracy": 0.23417955338954927,
|
|
"num_tokens": 76867510.0,
|
|
"step": 33520
|
|
},
|
|
{
|
|
"entropy": 5.188200759887695,
|
|
"epoch": 3.2204610951008648,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039823971745332764,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.24198615103960036,
|
|
"num_tokens": 76879919.0,
|
|
"step": 33525
|
|
},
|
|
{
|
|
"entropy": 5.102110242843628,
|
|
"epoch": 3.2209414024975986,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003982110325560336,
|
|
"loss": 4.6845,
|
|
"mean_token_accuracy": 0.2465267613530159,
|
|
"num_tokens": 76891402.0,
|
|
"step": 33530
|
|
},
|
|
{
|
|
"entropy": 5.21624722480774,
|
|
"epoch": 3.2214217098943325,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003981823447981453,
|
|
"loss": 4.7205,
|
|
"mean_token_accuracy": 0.2384330302476883,
|
|
"num_tokens": 76902703.0,
|
|
"step": 33535
|
|
},
|
|
{
|
|
"entropy": 5.176742696762085,
|
|
"epoch": 3.2219020172910664,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039815365418032855,
|
|
"loss": 4.6441,
|
|
"mean_token_accuracy": 0.24714283049106597,
|
|
"num_tokens": 76913661.0,
|
|
"step": 33540
|
|
},
|
|
{
|
|
"entropy": 5.0706555366516115,
|
|
"epoch": 3.2223823246878003,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039812496070324983,
|
|
"loss": 4.6269,
|
|
"mean_token_accuracy": 0.24780938029289246,
|
|
"num_tokens": 76924175.0,
|
|
"step": 33545
|
|
},
|
|
{
|
|
"entropy": 5.146559143066407,
|
|
"epoch": 3.222862632084534,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000398096264367575,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.24664385318756105,
|
|
"num_tokens": 76935158.0,
|
|
"step": 33550
|
|
},
|
|
{
|
|
"entropy": 5.092141056060791,
|
|
"epoch": 3.223342939481268,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003980675651739705,
|
|
"loss": 4.5774,
|
|
"mean_token_accuracy": 0.25531144738197326,
|
|
"num_tokens": 76944918.0,
|
|
"step": 33555
|
|
},
|
|
{
|
|
"entropy": 4.984448575973511,
|
|
"epoch": 3.223823246878002,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039803886312310253,
|
|
"loss": 4.5778,
|
|
"mean_token_accuracy": 0.2599306255578995,
|
|
"num_tokens": 76955128.0,
|
|
"step": 33560
|
|
},
|
|
{
|
|
"entropy": 5.086811828613281,
|
|
"epoch": 3.224303554274736,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00039801015821563755,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.24685008823871613,
|
|
"num_tokens": 76966227.0,
|
|
"step": 33565
|
|
},
|
|
{
|
|
"entropy": 5.1548779010772705,
|
|
"epoch": 3.2247838616714697,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003979814504522419,
|
|
"loss": 4.6292,
|
|
"mean_token_accuracy": 0.2514008343219757,
|
|
"num_tokens": 76977059.0,
|
|
"step": 33570
|
|
},
|
|
{
|
|
"entropy": 5.082441616058349,
|
|
"epoch": 3.2252641690682036,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039795273983358223,
|
|
"loss": 4.6281,
|
|
"mean_token_accuracy": 0.25355584621429444,
|
|
"num_tokens": 76987447.0,
|
|
"step": 33575
|
|
},
|
|
{
|
|
"entropy": 5.142194128036499,
|
|
"epoch": 3.2257444764649374,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00039792402636032497,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.24270786941051484,
|
|
"num_tokens": 76998960.0,
|
|
"step": 33580
|
|
},
|
|
{
|
|
"entropy": 5.164002847671509,
|
|
"epoch": 3.2262247838616713,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039789531003313696,
|
|
"loss": 4.7384,
|
|
"mean_token_accuracy": 0.24714633524417878,
|
|
"num_tokens": 77011255.0,
|
|
"step": 33585
|
|
},
|
|
{
|
|
"entropy": 5.131731128692627,
|
|
"epoch": 3.226705091258405,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003978665908526846,
|
|
"loss": 4.6872,
|
|
"mean_token_accuracy": 0.24668321758508682,
|
|
"num_tokens": 77023061.0,
|
|
"step": 33590
|
|
},
|
|
{
|
|
"entropy": 5.138454866409302,
|
|
"epoch": 3.227185398655139,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003978378688196349,
|
|
"loss": 4.6714,
|
|
"mean_token_accuracy": 0.24360019862651824,
|
|
"num_tokens": 77033949.0,
|
|
"step": 33595
|
|
},
|
|
{
|
|
"entropy": 5.085725450515747,
|
|
"epoch": 3.227665706051873,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003978091439346546,
|
|
"loss": 4.6435,
|
|
"mean_token_accuracy": 0.24432212114334106,
|
|
"num_tokens": 77044990.0,
|
|
"step": 33600
|
|
},
|
|
{
|
|
"entropy": 5.17355260848999,
|
|
"epoch": 3.2281460134486073,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003977804161984108,
|
|
"loss": 4.7341,
|
|
"mean_token_accuracy": 0.23729149103164673,
|
|
"num_tokens": 77055099.0,
|
|
"step": 33605
|
|
},
|
|
{
|
|
"entropy": 5.181184339523315,
|
|
"epoch": 3.228626320845341,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003977516856115702,
|
|
"loss": 4.6805,
|
|
"mean_token_accuracy": 0.2504589393734932,
|
|
"num_tokens": 77065854.0,
|
|
"step": 33610
|
|
},
|
|
{
|
|
"entropy": 5.106678247451782,
|
|
"epoch": 3.229106628242075,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00039772295217479993,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.24984317719936372,
|
|
"num_tokens": 77077531.0,
|
|
"step": 33615
|
|
},
|
|
{
|
|
"entropy": 5.15851240158081,
|
|
"epoch": 3.229586935638809,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003976942158887671,
|
|
"loss": 4.6836,
|
|
"mean_token_accuracy": 0.25565575808286667,
|
|
"num_tokens": 77088659.0,
|
|
"step": 33620
|
|
},
|
|
{
|
|
"entropy": 5.1838634490966795,
|
|
"epoch": 3.230067243035543,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000397665476754139,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.23699892312288284,
|
|
"num_tokens": 77099868.0,
|
|
"step": 33625
|
|
},
|
|
{
|
|
"entropy": 5.144813346862793,
|
|
"epoch": 3.2305475504322767,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003976367347715828,
|
|
"loss": 4.6943,
|
|
"mean_token_accuracy": 0.24964292347431183,
|
|
"num_tokens": 77112415.0,
|
|
"step": 33630
|
|
},
|
|
{
|
|
"entropy": 5.15960659980774,
|
|
"epoch": 3.2310278578290106,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003976079899417657,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.2354693740606308,
|
|
"num_tokens": 77124978.0,
|
|
"step": 33635
|
|
},
|
|
{
|
|
"entropy": 5.188811492919922,
|
|
"epoch": 3.2315081652257445,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003975792422653552,
|
|
"loss": 4.7502,
|
|
"mean_token_accuracy": 0.2446480616927147,
|
|
"num_tokens": 77135800.0,
|
|
"step": 33640
|
|
},
|
|
{
|
|
"entropy": 5.175107145309449,
|
|
"epoch": 3.2319884726224783,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003975504917430186,
|
|
"loss": 4.7446,
|
|
"mean_token_accuracy": 0.2387138396501541,
|
|
"num_tokens": 77147269.0,
|
|
"step": 33645
|
|
},
|
|
{
|
|
"entropy": 5.171355152130127,
|
|
"epoch": 3.2324687800192122,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0003975217383754235,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.2419290065765381,
|
|
"num_tokens": 77159522.0,
|
|
"step": 33650
|
|
},
|
|
{
|
|
"entropy": 5.17962236404419,
|
|
"epoch": 3.232949087415946,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003974929821632375,
|
|
"loss": 4.7138,
|
|
"mean_token_accuracy": 0.2471625104546547,
|
|
"num_tokens": 77170884.0,
|
|
"step": 33655
|
|
},
|
|
{
|
|
"entropy": 5.059878253936768,
|
|
"epoch": 3.23342939481268,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039746422310712814,
|
|
"loss": 4.5583,
|
|
"mean_token_accuracy": 0.2542255476117134,
|
|
"num_tokens": 77181554.0,
|
|
"step": 33660
|
|
},
|
|
{
|
|
"entropy": 5.1188866138458256,
|
|
"epoch": 3.233909702209414,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003974354612077632,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.2433898076415062,
|
|
"num_tokens": 77192988.0,
|
|
"step": 33665
|
|
},
|
|
{
|
|
"entropy": 5.140847682952881,
|
|
"epoch": 3.2343900096061478,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003974066964658104,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.25329323410987853,
|
|
"num_tokens": 77204107.0,
|
|
"step": 33670
|
|
},
|
|
{
|
|
"entropy": 5.248054647445679,
|
|
"epoch": 3.2348703170028816,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039737792888193754,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.23879464119672775,
|
|
"num_tokens": 77217008.0,
|
|
"step": 33675
|
|
},
|
|
{
|
|
"entropy": 5.156226968765258,
|
|
"epoch": 3.235350624399616,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003973491584568126,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.23833802491426467,
|
|
"num_tokens": 77228651.0,
|
|
"step": 33680
|
|
},
|
|
{
|
|
"entropy": 5.052379035949707,
|
|
"epoch": 3.23583093179635,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003973203851911035,
|
|
"loss": 4.5946,
|
|
"mean_token_accuracy": 0.25596962720155714,
|
|
"num_tokens": 77240251.0,
|
|
"step": 33685
|
|
},
|
|
{
|
|
"entropy": 5.215323877334595,
|
|
"epoch": 3.2363112391930837,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003972916090854782,
|
|
"loss": 4.709,
|
|
"mean_token_accuracy": 0.25014435350894926,
|
|
"num_tokens": 77252160.0,
|
|
"step": 33690
|
|
},
|
|
{
|
|
"entropy": 5.079945087432861,
|
|
"epoch": 3.2367915465898176,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00039726283014060497,
|
|
"loss": 4.6498,
|
|
"mean_token_accuracy": 0.24644416570663452,
|
|
"num_tokens": 77263678.0,
|
|
"step": 33695
|
|
},
|
|
{
|
|
"entropy": 5.147024202346802,
|
|
"epoch": 3.2372718539865515,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003972340483571519,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.24652099311351777,
|
|
"num_tokens": 77275180.0,
|
|
"step": 33700
|
|
},
|
|
{
|
|
"entropy": 5.1765392303466795,
|
|
"epoch": 3.2377521613832854,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039720526373578704,
|
|
"loss": 4.7153,
|
|
"mean_token_accuracy": 0.24069982916116714,
|
|
"num_tokens": 77286450.0,
|
|
"step": 33705
|
|
},
|
|
{
|
|
"entropy": 5.138689279556274,
|
|
"epoch": 3.2382324687800192,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039717647627717894,
|
|
"loss": 4.6553,
|
|
"mean_token_accuracy": 0.251186665892601,
|
|
"num_tokens": 77297011.0,
|
|
"step": 33710
|
|
},
|
|
{
|
|
"entropy": 5.0577552318573,
|
|
"epoch": 3.238712776176753,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003971476859819958,
|
|
"loss": 4.5613,
|
|
"mean_token_accuracy": 0.2626972123980522,
|
|
"num_tokens": 77307408.0,
|
|
"step": 33715
|
|
},
|
|
{
|
|
"entropy": 5.14210729598999,
|
|
"epoch": 3.239193083573487,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003971188928509062,
|
|
"loss": 4.7298,
|
|
"mean_token_accuracy": 0.24093144834041597,
|
|
"num_tokens": 77316762.0,
|
|
"step": 33720
|
|
},
|
|
{
|
|
"entropy": 5.1820728302001955,
|
|
"epoch": 3.239673390970221,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003970900968845784,
|
|
"loss": 4.7148,
|
|
"mean_token_accuracy": 0.2503121912479401,
|
|
"num_tokens": 77327233.0,
|
|
"step": 33725
|
|
},
|
|
{
|
|
"entropy": 5.20512285232544,
|
|
"epoch": 3.2401536983669548,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00039706129808368115,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.2423067420721054,
|
|
"num_tokens": 77338001.0,
|
|
"step": 33730
|
|
},
|
|
{
|
|
"entropy": 5.105156993865966,
|
|
"epoch": 3.2406340057636887,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003970324964488829,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.24166871160268782,
|
|
"num_tokens": 77350243.0,
|
|
"step": 33735
|
|
},
|
|
{
|
|
"entropy": 5.121255922317505,
|
|
"epoch": 3.2411143131604225,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00039700369198085255,
|
|
"loss": 4.7076,
|
|
"mean_token_accuracy": 0.24419745653867722,
|
|
"num_tokens": 77360712.0,
|
|
"step": 33740
|
|
},
|
|
{
|
|
"entropy": 5.135137939453125,
|
|
"epoch": 3.2415946205571564,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00039697488468025876,
|
|
"loss": 4.6445,
|
|
"mean_token_accuracy": 0.24538180977106094,
|
|
"num_tokens": 77371399.0,
|
|
"step": 33745
|
|
},
|
|
{
|
|
"entropy": 5.24214243888855,
|
|
"epoch": 3.2420749279538903,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003969460745477703,
|
|
"loss": 4.7514,
|
|
"mean_token_accuracy": 0.2402253821492195,
|
|
"num_tokens": 77381652.0,
|
|
"step": 33750
|
|
},
|
|
{
|
|
"entropy": 5.1354992389678955,
|
|
"epoch": 3.2425552353506246,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00039691726158405606,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.24654935896396638,
|
|
"num_tokens": 77393335.0,
|
|
"step": 33755
|
|
},
|
|
{
|
|
"entropy": 5.09569935798645,
|
|
"epoch": 3.2430355427473585,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039688844578978516,
|
|
"loss": 4.6904,
|
|
"mean_token_accuracy": 0.24951207786798477,
|
|
"num_tokens": 77404311.0,
|
|
"step": 33760
|
|
},
|
|
{
|
|
"entropy": 5.189496994018555,
|
|
"epoch": 3.2435158501440924,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003968596271656263,
|
|
"loss": 4.7153,
|
|
"mean_token_accuracy": 0.24537211358547212,
|
|
"num_tokens": 77415886.0,
|
|
"step": 33765
|
|
},
|
|
{
|
|
"entropy": 5.167610549926758,
|
|
"epoch": 3.2439961575408263,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039683080571224885,
|
|
"loss": 4.7116,
|
|
"mean_token_accuracy": 0.24089743793010712,
|
|
"num_tokens": 77426300.0,
|
|
"step": 33770
|
|
},
|
|
{
|
|
"entropy": 5.196613693237305,
|
|
"epoch": 3.24447646493756,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003968019814303219,
|
|
"loss": 4.7345,
|
|
"mean_token_accuracy": 0.23954146206378937,
|
|
"num_tokens": 77437803.0,
|
|
"step": 33775
|
|
},
|
|
{
|
|
"entropy": 5.209648895263672,
|
|
"epoch": 3.244956772334294,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003967731543205145,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.24779223203659057,
|
|
"num_tokens": 77448850.0,
|
|
"step": 33780
|
|
},
|
|
{
|
|
"entropy": 5.136538410186768,
|
|
"epoch": 3.245437079731028,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039674432438349607,
|
|
"loss": 4.6793,
|
|
"mean_token_accuracy": 0.24981993436813354,
|
|
"num_tokens": 77458933.0,
|
|
"step": 33785
|
|
},
|
|
{
|
|
"entropy": 5.157934236526489,
|
|
"epoch": 3.245917387127762,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000396715491619936,
|
|
"loss": 4.6938,
|
|
"mean_token_accuracy": 0.23801656067371368,
|
|
"num_tokens": 77469916.0,
|
|
"step": 33790
|
|
},
|
|
{
|
|
"entropy": 5.2046760559082035,
|
|
"epoch": 3.2463976945244957,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003966866560305036,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.25087636709213257,
|
|
"num_tokens": 77480548.0,
|
|
"step": 33795
|
|
},
|
|
{
|
|
"entropy": 5.160145664215088,
|
|
"epoch": 3.2468780019212296,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039665781761586837,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.2349955692887306,
|
|
"num_tokens": 77490664.0,
|
|
"step": 33800
|
|
},
|
|
{
|
|
"entropy": 5.169839525222779,
|
|
"epoch": 3.2473583093179634,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003966289763766999,
|
|
"loss": 4.6654,
|
|
"mean_token_accuracy": 0.25556123703718187,
|
|
"num_tokens": 77502010.0,
|
|
"step": 33805
|
|
},
|
|
{
|
|
"entropy": 5.089337635040283,
|
|
"epoch": 3.2478386167146973,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003966001323136678,
|
|
"loss": 4.6658,
|
|
"mean_token_accuracy": 0.25026115477085115,
|
|
"num_tokens": 77513453.0,
|
|
"step": 33810
|
|
},
|
|
{
|
|
"entropy": 5.135791397094726,
|
|
"epoch": 3.248318924111431,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003965712854274416,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.24009255617856978,
|
|
"num_tokens": 77526294.0,
|
|
"step": 33815
|
|
},
|
|
{
|
|
"entropy": 5.214708995819092,
|
|
"epoch": 3.248799231508165,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003965424357186912,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.24123853594064712,
|
|
"num_tokens": 77537753.0,
|
|
"step": 33820
|
|
},
|
|
{
|
|
"entropy": 5.101520252227783,
|
|
"epoch": 3.249279538904899,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003965135831880864,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.24870093464851378,
|
|
"num_tokens": 77548931.0,
|
|
"step": 33825
|
|
},
|
|
{
|
|
"entropy": 5.074456739425659,
|
|
"epoch": 3.249759846301633,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000396484727836297,
|
|
"loss": 4.6653,
|
|
"mean_token_accuracy": 0.25041928589344026,
|
|
"num_tokens": 77560259.0,
|
|
"step": 33830
|
|
},
|
|
{
|
|
"entropy": 5.13788628578186,
|
|
"epoch": 3.2502401536983667,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003964558696639928,
|
|
"loss": 4.7346,
|
|
"mean_token_accuracy": 0.24867938607931137,
|
|
"num_tokens": 77571688.0,
|
|
"step": 33835
|
|
},
|
|
{
|
|
"entropy": 5.218821811676025,
|
|
"epoch": 3.250720461095101,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003964270086718441,
|
|
"loss": 4.7645,
|
|
"mean_token_accuracy": 0.2389594003558159,
|
|
"num_tokens": 77583754.0,
|
|
"step": 33840
|
|
},
|
|
{
|
|
"entropy": 5.181476688385009,
|
|
"epoch": 3.251200768491835,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00039639814486052083,
|
|
"loss": 4.6359,
|
|
"mean_token_accuracy": 0.2599753841757774,
|
|
"num_tokens": 77596013.0,
|
|
"step": 33845
|
|
},
|
|
{
|
|
"entropy": 5.166803503036499,
|
|
"epoch": 3.251681075888569,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003963692782306931,
|
|
"loss": 4.763,
|
|
"mean_token_accuracy": 0.2419028177857399,
|
|
"num_tokens": 77607349.0,
|
|
"step": 33850
|
|
},
|
|
{
|
|
"entropy": 5.129150009155273,
|
|
"epoch": 3.2521613832853027,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003963404087830311,
|
|
"loss": 4.6895,
|
|
"mean_token_accuracy": 0.2532268092036247,
|
|
"num_tokens": 77618325.0,
|
|
"step": 33855
|
|
},
|
|
{
|
|
"entropy": 5.248684930801391,
|
|
"epoch": 3.2526416906820366,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003963115365182051,
|
|
"loss": 4.8095,
|
|
"mean_token_accuracy": 0.23170838952064515,
|
|
"num_tokens": 77629794.0,
|
|
"step": 33860
|
|
},
|
|
{
|
|
"entropy": 5.092555236816406,
|
|
"epoch": 3.2531219980787704,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039628266143688554,
|
|
"loss": 4.6602,
|
|
"mean_token_accuracy": 0.24678821116685867,
|
|
"num_tokens": 77641800.0,
|
|
"step": 33865
|
|
},
|
|
{
|
|
"entropy": 5.094211673736572,
|
|
"epoch": 3.2536023054755043,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003962537835397426,
|
|
"loss": 4.6507,
|
|
"mean_token_accuracy": 0.24265118986368178,
|
|
"num_tokens": 77653533.0,
|
|
"step": 33870
|
|
},
|
|
{
|
|
"entropy": 5.161838626861572,
|
|
"epoch": 3.254082612872238,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00039622490282744684,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.24809625148773193,
|
|
"num_tokens": 77663508.0,
|
|
"step": 33875
|
|
},
|
|
{
|
|
"entropy": 5.147768926620484,
|
|
"epoch": 3.254562920268972,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003961960193006689,
|
|
"loss": 4.7163,
|
|
"mean_token_accuracy": 0.2425049588084221,
|
|
"num_tokens": 77674956.0,
|
|
"step": 33880
|
|
},
|
|
{
|
|
"entropy": 5.212384796142578,
|
|
"epoch": 3.255043227665706,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003961671329600792,
|
|
"loss": 4.7231,
|
|
"mean_token_accuracy": 0.2458633601665497,
|
|
"num_tokens": 77686000.0,
|
|
"step": 33885
|
|
},
|
|
{
|
|
"entropy": 5.045244932174683,
|
|
"epoch": 3.25552353506244,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003961382438063485,
|
|
"loss": 4.6192,
|
|
"mean_token_accuracy": 0.24541434347629548,
|
|
"num_tokens": 77698979.0,
|
|
"step": 33890
|
|
},
|
|
{
|
|
"entropy": 5.071407079696655,
|
|
"epoch": 3.2560038424591737,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003961093518401475,
|
|
"loss": 4.5716,
|
|
"mean_token_accuracy": 0.2551067814230919,
|
|
"num_tokens": 77710397.0,
|
|
"step": 33895
|
|
},
|
|
{
|
|
"entropy": 5.109147834777832,
|
|
"epoch": 3.2564841498559076,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00039608045706214696,
|
|
"loss": 4.6745,
|
|
"mean_token_accuracy": 0.2413107380270958,
|
|
"num_tokens": 77721665.0,
|
|
"step": 33900
|
|
},
|
|
{
|
|
"entropy": 5.123679494857788,
|
|
"epoch": 3.2569644572526415,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003960515594730177,
|
|
"loss": 4.7107,
|
|
"mean_token_accuracy": 0.2452580064535141,
|
|
"num_tokens": 77733328.0,
|
|
"step": 33905
|
|
},
|
|
{
|
|
"entropy": 5.188190221786499,
|
|
"epoch": 3.2574447646493754,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003960226590734307,
|
|
"loss": 4.7102,
|
|
"mean_token_accuracy": 0.2380910187959671,
|
|
"num_tokens": 77745812.0,
|
|
"step": 33910
|
|
},
|
|
{
|
|
"entropy": 5.055864763259888,
|
|
"epoch": 3.2579250720461097,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000395993755864057,
|
|
"loss": 4.5632,
|
|
"mean_token_accuracy": 0.2566261425614357,
|
|
"num_tokens": 77757473.0,
|
|
"step": 33915
|
|
},
|
|
{
|
|
"entropy": 5.131983089447021,
|
|
"epoch": 3.2584053794428436,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003959648498455674,
|
|
"loss": 4.706,
|
|
"mean_token_accuracy": 0.24274701327085496,
|
|
"num_tokens": 77769924.0,
|
|
"step": 33920
|
|
},
|
|
{
|
|
"entropy": 5.140430450439453,
|
|
"epoch": 3.2588856868395775,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00039593594101863333,
|
|
"loss": 4.7128,
|
|
"mean_token_accuracy": 0.24548477530479432,
|
|
"num_tokens": 77782048.0,
|
|
"step": 33925
|
|
},
|
|
{
|
|
"entropy": 5.059807968139649,
|
|
"epoch": 3.2593659942363113,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039590702938392577,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.2589406281709671,
|
|
"num_tokens": 77792371.0,
|
|
"step": 33930
|
|
},
|
|
{
|
|
"entropy": 5.1418098449707035,
|
|
"epoch": 3.2598463016330452,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039587811494211594,
|
|
"loss": 4.697,
|
|
"mean_token_accuracy": 0.24300350844860077,
|
|
"num_tokens": 77804089.0,
|
|
"step": 33935
|
|
},
|
|
{
|
|
"entropy": 5.08389801979065,
|
|
"epoch": 3.260326609029779,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00039584919769387536,
|
|
"loss": 4.6733,
|
|
"mean_token_accuracy": 0.24134858101606368,
|
|
"num_tokens": 77815962.0,
|
|
"step": 33940
|
|
},
|
|
{
|
|
"entropy": 5.172362565994263,
|
|
"epoch": 3.260806916426513,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003958202776398751,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.2361164465546608,
|
|
"num_tokens": 77827396.0,
|
|
"step": 33945
|
|
},
|
|
{
|
|
"entropy": 5.121752309799194,
|
|
"epoch": 3.261287223823247,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003957913547807868,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.25314422100782397,
|
|
"num_tokens": 77838916.0,
|
|
"step": 33950
|
|
},
|
|
{
|
|
"entropy": 5.280124139785767,
|
|
"epoch": 3.2617675312199808,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000395762429117282,
|
|
"loss": 4.8501,
|
|
"mean_token_accuracy": 0.24219347685575485,
|
|
"num_tokens": 77851393.0,
|
|
"step": 33955
|
|
},
|
|
{
|
|
"entropy": 5.176369285583496,
|
|
"epoch": 3.2622478386167146,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003957335006500321,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.2453562393784523,
|
|
"num_tokens": 77863124.0,
|
|
"step": 33960
|
|
},
|
|
{
|
|
"entropy": 5.087285852432251,
|
|
"epoch": 3.2627281460134485,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00039570456937970883,
|
|
"loss": 4.6705,
|
|
"mean_token_accuracy": 0.2489240512251854,
|
|
"num_tokens": 77875568.0,
|
|
"step": 33965
|
|
},
|
|
{
|
|
"entropy": 5.2129159450531,
|
|
"epoch": 3.2632084534101824,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003956756353069839,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.24387864917516708,
|
|
"num_tokens": 77885747.0,
|
|
"step": 33970
|
|
},
|
|
{
|
|
"entropy": 5.089494037628174,
|
|
"epoch": 3.2636887608069163,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003956466984325291,
|
|
"loss": 4.5888,
|
|
"mean_token_accuracy": 0.25772673189640044,
|
|
"num_tokens": 77897074.0,
|
|
"step": 33975
|
|
},
|
|
{
|
|
"entropy": 5.190212869644165,
|
|
"epoch": 3.26416906820365,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039561775875701616,
|
|
"loss": 4.7101,
|
|
"mean_token_accuracy": 0.2444063499569893,
|
|
"num_tokens": 77907718.0,
|
|
"step": 33980
|
|
},
|
|
{
|
|
"entropy": 5.104616022109985,
|
|
"epoch": 3.264649375600384,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000395588816281117,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.24345436692237854,
|
|
"num_tokens": 77919768.0,
|
|
"step": 33985
|
|
},
|
|
{
|
|
"entropy": 5.184665489196777,
|
|
"epoch": 3.2651296829971184,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003955598710055036,
|
|
"loss": 4.728,
|
|
"mean_token_accuracy": 0.24487801194190978,
|
|
"num_tokens": 77930927.0,
|
|
"step": 33990
|
|
},
|
|
{
|
|
"entropy": 5.198826551437378,
|
|
"epoch": 3.2656099903938522,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000395530922930848,
|
|
"loss": 4.6836,
|
|
"mean_token_accuracy": 0.2453143134713173,
|
|
"num_tokens": 77941907.0,
|
|
"step": 33995
|
|
},
|
|
{
|
|
"entropy": 5.102096128463745,
|
|
"epoch": 3.266090297790586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003955019720578223,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.24842080771923064,
|
|
"num_tokens": 77952800.0,
|
|
"step": 34000
|
|
},
|
|
{
|
|
"entropy": 5.200928163528443,
|
|
"epoch": 3.26657060518732,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003954730183870987,
|
|
"loss": 4.7606,
|
|
"mean_token_accuracy": 0.23927248269319534,
|
|
"num_tokens": 77963874.0,
|
|
"step": 34005
|
|
},
|
|
{
|
|
"entropy": 5.099039459228516,
|
|
"epoch": 3.267050912584054,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003954440619193491,
|
|
"loss": 4.5719,
|
|
"mean_token_accuracy": 0.25312535613775256,
|
|
"num_tokens": 77975282.0,
|
|
"step": 34010
|
|
},
|
|
{
|
|
"entropy": 5.075852870941162,
|
|
"epoch": 3.2675312199807878,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00039541510265524626,
|
|
"loss": 4.6166,
|
|
"mean_token_accuracy": 0.24718856066465378,
|
|
"num_tokens": 77987511.0,
|
|
"step": 34015
|
|
},
|
|
{
|
|
"entropy": 5.152427816390992,
|
|
"epoch": 3.2680115273775217,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003953861405954622,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.24522191435098648,
|
|
"num_tokens": 77997805.0,
|
|
"step": 34020
|
|
},
|
|
{
|
|
"entropy": 5.167752981185913,
|
|
"epoch": 3.2684918347742555,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003953571757406694,
|
|
"loss": 4.7421,
|
|
"mean_token_accuracy": 0.24328739047050477,
|
|
"num_tokens": 78010312.0,
|
|
"step": 34025
|
|
},
|
|
{
|
|
"entropy": 5.140766525268555,
|
|
"epoch": 3.2689721421709894,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039532820809154044,
|
|
"loss": 4.6323,
|
|
"mean_token_accuracy": 0.24977598935365677,
|
|
"num_tokens": 78019934.0,
|
|
"step": 34030
|
|
},
|
|
{
|
|
"entropy": 5.114881229400635,
|
|
"epoch": 3.2694524495677233,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039529923764874774,
|
|
"loss": 4.6235,
|
|
"mean_token_accuracy": 0.2569864720106125,
|
|
"num_tokens": 78031263.0,
|
|
"step": 34035
|
|
},
|
|
{
|
|
"entropy": 5.119789505004883,
|
|
"epoch": 3.269932756964457,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000395270264412964,
|
|
"loss": 4.692,
|
|
"mean_token_accuracy": 0.24850669056177138,
|
|
"num_tokens": 78043829.0,
|
|
"step": 34040
|
|
},
|
|
{
|
|
"entropy": 5.278003931045532,
|
|
"epoch": 3.270413064361191,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00039524128838486184,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.24188674241304398,
|
|
"num_tokens": 78055292.0,
|
|
"step": 34045
|
|
},
|
|
{
|
|
"entropy": 5.143099975585938,
|
|
"epoch": 3.270893371757925,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000395212309565114,
|
|
"loss": 4.7234,
|
|
"mean_token_accuracy": 0.24343198239803315,
|
|
"num_tokens": 78066969.0,
|
|
"step": 34050
|
|
},
|
|
{
|
|
"entropy": 5.2366949081420895,
|
|
"epoch": 3.271373679154659,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00039518332795439326,
|
|
"loss": 4.798,
|
|
"mean_token_accuracy": 0.23775899708271026,
|
|
"num_tokens": 78077994.0,
|
|
"step": 34055
|
|
},
|
|
{
|
|
"entropy": 5.115898323059082,
|
|
"epoch": 3.2718539865513927,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039515434355337254,
|
|
"loss": 4.6502,
|
|
"mean_token_accuracy": 0.2463037148118019,
|
|
"num_tokens": 78089730.0,
|
|
"step": 34060
|
|
},
|
|
{
|
|
"entropy": 5.178283643722534,
|
|
"epoch": 3.272334293948127,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003951253563627248,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.24164287149906158,
|
|
"num_tokens": 78100125.0,
|
|
"step": 34065
|
|
},
|
|
{
|
|
"entropy": 5.215008878707886,
|
|
"epoch": 3.2728146013448605,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003950963663831229,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.2371304452419281,
|
|
"num_tokens": 78112170.0,
|
|
"step": 34070
|
|
},
|
|
{
|
|
"entropy": 5.203554105758667,
|
|
"epoch": 3.273294908741595,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039506737361524007,
|
|
"loss": 4.7441,
|
|
"mean_token_accuracy": 0.23578462302684783,
|
|
"num_tokens": 78123796.0,
|
|
"step": 34075
|
|
},
|
|
{
|
|
"entropy": 5.126674556732178,
|
|
"epoch": 3.2737752161383287,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039503837805974926,
|
|
"loss": 4.6243,
|
|
"mean_token_accuracy": 0.2508496567606926,
|
|
"num_tokens": 78134170.0,
|
|
"step": 34080
|
|
},
|
|
{
|
|
"entropy": 5.0652679920196535,
|
|
"epoch": 3.2742555235350626,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00039500937971732376,
|
|
"loss": 4.6745,
|
|
"mean_token_accuracy": 0.2518126621842384,
|
|
"num_tokens": 78145140.0,
|
|
"step": 34085
|
|
},
|
|
{
|
|
"entropy": 5.2364426612854,
|
|
"epoch": 3.2747358309317964,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003949803785886369,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.2405719593167305,
|
|
"num_tokens": 78157627.0,
|
|
"step": 34090
|
|
},
|
|
{
|
|
"entropy": 5.183147525787353,
|
|
"epoch": 3.2752161383285303,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039495137467436184,
|
|
"loss": 4.7722,
|
|
"mean_token_accuracy": 0.2372443750500679,
|
|
"num_tokens": 78170343.0,
|
|
"step": 34095
|
|
},
|
|
{
|
|
"entropy": 5.153350114822388,
|
|
"epoch": 3.275696445725264,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00039492236797517206,
|
|
"loss": 4.6695,
|
|
"mean_token_accuracy": 0.24853093326091766,
|
|
"num_tokens": 78181393.0,
|
|
"step": 34100
|
|
},
|
|
{
|
|
"entropy": 5.137990236282349,
|
|
"epoch": 3.276176753121998,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000394893358491741,
|
|
"loss": 4.7059,
|
|
"mean_token_accuracy": 0.24205240309238435,
|
|
"num_tokens": 78193048.0,
|
|
"step": 34105
|
|
},
|
|
{
|
|
"entropy": 5.102763652801514,
|
|
"epoch": 3.276657060518732,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00039486434622474216,
|
|
"loss": 4.6285,
|
|
"mean_token_accuracy": 0.2505753591656685,
|
|
"num_tokens": 78203738.0,
|
|
"step": 34110
|
|
},
|
|
{
|
|
"entropy": 5.1982728958129885,
|
|
"epoch": 3.277137367915466,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039483533117484916,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.2346199184656143,
|
|
"num_tokens": 78215171.0,
|
|
"step": 34115
|
|
},
|
|
{
|
|
"entropy": 5.146343231201172,
|
|
"epoch": 3.2776176753121997,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003948063133427356,
|
|
"loss": 4.6303,
|
|
"mean_token_accuracy": 0.2476674348115921,
|
|
"num_tokens": 78225901.0,
|
|
"step": 34120
|
|
},
|
|
{
|
|
"entropy": 5.125644874572754,
|
|
"epoch": 3.2780979827089336,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003947772927290751,
|
|
"loss": 4.642,
|
|
"mean_token_accuracy": 0.2453186869621277,
|
|
"num_tokens": 78237327.0,
|
|
"step": 34125
|
|
},
|
|
{
|
|
"entropy": 5.097128200531006,
|
|
"epoch": 3.2785782901056675,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003947482693345416,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.24400950372219085,
|
|
"num_tokens": 78248030.0,
|
|
"step": 34130
|
|
},
|
|
{
|
|
"entropy": 5.0906334400177,
|
|
"epoch": 3.2790585975024014,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039471924315980894,
|
|
"loss": 4.5949,
|
|
"mean_token_accuracy": 0.2529935672879219,
|
|
"num_tokens": 78259303.0,
|
|
"step": 34135
|
|
},
|
|
{
|
|
"entropy": 5.17118763923645,
|
|
"epoch": 3.2795389048991357,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00039469021420555087,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.24797320514917373,
|
|
"num_tokens": 78271284.0,
|
|
"step": 34140
|
|
},
|
|
{
|
|
"entropy": 5.100211572647095,
|
|
"epoch": 3.280019212295869,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039466118247244143,
|
|
"loss": 4.6281,
|
|
"mean_token_accuracy": 0.24860841333866118,
|
|
"num_tokens": 78282718.0,
|
|
"step": 34145
|
|
},
|
|
{
|
|
"entropy": 5.082750082015991,
|
|
"epoch": 3.2804995196926034,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003946321479611547,
|
|
"loss": 4.6662,
|
|
"mean_token_accuracy": 0.25259427577257154,
|
|
"num_tokens": 78294292.0,
|
|
"step": 34150
|
|
},
|
|
{
|
|
"entropy": 5.105408239364624,
|
|
"epoch": 3.2809798270893373,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039460311067236465,
|
|
"loss": 4.705,
|
|
"mean_token_accuracy": 0.24075779914855958,
|
|
"num_tokens": 78306834.0,
|
|
"step": 34155
|
|
},
|
|
{
|
|
"entropy": 5.173525953292847,
|
|
"epoch": 3.281460134486071,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00039457407060674557,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.23784261494874953,
|
|
"num_tokens": 78319866.0,
|
|
"step": 34160
|
|
},
|
|
{
|
|
"entropy": 5.136395978927612,
|
|
"epoch": 3.281940441882805,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039454502776497163,
|
|
"loss": 4.693,
|
|
"mean_token_accuracy": 0.24173314422369002,
|
|
"num_tokens": 78330933.0,
|
|
"step": 34165
|
|
},
|
|
{
|
|
"entropy": 5.130362939834595,
|
|
"epoch": 3.282420749279539,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039451598214771706,
|
|
"loss": 4.6541,
|
|
"mean_token_accuracy": 0.24638260304927825,
|
|
"num_tokens": 78342323.0,
|
|
"step": 34170
|
|
},
|
|
{
|
|
"entropy": 5.1579986095428465,
|
|
"epoch": 3.282901056676273,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003944869337556563,
|
|
"loss": 4.6648,
|
|
"mean_token_accuracy": 0.25402072072029114,
|
|
"num_tokens": 78353090.0,
|
|
"step": 34175
|
|
},
|
|
{
|
|
"entropy": 5.144975423812866,
|
|
"epoch": 3.2833813640730067,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003944578825894639,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.24356811195611955,
|
|
"num_tokens": 78362679.0,
|
|
"step": 34180
|
|
},
|
|
{
|
|
"entropy": 5.133348178863526,
|
|
"epoch": 3.2838616714697406,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039442882864981397,
|
|
"loss": 4.719,
|
|
"mean_token_accuracy": 0.23982588052749634,
|
|
"num_tokens": 78373592.0,
|
|
"step": 34185
|
|
},
|
|
{
|
|
"entropy": 5.071165943145752,
|
|
"epoch": 3.2843419788664745,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00039439977193738134,
|
|
"loss": 4.5937,
|
|
"mean_token_accuracy": 0.2567233607172966,
|
|
"num_tokens": 78384617.0,
|
|
"step": 34190
|
|
},
|
|
{
|
|
"entropy": 5.1175824165344235,
|
|
"epoch": 3.2848222862632084,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039437071245284055,
|
|
"loss": 4.7125,
|
|
"mean_token_accuracy": 0.24036370515823363,
|
|
"num_tokens": 78396253.0,
|
|
"step": 34195
|
|
},
|
|
{
|
|
"entropy": 5.181387853622437,
|
|
"epoch": 3.2853025936599423,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003943416501968663,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.23627979755401612,
|
|
"num_tokens": 78407852.0,
|
|
"step": 34200
|
|
},
|
|
{
|
|
"entropy": 5.096895503997803,
|
|
"epoch": 3.285782901056676,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039431258517013323,
|
|
"loss": 4.6138,
|
|
"mean_token_accuracy": 0.2537956193089485,
|
|
"num_tokens": 78419434.0,
|
|
"step": 34205
|
|
},
|
|
{
|
|
"entropy": 5.194113302230835,
|
|
"epoch": 3.28626320845341,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003942835173733163,
|
|
"loss": 4.7163,
|
|
"mean_token_accuracy": 0.24129782915115355,
|
|
"num_tokens": 78431820.0,
|
|
"step": 34210
|
|
},
|
|
{
|
|
"entropy": 5.1582550525665285,
|
|
"epoch": 3.286743515850144,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003942544468070903,
|
|
"loss": 4.7082,
|
|
"mean_token_accuracy": 0.2470415562391281,
|
|
"num_tokens": 78443062.0,
|
|
"step": 34215
|
|
},
|
|
{
|
|
"entropy": 5.179015445709228,
|
|
"epoch": 3.287223823246878,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0003942253734721301,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.24918436110019684,
|
|
"num_tokens": 78454091.0,
|
|
"step": 34220
|
|
},
|
|
{
|
|
"entropy": 5.17704668045044,
|
|
"epoch": 3.287704130643612,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00039419629736911076,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.24304568022489548,
|
|
"num_tokens": 78466108.0,
|
|
"step": 34225
|
|
},
|
|
{
|
|
"entropy": 5.097767305374146,
|
|
"epoch": 3.288184438040346,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039416721849870736,
|
|
"loss": 4.5938,
|
|
"mean_token_accuracy": 0.2503079503774643,
|
|
"num_tokens": 78476690.0,
|
|
"step": 34230
|
|
},
|
|
{
|
|
"entropy": 5.216614627838135,
|
|
"epoch": 3.28866474543708,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003941381368615951,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.23457180708646774,
|
|
"num_tokens": 78487157.0,
|
|
"step": 34235
|
|
},
|
|
{
|
|
"entropy": 5.203792762756348,
|
|
"epoch": 3.2891450528338138,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003941090524584489,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.24233219921588897,
|
|
"num_tokens": 78499034.0,
|
|
"step": 34240
|
|
},
|
|
{
|
|
"entropy": 5.111922836303711,
|
|
"epoch": 3.2896253602305476,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003940799652899442,
|
|
"loss": 4.62,
|
|
"mean_token_accuracy": 0.2556920275092125,
|
|
"num_tokens": 78509720.0,
|
|
"step": 34245
|
|
},
|
|
{
|
|
"entropy": 5.155395269393921,
|
|
"epoch": 3.2901056676272815,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003940508753567564,
|
|
"loss": 4.7109,
|
|
"mean_token_accuracy": 0.24745707362890243,
|
|
"num_tokens": 78522126.0,
|
|
"step": 34250
|
|
},
|
|
{
|
|
"entropy": 5.191883897781372,
|
|
"epoch": 3.2905859750240154,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00039402178265956074,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.24081843495368957,
|
|
"num_tokens": 78533348.0,
|
|
"step": 34255
|
|
},
|
|
{
|
|
"entropy": 5.168289709091186,
|
|
"epoch": 3.2910662824207493,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003939926871990328,
|
|
"loss": 4.6902,
|
|
"mean_token_accuracy": 0.24183135628700256,
|
|
"num_tokens": 78545889.0,
|
|
"step": 34260
|
|
},
|
|
{
|
|
"entropy": 5.166662788391113,
|
|
"epoch": 3.291546589817483,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003939635889758478,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.2446528434753418,
|
|
"num_tokens": 78557429.0,
|
|
"step": 34265
|
|
},
|
|
{
|
|
"entropy": 5.105626726150513,
|
|
"epoch": 3.292026897214217,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039393448799068164,
|
|
"loss": 4.6019,
|
|
"mean_token_accuracy": 0.25729805082082746,
|
|
"num_tokens": 78567824.0,
|
|
"step": 34270
|
|
},
|
|
{
|
|
"entropy": 5.202728891372681,
|
|
"epoch": 3.292507204610951,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003939053842442098,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.2451612636446953,
|
|
"num_tokens": 78578229.0,
|
|
"step": 34275
|
|
},
|
|
{
|
|
"entropy": 5.125255441665649,
|
|
"epoch": 3.292987512007685,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039387627773710803,
|
|
"loss": 4.7146,
|
|
"mean_token_accuracy": 0.24617656767368318,
|
|
"num_tokens": 78591619.0,
|
|
"step": 34280
|
|
},
|
|
{
|
|
"entropy": 5.135665798187256,
|
|
"epoch": 3.2934678194044187,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00039384716847005216,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.24433417171239852,
|
|
"num_tokens": 78602576.0,
|
|
"step": 34285
|
|
},
|
|
{
|
|
"entropy": 5.09686975479126,
|
|
"epoch": 3.2939481268011526,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039381805644371774,
|
|
"loss": 4.6725,
|
|
"mean_token_accuracy": 0.2532437637448311,
|
|
"num_tokens": 78613532.0,
|
|
"step": 34290
|
|
},
|
|
{
|
|
"entropy": 5.159070777893066,
|
|
"epoch": 3.2944284341978864,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000393788941658781,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.24293361753225326,
|
|
"num_tokens": 78626120.0,
|
|
"step": 34295
|
|
},
|
|
{
|
|
"entropy": 5.14443736076355,
|
|
"epoch": 3.2949087415946208,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039375982411591774,
|
|
"loss": 4.672,
|
|
"mean_token_accuracy": 0.2466450423002243,
|
|
"num_tokens": 78636175.0,
|
|
"step": 34300
|
|
},
|
|
{
|
|
"entropy": 5.205699920654297,
|
|
"epoch": 3.2953890489913547,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039373070381580404,
|
|
"loss": 4.7369,
|
|
"mean_token_accuracy": 0.24011295437812805,
|
|
"num_tokens": 78647429.0,
|
|
"step": 34305
|
|
},
|
|
{
|
|
"entropy": 5.156354141235352,
|
|
"epoch": 3.2958693563880885,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003937015807591159,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.23992310911417009,
|
|
"num_tokens": 78659792.0,
|
|
"step": 34310
|
|
},
|
|
{
|
|
"entropy": 5.097876024246216,
|
|
"epoch": 3.2963496637848224,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00039367245494652963,
|
|
"loss": 4.6292,
|
|
"mean_token_accuracy": 0.2515589311718941,
|
|
"num_tokens": 78670614.0,
|
|
"step": 34315
|
|
},
|
|
{
|
|
"entropy": 5.125292587280273,
|
|
"epoch": 3.2968299711815563,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039364332637872125,
|
|
"loss": 4.6484,
|
|
"mean_token_accuracy": 0.24853684455156327,
|
|
"num_tokens": 78681475.0,
|
|
"step": 34320
|
|
},
|
|
{
|
|
"entropy": 5.141855239868164,
|
|
"epoch": 3.29731027857829,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039361419505636714,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.2521594062447548,
|
|
"num_tokens": 78692251.0,
|
|
"step": 34325
|
|
},
|
|
{
|
|
"entropy": 5.1322534561157225,
|
|
"epoch": 3.297790585975024,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00039358506098014363,
|
|
"loss": 4.6947,
|
|
"mean_token_accuracy": 0.24853314310312272,
|
|
"num_tokens": 78704584.0,
|
|
"step": 34330
|
|
},
|
|
{
|
|
"entropy": 5.1246405124664305,
|
|
"epoch": 3.298270893371758,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039355592415072716,
|
|
"loss": 4.6298,
|
|
"mean_token_accuracy": 0.24206819236278534,
|
|
"num_tokens": 78715467.0,
|
|
"step": 34335
|
|
},
|
|
{
|
|
"entropy": 5.146251964569092,
|
|
"epoch": 3.298751200768492,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00039352678456879415,
|
|
"loss": 4.6249,
|
|
"mean_token_accuracy": 0.25209286212921145,
|
|
"num_tokens": 78725835.0,
|
|
"step": 34340
|
|
},
|
|
{
|
|
"entropy": 5.080556869506836,
|
|
"epoch": 3.2992315081652257,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003934976422350212,
|
|
"loss": 4.6198,
|
|
"mean_token_accuracy": 0.2547671049833298,
|
|
"num_tokens": 78737143.0,
|
|
"step": 34345
|
|
},
|
|
{
|
|
"entropy": 5.2710638523101805,
|
|
"epoch": 3.2997118155619596,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003934684971500848,
|
|
"loss": 4.8719,
|
|
"mean_token_accuracy": 0.23578266203403472,
|
|
"num_tokens": 78748641.0,
|
|
"step": 34350
|
|
},
|
|
{
|
|
"entropy": 5.160272121429443,
|
|
"epoch": 3.3001921229586935,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039343934931466165,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.24485700130462645,
|
|
"num_tokens": 78760200.0,
|
|
"step": 34355
|
|
},
|
|
{
|
|
"entropy": 5.0983278274536135,
|
|
"epoch": 3.3006724303554273,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00039341019872942855,
|
|
"loss": 4.6639,
|
|
"mean_token_accuracy": 0.24777539521455766,
|
|
"num_tokens": 78771347.0,
|
|
"step": 34360
|
|
},
|
|
{
|
|
"entropy": 5.065286779403687,
|
|
"epoch": 3.3011527377521612,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039338104539506227,
|
|
"loss": 4.5926,
|
|
"mean_token_accuracy": 0.2545404449105263,
|
|
"num_tokens": 78783514.0,
|
|
"step": 34365
|
|
},
|
|
{
|
|
"entropy": 5.165731430053711,
|
|
"epoch": 3.301633045148895,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003933518893122396,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.24035310447216035,
|
|
"num_tokens": 78794621.0,
|
|
"step": 34370
|
|
},
|
|
{
|
|
"entropy": 5.194527530670166,
|
|
"epoch": 3.3021133525456294,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003933227304816375,
|
|
"loss": 4.6951,
|
|
"mean_token_accuracy": 0.25118681639432905,
|
|
"num_tokens": 78806293.0,
|
|
"step": 34375
|
|
},
|
|
{
|
|
"entropy": 5.270431041717529,
|
|
"epoch": 3.302593659942363,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000393293568903933,
|
|
"loss": 4.7228,
|
|
"mean_token_accuracy": 0.23806269615888595,
|
|
"num_tokens": 78816930.0,
|
|
"step": 34380
|
|
},
|
|
{
|
|
"entropy": 5.147794771194458,
|
|
"epoch": 3.303073967339097,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003932644045798029,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.2353382483124733,
|
|
"num_tokens": 78828321.0,
|
|
"step": 34385
|
|
},
|
|
{
|
|
"entropy": 5.144099998474121,
|
|
"epoch": 3.303554274735831,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003932352375099247,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.23757449984550477,
|
|
"num_tokens": 78840967.0,
|
|
"step": 34390
|
|
},
|
|
{
|
|
"entropy": 5.1523298740386965,
|
|
"epoch": 3.304034582132565,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003932060676949753,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.24591094255447388,
|
|
"num_tokens": 78853037.0,
|
|
"step": 34395
|
|
},
|
|
{
|
|
"entropy": 5.245528745651245,
|
|
"epoch": 3.304514889529299,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003931768951356319,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.23967465460300447,
|
|
"num_tokens": 78863441.0,
|
|
"step": 34400
|
|
},
|
|
{
|
|
"entropy": 5.025860834121704,
|
|
"epoch": 3.3049951969260327,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003931477198325721,
|
|
"loss": 4.6144,
|
|
"mean_token_accuracy": 0.25725976526737215,
|
|
"num_tokens": 78875770.0,
|
|
"step": 34405
|
|
},
|
|
{
|
|
"entropy": 5.171040868759155,
|
|
"epoch": 3.3054755043227666,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000393118541786473,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.2519155129790306,
|
|
"num_tokens": 78886239.0,
|
|
"step": 34410
|
|
},
|
|
{
|
|
"entropy": 5.132843017578125,
|
|
"epoch": 3.3059558117195005,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00039308936099801203,
|
|
"loss": 4.7244,
|
|
"mean_token_accuracy": 0.23806411176919937,
|
|
"num_tokens": 78897497.0,
|
|
"step": 34415
|
|
},
|
|
{
|
|
"entropy": 5.204543590545654,
|
|
"epoch": 3.3064361191162344,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003930601774678669,
|
|
"loss": 4.7346,
|
|
"mean_token_accuracy": 0.24320772886276246,
|
|
"num_tokens": 78908643.0,
|
|
"step": 34420
|
|
},
|
|
{
|
|
"entropy": 5.2129076480865475,
|
|
"epoch": 3.3069164265129682,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039303099119671487,
|
|
"loss": 4.7874,
|
|
"mean_token_accuracy": 0.23983669579029082,
|
|
"num_tokens": 78921240.0,
|
|
"step": 34425
|
|
},
|
|
{
|
|
"entropy": 5.156590747833252,
|
|
"epoch": 3.307396733909702,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00039300180218523374,
|
|
"loss": 4.7241,
|
|
"mean_token_accuracy": 0.25276840031147,
|
|
"num_tokens": 78933803.0,
|
|
"step": 34430
|
|
},
|
|
{
|
|
"entropy": 5.23590726852417,
|
|
"epoch": 3.307877041306436,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003929726104341013,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.23650489896535873,
|
|
"num_tokens": 78944876.0,
|
|
"step": 34435
|
|
},
|
|
{
|
|
"entropy": 5.1138547420501705,
|
|
"epoch": 3.30835734870317,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039294341594399494,
|
|
"loss": 4.6416,
|
|
"mean_token_accuracy": 0.2512674733996391,
|
|
"num_tokens": 78957044.0,
|
|
"step": 34440
|
|
},
|
|
{
|
|
"entropy": 5.10453953742981,
|
|
"epoch": 3.3088376560999038,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039291421871559274,
|
|
"loss": 4.6523,
|
|
"mean_token_accuracy": 0.2502345472574234,
|
|
"num_tokens": 78968654.0,
|
|
"step": 34445
|
|
},
|
|
{
|
|
"entropy": 5.135651302337647,
|
|
"epoch": 3.309317963496638,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00039288501874957263,
|
|
"loss": 4.7206,
|
|
"mean_token_accuracy": 0.24480136185884477,
|
|
"num_tokens": 78980201.0,
|
|
"step": 34450
|
|
},
|
|
{
|
|
"entropy": 5.197422456741333,
|
|
"epoch": 3.3097982708933715,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003928558160466123,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.23653860241174698,
|
|
"num_tokens": 78991172.0,
|
|
"step": 34455
|
|
},
|
|
{
|
|
"entropy": 5.179793643951416,
|
|
"epoch": 3.310278578290106,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003928266106073899,
|
|
"loss": 4.6929,
|
|
"mean_token_accuracy": 0.24856820702552795,
|
|
"num_tokens": 79001944.0,
|
|
"step": 34460
|
|
},
|
|
{
|
|
"entropy": 5.152010154724121,
|
|
"epoch": 3.3107588856868397,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039279740243258353,
|
|
"loss": 4.728,
|
|
"mean_token_accuracy": 0.2474230334162712,
|
|
"num_tokens": 79014715.0,
|
|
"step": 34465
|
|
},
|
|
{
|
|
"entropy": 5.16886715888977,
|
|
"epoch": 3.3112391930835736,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003927681915228712,
|
|
"loss": 4.6395,
|
|
"mean_token_accuracy": 0.2521603241562843,
|
|
"num_tokens": 79025499.0,
|
|
"step": 34470
|
|
},
|
|
{
|
|
"entropy": 5.115682601928711,
|
|
"epoch": 3.3117195004803075,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0003927389778789312,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.24561145901679993,
|
|
"num_tokens": 79037400.0,
|
|
"step": 34475
|
|
},
|
|
{
|
|
"entropy": 5.1500975608825685,
|
|
"epoch": 3.3121998078770414,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003927097615014418,
|
|
"loss": 4.7003,
|
|
"mean_token_accuracy": 0.24636815637350082,
|
|
"num_tokens": 79048450.0,
|
|
"step": 34480
|
|
},
|
|
{
|
|
"entropy": 5.164562177658081,
|
|
"epoch": 3.3126801152737753,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003926805423910811,
|
|
"loss": 4.7672,
|
|
"mean_token_accuracy": 0.24603996127843858,
|
|
"num_tokens": 79061579.0,
|
|
"step": 34485
|
|
},
|
|
{
|
|
"entropy": 5.125393009185791,
|
|
"epoch": 3.313160422670509,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003926513205485278,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.24076797366142272,
|
|
"num_tokens": 79073106.0,
|
|
"step": 34490
|
|
},
|
|
{
|
|
"entropy": 5.133156871795654,
|
|
"epoch": 3.313640730067243,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003926220959744602,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.2379649430513382,
|
|
"num_tokens": 79085528.0,
|
|
"step": 34495
|
|
},
|
|
{
|
|
"entropy": 5.125233840942383,
|
|
"epoch": 3.314121037463977,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003925928686695567,
|
|
"loss": 4.5977,
|
|
"mean_token_accuracy": 0.26034876257181166,
|
|
"num_tokens": 79096429.0,
|
|
"step": 34500
|
|
},
|
|
{
|
|
"entropy": 5.187419366836548,
|
|
"epoch": 3.314601344860711,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000392563638634496,
|
|
"loss": 4.7515,
|
|
"mean_token_accuracy": 0.24408489912748338,
|
|
"num_tokens": 79107688.0,
|
|
"step": 34505
|
|
},
|
|
{
|
|
"entropy": 5.145610189437866,
|
|
"epoch": 3.3150816522574447,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003925344058699567,
|
|
"loss": 4.6704,
|
|
"mean_token_accuracy": 0.2493273839354515,
|
|
"num_tokens": 79119549.0,
|
|
"step": 34510
|
|
},
|
|
{
|
|
"entropy": 5.110235738754272,
|
|
"epoch": 3.3155619596541785,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003925051703766175,
|
|
"loss": 4.6514,
|
|
"mean_token_accuracy": 0.2570398971438408,
|
|
"num_tokens": 79131193.0,
|
|
"step": 34515
|
|
},
|
|
{
|
|
"entropy": 5.148912572860718,
|
|
"epoch": 3.3160422670509124,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003924759321551572,
|
|
"loss": 4.7292,
|
|
"mean_token_accuracy": 0.23679856657981874,
|
|
"num_tokens": 79142117.0,
|
|
"step": 34520
|
|
},
|
|
{
|
|
"entropy": 5.172797060012817,
|
|
"epoch": 3.3165225744476463,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003924466912062546,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.24731513261795043,
|
|
"num_tokens": 79154734.0,
|
|
"step": 34525
|
|
},
|
|
{
|
|
"entropy": 5.151692295074463,
|
|
"epoch": 3.31700288184438,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003924174475305885,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.23730453550815583,
|
|
"num_tokens": 79166077.0,
|
|
"step": 34530
|
|
},
|
|
{
|
|
"entropy": 5.169718265533447,
|
|
"epoch": 3.3174831892411145,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00039238820112883795,
|
|
"loss": 4.7128,
|
|
"mean_token_accuracy": 0.2431535854935646,
|
|
"num_tokens": 79177544.0,
|
|
"step": 34535
|
|
},
|
|
{
|
|
"entropy": 5.111993932723999,
|
|
"epoch": 3.3179634966378484,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003923589520016819,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.24877750426530837,
|
|
"num_tokens": 79189606.0,
|
|
"step": 34540
|
|
},
|
|
{
|
|
"entropy": 5.058762311935425,
|
|
"epoch": 3.3184438040345823,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039232970014979965,
|
|
"loss": 4.608,
|
|
"mean_token_accuracy": 0.25170712172985077,
|
|
"num_tokens": 79201385.0,
|
|
"step": 34545
|
|
},
|
|
{
|
|
"entropy": 5.1681684970855715,
|
|
"epoch": 3.318924111431316,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003923004455738699,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.2338995575904846,
|
|
"num_tokens": 79213481.0,
|
|
"step": 34550
|
|
},
|
|
{
|
|
"entropy": 5.121838235855103,
|
|
"epoch": 3.31940441882805,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00039227118827457234,
|
|
"loss": 4.6493,
|
|
"mean_token_accuracy": 0.24404061883687972,
|
|
"num_tokens": 79226369.0,
|
|
"step": 34555
|
|
},
|
|
{
|
|
"entropy": 5.168177700042724,
|
|
"epoch": 3.319884726224784,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039224192825258584,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.23898293673992158,
|
|
"num_tokens": 79238236.0,
|
|
"step": 34560
|
|
},
|
|
{
|
|
"entropy": 5.222214889526367,
|
|
"epoch": 3.320365033621518,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039221266550859004,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.24541564136743546,
|
|
"num_tokens": 79248536.0,
|
|
"step": 34565
|
|
},
|
|
{
|
|
"entropy": 5.130749320983886,
|
|
"epoch": 3.3208453410182517,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00039218340004326414,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.247484689950943,
|
|
"num_tokens": 79259273.0,
|
|
"step": 34570
|
|
},
|
|
{
|
|
"entropy": 4.999196004867554,
|
|
"epoch": 3.3213256484149856,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003921541318572876,
|
|
"loss": 4.5918,
|
|
"mean_token_accuracy": 0.25260053128004073,
|
|
"num_tokens": 79271986.0,
|
|
"step": 34575
|
|
},
|
|
{
|
|
"entropy": 5.127130222320557,
|
|
"epoch": 3.3218059558117194,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00039212486095134005,
|
|
"loss": 4.6846,
|
|
"mean_token_accuracy": 0.2496616944670677,
|
|
"num_tokens": 79282602.0,
|
|
"step": 34580
|
|
},
|
|
{
|
|
"entropy": 5.128148555755615,
|
|
"epoch": 3.3222862632084533,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003920955873261011,
|
|
"loss": 4.6904,
|
|
"mean_token_accuracy": 0.2517551377415657,
|
|
"num_tokens": 79295034.0,
|
|
"step": 34585
|
|
},
|
|
{
|
|
"entropy": 5.121544933319091,
|
|
"epoch": 3.322766570605187,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003920663109822502,
|
|
"loss": 4.6815,
|
|
"mean_token_accuracy": 0.24025364816188813,
|
|
"num_tokens": 79307434.0,
|
|
"step": 34590
|
|
},
|
|
{
|
|
"entropy": 5.213470888137818,
|
|
"epoch": 3.323246878001921,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00039203703192046717,
|
|
"loss": 4.7529,
|
|
"mean_token_accuracy": 0.2437213569879532,
|
|
"num_tokens": 79318185.0,
|
|
"step": 34595
|
|
},
|
|
{
|
|
"entropy": 5.0758607387542725,
|
|
"epoch": 3.323727185398655,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0003920077501414318,
|
|
"loss": 4.6305,
|
|
"mean_token_accuracy": 0.2536413937807083,
|
|
"num_tokens": 79329800.0,
|
|
"step": 34600
|
|
},
|
|
{
|
|
"entropy": 5.0811371326446535,
|
|
"epoch": 3.324207492795389,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039197846564582395,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.2418385773897171,
|
|
"num_tokens": 79342537.0,
|
|
"step": 34605
|
|
},
|
|
{
|
|
"entropy": 5.140053176879883,
|
|
"epoch": 3.324687800192123,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039194917843432347,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.2427401915192604,
|
|
"num_tokens": 79353727.0,
|
|
"step": 34610
|
|
},
|
|
{
|
|
"entropy": 5.125836896896362,
|
|
"epoch": 3.325168107588857,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003919198885076103,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.2533853486180305,
|
|
"num_tokens": 79364337.0,
|
|
"step": 34615
|
|
},
|
|
{
|
|
"entropy": 5.173584985733032,
|
|
"epoch": 3.325648414985591,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039189059586636465,
|
|
"loss": 4.6866,
|
|
"mean_token_accuracy": 0.24444528073072433,
|
|
"num_tokens": 79375890.0,
|
|
"step": 34620
|
|
},
|
|
{
|
|
"entropy": 5.175454711914062,
|
|
"epoch": 3.326128722382325,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003918613005112663,
|
|
"loss": 4.6769,
|
|
"mean_token_accuracy": 0.2469544917345047,
|
|
"num_tokens": 79386686.0,
|
|
"step": 34625
|
|
},
|
|
{
|
|
"entropy": 5.147291803359986,
|
|
"epoch": 3.3266090297790587,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003918320024429956,
|
|
"loss": 4.7112,
|
|
"mean_token_accuracy": 0.24575983881950378,
|
|
"num_tokens": 79397852.0,
|
|
"step": 34630
|
|
},
|
|
{
|
|
"entropy": 5.157345485687256,
|
|
"epoch": 3.3270893371757926,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003918027016622328,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.2550876662135124,
|
|
"num_tokens": 79409547.0,
|
|
"step": 34635
|
|
},
|
|
{
|
|
"entropy": 5.061700439453125,
|
|
"epoch": 3.3275696445725265,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003917733981696579,
|
|
"loss": 4.6713,
|
|
"mean_token_accuracy": 0.25345264077186586,
|
|
"num_tokens": 79421906.0,
|
|
"step": 34640
|
|
},
|
|
{
|
|
"entropy": 5.143097162246704,
|
|
"epoch": 3.3280499519692603,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003917440919659516,
|
|
"loss": 4.6625,
|
|
"mean_token_accuracy": 0.24853249341249467,
|
|
"num_tokens": 79433767.0,
|
|
"step": 34645
|
|
},
|
|
{
|
|
"entropy": 5.206482791900635,
|
|
"epoch": 3.3285302593659942,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003917147830517941,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.23552721440792085,
|
|
"num_tokens": 79445488.0,
|
|
"step": 34650
|
|
},
|
|
{
|
|
"entropy": 5.167483520507813,
|
|
"epoch": 3.329010566762728,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003916854714278659,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.24754005819559097,
|
|
"num_tokens": 79457908.0,
|
|
"step": 34655
|
|
},
|
|
{
|
|
"entropy": 5.147553491592407,
|
|
"epoch": 3.329490874159462,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003916561570948476,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.23872119784355164,
|
|
"num_tokens": 79469876.0,
|
|
"step": 34660
|
|
},
|
|
{
|
|
"entropy": 5.090311813354492,
|
|
"epoch": 3.329971181556196,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003916268400534197,
|
|
"loss": 4.6077,
|
|
"mean_token_accuracy": 0.24960871785879135,
|
|
"num_tokens": 79480532.0,
|
|
"step": 34665
|
|
},
|
|
{
|
|
"entropy": 5.084006929397583,
|
|
"epoch": 3.3304514889529298,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003915975203042628,
|
|
"loss": 4.6982,
|
|
"mean_token_accuracy": 0.24468864798545836,
|
|
"num_tokens": 79491298.0,
|
|
"step": 34670
|
|
},
|
|
{
|
|
"entropy": 5.141863632202148,
|
|
"epoch": 3.3309317963496636,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039156819784805783,
|
|
"loss": 4.6744,
|
|
"mean_token_accuracy": 0.23939260244369506,
|
|
"num_tokens": 79502794.0,
|
|
"step": 34675
|
|
},
|
|
{
|
|
"entropy": 5.129342889785766,
|
|
"epoch": 3.3314121037463975,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003915388726854854,
|
|
"loss": 4.678,
|
|
"mean_token_accuracy": 0.2417725458741188,
|
|
"num_tokens": 79513104.0,
|
|
"step": 34680
|
|
},
|
|
{
|
|
"entropy": 5.180205821990967,
|
|
"epoch": 3.331892411143132,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039150954481722634,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.23689423501491547,
|
|
"num_tokens": 79524660.0,
|
|
"step": 34685
|
|
},
|
|
{
|
|
"entropy": 5.196865653991699,
|
|
"epoch": 3.3323727185398653,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003914802142439617,
|
|
"loss": 4.6987,
|
|
"mean_token_accuracy": 0.2426236927509308,
|
|
"num_tokens": 79538027.0,
|
|
"step": 34690
|
|
},
|
|
{
|
|
"entropy": 5.131847620010376,
|
|
"epoch": 3.3328530259365996,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003914508809663723,
|
|
"loss": 4.6334,
|
|
"mean_token_accuracy": 0.2556400462985039,
|
|
"num_tokens": 79548894.0,
|
|
"step": 34695
|
|
},
|
|
{
|
|
"entropy": 5.130915689468384,
|
|
"epoch": 3.3333333333333335,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039142154498513913,
|
|
"loss": 4.7501,
|
|
"mean_token_accuracy": 0.23812695294618608,
|
|
"num_tokens": 79560520.0,
|
|
"step": 34700
|
|
},
|
|
{
|
|
"entropy": 5.182145309448242,
|
|
"epoch": 3.3338136407300674,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039139220630094357,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.25095427632331846,
|
|
"num_tokens": 79571440.0,
|
|
"step": 34705
|
|
},
|
|
{
|
|
"entropy": 5.15102071762085,
|
|
"epoch": 3.3342939481268012,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00039136286491446657,
|
|
"loss": 4.7183,
|
|
"mean_token_accuracy": 0.24366225749254228,
|
|
"num_tokens": 79582046.0,
|
|
"step": 34710
|
|
},
|
|
{
|
|
"entropy": 5.134501886367798,
|
|
"epoch": 3.334774255523535,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039133352082638923,
|
|
"loss": 4.675,
|
|
"mean_token_accuracy": 0.2436215788125992,
|
|
"num_tokens": 79593704.0,
|
|
"step": 34715
|
|
},
|
|
{
|
|
"entropy": 5.162458848953247,
|
|
"epoch": 3.335254562920269,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00039130417403739315,
|
|
"loss": 4.7315,
|
|
"mean_token_accuracy": 0.24540108442306519,
|
|
"num_tokens": 79605783.0,
|
|
"step": 34720
|
|
},
|
|
{
|
|
"entropy": 5.144255542755127,
|
|
"epoch": 3.335734870317003,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003912748245481594,
|
|
"loss": 4.603,
|
|
"mean_token_accuracy": 0.25359062254428866,
|
|
"num_tokens": 79617140.0,
|
|
"step": 34725
|
|
},
|
|
{
|
|
"entropy": 5.16116509437561,
|
|
"epoch": 3.3362151777137368,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00039124547235936947,
|
|
"loss": 4.6675,
|
|
"mean_token_accuracy": 0.24451946020126342,
|
|
"num_tokens": 79627763.0,
|
|
"step": 34730
|
|
},
|
|
{
|
|
"entropy": 5.206093692779541,
|
|
"epoch": 3.3366954851104706,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039121611747170495,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.24296429753303528,
|
|
"num_tokens": 79640056.0,
|
|
"step": 34735
|
|
},
|
|
{
|
|
"entropy": 5.103566408157349,
|
|
"epoch": 3.3371757925072045,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039118675988584724,
|
|
"loss": 4.7262,
|
|
"mean_token_accuracy": 0.24336702823638917,
|
|
"num_tokens": 79652795.0,
|
|
"step": 34740
|
|
},
|
|
{
|
|
"entropy": 5.272174215316772,
|
|
"epoch": 3.3376560999039384,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003911573996024779,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.2363782599568367,
|
|
"num_tokens": 79663734.0,
|
|
"step": 34745
|
|
},
|
|
{
|
|
"entropy": 5.1654621124267575,
|
|
"epoch": 3.3381364073006723,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003911280366222787,
|
|
"loss": 4.6347,
|
|
"mean_token_accuracy": 0.25025320798158646,
|
|
"num_tokens": 79675092.0,
|
|
"step": 34750
|
|
},
|
|
{
|
|
"entropy": 5.169509172439575,
|
|
"epoch": 3.338616714697406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039109867094593134,
|
|
"loss": 4.7889,
|
|
"mean_token_accuracy": 0.23360417187213897,
|
|
"num_tokens": 79687126.0,
|
|
"step": 34755
|
|
},
|
|
{
|
|
"entropy": 5.082536077499389,
|
|
"epoch": 3.3390970220941405,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003910693025741175,
|
|
"loss": 4.6191,
|
|
"mean_token_accuracy": 0.2558431580662727,
|
|
"num_tokens": 79698511.0,
|
|
"step": 34760
|
|
},
|
|
{
|
|
"entropy": 5.1482446670532225,
|
|
"epoch": 3.339577329490874,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00039103993150751916,
|
|
"loss": 4.7055,
|
|
"mean_token_accuracy": 0.24975054413080217,
|
|
"num_tokens": 79709407.0,
|
|
"step": 34765
|
|
},
|
|
{
|
|
"entropy": 5.145913600921631,
|
|
"epoch": 3.3400576368876083,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039101055774681825,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.24959675669670106,
|
|
"num_tokens": 79720562.0,
|
|
"step": 34770
|
|
},
|
|
{
|
|
"entropy": 5.187802028656006,
|
|
"epoch": 3.340537944284342,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003909811812926966,
|
|
"loss": 4.764,
|
|
"mean_token_accuracy": 0.23684799671173096,
|
|
"num_tokens": 79731687.0,
|
|
"step": 34775
|
|
},
|
|
{
|
|
"entropy": 5.153404951095581,
|
|
"epoch": 3.341018251681076,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003909518021458363,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.24776209145784378,
|
|
"num_tokens": 79742954.0,
|
|
"step": 34780
|
|
},
|
|
{
|
|
"entropy": 5.1659314155578615,
|
|
"epoch": 3.34149855907781,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003909224203069195,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.2406251147389412,
|
|
"num_tokens": 79754233.0,
|
|
"step": 34785
|
|
},
|
|
{
|
|
"entropy": 5.1623436450958256,
|
|
"epoch": 3.341978866474544,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003908930357766283,
|
|
"loss": 4.6046,
|
|
"mean_token_accuracy": 0.25928680449724195,
|
|
"num_tokens": 79765348.0,
|
|
"step": 34790
|
|
},
|
|
{
|
|
"entropy": 5.133464097976685,
|
|
"epoch": 3.3424591738712777,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003908636485556449,
|
|
"loss": 4.6813,
|
|
"mean_token_accuracy": 0.24805527478456496,
|
|
"num_tokens": 79776993.0,
|
|
"step": 34795
|
|
},
|
|
{
|
|
"entropy": 5.219621467590332,
|
|
"epoch": 3.3429394812680115,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039083425864465165,
|
|
"loss": 4.8036,
|
|
"mean_token_accuracy": 0.24228421598672867,
|
|
"num_tokens": 79787321.0,
|
|
"step": 34800
|
|
},
|
|
{
|
|
"entropy": 5.1782149314880375,
|
|
"epoch": 3.3434197886647454,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003908048660443309,
|
|
"loss": 4.6706,
|
|
"mean_token_accuracy": 0.24523494839668275,
|
|
"num_tokens": 79798130.0,
|
|
"step": 34805
|
|
},
|
|
{
|
|
"entropy": 5.1322122573852536,
|
|
"epoch": 3.3439000960614793,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003907754707553651,
|
|
"loss": 4.6369,
|
|
"mean_token_accuracy": 0.24953514486551284,
|
|
"num_tokens": 79809616.0,
|
|
"step": 34810
|
|
},
|
|
{
|
|
"entropy": 5.065086030960083,
|
|
"epoch": 3.344380403458213,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003907460727784365,
|
|
"loss": 4.6571,
|
|
"mean_token_accuracy": 0.25056277513504027,
|
|
"num_tokens": 79820355.0,
|
|
"step": 34815
|
|
},
|
|
{
|
|
"entropy": 5.149088764190674,
|
|
"epoch": 3.344860710854947,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039071667211422787,
|
|
"loss": 4.6769,
|
|
"mean_token_accuracy": 0.24731635600328444,
|
|
"num_tokens": 79831733.0,
|
|
"step": 34820
|
|
},
|
|
{
|
|
"entropy": 5.163938570022583,
|
|
"epoch": 3.345341018251681,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003906872687634217,
|
|
"loss": 4.7323,
|
|
"mean_token_accuracy": 0.24109246134757994,
|
|
"num_tokens": 79842961.0,
|
|
"step": 34825
|
|
},
|
|
{
|
|
"entropy": 5.1637921810150145,
|
|
"epoch": 3.345821325648415,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039065786272670066,
|
|
"loss": 4.7321,
|
|
"mean_token_accuracy": 0.2495728015899658,
|
|
"num_tokens": 79855142.0,
|
|
"step": 34830
|
|
},
|
|
{
|
|
"entropy": 5.129210758209228,
|
|
"epoch": 3.3463016330451487,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003906284540047475,
|
|
"loss": 4.6393,
|
|
"mean_token_accuracy": 0.2503399342298508,
|
|
"num_tokens": 79865973.0,
|
|
"step": 34835
|
|
},
|
|
{
|
|
"entropy": 5.205915260314941,
|
|
"epoch": 3.3467819404418826,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039059904259824507,
|
|
"loss": 4.6938,
|
|
"mean_token_accuracy": 0.2478860929608345,
|
|
"num_tokens": 79877424.0,
|
|
"step": 34840
|
|
},
|
|
{
|
|
"entropy": 5.185302591323852,
|
|
"epoch": 3.347262247838617,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000390569628507876,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.2388562723994255,
|
|
"num_tokens": 79889956.0,
|
|
"step": 34845
|
|
},
|
|
{
|
|
"entropy": 5.123113918304443,
|
|
"epoch": 3.347742555235351,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00039054021173432336,
|
|
"loss": 4.6926,
|
|
"mean_token_accuracy": 0.25038100928068163,
|
|
"num_tokens": 79902454.0,
|
|
"step": 34850
|
|
},
|
|
{
|
|
"entropy": 5.178503322601318,
|
|
"epoch": 3.3482228626320847,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003905107922782701,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.2439994528889656,
|
|
"num_tokens": 79914425.0,
|
|
"step": 34855
|
|
},
|
|
{
|
|
"entropy": 5.103240919113159,
|
|
"epoch": 3.3487031700288186,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003904813701403993,
|
|
"loss": 4.634,
|
|
"mean_token_accuracy": 0.2546871855854988,
|
|
"num_tokens": 79926225.0,
|
|
"step": 34860
|
|
},
|
|
{
|
|
"entropy": 5.056886911392212,
|
|
"epoch": 3.3491834774255524,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039045194532139396,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.25428557246923444,
|
|
"num_tokens": 79937804.0,
|
|
"step": 34865
|
|
},
|
|
{
|
|
"entropy": 5.181491804122925,
|
|
"epoch": 3.3496637848222863,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003904225178219372,
|
|
"loss": 4.6962,
|
|
"mean_token_accuracy": 0.2482994332909584,
|
|
"num_tokens": 79949588.0,
|
|
"step": 34870
|
|
},
|
|
{
|
|
"entropy": 5.129343128204345,
|
|
"epoch": 3.35014409221902,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039039308764271237,
|
|
"loss": 4.6353,
|
|
"mean_token_accuracy": 0.24763429164886475,
|
|
"num_tokens": 79960243.0,
|
|
"step": 34875
|
|
},
|
|
{
|
|
"entropy": 5.0590348720550535,
|
|
"epoch": 3.350624399615754,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003903636547844026,
|
|
"loss": 4.6803,
|
|
"mean_token_accuracy": 0.24622277319431304,
|
|
"num_tokens": 79971780.0,
|
|
"step": 34880
|
|
},
|
|
{
|
|
"entropy": 5.132399797439575,
|
|
"epoch": 3.351104707012488,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00039033421924769145,
|
|
"loss": 4.7077,
|
|
"mean_token_accuracy": 0.2483307048678398,
|
|
"num_tokens": 79982105.0,
|
|
"step": 34885
|
|
},
|
|
{
|
|
"entropy": 5.120762872695923,
|
|
"epoch": 3.351585014409222,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039030478103326216,
|
|
"loss": 4.6373,
|
|
"mean_token_accuracy": 0.2583233952522278,
|
|
"num_tokens": 79993456.0,
|
|
"step": 34890
|
|
},
|
|
{
|
|
"entropy": 5.197812843322754,
|
|
"epoch": 3.3520653218059557,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039027534014179823,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.23972882181406022,
|
|
"num_tokens": 80006335.0,
|
|
"step": 34895
|
|
},
|
|
{
|
|
"entropy": 5.113822984695434,
|
|
"epoch": 3.3525456292026896,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003902458965739832,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.25016317516565323,
|
|
"num_tokens": 80017574.0,
|
|
"step": 34900
|
|
},
|
|
{
|
|
"entropy": 5.122508525848389,
|
|
"epoch": 3.3530259365994235,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003902164503305006,
|
|
"loss": 4.69,
|
|
"mean_token_accuracy": 0.2335006833076477,
|
|
"num_tokens": 80029470.0,
|
|
"step": 34905
|
|
},
|
|
{
|
|
"entropy": 5.1068902015686035,
|
|
"epoch": 3.3535062439961574,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0003901870014120343,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.2529321849346161,
|
|
"num_tokens": 80040599.0,
|
|
"step": 34910
|
|
},
|
|
{
|
|
"entropy": 5.194512987136841,
|
|
"epoch": 3.3539865513928913,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003901575498192678,
|
|
"loss": 4.6978,
|
|
"mean_token_accuracy": 0.24440195858478547,
|
|
"num_tokens": 80052597.0,
|
|
"step": 34915
|
|
},
|
|
{
|
|
"entropy": 5.161388969421386,
|
|
"epoch": 3.3544668587896256,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003901280955528849,
|
|
"loss": 4.7321,
|
|
"mean_token_accuracy": 0.24234699159860612,
|
|
"num_tokens": 80063208.0,
|
|
"step": 34920
|
|
},
|
|
{
|
|
"entropy": 5.121552467346191,
|
|
"epoch": 3.3549471661863595,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003900986386135695,
|
|
"loss": 4.7198,
|
|
"mean_token_accuracy": 0.24962664246559144,
|
|
"num_tokens": 80074046.0,
|
|
"step": 34925
|
|
},
|
|
{
|
|
"entropy": 5.1623291015625,
|
|
"epoch": 3.3554274735830933,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00039006917900200543,
|
|
"loss": 4.7564,
|
|
"mean_token_accuracy": 0.24298668056726455,
|
|
"num_tokens": 80086054.0,
|
|
"step": 34930
|
|
},
|
|
{
|
|
"entropy": 5.213542890548706,
|
|
"epoch": 3.3559077809798272,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039003971671887675,
|
|
"loss": 4.651,
|
|
"mean_token_accuracy": 0.2548714175820351,
|
|
"num_tokens": 80096030.0,
|
|
"step": 34935
|
|
},
|
|
{
|
|
"entropy": 5.023552751541137,
|
|
"epoch": 3.356388088376561,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003900102517648674,
|
|
"loss": 4.5242,
|
|
"mean_token_accuracy": 0.25738399028778075,
|
|
"num_tokens": 80106412.0,
|
|
"step": 34940
|
|
},
|
|
{
|
|
"entropy": 5.116913080215454,
|
|
"epoch": 3.356868395773295,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003899807841406617,
|
|
"loss": 4.7011,
|
|
"mean_token_accuracy": 0.25394404381513597,
|
|
"num_tokens": 80116580.0,
|
|
"step": 34945
|
|
},
|
|
{
|
|
"entropy": 5.169130134582519,
|
|
"epoch": 3.357348703170029,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003899513138469434,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.2435622915625572,
|
|
"num_tokens": 80129055.0,
|
|
"step": 34950
|
|
},
|
|
{
|
|
"entropy": 5.150484848022461,
|
|
"epoch": 3.3578290105667628,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000389921840884397,
|
|
"loss": 4.7669,
|
|
"mean_token_accuracy": 0.23531322181224823,
|
|
"num_tokens": 80140626.0,
|
|
"step": 34955
|
|
},
|
|
{
|
|
"entropy": 5.208211374282837,
|
|
"epoch": 3.3583093179634966,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00038989236525370676,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.24791100174188613,
|
|
"num_tokens": 80151896.0,
|
|
"step": 34960
|
|
},
|
|
{
|
|
"entropy": 5.188724327087402,
|
|
"epoch": 3.3587896253602305,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003898628869555569,
|
|
"loss": 4.6601,
|
|
"mean_token_accuracy": 0.2533836841583252,
|
|
"num_tokens": 80162801.0,
|
|
"step": 34965
|
|
},
|
|
{
|
|
"entropy": 5.168248081207276,
|
|
"epoch": 3.3592699327569644,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00038983340599063187,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.24546606540679933,
|
|
"num_tokens": 80174998.0,
|
|
"step": 34970
|
|
},
|
|
{
|
|
"entropy": 5.223715972900391,
|
|
"epoch": 3.3597502401536983,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003898039223596162,
|
|
"loss": 4.838,
|
|
"mean_token_accuracy": 0.23608224987983703,
|
|
"num_tokens": 80188092.0,
|
|
"step": 34975
|
|
},
|
|
{
|
|
"entropy": 5.203223800659179,
|
|
"epoch": 3.360230547550432,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003897744360631943,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.24822287410497665,
|
|
"num_tokens": 80199749.0,
|
|
"step": 34980
|
|
},
|
|
{
|
|
"entropy": 5.111070442199707,
|
|
"epoch": 3.360710854947166,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038974494710205084,
|
|
"loss": 4.6525,
|
|
"mean_token_accuracy": 0.25020434260368346,
|
|
"num_tokens": 80211714.0,
|
|
"step": 34985
|
|
},
|
|
{
|
|
"entropy": 5.126537227630616,
|
|
"epoch": 3.3611911623439,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038971545547687036,
|
|
"loss": 4.6902,
|
|
"mean_token_accuracy": 0.2508800521492958,
|
|
"num_tokens": 80222258.0,
|
|
"step": 34990
|
|
},
|
|
{
|
|
"entropy": 5.056414079666138,
|
|
"epoch": 3.3616714697406342,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038968596118833766,
|
|
"loss": 4.6606,
|
|
"mean_token_accuracy": 0.25123048573732376,
|
|
"num_tokens": 80234532.0,
|
|
"step": 34995
|
|
},
|
|
{
|
|
"entropy": 5.132634258270263,
|
|
"epoch": 3.3621517771373677,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038965646423713744,
|
|
"loss": 4.6254,
|
|
"mean_token_accuracy": 0.24775761216878892,
|
|
"num_tokens": 80245826.0,
|
|
"step": 35000
|
|
},
|
|
{
|
|
"entropy": 5.137397956848145,
|
|
"epoch": 3.362632084534102,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00038962696462395473,
|
|
"loss": 4.5988,
|
|
"mean_token_accuracy": 0.2506577342748642,
|
|
"num_tokens": 80256715.0,
|
|
"step": 35005
|
|
},
|
|
{
|
|
"entropy": 5.154143524169922,
|
|
"epoch": 3.363112391930836,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003895974623494742,
|
|
"loss": 4.7166,
|
|
"mean_token_accuracy": 0.24861787408590316,
|
|
"num_tokens": 80267713.0,
|
|
"step": 35010
|
|
},
|
|
{
|
|
"entropy": 5.11757001876831,
|
|
"epoch": 3.3635926993275698,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038956795741438085,
|
|
"loss": 4.7227,
|
|
"mean_token_accuracy": 0.24641240686178206,
|
|
"num_tokens": 80278935.0,
|
|
"step": 35015
|
|
},
|
|
{
|
|
"entropy": 5.07843770980835,
|
|
"epoch": 3.3640730067243036,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00038953844981935975,
|
|
"loss": 4.5793,
|
|
"mean_token_accuracy": 0.259165121614933,
|
|
"num_tokens": 80289735.0,
|
|
"step": 35020
|
|
},
|
|
{
|
|
"entropy": 5.1762806415557865,
|
|
"epoch": 3.3645533141210375,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00038950893956509597,
|
|
"loss": 4.7583,
|
|
"mean_token_accuracy": 0.247892302274704,
|
|
"num_tokens": 80301617.0,
|
|
"step": 35025
|
|
},
|
|
{
|
|
"entropy": 5.104067087173462,
|
|
"epoch": 3.3650336215177714,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003894794266522746,
|
|
"loss": 4.5718,
|
|
"mean_token_accuracy": 0.2600106105208397,
|
|
"num_tokens": 80312996.0,
|
|
"step": 35030
|
|
},
|
|
{
|
|
"entropy": 5.130551290512085,
|
|
"epoch": 3.3655139289145053,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038944991108158094,
|
|
"loss": 4.6401,
|
|
"mean_token_accuracy": 0.24545565694570542,
|
|
"num_tokens": 80324435.0,
|
|
"step": 35035
|
|
},
|
|
{
|
|
"entropy": 5.091349315643311,
|
|
"epoch": 3.365994236311239,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003894203928537001,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.24843578934669494,
|
|
"num_tokens": 80335922.0,
|
|
"step": 35040
|
|
},
|
|
{
|
|
"entropy": 5.151780319213867,
|
|
"epoch": 3.366474543707973,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00038939087196931754,
|
|
"loss": 4.7119,
|
|
"mean_token_accuracy": 0.24881794303655624,
|
|
"num_tokens": 80348405.0,
|
|
"step": 35045
|
|
},
|
|
{
|
|
"entropy": 5.168756341934204,
|
|
"epoch": 3.366954851104707,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00038936134842911863,
|
|
"loss": 4.6724,
|
|
"mean_token_accuracy": 0.25083217918872835,
|
|
"num_tokens": 80361387.0,
|
|
"step": 35050
|
|
},
|
|
{
|
|
"entropy": 5.124174737930298,
|
|
"epoch": 3.367435158501441,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003893318222337888,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.24898438155651093,
|
|
"num_tokens": 80372500.0,
|
|
"step": 35055
|
|
},
|
|
{
|
|
"entropy": 5.219282484054565,
|
|
"epoch": 3.3679154658981747,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00038930229338401354,
|
|
"loss": 4.7883,
|
|
"mean_token_accuracy": 0.24008482992649077,
|
|
"num_tokens": 80384311.0,
|
|
"step": 35060
|
|
},
|
|
{
|
|
"entropy": 5.1323765277862545,
|
|
"epoch": 3.3683957732949086,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003892727618804783,
|
|
"loss": 4.6691,
|
|
"mean_token_accuracy": 0.24760151654481888,
|
|
"num_tokens": 80396259.0,
|
|
"step": 35065
|
|
},
|
|
{
|
|
"entropy": 5.113740253448486,
|
|
"epoch": 3.3688760806916425,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000389243227723869,
|
|
"loss": 4.681,
|
|
"mean_token_accuracy": 0.243132546544075,
|
|
"num_tokens": 80407420.0,
|
|
"step": 35070
|
|
},
|
|
{
|
|
"entropy": 5.126459312438965,
|
|
"epoch": 3.3693563880883763,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003892136909148711,
|
|
"loss": 4.6297,
|
|
"mean_token_accuracy": 0.24747464656829835,
|
|
"num_tokens": 80417130.0,
|
|
"step": 35075
|
|
},
|
|
{
|
|
"entropy": 5.162316989898682,
|
|
"epoch": 3.3698366954851107,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003891841514541706,
|
|
"loss": 4.6937,
|
|
"mean_token_accuracy": 0.24861887991428375,
|
|
"num_tokens": 80429405.0,
|
|
"step": 35080
|
|
},
|
|
{
|
|
"entropy": 5.1466306209564205,
|
|
"epoch": 3.3703170028818445,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000389154609342453,
|
|
"loss": 4.681,
|
|
"mean_token_accuracy": 0.24463891685009004,
|
|
"num_tokens": 80439895.0,
|
|
"step": 35085
|
|
},
|
|
{
|
|
"entropy": 5.0603128433227536,
|
|
"epoch": 3.3707973102785784,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003891250645804044,
|
|
"loss": 4.6431,
|
|
"mean_token_accuracy": 0.25427021384239196,
|
|
"num_tokens": 80451884.0,
|
|
"step": 35090
|
|
},
|
|
{
|
|
"entropy": 5.158304834365845,
|
|
"epoch": 3.3712776176753123,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038909551716871074,
|
|
"loss": 4.6941,
|
|
"mean_token_accuracy": 0.2508618369698524,
|
|
"num_tokens": 80462629.0,
|
|
"step": 35095
|
|
},
|
|
{
|
|
"entropy": 5.210780096054077,
|
|
"epoch": 3.371757925072046,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003890659671080579,
|
|
"loss": 4.7157,
|
|
"mean_token_accuracy": 0.2425542116165161,
|
|
"num_tokens": 80472066.0,
|
|
"step": 35100
|
|
},
|
|
{
|
|
"entropy": 5.151716089248657,
|
|
"epoch": 3.37223823246878,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000389036414399132,
|
|
"loss": 4.6398,
|
|
"mean_token_accuracy": 0.24997950792312623,
|
|
"num_tokens": 80483687.0,
|
|
"step": 35105
|
|
},
|
|
{
|
|
"entropy": 5.127964162826538,
|
|
"epoch": 3.372718539865514,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003890068590426191,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.24726386070251466,
|
|
"num_tokens": 80493323.0,
|
|
"step": 35110
|
|
},
|
|
{
|
|
"entropy": 5.127128028869629,
|
|
"epoch": 3.373198847262248,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003889773010392056,
|
|
"loss": 4.6937,
|
|
"mean_token_accuracy": 0.2513361766934395,
|
|
"num_tokens": 80504454.0,
|
|
"step": 35115
|
|
},
|
|
{
|
|
"entropy": 5.0981358051300045,
|
|
"epoch": 3.3736791546589817,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038894774038957756,
|
|
"loss": 4.6039,
|
|
"mean_token_accuracy": 0.25642564445734023,
|
|
"num_tokens": 80516201.0,
|
|
"step": 35120
|
|
},
|
|
{
|
|
"entropy": 5.092295455932617,
|
|
"epoch": 3.3741594620557156,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038891817709442135,
|
|
"loss": 4.6978,
|
|
"mean_token_accuracy": 0.24694399833679198,
|
|
"num_tokens": 80528319.0,
|
|
"step": 35125
|
|
},
|
|
{
|
|
"entropy": 5.102270030975342,
|
|
"epoch": 3.3746397694524495,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00038888861115442334,
|
|
"loss": 4.6313,
|
|
"mean_token_accuracy": 0.25585228502750396,
|
|
"num_tokens": 80539684.0,
|
|
"step": 35130
|
|
},
|
|
{
|
|
"entropy": 5.123061943054199,
|
|
"epoch": 3.3751200768491834,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003888590425702699,
|
|
"loss": 4.6544,
|
|
"mean_token_accuracy": 0.2553621008992195,
|
|
"num_tokens": 80550971.0,
|
|
"step": 35135
|
|
},
|
|
{
|
|
"entropy": 5.101758718490601,
|
|
"epoch": 3.3756003842459172,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003888294713426477,
|
|
"loss": 4.6594,
|
|
"mean_token_accuracy": 0.2500421941280365,
|
|
"num_tokens": 80562931.0,
|
|
"step": 35140
|
|
},
|
|
{
|
|
"entropy": 5.074270343780517,
|
|
"epoch": 3.376080691642651,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00038879989747224317,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.25843396335840224,
|
|
"num_tokens": 80573899.0,
|
|
"step": 35145
|
|
},
|
|
{
|
|
"entropy": 5.115423250198364,
|
|
"epoch": 3.376560999039385,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003887703209597428,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.24635871052742003,
|
|
"num_tokens": 80585453.0,
|
|
"step": 35150
|
|
},
|
|
{
|
|
"entropy": 5.126647853851319,
|
|
"epoch": 3.3770413064361193,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003887407418058335,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.246426784992218,
|
|
"num_tokens": 80597911.0,
|
|
"step": 35155
|
|
},
|
|
{
|
|
"entropy": 5.153801202774048,
|
|
"epoch": 3.377521613832853,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00038871116001120196,
|
|
"loss": 4.6679,
|
|
"mean_token_accuracy": 0.2472786381840706,
|
|
"num_tokens": 80609350.0,
|
|
"step": 35160
|
|
},
|
|
{
|
|
"entropy": 5.1478019714355465,
|
|
"epoch": 3.378001921229587,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0003886815755765348,
|
|
"loss": 4.7351,
|
|
"mean_token_accuracy": 0.24264449030160903,
|
|
"num_tokens": 80620710.0,
|
|
"step": 35165
|
|
},
|
|
{
|
|
"entropy": 5.175410318374634,
|
|
"epoch": 3.378482228626321,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003886519885025191,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.23941567540168762,
|
|
"num_tokens": 80633031.0,
|
|
"step": 35170
|
|
},
|
|
{
|
|
"entropy": 5.070417404174805,
|
|
"epoch": 3.378962536023055,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00038862239878984173,
|
|
"loss": 4.606,
|
|
"mean_token_accuracy": 0.25849782675504684,
|
|
"num_tokens": 80644047.0,
|
|
"step": 35175
|
|
},
|
|
{
|
|
"entropy": 5.113453149795532,
|
|
"epoch": 3.3794428434197887,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003885928064391897,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.24677301794290543,
|
|
"num_tokens": 80655769.0,
|
|
"step": 35180
|
|
},
|
|
{
|
|
"entropy": 5.177928924560547,
|
|
"epoch": 3.3799231508165226,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003885632114512499,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.24463046044111253,
|
|
"num_tokens": 80667881.0,
|
|
"step": 35185
|
|
},
|
|
{
|
|
"entropy": 5.200576210021973,
|
|
"epoch": 3.3804034582132565,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00038853361382670956,
|
|
"loss": 4.7614,
|
|
"mean_token_accuracy": 0.24534510374069213,
|
|
"num_tokens": 80679021.0,
|
|
"step": 35190
|
|
},
|
|
{
|
|
"entropy": 5.127397298812866,
|
|
"epoch": 3.3808837656099904,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00038850401356625583,
|
|
"loss": 4.6903,
|
|
"mean_token_accuracy": 0.2495172217488289,
|
|
"num_tokens": 80689366.0,
|
|
"step": 35195
|
|
},
|
|
{
|
|
"entropy": 5.049978017807007,
|
|
"epoch": 3.3813640730067243,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003884744106705759,
|
|
"loss": 4.6122,
|
|
"mean_token_accuracy": 0.2475672706961632,
|
|
"num_tokens": 80700755.0,
|
|
"step": 35200
|
|
},
|
|
{
|
|
"entropy": 5.167662715911865,
|
|
"epoch": 3.381844380403458,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038844480514035727,
|
|
"loss": 4.6782,
|
|
"mean_token_accuracy": 0.24898096024990082,
|
|
"num_tokens": 80712186.0,
|
|
"step": 35205
|
|
},
|
|
{
|
|
"entropy": 5.091697549819946,
|
|
"epoch": 3.382324687800192,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000388415196976287,
|
|
"loss": 4.6641,
|
|
"mean_token_accuracy": 0.2552251577377319,
|
|
"num_tokens": 80723865.0,
|
|
"step": 35210
|
|
},
|
|
{
|
|
"entropy": 5.127259922027588,
|
|
"epoch": 3.382804995196926,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003883855861790526,
|
|
"loss": 4.6932,
|
|
"mean_token_accuracy": 0.24685215204954147,
|
|
"num_tokens": 80735817.0,
|
|
"step": 35215
|
|
},
|
|
{
|
|
"entropy": 5.136834192276001,
|
|
"epoch": 3.38328530259366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003883559727493417,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.2443356215953827,
|
|
"num_tokens": 80747782.0,
|
|
"step": 35220
|
|
},
|
|
{
|
|
"entropy": 5.150741958618164,
|
|
"epoch": 3.3837656099903937,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003883263566878416,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.23866078108549119,
|
|
"num_tokens": 80759119.0,
|
|
"step": 35225
|
|
},
|
|
{
|
|
"entropy": 5.113545083999634,
|
|
"epoch": 3.384245917387128,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038829673799524006,
|
|
"loss": 4.6269,
|
|
"mean_token_accuracy": 0.2549636036157608,
|
|
"num_tokens": 80769792.0,
|
|
"step": 35230
|
|
},
|
|
{
|
|
"entropy": 5.073078155517578,
|
|
"epoch": 3.3847262247838614,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00038826711667222464,
|
|
"loss": 4.6278,
|
|
"mean_token_accuracy": 0.2526594415307045,
|
|
"num_tokens": 80781685.0,
|
|
"step": 35235
|
|
},
|
|
{
|
|
"entropy": 5.069280099868775,
|
|
"epoch": 3.3852065321805958,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038823749271948315,
|
|
"loss": 4.5778,
|
|
"mean_token_accuracy": 0.25985963493585584,
|
|
"num_tokens": 80792499.0,
|
|
"step": 35240
|
|
},
|
|
{
|
|
"entropy": 5.161238384246826,
|
|
"epoch": 3.3856868395773296,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038820786613770334,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.2534036457538605,
|
|
"num_tokens": 80803020.0,
|
|
"step": 35245
|
|
},
|
|
{
|
|
"entropy": 5.161848354339599,
|
|
"epoch": 3.3861671469740635,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038817823692757303,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.2532574951648712,
|
|
"num_tokens": 80814543.0,
|
|
"step": 35250
|
|
},
|
|
{
|
|
"entropy": 5.0607775211334225,
|
|
"epoch": 3.3866474543707974,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00038814860508978004,
|
|
"loss": 4.6239,
|
|
"mean_token_accuracy": 0.25939627140760424,
|
|
"num_tokens": 80826686.0,
|
|
"step": 35255
|
|
},
|
|
{
|
|
"entropy": 5.13223443031311,
|
|
"epoch": 3.3871277617675313,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003881189706250125,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.2391115605831146,
|
|
"num_tokens": 80838372.0,
|
|
"step": 35260
|
|
},
|
|
{
|
|
"entropy": 5.199919939041138,
|
|
"epoch": 3.387608069164265,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038808933353395836,
|
|
"loss": 4.7011,
|
|
"mean_token_accuracy": 0.24523348957300187,
|
|
"num_tokens": 80849334.0,
|
|
"step": 35265
|
|
},
|
|
{
|
|
"entropy": 5.074152278900146,
|
|
"epoch": 3.388088376560999,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038805969381730564,
|
|
"loss": 4.559,
|
|
"mean_token_accuracy": 0.2511142551898956,
|
|
"num_tokens": 80860682.0,
|
|
"step": 35270
|
|
},
|
|
{
|
|
"entropy": 5.147882652282715,
|
|
"epoch": 3.388568683957733,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038803005147574265,
|
|
"loss": 4.7186,
|
|
"mean_token_accuracy": 0.2461581975221634,
|
|
"num_tokens": 80872026.0,
|
|
"step": 35275
|
|
},
|
|
{
|
|
"entropy": 5.167284727096558,
|
|
"epoch": 3.389048991354467,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003880004065099575,
|
|
"loss": 4.7265,
|
|
"mean_token_accuracy": 0.24173777401447297,
|
|
"num_tokens": 80884146.0,
|
|
"step": 35280
|
|
},
|
|
{
|
|
"entropy": 5.140678453445434,
|
|
"epoch": 3.3895292987512007,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003879707589206383,
|
|
"loss": 4.6871,
|
|
"mean_token_accuracy": 0.24983020424842833,
|
|
"num_tokens": 80895975.0,
|
|
"step": 35285
|
|
},
|
|
{
|
|
"entropy": 5.217415428161621,
|
|
"epoch": 3.3900096061479346,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003879411087084736,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.24357006698846817,
|
|
"num_tokens": 80908144.0,
|
|
"step": 35290
|
|
},
|
|
{
|
|
"entropy": 5.124963998794556,
|
|
"epoch": 3.3904899135446684,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00038791145587415186,
|
|
"loss": 4.6718,
|
|
"mean_token_accuracy": 0.24821458458900453,
|
|
"num_tokens": 80918616.0,
|
|
"step": 35295
|
|
},
|
|
{
|
|
"entropy": 5.182640838623047,
|
|
"epoch": 3.3909702209414023,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00038788180041836117,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.24079196900129318,
|
|
"num_tokens": 80929690.0,
|
|
"step": 35300
|
|
},
|
|
{
|
|
"entropy": 5.166576719284057,
|
|
"epoch": 3.3914505283381366,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038785214234179037,
|
|
"loss": 4.6507,
|
|
"mean_token_accuracy": 0.2513709306716919,
|
|
"num_tokens": 80940817.0,
|
|
"step": 35305
|
|
},
|
|
{
|
|
"entropy": 5.168484735488891,
|
|
"epoch": 3.39193083573487,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038782248164512804,
|
|
"loss": 4.6472,
|
|
"mean_token_accuracy": 0.25147325098514556,
|
|
"num_tokens": 80950951.0,
|
|
"step": 35310
|
|
},
|
|
{
|
|
"entropy": 5.126372671127319,
|
|
"epoch": 3.3924111431316044,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038779281832906253,
|
|
"loss": 4.672,
|
|
"mean_token_accuracy": 0.25064203441143035,
|
|
"num_tokens": 80963511.0,
|
|
"step": 35315
|
|
},
|
|
{
|
|
"entropy": 5.216497707366943,
|
|
"epoch": 3.3928914505283383,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038776315239428275,
|
|
"loss": 4.7784,
|
|
"mean_token_accuracy": 0.2440475419163704,
|
|
"num_tokens": 80975905.0,
|
|
"step": 35320
|
|
},
|
|
{
|
|
"entropy": 5.17739200592041,
|
|
"epoch": 3.393371757925072,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00038773348384147743,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.24598495215177535,
|
|
"num_tokens": 80986850.0,
|
|
"step": 35325
|
|
},
|
|
{
|
|
"entropy": 5.018025875091553,
|
|
"epoch": 3.393852065321806,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003877038126713354,
|
|
"loss": 4.5721,
|
|
"mean_token_accuracy": 0.26067920923233034,
|
|
"num_tokens": 80998190.0,
|
|
"step": 35330
|
|
},
|
|
{
|
|
"entropy": 5.100456190109253,
|
|
"epoch": 3.39433237271854,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038767413888454537,
|
|
"loss": 4.6525,
|
|
"mean_token_accuracy": 0.2423853322863579,
|
|
"num_tokens": 81011086.0,
|
|
"step": 35335
|
|
},
|
|
{
|
|
"entropy": 5.277721500396728,
|
|
"epoch": 3.394812680115274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00038764446248179665,
|
|
"loss": 4.7571,
|
|
"mean_token_accuracy": 0.24489331394433975,
|
|
"num_tokens": 81022074.0,
|
|
"step": 35340
|
|
},
|
|
{
|
|
"entropy": 5.142676639556885,
|
|
"epoch": 3.3952929875120077,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003876147834637778,
|
|
"loss": 4.6666,
|
|
"mean_token_accuracy": 0.24484491348266602,
|
|
"num_tokens": 81033019.0,
|
|
"step": 35345
|
|
},
|
|
{
|
|
"entropy": 5.180561304092407,
|
|
"epoch": 3.3957732949087416,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038758510183117806,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.24068786054849625,
|
|
"num_tokens": 81044955.0,
|
|
"step": 35350
|
|
},
|
|
{
|
|
"entropy": 5.132597398757935,
|
|
"epoch": 3.3962536023054755,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003875554175846866,
|
|
"loss": 4.5784,
|
|
"mean_token_accuracy": 0.2612167030572891,
|
|
"num_tokens": 81055980.0,
|
|
"step": 35355
|
|
},
|
|
{
|
|
"entropy": 5.10514988899231,
|
|
"epoch": 3.3967339097022093,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00038752573072499267,
|
|
"loss": 4.6213,
|
|
"mean_token_accuracy": 0.2557134672999382,
|
|
"num_tokens": 81067960.0,
|
|
"step": 35360
|
|
},
|
|
{
|
|
"entropy": 5.165594530105591,
|
|
"epoch": 3.3972142170989432,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00038749604125278524,
|
|
"loss": 4.7193,
|
|
"mean_token_accuracy": 0.24775321036577225,
|
|
"num_tokens": 81078084.0,
|
|
"step": 35365
|
|
},
|
|
{
|
|
"entropy": 5.143951845169068,
|
|
"epoch": 3.397694524495677,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003874663491687539,
|
|
"loss": 4.6478,
|
|
"mean_token_accuracy": 0.24895476251840593,
|
|
"num_tokens": 81089376.0,
|
|
"step": 35370
|
|
},
|
|
{
|
|
"entropy": 5.165175676345825,
|
|
"epoch": 3.398174831892411,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00038743665447358785,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.2450385197997093,
|
|
"num_tokens": 81100906.0,
|
|
"step": 35375
|
|
},
|
|
{
|
|
"entropy": 5.1963742733001705,
|
|
"epoch": 3.398655139289145,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003874069571679766,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.24903709143400193,
|
|
"num_tokens": 81112839.0,
|
|
"step": 35380
|
|
},
|
|
{
|
|
"entropy": 5.081039619445801,
|
|
"epoch": 3.3991354466858787,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00038737725725260946,
|
|
"loss": 4.6347,
|
|
"mean_token_accuracy": 0.25012271404266356,
|
|
"num_tokens": 81126015.0,
|
|
"step": 35385
|
|
},
|
|
{
|
|
"entropy": 5.163181209564209,
|
|
"epoch": 3.399615754082613,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00038734755472817617,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.24159933179616927,
|
|
"num_tokens": 81139526.0,
|
|
"step": 35390
|
|
},
|
|
{
|
|
"entropy": 5.141846227645874,
|
|
"epoch": 3.400096061479347,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038731784959536626,
|
|
"loss": 4.6121,
|
|
"mean_token_accuracy": 0.25474112182855607,
|
|
"num_tokens": 81152340.0,
|
|
"step": 35395
|
|
},
|
|
{
|
|
"entropy": 5.241625118255615,
|
|
"epoch": 3.400576368876081,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00038728814185486944,
|
|
"loss": 4.7219,
|
|
"mean_token_accuracy": 0.23892828971147537,
|
|
"num_tokens": 81162724.0,
|
|
"step": 35400
|
|
},
|
|
{
|
|
"entropy": 5.15989842414856,
|
|
"epoch": 3.4010566762728147,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003872584315073753,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.2467575803399086,
|
|
"num_tokens": 81172933.0,
|
|
"step": 35405
|
|
},
|
|
{
|
|
"entropy": 5.105989074707031,
|
|
"epoch": 3.4015369836695486,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003872287185535738,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.24493507146835328,
|
|
"num_tokens": 81183774.0,
|
|
"step": 35410
|
|
},
|
|
{
|
|
"entropy": 5.035782814025879,
|
|
"epoch": 3.4020172910662825,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00038719900299415475,
|
|
"loss": 4.5367,
|
|
"mean_token_accuracy": 0.26555697470903394,
|
|
"num_tokens": 81194896.0,
|
|
"step": 35415
|
|
},
|
|
{
|
|
"entropy": 5.136112642288208,
|
|
"epoch": 3.4024975984630164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003871692848298079,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.2478817269206047,
|
|
"num_tokens": 81204889.0,
|
|
"step": 35420
|
|
},
|
|
{
|
|
"entropy": 5.170907926559448,
|
|
"epoch": 3.4029779058597502,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038713956406122334,
|
|
"loss": 4.7336,
|
|
"mean_token_accuracy": 0.24206767082214356,
|
|
"num_tokens": 81217177.0,
|
|
"step": 35425
|
|
},
|
|
{
|
|
"entropy": 5.172530555725098,
|
|
"epoch": 3.403458213256484,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00038710984068909116,
|
|
"loss": 4.7539,
|
|
"mean_token_accuracy": 0.24184914380311967,
|
|
"num_tokens": 81228767.0,
|
|
"step": 35430
|
|
},
|
|
{
|
|
"entropy": 5.113364171981812,
|
|
"epoch": 3.403938520653218,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003870801147141014,
|
|
"loss": 4.6254,
|
|
"mean_token_accuracy": 0.24375834167003632,
|
|
"num_tokens": 81239599.0,
|
|
"step": 35435
|
|
},
|
|
{
|
|
"entropy": 5.137655639648438,
|
|
"epoch": 3.404418828049952,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003870503861369441,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.25035239160060885,
|
|
"num_tokens": 81251051.0,
|
|
"step": 35440
|
|
},
|
|
{
|
|
"entropy": 5.158294582366944,
|
|
"epoch": 3.4048991354466858,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038702065495830956,
|
|
"loss": 4.751,
|
|
"mean_token_accuracy": 0.24702732712030412,
|
|
"num_tokens": 81262484.0,
|
|
"step": 35445
|
|
},
|
|
{
|
|
"entropy": 5.103233814239502,
|
|
"epoch": 3.4053794428434196,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003869909211788881,
|
|
"loss": 4.6365,
|
|
"mean_token_accuracy": 0.2557443007826805,
|
|
"num_tokens": 81273068.0,
|
|
"step": 35450
|
|
},
|
|
{
|
|
"entropy": 5.146712160110473,
|
|
"epoch": 3.4058597502401535,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038696118479936994,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.24362991899251937,
|
|
"num_tokens": 81285239.0,
|
|
"step": 35455
|
|
},
|
|
{
|
|
"entropy": 5.1828028678894045,
|
|
"epoch": 3.4063400576368874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038693144582044553,
|
|
"loss": 4.7059,
|
|
"mean_token_accuracy": 0.2429921641945839,
|
|
"num_tokens": 81295998.0,
|
|
"step": 35460
|
|
},
|
|
{
|
|
"entropy": 5.093336391448974,
|
|
"epoch": 3.4068203650336217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038690170424280534,
|
|
"loss": 4.603,
|
|
"mean_token_accuracy": 0.2526893958449364,
|
|
"num_tokens": 81307569.0,
|
|
"step": 35465
|
|
},
|
|
{
|
|
"entropy": 5.1020745754241945,
|
|
"epoch": 3.4073006724303556,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003868719600671399,
|
|
"loss": 4.6385,
|
|
"mean_token_accuracy": 0.2447736993432045,
|
|
"num_tokens": 81319023.0,
|
|
"step": 35470
|
|
},
|
|
{
|
|
"entropy": 5.024361801147461,
|
|
"epoch": 3.4077809798270895,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00038684221329413965,
|
|
"loss": 4.6195,
|
|
"mean_token_accuracy": 0.25101048946380616,
|
|
"num_tokens": 81330087.0,
|
|
"step": 35475
|
|
},
|
|
{
|
|
"entropy": 5.078883075714112,
|
|
"epoch": 3.4082612872238234,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003868124639244954,
|
|
"loss": 4.5721,
|
|
"mean_token_accuracy": 0.2604044139385223,
|
|
"num_tokens": 81341533.0,
|
|
"step": 35480
|
|
},
|
|
{
|
|
"entropy": 5.1673659324646,
|
|
"epoch": 3.4087415946205573,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038678271195889766,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.23330889642238617,
|
|
"num_tokens": 81353505.0,
|
|
"step": 35485
|
|
},
|
|
{
|
|
"entropy": 5.157960653305054,
|
|
"epoch": 3.409221902017291,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00038675295739803734,
|
|
"loss": 4.6907,
|
|
"mean_token_accuracy": 0.2495548591017723,
|
|
"num_tokens": 81365246.0,
|
|
"step": 35490
|
|
},
|
|
{
|
|
"entropy": 5.256409215927124,
|
|
"epoch": 3.409702209414025,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038672320024260516,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.23977768421173096,
|
|
"num_tokens": 81376403.0,
|
|
"step": 35495
|
|
},
|
|
{
|
|
"entropy": 5.143632221221924,
|
|
"epoch": 3.410182516810759,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00038669344049329204,
|
|
"loss": 4.6753,
|
|
"mean_token_accuracy": 0.24669647067785264,
|
|
"num_tokens": 81386865.0,
|
|
"step": 35500
|
|
},
|
|
{
|
|
"entropy": 5.02146897315979,
|
|
"epoch": 3.410662824207493,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00038666367815078887,
|
|
"loss": 4.6327,
|
|
"mean_token_accuracy": 0.2553836330771446,
|
|
"num_tokens": 81398191.0,
|
|
"step": 35505
|
|
},
|
|
{
|
|
"entropy": 5.147927761077881,
|
|
"epoch": 3.4111431316042267,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003866339132157867,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.2447207272052765,
|
|
"num_tokens": 81410694.0,
|
|
"step": 35510
|
|
},
|
|
{
|
|
"entropy": 5.140965461730957,
|
|
"epoch": 3.4116234390009605,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003866041456889764,
|
|
"loss": 4.6378,
|
|
"mean_token_accuracy": 0.25023227781057356,
|
|
"num_tokens": 81422195.0,
|
|
"step": 35515
|
|
},
|
|
{
|
|
"entropy": 5.109976148605346,
|
|
"epoch": 3.4121037463976944,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00038657437557104946,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.2501557856798172,
|
|
"num_tokens": 81432979.0,
|
|
"step": 35520
|
|
},
|
|
{
|
|
"entropy": 5.1021181583404545,
|
|
"epoch": 3.4125840537944283,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003865446028626967,
|
|
"loss": 4.6162,
|
|
"mean_token_accuracy": 0.25312971472740176,
|
|
"num_tokens": 81444328.0,
|
|
"step": 35525
|
|
},
|
|
{
|
|
"entropy": 5.237941026687622,
|
|
"epoch": 3.413064361191162,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038651482756460947,
|
|
"loss": 4.8869,
|
|
"mean_token_accuracy": 0.23744845390319824,
|
|
"num_tokens": 81455530.0,
|
|
"step": 35530
|
|
},
|
|
{
|
|
"entropy": 5.1280982971191404,
|
|
"epoch": 3.413544668587896,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038648504967747914,
|
|
"loss": 4.6571,
|
|
"mean_token_accuracy": 0.2546304062008858,
|
|
"num_tokens": 81466462.0,
|
|
"step": 35535
|
|
},
|
|
{
|
|
"entropy": 5.2058000564575195,
|
|
"epoch": 3.4140249759846304,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00038645526920199697,
|
|
"loss": 4.7723,
|
|
"mean_token_accuracy": 0.23904553651809693,
|
|
"num_tokens": 81479459.0,
|
|
"step": 35540
|
|
},
|
|
{
|
|
"entropy": 5.187608146667481,
|
|
"epoch": 3.414505283381364,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003864254861388544,
|
|
"loss": 4.8016,
|
|
"mean_token_accuracy": 0.24473185539245607,
|
|
"num_tokens": 81491026.0,
|
|
"step": 35545
|
|
},
|
|
{
|
|
"entropy": 5.194537591934204,
|
|
"epoch": 3.414985590778098,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00038639570048874295,
|
|
"loss": 4.6895,
|
|
"mean_token_accuracy": 0.2479396104812622,
|
|
"num_tokens": 81504469.0,
|
|
"step": 35550
|
|
},
|
|
{
|
|
"entropy": 5.109788656234741,
|
|
"epoch": 3.415465898174832,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038636591225235407,
|
|
"loss": 4.6213,
|
|
"mean_token_accuracy": 0.2499052479863167,
|
|
"num_tokens": 81515873.0,
|
|
"step": 35555
|
|
},
|
|
{
|
|
"entropy": 5.083378648757934,
|
|
"epoch": 3.415946205571566,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0003863361214303794,
|
|
"loss": 4.6551,
|
|
"mean_token_accuracy": 0.2487245559692383,
|
|
"num_tokens": 81528169.0,
|
|
"step": 35560
|
|
},
|
|
{
|
|
"entropy": 5.147656774520874,
|
|
"epoch": 3.4164265129683,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003863063280235106,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.24471379816532135,
|
|
"num_tokens": 81538831.0,
|
|
"step": 35565
|
|
},
|
|
{
|
|
"entropy": 5.205832624435425,
|
|
"epoch": 3.4169068203650337,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00038627653203243933,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.23526614755392075,
|
|
"num_tokens": 81549809.0,
|
|
"step": 35570
|
|
},
|
|
{
|
|
"entropy": 5.065957117080688,
|
|
"epoch": 3.4173871277617676,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003862467334578574,
|
|
"loss": 4.5932,
|
|
"mean_token_accuracy": 0.253609137237072,
|
|
"num_tokens": 81560537.0,
|
|
"step": 35575
|
|
},
|
|
{
|
|
"entropy": 5.10381007194519,
|
|
"epoch": 3.4178674351585014,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038621693230045677,
|
|
"loss": 4.6512,
|
|
"mean_token_accuracy": 0.2517675831913948,
|
|
"num_tokens": 81571983.0,
|
|
"step": 35580
|
|
},
|
|
{
|
|
"entropy": 5.066199779510498,
|
|
"epoch": 3.4183477425552353,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003861871285609291,
|
|
"loss": 4.6143,
|
|
"mean_token_accuracy": 0.24984218925237656,
|
|
"num_tokens": 81584783.0,
|
|
"step": 35585
|
|
},
|
|
{
|
|
"entropy": 5.097601890563965,
|
|
"epoch": 3.418828049951969,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0003861573222399665,
|
|
"loss": 4.5866,
|
|
"mean_token_accuracy": 0.25657844096422194,
|
|
"num_tokens": 81596619.0,
|
|
"step": 35590
|
|
},
|
|
{
|
|
"entropy": 5.248367023468018,
|
|
"epoch": 3.419308357348703,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000386127513338261,
|
|
"loss": 4.7847,
|
|
"mean_token_accuracy": 0.23805569410324096,
|
|
"num_tokens": 81607981.0,
|
|
"step": 35595
|
|
},
|
|
{
|
|
"entropy": 5.178387975692749,
|
|
"epoch": 3.419788664745437,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003860977018565046,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.24262208640575408,
|
|
"num_tokens": 81620444.0,
|
|
"step": 35600
|
|
},
|
|
{
|
|
"entropy": 5.156166219711304,
|
|
"epoch": 3.420268972142171,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003860678877953894,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.24538012593984604,
|
|
"num_tokens": 81631668.0,
|
|
"step": 35605
|
|
},
|
|
{
|
|
"entropy": 5.168297147750854,
|
|
"epoch": 3.4207492795389047,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003860380711556077,
|
|
"loss": 4.7833,
|
|
"mean_token_accuracy": 0.24245427399873734,
|
|
"num_tokens": 81643230.0,
|
|
"step": 35610
|
|
},
|
|
{
|
|
"entropy": 5.171787261962891,
|
|
"epoch": 3.421229586935639,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038600825193785173,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.247586590051651,
|
|
"num_tokens": 81654217.0,
|
|
"step": 35615
|
|
},
|
|
{
|
|
"entropy": 5.171520471572876,
|
|
"epoch": 3.4217098943323725,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003859784301428137,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.23910353928804398,
|
|
"num_tokens": 81666025.0,
|
|
"step": 35620
|
|
},
|
|
{
|
|
"entropy": 5.2009148597717285,
|
|
"epoch": 3.422190201729107,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003859486057711861,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.2442367136478424,
|
|
"num_tokens": 81677417.0,
|
|
"step": 35625
|
|
},
|
|
{
|
|
"entropy": 5.164230728149414,
|
|
"epoch": 3.4226705091258407,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003859187788236613,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.25029167979955674,
|
|
"num_tokens": 81687898.0,
|
|
"step": 35630
|
|
},
|
|
{
|
|
"entropy": 5.073283100128174,
|
|
"epoch": 3.4231508165225746,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038588894930093184,
|
|
"loss": 4.6249,
|
|
"mean_token_accuracy": 0.25119459182024,
|
|
"num_tokens": 81699532.0,
|
|
"step": 35635
|
|
},
|
|
{
|
|
"entropy": 5.193126153945923,
|
|
"epoch": 3.4236311239193085,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038585911720369023,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.2410747677087784,
|
|
"num_tokens": 81709164.0,
|
|
"step": 35640
|
|
},
|
|
{
|
|
"entropy": 5.156799364089966,
|
|
"epoch": 3.4241114313160423,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003858292825326291,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.251453198492527,
|
|
"num_tokens": 81721354.0,
|
|
"step": 35645
|
|
},
|
|
{
|
|
"entropy": 5.104229545593261,
|
|
"epoch": 3.4245917387127762,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003857994452884412,
|
|
"loss": 4.575,
|
|
"mean_token_accuracy": 0.26043111383914946,
|
|
"num_tokens": 81731793.0,
|
|
"step": 35650
|
|
},
|
|
{
|
|
"entropy": 5.17866268157959,
|
|
"epoch": 3.42507204610951,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003857696054718191,
|
|
"loss": 4.6995,
|
|
"mean_token_accuracy": 0.2563246950507164,
|
|
"num_tokens": 81743254.0,
|
|
"step": 35655
|
|
},
|
|
{
|
|
"entropy": 5.21606330871582,
|
|
"epoch": 3.425552353506244,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003857397630834557,
|
|
"loss": 4.7756,
|
|
"mean_token_accuracy": 0.24177161306142808,
|
|
"num_tokens": 81755080.0,
|
|
"step": 35660
|
|
},
|
|
{
|
|
"entropy": 5.183961486816406,
|
|
"epoch": 3.426032660902978,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00038570991812404384,
|
|
"loss": 4.7007,
|
|
"mean_token_accuracy": 0.2480090945959091,
|
|
"num_tokens": 81767367.0,
|
|
"step": 35665
|
|
},
|
|
{
|
|
"entropy": 5.170588827133178,
|
|
"epoch": 3.4265129682997117,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003856800705942764,
|
|
"loss": 4.778,
|
|
"mean_token_accuracy": 0.2361098900437355,
|
|
"num_tokens": 81778513.0,
|
|
"step": 35670
|
|
},
|
|
{
|
|
"entropy": 5.1624163627624515,
|
|
"epoch": 3.4269932756964456,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00038565022049484636,
|
|
"loss": 4.6377,
|
|
"mean_token_accuracy": 0.2551702558994293,
|
|
"num_tokens": 81789845.0,
|
|
"step": 35675
|
|
},
|
|
{
|
|
"entropy": 5.105020999908447,
|
|
"epoch": 3.4274735830931795,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00038562036782644675,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.24704273641109467,
|
|
"num_tokens": 81801287.0,
|
|
"step": 35680
|
|
},
|
|
{
|
|
"entropy": 5.098159408569336,
|
|
"epoch": 3.4279538904899134,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003855905125897708,
|
|
"loss": 4.6529,
|
|
"mean_token_accuracy": 0.2557205706834793,
|
|
"num_tokens": 81811462.0,
|
|
"step": 35685
|
|
},
|
|
{
|
|
"entropy": 5.05807900428772,
|
|
"epoch": 3.4284341978866473,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038556065478551147,
|
|
"loss": 4.5988,
|
|
"mean_token_accuracy": 0.24994870871305466,
|
|
"num_tokens": 81822590.0,
|
|
"step": 35690
|
|
},
|
|
{
|
|
"entropy": 5.220713472366333,
|
|
"epoch": 3.428914505283381,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000385530794414362,
|
|
"loss": 4.7032,
|
|
"mean_token_accuracy": 0.2515057668089867,
|
|
"num_tokens": 81834755.0,
|
|
"step": 35695
|
|
},
|
|
{
|
|
"entropy": 5.105886745452881,
|
|
"epoch": 3.4293948126801155,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003855009314770157,
|
|
"loss": 4.5795,
|
|
"mean_token_accuracy": 0.25738127529621124,
|
|
"num_tokens": 81846259.0,
|
|
"step": 35700
|
|
},
|
|
{
|
|
"entropy": 5.030340671539307,
|
|
"epoch": 3.4298751200768494,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00038547106597416593,
|
|
"loss": 4.6043,
|
|
"mean_token_accuracy": 0.2575574979186058,
|
|
"num_tokens": 81856262.0,
|
|
"step": 35705
|
|
},
|
|
{
|
|
"entropy": 5.135979032516479,
|
|
"epoch": 3.4303554274735832,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000385441197906506,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.2458172097802162,
|
|
"num_tokens": 81867201.0,
|
|
"step": 35710
|
|
},
|
|
{
|
|
"entropy": 5.2178600311279295,
|
|
"epoch": 3.430835734870317,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038541132727472945,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.24075170159339904,
|
|
"num_tokens": 81878654.0,
|
|
"step": 35715
|
|
},
|
|
{
|
|
"entropy": 5.157098340988159,
|
|
"epoch": 3.431316042267051,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00038538145407952964,
|
|
"loss": 4.6287,
|
|
"mean_token_accuracy": 0.2502920120954514,
|
|
"num_tokens": 81889672.0,
|
|
"step": 35720
|
|
},
|
|
{
|
|
"entropy": 5.136937093734741,
|
|
"epoch": 3.431796349663785,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003853515783216003,
|
|
"loss": 4.6621,
|
|
"mean_token_accuracy": 0.24853487312793732,
|
|
"num_tokens": 81901072.0,
|
|
"step": 35725
|
|
},
|
|
{
|
|
"entropy": 5.1480992317199705,
|
|
"epoch": 3.4322766570605188,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000385321700001635,
|
|
"loss": 4.6248,
|
|
"mean_token_accuracy": 0.2562401592731476,
|
|
"num_tokens": 81913146.0,
|
|
"step": 35730
|
|
},
|
|
{
|
|
"entropy": 5.1738275527954105,
|
|
"epoch": 3.4327569644572526,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003852918191203274,
|
|
"loss": 4.7354,
|
|
"mean_token_accuracy": 0.24211084395647048,
|
|
"num_tokens": 81924648.0,
|
|
"step": 35735
|
|
},
|
|
{
|
|
"entropy": 5.164928865432739,
|
|
"epoch": 3.4332372718539865,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003852619356783712,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.24030201882123947,
|
|
"num_tokens": 81935744.0,
|
|
"step": 35740
|
|
},
|
|
{
|
|
"entropy": 5.183221530914307,
|
|
"epoch": 3.4337175792507204,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003852320496764603,
|
|
"loss": 4.6703,
|
|
"mean_token_accuracy": 0.2462662786245346,
|
|
"num_tokens": 81946931.0,
|
|
"step": 35745
|
|
},
|
|
{
|
|
"entropy": 5.106213569641113,
|
|
"epoch": 3.4341978866474543,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00038520216111528855,
|
|
"loss": 4.6414,
|
|
"mean_token_accuracy": 0.25448284298181534,
|
|
"num_tokens": 81958009.0,
|
|
"step": 35750
|
|
},
|
|
{
|
|
"entropy": 5.115417242050171,
|
|
"epoch": 3.434678194044188,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003851722699955499,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.24673267751932143,
|
|
"num_tokens": 81970648.0,
|
|
"step": 35755
|
|
},
|
|
{
|
|
"entropy": 5.140151786804199,
|
|
"epoch": 3.435158501440922,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003851423763179382,
|
|
"loss": 4.6354,
|
|
"mean_token_accuracy": 0.2552123561501503,
|
|
"num_tokens": 81982293.0,
|
|
"step": 35760
|
|
},
|
|
{
|
|
"entropy": 5.094575214385986,
|
|
"epoch": 3.435638808837656,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038511248008314756,
|
|
"loss": 4.6518,
|
|
"mean_token_accuracy": 0.25122184306383133,
|
|
"num_tokens": 81993856.0,
|
|
"step": 35765
|
|
},
|
|
{
|
|
"entropy": 5.1850334167480465,
|
|
"epoch": 3.43611911623439,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003850825812918722,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.23959899246692656,
|
|
"num_tokens": 82005359.0,
|
|
"step": 35770
|
|
},
|
|
{
|
|
"entropy": 5.168342161178589,
|
|
"epoch": 3.436599423631124,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003850526799448061,
|
|
"loss": 4.6813,
|
|
"mean_token_accuracy": 0.2514591231942177,
|
|
"num_tokens": 82017789.0,
|
|
"step": 35775
|
|
},
|
|
{
|
|
"entropy": 5.1825765609741214,
|
|
"epoch": 3.437079731027858,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003850227760426436,
|
|
"loss": 4.6766,
|
|
"mean_token_accuracy": 0.24646678417921067,
|
|
"num_tokens": 82028147.0,
|
|
"step": 35780
|
|
},
|
|
{
|
|
"entropy": 5.0772443294525145,
|
|
"epoch": 3.437560038424592,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038499286958607894,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.2511718913912773,
|
|
"num_tokens": 82039485.0,
|
|
"step": 35785
|
|
},
|
|
{
|
|
"entropy": 5.083371305465699,
|
|
"epoch": 3.438040345821326,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003849629605758065,
|
|
"loss": 4.5835,
|
|
"mean_token_accuracy": 0.2576414242386818,
|
|
"num_tokens": 82050004.0,
|
|
"step": 35790
|
|
},
|
|
{
|
|
"entropy": 5.09267373085022,
|
|
"epoch": 3.4385206532180597,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003849330490125205,
|
|
"loss": 4.6022,
|
|
"mean_token_accuracy": 0.25644453167915343,
|
|
"num_tokens": 82060621.0,
|
|
"step": 35795
|
|
},
|
|
{
|
|
"entropy": 5.164886331558227,
|
|
"epoch": 3.4390009606147935,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00038490313489691566,
|
|
"loss": 4.6637,
|
|
"mean_token_accuracy": 0.24530232846736907,
|
|
"num_tokens": 82070955.0,
|
|
"step": 35800
|
|
},
|
|
{
|
|
"entropy": 5.255003118515015,
|
|
"epoch": 3.4394812680115274,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003848732182296863,
|
|
"loss": 4.8862,
|
|
"mean_token_accuracy": 0.22977777868509291,
|
|
"num_tokens": 82082623.0,
|
|
"step": 35805
|
|
},
|
|
{
|
|
"entropy": 5.114319229125977,
|
|
"epoch": 3.4399615754082613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038484329901152713,
|
|
"loss": 4.6151,
|
|
"mean_token_accuracy": 0.2515829920768738,
|
|
"num_tokens": 82092707.0,
|
|
"step": 35810
|
|
},
|
|
{
|
|
"entropy": 5.1184014797210695,
|
|
"epoch": 3.440441882804995,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038481337724313264,
|
|
"loss": 4.6601,
|
|
"mean_token_accuracy": 0.2534993126988411,
|
|
"num_tokens": 82105114.0,
|
|
"step": 35815
|
|
},
|
|
{
|
|
"entropy": 5.112124729156494,
|
|
"epoch": 3.440922190201729,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003847834529251977,
|
|
"loss": 4.6238,
|
|
"mean_token_accuracy": 0.2542474076151848,
|
|
"num_tokens": 82117638.0,
|
|
"step": 35820
|
|
},
|
|
{
|
|
"entropy": 5.133162784576416,
|
|
"epoch": 3.441402497598463,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00038475352605841693,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.24839437156915664,
|
|
"num_tokens": 82129100.0,
|
|
"step": 35825
|
|
},
|
|
{
|
|
"entropy": 5.165353584289551,
|
|
"epoch": 3.441882804995197,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003847235966434852,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.2513016387820244,
|
|
"num_tokens": 82140776.0,
|
|
"step": 35830
|
|
},
|
|
{
|
|
"entropy": 5.198472118377685,
|
|
"epoch": 3.4423631123919307,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003846936646810974,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.24050161689519883,
|
|
"num_tokens": 82151569.0,
|
|
"step": 35835
|
|
},
|
|
{
|
|
"entropy": 5.203648614883423,
|
|
"epoch": 3.4428434197886646,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00038466373017194834,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.2427465572953224,
|
|
"num_tokens": 82162696.0,
|
|
"step": 35840
|
|
},
|
|
{
|
|
"entropy": 5.0766242980957035,
|
|
"epoch": 3.4433237271853985,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003846337931167332,
|
|
"loss": 4.5505,
|
|
"mean_token_accuracy": 0.2533407241106033,
|
|
"num_tokens": 82173580.0,
|
|
"step": 35845
|
|
},
|
|
{
|
|
"entropy": 5.085100698471069,
|
|
"epoch": 3.443804034582133,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00038460385351614683,
|
|
"loss": 4.6664,
|
|
"mean_token_accuracy": 0.25117525458335876,
|
|
"num_tokens": 82185839.0,
|
|
"step": 35850
|
|
},
|
|
{
|
|
"entropy": 5.14958701133728,
|
|
"epoch": 3.4442843419788662,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038457391137088455,
|
|
"loss": 4.6599,
|
|
"mean_token_accuracy": 0.24583828300237656,
|
|
"num_tokens": 82196682.0,
|
|
"step": 35855
|
|
},
|
|
{
|
|
"entropy": 5.143909549713134,
|
|
"epoch": 3.4447646493756006,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00038454396668164136,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.24899957627058028,
|
|
"num_tokens": 82207349.0,
|
|
"step": 35860
|
|
},
|
|
{
|
|
"entropy": 5.145882177352905,
|
|
"epoch": 3.4452449567723344,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003845140194491126,
|
|
"loss": 4.6487,
|
|
"mean_token_accuracy": 0.25110517144203187,
|
|
"num_tokens": 82218547.0,
|
|
"step": 35865
|
|
},
|
|
{
|
|
"entropy": 5.152105617523193,
|
|
"epoch": 3.4457252641690683,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00038448406967399334,
|
|
"loss": 4.6675,
|
|
"mean_token_accuracy": 0.2530243068933487,
|
|
"num_tokens": 82230246.0,
|
|
"step": 35870
|
|
},
|
|
{
|
|
"entropy": 5.0324952602386475,
|
|
"epoch": 3.446205571565802,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00038445411735697917,
|
|
"loss": 4.6283,
|
|
"mean_token_accuracy": 0.24977963119745256,
|
|
"num_tokens": 82240924.0,
|
|
"step": 35875
|
|
},
|
|
{
|
|
"entropy": 5.118201446533203,
|
|
"epoch": 3.446685878962536,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003844241624987655,
|
|
"loss": 4.7053,
|
|
"mean_token_accuracy": 0.2496531918644905,
|
|
"num_tokens": 82252951.0,
|
|
"step": 35880
|
|
},
|
|
{
|
|
"entropy": 5.241723442077637,
|
|
"epoch": 3.44716618635927,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003843942051000476,
|
|
"loss": 4.7486,
|
|
"mean_token_accuracy": 0.23705194592475892,
|
|
"num_tokens": 82264377.0,
|
|
"step": 35885
|
|
},
|
|
{
|
|
"entropy": 5.202305650711059,
|
|
"epoch": 3.447646493756004,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000384364245161521,
|
|
"loss": 4.8009,
|
|
"mean_token_accuracy": 0.23084784746170045,
|
|
"num_tokens": 82276736.0,
|
|
"step": 35890
|
|
},
|
|
{
|
|
"entropy": 5.166099977493286,
|
|
"epoch": 3.4481268011527377,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003843342826838815,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.24728539437055588,
|
|
"num_tokens": 82288574.0,
|
|
"step": 35895
|
|
},
|
|
{
|
|
"entropy": 5.140314960479737,
|
|
"epoch": 3.4486071085494716,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00038430431766782463,
|
|
"loss": 4.6062,
|
|
"mean_token_accuracy": 0.25599681586027145,
|
|
"num_tokens": 82299570.0,
|
|
"step": 35900
|
|
},
|
|
{
|
|
"entropy": 5.178872013092041,
|
|
"epoch": 3.4490874159462055,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000384274350114046,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.2387193724513054,
|
|
"num_tokens": 82310449.0,
|
|
"step": 35905
|
|
},
|
|
{
|
|
"entropy": 5.144611406326294,
|
|
"epoch": 3.4495677233429394,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038424438002324145,
|
|
"loss": 4.7385,
|
|
"mean_token_accuracy": 0.23935449719429017,
|
|
"num_tokens": 82321517.0,
|
|
"step": 35910
|
|
},
|
|
{
|
|
"entropy": 5.105161952972412,
|
|
"epoch": 3.4500480307396733,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00038421440739610683,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.24576045125722884,
|
|
"num_tokens": 82334555.0,
|
|
"step": 35915
|
|
},
|
|
{
|
|
"entropy": 5.046426153182983,
|
|
"epoch": 3.450528338136407,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.00038418443223333797,
|
|
"loss": 4.5462,
|
|
"mean_token_accuracy": 0.2585986822843552,
|
|
"num_tokens": 82347166.0,
|
|
"step": 35920
|
|
},
|
|
{
|
|
"entropy": 5.0573211193084715,
|
|
"epoch": 3.451008645533141,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003841544545356308,
|
|
"loss": 4.5875,
|
|
"mean_token_accuracy": 0.2506593093276024,
|
|
"num_tokens": 82358220.0,
|
|
"step": 35925
|
|
},
|
|
{
|
|
"entropy": 5.142927789688111,
|
|
"epoch": 3.451488952929875,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00038412447430368125,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.2443858802318573,
|
|
"num_tokens": 82369154.0,
|
|
"step": 35930
|
|
},
|
|
{
|
|
"entropy": 5.139485263824463,
|
|
"epoch": 3.4519692603266092,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038409449153818556,
|
|
"loss": 4.6316,
|
|
"mean_token_accuracy": 0.2582821324467659,
|
|
"num_tokens": 82380311.0,
|
|
"step": 35935
|
|
},
|
|
{
|
|
"entropy": 5.0898970603942875,
|
|
"epoch": 3.452449567723343,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038406450623983964,
|
|
"loss": 4.6432,
|
|
"mean_token_accuracy": 0.2494583934545517,
|
|
"num_tokens": 82390895.0,
|
|
"step": 35940
|
|
},
|
|
{
|
|
"entropy": 5.146787214279175,
|
|
"epoch": 3.452929875120077,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038403451840933966,
|
|
"loss": 4.6154,
|
|
"mean_token_accuracy": 0.2509046345949173,
|
|
"num_tokens": 82400880.0,
|
|
"step": 35945
|
|
},
|
|
{
|
|
"entropy": 5.123151969909668,
|
|
"epoch": 3.453410182516811,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00038400452804738204,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.25401165932416914,
|
|
"num_tokens": 82413566.0,
|
|
"step": 35950
|
|
},
|
|
{
|
|
"entropy": 5.076843738555908,
|
|
"epoch": 3.4538904899135447,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038397453515466297,
|
|
"loss": 4.6159,
|
|
"mean_token_accuracy": 0.25957250595092773,
|
|
"num_tokens": 82424434.0,
|
|
"step": 35955
|
|
},
|
|
{
|
|
"entropy": 5.174961566925049,
|
|
"epoch": 3.4543707973102786,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003839445397318787,
|
|
"loss": 4.7435,
|
|
"mean_token_accuracy": 0.24397713989019393,
|
|
"num_tokens": 82436310.0,
|
|
"step": 35960
|
|
},
|
|
{
|
|
"entropy": 5.101727390289307,
|
|
"epoch": 3.4548511047070125,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003839145417797258,
|
|
"loss": 4.6013,
|
|
"mean_token_accuracy": 0.2511016756296158,
|
|
"num_tokens": 82446484.0,
|
|
"step": 35965
|
|
},
|
|
{
|
|
"entropy": 5.200941371917724,
|
|
"epoch": 3.4553314121037464,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003838845412989006,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.23557325899600984,
|
|
"num_tokens": 82458169.0,
|
|
"step": 35970
|
|
},
|
|
{
|
|
"entropy": 5.1151011943817135,
|
|
"epoch": 3.4558117195004803,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003838545382900997,
|
|
"loss": 4.6311,
|
|
"mean_token_accuracy": 0.25253243297338485,
|
|
"num_tokens": 82469407.0,
|
|
"step": 35975
|
|
},
|
|
{
|
|
"entropy": 5.096318531036377,
|
|
"epoch": 3.456292026897214,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003838245327540196,
|
|
"loss": 4.6158,
|
|
"mean_token_accuracy": 0.2555417984724045,
|
|
"num_tokens": 82480757.0,
|
|
"step": 35980
|
|
},
|
|
{
|
|
"entropy": 5.087097024917602,
|
|
"epoch": 3.456772334293948,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038379452469135706,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.25180825442075727,
|
|
"num_tokens": 82491073.0,
|
|
"step": 35985
|
|
},
|
|
{
|
|
"entropy": 5.147249603271485,
|
|
"epoch": 3.457252641690682,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00038376451410280864,
|
|
"loss": 4.6971,
|
|
"mean_token_accuracy": 0.25356541723012926,
|
|
"num_tokens": 82502243.0,
|
|
"step": 35990
|
|
},
|
|
{
|
|
"entropy": 5.195792722702026,
|
|
"epoch": 3.457732949087416,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038373450098907124,
|
|
"loss": 4.6694,
|
|
"mean_token_accuracy": 0.2445956662297249,
|
|
"num_tokens": 82514831.0,
|
|
"step": 35995
|
|
},
|
|
{
|
|
"entropy": 5.125249814987183,
|
|
"epoch": 3.4582132564841497,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038370448535084156,
|
|
"loss": 4.6763,
|
|
"mean_token_accuracy": 0.25372505336999895,
|
|
"num_tokens": 82525907.0,
|
|
"step": 36000
|
|
},
|
|
{
|
|
"epoch": 3.4582132564841497,
|
|
"eval_entropy": 4.938386408890938,
|
|
"eval_loss": 4.806099891662598,
|
|
"eval_mean_token_accuracy": 0.24943239452623409,
|
|
"eval_num_tokens": 82525907.0,
|
|
"eval_runtime": 26.7071,
|
|
"eval_samples_per_second": 1228.701,
|
|
"eval_steps_per_second": 153.592,
|
|
"step": 36000
|
|
},
|
|
{
|
|
"entropy": 5.175897455215454,
|
|
"epoch": 3.4586935638808836,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003836744671888165,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.24125944674015046,
|
|
"num_tokens": 82537130.0,
|
|
"step": 36005
|
|
},
|
|
{
|
|
"entropy": 5.0976804256439205,
|
|
"epoch": 3.459173871277618,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00038364444650369306,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.24547190219163895,
|
|
"num_tokens": 82548244.0,
|
|
"step": 36010
|
|
},
|
|
{
|
|
"entropy": 5.110092735290527,
|
|
"epoch": 3.4596541786743518,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038361442329616814,
|
|
"loss": 4.6151,
|
|
"mean_token_accuracy": 0.2515064612030983,
|
|
"num_tokens": 82559291.0,
|
|
"step": 36015
|
|
},
|
|
{
|
|
"entropy": 5.1265734195709225,
|
|
"epoch": 3.4601344860710856,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00038358439756693886,
|
|
"loss": 4.6438,
|
|
"mean_token_accuracy": 0.24948425889015197,
|
|
"num_tokens": 82570929.0,
|
|
"step": 36020
|
|
},
|
|
{
|
|
"entropy": 5.109566354751587,
|
|
"epoch": 3.4606147934678195,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038355436931670225,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.25069818943738936,
|
|
"num_tokens": 82583016.0,
|
|
"step": 36025
|
|
},
|
|
{
|
|
"entropy": 5.1773192405700685,
|
|
"epoch": 3.4610951008645534,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00038352433854615557,
|
|
"loss": 4.7052,
|
|
"mean_token_accuracy": 0.24535865783691407,
|
|
"num_tokens": 82593950.0,
|
|
"step": 36030
|
|
},
|
|
{
|
|
"entropy": 5.05225191116333,
|
|
"epoch": 3.4615754082612873,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00038349430525599606,
|
|
"loss": 4.5742,
|
|
"mean_token_accuracy": 0.24887338578701018,
|
|
"num_tokens": 82605764.0,
|
|
"step": 36035
|
|
},
|
|
{
|
|
"entropy": 5.112909317016602,
|
|
"epoch": 3.462055715658021,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00038346426944692075,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.24760213494300842,
|
|
"num_tokens": 82617336.0,
|
|
"step": 36040
|
|
},
|
|
{
|
|
"entropy": 5.109757614135742,
|
|
"epoch": 3.462536023054755,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003834342311196274,
|
|
"loss": 4.5853,
|
|
"mean_token_accuracy": 0.2638463854789734,
|
|
"num_tokens": 82628999.0,
|
|
"step": 36045
|
|
},
|
|
{
|
|
"entropy": 5.071820020675659,
|
|
"epoch": 3.463016330451489,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038340419027481305,
|
|
"loss": 4.6844,
|
|
"mean_token_accuracy": 0.2536777496337891,
|
|
"num_tokens": 82640141.0,
|
|
"step": 36050
|
|
},
|
|
{
|
|
"entropy": 5.10496506690979,
|
|
"epoch": 3.463496637848223,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003833741469131753,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.24599506556987763,
|
|
"num_tokens": 82651320.0,
|
|
"step": 36055
|
|
},
|
|
{
|
|
"entropy": 5.147433137893676,
|
|
"epoch": 3.4639769452449567,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003833441010354117,
|
|
"loss": 4.6629,
|
|
"mean_token_accuracy": 0.25153120905160903,
|
|
"num_tokens": 82662126.0,
|
|
"step": 36060
|
|
},
|
|
{
|
|
"entropy": 5.073838520050049,
|
|
"epoch": 3.4644572526416906,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00038331405264221974,
|
|
"loss": 4.6294,
|
|
"mean_token_accuracy": 0.25429482758045197,
|
|
"num_tokens": 82673266.0,
|
|
"step": 36065
|
|
},
|
|
{
|
|
"entropy": 5.1957673072814945,
|
|
"epoch": 3.4649375600384245,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003832840017342972,
|
|
"loss": 4.722,
|
|
"mean_token_accuracy": 0.24373950064182281,
|
|
"num_tokens": 82684797.0,
|
|
"step": 36070
|
|
},
|
|
{
|
|
"entropy": 5.0569226264953615,
|
|
"epoch": 3.4654178674351583,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00038325394831234164,
|
|
"loss": 4.6236,
|
|
"mean_token_accuracy": 0.25097730606794355,
|
|
"num_tokens": 82697531.0,
|
|
"step": 36075
|
|
},
|
|
{
|
|
"entropy": 5.18017053604126,
|
|
"epoch": 3.465898174831892,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003832238923770508,
|
|
"loss": 4.6935,
|
|
"mean_token_accuracy": 0.24859998673200606,
|
|
"num_tokens": 82708481.0,
|
|
"step": 36080
|
|
},
|
|
{
|
|
"entropy": 5.057299041748047,
|
|
"epoch": 3.4663784822286265,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003831938339291225,
|
|
"loss": 4.6628,
|
|
"mean_token_accuracy": 0.24683981537818908,
|
|
"num_tokens": 82719569.0,
|
|
"step": 36085
|
|
},
|
|
{
|
|
"entropy": 5.185129642486572,
|
|
"epoch": 3.46685878962536,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038316377296925474,
|
|
"loss": 4.7625,
|
|
"mean_token_accuracy": 0.2408883050084114,
|
|
"num_tokens": 82730219.0,
|
|
"step": 36090
|
|
},
|
|
{
|
|
"entropy": 5.193925380706787,
|
|
"epoch": 3.4673390970220943,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00038313370949814537,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.23866744190454484,
|
|
"num_tokens": 82741865.0,
|
|
"step": 36095
|
|
},
|
|
{
|
|
"entropy": 5.146476316452026,
|
|
"epoch": 3.467819404418828,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003831036435164923,
|
|
"loss": 4.6477,
|
|
"mean_token_accuracy": 0.25587181746959686,
|
|
"num_tokens": 82752751.0,
|
|
"step": 36100
|
|
},
|
|
{
|
|
"entropy": 5.18651065826416,
|
|
"epoch": 3.468299711815562,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003830735750249936,
|
|
"loss": 4.7539,
|
|
"mean_token_accuracy": 0.24371516555547715,
|
|
"num_tokens": 82763946.0,
|
|
"step": 36105
|
|
},
|
|
{
|
|
"entropy": 5.108306455612182,
|
|
"epoch": 3.468780019212296,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003830435040243475,
|
|
"loss": 4.6498,
|
|
"mean_token_accuracy": 0.24906240850687028,
|
|
"num_tokens": 82775659.0,
|
|
"step": 36110
|
|
},
|
|
{
|
|
"entropy": 5.140910243988037,
|
|
"epoch": 3.46926032660903,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000383013430515252,
|
|
"loss": 4.6856,
|
|
"mean_token_accuracy": 0.24263203591108323,
|
|
"num_tokens": 82787633.0,
|
|
"step": 36115
|
|
},
|
|
{
|
|
"entropy": 5.141036510467529,
|
|
"epoch": 3.4697406340057637,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003829833544984054,
|
|
"loss": 4.7384,
|
|
"mean_token_accuracy": 0.24512852132320403,
|
|
"num_tokens": 82799983.0,
|
|
"step": 36120
|
|
},
|
|
{
|
|
"entropy": 5.216569900512695,
|
|
"epoch": 3.4702209414024976,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003829532759745059,
|
|
"loss": 4.7157,
|
|
"mean_token_accuracy": 0.24760020077228545,
|
|
"num_tokens": 82811733.0,
|
|
"step": 36125
|
|
},
|
|
{
|
|
"entropy": 5.205350685119629,
|
|
"epoch": 3.4707012487992315,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038292319494425195,
|
|
"loss": 4.7166,
|
|
"mean_token_accuracy": 0.2397096797823906,
|
|
"num_tokens": 82823555.0,
|
|
"step": 36130
|
|
},
|
|
{
|
|
"entropy": 5.121596240997315,
|
|
"epoch": 3.4711815561959654,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003828931114083419,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.2527704492211342,
|
|
"num_tokens": 82835288.0,
|
|
"step": 36135
|
|
},
|
|
{
|
|
"entropy": 5.134416103363037,
|
|
"epoch": 3.4716618635926992,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000382863025367474,
|
|
"loss": 4.6489,
|
|
"mean_token_accuracy": 0.25899892300367355,
|
|
"num_tokens": 82846298.0,
|
|
"step": 36140
|
|
},
|
|
{
|
|
"entropy": 5.192988729476928,
|
|
"epoch": 3.472142170989433,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003828329368223471,
|
|
"loss": 4.7138,
|
|
"mean_token_accuracy": 0.2401803895831108,
|
|
"num_tokens": 82859265.0,
|
|
"step": 36145
|
|
},
|
|
{
|
|
"entropy": 5.129560708999634,
|
|
"epoch": 3.472622478386167,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003828028457736596,
|
|
"loss": 4.6847,
|
|
"mean_token_accuracy": 0.24750615656375885,
|
|
"num_tokens": 82870167.0,
|
|
"step": 36150
|
|
},
|
|
{
|
|
"entropy": 5.155483436584473,
|
|
"epoch": 3.473102785782901,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0003827727522221101,
|
|
"loss": 4.7248,
|
|
"mean_token_accuracy": 0.2453589305281639,
|
|
"num_tokens": 82883034.0,
|
|
"step": 36155
|
|
},
|
|
{
|
|
"entropy": 5.115746307373047,
|
|
"epoch": 3.473583093179635,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00038274265616839733,
|
|
"loss": 4.6096,
|
|
"mean_token_accuracy": 0.25590566396713255,
|
|
"num_tokens": 82894080.0,
|
|
"step": 36160
|
|
},
|
|
{
|
|
"entropy": 5.133813142776489,
|
|
"epoch": 3.4740634005763686,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00038271255761322,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.25081678926944734,
|
|
"num_tokens": 82905158.0,
|
|
"step": 36165
|
|
},
|
|
{
|
|
"entropy": 5.108436107635498,
|
|
"epoch": 3.474543707973103,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003826824565572769,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.25078868567943574,
|
|
"num_tokens": 82917246.0,
|
|
"step": 36170
|
|
},
|
|
{
|
|
"entropy": 5.087131404876709,
|
|
"epoch": 3.475024015369837,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003826523530012669,
|
|
"loss": 4.6049,
|
|
"mean_token_accuracy": 0.24980828166007996,
|
|
"num_tokens": 82928895.0,
|
|
"step": 36175
|
|
},
|
|
{
|
|
"entropy": 5.104122686386108,
|
|
"epoch": 3.4755043227665707,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000382622246945889,
|
|
"loss": 4.68,
|
|
"mean_token_accuracy": 0.2538630560040474,
|
|
"num_tokens": 82939239.0,
|
|
"step": 36180
|
|
},
|
|
{
|
|
"entropy": 5.125030469894409,
|
|
"epoch": 3.4759846301633046,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00038259213839184205,
|
|
"loss": 4.6559,
|
|
"mean_token_accuracy": 0.2518941476941109,
|
|
"num_tokens": 82950457.0,
|
|
"step": 36185
|
|
},
|
|
{
|
|
"entropy": 5.112875986099243,
|
|
"epoch": 3.4764649375600385,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038256202733982515,
|
|
"loss": 4.6227,
|
|
"mean_token_accuracy": 0.2522160679101944,
|
|
"num_tokens": 82961589.0,
|
|
"step": 36190
|
|
},
|
|
{
|
|
"entropy": 5.0799767017364506,
|
|
"epoch": 3.4769452449567724,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003825319137905373,
|
|
"loss": 4.5616,
|
|
"mean_token_accuracy": 0.25463595539331435,
|
|
"num_tokens": 82972397.0,
|
|
"step": 36195
|
|
},
|
|
{
|
|
"entropy": 5.135418033599853,
|
|
"epoch": 3.4774255523535063,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003825017977446778,
|
|
"loss": 4.667,
|
|
"mean_token_accuracy": 0.24660785645246505,
|
|
"num_tokens": 82984239.0,
|
|
"step": 36200
|
|
},
|
|
{
|
|
"entropy": 5.132601261138916,
|
|
"epoch": 3.47790585975024,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038247167920294574,
|
|
"loss": 4.7067,
|
|
"mean_token_accuracy": 0.2515007689595222,
|
|
"num_tokens": 82996544.0,
|
|
"step": 36205
|
|
},
|
|
{
|
|
"entropy": 5.260466432571411,
|
|
"epoch": 3.478386167146974,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038244155816604037,
|
|
"loss": 4.8445,
|
|
"mean_token_accuracy": 0.23798701614141465,
|
|
"num_tokens": 83009002.0,
|
|
"step": 36210
|
|
},
|
|
{
|
|
"entropy": 5.122015905380249,
|
|
"epoch": 3.478866474543708,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0003824114346346611,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.2422094762325287,
|
|
"num_tokens": 83021225.0,
|
|
"step": 36215
|
|
},
|
|
{
|
|
"entropy": 5.108890008926392,
|
|
"epoch": 3.479346781940442,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003823813086095073,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.24804001152515412,
|
|
"num_tokens": 83032682.0,
|
|
"step": 36220
|
|
},
|
|
{
|
|
"entropy": 5.144789361953736,
|
|
"epoch": 3.4798270893371757,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00038235118009127833,
|
|
"loss": 4.6522,
|
|
"mean_token_accuracy": 0.25696383565664294,
|
|
"num_tokens": 83045035.0,
|
|
"step": 36225
|
|
},
|
|
{
|
|
"entropy": 5.229673862457275,
|
|
"epoch": 3.4803073967339095,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003823210490806737,
|
|
"loss": 4.831,
|
|
"mean_token_accuracy": 0.23783012628555297,
|
|
"num_tokens": 83056724.0,
|
|
"step": 36230
|
|
},
|
|
{
|
|
"entropy": 5.157167530059814,
|
|
"epoch": 3.4807877041306434,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000382290915578393,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.24861735105514526,
|
|
"num_tokens": 83067736.0,
|
|
"step": 36235
|
|
},
|
|
{
|
|
"entropy": 5.110315942764283,
|
|
"epoch": 3.4812680115273773,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003822607795851359,
|
|
"loss": 4.6334,
|
|
"mean_token_accuracy": 0.258132703602314,
|
|
"num_tokens": 83079367.0,
|
|
"step": 36240
|
|
},
|
|
{
|
|
"entropy": 5.201521873474121,
|
|
"epoch": 3.4817483189241116,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003822306411016019,
|
|
"loss": 4.7102,
|
|
"mean_token_accuracy": 0.24178309142589569,
|
|
"num_tokens": 83091138.0,
|
|
"step": 36245
|
|
},
|
|
{
|
|
"entropy": 5.097733879089356,
|
|
"epoch": 3.4822286263208455,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003822005001284909,
|
|
"loss": 4.5907,
|
|
"mean_token_accuracy": 0.2590155988931656,
|
|
"num_tokens": 83101627.0,
|
|
"step": 36250
|
|
},
|
|
{
|
|
"entropy": 5.125740671157837,
|
|
"epoch": 3.4827089337175794,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003821703566665026,
|
|
"loss": 4.6682,
|
|
"mean_token_accuracy": 0.2485606014728546,
|
|
"num_tokens": 83112569.0,
|
|
"step": 36255
|
|
},
|
|
{
|
|
"entropy": 5.096224927902222,
|
|
"epoch": 3.4831892411143133,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003821402107163368,
|
|
"loss": 4.5742,
|
|
"mean_token_accuracy": 0.25608069598674776,
|
|
"num_tokens": 83124019.0,
|
|
"step": 36260
|
|
},
|
|
{
|
|
"entropy": 5.1128236770629885,
|
|
"epoch": 3.483669548511047,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003821100622786935,
|
|
"loss": 4.6121,
|
|
"mean_token_accuracy": 0.26119773983955386,
|
|
"num_tokens": 83135032.0,
|
|
"step": 36265
|
|
},
|
|
{
|
|
"entropy": 5.023627185821534,
|
|
"epoch": 3.484149855907781,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00038207991135427255,
|
|
"loss": 4.5397,
|
|
"mean_token_accuracy": 0.25468509942293166,
|
|
"num_tokens": 83147362.0,
|
|
"step": 36270
|
|
},
|
|
{
|
|
"entropy": 5.117301797866821,
|
|
"epoch": 3.484630163304515,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000382049757943774,
|
|
"loss": 4.6552,
|
|
"mean_token_accuracy": 0.25555762499570844,
|
|
"num_tokens": 83158531.0,
|
|
"step": 36275
|
|
},
|
|
{
|
|
"entropy": 5.170515012741089,
|
|
"epoch": 3.485110470701249,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00038201960204789796,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.2432562917470932,
|
|
"num_tokens": 83169565.0,
|
|
"step": 36280
|
|
},
|
|
{
|
|
"entropy": 5.152302360534668,
|
|
"epoch": 3.4855907780979827,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003819894436673446,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.24822264462709426,
|
|
"num_tokens": 83181084.0,
|
|
"step": 36285
|
|
},
|
|
{
|
|
"entropy": 5.183336210250855,
|
|
"epoch": 3.4860710854947166,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038195928280281406,
|
|
"loss": 4.7119,
|
|
"mean_token_accuracy": 0.23875396996736525,
|
|
"num_tokens": 83193477.0,
|
|
"step": 36290
|
|
},
|
|
{
|
|
"entropy": 5.126823663711548,
|
|
"epoch": 3.4865513928914504,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003819291194550066,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.2481584742665291,
|
|
"num_tokens": 83204408.0,
|
|
"step": 36295
|
|
},
|
|
{
|
|
"entropy": 5.207038450241089,
|
|
"epoch": 3.4870317002881843,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003818989536246224,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.24419762641191484,
|
|
"num_tokens": 83215152.0,
|
|
"step": 36300
|
|
},
|
|
{
|
|
"entropy": 5.100882625579834,
|
|
"epoch": 3.487512007684918,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00038186878531236196,
|
|
"loss": 4.6039,
|
|
"mean_token_accuracy": 0.2582545667886734,
|
|
"num_tokens": 83227094.0,
|
|
"step": 36305
|
|
},
|
|
{
|
|
"entropy": 5.142994356155396,
|
|
"epoch": 3.487992315081652,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00038183861451892567,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.25611541122198106,
|
|
"num_tokens": 83238149.0,
|
|
"step": 36310
|
|
},
|
|
{
|
|
"entropy": 5.136138153076172,
|
|
"epoch": 3.488472622478386,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000381808441245014,
|
|
"loss": 4.7272,
|
|
"mean_token_accuracy": 0.2435934603214264,
|
|
"num_tokens": 83249991.0,
|
|
"step": 36315
|
|
},
|
|
{
|
|
"entropy": 5.139973878860474,
|
|
"epoch": 3.4889529298751203,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003817782654913274,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.24988979399204253,
|
|
"num_tokens": 83262987.0,
|
|
"step": 36320
|
|
},
|
|
{
|
|
"entropy": 5.185416555404663,
|
|
"epoch": 3.489433237271854,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003817480872585667,
|
|
"loss": 4.7086,
|
|
"mean_token_accuracy": 0.24690861403942108,
|
|
"num_tokens": 83274155.0,
|
|
"step": 36325
|
|
},
|
|
{
|
|
"entropy": 5.206289911270142,
|
|
"epoch": 3.489913544668588,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038171790654743234,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.2473341017961502,
|
|
"num_tokens": 83286314.0,
|
|
"step": 36330
|
|
},
|
|
{
|
|
"entropy": 5.120683240890503,
|
|
"epoch": 3.490393852065322,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000381687723358625,
|
|
"loss": 4.7007,
|
|
"mean_token_accuracy": 0.24694877862930298,
|
|
"num_tokens": 83297435.0,
|
|
"step": 36335
|
|
},
|
|
{
|
|
"entropy": 5.071314764022827,
|
|
"epoch": 3.490874159462056,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003816575376928456,
|
|
"loss": 4.5462,
|
|
"mean_token_accuracy": 0.2582056999206543,
|
|
"num_tokens": 83308248.0,
|
|
"step": 36340
|
|
},
|
|
{
|
|
"entropy": 5.105325841903687,
|
|
"epoch": 3.4913544668587897,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00038162734955079483,
|
|
"loss": 4.6281,
|
|
"mean_token_accuracy": 0.2500329926609993,
|
|
"num_tokens": 83319446.0,
|
|
"step": 36345
|
|
},
|
|
{
|
|
"entropy": 5.248553085327148,
|
|
"epoch": 3.4918347742555236,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003815971589331736,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.24636409878730775,
|
|
"num_tokens": 83330340.0,
|
|
"step": 36350
|
|
},
|
|
{
|
|
"entropy": 5.086368560791016,
|
|
"epoch": 3.4923150816522575,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003815669658406829,
|
|
"loss": 4.5796,
|
|
"mean_token_accuracy": 0.25638708621263506,
|
|
"num_tokens": 83342338.0,
|
|
"step": 36355
|
|
},
|
|
{
|
|
"entropy": 5.104983139038086,
|
|
"epoch": 3.4927953890489913,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038153677027402374,
|
|
"loss": 4.6242,
|
|
"mean_token_accuracy": 0.25396613627672193,
|
|
"num_tokens": 83353272.0,
|
|
"step": 36360
|
|
},
|
|
{
|
|
"entropy": 5.138896083831787,
|
|
"epoch": 3.493275696445725,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038150657223389703,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.2502073869109154,
|
|
"num_tokens": 83364691.0,
|
|
"step": 36365
|
|
},
|
|
{
|
|
"entropy": 5.167219638824463,
|
|
"epoch": 3.493756003842459,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038147637172100397,
|
|
"loss": 4.6516,
|
|
"mean_token_accuracy": 0.25818939656019213,
|
|
"num_tokens": 83375110.0,
|
|
"step": 36370
|
|
},
|
|
{
|
|
"entropy": 5.081040239334106,
|
|
"epoch": 3.494236311239193,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003814461687360459,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.23983301520347594,
|
|
"num_tokens": 83387540.0,
|
|
"step": 36375
|
|
},
|
|
{
|
|
"entropy": 5.1895280361175535,
|
|
"epoch": 3.494716618635927,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038141596327972375,
|
|
"loss": 4.745,
|
|
"mean_token_accuracy": 0.23990361392498016,
|
|
"num_tokens": 83398895.0,
|
|
"step": 36380
|
|
},
|
|
{
|
|
"entropy": 5.132664489746094,
|
|
"epoch": 3.4951969260326607,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003813857553527389,
|
|
"loss": 4.6355,
|
|
"mean_token_accuracy": 0.24429842382669448,
|
|
"num_tokens": 83410712.0,
|
|
"step": 36385
|
|
},
|
|
{
|
|
"entropy": 5.196200180053711,
|
|
"epoch": 3.4956772334293946,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038135554495579273,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.23957151919603348,
|
|
"num_tokens": 83421168.0,
|
|
"step": 36390
|
|
},
|
|
{
|
|
"entropy": 5.1673290729522705,
|
|
"epoch": 3.496157540826129,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003813253320895866,
|
|
"loss": 4.7227,
|
|
"mean_token_accuracy": 0.24407393336296082,
|
|
"num_tokens": 83432634.0,
|
|
"step": 36395
|
|
},
|
|
{
|
|
"entropy": 5.1375268459320065,
|
|
"epoch": 3.4966378482228624,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000381295116754822,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.2449979826807976,
|
|
"num_tokens": 83444024.0,
|
|
"step": 36400
|
|
},
|
|
{
|
|
"entropy": 5.212603378295898,
|
|
"epoch": 3.4971181556195967,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038126489895220047,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.23882118612527847,
|
|
"num_tokens": 83455223.0,
|
|
"step": 36405
|
|
},
|
|
{
|
|
"entropy": 5.266806936264038,
|
|
"epoch": 3.4975984630163306,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00038123467868242345,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.23468692898750304,
|
|
"num_tokens": 83467295.0,
|
|
"step": 36410
|
|
},
|
|
{
|
|
"entropy": 5.242670726776123,
|
|
"epoch": 3.4980787704130645,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00038120445594619264,
|
|
"loss": 4.8029,
|
|
"mean_token_accuracy": 0.2405940353870392,
|
|
"num_tokens": 83478445.0,
|
|
"step": 36415
|
|
},
|
|
{
|
|
"entropy": 5.162256240844727,
|
|
"epoch": 3.4985590778097984,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003811742307442098,
|
|
"loss": 4.6847,
|
|
"mean_token_accuracy": 0.25059708654880525,
|
|
"num_tokens": 83490257.0,
|
|
"step": 36420
|
|
},
|
|
{
|
|
"entropy": 5.123780345916748,
|
|
"epoch": 3.4990393852065322,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00038114400307717657,
|
|
"loss": 4.6627,
|
|
"mean_token_accuracy": 0.24686498194932938,
|
|
"num_tokens": 83501773.0,
|
|
"step": 36425
|
|
},
|
|
{
|
|
"entropy": 5.141315603256226,
|
|
"epoch": 3.499519692603266,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003811137729457947,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.25182376652956007,
|
|
"num_tokens": 83513654.0,
|
|
"step": 36430
|
|
},
|
|
{
|
|
"entropy": 5.117262697219848,
|
|
"epoch": 3.5,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003810835403507662,
|
|
"loss": 4.6777,
|
|
"mean_token_accuracy": 0.24048301130533217,
|
|
"num_tokens": 83525251.0,
|
|
"step": 36435
|
|
},
|
|
{
|
|
"entropy": 5.2000573635101315,
|
|
"epoch": 3.500480307396734,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038105330529279285,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.2466490387916565,
|
|
"num_tokens": 83536937.0,
|
|
"step": 36440
|
|
},
|
|
{
|
|
"entropy": 5.16560697555542,
|
|
"epoch": 3.5009606147934678,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003810230677725767,
|
|
"loss": 4.6722,
|
|
"mean_token_accuracy": 0.24593015313148497,
|
|
"num_tokens": 83549686.0,
|
|
"step": 36445
|
|
},
|
|
{
|
|
"entropy": 5.179725694656372,
|
|
"epoch": 3.5014409221902016,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038099282779081975,
|
|
"loss": 4.6952,
|
|
"mean_token_accuracy": 0.2432386487722397,
|
|
"num_tokens": 83561774.0,
|
|
"step": 36450
|
|
},
|
|
{
|
|
"entropy": 5.184039115905762,
|
|
"epoch": 3.5019212295869355,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038096258534822404,
|
|
"loss": 4.7083,
|
|
"mean_token_accuracy": 0.24693856835365297,
|
|
"num_tokens": 83573236.0,
|
|
"step": 36455
|
|
},
|
|
{
|
|
"entropy": 5.138269281387329,
|
|
"epoch": 3.5024015369836694,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038093234044549174,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.248000767827034,
|
|
"num_tokens": 83584899.0,
|
|
"step": 36460
|
|
},
|
|
{
|
|
"entropy": 5.126636171340943,
|
|
"epoch": 3.5028818443804033,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038090209308332503,
|
|
"loss": 4.6985,
|
|
"mean_token_accuracy": 0.2547021463513374,
|
|
"num_tokens": 83596880.0,
|
|
"step": 36465
|
|
},
|
|
{
|
|
"entropy": 5.118296194076538,
|
|
"epoch": 3.5033621517771376,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00038087184326242627,
|
|
"loss": 4.7027,
|
|
"mean_token_accuracy": 0.24538444131612777,
|
|
"num_tokens": 83608747.0,
|
|
"step": 36470
|
|
},
|
|
{
|
|
"entropy": 5.161462068557739,
|
|
"epoch": 3.503842459173871,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003808415909834976,
|
|
"loss": 4.701,
|
|
"mean_token_accuracy": 0.24944612085819245,
|
|
"num_tokens": 83619971.0,
|
|
"step": 36475
|
|
},
|
|
{
|
|
"entropy": 5.229179430007934,
|
|
"epoch": 3.5043227665706054,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038081133624724147,
|
|
"loss": 4.7669,
|
|
"mean_token_accuracy": 0.24733600169420242,
|
|
"num_tokens": 83631030.0,
|
|
"step": 36480
|
|
},
|
|
{
|
|
"entropy": 5.1685731410980225,
|
|
"epoch": 3.5048030739673393,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00038078107905436035,
|
|
"loss": 4.6353,
|
|
"mean_token_accuracy": 0.25250186771154404,
|
|
"num_tokens": 83642854.0,
|
|
"step": 36485
|
|
},
|
|
{
|
|
"entropy": 5.156263208389282,
|
|
"epoch": 3.505283381364073,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00038075081940555666,
|
|
"loss": 4.633,
|
|
"mean_token_accuracy": 0.2528383702039719,
|
|
"num_tokens": 83653669.0,
|
|
"step": 36490
|
|
},
|
|
{
|
|
"entropy": 5.1255772590637205,
|
|
"epoch": 3.505763688760807,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00038072055730153297,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.2513938769698143,
|
|
"num_tokens": 83665098.0,
|
|
"step": 36495
|
|
},
|
|
{
|
|
"entropy": 5.128404664993286,
|
|
"epoch": 3.506243996157541,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038069029274299184,
|
|
"loss": 4.6891,
|
|
"mean_token_accuracy": 0.2523076593875885,
|
|
"num_tokens": 83677494.0,
|
|
"step": 36500
|
|
},
|
|
{
|
|
"entropy": 5.123869371414185,
|
|
"epoch": 3.506724303554275,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003806600257306359,
|
|
"loss": 4.5992,
|
|
"mean_token_accuracy": 0.25861309468746185,
|
|
"num_tokens": 83689128.0,
|
|
"step": 36505
|
|
},
|
|
{
|
|
"entropy": 5.03509488105774,
|
|
"epoch": 3.5072046109510087,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00038062975626516806,
|
|
"loss": 4.5938,
|
|
"mean_token_accuracy": 0.258887679874897,
|
|
"num_tokens": 83700113.0,
|
|
"step": 36510
|
|
},
|
|
{
|
|
"entropy": 5.175722217559814,
|
|
"epoch": 3.5076849183477425,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038059948434729086,
|
|
"loss": 4.6356,
|
|
"mean_token_accuracy": 0.2502396658062935,
|
|
"num_tokens": 83709549.0,
|
|
"step": 36515
|
|
},
|
|
{
|
|
"entropy": 5.1514781475067135,
|
|
"epoch": 3.5081652257444764,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038056920997770713,
|
|
"loss": 4.6844,
|
|
"mean_token_accuracy": 0.24719505459070207,
|
|
"num_tokens": 83720912.0,
|
|
"step": 36520
|
|
},
|
|
{
|
|
"entropy": 5.1345288276672365,
|
|
"epoch": 3.5086455331412103,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038053893315711997,
|
|
"loss": 4.6995,
|
|
"mean_token_accuracy": 0.24737947434186935,
|
|
"num_tokens": 83732885.0,
|
|
"step": 36525
|
|
},
|
|
{
|
|
"entropy": 5.18639817237854,
|
|
"epoch": 3.509125840537944,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000380508653886232,
|
|
"loss": 4.7104,
|
|
"mean_token_accuracy": 0.24400797188282014,
|
|
"num_tokens": 83744521.0,
|
|
"step": 36530
|
|
},
|
|
{
|
|
"entropy": 5.176835203170777,
|
|
"epoch": 3.509606147934678,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003804783721657465,
|
|
"loss": 4.7241,
|
|
"mean_token_accuracy": 0.25506533980369567,
|
|
"num_tokens": 83756184.0,
|
|
"step": 36535
|
|
},
|
|
{
|
|
"entropy": 5.0843421459198,
|
|
"epoch": 3.510086455331412,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038044808799636635,
|
|
"loss": 4.6537,
|
|
"mean_token_accuracy": 0.2555441617965698,
|
|
"num_tokens": 83767643.0,
|
|
"step": 36540
|
|
},
|
|
{
|
|
"entropy": 5.062747955322266,
|
|
"epoch": 3.5105667627281463,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003804178013787947,
|
|
"loss": 4.5843,
|
|
"mean_token_accuracy": 0.2597993269562721,
|
|
"num_tokens": 83778326.0,
|
|
"step": 36545
|
|
},
|
|
{
|
|
"entropy": 5.131123685836792,
|
|
"epoch": 3.5110470701248797,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00038038751231373477,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.2473263680934906,
|
|
"num_tokens": 83790396.0,
|
|
"step": 36550
|
|
},
|
|
{
|
|
"entropy": 5.164857816696167,
|
|
"epoch": 3.511527377521614,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00038035722080188974,
|
|
"loss": 4.6924,
|
|
"mean_token_accuracy": 0.2520906746387482,
|
|
"num_tokens": 83803199.0,
|
|
"step": 36555
|
|
},
|
|
{
|
|
"entropy": 5.150714015960693,
|
|
"epoch": 3.5120076849183475,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00038032692684396286,
|
|
"loss": 4.6556,
|
|
"mean_token_accuracy": 0.25012213438749314,
|
|
"num_tokens": 83815184.0,
|
|
"step": 36560
|
|
},
|
|
{
|
|
"entropy": 5.27449860572815,
|
|
"epoch": 3.512487992315082,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003802966304406575,
|
|
"loss": 4.7668,
|
|
"mean_token_accuracy": 0.24797675013542175,
|
|
"num_tokens": 83827627.0,
|
|
"step": 36565
|
|
},
|
|
{
|
|
"entropy": 5.1256676197052,
|
|
"epoch": 3.5129682997118157,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038026633159267707,
|
|
"loss": 4.6591,
|
|
"mean_token_accuracy": 0.25583763271570203,
|
|
"num_tokens": 83840771.0,
|
|
"step": 36570
|
|
},
|
|
{
|
|
"entropy": 5.1351401805877686,
|
|
"epoch": 3.5134486071085496,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038023603030072503,
|
|
"loss": 4.6372,
|
|
"mean_token_accuracy": 0.2553201332688332,
|
|
"num_tokens": 83851311.0,
|
|
"step": 36575
|
|
},
|
|
{
|
|
"entropy": 5.127445363998413,
|
|
"epoch": 3.5139289145052834,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003802057265655048,
|
|
"loss": 4.7103,
|
|
"mean_token_accuracy": 0.2524801030755043,
|
|
"num_tokens": 83863887.0,
|
|
"step": 36580
|
|
},
|
|
{
|
|
"entropy": 5.190648603439331,
|
|
"epoch": 3.5144092219020173,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00038017542038772003,
|
|
"loss": 4.6745,
|
|
"mean_token_accuracy": 0.24314107298851012,
|
|
"num_tokens": 83874183.0,
|
|
"step": 36585
|
|
},
|
|
{
|
|
"entropy": 5.124621486663818,
|
|
"epoch": 3.514889529298751,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038014511176807426,
|
|
"loss": 4.699,
|
|
"mean_token_accuracy": 0.24625176936388016,
|
|
"num_tokens": 83885973.0,
|
|
"step": 36590
|
|
},
|
|
{
|
|
"entropy": 5.076137924194336,
|
|
"epoch": 3.515369836695485,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00038011480070727124,
|
|
"loss": 4.6036,
|
|
"mean_token_accuracy": 0.253371998667717,
|
|
"num_tokens": 83897808.0,
|
|
"step": 36595
|
|
},
|
|
{
|
|
"entropy": 5.1509222984313965,
|
|
"epoch": 3.515850144092219,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003800844872060147,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.24924684911966324,
|
|
"num_tokens": 83909876.0,
|
|
"step": 36600
|
|
},
|
|
{
|
|
"entropy": 5.064430189132691,
|
|
"epoch": 3.516330451488953,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00038005417126500836,
|
|
"loss": 4.651,
|
|
"mean_token_accuracy": 0.24978163987398147,
|
|
"num_tokens": 83921181.0,
|
|
"step": 36605
|
|
},
|
|
{
|
|
"entropy": 5.175269937515258,
|
|
"epoch": 3.5168107588856867,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038002385288495613,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.2517410606145859,
|
|
"num_tokens": 83932946.0,
|
|
"step": 36610
|
|
},
|
|
{
|
|
"entropy": 5.112098836898804,
|
|
"epoch": 3.5172910662824206,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003799935320665619,
|
|
"loss": 4.653,
|
|
"mean_token_accuracy": 0.25096690803766253,
|
|
"num_tokens": 83945439.0,
|
|
"step": 36615
|
|
},
|
|
{
|
|
"entropy": 5.126339626312256,
|
|
"epoch": 3.517771373679155,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00037996320881052956,
|
|
"loss": 4.7122,
|
|
"mean_token_accuracy": 0.24606149792671203,
|
|
"num_tokens": 83956979.0,
|
|
"step": 36620
|
|
},
|
|
{
|
|
"entropy": 5.207331037521362,
|
|
"epoch": 3.5182516810758884,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00037993288311756327,
|
|
"loss": 4.7488,
|
|
"mean_token_accuracy": 0.24199920296669006,
|
|
"num_tokens": 83968371.0,
|
|
"step": 36625
|
|
},
|
|
{
|
|
"entropy": 5.19095401763916,
|
|
"epoch": 3.5187319884726227,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000379902554988367,
|
|
"loss": 4.6662,
|
|
"mean_token_accuracy": 0.2475794419646263,
|
|
"num_tokens": 83980815.0,
|
|
"step": 36630
|
|
},
|
|
{
|
|
"entropy": 5.10478777885437,
|
|
"epoch": 3.519212295869356,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003798722244236449,
|
|
"loss": 4.6387,
|
|
"mean_token_accuracy": 0.24702137261629104,
|
|
"num_tokens": 83991764.0,
|
|
"step": 36635
|
|
},
|
|
{
|
|
"entropy": 5.260344743728638,
|
|
"epoch": 3.5196926032660905,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003798418914241011,
|
|
"loss": 4.7982,
|
|
"mean_token_accuracy": 0.23780137300491333,
|
|
"num_tokens": 84003423.0,
|
|
"step": 36640
|
|
},
|
|
{
|
|
"entropy": 5.119483518600464,
|
|
"epoch": 3.5201729106628243,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00037981155599043997,
|
|
"loss": 4.6666,
|
|
"mean_token_accuracy": 0.2499799370765686,
|
|
"num_tokens": 84014431.0,
|
|
"step": 36645
|
|
},
|
|
{
|
|
"entropy": 5.147964811325073,
|
|
"epoch": 3.520653218059558,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003797812181233657,
|
|
"loss": 4.6567,
|
|
"mean_token_accuracy": 0.249834281206131,
|
|
"num_tokens": 84026024.0,
|
|
"step": 36650
|
|
},
|
|
{
|
|
"entropy": 5.179805850982666,
|
|
"epoch": 3.521133525456292,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00037975087782358264,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.24934693425893784,
|
|
"num_tokens": 84037533.0,
|
|
"step": 36655
|
|
},
|
|
{
|
|
"entropy": 5.238677501678467,
|
|
"epoch": 3.521613832853026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003797205350917953,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.2481730967760086,
|
|
"num_tokens": 84049065.0,
|
|
"step": 36660
|
|
},
|
|
{
|
|
"entropy": 5.1446747303009035,
|
|
"epoch": 3.52209414024976,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00037969018992870814,
|
|
"loss": 4.6415,
|
|
"mean_token_accuracy": 0.25329615324735644,
|
|
"num_tokens": 84060339.0,
|
|
"step": 36665
|
|
},
|
|
{
|
|
"entropy": 5.121104574203491,
|
|
"epoch": 3.5225744476464937,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037965984233502553,
|
|
"loss": 4.6952,
|
|
"mean_token_accuracy": 0.2552557811141014,
|
|
"num_tokens": 84071470.0,
|
|
"step": 36670
|
|
},
|
|
{
|
|
"entropy": 5.168283891677857,
|
|
"epoch": 3.5230547550432276,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003796294923114522,
|
|
"loss": 4.7381,
|
|
"mean_token_accuracy": 0.23904004991054534,
|
|
"num_tokens": 84082831.0,
|
|
"step": 36675
|
|
},
|
|
{
|
|
"entropy": 5.178862714767456,
|
|
"epoch": 3.5235350624399615,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00037959913985869276,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.25067162960767747,
|
|
"num_tokens": 84094547.0,
|
|
"step": 36680
|
|
},
|
|
{
|
|
"entropy": 5.149774646759033,
|
|
"epoch": 3.5240153698366954,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00037956878497745185,
|
|
"loss": 4.6269,
|
|
"mean_token_accuracy": 0.24804565459489822,
|
|
"num_tokens": 84106117.0,
|
|
"step": 36685
|
|
},
|
|
{
|
|
"entropy": 5.051564168930054,
|
|
"epoch": 3.5244956772334293,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003795384276684343,
|
|
"loss": 4.5897,
|
|
"mean_token_accuracy": 0.25224923640489577,
|
|
"num_tokens": 84116654.0,
|
|
"step": 36690
|
|
},
|
|
{
|
|
"entropy": 5.1446342945098875,
|
|
"epoch": 3.524975984630163,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003795080679323449,
|
|
"loss": 4.7192,
|
|
"mean_token_accuracy": 0.24987988471984862,
|
|
"num_tokens": 84128217.0,
|
|
"step": 36695
|
|
},
|
|
{
|
|
"entropy": 5.172293710708618,
|
|
"epoch": 3.525456292026897,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003794777057698884,
|
|
"loss": 4.672,
|
|
"mean_token_accuracy": 0.24763821065425873,
|
|
"num_tokens": 84139638.0,
|
|
"step": 36700
|
|
},
|
|
{
|
|
"entropy": 5.212976503372192,
|
|
"epoch": 3.5259365994236314,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003794473411817699,
|
|
"loss": 4.7302,
|
|
"mean_token_accuracy": 0.24519203305244447,
|
|
"num_tokens": 84150945.0,
|
|
"step": 36705
|
|
},
|
|
{
|
|
"entropy": 5.114077091217041,
|
|
"epoch": 3.526416906820365,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003794169741686942,
|
|
"loss": 4.6007,
|
|
"mean_token_accuracy": 0.25328188091516496,
|
|
"num_tokens": 84163443.0,
|
|
"step": 36710
|
|
},
|
|
{
|
|
"entropy": 5.184221410751343,
|
|
"epoch": 3.526897214217099,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003793866047313665,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.24440863728523254,
|
|
"num_tokens": 84174291.0,
|
|
"step": 36715
|
|
},
|
|
{
|
|
"entropy": 5.102268981933594,
|
|
"epoch": 3.527377521613833,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00037935623287049173,
|
|
"loss": 4.6272,
|
|
"mean_token_accuracy": 0.25858729630708693,
|
|
"num_tokens": 84185331.0,
|
|
"step": 36720
|
|
},
|
|
{
|
|
"entropy": 5.032703495025634,
|
|
"epoch": 3.527857829010567,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00037932585858677515,
|
|
"loss": 4.621,
|
|
"mean_token_accuracy": 0.2545526295900345,
|
|
"num_tokens": 84196930.0,
|
|
"step": 36725
|
|
},
|
|
{
|
|
"entropy": 5.069949388504028,
|
|
"epoch": 3.5283381364073008,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00037929548188092186,
|
|
"loss": 4.6129,
|
|
"mean_token_accuracy": 0.25544115602970124,
|
|
"num_tokens": 84208635.0,
|
|
"step": 36730
|
|
},
|
|
{
|
|
"entropy": 5.180825424194336,
|
|
"epoch": 3.5288184438040346,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037926510275363725,
|
|
"loss": 4.6552,
|
|
"mean_token_accuracy": 0.2546259880065918,
|
|
"num_tokens": 84219392.0,
|
|
"step": 36735
|
|
},
|
|
{
|
|
"entropy": 5.09009690284729,
|
|
"epoch": 3.5292987512007685,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003792347212056265,
|
|
"loss": 4.5969,
|
|
"mean_token_accuracy": 0.2553680881857872,
|
|
"num_tokens": 84230540.0,
|
|
"step": 36740
|
|
},
|
|
{
|
|
"entropy": 5.176604223251343,
|
|
"epoch": 3.5297790585975024,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00037920433723759506,
|
|
"loss": 4.6505,
|
|
"mean_token_accuracy": 0.2484718978404999,
|
|
"num_tokens": 84241339.0,
|
|
"step": 36745
|
|
},
|
|
{
|
|
"entropy": 5.133118915557861,
|
|
"epoch": 3.5302593659942363,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003791739508502483,
|
|
"loss": 4.6769,
|
|
"mean_token_accuracy": 0.250851546227932,
|
|
"num_tokens": 84252658.0,
|
|
"step": 36750
|
|
},
|
|
{
|
|
"entropy": 5.087225341796875,
|
|
"epoch": 3.53073967339097,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00037914356204429183,
|
|
"loss": 4.6561,
|
|
"mean_token_accuracy": 0.24693385660648345,
|
|
"num_tokens": 84264522.0,
|
|
"step": 36755
|
|
},
|
|
{
|
|
"entropy": 5.1970597267150875,
|
|
"epoch": 3.531219980787704,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00037911317082043103,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.24816944003105162,
|
|
"num_tokens": 84276330.0,
|
|
"step": 36760
|
|
},
|
|
{
|
|
"entropy": 5.247682380676269,
|
|
"epoch": 3.531700288184438,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003790827771793715,
|
|
"loss": 4.7488,
|
|
"mean_token_accuracy": 0.24413173645734787,
|
|
"num_tokens": 84287288.0,
|
|
"step": 36765
|
|
},
|
|
{
|
|
"entropy": 5.139055395126343,
|
|
"epoch": 3.532180595581172,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000379052381121819,
|
|
"loss": 4.6144,
|
|
"mean_token_accuracy": 0.2524954631924629,
|
|
"num_tokens": 84297472.0,
|
|
"step": 36770
|
|
},
|
|
{
|
|
"entropy": 5.052327680587768,
|
|
"epoch": 3.5326609029779057,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003790219826484792,
|
|
"loss": 4.597,
|
|
"mean_token_accuracy": 0.2570840910077095,
|
|
"num_tokens": 84308726.0,
|
|
"step": 36775
|
|
},
|
|
{
|
|
"entropy": 5.1516461849212645,
|
|
"epoch": 3.53314121037464,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00037899158176005784,
|
|
"loss": 4.7705,
|
|
"mean_token_accuracy": 0.2429365411400795,
|
|
"num_tokens": 84320439.0,
|
|
"step": 36780
|
|
},
|
|
{
|
|
"entropy": 5.234724617004394,
|
|
"epoch": 3.5336215177713735,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00037896117845726067,
|
|
"loss": 4.7443,
|
|
"mean_token_accuracy": 0.24953216761350633,
|
|
"num_tokens": 84331321.0,
|
|
"step": 36785
|
|
},
|
|
{
|
|
"entropy": 5.253979110717774,
|
|
"epoch": 3.534101825168108,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00037893077274079375,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.24280915558338165,
|
|
"num_tokens": 84344095.0,
|
|
"step": 36790
|
|
},
|
|
{
|
|
"entropy": 5.15471510887146,
|
|
"epoch": 3.5345821325648417,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037890036461136285,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.2421349734067917,
|
|
"num_tokens": 84355254.0,
|
|
"step": 36795
|
|
},
|
|
{
|
|
"entropy": 5.074810266494751,
|
|
"epoch": 3.5350624399615755,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000378869954069674,
|
|
"loss": 4.5555,
|
|
"mean_token_accuracy": 0.25804136097431185,
|
|
"num_tokens": 84365739.0,
|
|
"step": 36800
|
|
},
|
|
{
|
|
"entropy": 5.1287922859191895,
|
|
"epoch": 3.5355427473583094,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003788395411164332,
|
|
"loss": 4.7415,
|
|
"mean_token_accuracy": 0.24839794933795928,
|
|
"num_tokens": 84377881.0,
|
|
"step": 36805
|
|
},
|
|
{
|
|
"entropy": 5.190157175064087,
|
|
"epoch": 3.5360230547550433,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00037880912575234666,
|
|
"loss": 4.7,
|
|
"mean_token_accuracy": 0.250156344473362,
|
|
"num_tokens": 84388748.0,
|
|
"step": 36810
|
|
},
|
|
{
|
|
"entropy": 5.12593297958374,
|
|
"epoch": 3.536503362151777,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003787787079781205,
|
|
"loss": 4.659,
|
|
"mean_token_accuracy": 0.2486904412508011,
|
|
"num_tokens": 84399056.0,
|
|
"step": 36815
|
|
},
|
|
{
|
|
"entropy": 5.211796283721924,
|
|
"epoch": 3.536983669548511,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003787482877944608,
|
|
"loss": 4.7044,
|
|
"mean_token_accuracy": 0.2474951684474945,
|
|
"num_tokens": 84411441.0,
|
|
"step": 36820
|
|
},
|
|
{
|
|
"entropy": 5.207859182357788,
|
|
"epoch": 3.537463976945245,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000378717865202074,
|
|
"loss": 4.7534,
|
|
"mean_token_accuracy": 0.23659278601408004,
|
|
"num_tokens": 84423430.0,
|
|
"step": 36825
|
|
},
|
|
{
|
|
"entropy": 5.229129886627197,
|
|
"epoch": 3.537944284341979,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037868744020166635,
|
|
"loss": 4.807,
|
|
"mean_token_accuracy": 0.2413765698671341,
|
|
"num_tokens": 84435002.0,
|
|
"step": 36830
|
|
},
|
|
{
|
|
"entropy": 5.127749872207642,
|
|
"epoch": 3.5384245917387127,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00037865701279394414,
|
|
"loss": 4.6484,
|
|
"mean_token_accuracy": 0.25497528463602065,
|
|
"num_tokens": 84446858.0,
|
|
"step": 36835
|
|
},
|
|
{
|
|
"entropy": 5.1217851638793945,
|
|
"epoch": 3.5389048991354466,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00037862658297961393,
|
|
"loss": 4.6477,
|
|
"mean_token_accuracy": 0.2571419522166252,
|
|
"num_tokens": 84457603.0,
|
|
"step": 36840
|
|
},
|
|
{
|
|
"entropy": 5.17094931602478,
|
|
"epoch": 3.5393852065321805,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003785961507593823,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.2473358228802681,
|
|
"num_tokens": 84468755.0,
|
|
"step": 36845
|
|
},
|
|
{
|
|
"entropy": 5.132905006408691,
|
|
"epoch": 3.5398655139289144,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003785657161339555,
|
|
"loss": 4.6521,
|
|
"mean_token_accuracy": 0.25123917162418363,
|
|
"num_tokens": 84480248.0,
|
|
"step": 36850
|
|
},
|
|
{
|
|
"entropy": 5.175951099395752,
|
|
"epoch": 3.5403458213256487,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00037853527910404033,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.24438573569059371,
|
|
"num_tokens": 84493290.0,
|
|
"step": 36855
|
|
},
|
|
{
|
|
"entropy": 5.135014438629151,
|
|
"epoch": 3.540826128722382,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003785048396703435,
|
|
"loss": 4.6885,
|
|
"mean_token_accuracy": 0.24517594873905182,
|
|
"num_tokens": 84505353.0,
|
|
"step": 36860
|
|
},
|
|
{
|
|
"entropy": 5.246148920059204,
|
|
"epoch": 3.5413064361191164,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00037847439783357165,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.24331486970186234,
|
|
"num_tokens": 84517871.0,
|
|
"step": 36865
|
|
},
|
|
{
|
|
"entropy": 5.100400829315186,
|
|
"epoch": 3.54178674351585,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003784439535944314,
|
|
"loss": 4.5618,
|
|
"mean_token_accuracy": 0.2536443188786507,
|
|
"num_tokens": 84528513.0,
|
|
"step": 36870
|
|
},
|
|
{
|
|
"entropy": 5.245386266708374,
|
|
"epoch": 3.542267050912584,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003784135069536298,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.23745981454849244,
|
|
"num_tokens": 84539990.0,
|
|
"step": 36875
|
|
},
|
|
{
|
|
"entropy": 5.116847658157349,
|
|
"epoch": 3.542747358309318,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00037838305791187363,
|
|
"loss": 4.6169,
|
|
"mean_token_accuracy": 0.25171771794557574,
|
|
"num_tokens": 84551218.0,
|
|
"step": 36880
|
|
},
|
|
{
|
|
"entropy": 5.098001194000244,
|
|
"epoch": 3.543227665706052,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00037835260646986986,
|
|
"loss": 4.5722,
|
|
"mean_token_accuracy": 0.25188914984464644,
|
|
"num_tokens": 84561672.0,
|
|
"step": 36885
|
|
},
|
|
{
|
|
"entropy": 5.057216644287109,
|
|
"epoch": 3.543707973102786,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00037832215262832545,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.25142970532178877,
|
|
"num_tokens": 84574115.0,
|
|
"step": 36890
|
|
},
|
|
{
|
|
"entropy": 5.133550691604614,
|
|
"epoch": 3.5441882804995197,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003782916963879474,
|
|
"loss": 4.6916,
|
|
"mean_token_accuracy": 0.24302870780229568,
|
|
"num_tokens": 84586014.0,
|
|
"step": 36895
|
|
},
|
|
{
|
|
"entropy": 5.107852935791016,
|
|
"epoch": 3.5446685878962536,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000378261237749443,
|
|
"loss": 4.6516,
|
|
"mean_token_accuracy": 0.25405346751213076,
|
|
"num_tokens": 84597720.0,
|
|
"step": 36900
|
|
},
|
|
{
|
|
"entropy": 5.068949174880982,
|
|
"epoch": 3.5451488952929875,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003782307767135192,
|
|
"loss": 4.6161,
|
|
"mean_token_accuracy": 0.2598327904939651,
|
|
"num_tokens": 84609610.0,
|
|
"step": 36905
|
|
},
|
|
{
|
|
"entropy": 5.10055980682373,
|
|
"epoch": 3.5456292026897214,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00037820031328088325,
|
|
"loss": 4.6547,
|
|
"mean_token_accuracy": 0.25791182070970536,
|
|
"num_tokens": 84619806.0,
|
|
"step": 36910
|
|
},
|
|
{
|
|
"entropy": 5.0549506664276125,
|
|
"epoch": 3.5461095100864553,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003781698474522425,
|
|
"loss": 4.5953,
|
|
"mean_token_accuracy": 0.2546772837638855,
|
|
"num_tokens": 84631030.0,
|
|
"step": 36915
|
|
},
|
|
{
|
|
"entropy": 5.128772878646851,
|
|
"epoch": 3.546589817483189,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00037813937922830435,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.2477383628487587,
|
|
"num_tokens": 84643914.0,
|
|
"step": 36920
|
|
},
|
|
{
|
|
"entropy": 5.1295738697052,
|
|
"epoch": 3.547070124879923,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037810890860977595,
|
|
"loss": 4.639,
|
|
"mean_token_accuracy": 0.24663596153259276,
|
|
"num_tokens": 84655055.0,
|
|
"step": 36925
|
|
},
|
|
{
|
|
"entropy": 5.119801616668701,
|
|
"epoch": 3.547550432276657,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00037807843559736494,
|
|
"loss": 4.6881,
|
|
"mean_token_accuracy": 0.24776885509490967,
|
|
"num_tokens": 84667840.0,
|
|
"step": 36930
|
|
},
|
|
{
|
|
"entropy": 5.098639392852784,
|
|
"epoch": 3.5480307396733908,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037804796019177874,
|
|
"loss": 4.6473,
|
|
"mean_token_accuracy": 0.24852166771888734,
|
|
"num_tokens": 84678412.0,
|
|
"step": 36935
|
|
},
|
|
{
|
|
"entropy": 5.0642622947692875,
|
|
"epoch": 3.548511047070125,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003780174823937248,
|
|
"loss": 4.5931,
|
|
"mean_token_accuracy": 0.2600286066532135,
|
|
"num_tokens": 84688725.0,
|
|
"step": 36940
|
|
},
|
|
{
|
|
"entropy": 5.20031213760376,
|
|
"epoch": 3.5489913544668585,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00037798700220391087,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.24561489522457122,
|
|
"num_tokens": 84702489.0,
|
|
"step": 36945
|
|
},
|
|
{
|
|
"entropy": 5.0905585289001465,
|
|
"epoch": 3.549471661863593,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00037795651962304456,
|
|
"loss": 4.5537,
|
|
"mean_token_accuracy": 0.26570878326892855,
|
|
"num_tokens": 84712933.0,
|
|
"step": 36950
|
|
},
|
|
{
|
|
"entropy": 5.0839760303497314,
|
|
"epoch": 3.5499519692603267,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037792603465183354,
|
|
"loss": 4.6643,
|
|
"mean_token_accuracy": 0.24652693122625352,
|
|
"num_tokens": 84723540.0,
|
|
"step": 36955
|
|
},
|
|
{
|
|
"entropy": 5.15959095954895,
|
|
"epoch": 3.5504322766570606,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003778955472909857,
|
|
"loss": 4.7485,
|
|
"mean_token_accuracy": 0.24893069714307786,
|
|
"num_tokens": 84735671.0,
|
|
"step": 36960
|
|
},
|
|
{
|
|
"entropy": 5.2573846817016605,
|
|
"epoch": 3.5509125840537945,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00037786505754120874,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.2344299226999283,
|
|
"num_tokens": 84746719.0,
|
|
"step": 36965
|
|
},
|
|
{
|
|
"entropy": 5.1747682094573975,
|
|
"epoch": 3.5513928914505284,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00037783456540321065,
|
|
"loss": 4.7475,
|
|
"mean_token_accuracy": 0.2404470771551132,
|
|
"num_tokens": 84758774.0,
|
|
"step": 36970
|
|
},
|
|
{
|
|
"entropy": 5.134488582611084,
|
|
"epoch": 3.5518731988472623,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00037780407087769925,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.24662022441625595,
|
|
"num_tokens": 84771047.0,
|
|
"step": 36975
|
|
},
|
|
{
|
|
"entropy": 5.106885480880737,
|
|
"epoch": 3.552353506243996,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003777735739653826,
|
|
"loss": 4.6543,
|
|
"mean_token_accuracy": 0.25538571178913116,
|
|
"num_tokens": 84781249.0,
|
|
"step": 36980
|
|
},
|
|
{
|
|
"entropy": 5.063074016571045,
|
|
"epoch": 3.55283381364073,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003777430746669687,
|
|
"loss": 4.5654,
|
|
"mean_token_accuracy": 0.25336547642946244,
|
|
"num_tokens": 84791722.0,
|
|
"step": 36985
|
|
},
|
|
{
|
|
"entropy": 5.150617885589599,
|
|
"epoch": 3.553314121037464,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00037771257298316573,
|
|
"loss": 4.7093,
|
|
"mean_token_accuracy": 0.25027594715356827,
|
|
"num_tokens": 84804327.0,
|
|
"step": 36990
|
|
},
|
|
{
|
|
"entropy": 5.097036504745484,
|
|
"epoch": 3.553794428434198,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003776820689146818,
|
|
"loss": 4.6614,
|
|
"mean_token_accuracy": 0.2522004947066307,
|
|
"num_tokens": 84814381.0,
|
|
"step": 36995
|
|
},
|
|
{
|
|
"entropy": 5.0946571826934814,
|
|
"epoch": 3.5542747358309317,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00037765156246222513,
|
|
"loss": 4.6572,
|
|
"mean_token_accuracy": 0.2587950021028519,
|
|
"num_tokens": 84826274.0,
|
|
"step": 37000
|
|
},
|
|
{
|
|
"entropy": 5.149774503707886,
|
|
"epoch": 3.5547550432276656,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00037762105362650403,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.25111927539110185,
|
|
"num_tokens": 84838946.0,
|
|
"step": 37005
|
|
},
|
|
{
|
|
"entropy": 5.256749677658081,
|
|
"epoch": 3.5552353506243994,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00037759054240822675,
|
|
"loss": 4.7538,
|
|
"mean_token_accuracy": 0.23806524872779847,
|
|
"num_tokens": 84851767.0,
|
|
"step": 37010
|
|
},
|
|
{
|
|
"entropy": 5.088061857223511,
|
|
"epoch": 3.5557156580211338,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003775600288081018,
|
|
"loss": 4.6391,
|
|
"mean_token_accuracy": 0.2515964910387993,
|
|
"num_tokens": 84863712.0,
|
|
"step": 37015
|
|
},
|
|
{
|
|
"entropy": 5.086574745178223,
|
|
"epoch": 3.556195965417867,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003775295128268374,
|
|
"loss": 4.6119,
|
|
"mean_token_accuracy": 0.25897383540868757,
|
|
"num_tokens": 84875699.0,
|
|
"step": 37020
|
|
},
|
|
{
|
|
"entropy": 5.154344749450684,
|
|
"epoch": 3.5566762728146015,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00037749899446514216,
|
|
"loss": 4.6341,
|
|
"mean_token_accuracy": 0.2517706319689751,
|
|
"num_tokens": 84886772.0,
|
|
"step": 37025
|
|
},
|
|
{
|
|
"entropy": 5.076985788345337,
|
|
"epoch": 3.5571565802113354,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003774684737237247,
|
|
"loss": 4.6896,
|
|
"mean_token_accuracy": 0.2485234409570694,
|
|
"num_tokens": 84898501.0,
|
|
"step": 37030
|
|
},
|
|
{
|
|
"entropy": 5.2001220226287845,
|
|
"epoch": 3.5576368876080693,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003774379506032935,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.24343463629484177,
|
|
"num_tokens": 84908418.0,
|
|
"step": 37035
|
|
},
|
|
{
|
|
"entropy": 5.20690689086914,
|
|
"epoch": 3.558117195004803,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037740742510455726,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.24815598726272584,
|
|
"num_tokens": 84919792.0,
|
|
"step": 37040
|
|
},
|
|
{
|
|
"entropy": 5.123368883132935,
|
|
"epoch": 3.558597502401537,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003773768972282248,
|
|
"loss": 4.6833,
|
|
"mean_token_accuracy": 0.24967955499887468,
|
|
"num_tokens": 84931606.0,
|
|
"step": 37045
|
|
},
|
|
{
|
|
"entropy": 5.0870442390441895,
|
|
"epoch": 3.559077809798271,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003773463669750046,
|
|
"loss": 4.6593,
|
|
"mean_token_accuracy": 0.2560706287622452,
|
|
"num_tokens": 84943099.0,
|
|
"step": 37050
|
|
},
|
|
{
|
|
"entropy": 5.223842000961303,
|
|
"epoch": 3.559558117195005,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003773158343456058,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.23661798387765884,
|
|
"num_tokens": 84954444.0,
|
|
"step": 37055
|
|
},
|
|
{
|
|
"entropy": 5.141842365264893,
|
|
"epoch": 3.5600384245917387,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00037728529934073714,
|
|
"loss": 4.6086,
|
|
"mean_token_accuracy": 0.25019207298755647,
|
|
"num_tokens": 84965342.0,
|
|
"step": 37060
|
|
},
|
|
{
|
|
"entropy": 5.110138082504273,
|
|
"epoch": 3.5605187319884726,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003772547619611075,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.24617805927991868,
|
|
"num_tokens": 84977685.0,
|
|
"step": 37065
|
|
},
|
|
{
|
|
"entropy": 5.218567419052124,
|
|
"epoch": 3.5609990393852065,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003772242222074259,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.23727849423885344,
|
|
"num_tokens": 84990148.0,
|
|
"step": 37070
|
|
},
|
|
{
|
|
"entropy": 5.24532732963562,
|
|
"epoch": 3.5614793467819403,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00037719368008040145,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.2440970465540886,
|
|
"num_tokens": 85001611.0,
|
|
"step": 37075
|
|
},
|
|
{
|
|
"entropy": 5.255483913421631,
|
|
"epoch": 3.561959654178674,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00037716313558074327,
|
|
"loss": 4.7903,
|
|
"mean_token_accuracy": 0.2423325687646866,
|
|
"num_tokens": 85012558.0,
|
|
"step": 37080
|
|
},
|
|
{
|
|
"entropy": 5.141080284118653,
|
|
"epoch": 3.562439961575408,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003771325887091603,
|
|
"loss": 4.6444,
|
|
"mean_token_accuracy": 0.25183549225330354,
|
|
"num_tokens": 85022102.0,
|
|
"step": 37085
|
|
},
|
|
{
|
|
"entropy": 5.072988891601563,
|
|
"epoch": 3.5629202689721424,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000377102039466362,
|
|
"loss": 4.5922,
|
|
"mean_token_accuracy": 0.25510152280330656,
|
|
"num_tokens": 85033497.0,
|
|
"step": 37090
|
|
},
|
|
{
|
|
"entropy": 5.115988254547119,
|
|
"epoch": 3.563400576368876,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003770714878530575,
|
|
"loss": 4.67,
|
|
"mean_token_accuracy": 0.2512365862727165,
|
|
"num_tokens": 85044938.0,
|
|
"step": 37095
|
|
},
|
|
{
|
|
"entropy": 5.159042549133301,
|
|
"epoch": 3.56388088376561,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00037704093386995607,
|
|
"loss": 4.656,
|
|
"mean_token_accuracy": 0.2543660819530487,
|
|
"num_tokens": 85056545.0,
|
|
"step": 37100
|
|
},
|
|
{
|
|
"entropy": 5.109947252273559,
|
|
"epoch": 3.5643611911623436,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003770103775177673,
|
|
"loss": 4.5904,
|
|
"mean_token_accuracy": 0.2618038848042488,
|
|
"num_tokens": 85067660.0,
|
|
"step": 37105
|
|
},
|
|
{
|
|
"entropy": 5.078806829452515,
|
|
"epoch": 3.564841498559078,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00037697981879720034,
|
|
"loss": 4.6196,
|
|
"mean_token_accuracy": 0.256471087038517,
|
|
"num_tokens": 85078813.0,
|
|
"step": 37110
|
|
},
|
|
{
|
|
"entropy": 5.1942634105682375,
|
|
"epoch": 3.565321805955812,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00037694925770896486,
|
|
"loss": 4.6903,
|
|
"mean_token_accuracy": 0.24239225685596466,
|
|
"num_tokens": 85089473.0,
|
|
"step": 37115
|
|
},
|
|
{
|
|
"entropy": 5.262401866912842,
|
|
"epoch": 3.5658021133525457,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00037691869425377037,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.24173736572265625,
|
|
"num_tokens": 85101325.0,
|
|
"step": 37120
|
|
},
|
|
{
|
|
"entropy": 5.21146068572998,
|
|
"epoch": 3.5662824207492796,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003768881284323263,
|
|
"loss": 4.7533,
|
|
"mean_token_accuracy": 0.24320413768291474,
|
|
"num_tokens": 85112601.0,
|
|
"step": 37125
|
|
},
|
|
{
|
|
"entropy": 5.06304817199707,
|
|
"epoch": 3.5667627281460135,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003768575602453426,
|
|
"loss": 4.657,
|
|
"mean_token_accuracy": 0.25838887095451357,
|
|
"num_tokens": 85123189.0,
|
|
"step": 37130
|
|
},
|
|
{
|
|
"entropy": 5.174142980575562,
|
|
"epoch": 3.5672430355427474,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00037682698969352876,
|
|
"loss": 4.6728,
|
|
"mean_token_accuracy": 0.24707877039909362,
|
|
"num_tokens": 85133575.0,
|
|
"step": 37135
|
|
},
|
|
{
|
|
"entropy": 5.214577674865723,
|
|
"epoch": 3.5677233429394812,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003767964167775946,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.2572357729077339,
|
|
"num_tokens": 85144549.0,
|
|
"step": 37140
|
|
},
|
|
{
|
|
"entropy": 5.16481647491455,
|
|
"epoch": 3.568203650336215,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003767658414982498,
|
|
"loss": 4.7213,
|
|
"mean_token_accuracy": 0.2490665927529335,
|
|
"num_tokens": 85155715.0,
|
|
"step": 37145
|
|
},
|
|
{
|
|
"entropy": 5.177290725708008,
|
|
"epoch": 3.568683957732949,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003767352638562044,
|
|
"loss": 4.7264,
|
|
"mean_token_accuracy": 0.24465162307024002,
|
|
"num_tokens": 85168268.0,
|
|
"step": 37150
|
|
},
|
|
{
|
|
"entropy": 5.147821426391602,
|
|
"epoch": 3.569164265129683,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003767046838521683,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.2446170285344124,
|
|
"num_tokens": 85181326.0,
|
|
"step": 37155
|
|
},
|
|
{
|
|
"entropy": 5.126044750213623,
|
|
"epoch": 3.5696445725264168,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003766741014868515,
|
|
"loss": 4.5827,
|
|
"mean_token_accuracy": 0.2533319443464279,
|
|
"num_tokens": 85191640.0,
|
|
"step": 37160
|
|
},
|
|
{
|
|
"entropy": 5.123963212966919,
|
|
"epoch": 3.570124879923151,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00037664351676096385,
|
|
"loss": 4.6416,
|
|
"mean_token_accuracy": 0.2534370839595795,
|
|
"num_tokens": 85202801.0,
|
|
"step": 37165
|
|
},
|
|
{
|
|
"entropy": 5.1081544876098635,
|
|
"epoch": 3.5706051873198845,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00037661292967521563,
|
|
"loss": 4.6044,
|
|
"mean_token_accuracy": 0.2458333194255829,
|
|
"num_tokens": 85213833.0,
|
|
"step": 37170
|
|
},
|
|
{
|
|
"entropy": 5.1435990810394285,
|
|
"epoch": 3.571085494716619,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037658234023031694,
|
|
"loss": 4.6389,
|
|
"mean_token_accuracy": 0.25971301198005675,
|
|
"num_tokens": 85223856.0,
|
|
"step": 37175
|
|
},
|
|
{
|
|
"entropy": 5.164723014831543,
|
|
"epoch": 3.5715658021133523,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003765517484269779,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.24810027331113815,
|
|
"num_tokens": 85236282.0,
|
|
"step": 37180
|
|
},
|
|
{
|
|
"entropy": 5.1162632465362545,
|
|
"epoch": 3.5720461095100866,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00037652115426590874,
|
|
"loss": 4.662,
|
|
"mean_token_accuracy": 0.24537387639284133,
|
|
"num_tokens": 85247430.0,
|
|
"step": 37185
|
|
},
|
|
{
|
|
"entropy": 5.2303080558776855,
|
|
"epoch": 3.5725264169068205,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00037649055774782,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.2446892037987709,
|
|
"num_tokens": 85259091.0,
|
|
"step": 37190
|
|
},
|
|
{
|
|
"entropy": 5.116909837722778,
|
|
"epoch": 3.5730067243035544,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003764599588734218,
|
|
"loss": 4.5983,
|
|
"mean_token_accuracy": 0.2612420290708542,
|
|
"num_tokens": 85270686.0,
|
|
"step": 37195
|
|
},
|
|
{
|
|
"entropy": 5.100501585006714,
|
|
"epoch": 3.5734870317002883,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00037642935764342454,
|
|
"loss": 4.6524,
|
|
"mean_token_accuracy": 0.24943666607141496,
|
|
"num_tokens": 85281419.0,
|
|
"step": 37200
|
|
},
|
|
{
|
|
"entropy": 5.14401535987854,
|
|
"epoch": 3.573967339097022,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003763987540585389,
|
|
"loss": 4.6946,
|
|
"mean_token_accuracy": 0.2468782514333725,
|
|
"num_tokens": 85293116.0,
|
|
"step": 37205
|
|
},
|
|
{
|
|
"entropy": 5.244361495971679,
|
|
"epoch": 3.574447646493756,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003763681481194752,
|
|
"loss": 4.7282,
|
|
"mean_token_accuracy": 0.24897717237472533,
|
|
"num_tokens": 85304567.0,
|
|
"step": 37210
|
|
},
|
|
{
|
|
"entropy": 5.121249675750732,
|
|
"epoch": 3.57492795389049,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00037633753982694413,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.2494424030184746,
|
|
"num_tokens": 85315947.0,
|
|
"step": 37215
|
|
},
|
|
{
|
|
"entropy": 5.129593467712402,
|
|
"epoch": 3.5754082612872238,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00037630692918165634,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.23928438127040863,
|
|
"num_tokens": 85327309.0,
|
|
"step": 37220
|
|
},
|
|
{
|
|
"entropy": 5.152043151855469,
|
|
"epoch": 3.5758885686839577,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003762763161843224,
|
|
"loss": 4.7417,
|
|
"mean_token_accuracy": 0.2492375046014786,
|
|
"num_tokens": 85339034.0,
|
|
"step": 37225
|
|
},
|
|
{
|
|
"entropy": 5.1603819847106935,
|
|
"epoch": 3.5763688760806915,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003762457008356531,
|
|
"loss": 4.6744,
|
|
"mean_token_accuracy": 0.25058733820915224,
|
|
"num_tokens": 85351764.0,
|
|
"step": 37230
|
|
},
|
|
{
|
|
"entropy": 5.092384338378906,
|
|
"epoch": 3.5768491834774254,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00037621508313635945,
|
|
"loss": 4.5948,
|
|
"mean_token_accuracy": 0.2584647238254547,
|
|
"num_tokens": 85363234.0,
|
|
"step": 37235
|
|
},
|
|
{
|
|
"entropy": 5.091730213165283,
|
|
"epoch": 3.5773294908741593,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003761844630871519,
|
|
"loss": 4.6068,
|
|
"mean_token_accuracy": 0.253431099653244,
|
|
"num_tokens": 85374148.0,
|
|
"step": 37240
|
|
},
|
|
{
|
|
"entropy": 5.095055389404297,
|
|
"epoch": 3.577809798270893,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003761538406887417,
|
|
"loss": 4.6016,
|
|
"mean_token_accuracy": 0.25920668840408323,
|
|
"num_tokens": 85385952.0,
|
|
"step": 37245
|
|
},
|
|
{
|
|
"entropy": 5.1800790309906,
|
|
"epoch": 3.5782901056676275,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003761232159418397,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.24721042215824127,
|
|
"num_tokens": 85396182.0,
|
|
"step": 37250
|
|
},
|
|
{
|
|
"entropy": 5.1466258525848385,
|
|
"epoch": 3.578770413064361,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003760925888471568,
|
|
"loss": 4.6427,
|
|
"mean_token_accuracy": 0.2495805263519287,
|
|
"num_tokens": 85408109.0,
|
|
"step": 37255
|
|
},
|
|
{
|
|
"entropy": 5.178024625778198,
|
|
"epoch": 3.5792507204610953,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003760619594054042,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.23722267597913743,
|
|
"num_tokens": 85420622.0,
|
|
"step": 37260
|
|
},
|
|
{
|
|
"entropy": 5.138596391677856,
|
|
"epoch": 3.579731027857829,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00037603132761729303,
|
|
"loss": 4.6148,
|
|
"mean_token_accuracy": 0.24835793823003768,
|
|
"num_tokens": 85431890.0,
|
|
"step": 37265
|
|
},
|
|
{
|
|
"entropy": 5.101442432403564,
|
|
"epoch": 3.580211335254563,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003760006934835344,
|
|
"loss": 4.6712,
|
|
"mean_token_accuracy": 0.2439521938562393,
|
|
"num_tokens": 85442953.0,
|
|
"step": 37270
|
|
},
|
|
{
|
|
"entropy": 5.1532763004302975,
|
|
"epoch": 3.580691642651297,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003759700570048396,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.2480493649840355,
|
|
"num_tokens": 85454125.0,
|
|
"step": 37275
|
|
},
|
|
{
|
|
"entropy": 5.2566242694854735,
|
|
"epoch": 3.581171950048031,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003759394181819199,
|
|
"loss": 4.7969,
|
|
"mean_token_accuracy": 0.240082249045372,
|
|
"num_tokens": 85465162.0,
|
|
"step": 37280
|
|
},
|
|
{
|
|
"entropy": 5.132875108718872,
|
|
"epoch": 3.5816522574447647,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00037590877701548667,
|
|
"loss": 4.5748,
|
|
"mean_token_accuracy": 0.2582107067108154,
|
|
"num_tokens": 85475316.0,
|
|
"step": 37285
|
|
},
|
|
{
|
|
"entropy": 5.195631790161133,
|
|
"epoch": 3.5821325648414986,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003758781335062512,
|
|
"loss": 4.7153,
|
|
"mean_token_accuracy": 0.2473758950829506,
|
|
"num_tokens": 85487138.0,
|
|
"step": 37290
|
|
},
|
|
{
|
|
"entropy": 5.198083162307739,
|
|
"epoch": 3.5826128722382324,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003758474876549251,
|
|
"loss": 4.6432,
|
|
"mean_token_accuracy": 0.24971177577972412,
|
|
"num_tokens": 85498141.0,
|
|
"step": 37295
|
|
},
|
|
{
|
|
"entropy": 5.057068729400635,
|
|
"epoch": 3.5830931796349663,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00037581683946221974,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.25410828590393064,
|
|
"num_tokens": 85510123.0,
|
|
"step": 37300
|
|
},
|
|
{
|
|
"entropy": 5.158492517471314,
|
|
"epoch": 3.5835734870317,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003757861889288467,
|
|
"loss": 4.7483,
|
|
"mean_token_accuracy": 0.2331512078642845,
|
|
"num_tokens": 85522003.0,
|
|
"step": 37305
|
|
},
|
|
{
|
|
"entropy": 5.209647083282471,
|
|
"epoch": 3.584053794428434,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00037575553605551765,
|
|
"loss": 4.7128,
|
|
"mean_token_accuracy": 0.24149379581212999,
|
|
"num_tokens": 85533400.0,
|
|
"step": 37310
|
|
},
|
|
{
|
|
"entropy": 5.099365854263306,
|
|
"epoch": 3.584534101825168,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00037572488084294423,
|
|
"loss": 4.5743,
|
|
"mean_token_accuracy": 0.2636786162853241,
|
|
"num_tokens": 85543393.0,
|
|
"step": 37315
|
|
},
|
|
{
|
|
"entropy": 5.033010959625244,
|
|
"epoch": 3.585014409221902,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00037569422329183824,
|
|
"loss": 4.6458,
|
|
"mean_token_accuracy": 0.2586492314934731,
|
|
"num_tokens": 85554596.0,
|
|
"step": 37320
|
|
},
|
|
{
|
|
"entropy": 5.170847082138062,
|
|
"epoch": 3.585494716618636,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003756635634029112,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.24278320819139482,
|
|
"num_tokens": 85566144.0,
|
|
"step": 37325
|
|
},
|
|
{
|
|
"entropy": 5.209268617630005,
|
|
"epoch": 3.5859750240153696,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037563290117687535,
|
|
"loss": 4.7153,
|
|
"mean_token_accuracy": 0.2515823632478714,
|
|
"num_tokens": 85576824.0,
|
|
"step": 37330
|
|
},
|
|
{
|
|
"entropy": 5.2447929859161375,
|
|
"epoch": 3.586455331412104,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003756022366144423,
|
|
"loss": 4.7338,
|
|
"mean_token_accuracy": 0.2437677338719368,
|
|
"num_tokens": 85588719.0,
|
|
"step": 37335
|
|
},
|
|
{
|
|
"entropy": 5.097217273712158,
|
|
"epoch": 3.586935638808838,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003755715697163239,
|
|
"loss": 4.5712,
|
|
"mean_token_accuracy": 0.25242692083120344,
|
|
"num_tokens": 85598783.0,
|
|
"step": 37340
|
|
},
|
|
{
|
|
"entropy": 5.139313364028931,
|
|
"epoch": 3.5874159462055717,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00037554090048323247,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.23892731070518494,
|
|
"num_tokens": 85610222.0,
|
|
"step": 37345
|
|
},
|
|
{
|
|
"entropy": 5.16374135017395,
|
|
"epoch": 3.5878962536023056,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00037551022891587976,
|
|
"loss": 4.6643,
|
|
"mean_token_accuracy": 0.253552682697773,
|
|
"num_tokens": 85620660.0,
|
|
"step": 37350
|
|
},
|
|
{
|
|
"entropy": 5.266082048416138,
|
|
"epoch": 3.5883765609990395,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00037547955501497806,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.23718490898609162,
|
|
"num_tokens": 85632466.0,
|
|
"step": 37355
|
|
},
|
|
{
|
|
"entropy": 5.289459276199341,
|
|
"epoch": 3.5888568683957733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003754488787812394,
|
|
"loss": 4.8154,
|
|
"mean_token_accuracy": 0.2401794046163559,
|
|
"num_tokens": 85643343.0,
|
|
"step": 37360
|
|
},
|
|
{
|
|
"entropy": 5.094522905349732,
|
|
"epoch": 3.589337175792507,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003754182002153761,
|
|
"loss": 4.6309,
|
|
"mean_token_accuracy": 0.2559096500277519,
|
|
"num_tokens": 85655864.0,
|
|
"step": 37365
|
|
},
|
|
{
|
|
"entropy": 5.174360370635986,
|
|
"epoch": 3.589817483189241,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003753875193181003,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.24759117513895035,
|
|
"num_tokens": 85667729.0,
|
|
"step": 37370
|
|
},
|
|
{
|
|
"entropy": 5.2090081691741945,
|
|
"epoch": 3.590297790585975,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00037535683609012446,
|
|
"loss": 4.7558,
|
|
"mean_token_accuracy": 0.24654748141765595,
|
|
"num_tokens": 85679252.0,
|
|
"step": 37375
|
|
},
|
|
{
|
|
"entropy": 5.159677505493164,
|
|
"epoch": 3.590778097982709,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00037532615053216084,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.2549679785966873,
|
|
"num_tokens": 85690598.0,
|
|
"step": 37380
|
|
},
|
|
{
|
|
"entropy": 5.141229152679443,
|
|
"epoch": 3.5912584053794427,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000375295462644922,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.25590649992227554,
|
|
"num_tokens": 85703537.0,
|
|
"step": 37385
|
|
},
|
|
{
|
|
"entropy": 5.321116399765015,
|
|
"epoch": 3.5917387127761766,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003752647724291202,
|
|
"loss": 4.8848,
|
|
"mean_token_accuracy": 0.23192735761404037,
|
|
"num_tokens": 85717163.0,
|
|
"step": 37390
|
|
},
|
|
{
|
|
"entropy": 5.2406257629394535,
|
|
"epoch": 3.5922190201729105,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00037523407988546815,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.2435085266828537,
|
|
"num_tokens": 85728749.0,
|
|
"step": 37395
|
|
},
|
|
{
|
|
"entropy": 5.226823472976685,
|
|
"epoch": 3.592699327569645,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003752033850146785,
|
|
"loss": 4.7809,
|
|
"mean_token_accuracy": 0.24295933097600936,
|
|
"num_tokens": 85738653.0,
|
|
"step": 37400
|
|
},
|
|
{
|
|
"entropy": 5.133683919906616,
|
|
"epoch": 3.5931796349663783,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003751726878174637,
|
|
"loss": 4.6118,
|
|
"mean_token_accuracy": 0.2558001145720482,
|
|
"num_tokens": 85749244.0,
|
|
"step": 37405
|
|
},
|
|
{
|
|
"entropy": 5.169716215133667,
|
|
"epoch": 3.5936599423631126,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003751419882945365,
|
|
"loss": 4.6513,
|
|
"mean_token_accuracy": 0.2562285900115967,
|
|
"num_tokens": 85760314.0,
|
|
"step": 37410
|
|
},
|
|
{
|
|
"entropy": 5.1504593849182125,
|
|
"epoch": 3.594140249759846,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003751112864466097,
|
|
"loss": 4.6055,
|
|
"mean_token_accuracy": 0.257708865404129,
|
|
"num_tokens": 85771319.0,
|
|
"step": 37415
|
|
},
|
|
{
|
|
"entropy": 5.201339149475098,
|
|
"epoch": 3.5946205571565804,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003750805822743962,
|
|
"loss": 4.7075,
|
|
"mean_token_accuracy": 0.25284857898950575,
|
|
"num_tokens": 85781687.0,
|
|
"step": 37420
|
|
},
|
|
{
|
|
"entropy": 5.127151250839233,
|
|
"epoch": 3.5951008645533142,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003750498757786087,
|
|
"loss": 4.6535,
|
|
"mean_token_accuracy": 0.2490572914481163,
|
|
"num_tokens": 85793775.0,
|
|
"step": 37425
|
|
},
|
|
{
|
|
"entropy": 5.1449960231781,
|
|
"epoch": 3.595581171950048,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003750191669599602,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.24366853386163712,
|
|
"num_tokens": 85805404.0,
|
|
"step": 37430
|
|
},
|
|
{
|
|
"entropy": 5.193752765655518,
|
|
"epoch": 3.596061479346782,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003749884558191636,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.24579917192459105,
|
|
"num_tokens": 85818182.0,
|
|
"step": 37435
|
|
},
|
|
{
|
|
"entropy": 5.239299011230469,
|
|
"epoch": 3.596541786743516,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00037495774235693193,
|
|
"loss": 4.6922,
|
|
"mean_token_accuracy": 0.24539858400821685,
|
|
"num_tokens": 85828747.0,
|
|
"step": 37440
|
|
},
|
|
{
|
|
"entropy": 5.176601600646973,
|
|
"epoch": 3.5970220941402498,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00037492702657397837,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.25047991424798965,
|
|
"num_tokens": 85839914.0,
|
|
"step": 37445
|
|
},
|
|
{
|
|
"entropy": 5.1510004043579105,
|
|
"epoch": 3.5975024015369836,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000374896308471016,
|
|
"loss": 4.6277,
|
|
"mean_token_accuracy": 0.2532875448465347,
|
|
"num_tokens": 85851252.0,
|
|
"step": 37450
|
|
},
|
|
{
|
|
"entropy": 5.059959125518799,
|
|
"epoch": 3.5979827089337175,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00037486558804875785,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.25870987474918367,
|
|
"num_tokens": 85863287.0,
|
|
"step": 37455
|
|
},
|
|
{
|
|
"entropy": 5.187087535858154,
|
|
"epoch": 3.5984630163304514,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003748348653079174,
|
|
"loss": 4.8126,
|
|
"mean_token_accuracy": 0.23964477628469466,
|
|
"num_tokens": 85874575.0,
|
|
"step": 37460
|
|
},
|
|
{
|
|
"entropy": 5.162721252441406,
|
|
"epoch": 3.5989433237271853,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00037480414024920777,
|
|
"loss": 4.6466,
|
|
"mean_token_accuracy": 0.25268933176994324,
|
|
"num_tokens": 85886267.0,
|
|
"step": 37465
|
|
},
|
|
{
|
|
"entropy": 5.130048990249634,
|
|
"epoch": 3.599423631123919,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003747734128733424,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.24540135860443116,
|
|
"num_tokens": 85897149.0,
|
|
"step": 37470
|
|
},
|
|
{
|
|
"entropy": 5.049158763885498,
|
|
"epoch": 3.5999039385206535,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003747426831810346,
|
|
"loss": 4.5153,
|
|
"mean_token_accuracy": 0.2637906983494759,
|
|
"num_tokens": 85909045.0,
|
|
"step": 37475
|
|
},
|
|
{
|
|
"entropy": 5.14667067527771,
|
|
"epoch": 3.600384245917387,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037471195117299796,
|
|
"loss": 4.6561,
|
|
"mean_token_accuracy": 0.2570159092545509,
|
|
"num_tokens": 85919795.0,
|
|
"step": 37480
|
|
},
|
|
{
|
|
"entropy": 5.1592622756958,
|
|
"epoch": 3.6008645533141213,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003746812168499458,
|
|
"loss": 4.6973,
|
|
"mean_token_accuracy": 0.2509178414940834,
|
|
"num_tokens": 85930348.0,
|
|
"step": 37485
|
|
},
|
|
{
|
|
"entropy": 5.2371128559112545,
|
|
"epoch": 3.6013448607108547,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003746504802125918,
|
|
"loss": 4.7992,
|
|
"mean_token_accuracy": 0.23799474984407426,
|
|
"num_tokens": 85941956.0,
|
|
"step": 37490
|
|
},
|
|
{
|
|
"entropy": 5.158709573745727,
|
|
"epoch": 3.601825168107589,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037461974126164953,
|
|
"loss": 4.6276,
|
|
"mean_token_accuracy": 0.2544237196445465,
|
|
"num_tokens": 85953208.0,
|
|
"step": 37495
|
|
},
|
|
{
|
|
"entropy": 5.161597013473511,
|
|
"epoch": 3.602305475504323,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00037458899999783267,
|
|
"loss": 4.7062,
|
|
"mean_token_accuracy": 0.24543848931789397,
|
|
"num_tokens": 85967527.0,
|
|
"step": 37500
|
|
},
|
|
{
|
|
"entropy": 5.168769454956054,
|
|
"epoch": 3.6027857829010568,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037455825642185504,
|
|
"loss": 4.6988,
|
|
"mean_token_accuracy": 0.24904909878969192,
|
|
"num_tokens": 85979013.0,
|
|
"step": 37505
|
|
},
|
|
{
|
|
"entropy": 5.151583862304688,
|
|
"epoch": 3.6032660902977907,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0003745275105344303,
|
|
"loss": 4.6782,
|
|
"mean_token_accuracy": 0.2521553710103035,
|
|
"num_tokens": 85990331.0,
|
|
"step": 37510
|
|
},
|
|
{
|
|
"entropy": 5.17903733253479,
|
|
"epoch": 3.6037463976945245,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003744967623362723,
|
|
"loss": 4.7302,
|
|
"mean_token_accuracy": 0.24367193281650543,
|
|
"num_tokens": 86001883.0,
|
|
"step": 37515
|
|
},
|
|
{
|
|
"entropy": 5.181974267959594,
|
|
"epoch": 3.6042267050912584,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003744660118280949,
|
|
"loss": 4.6987,
|
|
"mean_token_accuracy": 0.24515289515256883,
|
|
"num_tokens": 86013069.0,
|
|
"step": 37520
|
|
},
|
|
{
|
|
"entropy": 5.220540189743042,
|
|
"epoch": 3.6047070124879923,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000374435259010612,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.24258489459753035,
|
|
"num_tokens": 86026107.0,
|
|
"step": 37525
|
|
},
|
|
{
|
|
"entropy": 5.124682950973511,
|
|
"epoch": 3.605187319884726,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00037440450388453767,
|
|
"loss": 4.5986,
|
|
"mean_token_accuracy": 0.2609339222311974,
|
|
"num_tokens": 86036914.0,
|
|
"step": 37530
|
|
},
|
|
{
|
|
"entropy": 5.157058382034302,
|
|
"epoch": 3.60566762728146,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000374373746450586,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.24399060308933257,
|
|
"num_tokens": 86047922.0,
|
|
"step": 37535
|
|
},
|
|
{
|
|
"entropy": 5.148695182800293,
|
|
"epoch": 3.606147934678194,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00037434298670947097,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.24643142223358155,
|
|
"num_tokens": 86058843.0,
|
|
"step": 37540
|
|
},
|
|
{
|
|
"entropy": 5.154376697540283,
|
|
"epoch": 3.606628242074928,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037431222466190677,
|
|
"loss": 4.6154,
|
|
"mean_token_accuracy": 0.2540105000138283,
|
|
"num_tokens": 86069212.0,
|
|
"step": 37545
|
|
},
|
|
{
|
|
"entropy": 5.115748739242553,
|
|
"epoch": 3.6071085494716617,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00037428146030860765,
|
|
"loss": 4.6416,
|
|
"mean_token_accuracy": 0.2510204866528511,
|
|
"num_tokens": 86080952.0,
|
|
"step": 37550
|
|
},
|
|
{
|
|
"entropy": 5.062708377838135,
|
|
"epoch": 3.6075888568683956,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003742506936502878,
|
|
"loss": 4.6498,
|
|
"mean_token_accuracy": 0.2605688586831093,
|
|
"num_tokens": 86091976.0,
|
|
"step": 37555
|
|
},
|
|
{
|
|
"entropy": 5.08995680809021,
|
|
"epoch": 3.60806916426513,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003742199246876616,
|
|
"loss": 4.5823,
|
|
"mean_token_accuracy": 0.26198951005935667,
|
|
"num_tokens": 86103135.0,
|
|
"step": 37560
|
|
},
|
|
{
|
|
"entropy": 5.251928758621216,
|
|
"epoch": 3.6085494716618634,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00037418915342144333,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.2487704187631607,
|
|
"num_tokens": 86113495.0,
|
|
"step": 37565
|
|
},
|
|
{
|
|
"entropy": 5.1655467510223385,
|
|
"epoch": 3.6090297790585977,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003741583798523474,
|
|
"loss": 4.6807,
|
|
"mean_token_accuracy": 0.24500119537115098,
|
|
"num_tokens": 86125489.0,
|
|
"step": 37570
|
|
},
|
|
{
|
|
"entropy": 5.165794754028321,
|
|
"epoch": 3.6095100864553316,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003741276039810884,
|
|
"loss": 4.6735,
|
|
"mean_token_accuracy": 0.24416756480932236,
|
|
"num_tokens": 86136109.0,
|
|
"step": 37575
|
|
},
|
|
{
|
|
"entropy": 5.1512798309326175,
|
|
"epoch": 3.6099903938520654,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003740968258083808,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.2506870344281197,
|
|
"num_tokens": 86147375.0,
|
|
"step": 37580
|
|
},
|
|
{
|
|
"entropy": 5.138375949859619,
|
|
"epoch": 3.6104707012487993,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003740660453349391,
|
|
"loss": 4.6763,
|
|
"mean_token_accuracy": 0.2515379324555397,
|
|
"num_tokens": 86158277.0,
|
|
"step": 37585
|
|
},
|
|
{
|
|
"entropy": 5.2091114044189455,
|
|
"epoch": 3.610951008645533,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000374035262561478,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.2445091798901558,
|
|
"num_tokens": 86169280.0,
|
|
"step": 37590
|
|
},
|
|
{
|
|
"entropy": 5.206213426589966,
|
|
"epoch": 3.611431316042267,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037400447748871224,
|
|
"loss": 4.65,
|
|
"mean_token_accuracy": 0.25512263625860215,
|
|
"num_tokens": 86179918.0,
|
|
"step": 37595
|
|
},
|
|
{
|
|
"entropy": 5.0237898349761965,
|
|
"epoch": 3.611911623439001,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00037397369011735643,
|
|
"loss": 4.5185,
|
|
"mean_token_accuracy": 0.2649864986538887,
|
|
"num_tokens": 86192616.0,
|
|
"step": 37600
|
|
},
|
|
{
|
|
"entropy": 5.112986087799072,
|
|
"epoch": 3.612391930835735,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003739429004481254,
|
|
"loss": 4.6483,
|
|
"mean_token_accuracy": 0.24966765493154525,
|
|
"num_tokens": 86203797.0,
|
|
"step": 37605
|
|
},
|
|
{
|
|
"entropy": 5.089088249206543,
|
|
"epoch": 3.6128722382324687,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037391210848173413,
|
|
"loss": 4.6181,
|
|
"mean_token_accuracy": 0.2587459996342659,
|
|
"num_tokens": 86214408.0,
|
|
"step": 37610
|
|
},
|
|
{
|
|
"entropy": 5.1453431129455565,
|
|
"epoch": 3.6133525456292026,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037388131421889733,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.2503780201077461,
|
|
"num_tokens": 86226382.0,
|
|
"step": 37615
|
|
},
|
|
{
|
|
"entropy": 5.1997874736785885,
|
|
"epoch": 3.6138328530259365,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003738505176603301,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.25106500685214994,
|
|
"num_tokens": 86236962.0,
|
|
"step": 37620
|
|
},
|
|
{
|
|
"entropy": 5.093987083435058,
|
|
"epoch": 3.6143131604226704,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00037381971880674726,
|
|
"loss": 4.6071,
|
|
"mean_token_accuracy": 0.2586097940802574,
|
|
"num_tokens": 86248867.0,
|
|
"step": 37625
|
|
},
|
|
{
|
|
"entropy": 5.199598360061645,
|
|
"epoch": 3.6147934678194042,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037378891765886405,
|
|
"loss": 4.71,
|
|
"mean_token_accuracy": 0.24395191967487334,
|
|
"num_tokens": 86260264.0,
|
|
"step": 37630
|
|
},
|
|
{
|
|
"entropy": 5.18228440284729,
|
|
"epoch": 3.6152737752161386,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00037375811421739555,
|
|
"loss": 4.7205,
|
|
"mean_token_accuracy": 0.24101427048444748,
|
|
"num_tokens": 86271707.0,
|
|
"step": 37635
|
|
},
|
|
{
|
|
"entropy": 5.10465030670166,
|
|
"epoch": 3.615754082612872,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00037372730848305683,
|
|
"loss": 4.6218,
|
|
"mean_token_accuracy": 0.25362022370100024,
|
|
"num_tokens": 86282532.0,
|
|
"step": 37640
|
|
},
|
|
{
|
|
"entropy": 5.19888072013855,
|
|
"epoch": 3.6162343900096063,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00037369650045656315,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.24806123673915864,
|
|
"num_tokens": 86295256.0,
|
|
"step": 37645
|
|
},
|
|
{
|
|
"entropy": 5.154560947418213,
|
|
"epoch": 3.61671469740634,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00037366569013862986,
|
|
"loss": 4.6744,
|
|
"mean_token_accuracy": 0.25091775357723234,
|
|
"num_tokens": 86306326.0,
|
|
"step": 37650
|
|
},
|
|
{
|
|
"entropy": 5.064209985733032,
|
|
"epoch": 3.617195004803074,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0003736348775299722,
|
|
"loss": 4.579,
|
|
"mean_token_accuracy": 0.2637642875313759,
|
|
"num_tokens": 86317313.0,
|
|
"step": 37655
|
|
},
|
|
{
|
|
"entropy": 5.159987926483154,
|
|
"epoch": 3.617675312199808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00037360406263130556,
|
|
"loss": 4.6287,
|
|
"mean_token_accuracy": 0.25140618681907656,
|
|
"num_tokens": 86327139.0,
|
|
"step": 37660
|
|
},
|
|
{
|
|
"entropy": 5.10192551612854,
|
|
"epoch": 3.618155619596542,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00037357324544334537,
|
|
"loss": 4.6806,
|
|
"mean_token_accuracy": 0.24554832130670548,
|
|
"num_tokens": 86338743.0,
|
|
"step": 37665
|
|
},
|
|
{
|
|
"entropy": 5.185241556167602,
|
|
"epoch": 3.6186359269932757,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003735424259668072,
|
|
"loss": 4.7359,
|
|
"mean_token_accuracy": 0.24767012894153595,
|
|
"num_tokens": 86349790.0,
|
|
"step": 37670
|
|
},
|
|
{
|
|
"entropy": 5.182073545455933,
|
|
"epoch": 3.6191162343900096,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003735116042024064,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.2473321482539177,
|
|
"num_tokens": 86361689.0,
|
|
"step": 37675
|
|
},
|
|
{
|
|
"entropy": 5.181369304656982,
|
|
"epoch": 3.6195965417867435,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003734807801508587,
|
|
"loss": 4.6879,
|
|
"mean_token_accuracy": 0.25257781744003294,
|
|
"num_tokens": 86372005.0,
|
|
"step": 37680
|
|
},
|
|
{
|
|
"entropy": 5.13061375617981,
|
|
"epoch": 3.6200768491834774,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00037344995381287984,
|
|
"loss": 4.7594,
|
|
"mean_token_accuracy": 0.24052048921585084,
|
|
"num_tokens": 86383789.0,
|
|
"step": 37685
|
|
},
|
|
{
|
|
"entropy": 5.092687559127808,
|
|
"epoch": 3.6205571565802113,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00037341912518918524,
|
|
"loss": 4.6675,
|
|
"mean_token_accuracy": 0.24513599872589112,
|
|
"num_tokens": 86395831.0,
|
|
"step": 37690
|
|
},
|
|
{
|
|
"entropy": 5.176110649108887,
|
|
"epoch": 3.621037463976945,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00037338829428049087,
|
|
"loss": 4.628,
|
|
"mean_token_accuracy": 0.2519341021776199,
|
|
"num_tokens": 86406807.0,
|
|
"step": 37695
|
|
},
|
|
{
|
|
"entropy": 5.206886672973633,
|
|
"epoch": 3.621517771373679,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037335746108751246,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.24513879120349885,
|
|
"num_tokens": 86418025.0,
|
|
"step": 37700
|
|
},
|
|
{
|
|
"entropy": 5.181005525588989,
|
|
"epoch": 3.621998078770413,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003733266256109658,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.24151116311550141,
|
|
"num_tokens": 86429019.0,
|
|
"step": 37705
|
|
},
|
|
{
|
|
"entropy": 5.288647890090942,
|
|
"epoch": 3.6224783861671472,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00037329578785156686,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.24405137002468108,
|
|
"num_tokens": 86439471.0,
|
|
"step": 37710
|
|
},
|
|
{
|
|
"entropy": 5.213916444778443,
|
|
"epoch": 3.6229586935638807,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003732649478100317,
|
|
"loss": 4.7116,
|
|
"mean_token_accuracy": 0.24285559207201005,
|
|
"num_tokens": 86450966.0,
|
|
"step": 37715
|
|
},
|
|
{
|
|
"entropy": 5.018002033233643,
|
|
"epoch": 3.623439000960615,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00037323410548707617,
|
|
"loss": 4.535,
|
|
"mean_token_accuracy": 0.2619576632976532,
|
|
"num_tokens": 86461467.0,
|
|
"step": 37720
|
|
},
|
|
{
|
|
"entropy": 5.138052368164063,
|
|
"epoch": 3.6239193083573484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003732032608834164,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.24665338099002837,
|
|
"num_tokens": 86472743.0,
|
|
"step": 37725
|
|
},
|
|
{
|
|
"entropy": 5.199283790588379,
|
|
"epoch": 3.6243996157540828,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00037317241399976856,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.24968904852867127,
|
|
"num_tokens": 86484101.0,
|
|
"step": 37730
|
|
},
|
|
{
|
|
"entropy": 5.163128614425659,
|
|
"epoch": 3.6248799231508166,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00037314156483684875,
|
|
"loss": 4.6794,
|
|
"mean_token_accuracy": 0.24939751774072647,
|
|
"num_tokens": 86496017.0,
|
|
"step": 37735
|
|
},
|
|
{
|
|
"entropy": 5.140254831314087,
|
|
"epoch": 3.6253602305475505,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003731107133953732,
|
|
"loss": 4.694,
|
|
"mean_token_accuracy": 0.2368271291255951,
|
|
"num_tokens": 86508198.0,
|
|
"step": 37740
|
|
},
|
|
{
|
|
"entropy": 5.280541944503784,
|
|
"epoch": 3.6258405379442844,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037307985967605827,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.2402528256177902,
|
|
"num_tokens": 86518712.0,
|
|
"step": 37745
|
|
},
|
|
{
|
|
"entropy": 5.116595220565796,
|
|
"epoch": 3.6263208453410183,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00037304900367962017,
|
|
"loss": 4.6452,
|
|
"mean_token_accuracy": 0.2501614108681679,
|
|
"num_tokens": 86531340.0,
|
|
"step": 37750
|
|
},
|
|
{
|
|
"entropy": 5.130249643325806,
|
|
"epoch": 3.626801152737752,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003730181454067754,
|
|
"loss": 4.6098,
|
|
"mean_token_accuracy": 0.254507440328598,
|
|
"num_tokens": 86541548.0,
|
|
"step": 37755
|
|
},
|
|
{
|
|
"entropy": 5.164282894134521,
|
|
"epoch": 3.627281460134486,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00037298728485824043,
|
|
"loss": 4.7291,
|
|
"mean_token_accuracy": 0.24630794525146485,
|
|
"num_tokens": 86553259.0,
|
|
"step": 37760
|
|
},
|
|
{
|
|
"entropy": 5.112849187850952,
|
|
"epoch": 3.62776176753122,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003729564220347315,
|
|
"loss": 4.6223,
|
|
"mean_token_accuracy": 0.2512123614549637,
|
|
"num_tokens": 86565199.0,
|
|
"step": 37765
|
|
},
|
|
{
|
|
"entropy": 5.030034446716309,
|
|
"epoch": 3.628242074927954,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003729255569369654,
|
|
"loss": 4.522,
|
|
"mean_token_accuracy": 0.2582956045866013,
|
|
"num_tokens": 86574949.0,
|
|
"step": 37770
|
|
},
|
|
{
|
|
"entropy": 5.068077135086059,
|
|
"epoch": 3.6287223823246877,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003728946895656586,
|
|
"loss": 4.6215,
|
|
"mean_token_accuracy": 0.25548398196697236,
|
|
"num_tokens": 86586039.0,
|
|
"step": 37775
|
|
},
|
|
{
|
|
"entropy": 5.2183473110198975,
|
|
"epoch": 3.6292026897214216,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003728638199215279,
|
|
"loss": 4.7015,
|
|
"mean_token_accuracy": 0.25172314792871475,
|
|
"num_tokens": 86598365.0,
|
|
"step": 37780
|
|
},
|
|
{
|
|
"entropy": 5.16177773475647,
|
|
"epoch": 3.629682997118156,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00037283294800528985,
|
|
"loss": 4.5932,
|
|
"mean_token_accuracy": 0.25882405787706375,
|
|
"num_tokens": 86609460.0,
|
|
"step": 37785
|
|
},
|
|
{
|
|
"entropy": 5.081621599197388,
|
|
"epoch": 3.6301633045148893,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003728020738176612,
|
|
"loss": 4.6592,
|
|
"mean_token_accuracy": 0.2537144526839256,
|
|
"num_tokens": 86621195.0,
|
|
"step": 37790
|
|
},
|
|
{
|
|
"entropy": 5.183621501922607,
|
|
"epoch": 3.6306436119116237,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003727711973593589,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.25018182545900347,
|
|
"num_tokens": 86632671.0,
|
|
"step": 37795
|
|
},
|
|
{
|
|
"entropy": 5.172001075744629,
|
|
"epoch": 3.631123919308357,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003727403186310996,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.24340808838605882,
|
|
"num_tokens": 86644224.0,
|
|
"step": 37800
|
|
},
|
|
{
|
|
"entropy": 5.200538206100464,
|
|
"epoch": 3.6316042267050914,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00037270943763360046,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.2458931416273117,
|
|
"num_tokens": 86655302.0,
|
|
"step": 37805
|
|
},
|
|
{
|
|
"entropy": 5.235613107681274,
|
|
"epoch": 3.6320845341018253,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003726785543675782,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.24610199481248857,
|
|
"num_tokens": 86665907.0,
|
|
"step": 37810
|
|
},
|
|
{
|
|
"entropy": 5.096827507019043,
|
|
"epoch": 3.632564841498559,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00037264766883375003,
|
|
"loss": 4.5945,
|
|
"mean_token_accuracy": 0.2622036784887314,
|
|
"num_tokens": 86676746.0,
|
|
"step": 37815
|
|
},
|
|
{
|
|
"entropy": 5.056214046478272,
|
|
"epoch": 3.633045148895293,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003726167810328329,
|
|
"loss": 4.6807,
|
|
"mean_token_accuracy": 0.24865404665470123,
|
|
"num_tokens": 86689274.0,
|
|
"step": 37820
|
|
},
|
|
{
|
|
"entropy": 5.159703922271729,
|
|
"epoch": 3.633525456292027,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000372585890965544,
|
|
"loss": 4.6613,
|
|
"mean_token_accuracy": 0.25482713580131533,
|
|
"num_tokens": 86700427.0,
|
|
"step": 37825
|
|
},
|
|
{
|
|
"entropy": 5.16128396987915,
|
|
"epoch": 3.634005763688761,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003725549986326004,
|
|
"loss": 4.6433,
|
|
"mean_token_accuracy": 0.25253173857927325,
|
|
"num_tokens": 86712780.0,
|
|
"step": 37830
|
|
},
|
|
{
|
|
"entropy": 5.138763189315796,
|
|
"epoch": 3.6344860710854947,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003725241040347196,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.2477031320333481,
|
|
"num_tokens": 86724359.0,
|
|
"step": 37835
|
|
},
|
|
{
|
|
"entropy": 5.1347081661224365,
|
|
"epoch": 3.6349663784822286,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003724932071726186,
|
|
"loss": 4.7292,
|
|
"mean_token_accuracy": 0.24520707428455352,
|
|
"num_tokens": 86735540.0,
|
|
"step": 37840
|
|
},
|
|
{
|
|
"entropy": 5.1626434326171875,
|
|
"epoch": 3.6354466858789625,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00037246230804701476,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.253428652882576,
|
|
"num_tokens": 86746879.0,
|
|
"step": 37845
|
|
},
|
|
{
|
|
"entropy": 5.165429210662841,
|
|
"epoch": 3.6359269932756964,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00037243140665862556,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.2554088056087494,
|
|
"num_tokens": 86756783.0,
|
|
"step": 37850
|
|
},
|
|
{
|
|
"entropy": 5.188591861724854,
|
|
"epoch": 3.6364073006724302,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00037240050300816843,
|
|
"loss": 4.6899,
|
|
"mean_token_accuracy": 0.256059567630291,
|
|
"num_tokens": 86768722.0,
|
|
"step": 37855
|
|
},
|
|
{
|
|
"entropy": 5.175281286239624,
|
|
"epoch": 3.636887608069164,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00037236959709636085,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.24784279316663743,
|
|
"num_tokens": 86780386.0,
|
|
"step": 37860
|
|
},
|
|
{
|
|
"entropy": 5.136850452423095,
|
|
"epoch": 3.637367915465898,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037233868892392035,
|
|
"loss": 4.6649,
|
|
"mean_token_accuracy": 0.24777935147285463,
|
|
"num_tokens": 86793008.0,
|
|
"step": 37865
|
|
},
|
|
{
|
|
"entropy": 5.183935451507568,
|
|
"epoch": 3.6378482228626323,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003723077784915645,
|
|
"loss": 4.6543,
|
|
"mean_token_accuracy": 0.252856607735157,
|
|
"num_tokens": 86804451.0,
|
|
"step": 37870
|
|
},
|
|
{
|
|
"entropy": 5.17041654586792,
|
|
"epoch": 3.6383285302593658,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00037227686580001095,
|
|
"loss": 4.7365,
|
|
"mean_token_accuracy": 0.24204785972833634,
|
|
"num_tokens": 86816391.0,
|
|
"step": 37875
|
|
},
|
|
{
|
|
"entropy": 5.231221866607666,
|
|
"epoch": 3.6388088376561,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003722459508499775,
|
|
"loss": 4.7694,
|
|
"mean_token_accuracy": 0.24255248606204988,
|
|
"num_tokens": 86828163.0,
|
|
"step": 37880
|
|
},
|
|
{
|
|
"entropy": 5.195094633102417,
|
|
"epoch": 3.639289145052834,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003722150336421818,
|
|
"loss": 4.6586,
|
|
"mean_token_accuracy": 0.2465899482369423,
|
|
"num_tokens": 86839311.0,
|
|
"step": 37885
|
|
},
|
|
{
|
|
"entropy": 5.224485969543457,
|
|
"epoch": 3.639769452449568,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003721841141773417,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.2409597083926201,
|
|
"num_tokens": 86849921.0,
|
|
"step": 37890
|
|
},
|
|
{
|
|
"entropy": 5.019923973083496,
|
|
"epoch": 3.6402497598463017,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00037215319245617503,
|
|
"loss": 4.5906,
|
|
"mean_token_accuracy": 0.2552749693393707,
|
|
"num_tokens": 86862858.0,
|
|
"step": 37895
|
|
},
|
|
{
|
|
"entropy": 5.13014669418335,
|
|
"epoch": 3.6407300672430356,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037212226847939975,
|
|
"loss": 4.5984,
|
|
"mean_token_accuracy": 0.2552096664905548,
|
|
"num_tokens": 86874152.0,
|
|
"step": 37900
|
|
},
|
|
{
|
|
"entropy": 5.1719423770904545,
|
|
"epoch": 3.6412103746397695,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003720913422477338,
|
|
"loss": 4.6455,
|
|
"mean_token_accuracy": 0.25845315903425214,
|
|
"num_tokens": 86886126.0,
|
|
"step": 37905
|
|
},
|
|
{
|
|
"entropy": 5.2842528343200685,
|
|
"epoch": 3.6416906820365034,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037206041376189515,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.2404300108551979,
|
|
"num_tokens": 86896046.0,
|
|
"step": 37910
|
|
},
|
|
{
|
|
"entropy": 5.040910863876343,
|
|
"epoch": 3.6421709894332372,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003720294830226018,
|
|
"loss": 4.5994,
|
|
"mean_token_accuracy": 0.2547954976558685,
|
|
"num_tokens": 86907946.0,
|
|
"step": 37915
|
|
},
|
|
{
|
|
"entropy": 5.089847183227539,
|
|
"epoch": 3.642651296829971,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003719985500305721,
|
|
"loss": 4.5941,
|
|
"mean_token_accuracy": 0.2586877435445786,
|
|
"num_tokens": 86919849.0,
|
|
"step": 37920
|
|
},
|
|
{
|
|
"entropy": 5.2464415550231935,
|
|
"epoch": 3.643131604226705,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003719676147865241,
|
|
"loss": 4.7486,
|
|
"mean_token_accuracy": 0.24580430537462233,
|
|
"num_tokens": 86930325.0,
|
|
"step": 37925
|
|
},
|
|
{
|
|
"entropy": 5.0840589046478275,
|
|
"epoch": 3.643611911623439,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000371936677291176,
|
|
"loss": 4.5779,
|
|
"mean_token_accuracy": 0.25817959755659103,
|
|
"num_tokens": 86942076.0,
|
|
"step": 37930
|
|
},
|
|
{
|
|
"entropy": 5.069951581954956,
|
|
"epoch": 3.6440922190201728,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003719057375452461,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.26757209599018095,
|
|
"num_tokens": 86953226.0,
|
|
"step": 37935
|
|
},
|
|
{
|
|
"entropy": 5.207354021072388,
|
|
"epoch": 3.6445725264169067,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003718747955494527,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.247088785469532,
|
|
"num_tokens": 86964606.0,
|
|
"step": 37940
|
|
},
|
|
{
|
|
"entropy": 5.094648838043213,
|
|
"epoch": 3.645052833813641,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00037184385130451425,
|
|
"loss": 4.5819,
|
|
"mean_token_accuracy": 0.25388672649860383,
|
|
"num_tokens": 86976738.0,
|
|
"step": 37945
|
|
},
|
|
{
|
|
"entropy": 5.164129447937012,
|
|
"epoch": 3.6455331412103744,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00037181290481114903,
|
|
"loss": 4.7845,
|
|
"mean_token_accuracy": 0.24697981774806976,
|
|
"num_tokens": 86988445.0,
|
|
"step": 37950
|
|
},
|
|
{
|
|
"entropy": 5.1315107345581055,
|
|
"epoch": 3.6460134486071087,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003717819560700758,
|
|
"loss": 4.6025,
|
|
"mean_token_accuracy": 0.25994391441345216,
|
|
"num_tokens": 87000818.0,
|
|
"step": 37955
|
|
},
|
|
{
|
|
"entropy": 5.179689025878906,
|
|
"epoch": 3.6464937560038426,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003717510050820128,
|
|
"loss": 4.7181,
|
|
"mean_token_accuracy": 0.2500323325395584,
|
|
"num_tokens": 87012398.0,
|
|
"step": 37960
|
|
},
|
|
{
|
|
"entropy": 5.202019166946411,
|
|
"epoch": 3.6469740634005765,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00037172005184767885,
|
|
"loss": 4.7441,
|
|
"mean_token_accuracy": 0.244164901971817,
|
|
"num_tokens": 87022885.0,
|
|
"step": 37965
|
|
},
|
|
{
|
|
"entropy": 5.149873113632202,
|
|
"epoch": 3.6474543707973104,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003716890963677924,
|
|
"loss": 4.6678,
|
|
"mean_token_accuracy": 0.2556825548410416,
|
|
"num_tokens": 87033973.0,
|
|
"step": 37970
|
|
},
|
|
{
|
|
"entropy": 5.124229383468628,
|
|
"epoch": 3.6479346781940443,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003716581386430723,
|
|
"loss": 4.6516,
|
|
"mean_token_accuracy": 0.25021855235099794,
|
|
"num_tokens": 87046391.0,
|
|
"step": 37975
|
|
},
|
|
{
|
|
"entropy": 5.214483308792114,
|
|
"epoch": 3.648414985590778,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003716271786742372,
|
|
"loss": 4.6871,
|
|
"mean_token_accuracy": 0.25116886049509046,
|
|
"num_tokens": 87056913.0,
|
|
"step": 37980
|
|
},
|
|
{
|
|
"entropy": 5.20869722366333,
|
|
"epoch": 3.648895292987512,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00037159621646200595,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.2497592657804489,
|
|
"num_tokens": 87068905.0,
|
|
"step": 37985
|
|
},
|
|
{
|
|
"entropy": 5.139099502563477,
|
|
"epoch": 3.649375600384246,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003715652520070974,
|
|
"loss": 4.7443,
|
|
"mean_token_accuracy": 0.24191294610500336,
|
|
"num_tokens": 87080186.0,
|
|
"step": 37990
|
|
},
|
|
{
|
|
"entropy": 5.129316425323486,
|
|
"epoch": 3.64985590778098,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003715342853102305,
|
|
"loss": 4.6568,
|
|
"mean_token_accuracy": 0.2539025515317917,
|
|
"num_tokens": 87091130.0,
|
|
"step": 37995
|
|
},
|
|
{
|
|
"entropy": 5.269346904754639,
|
|
"epoch": 3.6503362151777137,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003715033163721241,
|
|
"loss": 4.7461,
|
|
"mean_token_accuracy": 0.24477933049201966,
|
|
"num_tokens": 87103482.0,
|
|
"step": 38000
|
|
},
|
|
{
|
|
"entropy": 5.186242723464966,
|
|
"epoch": 3.6508165225744476,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003714723451934972,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.24582123309373854,
|
|
"num_tokens": 87114850.0,
|
|
"step": 38005
|
|
},
|
|
{
|
|
"entropy": 5.145034217834473,
|
|
"epoch": 3.6512968299711814,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00037144137177506887,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.25140823125839235,
|
|
"num_tokens": 87125840.0,
|
|
"step": 38010
|
|
},
|
|
{
|
|
"entropy": 5.160034704208374,
|
|
"epoch": 3.6517771373679153,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003714103961175584,
|
|
"loss": 4.7228,
|
|
"mean_token_accuracy": 0.2518065616488457,
|
|
"num_tokens": 87138216.0,
|
|
"step": 38015
|
|
},
|
|
{
|
|
"entropy": 5.176300764083862,
|
|
"epoch": 3.6522574447646496,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003713794182216847,
|
|
"loss": 4.6483,
|
|
"mean_token_accuracy": 0.25822460651397705,
|
|
"num_tokens": 87149071.0,
|
|
"step": 38020
|
|
},
|
|
{
|
|
"entropy": 5.109663343429565,
|
|
"epoch": 3.652737752161383,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037134843808816717,
|
|
"loss": 4.6353,
|
|
"mean_token_accuracy": 0.2585537925362587,
|
|
"num_tokens": 87160564.0,
|
|
"step": 38025
|
|
},
|
|
{
|
|
"entropy": 5.008924388885498,
|
|
"epoch": 3.6532180595581174,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00037131745571772497,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.26200799345970155,
|
|
"num_tokens": 87171536.0,
|
|
"step": 38030
|
|
},
|
|
{
|
|
"entropy": 5.216759061813354,
|
|
"epoch": 3.653698366954851,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00037128647111107736,
|
|
"loss": 4.763,
|
|
"mean_token_accuracy": 0.24633358120918275,
|
|
"num_tokens": 87183064.0,
|
|
"step": 38035
|
|
},
|
|
{
|
|
"entropy": 5.220616960525513,
|
|
"epoch": 3.654178674351585,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000371255484268944,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.2496157020330429,
|
|
"num_tokens": 87194034.0,
|
|
"step": 38040
|
|
},
|
|
{
|
|
"entropy": 5.148686408996582,
|
|
"epoch": 3.654658981748319,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00037122449519204397,
|
|
"loss": 4.7263,
|
|
"mean_token_accuracy": 0.2450135752558708,
|
|
"num_tokens": 87205083.0,
|
|
"step": 38045
|
|
},
|
|
{
|
|
"entropy": 5.22234354019165,
|
|
"epoch": 3.655139289145053,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00037119350388109697,
|
|
"loss": 4.6875,
|
|
"mean_token_accuracy": 0.24866264164447785,
|
|
"num_tokens": 87216034.0,
|
|
"step": 38050
|
|
},
|
|
{
|
|
"entropy": 5.126129674911499,
|
|
"epoch": 3.655619596541787,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00037116251033682236,
|
|
"loss": 4.6337,
|
|
"mean_token_accuracy": 0.25261838883161547,
|
|
"num_tokens": 87227231.0,
|
|
"step": 38055
|
|
},
|
|
{
|
|
"entropy": 5.165459108352661,
|
|
"epoch": 3.6560999039385207,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003711315145599398,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.2512372642755508,
|
|
"num_tokens": 87239630.0,
|
|
"step": 38060
|
|
},
|
|
{
|
|
"entropy": 5.173176097869873,
|
|
"epoch": 3.6565802113352546,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000371100516551169,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.24871889352798462,
|
|
"num_tokens": 87250008.0,
|
|
"step": 38065
|
|
},
|
|
{
|
|
"entropy": 5.147016143798828,
|
|
"epoch": 3.6570605187319885,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003710695163112295,
|
|
"loss": 4.6689,
|
|
"mean_token_accuracy": 0.2504251107573509,
|
|
"num_tokens": 87260802.0,
|
|
"step": 38070
|
|
},
|
|
{
|
|
"entropy": 5.19296350479126,
|
|
"epoch": 3.6575408261287223,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003710385138408412,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.24561755061149598,
|
|
"num_tokens": 87271960.0,
|
|
"step": 38075
|
|
},
|
|
{
|
|
"entropy": 5.100399827957153,
|
|
"epoch": 3.658021133525456,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003710075091407237,
|
|
"loss": 4.6097,
|
|
"mean_token_accuracy": 0.24787129312753678,
|
|
"num_tokens": 87285138.0,
|
|
"step": 38080
|
|
},
|
|
{
|
|
"entropy": 5.131773042678833,
|
|
"epoch": 3.65850144092219,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003709765022115969,
|
|
"loss": 4.6531,
|
|
"mean_token_accuracy": 0.25302300602197647,
|
|
"num_tokens": 87296650.0,
|
|
"step": 38085
|
|
},
|
|
{
|
|
"entropy": 5.119957828521729,
|
|
"epoch": 3.658981748318924,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003709454930541808,
|
|
"loss": 4.6429,
|
|
"mean_token_accuracy": 0.2594186767935753,
|
|
"num_tokens": 87307315.0,
|
|
"step": 38090
|
|
},
|
|
{
|
|
"entropy": 5.051396751403809,
|
|
"epoch": 3.659462055715658,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00037091448166919516,
|
|
"loss": 4.5205,
|
|
"mean_token_accuracy": 0.2599992588162422,
|
|
"num_tokens": 87318842.0,
|
|
"step": 38095
|
|
},
|
|
{
|
|
"entropy": 5.0804585933685305,
|
|
"epoch": 3.6599423631123917,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037088346805736014,
|
|
"loss": 4.5869,
|
|
"mean_token_accuracy": 0.2594689577817917,
|
|
"num_tokens": 87329308.0,
|
|
"step": 38100
|
|
},
|
|
{
|
|
"entropy": 5.184806442260742,
|
|
"epoch": 3.660422670509126,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003708524522193957,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.24894420206546783,
|
|
"num_tokens": 87340186.0,
|
|
"step": 38105
|
|
},
|
|
{
|
|
"entropy": 5.236883926391601,
|
|
"epoch": 3.6609029779058595,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00037082143415602186,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.24243318438529968,
|
|
"num_tokens": 87352547.0,
|
|
"step": 38110
|
|
},
|
|
{
|
|
"entropy": 5.192333173751831,
|
|
"epoch": 3.661383285302594,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003707904138679589,
|
|
"loss": 4.6945,
|
|
"mean_token_accuracy": 0.2484928250312805,
|
|
"num_tokens": 87363602.0,
|
|
"step": 38115
|
|
},
|
|
{
|
|
"entropy": 5.149674701690674,
|
|
"epoch": 3.6618635926993277,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000370759391355927,
|
|
"loss": 4.6881,
|
|
"mean_token_accuracy": 0.24981403946876526,
|
|
"num_tokens": 87375127.0,
|
|
"step": 38120
|
|
},
|
|
{
|
|
"entropy": 5.181605529785156,
|
|
"epoch": 3.6623439000960616,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003707283666206464,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.2490944966673851,
|
|
"num_tokens": 87386436.0,
|
|
"step": 38125
|
|
},
|
|
{
|
|
"entropy": 5.12442569732666,
|
|
"epoch": 3.6628242074927955,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003706973396628373,
|
|
"loss": 4.6662,
|
|
"mean_token_accuracy": 0.2540185421705246,
|
|
"num_tokens": 87399584.0,
|
|
"step": 38130
|
|
},
|
|
{
|
|
"entropy": 5.201237058639526,
|
|
"epoch": 3.6633045148895294,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003706663104832202,
|
|
"loss": 4.6937,
|
|
"mean_token_accuracy": 0.2513996437191963,
|
|
"num_tokens": 87410244.0,
|
|
"step": 38135
|
|
},
|
|
{
|
|
"entropy": 5.099209022521973,
|
|
"epoch": 3.6637848222862632,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037063527908251536,
|
|
"loss": 4.6133,
|
|
"mean_token_accuracy": 0.2557328179478645,
|
|
"num_tokens": 87421907.0,
|
|
"step": 38140
|
|
},
|
|
{
|
|
"entropy": 5.07440414428711,
|
|
"epoch": 3.664265129682997,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003706042454614434,
|
|
"loss": 4.5379,
|
|
"mean_token_accuracy": 0.2588096335530281,
|
|
"num_tokens": 87432202.0,
|
|
"step": 38145
|
|
},
|
|
{
|
|
"entropy": 5.040391969680786,
|
|
"epoch": 3.664745437079731,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003705732096207247,
|
|
"loss": 4.5687,
|
|
"mean_token_accuracy": 0.25761356204748154,
|
|
"num_tokens": 87443460.0,
|
|
"step": 38150
|
|
},
|
|
{
|
|
"entropy": 5.0761853694915775,
|
|
"epoch": 3.665225744476465,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00037054217156107987,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.257637494802475,
|
|
"num_tokens": 87455900.0,
|
|
"step": 38155
|
|
},
|
|
{
|
|
"entropy": 5.158331108093262,
|
|
"epoch": 3.6657060518731988,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00037051113128322953,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.25071342587471007,
|
|
"num_tokens": 87467593.0,
|
|
"step": 38160
|
|
},
|
|
{
|
|
"entropy": 5.109021425247192,
|
|
"epoch": 3.6661863592699326,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00037048008878789437,
|
|
"loss": 4.6438,
|
|
"mean_token_accuracy": 0.24870747476816177,
|
|
"num_tokens": 87479230.0,
|
|
"step": 38165
|
|
},
|
|
{
|
|
"entropy": 5.104383325576782,
|
|
"epoch": 3.6666666666666665,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00037044904407579506,
|
|
"loss": 4.627,
|
|
"mean_token_accuracy": 0.26198102831840514,
|
|
"num_tokens": 87489777.0,
|
|
"step": 38170
|
|
},
|
|
{
|
|
"entropy": 5.158572387695313,
|
|
"epoch": 3.6671469740634004,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00037041799714765226,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.23752044439315795,
|
|
"num_tokens": 87501202.0,
|
|
"step": 38175
|
|
},
|
|
{
|
|
"entropy": 5.1332344055175785,
|
|
"epoch": 3.6676272814601347,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000370386948004187,
|
|
"loss": 4.6579,
|
|
"mean_token_accuracy": 0.2533713594079018,
|
|
"num_tokens": 87512684.0,
|
|
"step": 38180
|
|
},
|
|
{
|
|
"entropy": 5.187321424484253,
|
|
"epoch": 3.668107588856868,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00037035589664612004,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.2505868628621101,
|
|
"num_tokens": 87525905.0,
|
|
"step": 38185
|
|
},
|
|
{
|
|
"entropy": 5.081480693817139,
|
|
"epoch": 3.6685878962536025,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003703248430741723,
|
|
"loss": 4.6117,
|
|
"mean_token_accuracy": 0.256259848177433,
|
|
"num_tokens": 87536764.0,
|
|
"step": 38190
|
|
},
|
|
{
|
|
"entropy": 5.161813640594483,
|
|
"epoch": 3.6690682036503364,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003702937872890647,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.24979589730501175,
|
|
"num_tokens": 87548807.0,
|
|
"step": 38195
|
|
},
|
|
{
|
|
"entropy": 5.013713788986206,
|
|
"epoch": 3.6695485110470702,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003702627292915184,
|
|
"loss": 4.5284,
|
|
"mean_token_accuracy": 0.25953962057828905,
|
|
"num_tokens": 87559570.0,
|
|
"step": 38200
|
|
},
|
|
{
|
|
"entropy": 5.156081962585449,
|
|
"epoch": 3.670028818443804,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003702316690822544,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.24950095415115356,
|
|
"num_tokens": 87570758.0,
|
|
"step": 38205
|
|
},
|
|
{
|
|
"entropy": 5.073321342468262,
|
|
"epoch": 3.670509125840538,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00037020060666199386,
|
|
"loss": 4.5391,
|
|
"mean_token_accuracy": 0.2544825628399849,
|
|
"num_tokens": 87581985.0,
|
|
"step": 38210
|
|
},
|
|
{
|
|
"entropy": 5.09008207321167,
|
|
"epoch": 3.670989433237272,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0003701695420314578,
|
|
"loss": 4.6627,
|
|
"mean_token_accuracy": 0.24872563630342484,
|
|
"num_tokens": 87595130.0,
|
|
"step": 38215
|
|
},
|
|
{
|
|
"entropy": 5.133439016342163,
|
|
"epoch": 3.6714697406340058,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037013847519136765,
|
|
"loss": 4.7044,
|
|
"mean_token_accuracy": 0.24287740886211395,
|
|
"num_tokens": 87608073.0,
|
|
"step": 38220
|
|
},
|
|
{
|
|
"entropy": 5.0420304298400875,
|
|
"epoch": 3.6719500480307397,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003701074061424446,
|
|
"loss": 4.541,
|
|
"mean_token_accuracy": 0.26200360953807833,
|
|
"num_tokens": 87618889.0,
|
|
"step": 38225
|
|
},
|
|
{
|
|
"entropy": 5.105528020858765,
|
|
"epoch": 3.6724303554274735,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00037007633488541,
|
|
"loss": 4.5857,
|
|
"mean_token_accuracy": 0.2550201117992401,
|
|
"num_tokens": 87630386.0,
|
|
"step": 38230
|
|
},
|
|
{
|
|
"entropy": 5.187676334381104,
|
|
"epoch": 3.6729106628242074,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037004526142098517,
|
|
"loss": 4.7351,
|
|
"mean_token_accuracy": 0.24668737053871154,
|
|
"num_tokens": 87642761.0,
|
|
"step": 38235
|
|
},
|
|
{
|
|
"entropy": 5.133597326278687,
|
|
"epoch": 3.6733909702209413,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00037001418574989165,
|
|
"loss": 4.6732,
|
|
"mean_token_accuracy": 0.24950021058320998,
|
|
"num_tokens": 87653661.0,
|
|
"step": 38240
|
|
},
|
|
{
|
|
"entropy": 5.067084550857544,
|
|
"epoch": 3.673871277617675,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00036998310787285084,
|
|
"loss": 4.6374,
|
|
"mean_token_accuracy": 0.2561600998044014,
|
|
"num_tokens": 87665025.0,
|
|
"step": 38245
|
|
},
|
|
{
|
|
"entropy": 5.151736783981323,
|
|
"epoch": 3.674351585014409,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003699520277905843,
|
|
"loss": 4.6544,
|
|
"mean_token_accuracy": 0.2525796592235565,
|
|
"num_tokens": 87676349.0,
|
|
"step": 38250
|
|
},
|
|
{
|
|
"entropy": 5.075395393371582,
|
|
"epoch": 3.6748318924111434,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003699209455038137,
|
|
"loss": 4.518,
|
|
"mean_token_accuracy": 0.2641995564103127,
|
|
"num_tokens": 87688149.0,
|
|
"step": 38255
|
|
},
|
|
{
|
|
"entropy": 5.112798976898193,
|
|
"epoch": 3.675312199807877,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00036988986101326056,
|
|
"loss": 4.5874,
|
|
"mean_token_accuracy": 0.25344758331775663,
|
|
"num_tokens": 87699323.0,
|
|
"step": 38260
|
|
},
|
|
{
|
|
"entropy": 5.128345155715943,
|
|
"epoch": 3.675792507204611,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003698587743196465,
|
|
"loss": 4.6513,
|
|
"mean_token_accuracy": 0.25382249504327775,
|
|
"num_tokens": 87709994.0,
|
|
"step": 38265
|
|
},
|
|
{
|
|
"entropy": 5.081667518615722,
|
|
"epoch": 3.6762728146013446,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00036982768542369353,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.25226187258958815,
|
|
"num_tokens": 87721979.0,
|
|
"step": 38270
|
|
},
|
|
{
|
|
"entropy": 5.143327474594116,
|
|
"epoch": 3.676753121998079,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00036979659432612324,
|
|
"loss": 4.6374,
|
|
"mean_token_accuracy": 0.24859957844018937,
|
|
"num_tokens": 87732194.0,
|
|
"step": 38275
|
|
},
|
|
{
|
|
"entropy": 5.019284248352051,
|
|
"epoch": 3.677233429394813,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003697655010276575,
|
|
"loss": 4.5223,
|
|
"mean_token_accuracy": 0.264199486374855,
|
|
"num_tokens": 87742736.0,
|
|
"step": 38280
|
|
},
|
|
{
|
|
"entropy": 5.1015533924102785,
|
|
"epoch": 3.6777137367915467,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003697344055290182,
|
|
"loss": 4.6351,
|
|
"mean_token_accuracy": 0.2518920511007309,
|
|
"num_tokens": 87753557.0,
|
|
"step": 38285
|
|
},
|
|
{
|
|
"entropy": 5.1259842872619625,
|
|
"epoch": 3.6781940441882806,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0003697033078309274,
|
|
"loss": 4.6951,
|
|
"mean_token_accuracy": 0.2491082951426506,
|
|
"num_tokens": 87766585.0,
|
|
"step": 38290
|
|
},
|
|
{
|
|
"entropy": 5.141530513763428,
|
|
"epoch": 3.6786743515850144,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00036967220793410687,
|
|
"loss": 4.6932,
|
|
"mean_token_accuracy": 0.24630052745342254,
|
|
"num_tokens": 87777679.0,
|
|
"step": 38295
|
|
},
|
|
{
|
|
"entropy": 5.0448273658752445,
|
|
"epoch": 3.6791546589817483,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003696411058392789,
|
|
"loss": 4.604,
|
|
"mean_token_accuracy": 0.2592935711145401,
|
|
"num_tokens": 87790083.0,
|
|
"step": 38300
|
|
},
|
|
{
|
|
"entropy": 5.059641265869141,
|
|
"epoch": 3.679634966378482,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003696100015471654,
|
|
"loss": 4.6006,
|
|
"mean_token_accuracy": 0.25757531076669693,
|
|
"num_tokens": 87802293.0,
|
|
"step": 38305
|
|
},
|
|
{
|
|
"entropy": 5.044550037384033,
|
|
"epoch": 3.680115273775216,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003695788950584886,
|
|
"loss": 4.6129,
|
|
"mean_token_accuracy": 0.25555177479982377,
|
|
"num_tokens": 87813367.0,
|
|
"step": 38310
|
|
},
|
|
{
|
|
"entropy": 5.08332200050354,
|
|
"epoch": 3.68059558117195,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00036954778637397084,
|
|
"loss": 4.6285,
|
|
"mean_token_accuracy": 0.2518509328365326,
|
|
"num_tokens": 87824669.0,
|
|
"step": 38315
|
|
},
|
|
{
|
|
"entropy": 5.167525148391723,
|
|
"epoch": 3.681075888568684,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00036951667549433404,
|
|
"loss": 4.7802,
|
|
"mean_token_accuracy": 0.244375604391098,
|
|
"num_tokens": 87836728.0,
|
|
"step": 38320
|
|
},
|
|
{
|
|
"entropy": 5.215084981918335,
|
|
"epoch": 3.6815561959654177,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036948556242030083,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.24162942320108413,
|
|
"num_tokens": 87848391.0,
|
|
"step": 38325
|
|
},
|
|
{
|
|
"entropy": 5.231409406661987,
|
|
"epoch": 3.682036503362152,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00036945444715259334,
|
|
"loss": 4.7016,
|
|
"mean_token_accuracy": 0.2570244580507278,
|
|
"num_tokens": 87860837.0,
|
|
"step": 38330
|
|
},
|
|
{
|
|
"entropy": 5.155489540100097,
|
|
"epoch": 3.6825168107588855,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003694233296919341,
|
|
"loss": 4.7028,
|
|
"mean_token_accuracy": 0.24352950155735015,
|
|
"num_tokens": 87873766.0,
|
|
"step": 38335
|
|
},
|
|
{
|
|
"entropy": 5.136341953277588,
|
|
"epoch": 3.68299711815562,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00036939221003904547,
|
|
"loss": 4.6585,
|
|
"mean_token_accuracy": 0.2562160849571228,
|
|
"num_tokens": 87885151.0,
|
|
"step": 38340
|
|
},
|
|
{
|
|
"entropy": 5.001521635055542,
|
|
"epoch": 3.6834774255523532,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00036936108819465006,
|
|
"loss": 4.5315,
|
|
"mean_token_accuracy": 0.26318626999855044,
|
|
"num_tokens": 87896967.0,
|
|
"step": 38345
|
|
},
|
|
{
|
|
"entropy": 5.114966487884521,
|
|
"epoch": 3.6839577329490876,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00036932996415947047,
|
|
"loss": 4.6251,
|
|
"mean_token_accuracy": 0.2497001275420189,
|
|
"num_tokens": 87908392.0,
|
|
"step": 38350
|
|
},
|
|
{
|
|
"entropy": 5.221485710144043,
|
|
"epoch": 3.6844380403458215,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00036929883793422906,
|
|
"loss": 4.781,
|
|
"mean_token_accuracy": 0.24574290364980697,
|
|
"num_tokens": 87920409.0,
|
|
"step": 38355
|
|
},
|
|
{
|
|
"entropy": 5.140281248092651,
|
|
"epoch": 3.6849183477425553,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003692677095196487,
|
|
"loss": 4.676,
|
|
"mean_token_accuracy": 0.2519399091601372,
|
|
"num_tokens": 87931609.0,
|
|
"step": 38360
|
|
},
|
|
{
|
|
"entropy": 5.165766096115112,
|
|
"epoch": 3.685398655139289,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000369236578916452,
|
|
"loss": 4.7616,
|
|
"mean_token_accuracy": 0.23290945887565612,
|
|
"num_tokens": 87943599.0,
|
|
"step": 38365
|
|
},
|
|
{
|
|
"entropy": 5.179135656356811,
|
|
"epoch": 3.685878962536023,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00036920544612536186,
|
|
"loss": 4.6658,
|
|
"mean_token_accuracy": 0.24790519922971727,
|
|
"num_tokens": 87953659.0,
|
|
"step": 38370
|
|
},
|
|
{
|
|
"entropy": 5.20915675163269,
|
|
"epoch": 3.686359269932757,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003691743111471009,
|
|
"loss": 4.7396,
|
|
"mean_token_accuracy": 0.23768969476222992,
|
|
"num_tokens": 87966174.0,
|
|
"step": 38375
|
|
},
|
|
{
|
|
"entropy": 5.131823587417602,
|
|
"epoch": 3.686839577329491,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003691431739823922,
|
|
"loss": 4.6524,
|
|
"mean_token_accuracy": 0.24654483199119567,
|
|
"num_tokens": 87978804.0,
|
|
"step": 38380
|
|
},
|
|
{
|
|
"entropy": 5.2011034965515135,
|
|
"epoch": 3.6873198847262247,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00036911203463195843,
|
|
"loss": 4.6923,
|
|
"mean_token_accuracy": 0.2519195884466171,
|
|
"num_tokens": 87989807.0,
|
|
"step": 38385
|
|
},
|
|
{
|
|
"entropy": 5.081535053253174,
|
|
"epoch": 3.6878001921229586,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00036908089309652266,
|
|
"loss": 4.6206,
|
|
"mean_token_accuracy": 0.25546774715185167,
|
|
"num_tokens": 88000978.0,
|
|
"step": 38390
|
|
},
|
|
{
|
|
"entropy": 5.1522339344024655,
|
|
"epoch": 3.6882804995196925,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000369049749376808,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.25077286660671233,
|
|
"num_tokens": 88012421.0,
|
|
"step": 38395
|
|
},
|
|
{
|
|
"entropy": 5.147921323776245,
|
|
"epoch": 3.6887608069164264,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00036901860347353735,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.25405672788619993,
|
|
"num_tokens": 88023315.0,
|
|
"step": 38400
|
|
},
|
|
{
|
|
"entropy": 5.104630374908448,
|
|
"epoch": 3.6892411143131603,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000368987455387434,
|
|
"loss": 4.6626,
|
|
"mean_token_accuracy": 0.25586254298686983,
|
|
"num_tokens": 88035368.0,
|
|
"step": 38405
|
|
},
|
|
{
|
|
"entropy": 5.09163761138916,
|
|
"epoch": 3.689721421709894,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003689563051192209,
|
|
"loss": 4.6419,
|
|
"mean_token_accuracy": 0.257462714612484,
|
|
"num_tokens": 88045809.0,
|
|
"step": 38410
|
|
},
|
|
{
|
|
"entropy": 5.181260871887207,
|
|
"epoch": 3.6902017291066285,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00036892515266962145,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.2548514172434807,
|
|
"num_tokens": 88056456.0,
|
|
"step": 38415
|
|
},
|
|
{
|
|
"entropy": 5.143804740905762,
|
|
"epoch": 3.690682036503362,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003688939980393588,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.24901550859212876,
|
|
"num_tokens": 88069387.0,
|
|
"step": 38420
|
|
},
|
|
{
|
|
"entropy": 5.152760648727417,
|
|
"epoch": 3.6911623439000962,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003688628412291564,
|
|
"loss": 4.6638,
|
|
"mean_token_accuracy": 0.24742020815610885,
|
|
"num_tokens": 88079393.0,
|
|
"step": 38425
|
|
},
|
|
{
|
|
"entropy": 5.192798280715943,
|
|
"epoch": 3.69164265129683,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036883168223973754,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.24571994841098785,
|
|
"num_tokens": 88089151.0,
|
|
"step": 38430
|
|
},
|
|
{
|
|
"entropy": 5.194323635101318,
|
|
"epoch": 3.692122958693564,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003688005210718257,
|
|
"loss": 4.6434,
|
|
"mean_token_accuracy": 0.24878001511096953,
|
|
"num_tokens": 88100497.0,
|
|
"step": 38435
|
|
},
|
|
{
|
|
"entropy": 5.216534423828125,
|
|
"epoch": 3.692603266090298,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003687693577261442,
|
|
"loss": 4.766,
|
|
"mean_token_accuracy": 0.2399820640683174,
|
|
"num_tokens": 88112818.0,
|
|
"step": 38440
|
|
},
|
|
{
|
|
"entropy": 5.212910175323486,
|
|
"epoch": 3.6930835734870318,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00036873819220341667,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.24700148701667785,
|
|
"num_tokens": 88123128.0,
|
|
"step": 38445
|
|
},
|
|
{
|
|
"entropy": 5.081011486053467,
|
|
"epoch": 3.6935638808837656,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00036870702450436655,
|
|
"loss": 4.6483,
|
|
"mean_token_accuracy": 0.2609351694583893,
|
|
"num_tokens": 88136062.0,
|
|
"step": 38450
|
|
},
|
|
{
|
|
"entropy": 5.174077558517456,
|
|
"epoch": 3.6940441882804995,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00036867585462971775,
|
|
"loss": 4.7329,
|
|
"mean_token_accuracy": 0.24462470561265945,
|
|
"num_tokens": 88147234.0,
|
|
"step": 38455
|
|
},
|
|
{
|
|
"entropy": 5.099536180496216,
|
|
"epoch": 3.6945244956772334,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003686446825801937,
|
|
"loss": 4.6164,
|
|
"mean_token_accuracy": 0.25498823523521424,
|
|
"num_tokens": 88158537.0,
|
|
"step": 38460
|
|
},
|
|
{
|
|
"entropy": 5.140117073059082,
|
|
"epoch": 3.6950048030739673,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003686135083565181,
|
|
"loss": 4.6115,
|
|
"mean_token_accuracy": 0.2524968281388283,
|
|
"num_tokens": 88169652.0,
|
|
"step": 38465
|
|
},
|
|
{
|
|
"entropy": 5.182451295852661,
|
|
"epoch": 3.695485110470701,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00036858233195941493,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.24085148572921752,
|
|
"num_tokens": 88181919.0,
|
|
"step": 38470
|
|
},
|
|
{
|
|
"entropy": 5.089308357238769,
|
|
"epoch": 3.695965417867435,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003685511533896079,
|
|
"loss": 4.6142,
|
|
"mean_token_accuracy": 0.2502070292830467,
|
|
"num_tokens": 88194070.0,
|
|
"step": 38475
|
|
},
|
|
{
|
|
"entropy": 5.155722665786743,
|
|
"epoch": 3.696445725264169,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00036851997264782083,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.24510451555252075,
|
|
"num_tokens": 88206410.0,
|
|
"step": 38480
|
|
},
|
|
{
|
|
"entropy": 5.124524021148682,
|
|
"epoch": 3.696926032660903,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00036848878973477767,
|
|
"loss": 4.6896,
|
|
"mean_token_accuracy": 0.24986092895269393,
|
|
"num_tokens": 88218921.0,
|
|
"step": 38485
|
|
},
|
|
{
|
|
"entropy": 5.152508640289307,
|
|
"epoch": 3.697406340057637,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00036845760465120247,
|
|
"loss": 4.6392,
|
|
"mean_token_accuracy": 0.25237261354923246,
|
|
"num_tokens": 88231026.0,
|
|
"step": 38490
|
|
},
|
|
{
|
|
"entropy": 5.265774822235107,
|
|
"epoch": 3.6978866474543706,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003684264173978192,
|
|
"loss": 4.7699,
|
|
"mean_token_accuracy": 0.24611775130033492,
|
|
"num_tokens": 88243731.0,
|
|
"step": 38495
|
|
},
|
|
{
|
|
"entropy": 5.092627239227295,
|
|
"epoch": 3.698366954851105,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003683952279753519,
|
|
"loss": 4.5886,
|
|
"mean_token_accuracy": 0.26297586411237717,
|
|
"num_tokens": 88254890.0,
|
|
"step": 38500
|
|
},
|
|
{
|
|
"entropy": 5.15948076248169,
|
|
"epoch": 3.6988472622478388,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036836403638452477,
|
|
"loss": 4.6846,
|
|
"mean_token_accuracy": 0.2442110851407051,
|
|
"num_tokens": 88267169.0,
|
|
"step": 38505
|
|
},
|
|
{
|
|
"entropy": 5.22315034866333,
|
|
"epoch": 3.6993275696445727,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003683328426260619,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.238990518450737,
|
|
"num_tokens": 88278635.0,
|
|
"step": 38510
|
|
},
|
|
{
|
|
"entropy": 5.1351251125335695,
|
|
"epoch": 3.6998078770413065,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00036830164670068754,
|
|
"loss": 4.6263,
|
|
"mean_token_accuracy": 0.25988602340221406,
|
|
"num_tokens": 88290155.0,
|
|
"step": 38515
|
|
},
|
|
{
|
|
"entropy": 5.171835088729859,
|
|
"epoch": 3.7002881844380404,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00036827044860912605,
|
|
"loss": 4.6579,
|
|
"mean_token_accuracy": 0.2519122377038002,
|
|
"num_tokens": 88301250.0,
|
|
"step": 38520
|
|
},
|
|
{
|
|
"entropy": 5.109819507598877,
|
|
"epoch": 3.7007684918347743,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003682392483521017,
|
|
"loss": 4.683,
|
|
"mean_token_accuracy": 0.25102727562189103,
|
|
"num_tokens": 88312214.0,
|
|
"step": 38525
|
|
},
|
|
{
|
|
"entropy": 5.07659683227539,
|
|
"epoch": 3.701248799231508,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036820804593033893,
|
|
"loss": 4.6766,
|
|
"mean_token_accuracy": 0.25179411470890045,
|
|
"num_tokens": 88322793.0,
|
|
"step": 38530
|
|
},
|
|
{
|
|
"entropy": 5.147150993347168,
|
|
"epoch": 3.701729106628242,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000368176841344562,
|
|
"loss": 4.6657,
|
|
"mean_token_accuracy": 0.2500222444534302,
|
|
"num_tokens": 88335032.0,
|
|
"step": 38535
|
|
},
|
|
{
|
|
"entropy": 5.16916184425354,
|
|
"epoch": 3.702209414024976,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00036814563459549557,
|
|
"loss": 4.6483,
|
|
"mean_token_accuracy": 0.2519660651683807,
|
|
"num_tokens": 88348186.0,
|
|
"step": 38540
|
|
},
|
|
{
|
|
"entropy": 5.233303546905518,
|
|
"epoch": 3.70268972142171,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036811442568386403,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.24616290032863616,
|
|
"num_tokens": 88358117.0,
|
|
"step": 38545
|
|
},
|
|
{
|
|
"entropy": 5.2224987030029295,
|
|
"epoch": 3.7031700288184437,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00036808321461039207,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.2421971306204796,
|
|
"num_tokens": 88368606.0,
|
|
"step": 38550
|
|
},
|
|
{
|
|
"entropy": 5.165818452835083,
|
|
"epoch": 3.7036503362151776,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003680520013758042,
|
|
"loss": 4.6833,
|
|
"mean_token_accuracy": 0.24884069114923477,
|
|
"num_tokens": 88379676.0,
|
|
"step": 38555
|
|
},
|
|
{
|
|
"entropy": 5.166764831542968,
|
|
"epoch": 3.7041306436119115,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00036802078598082523,
|
|
"loss": 4.7114,
|
|
"mean_token_accuracy": 0.245321524143219,
|
|
"num_tokens": 88390824.0,
|
|
"step": 38560
|
|
},
|
|
{
|
|
"entropy": 5.17697286605835,
|
|
"epoch": 3.704610951008646,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003679895684261798,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.2493407279253006,
|
|
"num_tokens": 88401783.0,
|
|
"step": 38565
|
|
},
|
|
{
|
|
"entropy": 5.233603858947754,
|
|
"epoch": 3.7050912584053792,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003679583487125927,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.24533487111330032,
|
|
"num_tokens": 88414366.0,
|
|
"step": 38570
|
|
},
|
|
{
|
|
"entropy": 5.137615060806274,
|
|
"epoch": 3.7055715658021136,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003679271268407888,
|
|
"loss": 4.7536,
|
|
"mean_token_accuracy": 0.24141700565814972,
|
|
"num_tokens": 88425458.0,
|
|
"step": 38575
|
|
},
|
|
{
|
|
"entropy": 5.217066717147827,
|
|
"epoch": 3.706051873198847,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003678959028114929,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.24189923852682113,
|
|
"num_tokens": 88435766.0,
|
|
"step": 38580
|
|
},
|
|
{
|
|
"entropy": 5.187029075622559,
|
|
"epoch": 3.7065321805955813,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00036786467662543,
|
|
"loss": 4.6806,
|
|
"mean_token_accuracy": 0.24997668415308,
|
|
"num_tokens": 88447807.0,
|
|
"step": 38585
|
|
},
|
|
{
|
|
"entropy": 5.137232923507691,
|
|
"epoch": 3.707012487992315,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003678334482833251,
|
|
"loss": 4.6795,
|
|
"mean_token_accuracy": 0.2544376105070114,
|
|
"num_tokens": 88459248.0,
|
|
"step": 38590
|
|
},
|
|
{
|
|
"entropy": 5.114790534973144,
|
|
"epoch": 3.707492795389049,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036780221778590316,
|
|
"loss": 4.6029,
|
|
"mean_token_accuracy": 0.260294708609581,
|
|
"num_tokens": 88471094.0,
|
|
"step": 38595
|
|
},
|
|
{
|
|
"entropy": 5.196448755264282,
|
|
"epoch": 3.707973102785783,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003677709851338893,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.2528925210237503,
|
|
"num_tokens": 88482154.0,
|
|
"step": 38600
|
|
},
|
|
{
|
|
"entropy": 5.172093486785888,
|
|
"epoch": 3.708453410182517,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00036773975032800867,
|
|
"loss": 4.6472,
|
|
"mean_token_accuracy": 0.2530860647559166,
|
|
"num_tokens": 88493267.0,
|
|
"step": 38605
|
|
},
|
|
{
|
|
"entropy": 5.119603013992309,
|
|
"epoch": 3.7089337175792507,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003677085133689864,
|
|
"loss": 4.6767,
|
|
"mean_token_accuracy": 0.2526757627725601,
|
|
"num_tokens": 88505510.0,
|
|
"step": 38610
|
|
},
|
|
{
|
|
"entropy": 5.115421485900879,
|
|
"epoch": 3.7094140249759846,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00036767727425754767,
|
|
"loss": 4.625,
|
|
"mean_token_accuracy": 0.25014727264642717,
|
|
"num_tokens": 88516657.0,
|
|
"step": 38615
|
|
},
|
|
{
|
|
"entropy": 5.172575616836548,
|
|
"epoch": 3.7098943323727185,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003676460329944179,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.2471907064318657,
|
|
"num_tokens": 88527470.0,
|
|
"step": 38620
|
|
},
|
|
{
|
|
"entropy": 5.218940114974975,
|
|
"epoch": 3.7103746397694524,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003676147895803223,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.24618344902992248,
|
|
"num_tokens": 88539267.0,
|
|
"step": 38625
|
|
},
|
|
{
|
|
"entropy": 5.0318902969360355,
|
|
"epoch": 3.7108549471661862,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003675835440159863,
|
|
"loss": 4.5601,
|
|
"mean_token_accuracy": 0.26051594167947767,
|
|
"num_tokens": 88551466.0,
|
|
"step": 38630
|
|
},
|
|
{
|
|
"entropy": 5.085195922851563,
|
|
"epoch": 3.71133525456292,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003675522963021354,
|
|
"loss": 4.614,
|
|
"mean_token_accuracy": 0.25539237558841704,
|
|
"num_tokens": 88563991.0,
|
|
"step": 38635
|
|
},
|
|
{
|
|
"entropy": 5.239408349990844,
|
|
"epoch": 3.7118155619596545,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00036752104643949493,
|
|
"loss": 4.7922,
|
|
"mean_token_accuracy": 0.23769748359918594,
|
|
"num_tokens": 88574308.0,
|
|
"step": 38640
|
|
},
|
|
{
|
|
"entropy": 5.200408267974853,
|
|
"epoch": 3.712295869356388,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003674897944287904,
|
|
"loss": 4.7422,
|
|
"mean_token_accuracy": 0.24393386095762254,
|
|
"num_tokens": 88585510.0,
|
|
"step": 38645
|
|
},
|
|
{
|
|
"entropy": 5.07673659324646,
|
|
"epoch": 3.712776176753122,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003674585402707477,
|
|
"loss": 4.5645,
|
|
"mean_token_accuracy": 0.25904577076435087,
|
|
"num_tokens": 88596575.0,
|
|
"step": 38650
|
|
},
|
|
{
|
|
"entropy": 5.213841819763184,
|
|
"epoch": 3.7132564841498557,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003674272839660921,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.24140862077474595,
|
|
"num_tokens": 88608549.0,
|
|
"step": 38655
|
|
},
|
|
{
|
|
"entropy": 5.078841257095337,
|
|
"epoch": 3.71373679154659,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00036739602551554945,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.2576169639825821,
|
|
"num_tokens": 88620611.0,
|
|
"step": 38660
|
|
},
|
|
{
|
|
"entropy": 5.19709587097168,
|
|
"epoch": 3.714217098943324,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003673647649198454,
|
|
"loss": 4.7402,
|
|
"mean_token_accuracy": 0.24256788790225983,
|
|
"num_tokens": 88630600.0,
|
|
"step": 38665
|
|
},
|
|
{
|
|
"entropy": 5.0955406665802006,
|
|
"epoch": 3.7146974063400577,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00036733350217970593,
|
|
"loss": 4.5935,
|
|
"mean_token_accuracy": 0.2537903398275375,
|
|
"num_tokens": 88642846.0,
|
|
"step": 38670
|
|
},
|
|
{
|
|
"entropy": 5.11826901435852,
|
|
"epoch": 3.7151777137367916,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00036730223729585654,
|
|
"loss": 4.6689,
|
|
"mean_token_accuracy": 0.25451190024614334,
|
|
"num_tokens": 88654981.0,
|
|
"step": 38675
|
|
},
|
|
{
|
|
"entropy": 5.217728948593139,
|
|
"epoch": 3.7156580211335255,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003672709702690234,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.24170441031455994,
|
|
"num_tokens": 88666737.0,
|
|
"step": 38680
|
|
},
|
|
{
|
|
"entropy": 5.152290916442871,
|
|
"epoch": 3.7161383285302594,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00036723970109993223,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.25704324543476104,
|
|
"num_tokens": 88678037.0,
|
|
"step": 38685
|
|
},
|
|
{
|
|
"entropy": 5.123686361312866,
|
|
"epoch": 3.7166186359269933,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003672084297893091,
|
|
"loss": 4.6251,
|
|
"mean_token_accuracy": 0.2496131718158722,
|
|
"num_tokens": 88689215.0,
|
|
"step": 38690
|
|
},
|
|
{
|
|
"entropy": 5.033425760269165,
|
|
"epoch": 3.717098943323727,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00036717715633788014,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.25637820214033125,
|
|
"num_tokens": 88701848.0,
|
|
"step": 38695
|
|
},
|
|
{
|
|
"entropy": 5.115482950210572,
|
|
"epoch": 3.717579250720461,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00036714588074637116,
|
|
"loss": 4.5766,
|
|
"mean_token_accuracy": 0.26210988909006117,
|
|
"num_tokens": 88712745.0,
|
|
"step": 38700
|
|
},
|
|
{
|
|
"entropy": 5.095513772964478,
|
|
"epoch": 3.718059558117195,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003671146030155086,
|
|
"loss": 4.5634,
|
|
"mean_token_accuracy": 0.2630790650844574,
|
|
"num_tokens": 88725048.0,
|
|
"step": 38705
|
|
},
|
|
{
|
|
"entropy": 5.073177766799927,
|
|
"epoch": 3.718539865513929,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003670833231460184,
|
|
"loss": 4.6166,
|
|
"mean_token_accuracy": 0.2535396009683609,
|
|
"num_tokens": 88736218.0,
|
|
"step": 38710
|
|
},
|
|
{
|
|
"entropy": 5.160373735427856,
|
|
"epoch": 3.7190201729106627,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00036705204113862683,
|
|
"loss": 4.7717,
|
|
"mean_token_accuracy": 0.24732548743486404,
|
|
"num_tokens": 88747967.0,
|
|
"step": 38715
|
|
},
|
|
{
|
|
"entropy": 5.180587959289551,
|
|
"epoch": 3.7195004803073966,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003670207569940603,
|
|
"loss": 4.6505,
|
|
"mean_token_accuracy": 0.25463001132011415,
|
|
"num_tokens": 88759565.0,
|
|
"step": 38720
|
|
},
|
|
{
|
|
"entropy": 5.025050687789917,
|
|
"epoch": 3.719980787704131,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00036698947071304495,
|
|
"loss": 4.5074,
|
|
"mean_token_accuracy": 0.2655519798398018,
|
|
"num_tokens": 88771153.0,
|
|
"step": 38725
|
|
},
|
|
{
|
|
"entropy": 5.156895160675049,
|
|
"epoch": 3.7204610951008643,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00036695818229630735,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.24928345680236816,
|
|
"num_tokens": 88782615.0,
|
|
"step": 38730
|
|
},
|
|
{
|
|
"entropy": 5.17026424407959,
|
|
"epoch": 3.7209414024975986,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003669268917445737,
|
|
"loss": 4.6677,
|
|
"mean_token_accuracy": 0.25125877261161805,
|
|
"num_tokens": 88794054.0,
|
|
"step": 38735
|
|
},
|
|
{
|
|
"entropy": 5.133632516860962,
|
|
"epoch": 3.7214217098943325,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003668955990585706,
|
|
"loss": 4.6485,
|
|
"mean_token_accuracy": 0.2555967316031456,
|
|
"num_tokens": 88804094.0,
|
|
"step": 38740
|
|
},
|
|
{
|
|
"entropy": 5.1386559963226315,
|
|
"epoch": 3.7219020172910664,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036686430423902466,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.2503530323505402,
|
|
"num_tokens": 88814661.0,
|
|
"step": 38745
|
|
},
|
|
{
|
|
"entropy": 5.110317230224609,
|
|
"epoch": 3.7223823246878003,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003668330072866623,
|
|
"loss": 4.6768,
|
|
"mean_token_accuracy": 0.24649929106235505,
|
|
"num_tokens": 88825256.0,
|
|
"step": 38750
|
|
},
|
|
{
|
|
"entropy": 5.164038276672363,
|
|
"epoch": 3.722862632084534,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00036680170820221013,
|
|
"loss": 4.6643,
|
|
"mean_token_accuracy": 0.25329040735960007,
|
|
"num_tokens": 88835914.0,
|
|
"step": 38755
|
|
},
|
|
{
|
|
"entropy": 5.107598686218262,
|
|
"epoch": 3.723342939481268,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000366770406986395,
|
|
"loss": 4.6017,
|
|
"mean_token_accuracy": 0.25286502093076707,
|
|
"num_tokens": 88846847.0,
|
|
"step": 38760
|
|
},
|
|
{
|
|
"entropy": 5.175160455703735,
|
|
"epoch": 3.723823246878002,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003667391036399435,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.2460036963224411,
|
|
"num_tokens": 88857899.0,
|
|
"step": 38765
|
|
},
|
|
{
|
|
"entropy": 5.091703081130982,
|
|
"epoch": 3.724303554274736,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003667077981635824,
|
|
"loss": 4.6121,
|
|
"mean_token_accuracy": 0.25800936967134475,
|
|
"num_tokens": 88867972.0,
|
|
"step": 38770
|
|
},
|
|
{
|
|
"entropy": 5.174439382553101,
|
|
"epoch": 3.7247838616714697,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00036667649055803855,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.247245192527771,
|
|
"num_tokens": 88880241.0,
|
|
"step": 38775
|
|
},
|
|
{
|
|
"entropy": 5.240871143341065,
|
|
"epoch": 3.7252641690682036,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00036664518082403876,
|
|
"loss": 4.7046,
|
|
"mean_token_accuracy": 0.24972773492336273,
|
|
"num_tokens": 88891833.0,
|
|
"step": 38780
|
|
},
|
|
{
|
|
"entropy": 5.075713634490967,
|
|
"epoch": 3.7257444764649374,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003666138689623101,
|
|
"loss": 4.5925,
|
|
"mean_token_accuracy": 0.2555830731987953,
|
|
"num_tokens": 88902537.0,
|
|
"step": 38785
|
|
},
|
|
{
|
|
"entropy": 5.102271509170532,
|
|
"epoch": 3.7262247838616713,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00036658255497357936,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.25047138184309004,
|
|
"num_tokens": 88914499.0,
|
|
"step": 38790
|
|
},
|
|
{
|
|
"entropy": 5.223896408081055,
|
|
"epoch": 3.726705091258405,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00036655123885857366,
|
|
"loss": 4.7261,
|
|
"mean_token_accuracy": 0.25109152793884276,
|
|
"num_tokens": 88927240.0,
|
|
"step": 38795
|
|
},
|
|
{
|
|
"entropy": 5.117507600784302,
|
|
"epoch": 3.7271853986551395,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00036651992061802007,
|
|
"loss": 4.6386,
|
|
"mean_token_accuracy": 0.2549307182431221,
|
|
"num_tokens": 88939877.0,
|
|
"step": 38800
|
|
},
|
|
{
|
|
"entropy": 5.075301170349121,
|
|
"epoch": 3.727665706051873,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003664886002526457,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.25394919216632844,
|
|
"num_tokens": 88952144.0,
|
|
"step": 38805
|
|
},
|
|
{
|
|
"entropy": 5.217699956893921,
|
|
"epoch": 3.7281460134486073,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00036645727776317763,
|
|
"loss": 4.7444,
|
|
"mean_token_accuracy": 0.24945712834596634,
|
|
"num_tokens": 88963700.0,
|
|
"step": 38810
|
|
},
|
|
{
|
|
"entropy": 5.256579828262329,
|
|
"epoch": 3.728626320845341,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003664259531503432,
|
|
"loss": 4.7584,
|
|
"mean_token_accuracy": 0.24472009837627412,
|
|
"num_tokens": 88973744.0,
|
|
"step": 38815
|
|
},
|
|
{
|
|
"entropy": 5.135899257659912,
|
|
"epoch": 3.729106628242075,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003663946264148696,
|
|
"loss": 4.6353,
|
|
"mean_token_accuracy": 0.2495298907160759,
|
|
"num_tokens": 88984506.0,
|
|
"step": 38820
|
|
},
|
|
{
|
|
"entropy": 5.180426073074341,
|
|
"epoch": 3.729586935638809,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003663632975574841,
|
|
"loss": 4.7015,
|
|
"mean_token_accuracy": 0.24982781261205672,
|
|
"num_tokens": 88995703.0,
|
|
"step": 38825
|
|
},
|
|
{
|
|
"entropy": 5.090858697891235,
|
|
"epoch": 3.730067243035543,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003663319665789142,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.26015887409448624,
|
|
"num_tokens": 89006529.0,
|
|
"step": 38830
|
|
},
|
|
{
|
|
"entropy": 5.155082321166992,
|
|
"epoch": 3.7305475504322767,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003663006334798872,
|
|
"loss": 4.7298,
|
|
"mean_token_accuracy": 0.24410956650972365,
|
|
"num_tokens": 89018555.0,
|
|
"step": 38835
|
|
},
|
|
{
|
|
"entropy": 5.142388534545899,
|
|
"epoch": 3.7310278578290106,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003662692982611306,
|
|
"loss": 4.5975,
|
|
"mean_token_accuracy": 0.2587051048874855,
|
|
"num_tokens": 89029603.0,
|
|
"step": 38840
|
|
},
|
|
{
|
|
"entropy": 5.10166220664978,
|
|
"epoch": 3.7315081652257445,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00036623796092337196,
|
|
"loss": 4.6508,
|
|
"mean_token_accuracy": 0.251489020884037,
|
|
"num_tokens": 89041560.0,
|
|
"step": 38845
|
|
},
|
|
{
|
|
"entropy": 5.19360237121582,
|
|
"epoch": 3.7319884726224783,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003662066214673388,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.2500130534172058,
|
|
"num_tokens": 89052133.0,
|
|
"step": 38850
|
|
},
|
|
{
|
|
"entropy": 5.086314916610718,
|
|
"epoch": 3.7324687800192122,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003661752798937586,
|
|
"loss": 4.5867,
|
|
"mean_token_accuracy": 0.25192857086658477,
|
|
"num_tokens": 89064829.0,
|
|
"step": 38855
|
|
},
|
|
{
|
|
"entropy": 5.22668194770813,
|
|
"epoch": 3.732949087415946,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00036614393620335923,
|
|
"loss": 4.7748,
|
|
"mean_token_accuracy": 0.24413991272449492,
|
|
"num_tokens": 89076310.0,
|
|
"step": 38860
|
|
},
|
|
{
|
|
"entropy": 5.166942977905274,
|
|
"epoch": 3.73342939481268,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003661125903968683,
|
|
"loss": 4.6923,
|
|
"mean_token_accuracy": 0.24297526925802232,
|
|
"num_tokens": 89088556.0,
|
|
"step": 38865
|
|
},
|
|
{
|
|
"entropy": 5.093750238418579,
|
|
"epoch": 3.733909702209414,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003660812424750135,
|
|
"loss": 4.5314,
|
|
"mean_token_accuracy": 0.2598715707659721,
|
|
"num_tokens": 89100020.0,
|
|
"step": 38870
|
|
},
|
|
{
|
|
"entropy": 5.0447478771209715,
|
|
"epoch": 3.734390009606148,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003660498924385228,
|
|
"loss": 4.5386,
|
|
"mean_token_accuracy": 0.26542953699827193,
|
|
"num_tokens": 89111538.0,
|
|
"step": 38875
|
|
},
|
|
{
|
|
"entropy": 5.149368715286255,
|
|
"epoch": 3.7348703170028816,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036601854028812394,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.24774941504001619,
|
|
"num_tokens": 89122674.0,
|
|
"step": 38880
|
|
},
|
|
{
|
|
"entropy": 5.190080451965332,
|
|
"epoch": 3.735350624399616,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00036598718602454474,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.2499757930636406,
|
|
"num_tokens": 89135165.0,
|
|
"step": 38885
|
|
},
|
|
{
|
|
"entropy": 5.133255863189698,
|
|
"epoch": 3.7358309317963494,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003659558296485133,
|
|
"loss": 4.6305,
|
|
"mean_token_accuracy": 0.2532294183969498,
|
|
"num_tokens": 89146353.0,
|
|
"step": 38890
|
|
},
|
|
{
|
|
"entropy": 5.15035982131958,
|
|
"epoch": 3.7363112391930837,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00036592447116075765,
|
|
"loss": 4.6606,
|
|
"mean_token_accuracy": 0.2477938190102577,
|
|
"num_tokens": 89157589.0,
|
|
"step": 38895
|
|
},
|
|
{
|
|
"entropy": 5.10148401260376,
|
|
"epoch": 3.7367915465898176,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00036589311056200573,
|
|
"loss": 4.6021,
|
|
"mean_token_accuracy": 0.262425634264946,
|
|
"num_tokens": 89169384.0,
|
|
"step": 38900
|
|
},
|
|
{
|
|
"entropy": 5.132775020599365,
|
|
"epoch": 3.7372718539865515,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003658617478529857,
|
|
"loss": 4.6295,
|
|
"mean_token_accuracy": 0.25217088162899015,
|
|
"num_tokens": 89180443.0,
|
|
"step": 38905
|
|
},
|
|
{
|
|
"entropy": 5.098582696914673,
|
|
"epoch": 3.7377521613832854,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00036583038303442567,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.24886466264724733,
|
|
"num_tokens": 89192434.0,
|
|
"step": 38910
|
|
},
|
|
{
|
|
"entropy": 5.1473921775817875,
|
|
"epoch": 3.7382324687800192,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036579901610705377,
|
|
"loss": 4.646,
|
|
"mean_token_accuracy": 0.2504624634981155,
|
|
"num_tokens": 89203965.0,
|
|
"step": 38915
|
|
},
|
|
{
|
|
"entropy": 5.106272029876709,
|
|
"epoch": 3.738712776176753,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00036576764707159853,
|
|
"loss": 4.5969,
|
|
"mean_token_accuracy": 0.24876097291707994,
|
|
"num_tokens": 89214754.0,
|
|
"step": 38920
|
|
},
|
|
{
|
|
"entropy": 5.0652776718139645,
|
|
"epoch": 3.739193083573487,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003657362759287879,
|
|
"loss": 4.5756,
|
|
"mean_token_accuracy": 0.26105867177248,
|
|
"num_tokens": 89226831.0,
|
|
"step": 38925
|
|
},
|
|
{
|
|
"entropy": 5.194700002670288,
|
|
"epoch": 3.739673390970221,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00036570490267935044,
|
|
"loss": 4.7784,
|
|
"mean_token_accuracy": 0.2437843695282936,
|
|
"num_tokens": 89237526.0,
|
|
"step": 38930
|
|
},
|
|
{
|
|
"entropy": 5.09691219329834,
|
|
"epoch": 3.7401536983669548,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00036567352732401443,
|
|
"loss": 4.5147,
|
|
"mean_token_accuracy": 0.26429249048233033,
|
|
"num_tokens": 89248841.0,
|
|
"step": 38935
|
|
},
|
|
{
|
|
"entropy": 5.1220039367675785,
|
|
"epoch": 3.7406340057636887,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00036564214986350844,
|
|
"loss": 4.6249,
|
|
"mean_token_accuracy": 0.25291562676429746,
|
|
"num_tokens": 89260208.0,
|
|
"step": 38940
|
|
},
|
|
{
|
|
"entropy": 5.113967370986939,
|
|
"epoch": 3.7411143131604225,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00036561077029856077,
|
|
"loss": 4.6603,
|
|
"mean_token_accuracy": 0.2620732754468918,
|
|
"num_tokens": 89270844.0,
|
|
"step": 38945
|
|
},
|
|
{
|
|
"entropy": 5.15020899772644,
|
|
"epoch": 3.7415946205571564,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00036557938862990017,
|
|
"loss": 4.7265,
|
|
"mean_token_accuracy": 0.2506668224930763,
|
|
"num_tokens": 89284301.0,
|
|
"step": 38950
|
|
},
|
|
{
|
|
"entropy": 5.1233666896820065,
|
|
"epoch": 3.7420749279538903,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00036554800485825506,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.25193090736866,
|
|
"num_tokens": 89296753.0,
|
|
"step": 38955
|
|
},
|
|
{
|
|
"entropy": 5.197212553024292,
|
|
"epoch": 3.7425552353506246,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00036551661898435414,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.24039781391620635,
|
|
"num_tokens": 89308745.0,
|
|
"step": 38960
|
|
},
|
|
{
|
|
"entropy": 5.168093347549439,
|
|
"epoch": 3.743035542747358,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003654852310089262,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.2562369093298912,
|
|
"num_tokens": 89320273.0,
|
|
"step": 38965
|
|
},
|
|
{
|
|
"entropy": 5.2362383842468265,
|
|
"epoch": 3.7435158501440924,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00036545384093269984,
|
|
"loss": 4.8161,
|
|
"mean_token_accuracy": 0.239684097468853,
|
|
"num_tokens": 89331657.0,
|
|
"step": 38970
|
|
},
|
|
{
|
|
"entropy": 5.109491395950317,
|
|
"epoch": 3.7439961575408263,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00036542244875640385,
|
|
"loss": 4.6222,
|
|
"mean_token_accuracy": 0.25483267456293107,
|
|
"num_tokens": 89342679.0,
|
|
"step": 38975
|
|
},
|
|
{
|
|
"entropy": 5.111223602294922,
|
|
"epoch": 3.74447646493756,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00036539105448076713,
|
|
"loss": 4.5636,
|
|
"mean_token_accuracy": 0.26430184990167616,
|
|
"num_tokens": 89353830.0,
|
|
"step": 38980
|
|
},
|
|
{
|
|
"entropy": 5.051750135421753,
|
|
"epoch": 3.744956772334294,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003653596581065185,
|
|
"loss": 4.5746,
|
|
"mean_token_accuracy": 0.2578745812177658,
|
|
"num_tokens": 89365397.0,
|
|
"step": 38985
|
|
},
|
|
{
|
|
"entropy": 5.068715238571167,
|
|
"epoch": 3.745437079731028,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0003653282596343869,
|
|
"loss": 4.6025,
|
|
"mean_token_accuracy": 0.25124933421611784,
|
|
"num_tokens": 89377255.0,
|
|
"step": 38990
|
|
},
|
|
{
|
|
"entropy": 5.0351637840271,
|
|
"epoch": 3.745917387127762,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003652968590651014,
|
|
"loss": 4.586,
|
|
"mean_token_accuracy": 0.2611438438296318,
|
|
"num_tokens": 89388603.0,
|
|
"step": 38995
|
|
},
|
|
{
|
|
"entropy": 5.194778633117676,
|
|
"epoch": 3.7463976945244957,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00036526545639939097,
|
|
"loss": 4.6737,
|
|
"mean_token_accuracy": 0.25167001932859423,
|
|
"num_tokens": 89400510.0,
|
|
"step": 39000
|
|
},
|
|
{
|
|
"epoch": 3.7463976945244957,
|
|
"eval_entropy": 4.993023019834357,
|
|
"eval_loss": 4.772107124328613,
|
|
"eval_mean_token_accuracy": 0.2536787044770947,
|
|
"eval_num_tokens": 89400510.0,
|
|
"eval_runtime": 26.6643,
|
|
"eval_samples_per_second": 1230.671,
|
|
"eval_steps_per_second": 153.839,
|
|
"step": 39000
|
|
},
|
|
{
|
|
"entropy": 5.2735819816589355,
|
|
"epoch": 3.7468780019212296,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003652340516379846,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.23617671728134154,
|
|
"num_tokens": 89411512.0,
|
|
"step": 39005
|
|
},
|
|
{
|
|
"entropy": 5.1452248096466064,
|
|
"epoch": 3.7473583093179634,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00036520264478161164,
|
|
"loss": 4.6425,
|
|
"mean_token_accuracy": 0.2506869211792946,
|
|
"num_tokens": 89422394.0,
|
|
"step": 39010
|
|
},
|
|
{
|
|
"entropy": 5.095580387115478,
|
|
"epoch": 3.7478386167146973,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0003651712358310009,
|
|
"loss": 4.6227,
|
|
"mean_token_accuracy": 0.25139847248792646,
|
|
"num_tokens": 89433420.0,
|
|
"step": 39015
|
|
},
|
|
{
|
|
"entropy": 5.110257577896118,
|
|
"epoch": 3.748318924111431,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00036513982478688197,
|
|
"loss": 4.6369,
|
|
"mean_token_accuracy": 0.25726188570261,
|
|
"num_tokens": 89444722.0,
|
|
"step": 39020
|
|
},
|
|
{
|
|
"entropy": 5.158622932434082,
|
|
"epoch": 3.748799231508165,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00036510841164998385,
|
|
"loss": 4.666,
|
|
"mean_token_accuracy": 0.25378281325101854,
|
|
"num_tokens": 89456601.0,
|
|
"step": 39025
|
|
},
|
|
{
|
|
"entropy": 5.1304121017456055,
|
|
"epoch": 3.749279538904899,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003650769964210361,
|
|
"loss": 4.6427,
|
|
"mean_token_accuracy": 0.25066311806440356,
|
|
"num_tokens": 89467753.0,
|
|
"step": 39030
|
|
},
|
|
{
|
|
"entropy": 5.222792863845825,
|
|
"epoch": 3.7497598463016333,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003650455791007679,
|
|
"loss": 4.7649,
|
|
"mean_token_accuracy": 0.2399856388568878,
|
|
"num_tokens": 89479303.0,
|
|
"step": 39035
|
|
},
|
|
{
|
|
"entropy": 5.213951826095581,
|
|
"epoch": 3.7502401536983667,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00036501415968990874,
|
|
"loss": 4.6951,
|
|
"mean_token_accuracy": 0.24709775745868684,
|
|
"num_tokens": 89491334.0,
|
|
"step": 39040
|
|
},
|
|
{
|
|
"entropy": 5.048871231079102,
|
|
"epoch": 3.750720461095101,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003649827381891881,
|
|
"loss": 4.5463,
|
|
"mean_token_accuracy": 0.26452588737010957,
|
|
"num_tokens": 89502788.0,
|
|
"step": 39045
|
|
},
|
|
{
|
|
"entropy": 5.091547155380249,
|
|
"epoch": 3.751200768491835,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003649513145993355,
|
|
"loss": 4.6158,
|
|
"mean_token_accuracy": 0.25237528532743453,
|
|
"num_tokens": 89514479.0,
|
|
"step": 39050
|
|
},
|
|
{
|
|
"entropy": 5.118595695495605,
|
|
"epoch": 3.751681075888569,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003649198889210804,
|
|
"loss": 4.6758,
|
|
"mean_token_accuracy": 0.2525202125310898,
|
|
"num_tokens": 89526534.0,
|
|
"step": 39055
|
|
},
|
|
{
|
|
"entropy": 5.180159187316894,
|
|
"epoch": 3.7521613832853027,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003648884611551525,
|
|
"loss": 4.6708,
|
|
"mean_token_accuracy": 0.2575022980570793,
|
|
"num_tokens": 89537231.0,
|
|
"step": 39060
|
|
},
|
|
{
|
|
"entropy": 5.140023231506348,
|
|
"epoch": 3.7526416906820366,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00036485703130228147,
|
|
"loss": 4.6566,
|
|
"mean_token_accuracy": 0.24531181305646896,
|
|
"num_tokens": 89547374.0,
|
|
"step": 39065
|
|
},
|
|
{
|
|
"entropy": 5.062006187438965,
|
|
"epoch": 3.7531219980787704,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00036482559936319703,
|
|
"loss": 4.5593,
|
|
"mean_token_accuracy": 0.25386263281106947,
|
|
"num_tokens": 89557776.0,
|
|
"step": 39070
|
|
},
|
|
{
|
|
"entropy": 5.121845817565918,
|
|
"epoch": 3.7536023054755043,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00036479416533862885,
|
|
"loss": 4.6527,
|
|
"mean_token_accuracy": 0.2521669790148735,
|
|
"num_tokens": 89569181.0,
|
|
"step": 39075
|
|
},
|
|
{
|
|
"entropy": 5.225430488586426,
|
|
"epoch": 3.754082612872238,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00036476272922930674,
|
|
"loss": 4.6511,
|
|
"mean_token_accuracy": 0.25166230350732804,
|
|
"num_tokens": 89580375.0,
|
|
"step": 39080
|
|
},
|
|
{
|
|
"entropy": 5.205957508087158,
|
|
"epoch": 3.754562920268972,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00036473129103596077,
|
|
"loss": 4.7365,
|
|
"mean_token_accuracy": 0.24643545597791672,
|
|
"num_tokens": 89591787.0,
|
|
"step": 39085
|
|
},
|
|
{
|
|
"entropy": 5.05412483215332,
|
|
"epoch": 3.755043227665706,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003646998507593205,
|
|
"loss": 4.6272,
|
|
"mean_token_accuracy": 0.24963872134685516,
|
|
"num_tokens": 89604389.0,
|
|
"step": 39090
|
|
},
|
|
{
|
|
"entropy": 5.013670110702515,
|
|
"epoch": 3.75552353506244,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003646684084001161,
|
|
"loss": 4.5347,
|
|
"mean_token_accuracy": 0.26669436097145083,
|
|
"num_tokens": 89615900.0,
|
|
"step": 39095
|
|
},
|
|
{
|
|
"entropy": 5.078435182571411,
|
|
"epoch": 3.7560038424591737,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003646369639590776,
|
|
"loss": 4.5792,
|
|
"mean_token_accuracy": 0.2527412369847298,
|
|
"num_tokens": 89627056.0,
|
|
"step": 39100
|
|
},
|
|
{
|
|
"entropy": 5.094937324523926,
|
|
"epoch": 3.7564841498559076,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003646055174369348,
|
|
"loss": 4.5872,
|
|
"mean_token_accuracy": 0.2573951959609985,
|
|
"num_tokens": 89637194.0,
|
|
"step": 39105
|
|
},
|
|
{
|
|
"entropy": 5.1515215873718265,
|
|
"epoch": 3.756964457252642,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003645740688344181,
|
|
"loss": 4.6518,
|
|
"mean_token_accuracy": 0.25244968980550764,
|
|
"num_tokens": 89648132.0,
|
|
"step": 39110
|
|
},
|
|
{
|
|
"entropy": 5.144691467285156,
|
|
"epoch": 3.7574447646493754,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003645426181522575,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.2560276255011559,
|
|
"num_tokens": 89658236.0,
|
|
"step": 39115
|
|
},
|
|
{
|
|
"entropy": 5.150832223892212,
|
|
"epoch": 3.7579250720461097,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00036451116539118304,
|
|
"loss": 4.6541,
|
|
"mean_token_accuracy": 0.24489172846078872,
|
|
"num_tokens": 89669660.0,
|
|
"step": 39120
|
|
},
|
|
{
|
|
"entropy": 5.097449064254761,
|
|
"epoch": 3.7584053794428436,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00036447971055192526,
|
|
"loss": 4.6311,
|
|
"mean_token_accuracy": 0.2510438084602356,
|
|
"num_tokens": 89681667.0,
|
|
"step": 39125
|
|
},
|
|
{
|
|
"entropy": 4.974386930465698,
|
|
"epoch": 3.7588856868395775,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003644482536352142,
|
|
"loss": 4.5034,
|
|
"mean_token_accuracy": 0.2653383895754814,
|
|
"num_tokens": 89694924.0,
|
|
"step": 39130
|
|
},
|
|
{
|
|
"entropy": 5.124817943572998,
|
|
"epoch": 3.7593659942363113,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00036441679464178044,
|
|
"loss": 4.638,
|
|
"mean_token_accuracy": 0.2540507659316063,
|
|
"num_tokens": 89705855.0,
|
|
"step": 39135
|
|
},
|
|
{
|
|
"entropy": 5.137297964096069,
|
|
"epoch": 3.7598463016330452,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003643853335723541,
|
|
"loss": 4.6304,
|
|
"mean_token_accuracy": 0.25100077688694,
|
|
"num_tokens": 89716766.0,
|
|
"step": 39140
|
|
},
|
|
{
|
|
"entropy": 5.153936195373535,
|
|
"epoch": 3.760326609029779,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00036435387042766575,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.2513232186436653,
|
|
"num_tokens": 89729595.0,
|
|
"step": 39145
|
|
},
|
|
{
|
|
"entropy": 5.092988014221191,
|
|
"epoch": 3.760806916426513,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003643224052084459,
|
|
"loss": 4.6242,
|
|
"mean_token_accuracy": 0.25195445120334625,
|
|
"num_tokens": 89740972.0,
|
|
"step": 39150
|
|
},
|
|
{
|
|
"entropy": 5.083464813232422,
|
|
"epoch": 3.761287223823247,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000364290937915425,
|
|
"loss": 4.6557,
|
|
"mean_token_accuracy": 0.2506023749709129,
|
|
"num_tokens": 89754660.0,
|
|
"step": 39155
|
|
},
|
|
{
|
|
"entropy": 5.230108737945557,
|
|
"epoch": 3.7617675312199808,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036425946854933374,
|
|
"loss": 4.7427,
|
|
"mean_token_accuracy": 0.24552324265241623,
|
|
"num_tokens": 89766298.0,
|
|
"step": 39160
|
|
},
|
|
{
|
|
"entropy": 5.187093734741211,
|
|
"epoch": 3.7622478386167146,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00036422799711090253,
|
|
"loss": 4.7071,
|
|
"mean_token_accuracy": 0.2480392947793007,
|
|
"num_tokens": 89778133.0,
|
|
"step": 39165
|
|
},
|
|
{
|
|
"entropy": 5.091800689697266,
|
|
"epoch": 3.7627281460134485,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003641965236008623,
|
|
"loss": 4.6639,
|
|
"mean_token_accuracy": 0.2535840839147568,
|
|
"num_tokens": 89789408.0,
|
|
"step": 39170
|
|
},
|
|
{
|
|
"entropy": 5.123193025588989,
|
|
"epoch": 3.7632084534101824,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003641650480199436,
|
|
"loss": 4.6248,
|
|
"mean_token_accuracy": 0.25515889972448347,
|
|
"num_tokens": 89800287.0,
|
|
"step": 39175
|
|
},
|
|
{
|
|
"entropy": 5.132559013366699,
|
|
"epoch": 3.7636887608069163,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00036413357036887723,
|
|
"loss": 4.6255,
|
|
"mean_token_accuracy": 0.24707266241312026,
|
|
"num_tokens": 89811639.0,
|
|
"step": 39180
|
|
},
|
|
{
|
|
"entropy": 5.140863752365112,
|
|
"epoch": 3.7641690682036506,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000364102090648394,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.2471991151571274,
|
|
"num_tokens": 89823075.0,
|
|
"step": 39185
|
|
},
|
|
{
|
|
"entropy": 5.024941349029541,
|
|
"epoch": 3.764649375600384,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003640706088592249,
|
|
"loss": 4.6187,
|
|
"mean_token_accuracy": 0.25474184304475783,
|
|
"num_tokens": 89835268.0,
|
|
"step": 39190
|
|
},
|
|
{
|
|
"entropy": 5.180916786193848,
|
|
"epoch": 3.7651296829971184,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00036403912500210066,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.24455203860998154,
|
|
"num_tokens": 89846983.0,
|
|
"step": 39195
|
|
},
|
|
{
|
|
"entropy": 5.144278860092163,
|
|
"epoch": 3.765609990393852,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003640076390777524,
|
|
"loss": 4.6255,
|
|
"mean_token_accuracy": 0.25468519926071165,
|
|
"num_tokens": 89857372.0,
|
|
"step": 39200
|
|
},
|
|
{
|
|
"entropy": 5.118162727355957,
|
|
"epoch": 3.766090297790586,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000363976151086911,
|
|
"loss": 4.6557,
|
|
"mean_token_accuracy": 0.25149705410003664,
|
|
"num_tokens": 89869286.0,
|
|
"step": 39205
|
|
},
|
|
{
|
|
"entropy": 5.166934394836426,
|
|
"epoch": 3.76657060518732,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003639446610303076,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.25343262404203415,
|
|
"num_tokens": 89879646.0,
|
|
"step": 39210
|
|
},
|
|
{
|
|
"entropy": 5.109432744979858,
|
|
"epoch": 3.767050912584054,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00036391316890867334,
|
|
"loss": 4.6273,
|
|
"mean_token_accuracy": 0.2579242095351219,
|
|
"num_tokens": 89891870.0,
|
|
"step": 39215
|
|
},
|
|
{
|
|
"entropy": 5.1624175071716305,
|
|
"epoch": 3.7675312199807878,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00036388167472273925,
|
|
"loss": 4.6521,
|
|
"mean_token_accuracy": 0.25273136496543885,
|
|
"num_tokens": 89903383.0,
|
|
"step": 39220
|
|
},
|
|
{
|
|
"entropy": 5.249175786972046,
|
|
"epoch": 3.7680115273775217,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003638501784732366,
|
|
"loss": 4.8513,
|
|
"mean_token_accuracy": 0.24009032398462296,
|
|
"num_tokens": 89913707.0,
|
|
"step": 39225
|
|
},
|
|
{
|
|
"entropy": 5.077703523635864,
|
|
"epoch": 3.7684918347742555,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003638186801608966,
|
|
"loss": 4.5997,
|
|
"mean_token_accuracy": 0.2628515660762787,
|
|
"num_tokens": 89924983.0,
|
|
"step": 39230
|
|
},
|
|
{
|
|
"entropy": 5.105389165878296,
|
|
"epoch": 3.7689721421709894,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00036378717978645067,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.24979488253593446,
|
|
"num_tokens": 89936404.0,
|
|
"step": 39235
|
|
},
|
|
{
|
|
"entropy": 5.219692277908325,
|
|
"epoch": 3.7694524495677233,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036375567735063,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.249610298871994,
|
|
"num_tokens": 89947916.0,
|
|
"step": 39240
|
|
},
|
|
{
|
|
"entropy": 5.203407287597656,
|
|
"epoch": 3.769932756964457,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003637241728541661,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.2518506392836571,
|
|
"num_tokens": 89959436.0,
|
|
"step": 39245
|
|
},
|
|
{
|
|
"entropy": 5.169427013397216,
|
|
"epoch": 3.770413064361191,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00036369266629779037,
|
|
"loss": 4.6527,
|
|
"mean_token_accuracy": 0.2519994452595711,
|
|
"num_tokens": 89969977.0,
|
|
"step": 39250
|
|
},
|
|
{
|
|
"entropy": 5.124570417404175,
|
|
"epoch": 3.770893371757925,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003636611576822342,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.244163616001606,
|
|
"num_tokens": 89981189.0,
|
|
"step": 39255
|
|
},
|
|
{
|
|
"entropy": 5.087349796295166,
|
|
"epoch": 3.771373679154659,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003636296470082293,
|
|
"loss": 4.7036,
|
|
"mean_token_accuracy": 0.24581552892923356,
|
|
"num_tokens": 89994120.0,
|
|
"step": 39260
|
|
},
|
|
{
|
|
"entropy": 5.054660129547119,
|
|
"epoch": 3.7718539865513927,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00036359813427650726,
|
|
"loss": 4.5252,
|
|
"mean_token_accuracy": 0.2635683432221413,
|
|
"num_tokens": 90005953.0,
|
|
"step": 39265
|
|
},
|
|
{
|
|
"entropy": 5.070942497253418,
|
|
"epoch": 3.772334293948127,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00036356661948779945,
|
|
"loss": 4.5829,
|
|
"mean_token_accuracy": 0.2529241591691971,
|
|
"num_tokens": 90017875.0,
|
|
"step": 39270
|
|
},
|
|
{
|
|
"entropy": 5.167127799987793,
|
|
"epoch": 3.7728146013448605,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00036353510264283776,
|
|
"loss": 4.6501,
|
|
"mean_token_accuracy": 0.2504694238305092,
|
|
"num_tokens": 90028096.0,
|
|
"step": 39275
|
|
},
|
|
{
|
|
"entropy": 5.196051359176636,
|
|
"epoch": 3.773294908741595,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003635035837423539,
|
|
"loss": 4.6743,
|
|
"mean_token_accuracy": 0.2497960075736046,
|
|
"num_tokens": 90038834.0,
|
|
"step": 39280
|
|
},
|
|
{
|
|
"entropy": 5.160498237609863,
|
|
"epoch": 3.7737752161383287,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003634720627870797,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.24911216348409654,
|
|
"num_tokens": 90051429.0,
|
|
"step": 39285
|
|
},
|
|
{
|
|
"entropy": 5.118266487121582,
|
|
"epoch": 3.7742555235350626,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00036344053977774684,
|
|
"loss": 4.6099,
|
|
"mean_token_accuracy": 0.25606291443109513,
|
|
"num_tokens": 90062269.0,
|
|
"step": 39290
|
|
},
|
|
{
|
|
"entropy": 5.066531324386597,
|
|
"epoch": 3.7747358309317964,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003634090147150873,
|
|
"loss": 4.6075,
|
|
"mean_token_accuracy": 0.26004396080970765,
|
|
"num_tokens": 90073573.0,
|
|
"step": 39295
|
|
},
|
|
{
|
|
"entropy": 5.102369737625122,
|
|
"epoch": 3.7752161383285303,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003633774875998329,
|
|
"loss": 4.5305,
|
|
"mean_token_accuracy": 0.2616272509098053,
|
|
"num_tokens": 90083543.0,
|
|
"step": 39300
|
|
},
|
|
{
|
|
"entropy": 5.133606338500977,
|
|
"epoch": 3.775696445725264,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003633459584327157,
|
|
"loss": 4.6878,
|
|
"mean_token_accuracy": 0.24789015352725982,
|
|
"num_tokens": 90095108.0,
|
|
"step": 39305
|
|
},
|
|
{
|
|
"entropy": 5.15880389213562,
|
|
"epoch": 3.776176753121998,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00036331442721446763,
|
|
"loss": 4.7704,
|
|
"mean_token_accuracy": 0.24168960899114608,
|
|
"num_tokens": 90107272.0,
|
|
"step": 39310
|
|
},
|
|
{
|
|
"entropy": 5.227480554580689,
|
|
"epoch": 3.776657060518732,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003632828939458209,
|
|
"loss": 4.7148,
|
|
"mean_token_accuracy": 0.24311331212520598,
|
|
"num_tokens": 90118167.0,
|
|
"step": 39315
|
|
},
|
|
{
|
|
"entropy": 5.163632440567016,
|
|
"epoch": 3.777137367915466,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00036325135862750745,
|
|
"loss": 4.6515,
|
|
"mean_token_accuracy": 0.24519377052783967,
|
|
"num_tokens": 90129790.0,
|
|
"step": 39320
|
|
},
|
|
{
|
|
"entropy": 5.119464969635009,
|
|
"epoch": 3.7776176753121997,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00036321982126025947,
|
|
"loss": 4.6623,
|
|
"mean_token_accuracy": 0.2478703811764717,
|
|
"num_tokens": 90141367.0,
|
|
"step": 39325
|
|
},
|
|
{
|
|
"entropy": 5.127146148681641,
|
|
"epoch": 3.7780979827089336,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003631882818448093,
|
|
"loss": 4.6309,
|
|
"mean_token_accuracy": 0.25522712916135787,
|
|
"num_tokens": 90151755.0,
|
|
"step": 39330
|
|
},
|
|
{
|
|
"entropy": 5.111348104476929,
|
|
"epoch": 3.7785782901056675,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00036315674038188905,
|
|
"loss": 4.6327,
|
|
"mean_token_accuracy": 0.2549299329519272,
|
|
"num_tokens": 90163262.0,
|
|
"step": 39335
|
|
},
|
|
{
|
|
"entropy": 5.304360342025757,
|
|
"epoch": 3.7790585975024014,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000363125196872231,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.23647709488868712,
|
|
"num_tokens": 90174704.0,
|
|
"step": 39340
|
|
},
|
|
{
|
|
"entropy": 5.130851173400879,
|
|
"epoch": 3.7795389048991357,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003630936513165676,
|
|
"loss": 4.5681,
|
|
"mean_token_accuracy": 0.25602699220180514,
|
|
"num_tokens": 90186885.0,
|
|
"step": 39345
|
|
},
|
|
{
|
|
"entropy": 5.12833309173584,
|
|
"epoch": 3.780019212295869,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003630621037156312,
|
|
"loss": 4.6281,
|
|
"mean_token_accuracy": 0.2557671755552292,
|
|
"num_tokens": 90198213.0,
|
|
"step": 39350
|
|
},
|
|
{
|
|
"entropy": 5.175882053375244,
|
|
"epoch": 3.7804995196926034,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00036303055407015437,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.2509311482310295,
|
|
"num_tokens": 90209623.0,
|
|
"step": 39355
|
|
},
|
|
{
|
|
"entropy": 5.156571674346924,
|
|
"epoch": 3.7809798270893373,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00036299900238086924,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.2528795421123505,
|
|
"num_tokens": 90221808.0,
|
|
"step": 39360
|
|
},
|
|
{
|
|
"entropy": 5.158152484893799,
|
|
"epoch": 3.781460134486071,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003629674486485087,
|
|
"loss": 4.6605,
|
|
"mean_token_accuracy": 0.24626469016075134,
|
|
"num_tokens": 90232894.0,
|
|
"step": 39365
|
|
},
|
|
{
|
|
"entropy": 5.079264736175537,
|
|
"epoch": 3.781940441882805,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003629358928738052,
|
|
"loss": 4.5708,
|
|
"mean_token_accuracy": 0.2595053821802139,
|
|
"num_tokens": 90243240.0,
|
|
"step": 39370
|
|
},
|
|
{
|
|
"entropy": 5.067290210723877,
|
|
"epoch": 3.782420749279539,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00036290433505749135,
|
|
"loss": 4.5724,
|
|
"mean_token_accuracy": 0.2614258497953415,
|
|
"num_tokens": 90255082.0,
|
|
"step": 39375
|
|
},
|
|
{
|
|
"entropy": 5.223908948898315,
|
|
"epoch": 3.782901056676273,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003628727752002999,
|
|
"loss": 4.7213,
|
|
"mean_token_accuracy": 0.24593911021947862,
|
|
"num_tokens": 90266521.0,
|
|
"step": 39380
|
|
},
|
|
{
|
|
"entropy": 5.09825644493103,
|
|
"epoch": 3.7833813640730067,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003628412133029636,
|
|
"loss": 4.5607,
|
|
"mean_token_accuracy": 0.2582599028944969,
|
|
"num_tokens": 90277145.0,
|
|
"step": 39385
|
|
},
|
|
{
|
|
"entropy": 5.016064167022705,
|
|
"epoch": 3.7838616714697406,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003628096493662151,
|
|
"loss": 4.5405,
|
|
"mean_token_accuracy": 0.25873593538999556,
|
|
"num_tokens": 90289290.0,
|
|
"step": 39390
|
|
},
|
|
{
|
|
"entropy": 5.157488107681274,
|
|
"epoch": 3.7843419788664745,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003627780833907873,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.25192315727472303,
|
|
"num_tokens": 90299863.0,
|
|
"step": 39395
|
|
},
|
|
{
|
|
"entropy": 5.09613356590271,
|
|
"epoch": 3.7848222862632084,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00036274651537741305,
|
|
"loss": 4.6744,
|
|
"mean_token_accuracy": 0.25005715191364286,
|
|
"num_tokens": 90310905.0,
|
|
"step": 39400
|
|
},
|
|
{
|
|
"entropy": 5.123774194717408,
|
|
"epoch": 3.7853025936599423,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003627149453268252,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.24856168180704116,
|
|
"num_tokens": 90322971.0,
|
|
"step": 39405
|
|
},
|
|
{
|
|
"entropy": 5.21009316444397,
|
|
"epoch": 3.785782901056676,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00036268337323975685,
|
|
"loss": 4.6553,
|
|
"mean_token_accuracy": 0.2536838039755821,
|
|
"num_tokens": 90333782.0,
|
|
"step": 39410
|
|
},
|
|
{
|
|
"entropy": 5.250014543533325,
|
|
"epoch": 3.78626320845341,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036265179911694094,
|
|
"loss": 4.7707,
|
|
"mean_token_accuracy": 0.2400129497051239,
|
|
"num_tokens": 90343695.0,
|
|
"step": 39415
|
|
},
|
|
{
|
|
"entropy": 5.075033521652221,
|
|
"epoch": 3.7867435158501443,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003626202229591105,
|
|
"loss": 4.6113,
|
|
"mean_token_accuracy": 0.25327838957309723,
|
|
"num_tokens": 90354932.0,
|
|
"step": 39420
|
|
},
|
|
{
|
|
"entropy": 5.1328634262084964,
|
|
"epoch": 3.787223823246878,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00036258864476699864,
|
|
"loss": 4.6494,
|
|
"mean_token_accuracy": 0.25253191143274306,
|
|
"num_tokens": 90367449.0,
|
|
"step": 39425
|
|
},
|
|
{
|
|
"entropy": 5.060295057296753,
|
|
"epoch": 3.787704130643612,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003625570645413386,
|
|
"loss": 4.5438,
|
|
"mean_token_accuracy": 0.26698967069387436,
|
|
"num_tokens": 90378915.0,
|
|
"step": 39430
|
|
},
|
|
{
|
|
"entropy": 5.124792003631592,
|
|
"epoch": 3.7881844380403455,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003625254822828635,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.2556629940867424,
|
|
"num_tokens": 90391868.0,
|
|
"step": 39435
|
|
},
|
|
{
|
|
"entropy": 5.16754846572876,
|
|
"epoch": 3.78866474543708,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003624938979923065,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.2460680603981018,
|
|
"num_tokens": 90402520.0,
|
|
"step": 39440
|
|
},
|
|
{
|
|
"entropy": 5.235311841964721,
|
|
"epoch": 3.7891450528338138,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00036246231167040105,
|
|
"loss": 4.7564,
|
|
"mean_token_accuracy": 0.24215202778577805,
|
|
"num_tokens": 90413425.0,
|
|
"step": 39445
|
|
},
|
|
{
|
|
"entropy": 5.276628875732422,
|
|
"epoch": 3.7896253602305476,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003624307233178805,
|
|
"loss": 4.7925,
|
|
"mean_token_accuracy": 0.24353133589029313,
|
|
"num_tokens": 90424976.0,
|
|
"step": 39450
|
|
},
|
|
{
|
|
"entropy": 5.129418087005615,
|
|
"epoch": 3.7901056676272815,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00036239913293547807,
|
|
"loss": 4.5738,
|
|
"mean_token_accuracy": 0.25636095106601714,
|
|
"num_tokens": 90436177.0,
|
|
"step": 39455
|
|
},
|
|
{
|
|
"entropy": 5.154420471191406,
|
|
"epoch": 3.7905859750240154,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00036236754052392737,
|
|
"loss": 4.7068,
|
|
"mean_token_accuracy": 0.25366606265306474,
|
|
"num_tokens": 90448066.0,
|
|
"step": 39460
|
|
},
|
|
{
|
|
"entropy": 5.103705978393554,
|
|
"epoch": 3.7910662824207493,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003623359460839618,
|
|
"loss": 4.5929,
|
|
"mean_token_accuracy": 0.2576447129249573,
|
|
"num_tokens": 90457913.0,
|
|
"step": 39465
|
|
},
|
|
{
|
|
"entropy": 5.053568983078003,
|
|
"epoch": 3.791546589817483,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003623043496163149,
|
|
"loss": 4.5917,
|
|
"mean_token_accuracy": 0.2629197552800179,
|
|
"num_tokens": 90469637.0,
|
|
"step": 39470
|
|
},
|
|
{
|
|
"entropy": 5.095473146438598,
|
|
"epoch": 3.792026897214217,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003622727511217202,
|
|
"loss": 4.648,
|
|
"mean_token_accuracy": 0.2539825662970543,
|
|
"num_tokens": 90481222.0,
|
|
"step": 39475
|
|
},
|
|
{
|
|
"entropy": 5.13051815032959,
|
|
"epoch": 3.792507204610951,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003622411506009113,
|
|
"loss": 4.5898,
|
|
"mean_token_accuracy": 0.25582021474838257,
|
|
"num_tokens": 90492911.0,
|
|
"step": 39480
|
|
},
|
|
{
|
|
"entropy": 5.11373381614685,
|
|
"epoch": 3.792987512007685,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003622095480546221,
|
|
"loss": 4.6784,
|
|
"mean_token_accuracy": 0.251277431845665,
|
|
"num_tokens": 90504583.0,
|
|
"step": 39485
|
|
},
|
|
{
|
|
"entropy": 5.136473655700684,
|
|
"epoch": 3.7934678194044187,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00036217794348358606,
|
|
"loss": 4.6729,
|
|
"mean_token_accuracy": 0.24837695062160492,
|
|
"num_tokens": 90516006.0,
|
|
"step": 39490
|
|
},
|
|
{
|
|
"entropy": 5.021417760848999,
|
|
"epoch": 3.793948126801153,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000362146336888537,
|
|
"loss": 4.533,
|
|
"mean_token_accuracy": 0.2557872772216797,
|
|
"num_tokens": 90527362.0,
|
|
"step": 39495
|
|
},
|
|
{
|
|
"entropy": 5.0873456478118895,
|
|
"epoch": 3.7944284341978864,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00036211472827020886,
|
|
"loss": 4.6131,
|
|
"mean_token_accuracy": 0.25709992945194243,
|
|
"num_tokens": 90538635.0,
|
|
"step": 39500
|
|
},
|
|
{
|
|
"entropy": 5.1544147491455075,
|
|
"epoch": 3.7949087415946208,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003620831176293354,
|
|
"loss": 4.6335,
|
|
"mean_token_accuracy": 0.2605398714542389,
|
|
"num_tokens": 90549996.0,
|
|
"step": 39505
|
|
},
|
|
{
|
|
"entropy": 5.1931110382080075,
|
|
"epoch": 3.795389048991354,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00036205150496665053,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.24623026549816132,
|
|
"num_tokens": 90563360.0,
|
|
"step": 39510
|
|
},
|
|
{
|
|
"entropy": 5.158077430725098,
|
|
"epoch": 3.7958693563880885,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00036201989028288815,
|
|
"loss": 4.7299,
|
|
"mean_token_accuracy": 0.2453143924474716,
|
|
"num_tokens": 90574617.0,
|
|
"step": 39515
|
|
},
|
|
{
|
|
"entropy": 5.181391000747681,
|
|
"epoch": 3.7963496637848224,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00036198827357878234,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.2457110106945038,
|
|
"num_tokens": 90586209.0,
|
|
"step": 39520
|
|
},
|
|
{
|
|
"entropy": 5.235628843307495,
|
|
"epoch": 3.7968299711815563,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0003619566548550671,
|
|
"loss": 4.7295,
|
|
"mean_token_accuracy": 0.24340281635522842,
|
|
"num_tokens": 90598409.0,
|
|
"step": 39525
|
|
},
|
|
{
|
|
"entropy": 5.149516153335571,
|
|
"epoch": 3.79731027857829,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003619250341124765,
|
|
"loss": 4.6375,
|
|
"mean_token_accuracy": 0.2553501710295677,
|
|
"num_tokens": 90610073.0,
|
|
"step": 39530
|
|
},
|
|
{
|
|
"entropy": 5.139547491073609,
|
|
"epoch": 3.797790585975024,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003618934113517448,
|
|
"loss": 4.7046,
|
|
"mean_token_accuracy": 0.2569425210356712,
|
|
"num_tokens": 90621782.0,
|
|
"step": 39535
|
|
},
|
|
{
|
|
"entropy": 5.101996278762817,
|
|
"epoch": 3.798270893371758,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003618617865736061,
|
|
"loss": 4.6673,
|
|
"mean_token_accuracy": 0.24831446558237075,
|
|
"num_tokens": 90633771.0,
|
|
"step": 39540
|
|
},
|
|
{
|
|
"entropy": 5.232988595962524,
|
|
"epoch": 3.798751200768492,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00036183015977879463,
|
|
"loss": 4.772,
|
|
"mean_token_accuracy": 0.24496597349643706,
|
|
"num_tokens": 90644965.0,
|
|
"step": 39545
|
|
},
|
|
{
|
|
"entropy": 5.124420022964477,
|
|
"epoch": 3.7992315081652257,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00036179853096804474,
|
|
"loss": 4.6177,
|
|
"mean_token_accuracy": 0.25049096196889875,
|
|
"num_tokens": 90656691.0,
|
|
"step": 39550
|
|
},
|
|
{
|
|
"entropy": 5.195028066635132,
|
|
"epoch": 3.7997118155619596,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00036176690014209055,
|
|
"loss": 4.6862,
|
|
"mean_token_accuracy": 0.25199016481637954,
|
|
"num_tokens": 90667760.0,
|
|
"step": 39555
|
|
},
|
|
{
|
|
"entropy": 5.113772535324097,
|
|
"epoch": 3.8001921229586935,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003617352673016667,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.25251376777887347,
|
|
"num_tokens": 90679640.0,
|
|
"step": 39560
|
|
},
|
|
{
|
|
"entropy": 5.114813423156738,
|
|
"epoch": 3.8006724303554273,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00036170363244750756,
|
|
"loss": 4.5858,
|
|
"mean_token_accuracy": 0.2618915200233459,
|
|
"num_tokens": 90693187.0,
|
|
"step": 39565
|
|
},
|
|
{
|
|
"entropy": 5.220853567123413,
|
|
"epoch": 3.8011527377521612,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003616719955803474,
|
|
"loss": 4.7812,
|
|
"mean_token_accuracy": 0.24330692738294601,
|
|
"num_tokens": 90704540.0,
|
|
"step": 39570
|
|
},
|
|
{
|
|
"entropy": 5.130422163009643,
|
|
"epoch": 3.801633045148895,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003616403567009209,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.2626357972621918,
|
|
"num_tokens": 90716577.0,
|
|
"step": 39575
|
|
},
|
|
{
|
|
"entropy": 5.047927951812744,
|
|
"epoch": 3.8021133525456294,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003616087158099626,
|
|
"loss": 4.5081,
|
|
"mean_token_accuracy": 0.2656306877732277,
|
|
"num_tokens": 90727134.0,
|
|
"step": 39580
|
|
},
|
|
{
|
|
"entropy": 5.105481338500977,
|
|
"epoch": 3.802593659942363,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003615770729082071,
|
|
"loss": 4.6487,
|
|
"mean_token_accuracy": 0.25651742666959765,
|
|
"num_tokens": 90738844.0,
|
|
"step": 39585
|
|
},
|
|
{
|
|
"entropy": 5.101681756973266,
|
|
"epoch": 3.803073967339097,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000361545427996389,
|
|
"loss": 4.6032,
|
|
"mean_token_accuracy": 0.25784257650375364,
|
|
"num_tokens": 90749882.0,
|
|
"step": 39590
|
|
},
|
|
{
|
|
"entropy": 5.193703651428223,
|
|
"epoch": 3.803554274735831,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003615137810752431,
|
|
"loss": 4.6681,
|
|
"mean_token_accuracy": 0.2546866923570633,
|
|
"num_tokens": 90762244.0,
|
|
"step": 39595
|
|
},
|
|
{
|
|
"entropy": 5.218584251403809,
|
|
"epoch": 3.804034582132565,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00036148213214550406,
|
|
"loss": 4.7433,
|
|
"mean_token_accuracy": 0.2575551509857178,
|
|
"num_tokens": 90774452.0,
|
|
"step": 39600
|
|
},
|
|
{
|
|
"entropy": 5.141557836532593,
|
|
"epoch": 3.804514889529299,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003614504812079068,
|
|
"loss": 4.6373,
|
|
"mean_token_accuracy": 0.2555434688925743,
|
|
"num_tokens": 90785506.0,
|
|
"step": 39605
|
|
},
|
|
{
|
|
"entropy": 5.09242959022522,
|
|
"epoch": 3.8049951969260327,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00036141882826318597,
|
|
"loss": 4.5654,
|
|
"mean_token_accuracy": 0.25971696674823763,
|
|
"num_tokens": 90796606.0,
|
|
"step": 39610
|
|
},
|
|
{
|
|
"entropy": 5.144300270080566,
|
|
"epoch": 3.8054755043227666,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003613871733120766,
|
|
"loss": 4.6785,
|
|
"mean_token_accuracy": 0.2585678815841675,
|
|
"num_tokens": 90807949.0,
|
|
"step": 39615
|
|
},
|
|
{
|
|
"entropy": 5.173112201690674,
|
|
"epoch": 3.8059558117195005,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00036135551635531354,
|
|
"loss": 4.7322,
|
|
"mean_token_accuracy": 0.24850808531045915,
|
|
"num_tokens": 90819206.0,
|
|
"step": 39620
|
|
},
|
|
{
|
|
"entropy": 5.267878246307373,
|
|
"epoch": 3.8064361191162344,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003613238573936319,
|
|
"loss": 4.7974,
|
|
"mean_token_accuracy": 0.23747601956129075,
|
|
"num_tokens": 90830335.0,
|
|
"step": 39625
|
|
},
|
|
{
|
|
"entropy": 5.191009473800659,
|
|
"epoch": 3.8069164265129682,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003612921964277665,
|
|
"loss": 4.6175,
|
|
"mean_token_accuracy": 0.2598300203680992,
|
|
"num_tokens": 90841236.0,
|
|
"step": 39630
|
|
},
|
|
{
|
|
"entropy": 5.114261722564697,
|
|
"epoch": 3.807396733909702,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003612605334584526,
|
|
"loss": 4.6451,
|
|
"mean_token_accuracy": 0.25058179050683976,
|
|
"num_tokens": 90852772.0,
|
|
"step": 39635
|
|
},
|
|
{
|
|
"entropy": 5.066570711135864,
|
|
"epoch": 3.807877041306436,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00036122886848642536,
|
|
"loss": 4.5397,
|
|
"mean_token_accuracy": 0.25867900550365447,
|
|
"num_tokens": 90864692.0,
|
|
"step": 39640
|
|
},
|
|
{
|
|
"entropy": 5.1302955627441404,
|
|
"epoch": 3.80835734870317,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003611972015124197,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.24704958498477936,
|
|
"num_tokens": 90875398.0,
|
|
"step": 39645
|
|
},
|
|
{
|
|
"entropy": 5.058121061325073,
|
|
"epoch": 3.8088376560999038,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000361165532537171,
|
|
"loss": 4.529,
|
|
"mean_token_accuracy": 0.25882760882377626,
|
|
"num_tokens": 90886997.0,
|
|
"step": 39650
|
|
},
|
|
{
|
|
"entropy": 5.198092412948609,
|
|
"epoch": 3.809317963496638,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003611338615614145,
|
|
"loss": 4.7079,
|
|
"mean_token_accuracy": 0.24447882622480394,
|
|
"num_tokens": 90898674.0,
|
|
"step": 39655
|
|
},
|
|
{
|
|
"entropy": 5.160060930252075,
|
|
"epoch": 3.8097982708933715,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00036110218858588554,
|
|
"loss": 4.7034,
|
|
"mean_token_accuracy": 0.24557385146617888,
|
|
"num_tokens": 90910165.0,
|
|
"step": 39660
|
|
},
|
|
{
|
|
"entropy": 5.169241285324096,
|
|
"epoch": 3.810278578290106,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00036107051361131934,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.25255786031484606,
|
|
"num_tokens": 90922380.0,
|
|
"step": 39665
|
|
},
|
|
{
|
|
"entropy": 5.193088245391846,
|
|
"epoch": 3.8107588856868397,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036103883663845155,
|
|
"loss": 4.6216,
|
|
"mean_token_accuracy": 0.2573059856891632,
|
|
"num_tokens": 90932913.0,
|
|
"step": 39670
|
|
},
|
|
{
|
|
"entropy": 5.088579750061035,
|
|
"epoch": 3.8112391930835736,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003610071576680173,
|
|
"loss": 4.6743,
|
|
"mean_token_accuracy": 0.24727849513292313,
|
|
"num_tokens": 90945247.0,
|
|
"step": 39675
|
|
},
|
|
{
|
|
"entropy": 5.1809266090393065,
|
|
"epoch": 3.8117195004803075,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00036097547670075226,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.2460060864686966,
|
|
"num_tokens": 90956064.0,
|
|
"step": 39680
|
|
},
|
|
{
|
|
"entropy": 5.257108116149903,
|
|
"epoch": 3.8121998078770414,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000360943793737392,
|
|
"loss": 4.8148,
|
|
"mean_token_accuracy": 0.24069973528385163,
|
|
"num_tokens": 90967636.0,
|
|
"step": 39685
|
|
},
|
|
{
|
|
"entropy": 5.177082443237305,
|
|
"epoch": 3.8126801152737753,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000360912108778672,
|
|
"loss": 4.685,
|
|
"mean_token_accuracy": 0.2537639498710632,
|
|
"num_tokens": 90979128.0,
|
|
"step": 39690
|
|
},
|
|
{
|
|
"entropy": 5.131850671768189,
|
|
"epoch": 3.813160422670509,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000360880421825328,
|
|
"loss": 4.6583,
|
|
"mean_token_accuracy": 0.24668407142162324,
|
|
"num_tokens": 90990743.0,
|
|
"step": 39695
|
|
},
|
|
{
|
|
"entropy": 5.1704161167144775,
|
|
"epoch": 3.813640730067243,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003608487328780956,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.25232319384813306,
|
|
"num_tokens": 91001160.0,
|
|
"step": 39700
|
|
},
|
|
{
|
|
"entropy": 5.195051479339599,
|
|
"epoch": 3.814121037463977,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00036081704193771056,
|
|
"loss": 4.661,
|
|
"mean_token_accuracy": 0.2593440726399422,
|
|
"num_tokens": 91012125.0,
|
|
"step": 39705
|
|
},
|
|
{
|
|
"entropy": 5.109303760528564,
|
|
"epoch": 3.814601344860711,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003607853490049085,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.2567370876669884,
|
|
"num_tokens": 91023557.0,
|
|
"step": 39710
|
|
},
|
|
{
|
|
"entropy": 5.139885282516479,
|
|
"epoch": 3.8150816522574447,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003607536540804255,
|
|
"loss": 4.6501,
|
|
"mean_token_accuracy": 0.24869007468223572,
|
|
"num_tokens": 91035274.0,
|
|
"step": 39715
|
|
},
|
|
{
|
|
"entropy": 5.2391462326049805,
|
|
"epoch": 3.8155619596541785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00036072195716499726,
|
|
"loss": 4.6568,
|
|
"mean_token_accuracy": 0.2513942882418633,
|
|
"num_tokens": 91047516.0,
|
|
"step": 39720
|
|
},
|
|
{
|
|
"entropy": 5.030110788345337,
|
|
"epoch": 3.8160422670509124,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00036069025825935974,
|
|
"loss": 4.4993,
|
|
"mean_token_accuracy": 0.26341311931610106,
|
|
"num_tokens": 91058529.0,
|
|
"step": 39725
|
|
},
|
|
{
|
|
"entropy": 5.099700450897217,
|
|
"epoch": 3.8165225744476468,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00036065855736424886,
|
|
"loss": 4.641,
|
|
"mean_token_accuracy": 0.25742596089839936,
|
|
"num_tokens": 91071277.0,
|
|
"step": 39730
|
|
},
|
|
{
|
|
"entropy": 5.089921188354492,
|
|
"epoch": 3.81700288184438,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003606268544804006,
|
|
"loss": 4.5846,
|
|
"mean_token_accuracy": 0.2615709826350212,
|
|
"num_tokens": 91083157.0,
|
|
"step": 39735
|
|
},
|
|
{
|
|
"entropy": 5.226417016983032,
|
|
"epoch": 3.8174831892411145,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00036059514960855104,
|
|
"loss": 4.7157,
|
|
"mean_token_accuracy": 0.24544398933649064,
|
|
"num_tokens": 91095945.0,
|
|
"step": 39740
|
|
},
|
|
{
|
|
"entropy": 5.177284145355225,
|
|
"epoch": 3.817963496637848,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003605634427494363,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.2470778241753578,
|
|
"num_tokens": 91107210.0,
|
|
"step": 39745
|
|
},
|
|
{
|
|
"entropy": 5.117995738983154,
|
|
"epoch": 3.8184438040345823,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003605317339037925,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.2451580584049225,
|
|
"num_tokens": 91120000.0,
|
|
"step": 39750
|
|
},
|
|
{
|
|
"entropy": 5.151231908798218,
|
|
"epoch": 3.818924111431316,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00036050002307235575,
|
|
"loss": 4.6982,
|
|
"mean_token_accuracy": 0.24981888383626938,
|
|
"num_tokens": 91131794.0,
|
|
"step": 39755
|
|
},
|
|
{
|
|
"entropy": 5.2202826023101805,
|
|
"epoch": 3.81940441882805,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003604683102558624,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.24611925482749938,
|
|
"num_tokens": 91143644.0,
|
|
"step": 39760
|
|
},
|
|
{
|
|
"entropy": 5.155805444717407,
|
|
"epoch": 3.819884726224784,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00036043659545504866,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.2604713127017021,
|
|
"num_tokens": 91153735.0,
|
|
"step": 39765
|
|
},
|
|
{
|
|
"entropy": 5.083735084533691,
|
|
"epoch": 3.820365033621518,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003604048786706509,
|
|
"loss": 4.6129,
|
|
"mean_token_accuracy": 0.26085211932659147,
|
|
"num_tokens": 91165436.0,
|
|
"step": 39770
|
|
},
|
|
{
|
|
"entropy": 5.111909580230713,
|
|
"epoch": 3.8208453410182517,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003603731599034054,
|
|
"loss": 4.6904,
|
|
"mean_token_accuracy": 0.25302052944898606,
|
|
"num_tokens": 91177203.0,
|
|
"step": 39775
|
|
},
|
|
{
|
|
"entropy": 5.089265441894531,
|
|
"epoch": 3.8213256484149856,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00036034143915404865,
|
|
"loss": 4.634,
|
|
"mean_token_accuracy": 0.25394164472818376,
|
|
"num_tokens": 91190486.0,
|
|
"step": 39780
|
|
},
|
|
{
|
|
"entropy": 5.220332193374634,
|
|
"epoch": 3.8218059558117194,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003603097164233171,
|
|
"loss": 4.6879,
|
|
"mean_token_accuracy": 0.24359025806188583,
|
|
"num_tokens": 91201859.0,
|
|
"step": 39785
|
|
},
|
|
{
|
|
"entropy": 5.207606315612793,
|
|
"epoch": 3.8222862632084533,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003602779917119473,
|
|
"loss": 4.7186,
|
|
"mean_token_accuracy": 0.24252777695655822,
|
|
"num_tokens": 91212743.0,
|
|
"step": 39790
|
|
},
|
|
{
|
|
"entropy": 5.167776823043823,
|
|
"epoch": 3.822766570605187,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00036024626502067565,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.2502587646245956,
|
|
"num_tokens": 91223890.0,
|
|
"step": 39795
|
|
},
|
|
{
|
|
"entropy": 5.069837474822998,
|
|
"epoch": 3.823246878001921,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00036021453635023894,
|
|
"loss": 4.5633,
|
|
"mean_token_accuracy": 0.26115739196538923,
|
|
"num_tokens": 91235821.0,
|
|
"step": 39800
|
|
},
|
|
{
|
|
"entropy": 5.1034464836120605,
|
|
"epoch": 3.8237271853986554,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00036018280570137374,
|
|
"loss": 4.6547,
|
|
"mean_token_accuracy": 0.253999263048172,
|
|
"num_tokens": 91246951.0,
|
|
"step": 39805
|
|
},
|
|
{
|
|
"entropy": 5.113783311843872,
|
|
"epoch": 3.824207492795389,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003601510730748167,
|
|
"loss": 4.5656,
|
|
"mean_token_accuracy": 0.25934213399887085,
|
|
"num_tokens": 91257093.0,
|
|
"step": 39810
|
|
},
|
|
{
|
|
"entropy": 5.179714965820312,
|
|
"epoch": 3.824687800192123,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003601193384713046,
|
|
"loss": 4.7194,
|
|
"mean_token_accuracy": 0.2480992332100868,
|
|
"num_tokens": 91269390.0,
|
|
"step": 39815
|
|
},
|
|
{
|
|
"entropy": 5.124880599975586,
|
|
"epoch": 3.8251681075888566,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003600876018915742,
|
|
"loss": 4.6344,
|
|
"mean_token_accuracy": 0.24504767954349518,
|
|
"num_tokens": 91280427.0,
|
|
"step": 39820
|
|
},
|
|
{
|
|
"entropy": 5.201726961135864,
|
|
"epoch": 3.825648414985591,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003600558633363624,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.24618684351444245,
|
|
"num_tokens": 91292415.0,
|
|
"step": 39825
|
|
},
|
|
{
|
|
"entropy": 5.142821645736694,
|
|
"epoch": 3.826128722382325,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003600241228064059,
|
|
"loss": 4.6406,
|
|
"mean_token_accuracy": 0.2570252403616905,
|
|
"num_tokens": 91302750.0,
|
|
"step": 39830
|
|
},
|
|
{
|
|
"entropy": 5.1068812847137455,
|
|
"epoch": 3.8266090297790587,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00035999238030244183,
|
|
"loss": 4.5697,
|
|
"mean_token_accuracy": 0.25474469512701037,
|
|
"num_tokens": 91313889.0,
|
|
"step": 39835
|
|
},
|
|
{
|
|
"entropy": 5.175496196746826,
|
|
"epoch": 3.8270893371757926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00035996063582520704,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.2488528832793236,
|
|
"num_tokens": 91324306.0,
|
|
"step": 39840
|
|
},
|
|
{
|
|
"entropy": 5.141390037536621,
|
|
"epoch": 3.8275696445725265,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00035992888937543856,
|
|
"loss": 4.7166,
|
|
"mean_token_accuracy": 0.2526367798447609,
|
|
"num_tokens": 91335317.0,
|
|
"step": 39845
|
|
},
|
|
{
|
|
"entropy": 5.191412734985351,
|
|
"epoch": 3.8280499519692603,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00035989714095387344,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.24837829917669296,
|
|
"num_tokens": 91346582.0,
|
|
"step": 39850
|
|
},
|
|
{
|
|
"entropy": 5.081250476837158,
|
|
"epoch": 3.8285302593659942,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00035986539056124877,
|
|
"loss": 4.6,
|
|
"mean_token_accuracy": 0.2603598043322563,
|
|
"num_tokens": 91359135.0,
|
|
"step": 39855
|
|
},
|
|
{
|
|
"entropy": 5.2307610511779785,
|
|
"epoch": 3.829010566762728,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003598336381983018,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.2514391228556633,
|
|
"num_tokens": 91370309.0,
|
|
"step": 39860
|
|
},
|
|
{
|
|
"entropy": 5.107520198822021,
|
|
"epoch": 3.829490874159462,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00035980188386576967,
|
|
"loss": 4.595,
|
|
"mean_token_accuracy": 0.2580480620265007,
|
|
"num_tokens": 91381322.0,
|
|
"step": 39865
|
|
},
|
|
{
|
|
"entropy": 5.133994483947754,
|
|
"epoch": 3.829971181556196,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003597701275643896,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.2544416293501854,
|
|
"num_tokens": 91393466.0,
|
|
"step": 39870
|
|
},
|
|
{
|
|
"entropy": 5.157820987701416,
|
|
"epoch": 3.8304514889529298,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003597383692948988,
|
|
"loss": 4.6014,
|
|
"mean_token_accuracy": 0.25939169377088545,
|
|
"num_tokens": 91403530.0,
|
|
"step": 39875
|
|
},
|
|
{
|
|
"entropy": 5.132364702224732,
|
|
"epoch": 3.8309317963496636,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003597066090580347,
|
|
"loss": 4.6261,
|
|
"mean_token_accuracy": 0.2532626956701279,
|
|
"num_tokens": 91414563.0,
|
|
"step": 39880
|
|
},
|
|
{
|
|
"entropy": 5.139072704315185,
|
|
"epoch": 3.8314121037463975,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003596748468545348,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.2478751853108406,
|
|
"num_tokens": 91427125.0,
|
|
"step": 39885
|
|
},
|
|
{
|
|
"entropy": 5.168937873840332,
|
|
"epoch": 3.831892411143132,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00035964308268513623,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.2516350656747818,
|
|
"num_tokens": 91438987.0,
|
|
"step": 39890
|
|
},
|
|
{
|
|
"entropy": 5.080731534957886,
|
|
"epoch": 3.8323727185398653,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00035961131655057674,
|
|
"loss": 4.5445,
|
|
"mean_token_accuracy": 0.26491766721010207,
|
|
"num_tokens": 91450986.0,
|
|
"step": 39895
|
|
},
|
|
{
|
|
"entropy": 5.093992519378662,
|
|
"epoch": 3.8328530259365996,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003595795484515936,
|
|
"loss": 4.6443,
|
|
"mean_token_accuracy": 0.25159132331609724,
|
|
"num_tokens": 91462590.0,
|
|
"step": 39900
|
|
},
|
|
{
|
|
"entropy": 5.185814380645752,
|
|
"epoch": 3.8333333333333335,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00035954777838892454,
|
|
"loss": 4.6817,
|
|
"mean_token_accuracy": 0.25169519484043124,
|
|
"num_tokens": 91472630.0,
|
|
"step": 39905
|
|
},
|
|
{
|
|
"entropy": 5.185035991668701,
|
|
"epoch": 3.8338136407300674,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003595160063633072,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.25690728276968,
|
|
"num_tokens": 91483335.0,
|
|
"step": 39910
|
|
},
|
|
{
|
|
"entropy": 5.194876766204834,
|
|
"epoch": 3.8342939481268012,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003594842323754791,
|
|
"loss": 4.7376,
|
|
"mean_token_accuracy": 0.24951972365379332,
|
|
"num_tokens": 91494395.0,
|
|
"step": 39915
|
|
},
|
|
{
|
|
"entropy": 5.132739925384522,
|
|
"epoch": 3.834774255523535,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00035945245642617795,
|
|
"loss": 4.6339,
|
|
"mean_token_accuracy": 0.26236269772052767,
|
|
"num_tokens": 91506412.0,
|
|
"step": 39920
|
|
},
|
|
{
|
|
"entropy": 5.139065074920654,
|
|
"epoch": 3.835254562920269,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00035942067851614165,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.25917679369449614,
|
|
"num_tokens": 91517624.0,
|
|
"step": 39925
|
|
},
|
|
{
|
|
"entropy": 5.065129899978638,
|
|
"epoch": 3.835734870317003,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00035938889864610776,
|
|
"loss": 4.6374,
|
|
"mean_token_accuracy": 0.26130766719579696,
|
|
"num_tokens": 91529497.0,
|
|
"step": 39930
|
|
},
|
|
{
|
|
"entropy": 5.260416793823242,
|
|
"epoch": 3.8362151777137368,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00035935711681681423,
|
|
"loss": 4.7333,
|
|
"mean_token_accuracy": 0.24643077552318574,
|
|
"num_tokens": 91540454.0,
|
|
"step": 39935
|
|
},
|
|
{
|
|
"entropy": 5.126136589050293,
|
|
"epoch": 3.8366954851104706,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000359325333028999,
|
|
"loss": 4.5953,
|
|
"mean_token_accuracy": 0.25918159931898116,
|
|
"num_tokens": 91551153.0,
|
|
"step": 39940
|
|
},
|
|
{
|
|
"entropy": 5.144937515258789,
|
|
"epoch": 3.8371757925072045,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00035929354728339986,
|
|
"loss": 4.6857,
|
|
"mean_token_accuracy": 0.2533204644918442,
|
|
"num_tokens": 91562108.0,
|
|
"step": 39945
|
|
},
|
|
{
|
|
"entropy": 5.108738756179809,
|
|
"epoch": 3.8376560999039384,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003592617595807549,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.257251700758934,
|
|
"num_tokens": 91572803.0,
|
|
"step": 39950
|
|
},
|
|
{
|
|
"entropy": 5.195183944702149,
|
|
"epoch": 3.8381364073006723,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00035922996992180213,
|
|
"loss": 4.6982,
|
|
"mean_token_accuracy": 0.2526129886507988,
|
|
"num_tokens": 91584292.0,
|
|
"step": 39955
|
|
},
|
|
{
|
|
"entropy": 5.211752128601074,
|
|
"epoch": 3.838616714697406,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00035919817830727945,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.248189577460289,
|
|
"num_tokens": 91596396.0,
|
|
"step": 39960
|
|
},
|
|
{
|
|
"entropy": 5.192458724975586,
|
|
"epoch": 3.8390970220941405,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003591663847379252,
|
|
"loss": 4.7047,
|
|
"mean_token_accuracy": 0.25323511809110644,
|
|
"num_tokens": 91608278.0,
|
|
"step": 39965
|
|
},
|
|
{
|
|
"entropy": 5.102475500106811,
|
|
"epoch": 3.839577329490874,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003591345892144774,
|
|
"loss": 4.6136,
|
|
"mean_token_accuracy": 0.2643261194229126,
|
|
"num_tokens": 91619579.0,
|
|
"step": 39970
|
|
},
|
|
{
|
|
"entropy": 5.141988945007324,
|
|
"epoch": 3.8400576368876083,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00035910279173767426,
|
|
"loss": 4.6743,
|
|
"mean_token_accuracy": 0.255073019862175,
|
|
"num_tokens": 91631586.0,
|
|
"step": 39975
|
|
},
|
|
{
|
|
"entropy": 5.111904048919678,
|
|
"epoch": 3.840537944284342,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000359070992308254,
|
|
"loss": 4.6061,
|
|
"mean_token_accuracy": 0.25987725555896757,
|
|
"num_tokens": 91643164.0,
|
|
"step": 39980
|
|
},
|
|
{
|
|
"entropy": 5.14837965965271,
|
|
"epoch": 3.841018251681076,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000359039190926955,
|
|
"loss": 4.6349,
|
|
"mean_token_accuracy": 0.252220618724823,
|
|
"num_tokens": 91654111.0,
|
|
"step": 39985
|
|
},
|
|
{
|
|
"entropy": 5.031796216964722,
|
|
"epoch": 3.84149855907781,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003590073875945154,
|
|
"loss": 4.4484,
|
|
"mean_token_accuracy": 0.2677996218204498,
|
|
"num_tokens": 91665474.0,
|
|
"step": 39990
|
|
},
|
|
{
|
|
"entropy": 5.1556727409362795,
|
|
"epoch": 3.841978866474544,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00035897558231167375,
|
|
"loss": 4.7021,
|
|
"mean_token_accuracy": 0.24533764719963075,
|
|
"num_tokens": 91676609.0,
|
|
"step": 39995
|
|
},
|
|
{
|
|
"entropy": 5.0933863639831545,
|
|
"epoch": 3.8424591738712777,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003589437750791685,
|
|
"loss": 4.5845,
|
|
"mean_token_accuracy": 0.25756586343050003,
|
|
"num_tokens": 91687213.0,
|
|
"step": 40000
|
|
},
|
|
{
|
|
"entropy": 5.107626819610596,
|
|
"epoch": 3.8429394812680115,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00035891196589773805,
|
|
"loss": 4.6551,
|
|
"mean_token_accuracy": 0.2537226751446724,
|
|
"num_tokens": 91699220.0,
|
|
"step": 40005
|
|
},
|
|
{
|
|
"entropy": 5.057270479202271,
|
|
"epoch": 3.8434197886647454,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00035888015476812085,
|
|
"loss": 4.544,
|
|
"mean_token_accuracy": 0.2624382734298706,
|
|
"num_tokens": 91710020.0,
|
|
"step": 40010
|
|
},
|
|
{
|
|
"entropy": 5.093918561935425,
|
|
"epoch": 3.8439000960614793,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003588483416910557,
|
|
"loss": 4.623,
|
|
"mean_token_accuracy": 0.253604157269001,
|
|
"num_tokens": 91720708.0,
|
|
"step": 40015
|
|
},
|
|
{
|
|
"entropy": 5.132309150695801,
|
|
"epoch": 3.844380403458213,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003588165266672809,
|
|
"loss": 4.6698,
|
|
"mean_token_accuracy": 0.25013910979032516,
|
|
"num_tokens": 91731545.0,
|
|
"step": 40020
|
|
},
|
|
{
|
|
"entropy": 5.124575233459472,
|
|
"epoch": 3.844860710854947,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00035878470969753524,
|
|
"loss": 4.6369,
|
|
"mean_token_accuracy": 0.2554022938013077,
|
|
"num_tokens": 91743848.0,
|
|
"step": 40025
|
|
},
|
|
{
|
|
"entropy": 5.2074662208557125,
|
|
"epoch": 3.845341018251681,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00035875289078255747,
|
|
"loss": 4.6315,
|
|
"mean_token_accuracy": 0.2581927806138992,
|
|
"num_tokens": 91754000.0,
|
|
"step": 40030
|
|
},
|
|
{
|
|
"entropy": 5.168651819229126,
|
|
"epoch": 3.845821325648415,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00035872106992308614,
|
|
"loss": 4.6226,
|
|
"mean_token_accuracy": 0.2528357312083244,
|
|
"num_tokens": 91765563.0,
|
|
"step": 40035
|
|
},
|
|
{
|
|
"entropy": 5.122859239578247,
|
|
"epoch": 3.846301633045149,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003586892471198603,
|
|
"loss": 4.6269,
|
|
"mean_token_accuracy": 0.2536277875304222,
|
|
"num_tokens": 91777394.0,
|
|
"step": 40040
|
|
},
|
|
{
|
|
"entropy": 5.122466325759888,
|
|
"epoch": 3.8467819404418826,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003586574223736186,
|
|
"loss": 4.5875,
|
|
"mean_token_accuracy": 0.2602391019463539,
|
|
"num_tokens": 91787161.0,
|
|
"step": 40045
|
|
},
|
|
{
|
|
"entropy": 5.175837659835816,
|
|
"epoch": 3.847262247838617,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00035862559568509994,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.24964166730642318,
|
|
"num_tokens": 91797001.0,
|
|
"step": 40050
|
|
},
|
|
{
|
|
"entropy": 5.221295118331909,
|
|
"epoch": 3.8477425552353504,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003585937670550433,
|
|
"loss": 4.6787,
|
|
"mean_token_accuracy": 0.24211323261260986,
|
|
"num_tokens": 91808195.0,
|
|
"step": 40055
|
|
},
|
|
{
|
|
"entropy": 5.177135467529297,
|
|
"epoch": 3.8482228626320847,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00035856193648418753,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.24929986894130707,
|
|
"num_tokens": 91819907.0,
|
|
"step": 40060
|
|
},
|
|
{
|
|
"entropy": 5.160035562515259,
|
|
"epoch": 3.8487031700288186,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00035853010397327186,
|
|
"loss": 4.696,
|
|
"mean_token_accuracy": 0.24493786990642546,
|
|
"num_tokens": 91831960.0,
|
|
"step": 40065
|
|
},
|
|
{
|
|
"entropy": 5.18866229057312,
|
|
"epoch": 3.8491834774255524,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003584982695230351,
|
|
"loss": 4.7449,
|
|
"mean_token_accuracy": 0.24203144609928132,
|
|
"num_tokens": 91844339.0,
|
|
"step": 40070
|
|
},
|
|
{
|
|
"entropy": 5.10486946105957,
|
|
"epoch": 3.8496637848222863,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003584664331342166,
|
|
"loss": 4.6358,
|
|
"mean_token_accuracy": 0.25937424749135973,
|
|
"num_tokens": 91856207.0,
|
|
"step": 40075
|
|
},
|
|
{
|
|
"entropy": 5.144255018234253,
|
|
"epoch": 3.85014409221902,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003584345948075552,
|
|
"loss": 4.6784,
|
|
"mean_token_accuracy": 0.25758144855499265,
|
|
"num_tokens": 91868307.0,
|
|
"step": 40080
|
|
},
|
|
{
|
|
"entropy": 5.110690021514893,
|
|
"epoch": 3.850624399615754,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003584027545437903,
|
|
"loss": 4.6435,
|
|
"mean_token_accuracy": 0.2528288170695305,
|
|
"num_tokens": 91881164.0,
|
|
"step": 40085
|
|
},
|
|
{
|
|
"entropy": 5.138786792755127,
|
|
"epoch": 3.851104707012488,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00035837091234366107,
|
|
"loss": 4.6947,
|
|
"mean_token_accuracy": 0.25546482503414153,
|
|
"num_tokens": 91893725.0,
|
|
"step": 40090
|
|
},
|
|
{
|
|
"entropy": 5.071440029144287,
|
|
"epoch": 3.851585014409222,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000358339068207907,
|
|
"loss": 4.5213,
|
|
"mean_token_accuracy": 0.2623946249485016,
|
|
"num_tokens": 91904646.0,
|
|
"step": 40095
|
|
},
|
|
{
|
|
"entropy": 5.120625114440918,
|
|
"epoch": 3.8520653218059557,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00035830722213726695,
|
|
"loss": 4.6136,
|
|
"mean_token_accuracy": 0.2646736279129982,
|
|
"num_tokens": 91916001.0,
|
|
"step": 40100
|
|
},
|
|
{
|
|
"entropy": 5.149594068527222,
|
|
"epoch": 3.8525456292026896,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00035827537413248077,
|
|
"loss": 4.7004,
|
|
"mean_token_accuracy": 0.24637559354305266,
|
|
"num_tokens": 91927247.0,
|
|
"step": 40105
|
|
},
|
|
{
|
|
"entropy": 5.179963207244873,
|
|
"epoch": 3.8530259365994235,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003582435241942877,
|
|
"loss": 4.6559,
|
|
"mean_token_accuracy": 0.25371492803096773,
|
|
"num_tokens": 91938081.0,
|
|
"step": 40110
|
|
},
|
|
{
|
|
"entropy": 5.187190437316895,
|
|
"epoch": 3.8535062439961574,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00035821167232342706,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.2466219574213028,
|
|
"num_tokens": 91949497.0,
|
|
"step": 40115
|
|
},
|
|
{
|
|
"entropy": 5.149706315994263,
|
|
"epoch": 3.8539865513928913,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003581798185206385,
|
|
"loss": 4.6475,
|
|
"mean_token_accuracy": 0.25478599965572357,
|
|
"num_tokens": 91960134.0,
|
|
"step": 40120
|
|
},
|
|
{
|
|
"entropy": 5.1294646739959715,
|
|
"epoch": 3.8544668587896256,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00035814796278666166,
|
|
"loss": 4.5932,
|
|
"mean_token_accuracy": 0.2617149293422699,
|
|
"num_tokens": 91970402.0,
|
|
"step": 40125
|
|
},
|
|
{
|
|
"entropy": 5.050214052200317,
|
|
"epoch": 3.854947166186359,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00035811610512223585,
|
|
"loss": 4.5932,
|
|
"mean_token_accuracy": 0.26045573949813844,
|
|
"num_tokens": 91980542.0,
|
|
"step": 40130
|
|
},
|
|
{
|
|
"entropy": 5.080541276931763,
|
|
"epoch": 3.8554274735830933,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000358084245528101,
|
|
"loss": 4.4951,
|
|
"mean_token_accuracy": 0.26996518671512604,
|
|
"num_tokens": 91992078.0,
|
|
"step": 40135
|
|
},
|
|
{
|
|
"entropy": 5.166178798675537,
|
|
"epoch": 3.8559077809798272,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00035805238400499667,
|
|
"loss": 4.5835,
|
|
"mean_token_accuracy": 0.25772543996572495,
|
|
"num_tokens": 92002940.0,
|
|
"step": 40140
|
|
},
|
|
{
|
|
"entropy": 5.126374578475952,
|
|
"epoch": 3.856388088376561,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003580205205536626,
|
|
"loss": 4.6316,
|
|
"mean_token_accuracy": 0.2566342204809189,
|
|
"num_tokens": 92015911.0,
|
|
"step": 40145
|
|
},
|
|
{
|
|
"entropy": 5.1480265140533445,
|
|
"epoch": 3.856868395773295,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003579886551748385,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.24541462063789368,
|
|
"num_tokens": 92028008.0,
|
|
"step": 40150
|
|
},
|
|
{
|
|
"entropy": 5.262385654449463,
|
|
"epoch": 3.857348703170029,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00035795678786926434,
|
|
"loss": 4.811,
|
|
"mean_token_accuracy": 0.240216164290905,
|
|
"num_tokens": 92039833.0,
|
|
"step": 40155
|
|
},
|
|
{
|
|
"entropy": 5.094263362884521,
|
|
"epoch": 3.8578290105667628,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00035792491863767984,
|
|
"loss": 4.5376,
|
|
"mean_token_accuracy": 0.25796143561601637,
|
|
"num_tokens": 92051929.0,
|
|
"step": 40160
|
|
},
|
|
{
|
|
"entropy": 5.2403669357299805,
|
|
"epoch": 3.8583093179634966,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00035789304748082496,
|
|
"loss": 4.6699,
|
|
"mean_token_accuracy": 0.2542237892746925,
|
|
"num_tokens": 92062521.0,
|
|
"step": 40165
|
|
},
|
|
{
|
|
"entropy": 5.065118980407715,
|
|
"epoch": 3.8587896253602305,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00035786117439943967,
|
|
"loss": 4.6097,
|
|
"mean_token_accuracy": 0.2589932054281235,
|
|
"num_tokens": 92074120.0,
|
|
"step": 40170
|
|
},
|
|
{
|
|
"entropy": 5.1331785202026365,
|
|
"epoch": 3.8592699327569644,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00035782929939426393,
|
|
"loss": 4.6342,
|
|
"mean_token_accuracy": 0.25682666152715683,
|
|
"num_tokens": 92085687.0,
|
|
"step": 40175
|
|
},
|
|
{
|
|
"entropy": 5.12560715675354,
|
|
"epoch": 3.8597502401536983,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003577974224660379,
|
|
"loss": 4.6068,
|
|
"mean_token_accuracy": 0.26072424054145815,
|
|
"num_tokens": 92098034.0,
|
|
"step": 40180
|
|
},
|
|
{
|
|
"entropy": 5.171963930130005,
|
|
"epoch": 3.860230547550432,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003577655436155015,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.24710030406713485,
|
|
"num_tokens": 92108220.0,
|
|
"step": 40185
|
|
},
|
|
{
|
|
"entropy": 5.135533189773559,
|
|
"epoch": 3.860710854947166,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003577336628433949,
|
|
"loss": 4.6061,
|
|
"mean_token_accuracy": 0.25719339549541476,
|
|
"num_tokens": 92120061.0,
|
|
"step": 40190
|
|
},
|
|
{
|
|
"entropy": 5.120262908935547,
|
|
"epoch": 3.8611911623439,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00035770178015045843,
|
|
"loss": 4.6369,
|
|
"mean_token_accuracy": 0.2534713536500931,
|
|
"num_tokens": 92131199.0,
|
|
"step": 40195
|
|
},
|
|
{
|
|
"entropy": 5.1102059841156,
|
|
"epoch": 3.8616714697406342,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003576698955374321,
|
|
"loss": 4.6348,
|
|
"mean_token_accuracy": 0.25304626673460007,
|
|
"num_tokens": 92142738.0,
|
|
"step": 40200
|
|
},
|
|
{
|
|
"entropy": 5.164498138427734,
|
|
"epoch": 3.8621517771373677,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003576380090050564,
|
|
"loss": 4.6572,
|
|
"mean_token_accuracy": 0.25355994403362275,
|
|
"num_tokens": 92154090.0,
|
|
"step": 40205
|
|
},
|
|
{
|
|
"entropy": 5.186942386627197,
|
|
"epoch": 3.862632084534102,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003576061205540714,
|
|
"loss": 4.6472,
|
|
"mean_token_accuracy": 0.24867744147777557,
|
|
"num_tokens": 92166100.0,
|
|
"step": 40210
|
|
},
|
|
{
|
|
"entropy": 5.109003210067749,
|
|
"epoch": 3.863112391930836,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003575742301852176,
|
|
"loss": 4.6763,
|
|
"mean_token_accuracy": 0.25120825618505477,
|
|
"num_tokens": 92178336.0,
|
|
"step": 40215
|
|
},
|
|
{
|
|
"entropy": 5.177221393585205,
|
|
"epoch": 3.8635926993275698,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003575423378992354,
|
|
"loss": 4.6301,
|
|
"mean_token_accuracy": 0.24898865967988967,
|
|
"num_tokens": 92189211.0,
|
|
"step": 40220
|
|
},
|
|
{
|
|
"entropy": 5.034275865554809,
|
|
"epoch": 3.8640730067243036,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003575104436968652,
|
|
"loss": 4.5623,
|
|
"mean_token_accuracy": 0.2624985843896866,
|
|
"num_tokens": 92200699.0,
|
|
"step": 40225
|
|
},
|
|
{
|
|
"entropy": 5.097421789169312,
|
|
"epoch": 3.8645533141210375,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00035747854757884744,
|
|
"loss": 4.5575,
|
|
"mean_token_accuracy": 0.2534117951989174,
|
|
"num_tokens": 92212640.0,
|
|
"step": 40230
|
|
},
|
|
{
|
|
"entropy": 5.234732627868652,
|
|
"epoch": 3.8650336215177714,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00035744664954592283,
|
|
"loss": 4.7434,
|
|
"mean_token_accuracy": 0.24792848527431488,
|
|
"num_tokens": 92225888.0,
|
|
"step": 40235
|
|
},
|
|
{
|
|
"entropy": 5.1467772960662845,
|
|
"epoch": 3.8655139289145053,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00035741474959883175,
|
|
"loss": 4.6293,
|
|
"mean_token_accuracy": 0.25447013825178144,
|
|
"num_tokens": 92237842.0,
|
|
"step": 40240
|
|
},
|
|
{
|
|
"entropy": 5.168644046783447,
|
|
"epoch": 3.865994236311239,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000357382847738315,
|
|
"loss": 4.7093,
|
|
"mean_token_accuracy": 0.24748732149600983,
|
|
"num_tokens": 92249986.0,
|
|
"step": 40245
|
|
},
|
|
{
|
|
"entropy": 5.177753925323486,
|
|
"epoch": 3.866474543707973,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00035735094396511304,
|
|
"loss": 4.6754,
|
|
"mean_token_accuracy": 0.24573372900485993,
|
|
"num_tokens": 92262682.0,
|
|
"step": 40250
|
|
},
|
|
{
|
|
"entropy": 5.175303936004639,
|
|
"epoch": 3.866954851104707,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003573190382799667,
|
|
"loss": 4.6718,
|
|
"mean_token_accuracy": 0.256024132668972,
|
|
"num_tokens": 92274890.0,
|
|
"step": 40255
|
|
},
|
|
{
|
|
"entropy": 5.157070016860962,
|
|
"epoch": 3.867435158501441,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00035728713068361684,
|
|
"loss": 4.695,
|
|
"mean_token_accuracy": 0.2500536859035492,
|
|
"num_tokens": 92284790.0,
|
|
"step": 40260
|
|
},
|
|
{
|
|
"entropy": 5.146434020996094,
|
|
"epoch": 3.8679154658981747,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00035725522117680404,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.2459663763642311,
|
|
"num_tokens": 92296108.0,
|
|
"step": 40265
|
|
},
|
|
{
|
|
"entropy": 5.176788473129273,
|
|
"epoch": 3.8683957732949086,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003572233097602693,
|
|
"loss": 4.6959,
|
|
"mean_token_accuracy": 0.2452723503112793,
|
|
"num_tokens": 92307648.0,
|
|
"step": 40270
|
|
},
|
|
{
|
|
"entropy": 5.168786096572876,
|
|
"epoch": 3.868876080691643,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00035719139643475344,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.2471895396709442,
|
|
"num_tokens": 92320405.0,
|
|
"step": 40275
|
|
},
|
|
{
|
|
"entropy": 5.169554853439331,
|
|
"epoch": 3.8693563880883763,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00035715948120099747,
|
|
"loss": 4.655,
|
|
"mean_token_accuracy": 0.2586383730173111,
|
|
"num_tokens": 92331903.0,
|
|
"step": 40280
|
|
},
|
|
{
|
|
"entropy": 5.175698900222779,
|
|
"epoch": 3.8698366954851107,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00035712756405974216,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.25178092569112775,
|
|
"num_tokens": 92343336.0,
|
|
"step": 40285
|
|
},
|
|
{
|
|
"entropy": 5.164608573913574,
|
|
"epoch": 3.870317002881844,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003570956450117288,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.24564290344715117,
|
|
"num_tokens": 92356283.0,
|
|
"step": 40290
|
|
},
|
|
{
|
|
"entropy": 5.145309114456177,
|
|
"epoch": 3.8707973102785784,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003570637240576983,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.2516979843378067,
|
|
"num_tokens": 92367893.0,
|
|
"step": 40295
|
|
},
|
|
{
|
|
"entropy": 5.093063163757324,
|
|
"epoch": 3.8712776176753123,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00035703180119839187,
|
|
"loss": 4.559,
|
|
"mean_token_accuracy": 0.2560379311442375,
|
|
"num_tokens": 92379019.0,
|
|
"step": 40300
|
|
},
|
|
{
|
|
"entropy": 5.104631757736206,
|
|
"epoch": 3.871757925072046,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003569998764345506,
|
|
"loss": 4.5814,
|
|
"mean_token_accuracy": 0.26079364120960236,
|
|
"num_tokens": 92390082.0,
|
|
"step": 40305
|
|
},
|
|
{
|
|
"entropy": 5.102129364013672,
|
|
"epoch": 3.87223823246878,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00035696794976691564,
|
|
"loss": 4.6173,
|
|
"mean_token_accuracy": 0.2600747987627983,
|
|
"num_tokens": 92401323.0,
|
|
"step": 40310
|
|
},
|
|
{
|
|
"entropy": 5.090641069412231,
|
|
"epoch": 3.872718539865514,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00035693602119622823,
|
|
"loss": 4.5843,
|
|
"mean_token_accuracy": 0.2548932835459709,
|
|
"num_tokens": 92412329.0,
|
|
"step": 40315
|
|
},
|
|
{
|
|
"entropy": 5.304976177215576,
|
|
"epoch": 3.873198847262248,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003569040907232298,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.2464743509888649,
|
|
"num_tokens": 92423267.0,
|
|
"step": 40320
|
|
},
|
|
{
|
|
"entropy": 5.095067739486694,
|
|
"epoch": 3.8736791546589817,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00035687215834866154,
|
|
"loss": 4.5737,
|
|
"mean_token_accuracy": 0.26243738234043124,
|
|
"num_tokens": 92434519.0,
|
|
"step": 40325
|
|
},
|
|
{
|
|
"entropy": 5.088017749786377,
|
|
"epoch": 3.8741594620557156,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00035684022407326486,
|
|
"loss": 4.5649,
|
|
"mean_token_accuracy": 0.2572364196181297,
|
|
"num_tokens": 92445834.0,
|
|
"step": 40330
|
|
},
|
|
{
|
|
"entropy": 5.105040121078491,
|
|
"epoch": 3.8746397694524495,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00035680828789778126,
|
|
"loss": 4.6741,
|
|
"mean_token_accuracy": 0.2492538273334503,
|
|
"num_tokens": 92457648.0,
|
|
"step": 40335
|
|
},
|
|
{
|
|
"entropy": 5.151471281051636,
|
|
"epoch": 3.8751200768491834,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003567763498229521,
|
|
"loss": 4.6751,
|
|
"mean_token_accuracy": 0.2573514699935913,
|
|
"num_tokens": 92469080.0,
|
|
"step": 40340
|
|
},
|
|
{
|
|
"entropy": 5.14219708442688,
|
|
"epoch": 3.8756003842459172,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003567444098495189,
|
|
"loss": 4.6686,
|
|
"mean_token_accuracy": 0.2520801931619644,
|
|
"num_tokens": 92481679.0,
|
|
"step": 40345
|
|
},
|
|
{
|
|
"entropy": 5.131557512283325,
|
|
"epoch": 3.8760806916426516,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00035671246797822325,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.2603638470172882,
|
|
"num_tokens": 92493143.0,
|
|
"step": 40350
|
|
},
|
|
{
|
|
"entropy": 5.095791053771973,
|
|
"epoch": 3.876560999039385,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003566805242098067,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.25409370809793475,
|
|
"num_tokens": 92504302.0,
|
|
"step": 40355
|
|
},
|
|
{
|
|
"entropy": 5.166284608840942,
|
|
"epoch": 3.8770413064361193,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000356648578545011,
|
|
"loss": 4.6419,
|
|
"mean_token_accuracy": 0.2486351579427719,
|
|
"num_tokens": 92514797.0,
|
|
"step": 40360
|
|
},
|
|
{
|
|
"entropy": 5.186915636062622,
|
|
"epoch": 3.8775216138328528,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003566166309845777,
|
|
"loss": 4.738,
|
|
"mean_token_accuracy": 0.24464109688997268,
|
|
"num_tokens": 92526492.0,
|
|
"step": 40365
|
|
},
|
|
{
|
|
"entropy": 5.130360460281372,
|
|
"epoch": 3.878001921229587,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003565846815292486,
|
|
"loss": 4.6654,
|
|
"mean_token_accuracy": 0.25297434628009796,
|
|
"num_tokens": 92536980.0,
|
|
"step": 40370
|
|
},
|
|
{
|
|
"entropy": 5.063006210327148,
|
|
"epoch": 3.878482228626321,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003565527301797654,
|
|
"loss": 4.6188,
|
|
"mean_token_accuracy": 0.2556703373789787,
|
|
"num_tokens": 92548384.0,
|
|
"step": 40375
|
|
},
|
|
{
|
|
"entropy": 5.067806529998779,
|
|
"epoch": 3.878962536023055,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00035652077693687,
|
|
"loss": 4.638,
|
|
"mean_token_accuracy": 0.2554320693016052,
|
|
"num_tokens": 92559853.0,
|
|
"step": 40380
|
|
},
|
|
{
|
|
"entropy": 5.207918262481689,
|
|
"epoch": 3.8794428434197887,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003564888218013042,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.2413242354989052,
|
|
"num_tokens": 92570740.0,
|
|
"step": 40385
|
|
},
|
|
{
|
|
"entropy": 5.030303525924682,
|
|
"epoch": 3.8799231508165226,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00035645686477380996,
|
|
"loss": 4.5272,
|
|
"mean_token_accuracy": 0.262220473587513,
|
|
"num_tokens": 92583246.0,
|
|
"step": 40390
|
|
},
|
|
{
|
|
"entropy": 5.1987175941467285,
|
|
"epoch": 3.8804034582132565,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003564249058551293,
|
|
"loss": 4.7479,
|
|
"mean_token_accuracy": 0.24824442863464355,
|
|
"num_tokens": 92595551.0,
|
|
"step": 40395
|
|
},
|
|
{
|
|
"entropy": 5.0931024074554445,
|
|
"epoch": 3.8808837656099904,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003563929450460039,
|
|
"loss": 4.5605,
|
|
"mean_token_accuracy": 0.26034791618585584,
|
|
"num_tokens": 92608620.0,
|
|
"step": 40400
|
|
},
|
|
{
|
|
"entropy": 5.09530200958252,
|
|
"epoch": 3.8813640730067243,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003563609823471761,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.2527588248252869,
|
|
"num_tokens": 92620342.0,
|
|
"step": 40405
|
|
},
|
|
{
|
|
"entropy": 5.053324222564697,
|
|
"epoch": 3.881844380403458,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00035632901775938794,
|
|
"loss": 4.5908,
|
|
"mean_token_accuracy": 0.2606349170207977,
|
|
"num_tokens": 92630633.0,
|
|
"step": 40410
|
|
},
|
|
{
|
|
"entropy": 5.1913827419281,
|
|
"epoch": 3.882324687800192,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003562970512833814,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.23417655378580093,
|
|
"num_tokens": 92643134.0,
|
|
"step": 40415
|
|
},
|
|
{
|
|
"entropy": 5.136071443557739,
|
|
"epoch": 3.882804995196926,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003562650829198988,
|
|
"loss": 4.575,
|
|
"mean_token_accuracy": 0.262100325524807,
|
|
"num_tokens": 92654765.0,
|
|
"step": 40420
|
|
},
|
|
{
|
|
"entropy": 5.1639063358306885,
|
|
"epoch": 3.88328530259366,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00035623311266968225,
|
|
"loss": 4.7079,
|
|
"mean_token_accuracy": 0.2546079531311989,
|
|
"num_tokens": 92666321.0,
|
|
"step": 40425
|
|
},
|
|
{
|
|
"entropy": 5.122293424606323,
|
|
"epoch": 3.8837656099903937,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000356201140533474,
|
|
"loss": 4.6353,
|
|
"mean_token_accuracy": 0.24907058328390122,
|
|
"num_tokens": 92679214.0,
|
|
"step": 40430
|
|
},
|
|
{
|
|
"entropy": 5.043644142150879,
|
|
"epoch": 3.884245917387128,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0003561691665120164,
|
|
"loss": 4.6199,
|
|
"mean_token_accuracy": 0.2591404959559441,
|
|
"num_tokens": 92692064.0,
|
|
"step": 40435
|
|
},
|
|
{
|
|
"entropy": 5.175560712814331,
|
|
"epoch": 3.8847262247838614,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0003561371906060518,
|
|
"loss": 4.6532,
|
|
"mean_token_accuracy": 0.2553495779633522,
|
|
"num_tokens": 92704732.0,
|
|
"step": 40440
|
|
},
|
|
{
|
|
"entropy": 5.173536872863769,
|
|
"epoch": 3.8852065321805958,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00035610521281632257,
|
|
"loss": 4.6394,
|
|
"mean_token_accuracy": 0.2617566347122192,
|
|
"num_tokens": 92714176.0,
|
|
"step": 40445
|
|
},
|
|
{
|
|
"entropy": 5.108662891387939,
|
|
"epoch": 3.8856868395773296,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003560732331435711,
|
|
"loss": 4.5988,
|
|
"mean_token_accuracy": 0.25285490453243253,
|
|
"num_tokens": 92725874.0,
|
|
"step": 40450
|
|
},
|
|
{
|
|
"entropy": 5.0403789520263675,
|
|
"epoch": 3.8861671469740635,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00035604125158853996,
|
|
"loss": 4.5295,
|
|
"mean_token_accuracy": 0.2686223566532135,
|
|
"num_tokens": 92738040.0,
|
|
"step": 40455
|
|
},
|
|
{
|
|
"entropy": 5.193120622634888,
|
|
"epoch": 3.8866474543707974,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003560092681519715,
|
|
"loss": 4.6397,
|
|
"mean_token_accuracy": 0.2537831008434296,
|
|
"num_tokens": 92749818.0,
|
|
"step": 40460
|
|
},
|
|
{
|
|
"entropy": 5.097569513320923,
|
|
"epoch": 3.8871277617675313,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00035597728283460843,
|
|
"loss": 4.6332,
|
|
"mean_token_accuracy": 0.2546521112322807,
|
|
"num_tokens": 92761209.0,
|
|
"step": 40465
|
|
},
|
|
{
|
|
"entropy": 5.045261478424072,
|
|
"epoch": 3.887608069164265,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00035594529563719336,
|
|
"loss": 4.5552,
|
|
"mean_token_accuracy": 0.25910390317440035,
|
|
"num_tokens": 92771698.0,
|
|
"step": 40470
|
|
},
|
|
{
|
|
"entropy": 5.151317834854126,
|
|
"epoch": 3.888088376560999,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003559133065604688,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.26074604541063306,
|
|
"num_tokens": 92783753.0,
|
|
"step": 40475
|
|
},
|
|
{
|
|
"entropy": 5.134385442733764,
|
|
"epoch": 3.888568683957733,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003558813156051776,
|
|
"loss": 4.6038,
|
|
"mean_token_accuracy": 0.25830976366996766,
|
|
"num_tokens": 92796640.0,
|
|
"step": 40480
|
|
},
|
|
{
|
|
"entropy": 5.16023268699646,
|
|
"epoch": 3.889048991354467,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003558493227720624,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.24794047474861144,
|
|
"num_tokens": 92808163.0,
|
|
"step": 40485
|
|
},
|
|
{
|
|
"entropy": 5.071249771118164,
|
|
"epoch": 3.8895292987512007,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00035581732806186595,
|
|
"loss": 4.5699,
|
|
"mean_token_accuracy": 0.2617816239595413,
|
|
"num_tokens": 92818953.0,
|
|
"step": 40490
|
|
},
|
|
{
|
|
"entropy": 5.112238073348999,
|
|
"epoch": 3.8900096061479346,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0003557853314753311,
|
|
"loss": 4.627,
|
|
"mean_token_accuracy": 0.25313128530979156,
|
|
"num_tokens": 92830555.0,
|
|
"step": 40495
|
|
},
|
|
{
|
|
"entropy": 5.226541948318482,
|
|
"epoch": 3.8904899135446684,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00035575333301320083,
|
|
"loss": 4.6674,
|
|
"mean_token_accuracy": 0.2502004444599152,
|
|
"num_tokens": 92841491.0,
|
|
"step": 40500
|
|
},
|
|
{
|
|
"entropy": 5.115005970001221,
|
|
"epoch": 3.8909702209414023,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00035572133267621793,
|
|
"loss": 4.6649,
|
|
"mean_token_accuracy": 0.2603506326675415,
|
|
"num_tokens": 92853102.0,
|
|
"step": 40505
|
|
},
|
|
{
|
|
"entropy": 5.103706741333008,
|
|
"epoch": 3.8914505283381366,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003556893304651253,
|
|
"loss": 4.625,
|
|
"mean_token_accuracy": 0.2573301836848259,
|
|
"num_tokens": 92863034.0,
|
|
"step": 40510
|
|
},
|
|
{
|
|
"entropy": 5.157211399078369,
|
|
"epoch": 3.89193083573487,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003556573263806661,
|
|
"loss": 4.6586,
|
|
"mean_token_accuracy": 0.25184263437986376,
|
|
"num_tokens": 92875076.0,
|
|
"step": 40515
|
|
},
|
|
{
|
|
"entropy": 5.104033279418945,
|
|
"epoch": 3.8924111431316044,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003556253204235833,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.25278852730989454,
|
|
"num_tokens": 92886725.0,
|
|
"step": 40520
|
|
},
|
|
{
|
|
"entropy": 5.181823205947876,
|
|
"epoch": 3.8928914505283383,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003555933125946199,
|
|
"loss": 4.6327,
|
|
"mean_token_accuracy": 0.2479334518313408,
|
|
"num_tokens": 92897244.0,
|
|
"step": 40525
|
|
},
|
|
{
|
|
"entropy": 5.234023094177246,
|
|
"epoch": 3.893371757925072,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003555613028945191,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.2462846577167511,
|
|
"num_tokens": 92908161.0,
|
|
"step": 40530
|
|
},
|
|
{
|
|
"entropy": 5.08698034286499,
|
|
"epoch": 3.893852065321806,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00035552929132402414,
|
|
"loss": 4.5917,
|
|
"mean_token_accuracy": 0.25872706323862077,
|
|
"num_tokens": 92919065.0,
|
|
"step": 40535
|
|
},
|
|
{
|
|
"entropy": 5.186538219451904,
|
|
"epoch": 3.89433237271854,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00035549727788387805,
|
|
"loss": 4.72,
|
|
"mean_token_accuracy": 0.24528113305568694,
|
|
"num_tokens": 92930224.0,
|
|
"step": 40540
|
|
},
|
|
{
|
|
"entropy": 5.142897605895996,
|
|
"epoch": 3.894812680115274,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00035546526257482426,
|
|
"loss": 4.6537,
|
|
"mean_token_accuracy": 0.2620913550257683,
|
|
"num_tokens": 92942109.0,
|
|
"step": 40545
|
|
},
|
|
{
|
|
"entropy": 5.1256022453308105,
|
|
"epoch": 3.8952929875120077,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00035543324539760604,
|
|
"loss": 4.5898,
|
|
"mean_token_accuracy": 0.2602944985032082,
|
|
"num_tokens": 92954984.0,
|
|
"step": 40550
|
|
},
|
|
{
|
|
"entropy": 5.157463550567627,
|
|
"epoch": 3.8957732949087416,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003554012263529666,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.25067440420389175,
|
|
"num_tokens": 92965946.0,
|
|
"step": 40555
|
|
},
|
|
{
|
|
"entropy": 5.137538051605224,
|
|
"epoch": 3.8962536023054755,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003553692054416495,
|
|
"loss": 4.6272,
|
|
"mean_token_accuracy": 0.2565064042806625,
|
|
"num_tokens": 92978035.0,
|
|
"step": 40560
|
|
},
|
|
{
|
|
"entropy": 5.125887632369995,
|
|
"epoch": 3.8967339097022093,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003553371826643981,
|
|
"loss": 4.6556,
|
|
"mean_token_accuracy": 0.25127244740724564,
|
|
"num_tokens": 92989647.0,
|
|
"step": 40565
|
|
},
|
|
{
|
|
"entropy": 5.083491230010987,
|
|
"epoch": 3.8972142170989432,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003553051580219558,
|
|
"loss": 4.6164,
|
|
"mean_token_accuracy": 0.25861355364322663,
|
|
"num_tokens": 93000699.0,
|
|
"step": 40570
|
|
},
|
|
{
|
|
"entropy": 5.103936243057251,
|
|
"epoch": 3.897694524495677,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003552731315150662,
|
|
"loss": 4.5281,
|
|
"mean_token_accuracy": 0.2600432798266411,
|
|
"num_tokens": 93011463.0,
|
|
"step": 40575
|
|
},
|
|
{
|
|
"entropy": 5.165136337280273,
|
|
"epoch": 3.898174831892411,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00035524110314447295,
|
|
"loss": 4.6854,
|
|
"mean_token_accuracy": 0.2555814743041992,
|
|
"num_tokens": 93022147.0,
|
|
"step": 40580
|
|
},
|
|
{
|
|
"entropy": 5.022917413711548,
|
|
"epoch": 3.8986551392891453,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003552090729109195,
|
|
"loss": 4.5383,
|
|
"mean_token_accuracy": 0.26044892966747285,
|
|
"num_tokens": 93035155.0,
|
|
"step": 40585
|
|
},
|
|
{
|
|
"entropy": 5.225841760635376,
|
|
"epoch": 3.8991354466858787,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003551770408151496,
|
|
"loss": 4.6359,
|
|
"mean_token_accuracy": 0.25997077077627184,
|
|
"num_tokens": 93045724.0,
|
|
"step": 40590
|
|
},
|
|
{
|
|
"entropy": 5.169120025634766,
|
|
"epoch": 3.899615754082613,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00035514500685790673,
|
|
"loss": 4.7124,
|
|
"mean_token_accuracy": 0.24989465475082398,
|
|
"num_tokens": 93057629.0,
|
|
"step": 40595
|
|
},
|
|
{
|
|
"entropy": 5.085489511489868,
|
|
"epoch": 3.9000960614793465,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00035511297103993486,
|
|
"loss": 4.6492,
|
|
"mean_token_accuracy": 0.256605227291584,
|
|
"num_tokens": 93068426.0,
|
|
"step": 40600
|
|
},
|
|
{
|
|
"entropy": 5.116937160491943,
|
|
"epoch": 3.900576368876081,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003550809333619778,
|
|
"loss": 4.6465,
|
|
"mean_token_accuracy": 0.2585410013794899,
|
|
"num_tokens": 93079344.0,
|
|
"step": 40605
|
|
},
|
|
{
|
|
"entropy": 5.095519351959228,
|
|
"epoch": 3.9010566762728147,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003550488938247791,
|
|
"loss": 4.6289,
|
|
"mean_token_accuracy": 0.24840036183595657,
|
|
"num_tokens": 93091111.0,
|
|
"step": 40610
|
|
},
|
|
{
|
|
"entropy": 5.177192878723145,
|
|
"epoch": 3.9015369836695486,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003550168524290828,
|
|
"loss": 4.6788,
|
|
"mean_token_accuracy": 0.2506547451019287,
|
|
"num_tokens": 93102202.0,
|
|
"step": 40615
|
|
},
|
|
{
|
|
"entropy": 5.088584280014038,
|
|
"epoch": 3.9020172910662825,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00035498480917563294,
|
|
"loss": 4.5951,
|
|
"mean_token_accuracy": 0.26297510266304014,
|
|
"num_tokens": 93113575.0,
|
|
"step": 40620
|
|
},
|
|
{
|
|
"entropy": 5.124436855316162,
|
|
"epoch": 3.9024975984630164,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003549527640651732,
|
|
"loss": 4.6433,
|
|
"mean_token_accuracy": 0.25712113082408905,
|
|
"num_tokens": 93125402.0,
|
|
"step": 40625
|
|
},
|
|
{
|
|
"entropy": 5.084873390197754,
|
|
"epoch": 3.9029779058597502,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003549207170984476,
|
|
"loss": 4.6139,
|
|
"mean_token_accuracy": 0.2645573869347572,
|
|
"num_tokens": 93138147.0,
|
|
"step": 40630
|
|
},
|
|
{
|
|
"entropy": 5.186705303192139,
|
|
"epoch": 3.903458213256484,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00035488866827620047,
|
|
"loss": 4.6285,
|
|
"mean_token_accuracy": 0.2543892815709114,
|
|
"num_tokens": 93150299.0,
|
|
"step": 40635
|
|
},
|
|
{
|
|
"entropy": 5.040454912185669,
|
|
"epoch": 3.903938520653218,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003548566175991756,
|
|
"loss": 4.519,
|
|
"mean_token_accuracy": 0.268873430788517,
|
|
"num_tokens": 93162224.0,
|
|
"step": 40640
|
|
},
|
|
{
|
|
"entropy": 5.116019296646118,
|
|
"epoch": 3.904418828049952,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00035482456506811714,
|
|
"loss": 4.6652,
|
|
"mean_token_accuracy": 0.2594545617699623,
|
|
"num_tokens": 93173144.0,
|
|
"step": 40645
|
|
},
|
|
{
|
|
"entropy": 5.258983945846557,
|
|
"epoch": 3.9048991354466858,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035479251068376935,
|
|
"loss": 4.8107,
|
|
"mean_token_accuracy": 0.23879521042108537,
|
|
"num_tokens": 93183515.0,
|
|
"step": 40650
|
|
},
|
|
{
|
|
"entropy": 5.052014255523682,
|
|
"epoch": 3.9053794428434196,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00035476045444687637,
|
|
"loss": 4.5457,
|
|
"mean_token_accuracy": 0.2647654011845589,
|
|
"num_tokens": 93194184.0,
|
|
"step": 40655
|
|
},
|
|
{
|
|
"entropy": 5.245631742477417,
|
|
"epoch": 3.905859750240154,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003547283963581825,
|
|
"loss": 4.8164,
|
|
"mean_token_accuracy": 0.24432261735200883,
|
|
"num_tokens": 93205088.0,
|
|
"step": 40660
|
|
},
|
|
{
|
|
"entropy": 5.161050844192505,
|
|
"epoch": 3.9063400576368874,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000354696336418432,
|
|
"loss": 4.6146,
|
|
"mean_token_accuracy": 0.2589522063732147,
|
|
"num_tokens": 93216160.0,
|
|
"step": 40665
|
|
},
|
|
{
|
|
"entropy": 5.086620807647705,
|
|
"epoch": 3.9068203650336217,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00035466427462836923,
|
|
"loss": 4.5755,
|
|
"mean_token_accuracy": 0.261336176097393,
|
|
"num_tokens": 93227658.0,
|
|
"step": 40670
|
|
},
|
|
{
|
|
"entropy": 5.109696102142334,
|
|
"epoch": 3.907300672430355,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00035463221098873854,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.24968240410089493,
|
|
"num_tokens": 93238684.0,
|
|
"step": 40675
|
|
},
|
|
{
|
|
"entropy": 5.205865716934204,
|
|
"epoch": 3.9077809798270895,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003546001455002844,
|
|
"loss": 4.8039,
|
|
"mean_token_accuracy": 0.23594053983688354,
|
|
"num_tokens": 93249772.0,
|
|
"step": 40680
|
|
},
|
|
{
|
|
"entropy": 5.184907102584839,
|
|
"epoch": 3.9082612872238234,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003545680781637512,
|
|
"loss": 4.6477,
|
|
"mean_token_accuracy": 0.2587274193763733,
|
|
"num_tokens": 93261642.0,
|
|
"step": 40685
|
|
},
|
|
{
|
|
"entropy": 5.143085241317749,
|
|
"epoch": 3.9087415946205573,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003545360089798836,
|
|
"loss": 4.6089,
|
|
"mean_token_accuracy": 0.2547252759337425,
|
|
"num_tokens": 93273704.0,
|
|
"step": 40690
|
|
},
|
|
{
|
|
"entropy": 5.10231499671936,
|
|
"epoch": 3.909221902017291,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003545039379494259,
|
|
"loss": 4.6393,
|
|
"mean_token_accuracy": 0.2555072754621506,
|
|
"num_tokens": 93285396.0,
|
|
"step": 40695
|
|
},
|
|
{
|
|
"entropy": 5.145782852172852,
|
|
"epoch": 3.909702209414025,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000354471865073123,
|
|
"loss": 4.6696,
|
|
"mean_token_accuracy": 0.2510369345545769,
|
|
"num_tokens": 93297411.0,
|
|
"step": 40700
|
|
},
|
|
{
|
|
"entropy": 5.088284158706665,
|
|
"epoch": 3.910182516810759,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003544397903517192,
|
|
"loss": 4.5864,
|
|
"mean_token_accuracy": 0.25659879893064497,
|
|
"num_tokens": 93310545.0,
|
|
"step": 40705
|
|
},
|
|
{
|
|
"entropy": 5.10136775970459,
|
|
"epoch": 3.910662824207493,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003544077137859595,
|
|
"loss": 4.576,
|
|
"mean_token_accuracy": 0.25660459250211715,
|
|
"num_tokens": 93321851.0,
|
|
"step": 40710
|
|
},
|
|
{
|
|
"entropy": 5.169710350036621,
|
|
"epoch": 3.9111431316042267,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00035437563537658835,
|
|
"loss": 4.6124,
|
|
"mean_token_accuracy": 0.25877594500780104,
|
|
"num_tokens": 93332662.0,
|
|
"step": 40715
|
|
},
|
|
{
|
|
"entropy": 5.047652959823608,
|
|
"epoch": 3.9116234390009605,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00035434355512435075,
|
|
"loss": 4.5506,
|
|
"mean_token_accuracy": 0.2656233012676239,
|
|
"num_tokens": 93344979.0,
|
|
"step": 40720
|
|
},
|
|
{
|
|
"entropy": 5.0906164169311525,
|
|
"epoch": 3.9121037463976944,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003543114730299913,
|
|
"loss": 4.5903,
|
|
"mean_token_accuracy": 0.2615236297249794,
|
|
"num_tokens": 93356427.0,
|
|
"step": 40725
|
|
},
|
|
{
|
|
"entropy": 5.172247505187988,
|
|
"epoch": 3.9125840537944283,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003542793890942551,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.251352496445179,
|
|
"num_tokens": 93368377.0,
|
|
"step": 40730
|
|
},
|
|
{
|
|
"entropy": 5.131093597412109,
|
|
"epoch": 3.913064361191162,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003542473033178868,
|
|
"loss": 4.6426,
|
|
"mean_token_accuracy": 0.2503842800855637,
|
|
"num_tokens": 93378203.0,
|
|
"step": 40735
|
|
},
|
|
{
|
|
"entropy": 5.027871608734131,
|
|
"epoch": 3.913544668587896,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003542152157016315,
|
|
"loss": 4.5457,
|
|
"mean_token_accuracy": 0.2619370311498642,
|
|
"num_tokens": 93390326.0,
|
|
"step": 40740
|
|
},
|
|
{
|
|
"entropy": 5.086930227279663,
|
|
"epoch": 3.9140249759846304,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000354183126246234,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.2584588184952736,
|
|
"num_tokens": 93401364.0,
|
|
"step": 40745
|
|
},
|
|
{
|
|
"entropy": 5.120219945907593,
|
|
"epoch": 3.914505283381364,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003541510349524395,
|
|
"loss": 4.5433,
|
|
"mean_token_accuracy": 0.2641299679875374,
|
|
"num_tokens": 93412468.0,
|
|
"step": 40750
|
|
},
|
|
{
|
|
"entropy": 5.151014804840088,
|
|
"epoch": 3.914985590778098,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000354118941820993,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.24758631139993667,
|
|
"num_tokens": 93424605.0,
|
|
"step": 40755
|
|
},
|
|
{
|
|
"entropy": 5.087756395339966,
|
|
"epoch": 3.915465898174832,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00035408684685263954,
|
|
"loss": 4.5141,
|
|
"mean_token_accuracy": 0.2609035700559616,
|
|
"num_tokens": 93435624.0,
|
|
"step": 40760
|
|
},
|
|
{
|
|
"entropy": 5.19538106918335,
|
|
"epoch": 3.915946205571566,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003540547500481244,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.23342865705490112,
|
|
"num_tokens": 93447455.0,
|
|
"step": 40765
|
|
},
|
|
{
|
|
"entropy": 5.1297296524047855,
|
|
"epoch": 3.9164265129683,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003540226514081927,
|
|
"loss": 4.6147,
|
|
"mean_token_accuracy": 0.2548052057623863,
|
|
"num_tokens": 93459928.0,
|
|
"step": 40770
|
|
},
|
|
{
|
|
"entropy": 5.177817964553833,
|
|
"epoch": 3.9169068203650337,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00035399055093358965,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.2566866233944893,
|
|
"num_tokens": 93471277.0,
|
|
"step": 40775
|
|
},
|
|
{
|
|
"entropy": 5.186593866348266,
|
|
"epoch": 3.9173871277617676,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00035395844862506063,
|
|
"loss": 4.6392,
|
|
"mean_token_accuracy": 0.2519995257258415,
|
|
"num_tokens": 93483085.0,
|
|
"step": 40780
|
|
},
|
|
{
|
|
"entropy": 5.1256626605987545,
|
|
"epoch": 3.9178674351585014,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003539263444833509,
|
|
"loss": 4.6352,
|
|
"mean_token_accuracy": 0.25814177840948105,
|
|
"num_tokens": 93494769.0,
|
|
"step": 40785
|
|
},
|
|
{
|
|
"entropy": 5.079195547103882,
|
|
"epoch": 3.9183477425552353,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00035389423850920576,
|
|
"loss": 4.6097,
|
|
"mean_token_accuracy": 0.25327080488204956,
|
|
"num_tokens": 93506860.0,
|
|
"step": 40790
|
|
},
|
|
{
|
|
"entropy": 5.036570692062378,
|
|
"epoch": 3.918828049951969,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00035386213070337063,
|
|
"loss": 4.5747,
|
|
"mean_token_accuracy": 0.25496399849653245,
|
|
"num_tokens": 93519260.0,
|
|
"step": 40795
|
|
},
|
|
{
|
|
"entropy": 5.133291435241699,
|
|
"epoch": 3.919308357348703,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00035383002106659114,
|
|
"loss": 4.5748,
|
|
"mean_token_accuracy": 0.2594481334090233,
|
|
"num_tokens": 93530261.0,
|
|
"step": 40800
|
|
},
|
|
{
|
|
"entropy": 5.188005828857422,
|
|
"epoch": 3.919788664745437,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00035379790959961247,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.25506040155887605,
|
|
"num_tokens": 93542317.0,
|
|
"step": 40805
|
|
},
|
|
{
|
|
"entropy": 5.127929639816284,
|
|
"epoch": 3.920268972142171,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003537657963031804,
|
|
"loss": 4.6124,
|
|
"mean_token_accuracy": 0.25788632184267046,
|
|
"num_tokens": 93554038.0,
|
|
"step": 40810
|
|
},
|
|
{
|
|
"entropy": 5.136408996582031,
|
|
"epoch": 3.9207492795389047,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00035373368117804047,
|
|
"loss": 4.6076,
|
|
"mean_token_accuracy": 0.25492801815271376,
|
|
"num_tokens": 93565263.0,
|
|
"step": 40815
|
|
},
|
|
{
|
|
"entropy": 5.204004287719727,
|
|
"epoch": 3.921229586935639,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00035370156422493814,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.24980061650276184,
|
|
"num_tokens": 93575724.0,
|
|
"step": 40820
|
|
},
|
|
{
|
|
"entropy": 5.130502367019654,
|
|
"epoch": 3.9217098943323725,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00035366944544461926,
|
|
"loss": 4.6025,
|
|
"mean_token_accuracy": 0.2553321421146393,
|
|
"num_tokens": 93587289.0,
|
|
"step": 40825
|
|
},
|
|
{
|
|
"entropy": 5.173039340972901,
|
|
"epoch": 3.922190201729107,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003536373248378295,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.24809274226427078,
|
|
"num_tokens": 93599993.0,
|
|
"step": 40830
|
|
},
|
|
{
|
|
"entropy": 5.136140823364258,
|
|
"epoch": 3.9226705091258407,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00035360520240531446,
|
|
"loss": 4.6494,
|
|
"mean_token_accuracy": 0.256648862361908,
|
|
"num_tokens": 93611542.0,
|
|
"step": 40835
|
|
},
|
|
{
|
|
"entropy": 5.084309005737305,
|
|
"epoch": 3.9231508165225746,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00035357307814782007,
|
|
"loss": 4.5597,
|
|
"mean_token_accuracy": 0.2625394195318222,
|
|
"num_tokens": 93622650.0,
|
|
"step": 40840
|
|
},
|
|
{
|
|
"entropy": 5.094501256942749,
|
|
"epoch": 3.9236311239193085,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003535409520660922,
|
|
"loss": 4.5494,
|
|
"mean_token_accuracy": 0.2614794194698334,
|
|
"num_tokens": 93634481.0,
|
|
"step": 40845
|
|
},
|
|
{
|
|
"entropy": 5.070146942138672,
|
|
"epoch": 3.9241114313160423,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003535088241608765,
|
|
"loss": 4.6386,
|
|
"mean_token_accuracy": 0.24972016662359237,
|
|
"num_tokens": 93647225.0,
|
|
"step": 40850
|
|
},
|
|
{
|
|
"entropy": 5.124701023101807,
|
|
"epoch": 3.9245917387127762,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003534766944329191,
|
|
"loss": 4.6201,
|
|
"mean_token_accuracy": 0.2583256408572197,
|
|
"num_tokens": 93657984.0,
|
|
"step": 40855
|
|
},
|
|
{
|
|
"entropy": 5.179844522476197,
|
|
"epoch": 3.92507204610951,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00035344456288296595,
|
|
"loss": 4.6217,
|
|
"mean_token_accuracy": 0.25037098228931426,
|
|
"num_tokens": 93669420.0,
|
|
"step": 40860
|
|
},
|
|
{
|
|
"entropy": 5.0839395999908445,
|
|
"epoch": 3.925552353506244,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003534124295117629,
|
|
"loss": 4.5695,
|
|
"mean_token_accuracy": 0.2638559713959694,
|
|
"num_tokens": 93680649.0,
|
|
"step": 40865
|
|
},
|
|
{
|
|
"entropy": 5.113726043701172,
|
|
"epoch": 3.926032660902978,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003533802943200561,
|
|
"loss": 4.7018,
|
|
"mean_token_accuracy": 0.24676373302936555,
|
|
"num_tokens": 93693314.0,
|
|
"step": 40870
|
|
},
|
|
{
|
|
"entropy": 5.173453712463379,
|
|
"epoch": 3.9265129682997117,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003533481573085916,
|
|
"loss": 4.5999,
|
|
"mean_token_accuracy": 0.2539998576045036,
|
|
"num_tokens": 93704271.0,
|
|
"step": 40875
|
|
},
|
|
{
|
|
"entropy": 5.098687839508057,
|
|
"epoch": 3.9269932756964456,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003533160184781155,
|
|
"loss": 4.5846,
|
|
"mean_token_accuracy": 0.26106591075658797,
|
|
"num_tokens": 93715561.0,
|
|
"step": 40880
|
|
},
|
|
{
|
|
"entropy": 5.136365556716919,
|
|
"epoch": 3.9274735830931795,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000353283877829374,
|
|
"loss": 4.6592,
|
|
"mean_token_accuracy": 0.252382130920887,
|
|
"num_tokens": 93727115.0,
|
|
"step": 40885
|
|
},
|
|
{
|
|
"entropy": 5.148686647415161,
|
|
"epoch": 3.9279538904899134,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003532517353631134,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.24921972006559373,
|
|
"num_tokens": 93738439.0,
|
|
"step": 40890
|
|
},
|
|
{
|
|
"entropy": 5.12748761177063,
|
|
"epoch": 3.9284341978866477,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003532195910800798,
|
|
"loss": 4.6032,
|
|
"mean_token_accuracy": 0.255778880417347,
|
|
"num_tokens": 93749722.0,
|
|
"step": 40895
|
|
},
|
|
{
|
|
"entropy": 5.171913290023804,
|
|
"epoch": 3.928914505283381,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003531874449810195,
|
|
"loss": 4.6279,
|
|
"mean_token_accuracy": 0.2500307962298393,
|
|
"num_tokens": 93761122.0,
|
|
"step": 40900
|
|
},
|
|
{
|
|
"entropy": 5.157922315597534,
|
|
"epoch": 3.9293948126801155,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00035315529706667905,
|
|
"loss": 4.6474,
|
|
"mean_token_accuracy": 0.25152559131383895,
|
|
"num_tokens": 93771369.0,
|
|
"step": 40905
|
|
},
|
|
{
|
|
"entropy": 5.125244379043579,
|
|
"epoch": 3.929875120076849,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003531231473378046,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.24742248952388762,
|
|
"num_tokens": 93782380.0,
|
|
"step": 40910
|
|
},
|
|
{
|
|
"entropy": 5.14873366355896,
|
|
"epoch": 3.9303554274735832,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00035309099579514255,
|
|
"loss": 4.6096,
|
|
"mean_token_accuracy": 0.25166428834199905,
|
|
"num_tokens": 93793162.0,
|
|
"step": 40915
|
|
},
|
|
{
|
|
"entropy": 5.2124958515167235,
|
|
"epoch": 3.930835734870317,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003530588424394396,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.2507708087563515,
|
|
"num_tokens": 93804441.0,
|
|
"step": 40920
|
|
},
|
|
{
|
|
"entropy": 5.162117910385132,
|
|
"epoch": 3.931316042267051,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00035302668727144206,
|
|
"loss": 4.662,
|
|
"mean_token_accuracy": 0.25017296671867373,
|
|
"num_tokens": 93816080.0,
|
|
"step": 40925
|
|
},
|
|
{
|
|
"entropy": 5.140452289581299,
|
|
"epoch": 3.931796349663785,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00035299453029189647,
|
|
"loss": 4.6669,
|
|
"mean_token_accuracy": 0.2496793895959854,
|
|
"num_tokens": 93828494.0,
|
|
"step": 40930
|
|
},
|
|
{
|
|
"entropy": 5.145290517807007,
|
|
"epoch": 3.9322766570605188,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00035296237150154964,
|
|
"loss": 4.6693,
|
|
"mean_token_accuracy": 0.25034123212099074,
|
|
"num_tokens": 93839323.0,
|
|
"step": 40935
|
|
},
|
|
{
|
|
"entropy": 5.173583078384399,
|
|
"epoch": 3.9327569644572526,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0003529302109011479,
|
|
"loss": 4.6995,
|
|
"mean_token_accuracy": 0.2546057507395744,
|
|
"num_tokens": 93851474.0,
|
|
"step": 40940
|
|
},
|
|
{
|
|
"entropy": 5.1868510246276855,
|
|
"epoch": 3.9332372718539865,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00035289804849143806,
|
|
"loss": 4.7435,
|
|
"mean_token_accuracy": 0.2456383854150772,
|
|
"num_tokens": 93863484.0,
|
|
"step": 40945
|
|
},
|
|
{
|
|
"entropy": 5.10476541519165,
|
|
"epoch": 3.9337175792507204,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000352865884273167,
|
|
"loss": 4.6146,
|
|
"mean_token_accuracy": 0.26008570939302444,
|
|
"num_tokens": 93874124.0,
|
|
"step": 40950
|
|
},
|
|
{
|
|
"entropy": 5.156193447113037,
|
|
"epoch": 3.9341978866474543,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003528337182470812,
|
|
"loss": 4.6654,
|
|
"mean_token_accuracy": 0.25085425078868867,
|
|
"num_tokens": 93884880.0,
|
|
"step": 40955
|
|
},
|
|
{
|
|
"entropy": 5.077134799957276,
|
|
"epoch": 3.934678194044188,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00035280155041392757,
|
|
"loss": 4.569,
|
|
"mean_token_accuracy": 0.26185702830553054,
|
|
"num_tokens": 93895737.0,
|
|
"step": 40960
|
|
},
|
|
{
|
|
"entropy": 5.1421630859375,
|
|
"epoch": 3.935158501440922,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003527693807744531,
|
|
"loss": 4.6341,
|
|
"mean_token_accuracy": 0.25754541754722593,
|
|
"num_tokens": 93906916.0,
|
|
"step": 40965
|
|
},
|
|
{
|
|
"entropy": 5.159967041015625,
|
|
"epoch": 3.9356388088376564,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003527372093294044,
|
|
"loss": 4.6551,
|
|
"mean_token_accuracy": 0.24758546501398088,
|
|
"num_tokens": 93918471.0,
|
|
"step": 40970
|
|
},
|
|
{
|
|
"entropy": 5.067688751220703,
|
|
"epoch": 3.93611911623439,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003527050360795285,
|
|
"loss": 4.5236,
|
|
"mean_token_accuracy": 0.2630940243601799,
|
|
"num_tokens": 93929874.0,
|
|
"step": 40975
|
|
},
|
|
{
|
|
"entropy": 5.150241327285767,
|
|
"epoch": 3.936599423631124,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003526728610255725,
|
|
"loss": 4.6852,
|
|
"mean_token_accuracy": 0.2437395542860031,
|
|
"num_tokens": 93940785.0,
|
|
"step": 40980
|
|
},
|
|
{
|
|
"entropy": 5.162782382965088,
|
|
"epoch": 3.9370797310278576,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00035264068416828326,
|
|
"loss": 4.636,
|
|
"mean_token_accuracy": 0.2513482466340065,
|
|
"num_tokens": 93953255.0,
|
|
"step": 40985
|
|
},
|
|
{
|
|
"entropy": 5.081449031829834,
|
|
"epoch": 3.937560038424592,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003526085055084079,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.25815801322460175,
|
|
"num_tokens": 93964581.0,
|
|
"step": 40990
|
|
},
|
|
{
|
|
"entropy": 5.145799827575684,
|
|
"epoch": 3.938040345821326,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003525763250466935,
|
|
"loss": 4.6859,
|
|
"mean_token_accuracy": 0.2515065982937813,
|
|
"num_tokens": 93976222.0,
|
|
"step": 40995
|
|
},
|
|
{
|
|
"entropy": 5.167055368423462,
|
|
"epoch": 3.9385206532180597,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003525441427838872,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.24851278811693192,
|
|
"num_tokens": 93986936.0,
|
|
"step": 41000
|
|
},
|
|
{
|
|
"entropy": 5.181660795211792,
|
|
"epoch": 3.9390009606147935,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003525119587207361,
|
|
"loss": 4.6528,
|
|
"mean_token_accuracy": 0.2519474789500237,
|
|
"num_tokens": 93999518.0,
|
|
"step": 41005
|
|
},
|
|
{
|
|
"entropy": 5.18757438659668,
|
|
"epoch": 3.9394812680115274,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003524797728579875,
|
|
"loss": 4.6309,
|
|
"mean_token_accuracy": 0.2569980829954147,
|
|
"num_tokens": 94010500.0,
|
|
"step": 41010
|
|
},
|
|
{
|
|
"entropy": 5.051423406600952,
|
|
"epoch": 3.9399615754082613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003524475851963887,
|
|
"loss": 4.5746,
|
|
"mean_token_accuracy": 0.26074855774641037,
|
|
"num_tokens": 94020848.0,
|
|
"step": 41015
|
|
},
|
|
{
|
|
"entropy": 5.1825555801391605,
|
|
"epoch": 3.940441882804995,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00035241539573668693,
|
|
"loss": 4.6977,
|
|
"mean_token_accuracy": 0.24915846884250642,
|
|
"num_tokens": 94033154.0,
|
|
"step": 41020
|
|
},
|
|
{
|
|
"entropy": 5.168824863433838,
|
|
"epoch": 3.940922190201729,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00035238320447962947,
|
|
"loss": 4.6292,
|
|
"mean_token_accuracy": 0.25437517315149305,
|
|
"num_tokens": 94044131.0,
|
|
"step": 41025
|
|
},
|
|
{
|
|
"entropy": 5.123957586288452,
|
|
"epoch": 3.941402497598463,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003523510114259638,
|
|
"loss": 4.6132,
|
|
"mean_token_accuracy": 0.25164267867803575,
|
|
"num_tokens": 94055877.0,
|
|
"step": 41030
|
|
},
|
|
{
|
|
"entropy": 5.013245534896851,
|
|
"epoch": 3.941882804995197,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003523188165764374,
|
|
"loss": 4.5729,
|
|
"mean_token_accuracy": 0.2626459807157516,
|
|
"num_tokens": 94067341.0,
|
|
"step": 41035
|
|
},
|
|
{
|
|
"entropy": 5.133576583862305,
|
|
"epoch": 3.9423631123919307,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00035228661993179757,
|
|
"loss": 4.549,
|
|
"mean_token_accuracy": 0.261459943652153,
|
|
"num_tokens": 94079618.0,
|
|
"step": 41040
|
|
},
|
|
{
|
|
"entropy": 5.215913915634156,
|
|
"epoch": 3.9428434197886646,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000352254421492792,
|
|
"loss": 4.6931,
|
|
"mean_token_accuracy": 0.2453751191496849,
|
|
"num_tokens": 94090607.0,
|
|
"step": 41045
|
|
},
|
|
{
|
|
"entropy": 5.1516259670257565,
|
|
"epoch": 3.9433237271853985,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00035222222126016814,
|
|
"loss": 4.6703,
|
|
"mean_token_accuracy": 0.24812671691179275,
|
|
"num_tokens": 94102078.0,
|
|
"step": 41050
|
|
},
|
|
{
|
|
"entropy": 5.06051230430603,
|
|
"epoch": 3.943804034582133,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003521900192346736,
|
|
"loss": 4.5063,
|
|
"mean_token_accuracy": 0.26085884869098663,
|
|
"num_tokens": 94113524.0,
|
|
"step": 41055
|
|
},
|
|
{
|
|
"entropy": 5.101738500595093,
|
|
"epoch": 3.9442843419788662,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000352157815417056,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.2610786497592926,
|
|
"num_tokens": 94125003.0,
|
|
"step": 41060
|
|
},
|
|
{
|
|
"entropy": 5.2035173892974855,
|
|
"epoch": 3.9447646493756006,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00035212560980806305,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.24376726746559144,
|
|
"num_tokens": 94136670.0,
|
|
"step": 41065
|
|
},
|
|
{
|
|
"entropy": 5.190672826766968,
|
|
"epoch": 3.9452449567723344,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003520934024084425,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.25311207622289655,
|
|
"num_tokens": 94148541.0,
|
|
"step": 41070
|
|
},
|
|
{
|
|
"entropy": 5.181342124938965,
|
|
"epoch": 3.9457252641690683,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000352061193218942,
|
|
"loss": 4.7105,
|
|
"mean_token_accuracy": 0.2528378114104271,
|
|
"num_tokens": 94159936.0,
|
|
"step": 41075
|
|
},
|
|
{
|
|
"entropy": 5.088648080825806,
|
|
"epoch": 3.946205571565802,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003520289822403095,
|
|
"loss": 4.619,
|
|
"mean_token_accuracy": 0.2554706856608391,
|
|
"num_tokens": 94171042.0,
|
|
"step": 41080
|
|
},
|
|
{
|
|
"entropy": 5.1492146968841555,
|
|
"epoch": 3.946685878962536,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00035199676947329274,
|
|
"loss": 4.6972,
|
|
"mean_token_accuracy": 0.253499248623848,
|
|
"num_tokens": 94181610.0,
|
|
"step": 41085
|
|
},
|
|
{
|
|
"entropy": 5.223570442199707,
|
|
"epoch": 3.94716618635927,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00035196455491863954,
|
|
"loss": 4.7258,
|
|
"mean_token_accuracy": 0.2472410723567009,
|
|
"num_tokens": 94192684.0,
|
|
"step": 41090
|
|
},
|
|
{
|
|
"entropy": 5.211251735687256,
|
|
"epoch": 3.947646493756004,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000351932338577098,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.24570429027080537,
|
|
"num_tokens": 94204211.0,
|
|
"step": 41095
|
|
},
|
|
{
|
|
"entropy": 5.0950267791748045,
|
|
"epoch": 3.9481268011527377,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00035190012044941605,
|
|
"loss": 4.5975,
|
|
"mean_token_accuracy": 0.2599305883049965,
|
|
"num_tokens": 94216175.0,
|
|
"step": 41100
|
|
},
|
|
{
|
|
"entropy": 5.116603422164917,
|
|
"epoch": 3.9486071085494716,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003518679005363415,
|
|
"loss": 4.5863,
|
|
"mean_token_accuracy": 0.26281955987215044,
|
|
"num_tokens": 94227735.0,
|
|
"step": 41105
|
|
},
|
|
{
|
|
"entropy": 5.103160095214844,
|
|
"epoch": 3.9490874159462055,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003518356788386226,
|
|
"loss": 4.5873,
|
|
"mean_token_accuracy": 0.2677686229348183,
|
|
"num_tokens": 94238247.0,
|
|
"step": 41110
|
|
},
|
|
{
|
|
"entropy": 5.166254091262817,
|
|
"epoch": 3.9495677233429394,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00035180345535700745,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.25060353577136996,
|
|
"num_tokens": 94249839.0,
|
|
"step": 41115
|
|
},
|
|
{
|
|
"entropy": 5.203504943847657,
|
|
"epoch": 3.9500480307396733,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003517712300922441,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.2528615027666092,
|
|
"num_tokens": 94261794.0,
|
|
"step": 41120
|
|
},
|
|
{
|
|
"entropy": 5.169226264953613,
|
|
"epoch": 3.950528338136407,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00035173900304508074,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.243039171397686,
|
|
"num_tokens": 94276197.0,
|
|
"step": 41125
|
|
},
|
|
{
|
|
"entropy": 5.182999515533448,
|
|
"epoch": 3.9510086455331415,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003517067742162656,
|
|
"loss": 4.6698,
|
|
"mean_token_accuracy": 0.24634993076324463,
|
|
"num_tokens": 94288419.0,
|
|
"step": 41130
|
|
},
|
|
{
|
|
"entropy": 5.146847534179687,
|
|
"epoch": 3.951488952929875,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000351674543606547,
|
|
"loss": 4.6866,
|
|
"mean_token_accuracy": 0.25086202621459963,
|
|
"num_tokens": 94300521.0,
|
|
"step": 41135
|
|
},
|
|
{
|
|
"entropy": 5.037253904342651,
|
|
"epoch": 3.9519692603266092,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003516423112166731,
|
|
"loss": 4.5004,
|
|
"mean_token_accuracy": 0.2679607406258583,
|
|
"num_tokens": 94311349.0,
|
|
"step": 41140
|
|
},
|
|
{
|
|
"entropy": 5.096043634414673,
|
|
"epoch": 3.952449567723343,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00035161007704739226,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.25861848294734957,
|
|
"num_tokens": 94322383.0,
|
|
"step": 41145
|
|
},
|
|
{
|
|
"entropy": 5.082073450088501,
|
|
"epoch": 3.952929875120077,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000351577841099453,
|
|
"loss": 4.6592,
|
|
"mean_token_accuracy": 0.24541812837123872,
|
|
"num_tokens": 94334807.0,
|
|
"step": 41150
|
|
},
|
|
{
|
|
"entropy": 5.104023265838623,
|
|
"epoch": 3.953410182516811,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003515456033736036,
|
|
"loss": 4.5457,
|
|
"mean_token_accuracy": 0.2606156006455421,
|
|
"num_tokens": 94345444.0,
|
|
"step": 41155
|
|
},
|
|
{
|
|
"entropy": 5.168655633926392,
|
|
"epoch": 3.9538904899135447,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00035151336387059275,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.25222004055976865,
|
|
"num_tokens": 94356802.0,
|
|
"step": 41160
|
|
},
|
|
{
|
|
"entropy": 5.121954441070557,
|
|
"epoch": 3.9543707973102786,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003514811225911686,
|
|
"loss": 4.6596,
|
|
"mean_token_accuracy": 0.2596360817551613,
|
|
"num_tokens": 94367694.0,
|
|
"step": 41165
|
|
},
|
|
{
|
|
"entropy": 5.146133947372436,
|
|
"epoch": 3.9548511047070125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00035144887953607995,
|
|
"loss": 4.6317,
|
|
"mean_token_accuracy": 0.2620352432131767,
|
|
"num_tokens": 94379714.0,
|
|
"step": 41170
|
|
},
|
|
{
|
|
"entropy": 5.19910945892334,
|
|
"epoch": 3.9553314121037464,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003514166347060753,
|
|
"loss": 4.7021,
|
|
"mean_token_accuracy": 0.25227670222520826,
|
|
"num_tokens": 94391405.0,
|
|
"step": 41175
|
|
},
|
|
{
|
|
"entropy": 5.084824514389038,
|
|
"epoch": 3.9558117195004803,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003513843881019033,
|
|
"loss": 4.5273,
|
|
"mean_token_accuracy": 0.26878916919231416,
|
|
"num_tokens": 94402785.0,
|
|
"step": 41180
|
|
},
|
|
{
|
|
"entropy": 5.117837810516358,
|
|
"epoch": 3.956292026897214,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00035135213972431267,
|
|
"loss": 4.6282,
|
|
"mean_token_accuracy": 0.2553041264414787,
|
|
"num_tokens": 94414373.0,
|
|
"step": 41185
|
|
},
|
|
{
|
|
"entropy": 5.094186162948608,
|
|
"epoch": 3.956772334293948,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00035131988957405206,
|
|
"loss": 4.5641,
|
|
"mean_token_accuracy": 0.256536266207695,
|
|
"num_tokens": 94427285.0,
|
|
"step": 41190
|
|
},
|
|
{
|
|
"entropy": 5.154774951934814,
|
|
"epoch": 3.957252641690682,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00035128763765187026,
|
|
"loss": 4.652,
|
|
"mean_token_accuracy": 0.2527754545211792,
|
|
"num_tokens": 94439520.0,
|
|
"step": 41195
|
|
},
|
|
{
|
|
"entropy": 5.083364486694336,
|
|
"epoch": 3.957732949087416,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000351255383958516,
|
|
"loss": 4.5912,
|
|
"mean_token_accuracy": 0.26051324009895327,
|
|
"num_tokens": 94450707.0,
|
|
"step": 41200
|
|
},
|
|
{
|
|
"entropy": 5.096285104751587,
|
|
"epoch": 3.95821325648415,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003512231284947382,
|
|
"loss": 4.6285,
|
|
"mean_token_accuracy": 0.25469771176576617,
|
|
"num_tokens": 94461941.0,
|
|
"step": 41205
|
|
},
|
|
{
|
|
"entropy": 5.225884962081909,
|
|
"epoch": 3.9586935638808836,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003511908712612857,
|
|
"loss": 4.6672,
|
|
"mean_token_accuracy": 0.2555553108453751,
|
|
"num_tokens": 94471931.0,
|
|
"step": 41210
|
|
},
|
|
{
|
|
"entropy": 5.136250019073486,
|
|
"epoch": 3.959173871277618,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003511586122589073,
|
|
"loss": 4.6384,
|
|
"mean_token_accuracy": 0.25697881132364275,
|
|
"num_tokens": 94482692.0,
|
|
"step": 41215
|
|
},
|
|
{
|
|
"entropy": 5.0597716808319095,
|
|
"epoch": 3.9596541786743513,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003511263514883522,
|
|
"loss": 4.5582,
|
|
"mean_token_accuracy": 0.2635821998119354,
|
|
"num_tokens": 94493650.0,
|
|
"step": 41220
|
|
},
|
|
{
|
|
"entropy": 5.071850681304932,
|
|
"epoch": 3.9601344860710856,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003510940889503692,
|
|
"loss": 4.4895,
|
|
"mean_token_accuracy": 0.27014944702386856,
|
|
"num_tokens": 94503878.0,
|
|
"step": 41225
|
|
},
|
|
{
|
|
"entropy": 5.113554430007935,
|
|
"epoch": 3.9606147934678195,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00035106182464570736,
|
|
"loss": 4.6547,
|
|
"mean_token_accuracy": 0.2573467090725899,
|
|
"num_tokens": 94516930.0,
|
|
"step": 41230
|
|
},
|
|
{
|
|
"entropy": 5.12723445892334,
|
|
"epoch": 3.9610951008645534,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003510295585751159,
|
|
"loss": 4.6258,
|
|
"mean_token_accuracy": 0.2505720004439354,
|
|
"num_tokens": 94527523.0,
|
|
"step": 41235
|
|
},
|
|
{
|
|
"entropy": 5.154781675338745,
|
|
"epoch": 3.9615754082612873,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00035099729073934376,
|
|
"loss": 4.6319,
|
|
"mean_token_accuracy": 0.2608829140663147,
|
|
"num_tokens": 94537594.0,
|
|
"step": 41240
|
|
},
|
|
{
|
|
"entropy": 5.168537330627442,
|
|
"epoch": 3.962055715658021,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003509650211391403,
|
|
"loss": 4.7051,
|
|
"mean_token_accuracy": 0.2462943375110626,
|
|
"num_tokens": 94548293.0,
|
|
"step": 41245
|
|
},
|
|
{
|
|
"entropy": 5.141452741622925,
|
|
"epoch": 3.962536023054755,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00035093274977525456,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.25285488814115525,
|
|
"num_tokens": 94559116.0,
|
|
"step": 41250
|
|
},
|
|
{
|
|
"entropy": 5.193531179428101,
|
|
"epoch": 3.963016330451489,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003509004766484359,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.2416313633322716,
|
|
"num_tokens": 94570208.0,
|
|
"step": 41255
|
|
},
|
|
{
|
|
"entropy": 5.101978540420532,
|
|
"epoch": 3.963496637848223,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00035086820175943344,
|
|
"loss": 4.5927,
|
|
"mean_token_accuracy": 0.2605370953679085,
|
|
"num_tokens": 94580982.0,
|
|
"step": 41260
|
|
},
|
|
{
|
|
"entropy": 5.0915192604064945,
|
|
"epoch": 3.9639769452449567,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003508359251089967,
|
|
"loss": 4.6354,
|
|
"mean_token_accuracy": 0.2560127764940262,
|
|
"num_tokens": 94593364.0,
|
|
"step": 41265
|
|
},
|
|
{
|
|
"entropy": 5.172867345809936,
|
|
"epoch": 3.9644572526416906,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00035080364669787495,
|
|
"loss": 4.6223,
|
|
"mean_token_accuracy": 0.25682436376810075,
|
|
"num_tokens": 94605072.0,
|
|
"step": 41270
|
|
},
|
|
{
|
|
"entropy": 5.137899398803711,
|
|
"epoch": 3.9649375600384245,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00035077136652681757,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.24919624626636505,
|
|
"num_tokens": 94617226.0,
|
|
"step": 41275
|
|
},
|
|
{
|
|
"entropy": 5.1374529838562015,
|
|
"epoch": 3.9654178674351583,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00035073908459657413,
|
|
"loss": 4.6034,
|
|
"mean_token_accuracy": 0.25646490305662156,
|
|
"num_tokens": 94629807.0,
|
|
"step": 41280
|
|
},
|
|
{
|
|
"entropy": 5.139596843719483,
|
|
"epoch": 3.965898174831892,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00035070680090789404,
|
|
"loss": 4.5784,
|
|
"mean_token_accuracy": 0.26147884875535965,
|
|
"num_tokens": 94640866.0,
|
|
"step": 41285
|
|
},
|
|
{
|
|
"entropy": 5.111059284210205,
|
|
"epoch": 3.9663784822286265,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0003506745154615268,
|
|
"loss": 4.6014,
|
|
"mean_token_accuracy": 0.25189274698495867,
|
|
"num_tokens": 94651872.0,
|
|
"step": 41290
|
|
},
|
|
{
|
|
"entropy": 5.168352651596069,
|
|
"epoch": 3.96685878962536,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00035064222825822197,
|
|
"loss": 4.7023,
|
|
"mean_token_accuracy": 0.258437505364418,
|
|
"num_tokens": 94664890.0,
|
|
"step": 41295
|
|
},
|
|
{
|
|
"entropy": 5.0083259582519535,
|
|
"epoch": 3.9673390970220943,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00035060993929872923,
|
|
"loss": 4.4623,
|
|
"mean_token_accuracy": 0.264873568713665,
|
|
"num_tokens": 94677447.0,
|
|
"step": 41300
|
|
},
|
|
{
|
|
"entropy": 5.144082355499267,
|
|
"epoch": 3.967819404418828,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003505776485837983,
|
|
"loss": 4.7013,
|
|
"mean_token_accuracy": 0.25359803438186646,
|
|
"num_tokens": 94690432.0,
|
|
"step": 41305
|
|
},
|
|
{
|
|
"entropy": 5.092530155181885,
|
|
"epoch": 3.968299711815562,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003505453561141787,
|
|
"loss": 4.5766,
|
|
"mean_token_accuracy": 0.2581735372543335,
|
|
"num_tokens": 94703357.0,
|
|
"step": 41310
|
|
},
|
|
{
|
|
"entropy": 5.123774576187134,
|
|
"epoch": 3.968780019212296,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003505130618906203,
|
|
"loss": 4.5842,
|
|
"mean_token_accuracy": 0.2611533984541893,
|
|
"num_tokens": 94715276.0,
|
|
"step": 41315
|
|
},
|
|
{
|
|
"entropy": 5.16771297454834,
|
|
"epoch": 3.96926032660903,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003504807659138728,
|
|
"loss": 4.6018,
|
|
"mean_token_accuracy": 0.2556830897927284,
|
|
"num_tokens": 94725692.0,
|
|
"step": 41320
|
|
},
|
|
{
|
|
"entropy": 5.194298362731933,
|
|
"epoch": 3.9697406340057637,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003504484681846861,
|
|
"loss": 4.7322,
|
|
"mean_token_accuracy": 0.24949100464582444,
|
|
"num_tokens": 94737211.0,
|
|
"step": 41325
|
|
},
|
|
{
|
|
"entropy": 5.151398992538452,
|
|
"epoch": 3.9702209414024976,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00035041616870380997,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.25314734131097794,
|
|
"num_tokens": 94749140.0,
|
|
"step": 41330
|
|
},
|
|
{
|
|
"entropy": 5.187518548965454,
|
|
"epoch": 3.9707012487992315,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00035038386747199437,
|
|
"loss": 4.5975,
|
|
"mean_token_accuracy": 0.25326935201883316,
|
|
"num_tokens": 94759409.0,
|
|
"step": 41335
|
|
},
|
|
{
|
|
"entropy": 5.104962539672852,
|
|
"epoch": 3.9711815561959654,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003503515644899892,
|
|
"loss": 4.6091,
|
|
"mean_token_accuracy": 0.25208630412817,
|
|
"num_tokens": 94770267.0,
|
|
"step": 41340
|
|
},
|
|
{
|
|
"entropy": 5.154934024810791,
|
|
"epoch": 3.9716618635926992,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003503192597585444,
|
|
"loss": 4.6422,
|
|
"mean_token_accuracy": 0.2520579308271408,
|
|
"num_tokens": 94780479.0,
|
|
"step": 41345
|
|
},
|
|
{
|
|
"entropy": 5.100390148162842,
|
|
"epoch": 3.972142170989433,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003502869532784101,
|
|
"loss": 4.5681,
|
|
"mean_token_accuracy": 0.26595726162195205,
|
|
"num_tokens": 94791192.0,
|
|
"step": 41350
|
|
},
|
|
{
|
|
"entropy": 5.157297801971436,
|
|
"epoch": 3.972622478386167,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00035025464505033626,
|
|
"loss": 4.616,
|
|
"mean_token_accuracy": 0.24954167753458023,
|
|
"num_tokens": 94802090.0,
|
|
"step": 41355
|
|
},
|
|
{
|
|
"entropy": 5.038860416412353,
|
|
"epoch": 3.973102785782901,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000350222335075073,
|
|
"loss": 4.5792,
|
|
"mean_token_accuracy": 0.2562897190451622,
|
|
"num_tokens": 94814246.0,
|
|
"step": 41360
|
|
},
|
|
{
|
|
"entropy": 5.127254676818848,
|
|
"epoch": 3.973583093179635,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00035019002335337057,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.2596456602215767,
|
|
"num_tokens": 94825754.0,
|
|
"step": 41365
|
|
},
|
|
{
|
|
"entropy": 5.160164022445679,
|
|
"epoch": 3.9740634005763686,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003501577098859791,
|
|
"loss": 4.7235,
|
|
"mean_token_accuracy": 0.24952080994844436,
|
|
"num_tokens": 94837790.0,
|
|
"step": 41370
|
|
},
|
|
{
|
|
"entropy": 5.075568914413452,
|
|
"epoch": 3.974543707973103,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00035012539467364865,
|
|
"loss": 4.6182,
|
|
"mean_token_accuracy": 0.25191327184438705,
|
|
"num_tokens": 94848694.0,
|
|
"step": 41375
|
|
},
|
|
{
|
|
"entropy": 5.1005411624908445,
|
|
"epoch": 3.975024015369837,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003500930777171296,
|
|
"loss": 4.6298,
|
|
"mean_token_accuracy": 0.2563129797577858,
|
|
"num_tokens": 94861602.0,
|
|
"step": 41380
|
|
},
|
|
{
|
|
"entropy": 5.186616325378418,
|
|
"epoch": 3.9755043227665707,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003500607590171724,
|
|
"loss": 4.6543,
|
|
"mean_token_accuracy": 0.25448039919137955,
|
|
"num_tokens": 94872857.0,
|
|
"step": 41385
|
|
},
|
|
{
|
|
"entropy": 5.2468033790588375,
|
|
"epoch": 3.9759846301633046,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003500284385745272,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.25180334597826004,
|
|
"num_tokens": 94884716.0,
|
|
"step": 41390
|
|
},
|
|
{
|
|
"entropy": 5.152046823501587,
|
|
"epoch": 3.9764649375600385,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0003499961163899444,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.25667054355144503,
|
|
"num_tokens": 94897721.0,
|
|
"step": 41395
|
|
},
|
|
{
|
|
"entropy": 5.209504127502441,
|
|
"epoch": 3.9769452449567724,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00034996379246417453,
|
|
"loss": 4.6643,
|
|
"mean_token_accuracy": 0.257412976026535,
|
|
"num_tokens": 94908099.0,
|
|
"step": 41400
|
|
},
|
|
{
|
|
"entropy": 5.163052749633789,
|
|
"epoch": 3.9774255523535063,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00034993146679796795,
|
|
"loss": 4.633,
|
|
"mean_token_accuracy": 0.25986539423465727,
|
|
"num_tokens": 94919944.0,
|
|
"step": 41405
|
|
},
|
|
{
|
|
"entropy": 5.136471128463745,
|
|
"epoch": 3.97790585975024,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003498991393920752,
|
|
"loss": 4.6411,
|
|
"mean_token_accuracy": 0.25762397348880767,
|
|
"num_tokens": 94932104.0,
|
|
"step": 41410
|
|
},
|
|
{
|
|
"entropy": 5.163205099105835,
|
|
"epoch": 3.978386167146974,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034986681024724696,
|
|
"loss": 4.7238,
|
|
"mean_token_accuracy": 0.24586506336927413,
|
|
"num_tokens": 94943869.0,
|
|
"step": 41415
|
|
},
|
|
{
|
|
"entropy": 5.223615741729736,
|
|
"epoch": 3.978866474543708,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00034983447936423357,
|
|
"loss": 4.6995,
|
|
"mean_token_accuracy": 0.24575095921754836,
|
|
"num_tokens": 94955812.0,
|
|
"step": 41420
|
|
},
|
|
{
|
|
"entropy": 5.099835157394409,
|
|
"epoch": 3.979346781940442,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0003498021467437858,
|
|
"loss": 4.5713,
|
|
"mean_token_accuracy": 0.2572330176830292,
|
|
"num_tokens": 94967320.0,
|
|
"step": 41425
|
|
},
|
|
{
|
|
"entropy": 5.125391960144043,
|
|
"epoch": 3.9798270893371757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003497698123866544,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.2581933170557022,
|
|
"num_tokens": 94978249.0,
|
|
"step": 41430
|
|
},
|
|
{
|
|
"entropy": 5.14319167137146,
|
|
"epoch": 3.9803073967339095,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00034973747629358983,
|
|
"loss": 4.6836,
|
|
"mean_token_accuracy": 0.2531828969717026,
|
|
"num_tokens": 94990776.0,
|
|
"step": 41435
|
|
},
|
|
{
|
|
"entropy": 5.191263818740845,
|
|
"epoch": 3.980787704130644,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00034970513846534305,
|
|
"loss": 4.6532,
|
|
"mean_token_accuracy": 0.2578085958957672,
|
|
"num_tokens": 95001361.0,
|
|
"step": 41440
|
|
},
|
|
{
|
|
"entropy": 5.169906282424927,
|
|
"epoch": 3.9812680115273773,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003496727989026648,
|
|
"loss": 4.7234,
|
|
"mean_token_accuracy": 0.24958798438310623,
|
|
"num_tokens": 95013748.0,
|
|
"step": 41445
|
|
},
|
|
{
|
|
"entropy": 5.069540357589721,
|
|
"epoch": 3.9817483189241116,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00034964045760630584,
|
|
"loss": 4.5848,
|
|
"mean_token_accuracy": 0.2578407362103462,
|
|
"num_tokens": 95025700.0,
|
|
"step": 41450
|
|
},
|
|
{
|
|
"entropy": 5.178945255279541,
|
|
"epoch": 3.982228626320845,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00034960811457701715,
|
|
"loss": 4.6966,
|
|
"mean_token_accuracy": 0.2468561813235283,
|
|
"num_tokens": 95037653.0,
|
|
"step": 41455
|
|
},
|
|
{
|
|
"entropy": 5.091853427886963,
|
|
"epoch": 3.9827089337175794,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00034957576981554955,
|
|
"loss": 4.5985,
|
|
"mean_token_accuracy": 0.2560122340917587,
|
|
"num_tokens": 95049859.0,
|
|
"step": 41460
|
|
},
|
|
{
|
|
"entropy": 5.058329629898071,
|
|
"epoch": 3.9831892411143133,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00034954342332265407,
|
|
"loss": 4.5769,
|
|
"mean_token_accuracy": 0.2601110875606537,
|
|
"num_tokens": 95062862.0,
|
|
"step": 41465
|
|
},
|
|
{
|
|
"entropy": 5.108576345443725,
|
|
"epoch": 3.983669548511047,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00034951107509908157,
|
|
"loss": 4.6293,
|
|
"mean_token_accuracy": 0.24355826377868653,
|
|
"num_tokens": 95073555.0,
|
|
"step": 41470
|
|
},
|
|
{
|
|
"entropy": 5.151350355148315,
|
|
"epoch": 3.984149855907781,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003494787251455832,
|
|
"loss": 4.6029,
|
|
"mean_token_accuracy": 0.2608793154358864,
|
|
"num_tokens": 95086165.0,
|
|
"step": 41475
|
|
},
|
|
{
|
|
"entropy": 5.2152410507202145,
|
|
"epoch": 3.984630163304515,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00034944637346291,
|
|
"loss": 4.6935,
|
|
"mean_token_accuracy": 0.24896145164966582,
|
|
"num_tokens": 95098475.0,
|
|
"step": 41480
|
|
},
|
|
{
|
|
"entropy": 5.17709002494812,
|
|
"epoch": 3.985110470701249,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000349414020051813,
|
|
"loss": 4.6999,
|
|
"mean_token_accuracy": 0.24659184813499452,
|
|
"num_tokens": 95109972.0,
|
|
"step": 41485
|
|
},
|
|
{
|
|
"entropy": 5.159483003616333,
|
|
"epoch": 3.9855907780979827,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003493816649130435,
|
|
"loss": 4.6934,
|
|
"mean_token_accuracy": 0.25635203570127485,
|
|
"num_tokens": 95122043.0,
|
|
"step": 41490
|
|
},
|
|
{
|
|
"entropy": 5.086060905456543,
|
|
"epoch": 3.9860710854947166,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003493493080473526,
|
|
"loss": 4.5573,
|
|
"mean_token_accuracy": 0.262637285888195,
|
|
"num_tokens": 95133685.0,
|
|
"step": 41495
|
|
},
|
|
{
|
|
"entropy": 5.152785539627075,
|
|
"epoch": 3.9865513928914504,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00034931694945549146,
|
|
"loss": 4.6526,
|
|
"mean_token_accuracy": 0.24720337688922883,
|
|
"num_tokens": 95146018.0,
|
|
"step": 41500
|
|
},
|
|
{
|
|
"entropy": 5.116060400009156,
|
|
"epoch": 3.9870317002881843,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003492845891382115,
|
|
"loss": 4.6717,
|
|
"mean_token_accuracy": 0.248232638835907,
|
|
"num_tokens": 95158262.0,
|
|
"step": 41505
|
|
},
|
|
{
|
|
"entropy": 5.1308002948760985,
|
|
"epoch": 3.987512007684918,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000349252227096264,
|
|
"loss": 4.6341,
|
|
"mean_token_accuracy": 0.24726989567279817,
|
|
"num_tokens": 95170162.0,
|
|
"step": 41510
|
|
},
|
|
{
|
|
"entropy": 5.140854167938232,
|
|
"epoch": 3.9879923150816525,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003492198633304002,
|
|
"loss": 4.6322,
|
|
"mean_token_accuracy": 0.2543304622173309,
|
|
"num_tokens": 95182574.0,
|
|
"step": 41515
|
|
},
|
|
{
|
|
"entropy": 5.200664854049682,
|
|
"epoch": 3.988472622478386,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003491874978413716,
|
|
"loss": 4.6951,
|
|
"mean_token_accuracy": 0.2467207670211792,
|
|
"num_tokens": 95194527.0,
|
|
"step": 41520
|
|
},
|
|
{
|
|
"entropy": 5.105529022216797,
|
|
"epoch": 3.9889529298751203,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003491551306299296,
|
|
"loss": 4.5911,
|
|
"mean_token_accuracy": 0.2509583383798599,
|
|
"num_tokens": 95207842.0,
|
|
"step": 41525
|
|
},
|
|
{
|
|
"entropy": 5.173578071594238,
|
|
"epoch": 3.9894332372718537,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00034912276169682556,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.25555148869752886,
|
|
"num_tokens": 95219694.0,
|
|
"step": 41530
|
|
},
|
|
{
|
|
"entropy": 5.101839780807495,
|
|
"epoch": 3.989913544668588,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00034909039104281123,
|
|
"loss": 4.591,
|
|
"mean_token_accuracy": 0.2649638056755066,
|
|
"num_tokens": 95231397.0,
|
|
"step": 41535
|
|
},
|
|
{
|
|
"entropy": 5.063845920562744,
|
|
"epoch": 3.990393852065322,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0003490580186686379,
|
|
"loss": 4.5895,
|
|
"mean_token_accuracy": 0.2648359164595604,
|
|
"num_tokens": 95243575.0,
|
|
"step": 41540
|
|
},
|
|
{
|
|
"entropy": 5.1956737518310545,
|
|
"epoch": 3.990874159462056,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003490256445750573,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.2455470457673073,
|
|
"num_tokens": 95255866.0,
|
|
"step": 41545
|
|
},
|
|
{
|
|
"entropy": 5.182393312454224,
|
|
"epoch": 3.9913544668587897,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003489932687628211,
|
|
"loss": 4.6414,
|
|
"mean_token_accuracy": 0.2534100666642189,
|
|
"num_tokens": 95266812.0,
|
|
"step": 41550
|
|
},
|
|
{
|
|
"entropy": 5.109457540512085,
|
|
"epoch": 3.9918347742555236,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00034896089123268096,
|
|
"loss": 4.6534,
|
|
"mean_token_accuracy": 0.25337186008691787,
|
|
"num_tokens": 95278482.0,
|
|
"step": 41555
|
|
},
|
|
{
|
|
"entropy": 5.076082038879394,
|
|
"epoch": 3.9923150816522575,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003489285119853884,
|
|
"loss": 4.6698,
|
|
"mean_token_accuracy": 0.25423820614814757,
|
|
"num_tokens": 95289374.0,
|
|
"step": 41560
|
|
},
|
|
{
|
|
"entropy": 5.148150157928467,
|
|
"epoch": 3.9927953890489913,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003488961310216954,
|
|
"loss": 4.6129,
|
|
"mean_token_accuracy": 0.2571450635790825,
|
|
"num_tokens": 95301913.0,
|
|
"step": 41565
|
|
},
|
|
{
|
|
"entropy": 5.225524806976319,
|
|
"epoch": 3.993275696445725,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003488637483423537,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.24209627658128738,
|
|
"num_tokens": 95314560.0,
|
|
"step": 41570
|
|
},
|
|
{
|
|
"entropy": 5.1870810985565186,
|
|
"epoch": 3.993756003842459,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00034883136394811505,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.24665948897600173,
|
|
"num_tokens": 95326956.0,
|
|
"step": 41575
|
|
},
|
|
{
|
|
"entropy": 5.164495277404785,
|
|
"epoch": 3.994236311239193,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00034879897783973143,
|
|
"loss": 4.6408,
|
|
"mean_token_accuracy": 0.2554969683289528,
|
|
"num_tokens": 95338405.0,
|
|
"step": 41580
|
|
},
|
|
{
|
|
"entropy": 5.1376128673553465,
|
|
"epoch": 3.994716618635927,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003487665900179545,
|
|
"loss": 4.6724,
|
|
"mean_token_accuracy": 0.2504788801074028,
|
|
"num_tokens": 95349269.0,
|
|
"step": 41585
|
|
},
|
|
{
|
|
"entropy": 5.223145580291748,
|
|
"epoch": 3.9951969260326607,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003487342004835366,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.2523189872503281,
|
|
"num_tokens": 95359940.0,
|
|
"step": 41590
|
|
},
|
|
{
|
|
"entropy": 5.19242525100708,
|
|
"epoch": 3.9956772334293946,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003487018092372294,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.2515302300453186,
|
|
"num_tokens": 95370830.0,
|
|
"step": 41595
|
|
},
|
|
{
|
|
"entropy": 5.21939058303833,
|
|
"epoch": 3.996157540826129,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000348669416279785,
|
|
"loss": 4.746,
|
|
"mean_token_accuracy": 0.24756401777267456,
|
|
"num_tokens": 95382805.0,
|
|
"step": 41600
|
|
},
|
|
{
|
|
"entropy": 5.0570660591125485,
|
|
"epoch": 3.9966378482228624,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00034863702161195566,
|
|
"loss": 4.5288,
|
|
"mean_token_accuracy": 0.26010286808013916,
|
|
"num_tokens": 95394380.0,
|
|
"step": 41605
|
|
},
|
|
{
|
|
"entropy": 5.0271929740905765,
|
|
"epoch": 3.9971181556195967,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003486046252344933,
|
|
"loss": 4.4849,
|
|
"mean_token_accuracy": 0.26492141634225846,
|
|
"num_tokens": 95406240.0,
|
|
"step": 41610
|
|
},
|
|
{
|
|
"entropy": 5.207396173477173,
|
|
"epoch": 3.9975984630163306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00034857222714814996,
|
|
"loss": 4.6902,
|
|
"mean_token_accuracy": 0.24526077061891555,
|
|
"num_tokens": 95417021.0,
|
|
"step": 41615
|
|
},
|
|
{
|
|
"entropy": 5.155864238739014,
|
|
"epoch": 3.9980787704130645,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000348539827353678,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.2427007019519806,
|
|
"num_tokens": 95429315.0,
|
|
"step": 41620
|
|
},
|
|
{
|
|
"entropy": 5.18950080871582,
|
|
"epoch": 3.9985590778097984,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003485074258518298,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.253722770512104,
|
|
"num_tokens": 95441149.0,
|
|
"step": 41625
|
|
},
|
|
{
|
|
"entropy": 5.208589029312134,
|
|
"epoch": 3.9990393852065322,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003484750226433573,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.24653394669294357,
|
|
"num_tokens": 95452753.0,
|
|
"step": 41630
|
|
},
|
|
{
|
|
"entropy": 5.039046287536621,
|
|
"epoch": 3.999519692603266,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00034844261772901293,
|
|
"loss": 4.5774,
|
|
"mean_token_accuracy": 0.2655496716499329,
|
|
"num_tokens": 95464901.0,
|
|
"step": 41635
|
|
},
|
|
{
|
|
"entropy": 5.2578513622283936,
|
|
"epoch": 4.0,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003484102111095492,
|
|
"loss": 4.6326,
|
|
"mean_token_accuracy": 0.2616613209247589,
|
|
"num_tokens": 95474144.0,
|
|
"step": 41640
|
|
},
|
|
{
|
|
"entropy": 5.188993787765503,
|
|
"epoch": 4.000480307396734,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00034837780278571814,
|
|
"loss": 4.6138,
|
|
"mean_token_accuracy": 0.2521784618496895,
|
|
"num_tokens": 95483973.0,
|
|
"step": 41645
|
|
},
|
|
{
|
|
"entropy": 5.112954616546631,
|
|
"epoch": 4.000960614793468,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003483453927582725,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.25726163685321807,
|
|
"num_tokens": 95495989.0,
|
|
"step": 41650
|
|
},
|
|
{
|
|
"entropy": 5.0782084465026855,
|
|
"epoch": 4.001440922190202,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003483129810279647,
|
|
"loss": 4.5182,
|
|
"mean_token_accuracy": 0.2684644550085068,
|
|
"num_tokens": 95507286.0,
|
|
"step": 41655
|
|
},
|
|
{
|
|
"entropy": 5.207351112365723,
|
|
"epoch": 4.0019212295869355,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000348280567595547,
|
|
"loss": 4.6409,
|
|
"mean_token_accuracy": 0.26044773012399675,
|
|
"num_tokens": 95519499.0,
|
|
"step": 41660
|
|
},
|
|
{
|
|
"entropy": 5.144596147537231,
|
|
"epoch": 4.00240153698367,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034824815246177227,
|
|
"loss": 4.5444,
|
|
"mean_token_accuracy": 0.2549943685531616,
|
|
"num_tokens": 95532134.0,
|
|
"step": 41665
|
|
},
|
|
{
|
|
"entropy": 5.130008697509766,
|
|
"epoch": 4.002881844380403,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003482157356273929,
|
|
"loss": 4.5801,
|
|
"mean_token_accuracy": 0.26283578425645826,
|
|
"num_tokens": 95542157.0,
|
|
"step": 41670
|
|
},
|
|
{
|
|
"entropy": 5.146264982223511,
|
|
"epoch": 4.003362151777138,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003481833170931615,
|
|
"loss": 4.5298,
|
|
"mean_token_accuracy": 0.2635056287050247,
|
|
"num_tokens": 95553345.0,
|
|
"step": 41675
|
|
},
|
|
{
|
|
"entropy": 5.096359491348267,
|
|
"epoch": 4.003842459173871,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00034815089685983085,
|
|
"loss": 4.5129,
|
|
"mean_token_accuracy": 0.263239760696888,
|
|
"num_tokens": 95564795.0,
|
|
"step": 41680
|
|
},
|
|
{
|
|
"entropy": 5.131832504272461,
|
|
"epoch": 4.004322766570605,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003481184749281536,
|
|
"loss": 4.619,
|
|
"mean_token_accuracy": 0.2589213877916336,
|
|
"num_tokens": 95576777.0,
|
|
"step": 41685
|
|
},
|
|
{
|
|
"entropy": 5.135291957855225,
|
|
"epoch": 4.004803073967339,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00034808605129888246,
|
|
"loss": 4.5823,
|
|
"mean_token_accuracy": 0.26478118896484376,
|
|
"num_tokens": 95588483.0,
|
|
"step": 41690
|
|
},
|
|
{
|
|
"entropy": 5.089664649963379,
|
|
"epoch": 4.005283381364073,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00034805362597277017,
|
|
"loss": 4.4694,
|
|
"mean_token_accuracy": 0.26886060684919355,
|
|
"num_tokens": 95600300.0,
|
|
"step": 41695
|
|
},
|
|
{
|
|
"entropy": 5.131202268600464,
|
|
"epoch": 4.005763688760807,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00034802119895056973,
|
|
"loss": 4.5555,
|
|
"mean_token_accuracy": 0.25631280839443205,
|
|
"num_tokens": 95611596.0,
|
|
"step": 41700
|
|
},
|
|
{
|
|
"entropy": 5.10271954536438,
|
|
"epoch": 4.006243996157541,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00034798877023303385,
|
|
"loss": 4.555,
|
|
"mean_token_accuracy": 0.2603612124919891,
|
|
"num_tokens": 95622813.0,
|
|
"step": 41705
|
|
},
|
|
{
|
|
"entropy": 5.059698247909546,
|
|
"epoch": 4.006724303554274,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034795633982091534,
|
|
"loss": 4.5021,
|
|
"mean_token_accuracy": 0.2649715796113014,
|
|
"num_tokens": 95635862.0,
|
|
"step": 41710
|
|
},
|
|
{
|
|
"entropy": 5.204945611953735,
|
|
"epoch": 4.007204610951009,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00034792390771496735,
|
|
"loss": 4.6692,
|
|
"mean_token_accuracy": 0.2569692239165306,
|
|
"num_tokens": 95647396.0,
|
|
"step": 41715
|
|
},
|
|
{
|
|
"entropy": 5.165604162216186,
|
|
"epoch": 4.007684918347743,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00034789147391594275,
|
|
"loss": 4.6054,
|
|
"mean_token_accuracy": 0.2579581379890442,
|
|
"num_tokens": 95657882.0,
|
|
"step": 41720
|
|
},
|
|
{
|
|
"entropy": 5.111082267761231,
|
|
"epoch": 4.008165225744476,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003478590384245945,
|
|
"loss": 4.4858,
|
|
"mean_token_accuracy": 0.2672068864107132,
|
|
"num_tokens": 95669915.0,
|
|
"step": 41725
|
|
},
|
|
{
|
|
"entropy": 5.067381906509399,
|
|
"epoch": 4.008645533141211,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00034782660124167583,
|
|
"loss": 4.4638,
|
|
"mean_token_accuracy": 0.26838111132383347,
|
|
"num_tokens": 95680660.0,
|
|
"step": 41730
|
|
},
|
|
{
|
|
"entropy": 5.112824296951294,
|
|
"epoch": 4.009125840537944,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0003477941623679397,
|
|
"loss": 4.6185,
|
|
"mean_token_accuracy": 0.25070231407880783,
|
|
"num_tokens": 95692604.0,
|
|
"step": 41735
|
|
},
|
|
{
|
|
"entropy": 5.0835786819458,
|
|
"epoch": 4.0096061479346785,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003477617218041393,
|
|
"loss": 4.5342,
|
|
"mean_token_accuracy": 0.2652730256319046,
|
|
"num_tokens": 95703761.0,
|
|
"step": 41740
|
|
},
|
|
{
|
|
"entropy": 5.025597000122071,
|
|
"epoch": 4.010086455331412,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003477292795510277,
|
|
"loss": 4.4416,
|
|
"mean_token_accuracy": 0.27138099521398545,
|
|
"num_tokens": 95715776.0,
|
|
"step": 41745
|
|
},
|
|
{
|
|
"entropy": 5.127147483825683,
|
|
"epoch": 4.010566762728146,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003476968356093582,
|
|
"loss": 4.6468,
|
|
"mean_token_accuracy": 0.2543772801756859,
|
|
"num_tokens": 95727812.0,
|
|
"step": 41750
|
|
},
|
|
{
|
|
"entropy": 5.110024929046631,
|
|
"epoch": 4.01104707012488,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003476643899798841,
|
|
"loss": 4.5644,
|
|
"mean_token_accuracy": 0.2607039034366608,
|
|
"num_tokens": 95740453.0,
|
|
"step": 41755
|
|
},
|
|
{
|
|
"entropy": 5.033160877227783,
|
|
"epoch": 4.011527377521614,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00034763194266335855,
|
|
"loss": 4.4676,
|
|
"mean_token_accuracy": 0.27712756395339966,
|
|
"num_tokens": 95753436.0,
|
|
"step": 41760
|
|
},
|
|
{
|
|
"entropy": 5.180290412902832,
|
|
"epoch": 4.0120076849183475,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003475994936605351,
|
|
"loss": 4.6078,
|
|
"mean_token_accuracy": 0.2532478183507919,
|
|
"num_tokens": 95763936.0,
|
|
"step": 41765
|
|
},
|
|
{
|
|
"entropy": 5.147741174697876,
|
|
"epoch": 4.012487992315082,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00034756704297216686,
|
|
"loss": 4.5917,
|
|
"mean_token_accuracy": 0.25890630632638933,
|
|
"num_tokens": 95775535.0,
|
|
"step": 41770
|
|
},
|
|
{
|
|
"entropy": 5.105518960952759,
|
|
"epoch": 4.012968299711815,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034753459059900745,
|
|
"loss": 4.6049,
|
|
"mean_token_accuracy": 0.26370391994714737,
|
|
"num_tokens": 95786814.0,
|
|
"step": 41775
|
|
},
|
|
{
|
|
"entropy": 5.203647661209106,
|
|
"epoch": 4.01344860710855,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034750213654181016,
|
|
"loss": 4.61,
|
|
"mean_token_accuracy": 0.266436804831028,
|
|
"num_tokens": 95798141.0,
|
|
"step": 41780
|
|
},
|
|
{
|
|
"entropy": 5.173744583129883,
|
|
"epoch": 4.013928914505283,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00034746968080132855,
|
|
"loss": 4.6016,
|
|
"mean_token_accuracy": 0.2678267195820808,
|
|
"num_tokens": 95811244.0,
|
|
"step": 41785
|
|
},
|
|
{
|
|
"entropy": 5.156560802459717,
|
|
"epoch": 4.014409221902017,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003474372233783162,
|
|
"loss": 4.4939,
|
|
"mean_token_accuracy": 0.26957386285066604,
|
|
"num_tokens": 95821824.0,
|
|
"step": 41790
|
|
},
|
|
{
|
|
"entropy": 5.048311614990235,
|
|
"epoch": 4.014889529298751,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00034740476427352657,
|
|
"loss": 4.458,
|
|
"mean_token_accuracy": 0.2728587299585342,
|
|
"num_tokens": 95833122.0,
|
|
"step": 41795
|
|
},
|
|
{
|
|
"entropy": 5.023447751998901,
|
|
"epoch": 4.015369836695485,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003473723034877133,
|
|
"loss": 4.5195,
|
|
"mean_token_accuracy": 0.2607302963733673,
|
|
"num_tokens": 95844325.0,
|
|
"step": 41800
|
|
},
|
|
{
|
|
"entropy": 5.126571416854858,
|
|
"epoch": 4.015850144092219,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034733984102163005,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.25783698707818986,
|
|
"num_tokens": 95855788.0,
|
|
"step": 41805
|
|
},
|
|
{
|
|
"entropy": 5.213913440704346,
|
|
"epoch": 4.016330451488953,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003473073768760306,
|
|
"loss": 4.6098,
|
|
"mean_token_accuracy": 0.2556165471673012,
|
|
"num_tokens": 95867387.0,
|
|
"step": 41810
|
|
},
|
|
{
|
|
"entropy": 5.206772804260254,
|
|
"epoch": 4.016810758885687,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00034727491105166847,
|
|
"loss": 4.638,
|
|
"mean_token_accuracy": 0.2518103733658791,
|
|
"num_tokens": 95878258.0,
|
|
"step": 41815
|
|
},
|
|
{
|
|
"entropy": 5.165910482406616,
|
|
"epoch": 4.017291066282421,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003472424435492975,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.2659220814704895,
|
|
"num_tokens": 95889312.0,
|
|
"step": 41820
|
|
},
|
|
{
|
|
"entropy": 5.208985280990601,
|
|
"epoch": 4.017771373679155,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003472099743696716,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.2515991061925888,
|
|
"num_tokens": 95901930.0,
|
|
"step": 41825
|
|
},
|
|
{
|
|
"entropy": 5.071145057678223,
|
|
"epoch": 4.018251681075888,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003471775035135444,
|
|
"loss": 4.481,
|
|
"mean_token_accuracy": 0.26109506785869596,
|
|
"num_tokens": 95913877.0,
|
|
"step": 41830
|
|
},
|
|
{
|
|
"entropy": 5.116670942306518,
|
|
"epoch": 4.018731988472623,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00034714503098166996,
|
|
"loss": 4.5967,
|
|
"mean_token_accuracy": 0.26196528822183607,
|
|
"num_tokens": 95925259.0,
|
|
"step": 41835
|
|
},
|
|
{
|
|
"entropy": 5.106530570983887,
|
|
"epoch": 4.019212295869356,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00034711255677480216,
|
|
"loss": 4.5232,
|
|
"mean_token_accuracy": 0.26842849850654604,
|
|
"num_tokens": 95936612.0,
|
|
"step": 41840
|
|
},
|
|
{
|
|
"entropy": 5.075881671905518,
|
|
"epoch": 4.0196926032660905,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003470800808936948,
|
|
"loss": 4.5713,
|
|
"mean_token_accuracy": 0.26026141494512556,
|
|
"num_tokens": 95948505.0,
|
|
"step": 41845
|
|
},
|
|
{
|
|
"entropy": 5.048378562927246,
|
|
"epoch": 4.020172910662824,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00034704760333910205,
|
|
"loss": 4.4689,
|
|
"mean_token_accuracy": 0.27494739592075346,
|
|
"num_tokens": 95959767.0,
|
|
"step": 41850
|
|
},
|
|
{
|
|
"entropy": 5.210935640335083,
|
|
"epoch": 4.020653218059558,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003470151241117779,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.2527985006570816,
|
|
"num_tokens": 95971470.0,
|
|
"step": 41855
|
|
},
|
|
{
|
|
"entropy": 5.118702554702759,
|
|
"epoch": 4.021133525456292,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003469826432124764,
|
|
"loss": 4.522,
|
|
"mean_token_accuracy": 0.26311853528022766,
|
|
"num_tokens": 95983610.0,
|
|
"step": 41860
|
|
},
|
|
{
|
|
"entropy": 5.111933755874634,
|
|
"epoch": 4.021613832853026,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003469501606419517,
|
|
"loss": 4.5466,
|
|
"mean_token_accuracy": 0.26790870279073714,
|
|
"num_tokens": 95995199.0,
|
|
"step": 41865
|
|
},
|
|
{
|
|
"entropy": 5.163121128082276,
|
|
"epoch": 4.022094140249759,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003469176764009579,
|
|
"loss": 4.6217,
|
|
"mean_token_accuracy": 0.25430611819028853,
|
|
"num_tokens": 96005881.0,
|
|
"step": 41870
|
|
},
|
|
{
|
|
"entropy": 5.135541391372681,
|
|
"epoch": 4.022574447646494,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00034688519049024924,
|
|
"loss": 4.5133,
|
|
"mean_token_accuracy": 0.2631680816411972,
|
|
"num_tokens": 96016973.0,
|
|
"step": 41875
|
|
},
|
|
{
|
|
"entropy": 5.119970273971558,
|
|
"epoch": 4.023054755043228,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00034685270291057987,
|
|
"loss": 4.6381,
|
|
"mean_token_accuracy": 0.2447785884141922,
|
|
"num_tokens": 96029500.0,
|
|
"step": 41880
|
|
},
|
|
{
|
|
"entropy": 5.110211563110352,
|
|
"epoch": 4.0235350624399615,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00034682021366270403,
|
|
"loss": 4.477,
|
|
"mean_token_accuracy": 0.26997395157814025,
|
|
"num_tokens": 96042239.0,
|
|
"step": 41885
|
|
},
|
|
{
|
|
"entropy": 5.218335342407227,
|
|
"epoch": 4.024015369836696,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034678772274737626,
|
|
"loss": 4.6554,
|
|
"mean_token_accuracy": 0.25206792801618577,
|
|
"num_tokens": 96053385.0,
|
|
"step": 41890
|
|
},
|
|
{
|
|
"entropy": 5.117905330657959,
|
|
"epoch": 4.024495677233429,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00034675523016535067,
|
|
"loss": 4.5545,
|
|
"mean_token_accuracy": 0.26436540484428406,
|
|
"num_tokens": 96065600.0,
|
|
"step": 41895
|
|
},
|
|
{
|
|
"entropy": 5.151217317581176,
|
|
"epoch": 4.024975984630164,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00034672273591738155,
|
|
"loss": 4.5882,
|
|
"mean_token_accuracy": 0.25374262034893036,
|
|
"num_tokens": 96076591.0,
|
|
"step": 41900
|
|
},
|
|
{
|
|
"entropy": 5.043724298477173,
|
|
"epoch": 4.025456292026897,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0003466902400042236,
|
|
"loss": 4.5322,
|
|
"mean_token_accuracy": 0.2741218641400337,
|
|
"num_tokens": 96088643.0,
|
|
"step": 41905
|
|
},
|
|
{
|
|
"entropy": 5.156721067428589,
|
|
"epoch": 4.025936599423631,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003466577424266312,
|
|
"loss": 4.5906,
|
|
"mean_token_accuracy": 0.25970755964517594,
|
|
"num_tokens": 96101592.0,
|
|
"step": 41910
|
|
},
|
|
{
|
|
"entropy": 5.094272661209106,
|
|
"epoch": 4.026416906820365,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00034662524318535877,
|
|
"loss": 4.4815,
|
|
"mean_token_accuracy": 0.2705208703875542,
|
|
"num_tokens": 96113434.0,
|
|
"step": 41915
|
|
},
|
|
{
|
|
"entropy": 5.131614446640015,
|
|
"epoch": 4.026897214217099,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00034659274228116086,
|
|
"loss": 4.576,
|
|
"mean_token_accuracy": 0.26605685204267504,
|
|
"num_tokens": 96123576.0,
|
|
"step": 41920
|
|
},
|
|
{
|
|
"entropy": 5.1606916904449465,
|
|
"epoch": 4.027377521613833,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00034656023971479206,
|
|
"loss": 4.6762,
|
|
"mean_token_accuracy": 0.2504259541630745,
|
|
"num_tokens": 96135415.0,
|
|
"step": 41925
|
|
},
|
|
{
|
|
"entropy": 5.202372312545776,
|
|
"epoch": 4.027857829010567,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003465277354870069,
|
|
"loss": 4.6291,
|
|
"mean_token_accuracy": 0.26020716726779936,
|
|
"num_tokens": 96146740.0,
|
|
"step": 41930
|
|
},
|
|
{
|
|
"entropy": 5.036332368850708,
|
|
"epoch": 4.0283381364073,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00034649522959856027,
|
|
"loss": 4.4762,
|
|
"mean_token_accuracy": 0.2726058229804039,
|
|
"num_tokens": 96158650.0,
|
|
"step": 41935
|
|
},
|
|
{
|
|
"entropy": 5.176791477203369,
|
|
"epoch": 4.028818443804035,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00034646272205020664,
|
|
"loss": 4.6125,
|
|
"mean_token_accuracy": 0.2640493020415306,
|
|
"num_tokens": 96169394.0,
|
|
"step": 41940
|
|
},
|
|
{
|
|
"entropy": 5.144351863861084,
|
|
"epoch": 4.029298751200768,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003464302128427008,
|
|
"loss": 4.604,
|
|
"mean_token_accuracy": 0.2622025221586227,
|
|
"num_tokens": 96180791.0,
|
|
"step": 41945
|
|
},
|
|
{
|
|
"entropy": 5.031277227401733,
|
|
"epoch": 4.029779058597502,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003463977019767975,
|
|
"loss": 4.42,
|
|
"mean_token_accuracy": 0.27577112019062044,
|
|
"num_tokens": 96191705.0,
|
|
"step": 41950
|
|
},
|
|
{
|
|
"entropy": 5.157811546325684,
|
|
"epoch": 4.030259365994237,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003463651894532516,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.2517913028597832,
|
|
"num_tokens": 96203742.0,
|
|
"step": 41955
|
|
},
|
|
{
|
|
"entropy": 5.118921852111816,
|
|
"epoch": 4.03073967339097,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000346332675272818,
|
|
"loss": 4.5629,
|
|
"mean_token_accuracy": 0.2695233881473541,
|
|
"num_tokens": 96214991.0,
|
|
"step": 41960
|
|
},
|
|
{
|
|
"entropy": 5.071808004379273,
|
|
"epoch": 4.0312199807877045,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003463001594362513,
|
|
"loss": 4.524,
|
|
"mean_token_accuracy": 0.2629170551896095,
|
|
"num_tokens": 96227122.0,
|
|
"step": 41965
|
|
},
|
|
{
|
|
"entropy": 5.106209087371826,
|
|
"epoch": 4.031700288184438,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003462676419443067,
|
|
"loss": 4.4955,
|
|
"mean_token_accuracy": 0.2669056013226509,
|
|
"num_tokens": 96237508.0,
|
|
"step": 41970
|
|
},
|
|
{
|
|
"entropy": 5.088997650146484,
|
|
"epoch": 4.032180595581172,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003462351227977391,
|
|
"loss": 4.6274,
|
|
"mean_token_accuracy": 0.25512009412050246,
|
|
"num_tokens": 96250375.0,
|
|
"step": 41975
|
|
},
|
|
{
|
|
"entropy": 5.192554759979248,
|
|
"epoch": 4.032660902977906,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034620260199730345,
|
|
"loss": 4.5722,
|
|
"mean_token_accuracy": 0.2611354231834412,
|
|
"num_tokens": 96261199.0,
|
|
"step": 41980
|
|
},
|
|
{
|
|
"entropy": 5.180995845794678,
|
|
"epoch": 4.03314121037464,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00034617007954375486,
|
|
"loss": 4.6113,
|
|
"mean_token_accuracy": 0.25605629086494447,
|
|
"num_tokens": 96272492.0,
|
|
"step": 41985
|
|
},
|
|
{
|
|
"entropy": 5.052574300765992,
|
|
"epoch": 4.0336215177713735,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003461375554378483,
|
|
"loss": 4.4879,
|
|
"mean_token_accuracy": 0.2623376354575157,
|
|
"num_tokens": 96284657.0,
|
|
"step": 41990
|
|
},
|
|
{
|
|
"entropy": 5.214763116836548,
|
|
"epoch": 4.034101825168108,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00034610502968033895,
|
|
"loss": 4.6867,
|
|
"mean_token_accuracy": 0.24794410169124603,
|
|
"num_tokens": 96296958.0,
|
|
"step": 41995
|
|
},
|
|
{
|
|
"entropy": 5.113260698318482,
|
|
"epoch": 4.034582132564841,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000346072502271982,
|
|
"loss": 4.5142,
|
|
"mean_token_accuracy": 0.27240069061517713,
|
|
"num_tokens": 96307923.0,
|
|
"step": 42000
|
|
},
|
|
{
|
|
"epoch": 4.034582132564841,
|
|
"eval_entropy": 4.964730816082743,
|
|
"eval_loss": 4.745641231536865,
|
|
"eval_mean_token_accuracy": 0.2578337220842884,
|
|
"eval_num_tokens": 96307923.0,
|
|
"eval_runtime": 26.5974,
|
|
"eval_samples_per_second": 1233.767,
|
|
"eval_steps_per_second": 154.226,
|
|
"step": 42000
|
|
},
|
|
{
|
|
"entropy": 5.126488828659058,
|
|
"epoch": 4.0350624399615755,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003460399732135326,
|
|
"loss": 4.6007,
|
|
"mean_token_accuracy": 0.26087645888328553,
|
|
"num_tokens": 96320177.0,
|
|
"step": 42005
|
|
},
|
|
{
|
|
"entropy": 5.168888330459595,
|
|
"epoch": 4.035542747358309,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003460074425057458,
|
|
"loss": 4.6243,
|
|
"mean_token_accuracy": 0.26060561686754224,
|
|
"num_tokens": 96331860.0,
|
|
"step": 42010
|
|
},
|
|
{
|
|
"entropy": 4.980177974700927,
|
|
"epoch": 4.036023054755043,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00034597491014937723,
|
|
"loss": 4.4147,
|
|
"mean_token_accuracy": 0.2685848295688629,
|
|
"num_tokens": 96342111.0,
|
|
"step": 42015
|
|
},
|
|
{
|
|
"entropy": 5.072343587875366,
|
|
"epoch": 4.036503362151777,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003459423761451819,
|
|
"loss": 4.5981,
|
|
"mean_token_accuracy": 0.2580172911286354,
|
|
"num_tokens": 96353930.0,
|
|
"step": 42020
|
|
},
|
|
{
|
|
"entropy": 5.131817626953125,
|
|
"epoch": 4.036983669548511,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003459098404939153,
|
|
"loss": 4.5944,
|
|
"mean_token_accuracy": 0.2618457168340683,
|
|
"num_tokens": 96364924.0,
|
|
"step": 42025
|
|
},
|
|
{
|
|
"entropy": 5.1922516345977785,
|
|
"epoch": 4.037463976945245,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00034587730319633265,
|
|
"loss": 4.5945,
|
|
"mean_token_accuracy": 0.2551957294344902,
|
|
"num_tokens": 96377043.0,
|
|
"step": 42030
|
|
},
|
|
{
|
|
"entropy": 5.087650394439697,
|
|
"epoch": 4.037944284341979,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00034584476425318964,
|
|
"loss": 4.5167,
|
|
"mean_token_accuracy": 0.2682971253991127,
|
|
"num_tokens": 96388122.0,
|
|
"step": 42035
|
|
},
|
|
{
|
|
"entropy": 5.065549325942993,
|
|
"epoch": 4.038424591738713,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00034581222366524147,
|
|
"loss": 4.5342,
|
|
"mean_token_accuracy": 0.2616880744695663,
|
|
"num_tokens": 96399347.0,
|
|
"step": 42040
|
|
},
|
|
{
|
|
"entropy": 5.0761558532714846,
|
|
"epoch": 4.038904899135447,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00034577968143324365,
|
|
"loss": 4.5186,
|
|
"mean_token_accuracy": 0.2680987000465393,
|
|
"num_tokens": 96411249.0,
|
|
"step": 42045
|
|
},
|
|
{
|
|
"entropy": 5.163793563842773,
|
|
"epoch": 4.039385206532181,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000345747137557952,
|
|
"loss": 4.6614,
|
|
"mean_token_accuracy": 0.25495964735746385,
|
|
"num_tokens": 96423274.0,
|
|
"step": 42050
|
|
},
|
|
{
|
|
"entropy": 5.199334239959716,
|
|
"epoch": 4.039865513928914,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003457145920401218,
|
|
"loss": 4.6047,
|
|
"mean_token_accuracy": 0.2606772303581238,
|
|
"num_tokens": 96434822.0,
|
|
"step": 42055
|
|
},
|
|
{
|
|
"entropy": 5.121702814102173,
|
|
"epoch": 4.040345821325649,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00034568204488050875,
|
|
"loss": 4.5434,
|
|
"mean_token_accuracy": 0.2618080034852028,
|
|
"num_tokens": 96446313.0,
|
|
"step": 42060
|
|
},
|
|
{
|
|
"entropy": 5.178958797454834,
|
|
"epoch": 4.040826128722382,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003456494960798685,
|
|
"loss": 4.6234,
|
|
"mean_token_accuracy": 0.25628596544265747,
|
|
"num_tokens": 96457669.0,
|
|
"step": 42065
|
|
},
|
|
{
|
|
"entropy": 5.115191650390625,
|
|
"epoch": 4.041306436119116,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003456169456389567,
|
|
"loss": 4.5783,
|
|
"mean_token_accuracy": 0.26452783644199374,
|
|
"num_tokens": 96469056.0,
|
|
"step": 42070
|
|
},
|
|
{
|
|
"entropy": 5.007254600524902,
|
|
"epoch": 4.04178674351585,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00034558439355852915,
|
|
"loss": 4.4532,
|
|
"mean_token_accuracy": 0.2718577891588211,
|
|
"num_tokens": 96479783.0,
|
|
"step": 42075
|
|
},
|
|
{
|
|
"entropy": 5.082509136199951,
|
|
"epoch": 4.042267050912584,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003455518398393416,
|
|
"loss": 4.56,
|
|
"mean_token_accuracy": 0.2644143894314766,
|
|
"num_tokens": 96491473.0,
|
|
"step": 42080
|
|
},
|
|
{
|
|
"entropy": 5.15862512588501,
|
|
"epoch": 4.042747358309318,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034551928448214983,
|
|
"loss": 4.6127,
|
|
"mean_token_accuracy": 0.2645921528339386,
|
|
"num_tokens": 96502380.0,
|
|
"step": 42085
|
|
},
|
|
{
|
|
"entropy": 5.261500549316406,
|
|
"epoch": 4.043227665706052,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003454867274877096,
|
|
"loss": 4.6978,
|
|
"mean_token_accuracy": 0.25104417502880094,
|
|
"num_tokens": 96514157.0,
|
|
"step": 42090
|
|
},
|
|
{
|
|
"entropy": 5.19370551109314,
|
|
"epoch": 4.043707973102785,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00034545416885677695,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.2512030228972435,
|
|
"num_tokens": 96526549.0,
|
|
"step": 42095
|
|
},
|
|
{
|
|
"entropy": 5.125468826293945,
|
|
"epoch": 4.04418828049952,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003454216085901076,
|
|
"loss": 4.5855,
|
|
"mean_token_accuracy": 0.26254955381155015,
|
|
"num_tokens": 96539158.0,
|
|
"step": 42100
|
|
},
|
|
{
|
|
"entropy": 5.040839433670044,
|
|
"epoch": 4.044668587896253,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00034538904668845766,
|
|
"loss": 4.4967,
|
|
"mean_token_accuracy": 0.26936534494161607,
|
|
"num_tokens": 96552604.0,
|
|
"step": 42105
|
|
},
|
|
{
|
|
"entropy": 5.022911071777344,
|
|
"epoch": 4.0451488952929875,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003453564831525831,
|
|
"loss": 4.5063,
|
|
"mean_token_accuracy": 0.26450171917676923,
|
|
"num_tokens": 96565457.0,
|
|
"step": 42110
|
|
},
|
|
{
|
|
"entropy": 5.129180812835694,
|
|
"epoch": 4.045629202689722,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003453239179832399,
|
|
"loss": 4.5771,
|
|
"mean_token_accuracy": 0.262500436604023,
|
|
"num_tokens": 96575605.0,
|
|
"step": 42115
|
|
},
|
|
{
|
|
"entropy": 5.125135707855224,
|
|
"epoch": 4.046109510086455,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003452913511811841,
|
|
"loss": 4.5876,
|
|
"mean_token_accuracy": 0.2582676038146019,
|
|
"num_tokens": 96586426.0,
|
|
"step": 42120
|
|
},
|
|
{
|
|
"entropy": 5.118356084823608,
|
|
"epoch": 4.04658981748319,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003452587827471719,
|
|
"loss": 4.5469,
|
|
"mean_token_accuracy": 0.2577823489904404,
|
|
"num_tokens": 96597955.0,
|
|
"step": 42125
|
|
},
|
|
{
|
|
"entropy": 5.046468353271484,
|
|
"epoch": 4.047070124879923,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00034522621268195936,
|
|
"loss": 4.4915,
|
|
"mean_token_accuracy": 0.27014843076467515,
|
|
"num_tokens": 96609148.0,
|
|
"step": 42130
|
|
},
|
|
{
|
|
"entropy": 5.044950008392334,
|
|
"epoch": 4.047550432276657,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003451936409863027,
|
|
"loss": 4.4994,
|
|
"mean_token_accuracy": 0.2691175818443298,
|
|
"num_tokens": 96621221.0,
|
|
"step": 42135
|
|
},
|
|
{
|
|
"entropy": 5.128892421722412,
|
|
"epoch": 4.048030739673391,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034516106766095813,
|
|
"loss": 4.6134,
|
|
"mean_token_accuracy": 0.2595978543162346,
|
|
"num_tokens": 96632567.0,
|
|
"step": 42140
|
|
},
|
|
{
|
|
"entropy": 5.132300090789795,
|
|
"epoch": 4.048511047070125,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003451284927066819,
|
|
"loss": 4.5039,
|
|
"mean_token_accuracy": 0.2598700687289238,
|
|
"num_tokens": 96643501.0,
|
|
"step": 42145
|
|
},
|
|
{
|
|
"entropy": 5.050378274917603,
|
|
"epoch": 4.0489913544668585,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003450959161242303,
|
|
"loss": 4.5323,
|
|
"mean_token_accuracy": 0.26426228880882263,
|
|
"num_tokens": 96654395.0,
|
|
"step": 42150
|
|
},
|
|
{
|
|
"entropy": 5.16731972694397,
|
|
"epoch": 4.049471661863593,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003450633379143597,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.24512210637331008,
|
|
"num_tokens": 96666135.0,
|
|
"step": 42155
|
|
},
|
|
{
|
|
"entropy": 5.0924335479736325,
|
|
"epoch": 4.049951969260326,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00034503075807782634,
|
|
"loss": 4.4843,
|
|
"mean_token_accuracy": 0.26852212101221085,
|
|
"num_tokens": 96678149.0,
|
|
"step": 42160
|
|
},
|
|
{
|
|
"entropy": 5.102594614028931,
|
|
"epoch": 4.050432276657061,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003449981766153869,
|
|
"loss": 4.5368,
|
|
"mean_token_accuracy": 0.2710242852568626,
|
|
"num_tokens": 96688557.0,
|
|
"step": 42165
|
|
},
|
|
{
|
|
"entropy": 5.07190957069397,
|
|
"epoch": 4.050912584053794,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003449655935277976,
|
|
"loss": 4.5523,
|
|
"mean_token_accuracy": 0.2614740952849388,
|
|
"num_tokens": 96699404.0,
|
|
"step": 42170
|
|
},
|
|
{
|
|
"entropy": 5.069172477722168,
|
|
"epoch": 4.051392891450528,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034493300881581484,
|
|
"loss": 4.5174,
|
|
"mean_token_accuracy": 0.2603950411081314,
|
|
"num_tokens": 96711673.0,
|
|
"step": 42175
|
|
},
|
|
{
|
|
"entropy": 5.101453971862793,
|
|
"epoch": 4.051873198847262,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003449004224801954,
|
|
"loss": 4.5579,
|
|
"mean_token_accuracy": 0.2664817079901695,
|
|
"num_tokens": 96723113.0,
|
|
"step": 42180
|
|
},
|
|
{
|
|
"entropy": 5.21935076713562,
|
|
"epoch": 4.052353506243996,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003448678345216957,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.25735178887844085,
|
|
"num_tokens": 96733323.0,
|
|
"step": 42185
|
|
},
|
|
{
|
|
"entropy": 5.127061271667481,
|
|
"epoch": 4.0528338136407305,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00034483524494107235,
|
|
"loss": 4.5564,
|
|
"mean_token_accuracy": 0.261511518061161,
|
|
"num_tokens": 96743524.0,
|
|
"step": 42190
|
|
},
|
|
{
|
|
"entropy": 5.215609455108643,
|
|
"epoch": 4.053314121037464,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034480265373908187,
|
|
"loss": 4.6999,
|
|
"mean_token_accuracy": 0.251594765484333,
|
|
"num_tokens": 96756565.0,
|
|
"step": 42195
|
|
},
|
|
{
|
|
"entropy": 5.126093006134033,
|
|
"epoch": 4.053794428434198,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00034477006091648116,
|
|
"loss": 4.5085,
|
|
"mean_token_accuracy": 0.26199250519275663,
|
|
"num_tokens": 96767391.0,
|
|
"step": 42200
|
|
},
|
|
{
|
|
"entropy": 5.0698014259338375,
|
|
"epoch": 4.054274735830932,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00034473746647402674,
|
|
"loss": 4.5405,
|
|
"mean_token_accuracy": 0.2710871174931526,
|
|
"num_tokens": 96778074.0,
|
|
"step": 42205
|
|
},
|
|
{
|
|
"entropy": 5.0257950782775875,
|
|
"epoch": 4.054755043227666,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003447048704124754,
|
|
"loss": 4.4294,
|
|
"mean_token_accuracy": 0.27573995739221574,
|
|
"num_tokens": 96789669.0,
|
|
"step": 42210
|
|
},
|
|
{
|
|
"entropy": 5.170459175109864,
|
|
"epoch": 4.055235350624399,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003446722727325841,
|
|
"loss": 4.631,
|
|
"mean_token_accuracy": 0.25989709347486495,
|
|
"num_tokens": 96800089.0,
|
|
"step": 42215
|
|
},
|
|
{
|
|
"entropy": 5.136102676391602,
|
|
"epoch": 4.055715658021134,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003446396734351094,
|
|
"loss": 4.6613,
|
|
"mean_token_accuracy": 0.2536627218127251,
|
|
"num_tokens": 96812248.0,
|
|
"step": 42220
|
|
},
|
|
{
|
|
"entropy": 5.225402164459228,
|
|
"epoch": 4.056195965417867,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003446070725208083,
|
|
"loss": 4.6788,
|
|
"mean_token_accuracy": 0.24863726794719695,
|
|
"num_tokens": 96824016.0,
|
|
"step": 42225
|
|
},
|
|
{
|
|
"entropy": 5.1613787651062015,
|
|
"epoch": 4.0566762728146015,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003445744699904377,
|
|
"loss": 4.5383,
|
|
"mean_token_accuracy": 0.25919917821884153,
|
|
"num_tokens": 96835128.0,
|
|
"step": 42230
|
|
},
|
|
{
|
|
"entropy": 5.057219314575195,
|
|
"epoch": 4.057156580211335,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003445418658447544,
|
|
"loss": 4.5086,
|
|
"mean_token_accuracy": 0.2666572079062462,
|
|
"num_tokens": 96846755.0,
|
|
"step": 42235
|
|
},
|
|
{
|
|
"entropy": 5.088881731033325,
|
|
"epoch": 4.057636887608069,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00034450926008451556,
|
|
"loss": 4.5692,
|
|
"mean_token_accuracy": 0.26195970773696897,
|
|
"num_tokens": 96858262.0,
|
|
"step": 42240
|
|
},
|
|
{
|
|
"entropy": 5.14189567565918,
|
|
"epoch": 4.058117195004803,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003444766527104781,
|
|
"loss": 4.5794,
|
|
"mean_token_accuracy": 0.25847764760255815,
|
|
"num_tokens": 96871533.0,
|
|
"step": 42245
|
|
},
|
|
{
|
|
"entropy": 5.159091472625732,
|
|
"epoch": 4.058597502401537,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000344444043723399,
|
|
"loss": 4.589,
|
|
"mean_token_accuracy": 0.26295434683561325,
|
|
"num_tokens": 96883668.0,
|
|
"step": 42250
|
|
},
|
|
{
|
|
"entropy": 5.145650577545166,
|
|
"epoch": 4.0590778097982705,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003444114331240355,
|
|
"loss": 4.6189,
|
|
"mean_token_accuracy": 0.25386513620615003,
|
|
"num_tokens": 96894196.0,
|
|
"step": 42255
|
|
},
|
|
{
|
|
"entropy": 5.162836503982544,
|
|
"epoch": 4.059558117195005,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003443788209131446,
|
|
"loss": 4.6119,
|
|
"mean_token_accuracy": 0.2587836146354675,
|
|
"num_tokens": 96905570.0,
|
|
"step": 42260
|
|
},
|
|
{
|
|
"entropy": 5.156788682937622,
|
|
"epoch": 4.060038424591739,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00034434620709148343,
|
|
"loss": 4.5827,
|
|
"mean_token_accuracy": 0.2657826945185661,
|
|
"num_tokens": 96916852.0,
|
|
"step": 42265
|
|
},
|
|
{
|
|
"entropy": 5.099807024002075,
|
|
"epoch": 4.060518731988473,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003443135916598093,
|
|
"loss": 4.5498,
|
|
"mean_token_accuracy": 0.2566095158457756,
|
|
"num_tokens": 96927851.0,
|
|
"step": 42270
|
|
},
|
|
{
|
|
"entropy": 5.0897064208984375,
|
|
"epoch": 4.060999039385207,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00034428097461887934,
|
|
"loss": 4.5855,
|
|
"mean_token_accuracy": 0.2576803997159004,
|
|
"num_tokens": 96939976.0,
|
|
"step": 42275
|
|
},
|
|
{
|
|
"entropy": 5.13118348121643,
|
|
"epoch": 4.06147934678194,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003442483559694509,
|
|
"loss": 4.6167,
|
|
"mean_token_accuracy": 0.2592759311199188,
|
|
"num_tokens": 96951920.0,
|
|
"step": 42280
|
|
},
|
|
{
|
|
"entropy": 5.156069087982178,
|
|
"epoch": 4.061959654178675,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034421573571228134,
|
|
"loss": 4.5862,
|
|
"mean_token_accuracy": 0.260748428106308,
|
|
"num_tokens": 96963389.0,
|
|
"step": 42285
|
|
},
|
|
{
|
|
"entropy": 5.113003349304199,
|
|
"epoch": 4.062439961575408,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003441831138481279,
|
|
"loss": 4.5887,
|
|
"mean_token_accuracy": 0.2667728245258331,
|
|
"num_tokens": 96975250.0,
|
|
"step": 42290
|
|
},
|
|
{
|
|
"entropy": 5.032415342330933,
|
|
"epoch": 4.062920268972142,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003441504903777479,
|
|
"loss": 4.4852,
|
|
"mean_token_accuracy": 0.2683944717049599,
|
|
"num_tokens": 96986116.0,
|
|
"step": 42295
|
|
},
|
|
{
|
|
"entropy": 5.094413328170776,
|
|
"epoch": 4.063400576368876,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00034411786530189894,
|
|
"loss": 4.5612,
|
|
"mean_token_accuracy": 0.26135624945163727,
|
|
"num_tokens": 96998370.0,
|
|
"step": 42300
|
|
},
|
|
{
|
|
"entropy": 5.084097385406494,
|
|
"epoch": 4.06388088376561,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00034408523862133834,
|
|
"loss": 4.497,
|
|
"mean_token_accuracy": 0.26003549695014955,
|
|
"num_tokens": 97010866.0,
|
|
"step": 42305
|
|
},
|
|
{
|
|
"entropy": 5.180100822448731,
|
|
"epoch": 4.064361191162344,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00034405261033682363,
|
|
"loss": 4.5953,
|
|
"mean_token_accuracy": 0.2604702889919281,
|
|
"num_tokens": 97023127.0,
|
|
"step": 42310
|
|
},
|
|
{
|
|
"entropy": 5.174615669250488,
|
|
"epoch": 4.064841498559078,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003440199804491123,
|
|
"loss": 4.6224,
|
|
"mean_token_accuracy": 0.2553544119000435,
|
|
"num_tokens": 97035117.0,
|
|
"step": 42315
|
|
},
|
|
{
|
|
"entropy": 5.159887266159058,
|
|
"epoch": 4.065321805955811,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003439873489589621,
|
|
"loss": 4.6345,
|
|
"mean_token_accuracy": 0.25264530032873156,
|
|
"num_tokens": 97046711.0,
|
|
"step": 42320
|
|
},
|
|
{
|
|
"entropy": 5.134364891052246,
|
|
"epoch": 4.065802113352546,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003439547158671304,
|
|
"loss": 4.5371,
|
|
"mean_token_accuracy": 0.26378531754016876,
|
|
"num_tokens": 97059120.0,
|
|
"step": 42325
|
|
},
|
|
{
|
|
"entropy": 5.091711616516113,
|
|
"epoch": 4.066282420749279,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00034392208117437503,
|
|
"loss": 4.5584,
|
|
"mean_token_accuracy": 0.2544677823781967,
|
|
"num_tokens": 97071879.0,
|
|
"step": 42330
|
|
},
|
|
{
|
|
"entropy": 5.1580249786376955,
|
|
"epoch": 4.0667627281460135,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00034388944488145356,
|
|
"loss": 4.5774,
|
|
"mean_token_accuracy": 0.26482005417346954,
|
|
"num_tokens": 97082883.0,
|
|
"step": 42335
|
|
},
|
|
{
|
|
"entropy": 5.1096007347106935,
|
|
"epoch": 4.067243035542747,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00034385680698912377,
|
|
"loss": 4.5448,
|
|
"mean_token_accuracy": 0.26454581022262574,
|
|
"num_tokens": 97094174.0,
|
|
"step": 42340
|
|
},
|
|
{
|
|
"entropy": 5.157679224014283,
|
|
"epoch": 4.067723342939481,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034382416749814335,
|
|
"loss": 4.5979,
|
|
"mean_token_accuracy": 0.25676509737968445,
|
|
"num_tokens": 97104328.0,
|
|
"step": 42345
|
|
},
|
|
{
|
|
"entropy": 5.123759746551514,
|
|
"epoch": 4.068203650336216,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003437915264092701,
|
|
"loss": 4.5879,
|
|
"mean_token_accuracy": 0.2656217679381371,
|
|
"num_tokens": 97117533.0,
|
|
"step": 42350
|
|
},
|
|
{
|
|
"entropy": 5.16289119720459,
|
|
"epoch": 4.068683957732949,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003437588837232619,
|
|
"loss": 4.6152,
|
|
"mean_token_accuracy": 0.25809610784053805,
|
|
"num_tokens": 97129355.0,
|
|
"step": 42355
|
|
},
|
|
{
|
|
"entropy": 5.1024257183074955,
|
|
"epoch": 4.069164265129683,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00034372623944087656,
|
|
"loss": 4.5191,
|
|
"mean_token_accuracy": 0.2657457202672958,
|
|
"num_tokens": 97141424.0,
|
|
"step": 42360
|
|
},
|
|
{
|
|
"entropy": 5.10643162727356,
|
|
"epoch": 4.069644572526417,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003436935935628721,
|
|
"loss": 4.5762,
|
|
"mean_token_accuracy": 0.2666286930441856,
|
|
"num_tokens": 97152900.0,
|
|
"step": 42365
|
|
},
|
|
{
|
|
"entropy": 5.155328559875488,
|
|
"epoch": 4.070124879923151,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00034366094609000633,
|
|
"loss": 4.6302,
|
|
"mean_token_accuracy": 0.25692760199308395,
|
|
"num_tokens": 97163894.0,
|
|
"step": 42370
|
|
},
|
|
{
|
|
"entropy": 5.130299043655396,
|
|
"epoch": 4.0706051873198845,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003436282970230372,
|
|
"loss": 4.5929,
|
|
"mean_token_accuracy": 0.25584309697151186,
|
|
"num_tokens": 97175385.0,
|
|
"step": 42375
|
|
},
|
|
{
|
|
"entropy": 5.150226306915283,
|
|
"epoch": 4.071085494716619,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00034359564636272287,
|
|
"loss": 4.575,
|
|
"mean_token_accuracy": 0.2640173569321632,
|
|
"num_tokens": 97186830.0,
|
|
"step": 42380
|
|
},
|
|
{
|
|
"entropy": 5.202899551391601,
|
|
"epoch": 4.071565802113352,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003435629941098213,
|
|
"loss": 4.6178,
|
|
"mean_token_accuracy": 0.2574114233255386,
|
|
"num_tokens": 97197816.0,
|
|
"step": 42385
|
|
},
|
|
{
|
|
"entropy": 5.154549789428711,
|
|
"epoch": 4.072046109510087,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003435303402650906,
|
|
"loss": 4.5555,
|
|
"mean_token_accuracy": 0.26320657432079314,
|
|
"num_tokens": 97208721.0,
|
|
"step": 42390
|
|
},
|
|
{
|
|
"entropy": 5.153997945785522,
|
|
"epoch": 4.07252641690682,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000343497684829289,
|
|
"loss": 4.6824,
|
|
"mean_token_accuracy": 0.24842212498188018,
|
|
"num_tokens": 97220487.0,
|
|
"step": 42395
|
|
},
|
|
{
|
|
"entropy": 5.084363174438477,
|
|
"epoch": 4.073006724303554,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003434650278031744,
|
|
"loss": 4.5232,
|
|
"mean_token_accuracy": 0.27033036649227143,
|
|
"num_tokens": 97231995.0,
|
|
"step": 42400
|
|
},
|
|
{
|
|
"entropy": 5.097715568542481,
|
|
"epoch": 4.073487031700288,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00034343236918750523,
|
|
"loss": 4.471,
|
|
"mean_token_accuracy": 0.27465118914842607,
|
|
"num_tokens": 97243168.0,
|
|
"step": 42405
|
|
},
|
|
{
|
|
"entropy": 5.119933223724365,
|
|
"epoch": 4.073967339097022,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00034339970898303963,
|
|
"loss": 4.5722,
|
|
"mean_token_accuracy": 0.26859549432992935,
|
|
"num_tokens": 97254361.0,
|
|
"step": 42410
|
|
},
|
|
{
|
|
"entropy": 5.1479161262512205,
|
|
"epoch": 4.074447646493756,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00034336704719053584,
|
|
"loss": 4.529,
|
|
"mean_token_accuracy": 0.26103450655937194,
|
|
"num_tokens": 97265535.0,
|
|
"step": 42415
|
|
},
|
|
{
|
|
"entropy": 5.004811859130859,
|
|
"epoch": 4.07492795389049,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003433343838107523,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.26950025707483294,
|
|
"num_tokens": 97277426.0,
|
|
"step": 42420
|
|
},
|
|
{
|
|
"entropy": 5.00476040840149,
|
|
"epoch": 4.075408261287224,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00034330171884444725,
|
|
"loss": 4.5165,
|
|
"mean_token_accuracy": 0.2644503816962242,
|
|
"num_tokens": 97288897.0,
|
|
"step": 42425
|
|
},
|
|
{
|
|
"entropy": 5.105033683776855,
|
|
"epoch": 4.075888568683958,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034326905229237914,
|
|
"loss": 4.5587,
|
|
"mean_token_accuracy": 0.2560152724385262,
|
|
"num_tokens": 97299288.0,
|
|
"step": 42430
|
|
},
|
|
{
|
|
"entropy": 5.19445767402649,
|
|
"epoch": 4.076368876080692,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00034323638415530627,
|
|
"loss": 4.5803,
|
|
"mean_token_accuracy": 0.2621714100241661,
|
|
"num_tokens": 97309122.0,
|
|
"step": 42435
|
|
},
|
|
{
|
|
"entropy": 5.026162338256836,
|
|
"epoch": 4.076849183477425,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003432037144339872,
|
|
"loss": 4.5051,
|
|
"mean_token_accuracy": 0.26461121141910554,
|
|
"num_tokens": 97320390.0,
|
|
"step": 42440
|
|
},
|
|
{
|
|
"entropy": 5.090794897079467,
|
|
"epoch": 4.07732949087416,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00034317104312918054,
|
|
"loss": 4.6146,
|
|
"mean_token_accuracy": 0.25537932515144346,
|
|
"num_tokens": 97332062.0,
|
|
"step": 42445
|
|
},
|
|
{
|
|
"entropy": 5.108237648010254,
|
|
"epoch": 4.077809798270893,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003431383702416445,
|
|
"loss": 4.4971,
|
|
"mean_token_accuracy": 0.2655400767922401,
|
|
"num_tokens": 97343197.0,
|
|
"step": 42450
|
|
},
|
|
{
|
|
"entropy": 5.1483376026153564,
|
|
"epoch": 4.0782901056676275,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00034310569577213795,
|
|
"loss": 4.5507,
|
|
"mean_token_accuracy": 0.2647093921899796,
|
|
"num_tokens": 97354667.0,
|
|
"step": 42455
|
|
},
|
|
{
|
|
"entropy": 5.23777141571045,
|
|
"epoch": 4.078770413064361,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003430730197214193,
|
|
"loss": 4.7112,
|
|
"mean_token_accuracy": 0.25243735909461973,
|
|
"num_tokens": 97365011.0,
|
|
"step": 42460
|
|
},
|
|
{
|
|
"entropy": 5.0989912986755375,
|
|
"epoch": 4.079250720461095,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003430403420902473,
|
|
"loss": 4.5982,
|
|
"mean_token_accuracy": 0.25901423692703246,
|
|
"num_tokens": 97376285.0,
|
|
"step": 42465
|
|
},
|
|
{
|
|
"entropy": 5.093492031097412,
|
|
"epoch": 4.079731027857829,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00034300766287938066,
|
|
"loss": 4.5962,
|
|
"mean_token_accuracy": 0.26357435137033464,
|
|
"num_tokens": 97387901.0,
|
|
"step": 42470
|
|
},
|
|
{
|
|
"entropy": 5.1244653224945065,
|
|
"epoch": 4.080211335254563,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00034297498208957797,
|
|
"loss": 4.5286,
|
|
"mean_token_accuracy": 0.26892791986465453,
|
|
"num_tokens": 97399854.0,
|
|
"step": 42475
|
|
},
|
|
{
|
|
"entropy": 5.087628555297852,
|
|
"epoch": 4.0806916426512965,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000342942299721598,
|
|
"loss": 4.5247,
|
|
"mean_token_accuracy": 0.26527330428361895,
|
|
"num_tokens": 97410867.0,
|
|
"step": 42480
|
|
},
|
|
{
|
|
"entropy": 5.100114536285401,
|
|
"epoch": 4.081171950048031,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003429096157761997,
|
|
"loss": 4.6124,
|
|
"mean_token_accuracy": 0.2569648653268814,
|
|
"num_tokens": 97422890.0,
|
|
"step": 42485
|
|
},
|
|
{
|
|
"entropy": 5.065978765487671,
|
|
"epoch": 4.081652257444764,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003428769302541416,
|
|
"loss": 4.5177,
|
|
"mean_token_accuracy": 0.26677334755659105,
|
|
"num_tokens": 97434465.0,
|
|
"step": 42490
|
|
},
|
|
{
|
|
"entropy": 5.085080528259278,
|
|
"epoch": 4.082132564841499,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003428442431561828,
|
|
"loss": 4.4918,
|
|
"mean_token_accuracy": 0.2686756521463394,
|
|
"num_tokens": 97445358.0,
|
|
"step": 42495
|
|
},
|
|
{
|
|
"entropy": 5.095644474029541,
|
|
"epoch": 4.082612872238233,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003428115544830823,
|
|
"loss": 4.5132,
|
|
"mean_token_accuracy": 0.2669607475399971,
|
|
"num_tokens": 97456120.0,
|
|
"step": 42500
|
|
},
|
|
{
|
|
"entropy": 5.093516206741333,
|
|
"epoch": 4.083093179634966,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00034277886423559863,
|
|
"loss": 4.5857,
|
|
"mean_token_accuracy": 0.25843480676412584,
|
|
"num_tokens": 97467377.0,
|
|
"step": 42505
|
|
},
|
|
{
|
|
"entropy": 5.0444310188293455,
|
|
"epoch": 4.083573487031701,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00034274617241449105,
|
|
"loss": 4.6072,
|
|
"mean_token_accuracy": 0.2561612159013748,
|
|
"num_tokens": 97479250.0,
|
|
"step": 42510
|
|
},
|
|
{
|
|
"entropy": 5.175676870346069,
|
|
"epoch": 4.084053794428434,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00034271347902051864,
|
|
"loss": 4.6355,
|
|
"mean_token_accuracy": 0.2582369953393936,
|
|
"num_tokens": 97491157.0,
|
|
"step": 42515
|
|
},
|
|
{
|
|
"entropy": 5.080387115478516,
|
|
"epoch": 4.084534101825168,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003426807840544401,
|
|
"loss": 4.4717,
|
|
"mean_token_accuracy": 0.26577836722135545,
|
|
"num_tokens": 97503075.0,
|
|
"step": 42520
|
|
},
|
|
{
|
|
"entropy": 5.152067518234253,
|
|
"epoch": 4.085014409221902,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003426480875170149,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.25322952717542646,
|
|
"num_tokens": 97514026.0,
|
|
"step": 42525
|
|
},
|
|
{
|
|
"entropy": 5.107225704193115,
|
|
"epoch": 4.085494716618636,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00034261538940900195,
|
|
"loss": 4.5463,
|
|
"mean_token_accuracy": 0.25988485366106034,
|
|
"num_tokens": 97526866.0,
|
|
"step": 42530
|
|
},
|
|
{
|
|
"entropy": 5.167161226272583,
|
|
"epoch": 4.08597502401537,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003425826897311604,
|
|
"loss": 4.6546,
|
|
"mean_token_accuracy": 0.25486822724342345,
|
|
"num_tokens": 97538632.0,
|
|
"step": 42535
|
|
},
|
|
{
|
|
"entropy": 5.13564510345459,
|
|
"epoch": 4.086455331412104,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00034254998848424947,
|
|
"loss": 4.5518,
|
|
"mean_token_accuracy": 0.25787952840328215,
|
|
"num_tokens": 97549288.0,
|
|
"step": 42540
|
|
},
|
|
{
|
|
"entropy": 5.1351018905639645,
|
|
"epoch": 4.086935638808837,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003425172856690284,
|
|
"loss": 4.6319,
|
|
"mean_token_accuracy": 0.25834757685661314,
|
|
"num_tokens": 97560582.0,
|
|
"step": 42545
|
|
},
|
|
{
|
|
"entropy": 5.074346494674683,
|
|
"epoch": 4.087415946205572,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00034248458128625643,
|
|
"loss": 4.4917,
|
|
"mean_token_accuracy": 0.261666776239872,
|
|
"num_tokens": 97571974.0,
|
|
"step": 42550
|
|
},
|
|
{
|
|
"entropy": 5.131081438064575,
|
|
"epoch": 4.087896253602305,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00034245187533669285,
|
|
"loss": 4.5116,
|
|
"mean_token_accuracy": 0.2665835306048393,
|
|
"num_tokens": 97582456.0,
|
|
"step": 42555
|
|
},
|
|
{
|
|
"entropy": 5.142530059814453,
|
|
"epoch": 4.0883765609990395,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00034241916782109714,
|
|
"loss": 4.6314,
|
|
"mean_token_accuracy": 0.26058182269334795,
|
|
"num_tokens": 97593246.0,
|
|
"step": 42560
|
|
},
|
|
{
|
|
"entropy": 4.995113849639893,
|
|
"epoch": 4.088856868395773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00034238645874022845,
|
|
"loss": 4.426,
|
|
"mean_token_accuracy": 0.27428969591856,
|
|
"num_tokens": 97604004.0,
|
|
"step": 42565
|
|
},
|
|
{
|
|
"entropy": 5.144605875015259,
|
|
"epoch": 4.089337175792507,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00034235374809484626,
|
|
"loss": 4.6356,
|
|
"mean_token_accuracy": 0.2586605742573738,
|
|
"num_tokens": 97616122.0,
|
|
"step": 42570
|
|
},
|
|
{
|
|
"entropy": 5.099444055557251,
|
|
"epoch": 4.0898174831892415,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003423210358857101,
|
|
"loss": 4.5061,
|
|
"mean_token_accuracy": 0.26942131519317625,
|
|
"num_tokens": 97627550.0,
|
|
"step": 42575
|
|
},
|
|
{
|
|
"entropy": 5.180981826782227,
|
|
"epoch": 4.090297790585975,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00034228832211357935,
|
|
"loss": 4.6622,
|
|
"mean_token_accuracy": 0.24883010387420654,
|
|
"num_tokens": 97639952.0,
|
|
"step": 42580
|
|
},
|
|
{
|
|
"entropy": 5.064950037002563,
|
|
"epoch": 4.090778097982709,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00034225560677921354,
|
|
"loss": 4.4953,
|
|
"mean_token_accuracy": 0.2656998440623283,
|
|
"num_tokens": 97653158.0,
|
|
"step": 42585
|
|
},
|
|
{
|
|
"entropy": 5.180100059509277,
|
|
"epoch": 4.091258405379443,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00034222288988337233,
|
|
"loss": 4.6524,
|
|
"mean_token_accuracy": 0.2566633641719818,
|
|
"num_tokens": 97666768.0,
|
|
"step": 42590
|
|
},
|
|
{
|
|
"entropy": 5.154083299636841,
|
|
"epoch": 4.091738712776177,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003421901714268152,
|
|
"loss": 4.5637,
|
|
"mean_token_accuracy": 0.2623424962162971,
|
|
"num_tokens": 97678128.0,
|
|
"step": 42595
|
|
},
|
|
{
|
|
"entropy": 5.141461992263794,
|
|
"epoch": 4.0922190201729105,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00034215745141030177,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.2572967723011971,
|
|
"num_tokens": 97689565.0,
|
|
"step": 42600
|
|
},
|
|
{
|
|
"entropy": 5.098570775985718,
|
|
"epoch": 4.092699327569645,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00034212472983459176,
|
|
"loss": 4.5424,
|
|
"mean_token_accuracy": 0.2656812325119972,
|
|
"num_tokens": 97701315.0,
|
|
"step": 42605
|
|
},
|
|
{
|
|
"entropy": 5.189773797988892,
|
|
"epoch": 4.093179634966378,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003420920067004448,
|
|
"loss": 4.6043,
|
|
"mean_token_accuracy": 0.2607677161693573,
|
|
"num_tokens": 97712404.0,
|
|
"step": 42610
|
|
},
|
|
{
|
|
"entropy": 5.097449493408203,
|
|
"epoch": 4.093659942363113,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003420592820086207,
|
|
"loss": 4.5418,
|
|
"mean_token_accuracy": 0.26138817965984346,
|
|
"num_tokens": 97723547.0,
|
|
"step": 42615
|
|
},
|
|
{
|
|
"entropy": 5.077188396453858,
|
|
"epoch": 4.094140249759846,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00034202655575987925,
|
|
"loss": 4.5358,
|
|
"mean_token_accuracy": 0.27112307250499723,
|
|
"num_tokens": 97734133.0,
|
|
"step": 42620
|
|
},
|
|
{
|
|
"entropy": 5.178392553329468,
|
|
"epoch": 4.09462055715658,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00034199382795498015,
|
|
"loss": 4.6347,
|
|
"mean_token_accuracy": 0.2486893743276596,
|
|
"num_tokens": 97746479.0,
|
|
"step": 42625
|
|
},
|
|
{
|
|
"entropy": 5.149146986007691,
|
|
"epoch": 4.095100864553314,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00034196109859468325,
|
|
"loss": 4.5711,
|
|
"mean_token_accuracy": 0.2636167645454407,
|
|
"num_tokens": 97758042.0,
|
|
"step": 42630
|
|
},
|
|
{
|
|
"entropy": 5.084850168228149,
|
|
"epoch": 4.095581171950048,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003419283676797485,
|
|
"loss": 4.5688,
|
|
"mean_token_accuracy": 0.2663700684905052,
|
|
"num_tokens": 97770338.0,
|
|
"step": 42635
|
|
},
|
|
{
|
|
"entropy": 5.120107555389405,
|
|
"epoch": 4.0960614793467816,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00034189563521093587,
|
|
"loss": 4.5855,
|
|
"mean_token_accuracy": 0.26249847561120987,
|
|
"num_tokens": 97781274.0,
|
|
"step": 42640
|
|
},
|
|
{
|
|
"entropy": 5.168723678588867,
|
|
"epoch": 4.096541786743516,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003418629011890051,
|
|
"loss": 4.6505,
|
|
"mean_token_accuracy": 0.2564865604043007,
|
|
"num_tokens": 97792241.0,
|
|
"step": 42645
|
|
},
|
|
{
|
|
"entropy": 5.132556819915772,
|
|
"epoch": 4.09702209414025,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00034183016561471644,
|
|
"loss": 4.6197,
|
|
"mean_token_accuracy": 0.2609447404742241,
|
|
"num_tokens": 97803315.0,
|
|
"step": 42650
|
|
},
|
|
{
|
|
"entropy": 5.247826957702637,
|
|
"epoch": 4.097502401536984,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00034179742848882967,
|
|
"loss": 4.7212,
|
|
"mean_token_accuracy": 0.25188828706741334,
|
|
"num_tokens": 97815138.0,
|
|
"step": 42655
|
|
},
|
|
{
|
|
"entropy": 5.149366807937622,
|
|
"epoch": 4.097982708933718,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00034176468981210494,
|
|
"loss": 4.5231,
|
|
"mean_token_accuracy": 0.2682841747999191,
|
|
"num_tokens": 97826846.0,
|
|
"step": 42660
|
|
},
|
|
{
|
|
"entropy": 5.154016399383545,
|
|
"epoch": 4.098463016330451,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003417319495853025,
|
|
"loss": 4.6022,
|
|
"mean_token_accuracy": 0.2589025229215622,
|
|
"num_tokens": 97838561.0,
|
|
"step": 42665
|
|
},
|
|
{
|
|
"entropy": 5.129297351837158,
|
|
"epoch": 4.098943323727186,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003416992078091823,
|
|
"loss": 4.5809,
|
|
"mean_token_accuracy": 0.25565403401851655,
|
|
"num_tokens": 97850306.0,
|
|
"step": 42670
|
|
},
|
|
{
|
|
"entropy": 5.127656936645508,
|
|
"epoch": 4.099423631123919,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003416664644845044,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.26217167675495145,
|
|
"num_tokens": 97862193.0,
|
|
"step": 42675
|
|
},
|
|
{
|
|
"entropy": 5.163205289840699,
|
|
"epoch": 4.0999039385206535,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00034163371961202935,
|
|
"loss": 4.6342,
|
|
"mean_token_accuracy": 0.2522799357771873,
|
|
"num_tokens": 97874557.0,
|
|
"step": 42680
|
|
},
|
|
{
|
|
"entropy": 5.137312698364258,
|
|
"epoch": 4.100384245917387,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00034160097319251714,
|
|
"loss": 4.6192,
|
|
"mean_token_accuracy": 0.25824748128652575,
|
|
"num_tokens": 97885334.0,
|
|
"step": 42685
|
|
},
|
|
{
|
|
"entropy": 5.213319635391235,
|
|
"epoch": 4.100864553314121,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00034156822522672805,
|
|
"loss": 4.6689,
|
|
"mean_token_accuracy": 0.24872807264328003,
|
|
"num_tokens": 97896857.0,
|
|
"step": 42690
|
|
},
|
|
{
|
|
"entropy": 5.0915947437286375,
|
|
"epoch": 4.101344860710855,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003415354757154225,
|
|
"loss": 4.5071,
|
|
"mean_token_accuracy": 0.2635498076677322,
|
|
"num_tokens": 97908172.0,
|
|
"step": 42695
|
|
},
|
|
{
|
|
"entropy": 5.067932987213135,
|
|
"epoch": 4.101825168107589,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00034150272465936066,
|
|
"loss": 4.5064,
|
|
"mean_token_accuracy": 0.26923156529664993,
|
|
"num_tokens": 97920176.0,
|
|
"step": 42700
|
|
},
|
|
{
|
|
"entropy": 5.084629058837891,
|
|
"epoch": 4.1023054755043225,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00034146997205930307,
|
|
"loss": 4.5489,
|
|
"mean_token_accuracy": 0.2604499340057373,
|
|
"num_tokens": 97932225.0,
|
|
"step": 42705
|
|
},
|
|
{
|
|
"entropy": 5.115437078475952,
|
|
"epoch": 4.102785782901057,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003414372179160101,
|
|
"loss": 4.5481,
|
|
"mean_token_accuracy": 0.26465167552232743,
|
|
"num_tokens": 97942457.0,
|
|
"step": 42710
|
|
},
|
|
{
|
|
"entropy": 5.183927392959594,
|
|
"epoch": 4.10326609029779,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003414044622302424,
|
|
"loss": 4.6713,
|
|
"mean_token_accuracy": 0.2616240844130516,
|
|
"num_tokens": 97954278.0,
|
|
"step": 42715
|
|
},
|
|
{
|
|
"entropy": 5.179610109329223,
|
|
"epoch": 4.1037463976945245,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00034137170500276004,
|
|
"loss": 4.5804,
|
|
"mean_token_accuracy": 0.25446465611457825,
|
|
"num_tokens": 97966441.0,
|
|
"step": 42720
|
|
},
|
|
{
|
|
"entropy": 5.199604034423828,
|
|
"epoch": 4.104226705091258,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003413389462343238,
|
|
"loss": 4.5571,
|
|
"mean_token_accuracy": 0.26408916115760805,
|
|
"num_tokens": 97976810.0,
|
|
"step": 42725
|
|
},
|
|
{
|
|
"entropy": 5.097277307510376,
|
|
"epoch": 4.104707012487992,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003413061859256943,
|
|
"loss": 4.5519,
|
|
"mean_token_accuracy": 0.2615211308002472,
|
|
"num_tokens": 97989012.0,
|
|
"step": 42730
|
|
},
|
|
{
|
|
"entropy": 5.228954553604126,
|
|
"epoch": 4.105187319884727,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00034127342407763196,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.2463416188955307,
|
|
"num_tokens": 98000280.0,
|
|
"step": 42735
|
|
},
|
|
{
|
|
"entropy": 5.23823127746582,
|
|
"epoch": 4.10566762728146,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003412406606908976,
|
|
"loss": 4.6446,
|
|
"mean_token_accuracy": 0.2520978957414627,
|
|
"num_tokens": 98012097.0,
|
|
"step": 42740
|
|
},
|
|
{
|
|
"entropy": 5.21138277053833,
|
|
"epoch": 4.106147934678194,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003412078957662517,
|
|
"loss": 4.6722,
|
|
"mean_token_accuracy": 0.24687057584524155,
|
|
"num_tokens": 98022602.0,
|
|
"step": 42745
|
|
},
|
|
{
|
|
"entropy": 5.172147941589356,
|
|
"epoch": 4.106628242074928,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00034117512930445504,
|
|
"loss": 4.6308,
|
|
"mean_token_accuracy": 0.2555234909057617,
|
|
"num_tokens": 98034535.0,
|
|
"step": 42750
|
|
},
|
|
{
|
|
"entropy": 5.102917098999024,
|
|
"epoch": 4.107108549471662,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00034114236130626855,
|
|
"loss": 4.5439,
|
|
"mean_token_accuracy": 0.25935748517513274,
|
|
"num_tokens": 98046525.0,
|
|
"step": 42755
|
|
},
|
|
{
|
|
"entropy": 5.198196792602539,
|
|
"epoch": 4.107588856868396,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003411095917724527,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.2612493738532066,
|
|
"num_tokens": 98057540.0,
|
|
"step": 42760
|
|
},
|
|
{
|
|
"entropy": 5.177519464492798,
|
|
"epoch": 4.10806916426513,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034107682070376845,
|
|
"loss": 4.5992,
|
|
"mean_token_accuracy": 0.26878341287374496,
|
|
"num_tokens": 98068578.0,
|
|
"step": 42765
|
|
},
|
|
{
|
|
"entropy": 5.0950075626373295,
|
|
"epoch": 4.108549471661863,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00034104404810097663,
|
|
"loss": 4.5365,
|
|
"mean_token_accuracy": 0.25853474885225297,
|
|
"num_tokens": 98079981.0,
|
|
"step": 42770
|
|
},
|
|
{
|
|
"entropy": 5.0954183578491214,
|
|
"epoch": 4.109029779058598,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003410112739648381,
|
|
"loss": 4.5722,
|
|
"mean_token_accuracy": 0.26313221603631975,
|
|
"num_tokens": 98091579.0,
|
|
"step": 42775
|
|
},
|
|
{
|
|
"entropy": 5.158852910995483,
|
|
"epoch": 4.109510086455331,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00034097849829611387,
|
|
"loss": 4.6494,
|
|
"mean_token_accuracy": 0.2487236186861992,
|
|
"num_tokens": 98103239.0,
|
|
"step": 42780
|
|
},
|
|
{
|
|
"entropy": 5.172920227050781,
|
|
"epoch": 4.109990393852065,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00034094572109556477,
|
|
"loss": 4.5525,
|
|
"mean_token_accuracy": 0.26216920763254165,
|
|
"num_tokens": 98114865.0,
|
|
"step": 42785
|
|
},
|
|
{
|
|
"entropy": 5.099450397491455,
|
|
"epoch": 4.110470701248799,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00034091294236395186,
|
|
"loss": 4.5233,
|
|
"mean_token_accuracy": 0.2562653377652168,
|
|
"num_tokens": 98125831.0,
|
|
"step": 42790
|
|
},
|
|
{
|
|
"entropy": 5.072196578979492,
|
|
"epoch": 4.110951008645533,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00034088016210203617,
|
|
"loss": 4.5441,
|
|
"mean_token_accuracy": 0.2606132045388222,
|
|
"num_tokens": 98136129.0,
|
|
"step": 42795
|
|
},
|
|
{
|
|
"entropy": 5.179393625259399,
|
|
"epoch": 4.111431316042267,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003408473803105788,
|
|
"loss": 4.6532,
|
|
"mean_token_accuracy": 0.2511350974440575,
|
|
"num_tokens": 98148022.0,
|
|
"step": 42800
|
|
},
|
|
{
|
|
"entropy": 5.1367028713226315,
|
|
"epoch": 4.111911623439001,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003408145969903406,
|
|
"loss": 4.5108,
|
|
"mean_token_accuracy": 0.26437780261039734,
|
|
"num_tokens": 98159567.0,
|
|
"step": 42805
|
|
},
|
|
{
|
|
"entropy": 5.179000043869019,
|
|
"epoch": 4.112391930835735,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00034078181214208304,
|
|
"loss": 4.6695,
|
|
"mean_token_accuracy": 0.25815082937479017,
|
|
"num_tokens": 98171957.0,
|
|
"step": 42810
|
|
},
|
|
{
|
|
"entropy": 5.046087694168091,
|
|
"epoch": 4.112872238232469,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003407490257665671,
|
|
"loss": 4.5124,
|
|
"mean_token_accuracy": 0.27057994306087496,
|
|
"num_tokens": 98184553.0,
|
|
"step": 42815
|
|
},
|
|
{
|
|
"entropy": 5.196060562133789,
|
|
"epoch": 4.113352545629203,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000340716237864554,
|
|
"loss": 4.6623,
|
|
"mean_token_accuracy": 0.2481478065252304,
|
|
"num_tokens": 98196510.0,
|
|
"step": 42820
|
|
},
|
|
{
|
|
"entropy": 5.211407661437988,
|
|
"epoch": 4.1138328530259365,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00034068344843680493,
|
|
"loss": 4.6923,
|
|
"mean_token_accuracy": 0.24605648666620256,
|
|
"num_tokens": 98207234.0,
|
|
"step": 42825
|
|
},
|
|
{
|
|
"entropy": 5.123365068435669,
|
|
"epoch": 4.114313160422671,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00034065065748408135,
|
|
"loss": 4.5194,
|
|
"mean_token_accuracy": 0.26389059871435167,
|
|
"num_tokens": 98218853.0,
|
|
"step": 42830
|
|
},
|
|
{
|
|
"entropy": 5.1285326957702635,
|
|
"epoch": 4.114793467819404,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034061786500714434,
|
|
"loss": 4.608,
|
|
"mean_token_accuracy": 0.2612140506505966,
|
|
"num_tokens": 98230668.0,
|
|
"step": 42835
|
|
},
|
|
{
|
|
"entropy": 5.055058431625366,
|
|
"epoch": 4.115273775216139,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00034058507100675545,
|
|
"loss": 4.4907,
|
|
"mean_token_accuracy": 0.26553813368082047,
|
|
"num_tokens": 98241982.0,
|
|
"step": 42840
|
|
},
|
|
{
|
|
"entropy": 5.168752431869507,
|
|
"epoch": 4.115754082612872,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00034055227548367595,
|
|
"loss": 4.6225,
|
|
"mean_token_accuracy": 0.25371553301811217,
|
|
"num_tokens": 98253726.0,
|
|
"step": 42845
|
|
},
|
|
{
|
|
"entropy": 5.207250261306763,
|
|
"epoch": 4.116234390009606,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003405194784386672,
|
|
"loss": 4.564,
|
|
"mean_token_accuracy": 0.2575871378183365,
|
|
"num_tokens": 98264290.0,
|
|
"step": 42850
|
|
},
|
|
{
|
|
"entropy": 5.115624809265137,
|
|
"epoch": 4.11671469740634,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003404866798724907,
|
|
"loss": 4.5444,
|
|
"mean_token_accuracy": 0.2632287308573723,
|
|
"num_tokens": 98276175.0,
|
|
"step": 42855
|
|
},
|
|
{
|
|
"entropy": 5.007231044769287,
|
|
"epoch": 4.117195004803074,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000340453879785908,
|
|
"loss": 4.4986,
|
|
"mean_token_accuracy": 0.26710980832576753,
|
|
"num_tokens": 98287023.0,
|
|
"step": 42860
|
|
},
|
|
{
|
|
"entropy": 5.109439992904663,
|
|
"epoch": 4.1176753121998075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00034042107817968054,
|
|
"loss": 4.5375,
|
|
"mean_token_accuracy": 0.266175651550293,
|
|
"num_tokens": 98297576.0,
|
|
"step": 42865
|
|
},
|
|
{
|
|
"entropy": 5.096857309341431,
|
|
"epoch": 4.118155619596542,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00034038827505456995,
|
|
"loss": 4.57,
|
|
"mean_token_accuracy": 0.258187335729599,
|
|
"num_tokens": 98308951.0,
|
|
"step": 42870
|
|
},
|
|
{
|
|
"entropy": 5.133897304534912,
|
|
"epoch": 4.118635926993275,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003403554704113378,
|
|
"loss": 4.5915,
|
|
"mean_token_accuracy": 0.2622078821063042,
|
|
"num_tokens": 98320696.0,
|
|
"step": 42875
|
|
},
|
|
{
|
|
"entropy": 5.162302446365357,
|
|
"epoch": 4.11911623439001,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003403226642507456,
|
|
"loss": 4.5919,
|
|
"mean_token_accuracy": 0.2583540499210358,
|
|
"num_tokens": 98331778.0,
|
|
"step": 42880
|
|
},
|
|
{
|
|
"entropy": 5.158097887039185,
|
|
"epoch": 4.119596541786744,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00034028985657355516,
|
|
"loss": 4.5785,
|
|
"mean_token_accuracy": 0.26226812452077863,
|
|
"num_tokens": 98343142.0,
|
|
"step": 42885
|
|
},
|
|
{
|
|
"entropy": 5.127803611755371,
|
|
"epoch": 4.120076849183477,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003402570473805281,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.25838354229927063,
|
|
"num_tokens": 98354907.0,
|
|
"step": 42890
|
|
},
|
|
{
|
|
"entropy": 5.171200227737427,
|
|
"epoch": 4.120557156580212,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003402242366724262,
|
|
"loss": 4.7186,
|
|
"mean_token_accuracy": 0.25251453518867495,
|
|
"num_tokens": 98366846.0,
|
|
"step": 42895
|
|
},
|
|
{
|
|
"entropy": 5.174951076507568,
|
|
"epoch": 4.121037463976945,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00034019142445001116,
|
|
"loss": 4.5972,
|
|
"mean_token_accuracy": 0.2634399965405464,
|
|
"num_tokens": 98379572.0,
|
|
"step": 42900
|
|
},
|
|
{
|
|
"entropy": 5.147320175170899,
|
|
"epoch": 4.1215177713736795,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00034015861071404484,
|
|
"loss": 4.6109,
|
|
"mean_token_accuracy": 0.2547128960490227,
|
|
"num_tokens": 98391151.0,
|
|
"step": 42905
|
|
},
|
|
{
|
|
"entropy": 5.113903141021728,
|
|
"epoch": 4.121998078770413,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003401257954652891,
|
|
"loss": 4.5394,
|
|
"mean_token_accuracy": 0.2641802117228508,
|
|
"num_tokens": 98402012.0,
|
|
"step": 42910
|
|
},
|
|
{
|
|
"entropy": 5.093675136566162,
|
|
"epoch": 4.122478386167147,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00034009297870450574,
|
|
"loss": 4.4939,
|
|
"mean_token_accuracy": 0.26563109308481214,
|
|
"num_tokens": 98413533.0,
|
|
"step": 42915
|
|
},
|
|
{
|
|
"entropy": 5.034172630310058,
|
|
"epoch": 4.122958693563881,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003400601604324567,
|
|
"loss": 4.4762,
|
|
"mean_token_accuracy": 0.2697063058614731,
|
|
"num_tokens": 98425056.0,
|
|
"step": 42920
|
|
},
|
|
{
|
|
"entropy": 5.158039140701294,
|
|
"epoch": 4.123439000960615,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00034002734064990386,
|
|
"loss": 4.635,
|
|
"mean_token_accuracy": 0.2594065651297569,
|
|
"num_tokens": 98436768.0,
|
|
"step": 42925
|
|
},
|
|
{
|
|
"entropy": 5.208445978164673,
|
|
"epoch": 4.123919308357348,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003399945193576093,
|
|
"loss": 4.6584,
|
|
"mean_token_accuracy": 0.25427514165639875,
|
|
"num_tokens": 98449360.0,
|
|
"step": 42930
|
|
},
|
|
{
|
|
"entropy": 5.115215396881103,
|
|
"epoch": 4.124399615754083,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003399616965563351,
|
|
"loss": 4.5407,
|
|
"mean_token_accuracy": 0.2642518475651741,
|
|
"num_tokens": 98461717.0,
|
|
"step": 42935
|
|
},
|
|
{
|
|
"entropy": 5.110986757278442,
|
|
"epoch": 4.124879923150816,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003399288722468431,
|
|
"loss": 4.5529,
|
|
"mean_token_accuracy": 0.2622468858957291,
|
|
"num_tokens": 98472186.0,
|
|
"step": 42940
|
|
},
|
|
{
|
|
"entropy": 5.152590036392212,
|
|
"epoch": 4.1253602305475505,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003398960464298955,
|
|
"loss": 4.5995,
|
|
"mean_token_accuracy": 0.26010182946920396,
|
|
"num_tokens": 98483266.0,
|
|
"step": 42945
|
|
},
|
|
{
|
|
"entropy": 5.066562461853027,
|
|
"epoch": 4.125840537944284,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003398632191062544,
|
|
"loss": 4.4853,
|
|
"mean_token_accuracy": 0.26762074530124663,
|
|
"num_tokens": 98494984.0,
|
|
"step": 42950
|
|
},
|
|
{
|
|
"entropy": 5.076995420455932,
|
|
"epoch": 4.126320845341018,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000339830390276682,
|
|
"loss": 4.5221,
|
|
"mean_token_accuracy": 0.26983180195093154,
|
|
"num_tokens": 98506564.0,
|
|
"step": 42955
|
|
},
|
|
{
|
|
"entropy": 5.057938718795777,
|
|
"epoch": 4.126801152737752,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00033979755994194033,
|
|
"loss": 4.5311,
|
|
"mean_token_accuracy": 0.26580351740121844,
|
|
"num_tokens": 98519732.0,
|
|
"step": 42960
|
|
},
|
|
{
|
|
"entropy": 5.17632098197937,
|
|
"epoch": 4.127281460134486,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003397647281027919,
|
|
"loss": 4.6411,
|
|
"mean_token_accuracy": 0.2564285323023796,
|
|
"num_tokens": 98530271.0,
|
|
"step": 42965
|
|
},
|
|
{
|
|
"entropy": 5.111835908889771,
|
|
"epoch": 4.12776176753122,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003397318947599987,
|
|
"loss": 4.5028,
|
|
"mean_token_accuracy": 0.2680714622139931,
|
|
"num_tokens": 98540178.0,
|
|
"step": 42970
|
|
},
|
|
{
|
|
"entropy": 5.107823848724365,
|
|
"epoch": 4.128242074927954,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00033969905991432307,
|
|
"loss": 4.6143,
|
|
"mean_token_accuracy": 0.256190088391304,
|
|
"num_tokens": 98551513.0,
|
|
"step": 42975
|
|
},
|
|
{
|
|
"entropy": 5.199556159973144,
|
|
"epoch": 4.128722382324688,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00033966622356652746,
|
|
"loss": 4.6723,
|
|
"mean_token_accuracy": 0.2537394553422928,
|
|
"num_tokens": 98563971.0,
|
|
"step": 42980
|
|
},
|
|
{
|
|
"entropy": 5.236239051818847,
|
|
"epoch": 4.129202689721422,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003396333857173741,
|
|
"loss": 4.607,
|
|
"mean_token_accuracy": 0.26102848500013354,
|
|
"num_tokens": 98575348.0,
|
|
"step": 42985
|
|
},
|
|
{
|
|
"entropy": 5.1129528999328615,
|
|
"epoch": 4.129682997118156,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003396005463676255,
|
|
"loss": 4.5717,
|
|
"mean_token_accuracy": 0.25404597669839857,
|
|
"num_tokens": 98586238.0,
|
|
"step": 42990
|
|
},
|
|
{
|
|
"entropy": 5.0700725555419925,
|
|
"epoch": 4.130163304514889,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000339567705518044,
|
|
"loss": 4.5618,
|
|
"mean_token_accuracy": 0.26050373166799545,
|
|
"num_tokens": 98599051.0,
|
|
"step": 42995
|
|
},
|
|
{
|
|
"entropy": 5.0803821086883545,
|
|
"epoch": 4.130643611911624,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00033953486316939214,
|
|
"loss": 4.5293,
|
|
"mean_token_accuracy": 0.2624590054154396,
|
|
"num_tokens": 98610526.0,
|
|
"step": 43000
|
|
},
|
|
{
|
|
"entropy": 5.04176549911499,
|
|
"epoch": 4.131123919308357,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00033950201932243237,
|
|
"loss": 4.4103,
|
|
"mean_token_accuracy": 0.2715850591659546,
|
|
"num_tokens": 98621720.0,
|
|
"step": 43005
|
|
},
|
|
{
|
|
"entropy": 5.077356243133545,
|
|
"epoch": 4.131604226705091,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00033946917397792724,
|
|
"loss": 4.5606,
|
|
"mean_token_accuracy": 0.2669913649559021,
|
|
"num_tokens": 98632248.0,
|
|
"step": 43010
|
|
},
|
|
{
|
|
"entropy": 5.046194362640381,
|
|
"epoch": 4.132084534101825,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003394363271366393,
|
|
"loss": 4.5693,
|
|
"mean_token_accuracy": 0.26449274718761445,
|
|
"num_tokens": 98643097.0,
|
|
"step": 43015
|
|
},
|
|
{
|
|
"entropy": 5.092310762405395,
|
|
"epoch": 4.132564841498559,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003394034787993312,
|
|
"loss": 4.4582,
|
|
"mean_token_accuracy": 0.2707664057612419,
|
|
"num_tokens": 98653429.0,
|
|
"step": 43020
|
|
},
|
|
{
|
|
"entropy": 5.107049131393433,
|
|
"epoch": 4.133045148895293,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00033937062896676563,
|
|
"loss": 4.5205,
|
|
"mean_token_accuracy": 0.26319051831960677,
|
|
"num_tokens": 98664972.0,
|
|
"step": 43025
|
|
},
|
|
{
|
|
"entropy": 5.128238821029663,
|
|
"epoch": 4.133525456292027,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00033933777763970506,
|
|
"loss": 4.6113,
|
|
"mean_token_accuracy": 0.2607093006372452,
|
|
"num_tokens": 98675075.0,
|
|
"step": 43030
|
|
},
|
|
{
|
|
"entropy": 5.195500278472901,
|
|
"epoch": 4.13400576368876,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003393049248189124,
|
|
"loss": 4.6382,
|
|
"mean_token_accuracy": 0.256962476670742,
|
|
"num_tokens": 98686749.0,
|
|
"step": 43035
|
|
},
|
|
{
|
|
"entropy": 5.1503767490386965,
|
|
"epoch": 4.134486071085495,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003392720705051504,
|
|
"loss": 4.6411,
|
|
"mean_token_accuracy": 0.2528755247592926,
|
|
"num_tokens": 98698229.0,
|
|
"step": 43040
|
|
},
|
|
{
|
|
"entropy": 5.109026670455933,
|
|
"epoch": 4.134966378482229,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00033923921469918174,
|
|
"loss": 4.6057,
|
|
"mean_token_accuracy": 0.26050054132938383,
|
|
"num_tokens": 98708302.0,
|
|
"step": 43045
|
|
},
|
|
{
|
|
"entropy": 5.125288820266723,
|
|
"epoch": 4.1354466858789625,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003392063574017692,
|
|
"loss": 4.5676,
|
|
"mean_token_accuracy": 0.26695929914712907,
|
|
"num_tokens": 98719882.0,
|
|
"step": 43050
|
|
},
|
|
{
|
|
"entropy": 5.1315244197845455,
|
|
"epoch": 4.135926993275697,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00033917349861367575,
|
|
"loss": 4.5722,
|
|
"mean_token_accuracy": 0.2668458819389343,
|
|
"num_tokens": 98730123.0,
|
|
"step": 43055
|
|
},
|
|
{
|
|
"entropy": 5.090600252151489,
|
|
"epoch": 4.13640730067243,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003391406383356642,
|
|
"loss": 4.5518,
|
|
"mean_token_accuracy": 0.2654767245054245,
|
|
"num_tokens": 98739605.0,
|
|
"step": 43060
|
|
},
|
|
{
|
|
"entropy": 5.125637054443359,
|
|
"epoch": 4.136887608069165,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00033910777656849745,
|
|
"loss": 4.6047,
|
|
"mean_token_accuracy": 0.26437491178512573,
|
|
"num_tokens": 98752474.0,
|
|
"step": 43065
|
|
},
|
|
{
|
|
"entropy": 5.175007247924805,
|
|
"epoch": 4.137367915465898,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003390749133129386,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.2535927876830101,
|
|
"num_tokens": 98764982.0,
|
|
"step": 43070
|
|
},
|
|
{
|
|
"entropy": 5.108830785751342,
|
|
"epoch": 4.137848222862632,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003390420485697504,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.26499575525522234,
|
|
"num_tokens": 98777464.0,
|
|
"step": 43075
|
|
},
|
|
{
|
|
"entropy": 5.163952493667603,
|
|
"epoch": 4.138328530259366,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033900918233969606,
|
|
"loss": 4.5634,
|
|
"mean_token_accuracy": 0.262498240172863,
|
|
"num_tokens": 98788672.0,
|
|
"step": 43080
|
|
},
|
|
{
|
|
"entropy": 5.255588006973267,
|
|
"epoch": 4.1388088376561,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00033897631462353854,
|
|
"loss": 4.7503,
|
|
"mean_token_accuracy": 0.24474239498376846,
|
|
"num_tokens": 98801531.0,
|
|
"step": 43085
|
|
},
|
|
{
|
|
"entropy": 5.101682472229004,
|
|
"epoch": 4.1392891450528335,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000338943445422041,
|
|
"loss": 4.5405,
|
|
"mean_token_accuracy": 0.26682236045598984,
|
|
"num_tokens": 98811534.0,
|
|
"step": 43090
|
|
},
|
|
{
|
|
"entropy": 5.192019653320313,
|
|
"epoch": 4.139769452449568,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00033891057473596655,
|
|
"loss": 4.6376,
|
|
"mean_token_accuracy": 0.25865285843610764,
|
|
"num_tokens": 98823220.0,
|
|
"step": 43095
|
|
},
|
|
{
|
|
"entropy": 5.096272945404053,
|
|
"epoch": 4.140249759846301,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003388777025660783,
|
|
"loss": 4.4987,
|
|
"mean_token_accuracy": 0.2667289212346077,
|
|
"num_tokens": 98834389.0,
|
|
"step": 43100
|
|
},
|
|
{
|
|
"entropy": 5.144219398498535,
|
|
"epoch": 4.140730067243036,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003388448289131395,
|
|
"loss": 4.6224,
|
|
"mean_token_accuracy": 0.25197176784276965,
|
|
"num_tokens": 98846399.0,
|
|
"step": 43105
|
|
},
|
|
{
|
|
"entropy": 5.19870548248291,
|
|
"epoch": 4.141210374639769,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00033881195377791337,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.2484152227640152,
|
|
"num_tokens": 98858448.0,
|
|
"step": 43110
|
|
},
|
|
{
|
|
"entropy": 5.0163792133331295,
|
|
"epoch": 4.141690682036503,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00033877907716116314,
|
|
"loss": 4.4161,
|
|
"mean_token_accuracy": 0.2706933617591858,
|
|
"num_tokens": 98871113.0,
|
|
"step": 43115
|
|
},
|
|
{
|
|
"entropy": 5.137840223312378,
|
|
"epoch": 4.142170989433238,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000338746199063652,
|
|
"loss": 4.5799,
|
|
"mean_token_accuracy": 0.257862514257431,
|
|
"num_tokens": 98881779.0,
|
|
"step": 43120
|
|
},
|
|
{
|
|
"entropy": 5.136895704269409,
|
|
"epoch": 4.142651296829971,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003387133194861435,
|
|
"loss": 4.5673,
|
|
"mean_token_accuracy": 0.2590453624725342,
|
|
"num_tokens": 98893490.0,
|
|
"step": 43125
|
|
},
|
|
{
|
|
"entropy": 5.207380294799805,
|
|
"epoch": 4.1431316042267055,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033868043842940097,
|
|
"loss": 4.6364,
|
|
"mean_token_accuracy": 0.2615066349506378,
|
|
"num_tokens": 98904485.0,
|
|
"step": 43130
|
|
},
|
|
{
|
|
"entropy": 5.107270431518555,
|
|
"epoch": 4.143611911623439,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00033864755589418764,
|
|
"loss": 4.5654,
|
|
"mean_token_accuracy": 0.26077206432819366,
|
|
"num_tokens": 98916276.0,
|
|
"step": 43135
|
|
},
|
|
{
|
|
"entropy": 5.081212902069092,
|
|
"epoch": 4.144092219020173,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033861467188126714,
|
|
"loss": 4.5932,
|
|
"mean_token_accuracy": 0.2637625813484192,
|
|
"num_tokens": 98927891.0,
|
|
"step": 43140
|
|
},
|
|
{
|
|
"entropy": 5.134432601928711,
|
|
"epoch": 4.144572526416907,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00033858178639140286,
|
|
"loss": 4.5604,
|
|
"mean_token_accuracy": 0.2648747399449348,
|
|
"num_tokens": 98939396.0,
|
|
"step": 43145
|
|
},
|
|
{
|
|
"entropy": 5.117592906951904,
|
|
"epoch": 4.145052833813641,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003385488994253583,
|
|
"loss": 4.5354,
|
|
"mean_token_accuracy": 0.2645690947771072,
|
|
"num_tokens": 98950327.0,
|
|
"step": 43150
|
|
},
|
|
{
|
|
"entropy": 5.148918485641479,
|
|
"epoch": 4.145533141210374,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000338516010983897,
|
|
"loss": 4.6297,
|
|
"mean_token_accuracy": 0.2622546821832657,
|
|
"num_tokens": 98961867.0,
|
|
"step": 43155
|
|
},
|
|
{
|
|
"entropy": 5.158444452285766,
|
|
"epoch": 4.146013448607109,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00033848312106778247,
|
|
"loss": 4.5811,
|
|
"mean_token_accuracy": 0.25925479978322985,
|
|
"num_tokens": 98972998.0,
|
|
"step": 43160
|
|
},
|
|
{
|
|
"entropy": 5.157982110977173,
|
|
"epoch": 4.146493756003842,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033845022967777833,
|
|
"loss": 4.6657,
|
|
"mean_token_accuracy": 0.2519380271434784,
|
|
"num_tokens": 98986898.0,
|
|
"step": 43165
|
|
},
|
|
{
|
|
"entropy": 5.197014904022216,
|
|
"epoch": 4.1469740634005765,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00033841733681464837,
|
|
"loss": 4.5886,
|
|
"mean_token_accuracy": 0.26340105980634687,
|
|
"num_tokens": 98997881.0,
|
|
"step": 43170
|
|
},
|
|
{
|
|
"entropy": 5.102772235870361,
|
|
"epoch": 4.14745437079731,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00033838444247915613,
|
|
"loss": 4.5367,
|
|
"mean_token_accuracy": 0.26367844045162203,
|
|
"num_tokens": 99012328.0,
|
|
"step": 43175
|
|
},
|
|
{
|
|
"entropy": 5.175368118286133,
|
|
"epoch": 4.147934678194044,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003383515466720653,
|
|
"loss": 4.6219,
|
|
"mean_token_accuracy": 0.25392477214336395,
|
|
"num_tokens": 99023383.0,
|
|
"step": 43180
|
|
},
|
|
{
|
|
"entropy": 5.153623962402344,
|
|
"epoch": 4.148414985590778,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033831864939413975,
|
|
"loss": 4.5598,
|
|
"mean_token_accuracy": 0.26254572421312333,
|
|
"num_tokens": 99034264.0,
|
|
"step": 43185
|
|
},
|
|
{
|
|
"entropy": 5.0967031955719,
|
|
"epoch": 4.148895292987512,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003382857506461432,
|
|
"loss": 4.5579,
|
|
"mean_token_accuracy": 0.2661526143550873,
|
|
"num_tokens": 99046593.0,
|
|
"step": 43190
|
|
},
|
|
{
|
|
"entropy": 5.0380934715271,
|
|
"epoch": 4.149375600384246,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00033825285042883937,
|
|
"loss": 4.5758,
|
|
"mean_token_accuracy": 0.264330093562603,
|
|
"num_tokens": 99059068.0,
|
|
"step": 43195
|
|
},
|
|
{
|
|
"entropy": 5.216998624801636,
|
|
"epoch": 4.14985590778098,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00033821994874299216,
|
|
"loss": 4.7052,
|
|
"mean_token_accuracy": 0.2505865141749382,
|
|
"num_tokens": 99070547.0,
|
|
"step": 43200
|
|
},
|
|
{
|
|
"entropy": 5.171139812469482,
|
|
"epoch": 4.150336215177714,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003381870455893655,
|
|
"loss": 4.6101,
|
|
"mean_token_accuracy": 0.262862391769886,
|
|
"num_tokens": 99082118.0,
|
|
"step": 43205
|
|
},
|
|
{
|
|
"entropy": 5.071386480331421,
|
|
"epoch": 4.1508165225744476,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00033815414096872326,
|
|
"loss": 4.5172,
|
|
"mean_token_accuracy": 0.25844438225030897,
|
|
"num_tokens": 99093514.0,
|
|
"step": 43210
|
|
},
|
|
{
|
|
"entropy": 5.078430986404419,
|
|
"epoch": 4.151296829971182,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003381212348818294,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.26299189776182175,
|
|
"num_tokens": 99104309.0,
|
|
"step": 43215
|
|
},
|
|
{
|
|
"entropy": 5.066232395172119,
|
|
"epoch": 4.151777137367915,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003380883273294479,
|
|
"loss": 4.5842,
|
|
"mean_token_accuracy": 0.25658503621816636,
|
|
"num_tokens": 99116503.0,
|
|
"step": 43220
|
|
},
|
|
{
|
|
"entropy": 5.156018495559692,
|
|
"epoch": 4.15225744476465,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00033805541831234275,
|
|
"loss": 4.554,
|
|
"mean_token_accuracy": 0.25882008820772173,
|
|
"num_tokens": 99127212.0,
|
|
"step": 43225
|
|
},
|
|
{
|
|
"entropy": 5.134460353851319,
|
|
"epoch": 4.152737752161383,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000338022507831278,
|
|
"loss": 4.5383,
|
|
"mean_token_accuracy": 0.2665118083357811,
|
|
"num_tokens": 99137947.0,
|
|
"step": 43230
|
|
},
|
|
{
|
|
"entropy": 5.155100536346436,
|
|
"epoch": 4.153218059558117,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00033798959588701786,
|
|
"loss": 4.5946,
|
|
"mean_token_accuracy": 0.2553700566291809,
|
|
"num_tokens": 99150084.0,
|
|
"step": 43235
|
|
},
|
|
{
|
|
"entropy": 5.155261754989624,
|
|
"epoch": 4.153698366954851,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003379566824803263,
|
|
"loss": 4.5759,
|
|
"mean_token_accuracy": 0.2619387716054916,
|
|
"num_tokens": 99160126.0,
|
|
"step": 43240
|
|
},
|
|
{
|
|
"entropy": 5.096473026275635,
|
|
"epoch": 4.154178674351585,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003379237676119675,
|
|
"loss": 4.6069,
|
|
"mean_token_accuracy": 0.25492328107357026,
|
|
"num_tokens": 99172349.0,
|
|
"step": 43245
|
|
},
|
|
{
|
|
"entropy": 5.075168561935425,
|
|
"epoch": 4.154658981748319,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003378908512827057,
|
|
"loss": 4.5032,
|
|
"mean_token_accuracy": 0.2670445919036865,
|
|
"num_tokens": 99183826.0,
|
|
"step": 43250
|
|
},
|
|
{
|
|
"entropy": 5.120257377624512,
|
|
"epoch": 4.155139289145053,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00033785793349330495,
|
|
"loss": 4.5455,
|
|
"mean_token_accuracy": 0.2655447646975517,
|
|
"num_tokens": 99195713.0,
|
|
"step": 43255
|
|
},
|
|
{
|
|
"entropy": 5.157724475860595,
|
|
"epoch": 4.155619596541786,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033782501424452975,
|
|
"loss": 4.6338,
|
|
"mean_token_accuracy": 0.2568825393915176,
|
|
"num_tokens": 99206544.0,
|
|
"step": 43260
|
|
},
|
|
{
|
|
"entropy": 5.027705144882202,
|
|
"epoch": 4.156099903938521,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00033779209353714424,
|
|
"loss": 4.4398,
|
|
"mean_token_accuracy": 0.2800274774432182,
|
|
"num_tokens": 99218073.0,
|
|
"step": 43265
|
|
},
|
|
{
|
|
"entropy": 5.078403806686401,
|
|
"epoch": 4.156580211335255,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003377591713719128,
|
|
"loss": 4.5591,
|
|
"mean_token_accuracy": 0.2623721331357956,
|
|
"num_tokens": 99228627.0,
|
|
"step": 43270
|
|
},
|
|
{
|
|
"entropy": 5.135380363464355,
|
|
"epoch": 4.1570605187319885,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003377262477495997,
|
|
"loss": 4.5582,
|
|
"mean_token_accuracy": 0.2691991776227951,
|
|
"num_tokens": 99240863.0,
|
|
"step": 43275
|
|
},
|
|
{
|
|
"entropy": 5.157921409606933,
|
|
"epoch": 4.157540826128723,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003376933226709694,
|
|
"loss": 4.6145,
|
|
"mean_token_accuracy": 0.25570350885391235,
|
|
"num_tokens": 99253255.0,
|
|
"step": 43280
|
|
},
|
|
{
|
|
"entropy": 5.144768381118775,
|
|
"epoch": 4.158021133525456,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033766039613678634,
|
|
"loss": 4.5935,
|
|
"mean_token_accuracy": 0.25904482007026675,
|
|
"num_tokens": 99264850.0,
|
|
"step": 43285
|
|
},
|
|
{
|
|
"entropy": 5.062422800064087,
|
|
"epoch": 4.1585014409221905,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00033762746814781496,
|
|
"loss": 4.4615,
|
|
"mean_token_accuracy": 0.27152850329875944,
|
|
"num_tokens": 99275389.0,
|
|
"step": 43290
|
|
},
|
|
{
|
|
"entropy": 5.080011510848999,
|
|
"epoch": 4.158981748318924,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003375945387048197,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.25895256698131563,
|
|
"num_tokens": 99286265.0,
|
|
"step": 43295
|
|
},
|
|
{
|
|
"entropy": 5.105927324295044,
|
|
"epoch": 4.159462055715658,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003375616078085651,
|
|
"loss": 4.587,
|
|
"mean_token_accuracy": 0.2552463486790657,
|
|
"num_tokens": 99298382.0,
|
|
"step": 43300
|
|
},
|
|
{
|
|
"entropy": 5.154765462875366,
|
|
"epoch": 4.159942363112392,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00033752867545981576,
|
|
"loss": 4.5834,
|
|
"mean_token_accuracy": 0.2613224759697914,
|
|
"num_tokens": 99308706.0,
|
|
"step": 43305
|
|
},
|
|
{
|
|
"entropy": 5.104847621917725,
|
|
"epoch": 4.160422670509126,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00033749574165933626,
|
|
"loss": 4.5238,
|
|
"mean_token_accuracy": 0.2634550079703331,
|
|
"num_tokens": 99318952.0,
|
|
"step": 43310
|
|
},
|
|
{
|
|
"entropy": 5.1071672439575195,
|
|
"epoch": 4.1609029779058595,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003374628064078912,
|
|
"loss": 4.5972,
|
|
"mean_token_accuracy": 0.2568727433681488,
|
|
"num_tokens": 99330857.0,
|
|
"step": 43315
|
|
},
|
|
{
|
|
"entropy": 5.033275747299195,
|
|
"epoch": 4.161383285302594,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00033742986970624526,
|
|
"loss": 4.4181,
|
|
"mean_token_accuracy": 0.27511279881000517,
|
|
"num_tokens": 99341214.0,
|
|
"step": 43320
|
|
},
|
|
{
|
|
"entropy": 5.124514961242676,
|
|
"epoch": 4.161863592699327,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00033739693155516315,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.2593007445335388,
|
|
"num_tokens": 99353312.0,
|
|
"step": 43325
|
|
},
|
|
{
|
|
"entropy": 5.211864709854126,
|
|
"epoch": 4.162343900096062,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033736399195540955,
|
|
"loss": 4.5847,
|
|
"mean_token_accuracy": 0.25920470654964445,
|
|
"num_tokens": 99363965.0,
|
|
"step": 43330
|
|
},
|
|
{
|
|
"entropy": 5.1320349216461185,
|
|
"epoch": 4.162824207492795,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00033733105090774917,
|
|
"loss": 4.541,
|
|
"mean_token_accuracy": 0.2662133827805519,
|
|
"num_tokens": 99375027.0,
|
|
"step": 43335
|
|
},
|
|
{
|
|
"entropy": 5.163074064254761,
|
|
"epoch": 4.163304514889529,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000337298108412947,
|
|
"loss": 4.7067,
|
|
"mean_token_accuracy": 0.2478715181350708,
|
|
"num_tokens": 99385998.0,
|
|
"step": 43340
|
|
},
|
|
{
|
|
"entropy": 5.101756191253662,
|
|
"epoch": 4.163784822286263,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00033726516447176764,
|
|
"loss": 4.4889,
|
|
"mean_token_accuracy": 0.2683610960841179,
|
|
"num_tokens": 99396358.0,
|
|
"step": 43345
|
|
},
|
|
{
|
|
"entropy": 5.164179897308349,
|
|
"epoch": 4.164265129682997,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003372322190849761,
|
|
"loss": 4.6485,
|
|
"mean_token_accuracy": 0.25669586956501006,
|
|
"num_tokens": 99407289.0,
|
|
"step": 43350
|
|
},
|
|
{
|
|
"entropy": 5.138799047470092,
|
|
"epoch": 4.164745437079731,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003371992722533372,
|
|
"loss": 4.6448,
|
|
"mean_token_accuracy": 0.2537570968270302,
|
|
"num_tokens": 99419036.0,
|
|
"step": 43355
|
|
},
|
|
{
|
|
"entropy": 5.16411862373352,
|
|
"epoch": 4.165225744476465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003371663239776159,
|
|
"loss": 4.5341,
|
|
"mean_token_accuracy": 0.25541566461324694,
|
|
"num_tokens": 99429589.0,
|
|
"step": 43360
|
|
},
|
|
{
|
|
"entropy": 5.097842264175415,
|
|
"epoch": 4.165706051873199,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00033713337425857713,
|
|
"loss": 4.5175,
|
|
"mean_token_accuracy": 0.26032368987798693,
|
|
"num_tokens": 99440398.0,
|
|
"step": 43365
|
|
},
|
|
{
|
|
"entropy": 5.1038977146148685,
|
|
"epoch": 4.166186359269933,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000337100423096986,
|
|
"loss": 4.5089,
|
|
"mean_token_accuracy": 0.266445155441761,
|
|
"num_tokens": 99452000.0,
|
|
"step": 43370
|
|
},
|
|
{
|
|
"entropy": 5.159334754943847,
|
|
"epoch": 4.166666666666667,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003370674704936074,
|
|
"loss": 4.576,
|
|
"mean_token_accuracy": 0.25622153133153913,
|
|
"num_tokens": 99462403.0,
|
|
"step": 43375
|
|
},
|
|
{
|
|
"entropy": 5.053716850280762,
|
|
"epoch": 4.1671469740634,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033703451644920637,
|
|
"loss": 4.4738,
|
|
"mean_token_accuracy": 0.27041085064411163,
|
|
"num_tokens": 99474284.0,
|
|
"step": 43380
|
|
},
|
|
{
|
|
"entropy": 5.137935972213745,
|
|
"epoch": 4.167627281460135,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033700156096454816,
|
|
"loss": 4.627,
|
|
"mean_token_accuracy": 0.2584590047597885,
|
|
"num_tokens": 99486189.0,
|
|
"step": 43385
|
|
},
|
|
{
|
|
"entropy": 5.140599060058594,
|
|
"epoch": 4.168107588856868,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033696860404039777,
|
|
"loss": 4.657,
|
|
"mean_token_accuracy": 0.2594139605760574,
|
|
"num_tokens": 99498047.0,
|
|
"step": 43390
|
|
},
|
|
{
|
|
"entropy": 5.064700365066528,
|
|
"epoch": 4.1685878962536025,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00033693564567752036,
|
|
"loss": 4.5209,
|
|
"mean_token_accuracy": 0.26062560826539993,
|
|
"num_tokens": 99509523.0,
|
|
"step": 43395
|
|
},
|
|
{
|
|
"entropy": 5.115128421783448,
|
|
"epoch": 4.169068203650336,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003369026858766813,
|
|
"loss": 4.4919,
|
|
"mean_token_accuracy": 0.2630627855658531,
|
|
"num_tokens": 99521357.0,
|
|
"step": 43400
|
|
},
|
|
{
|
|
"entropy": 5.119316577911377,
|
|
"epoch": 4.16954851104707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00033686972463864553,
|
|
"loss": 4.607,
|
|
"mean_token_accuracy": 0.2578336462378502,
|
|
"num_tokens": 99532484.0,
|
|
"step": 43405
|
|
},
|
|
{
|
|
"entropy": 5.1856677532196045,
|
|
"epoch": 4.170028818443804,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003368367619641785,
|
|
"loss": 4.5691,
|
|
"mean_token_accuracy": 0.2660838574171066,
|
|
"num_tokens": 99543082.0,
|
|
"step": 43410
|
|
},
|
|
{
|
|
"entropy": 5.113144302368164,
|
|
"epoch": 4.170509125840538,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003368037978540455,
|
|
"loss": 4.619,
|
|
"mean_token_accuracy": 0.2533662900328636,
|
|
"num_tokens": 99555380.0,
|
|
"step": 43415
|
|
},
|
|
{
|
|
"entropy": 5.132107543945312,
|
|
"epoch": 4.1709894332372714,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003367708323090119,
|
|
"loss": 4.6335,
|
|
"mean_token_accuracy": 0.26031582802534103,
|
|
"num_tokens": 99566394.0,
|
|
"step": 43420
|
|
},
|
|
{
|
|
"entropy": 5.139598798751831,
|
|
"epoch": 4.171469740634006,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000336737865329843,
|
|
"loss": 4.577,
|
|
"mean_token_accuracy": 0.2574335321784019,
|
|
"num_tokens": 99579156.0,
|
|
"step": 43425
|
|
},
|
|
{
|
|
"entropy": 5.132538795471191,
|
|
"epoch": 4.17195004803074,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00033670489691730405,
|
|
"loss": 4.5909,
|
|
"mean_token_accuracy": 0.26213984191417694,
|
|
"num_tokens": 99589899.0,
|
|
"step": 43430
|
|
},
|
|
{
|
|
"entropy": 5.155674743652344,
|
|
"epoch": 4.1724303554274735,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003366719270721607,
|
|
"loss": 4.6311,
|
|
"mean_token_accuracy": 0.2571592301130295,
|
|
"num_tokens": 99602337.0,
|
|
"step": 43435
|
|
},
|
|
{
|
|
"entropy": 5.192333030700683,
|
|
"epoch": 4.172910662824208,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00033663895579517835,
|
|
"loss": 4.6726,
|
|
"mean_token_accuracy": 0.2515497997403145,
|
|
"num_tokens": 99613375.0,
|
|
"step": 43440
|
|
},
|
|
{
|
|
"entropy": 5.096249008178711,
|
|
"epoch": 4.173390970220941,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00033660598308712247,
|
|
"loss": 4.5059,
|
|
"mean_token_accuracy": 0.2739394217729568,
|
|
"num_tokens": 99624156.0,
|
|
"step": 43445
|
|
},
|
|
{
|
|
"entropy": 5.038822412490845,
|
|
"epoch": 4.173871277617676,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00033657300894875857,
|
|
"loss": 4.4835,
|
|
"mean_token_accuracy": 0.2656427130103111,
|
|
"num_tokens": 99635360.0,
|
|
"step": 43450
|
|
},
|
|
{
|
|
"entropy": 5.141566467285156,
|
|
"epoch": 4.174351585014409,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00033654003338085225,
|
|
"loss": 4.5145,
|
|
"mean_token_accuracy": 0.2704131081700325,
|
|
"num_tokens": 99646479.0,
|
|
"step": 43455
|
|
},
|
|
{
|
|
"entropy": 5.110743808746338,
|
|
"epoch": 4.174831892411143,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033650705638416914,
|
|
"loss": 4.5457,
|
|
"mean_token_accuracy": 0.26254172027111056,
|
|
"num_tokens": 99656688.0,
|
|
"step": 43460
|
|
},
|
|
{
|
|
"entropy": 5.082004499435425,
|
|
"epoch": 4.175312199807877,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003364740779594747,
|
|
"loss": 4.5414,
|
|
"mean_token_accuracy": 0.26403298079967497,
|
|
"num_tokens": 99667859.0,
|
|
"step": 43465
|
|
},
|
|
{
|
|
"entropy": 5.116665363311768,
|
|
"epoch": 4.175792507204611,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00033644109810753483,
|
|
"loss": 4.5693,
|
|
"mean_token_accuracy": 0.25877859741449355,
|
|
"num_tokens": 99679012.0,
|
|
"step": 43470
|
|
},
|
|
{
|
|
"entropy": 5.099866819381714,
|
|
"epoch": 4.176272814601345,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000336408116829115,
|
|
"loss": 4.5418,
|
|
"mean_token_accuracy": 0.261824956536293,
|
|
"num_tokens": 99689734.0,
|
|
"step": 43475
|
|
},
|
|
{
|
|
"entropy": 5.0726766109466555,
|
|
"epoch": 4.176753121998079,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033637513412498117,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.26644298881292344,
|
|
"num_tokens": 99700445.0,
|
|
"step": 43480
|
|
},
|
|
{
|
|
"entropy": 5.120791578292847,
|
|
"epoch": 4.177233429394812,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003363421499958989,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.2589690774679184,
|
|
"num_tokens": 99711317.0,
|
|
"step": 43485
|
|
},
|
|
{
|
|
"entropy": 5.0688529968261715,
|
|
"epoch": 4.177713736791547,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033630916444263407,
|
|
"loss": 4.4988,
|
|
"mean_token_accuracy": 0.2654005795717239,
|
|
"num_tokens": 99722355.0,
|
|
"step": 43490
|
|
},
|
|
{
|
|
"entropy": 5.154725360870361,
|
|
"epoch": 4.17819404418828,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003362761774659525,
|
|
"loss": 4.5788,
|
|
"mean_token_accuracy": 0.2601359307765961,
|
|
"num_tokens": 99733010.0,
|
|
"step": 43495
|
|
},
|
|
{
|
|
"entropy": 5.190041399002075,
|
|
"epoch": 4.178674351585014,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00033624318906662,
|
|
"loss": 4.6177,
|
|
"mean_token_accuracy": 0.2549016401171684,
|
|
"num_tokens": 99744724.0,
|
|
"step": 43500
|
|
},
|
|
{
|
|
"entropy": 5.208281564712524,
|
|
"epoch": 4.179154658981748,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033621019924540255,
|
|
"loss": 4.6535,
|
|
"mean_token_accuracy": 0.24872801154851915,
|
|
"num_tokens": 99756772.0,
|
|
"step": 43505
|
|
},
|
|
{
|
|
"entropy": 5.164304924011231,
|
|
"epoch": 4.179634966378482,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000336177208003066,
|
|
"loss": 4.6455,
|
|
"mean_token_accuracy": 0.2531985878944397,
|
|
"num_tokens": 99768398.0,
|
|
"step": 43510
|
|
},
|
|
{
|
|
"entropy": 5.206340074539185,
|
|
"epoch": 4.1801152737752165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003361442153403763,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.25086362659931183,
|
|
"num_tokens": 99780110.0,
|
|
"step": 43515
|
|
},
|
|
{
|
|
"entropy": 5.1162535667419435,
|
|
"epoch": 4.18059558117195,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003361112212580995,
|
|
"loss": 4.5278,
|
|
"mean_token_accuracy": 0.2628335550427437,
|
|
"num_tokens": 99791329.0,
|
|
"step": 43520
|
|
},
|
|
{
|
|
"entropy": 5.145435619354248,
|
|
"epoch": 4.181075888568684,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003360782257570017,
|
|
"loss": 4.6369,
|
|
"mean_token_accuracy": 0.25034712105989454,
|
|
"num_tokens": 99802890.0,
|
|
"step": 43525
|
|
},
|
|
{
|
|
"entropy": 5.1490302085876465,
|
|
"epoch": 4.181556195965418,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003360452288378488,
|
|
"loss": 4.5325,
|
|
"mean_token_accuracy": 0.2618770316243172,
|
|
"num_tokens": 99814076.0,
|
|
"step": 43530
|
|
},
|
|
{
|
|
"entropy": 5.107022380828857,
|
|
"epoch": 4.182036503362152,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00033601223050140687,
|
|
"loss": 4.5579,
|
|
"mean_token_accuracy": 0.2617477625608444,
|
|
"num_tokens": 99825894.0,
|
|
"step": 43535
|
|
},
|
|
{
|
|
"entropy": 5.136961126327515,
|
|
"epoch": 4.1825168107588855,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003359792307484423,
|
|
"loss": 4.5587,
|
|
"mean_token_accuracy": 0.26598081588745115,
|
|
"num_tokens": 99837217.0,
|
|
"step": 43540
|
|
},
|
|
{
|
|
"entropy": 5.251386594772339,
|
|
"epoch": 4.18299711815562,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00033594622957972096,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.2517025277018547,
|
|
"num_tokens": 99848728.0,
|
|
"step": 43545
|
|
},
|
|
{
|
|
"entropy": 5.074080276489258,
|
|
"epoch": 4.183477425552353,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003359132269960091,
|
|
"loss": 4.5359,
|
|
"mean_token_accuracy": 0.2715119391679764,
|
|
"num_tokens": 99860116.0,
|
|
"step": 43550
|
|
},
|
|
{
|
|
"entropy": 5.170003509521484,
|
|
"epoch": 4.183957732949088,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000335880222998073,
|
|
"loss": 4.5335,
|
|
"mean_token_accuracy": 0.26571066826581957,
|
|
"num_tokens": 99870720.0,
|
|
"step": 43555
|
|
},
|
|
{
|
|
"entropy": 5.09278416633606,
|
|
"epoch": 4.184438040345821,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003358472175866789,
|
|
"loss": 4.5323,
|
|
"mean_token_accuracy": 0.2637945994734764,
|
|
"num_tokens": 99881882.0,
|
|
"step": 43560
|
|
},
|
|
{
|
|
"entropy": 5.220172309875489,
|
|
"epoch": 4.184918347742555,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003358142107625931,
|
|
"loss": 4.6397,
|
|
"mean_token_accuracy": 0.25092630088329315,
|
|
"num_tokens": 99892845.0,
|
|
"step": 43565
|
|
},
|
|
{
|
|
"entropy": 5.088028860092163,
|
|
"epoch": 4.185398655139289,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003357812025265819,
|
|
"loss": 4.5515,
|
|
"mean_token_accuracy": 0.26175086498260497,
|
|
"num_tokens": 99905024.0,
|
|
"step": 43570
|
|
},
|
|
{
|
|
"entropy": 5.137296056747436,
|
|
"epoch": 4.185878962536023,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00033574819287941174,
|
|
"loss": 4.5961,
|
|
"mean_token_accuracy": 0.25966359227895736,
|
|
"num_tokens": 99917899.0,
|
|
"step": 43575
|
|
},
|
|
{
|
|
"entropy": 5.119995832443237,
|
|
"epoch": 4.1863592699327565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00033571518182184886,
|
|
"loss": 4.5881,
|
|
"mean_token_accuracy": 0.2528459429740906,
|
|
"num_tokens": 99929245.0,
|
|
"step": 43580
|
|
},
|
|
{
|
|
"entropy": 5.190898990631103,
|
|
"epoch": 4.186839577329491,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033568216935465976,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.2580281838774681,
|
|
"num_tokens": 99940806.0,
|
|
"step": 43585
|
|
},
|
|
{
|
|
"entropy": 5.133806467056274,
|
|
"epoch": 4.187319884726225,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003356491554786109,
|
|
"loss": 4.5671,
|
|
"mean_token_accuracy": 0.26301381587982176,
|
|
"num_tokens": 99953369.0,
|
|
"step": 43590
|
|
},
|
|
{
|
|
"entropy": 5.124722957611084,
|
|
"epoch": 4.187800192122959,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00033561614019446867,
|
|
"loss": 4.5871,
|
|
"mean_token_accuracy": 0.25753271132707595,
|
|
"num_tokens": 99964563.0,
|
|
"step": 43595
|
|
},
|
|
{
|
|
"entropy": 5.169952154159546,
|
|
"epoch": 4.188280499519693,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033558312350299963,
|
|
"loss": 4.6435,
|
|
"mean_token_accuracy": 0.2569850027561188,
|
|
"num_tokens": 99975143.0,
|
|
"step": 43600
|
|
},
|
|
{
|
|
"entropy": 5.260245990753174,
|
|
"epoch": 4.188760806916426,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00033555010540497045,
|
|
"loss": 4.6613,
|
|
"mean_token_accuracy": 0.252106773853302,
|
|
"num_tokens": 99987430.0,
|
|
"step": 43605
|
|
},
|
|
{
|
|
"entropy": 5.0705810546875,
|
|
"epoch": 4.189241114313161,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003355170859011476,
|
|
"loss": 4.4993,
|
|
"mean_token_accuracy": 0.27606816589832306,
|
|
"num_tokens": 99998638.0,
|
|
"step": 43610
|
|
},
|
|
{
|
|
"entropy": 5.147929525375366,
|
|
"epoch": 4.189721421709894,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003354840649922977,
|
|
"loss": 4.6395,
|
|
"mean_token_accuracy": 0.2548928946256638,
|
|
"num_tokens": 100011054.0,
|
|
"step": 43615
|
|
},
|
|
{
|
|
"entropy": 5.258962202072143,
|
|
"epoch": 4.1902017291066285,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003354510426791874,
|
|
"loss": 4.7184,
|
|
"mean_token_accuracy": 0.25347796976566317,
|
|
"num_tokens": 100022695.0,
|
|
"step": 43620
|
|
},
|
|
{
|
|
"entropy": 5.156949043273926,
|
|
"epoch": 4.190682036503362,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00033541801896258344,
|
|
"loss": 4.6019,
|
|
"mean_token_accuracy": 0.256259360909462,
|
|
"num_tokens": 100034402.0,
|
|
"step": 43625
|
|
},
|
|
{
|
|
"entropy": 5.206487607955933,
|
|
"epoch": 4.191162343900096,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003353849938432524,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.25304743051528933,
|
|
"num_tokens": 100046429.0,
|
|
"step": 43630
|
|
},
|
|
{
|
|
"entropy": 5.087773323059082,
|
|
"epoch": 4.19164265129683,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003353519673219612,
|
|
"loss": 4.5296,
|
|
"mean_token_accuracy": 0.2627839848399162,
|
|
"num_tokens": 100057019.0,
|
|
"step": 43635
|
|
},
|
|
{
|
|
"entropy": 5.167032051086426,
|
|
"epoch": 4.192122958693564,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003353189393994765,
|
|
"loss": 4.6791,
|
|
"mean_token_accuracy": 0.2576664909720421,
|
|
"num_tokens": 100069763.0,
|
|
"step": 43640
|
|
},
|
|
{
|
|
"entropy": 5.073987531661987,
|
|
"epoch": 4.192603266090297,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00033528591007656516,
|
|
"loss": 4.5086,
|
|
"mean_token_accuracy": 0.2646015554666519,
|
|
"num_tokens": 100082838.0,
|
|
"step": 43645
|
|
},
|
|
{
|
|
"entropy": 5.137806367874146,
|
|
"epoch": 4.193083573487032,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003352528793539939,
|
|
"loss": 4.6057,
|
|
"mean_token_accuracy": 0.25954934656620027,
|
|
"num_tokens": 100095422.0,
|
|
"step": 43650
|
|
},
|
|
{
|
|
"entropy": 5.136856412887573,
|
|
"epoch": 4.193563880883765,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00033521984723252973,
|
|
"loss": 4.555,
|
|
"mean_token_accuracy": 0.2655303955078125,
|
|
"num_tokens": 100107000.0,
|
|
"step": 43655
|
|
},
|
|
{
|
|
"entropy": 5.17200288772583,
|
|
"epoch": 4.1940441882804995,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00033518681371293965,
|
|
"loss": 4.6075,
|
|
"mean_token_accuracy": 0.25843123346567154,
|
|
"num_tokens": 100121086.0,
|
|
"step": 43660
|
|
},
|
|
{
|
|
"entropy": 5.050345325469971,
|
|
"epoch": 4.194524495677234,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033515377879599035,
|
|
"loss": 4.4821,
|
|
"mean_token_accuracy": 0.26532799005508423,
|
|
"num_tokens": 100131476.0,
|
|
"step": 43665
|
|
},
|
|
{
|
|
"entropy": 5.134591388702392,
|
|
"epoch": 4.195004803073967,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00033512074248244895,
|
|
"loss": 4.552,
|
|
"mean_token_accuracy": 0.2613441750407219,
|
|
"num_tokens": 100142461.0,
|
|
"step": 43670
|
|
},
|
|
{
|
|
"entropy": 5.051993560791016,
|
|
"epoch": 4.195485110470702,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003350877047730825,
|
|
"loss": 4.4786,
|
|
"mean_token_accuracy": 0.2667852893471718,
|
|
"num_tokens": 100154317.0,
|
|
"step": 43675
|
|
},
|
|
{
|
|
"entropy": 5.131564092636109,
|
|
"epoch": 4.195965417867435,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00033505466566865783,
|
|
"loss": 4.5285,
|
|
"mean_token_accuracy": 0.2667025849223137,
|
|
"num_tokens": 100165197.0,
|
|
"step": 43680
|
|
},
|
|
{
|
|
"entropy": 5.074692821502685,
|
|
"epoch": 4.196445725264169,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003350216251699422,
|
|
"loss": 4.5573,
|
|
"mean_token_accuracy": 0.26150207966566086,
|
|
"num_tokens": 100176745.0,
|
|
"step": 43685
|
|
},
|
|
{
|
|
"entropy": 5.050025367736817,
|
|
"epoch": 4.196926032660903,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00033498858327770276,
|
|
"loss": 4.5365,
|
|
"mean_token_accuracy": 0.2654877841472626,
|
|
"num_tokens": 100188202.0,
|
|
"step": 43690
|
|
},
|
|
{
|
|
"entropy": 5.158103561401367,
|
|
"epoch": 4.197406340057637,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00033495553999270643,
|
|
"loss": 4.6191,
|
|
"mean_token_accuracy": 0.2611777827143669,
|
|
"num_tokens": 100199044.0,
|
|
"step": 43695
|
|
},
|
|
{
|
|
"entropy": 5.104278707504273,
|
|
"epoch": 4.197886647454371,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00033492249531572054,
|
|
"loss": 4.5388,
|
|
"mean_token_accuracy": 0.26676966398954394,
|
|
"num_tokens": 100210272.0,
|
|
"step": 43700
|
|
},
|
|
{
|
|
"entropy": 5.029407405853272,
|
|
"epoch": 4.198366954851105,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003348894492475123,
|
|
"loss": 4.4884,
|
|
"mean_token_accuracy": 0.26892287880182264,
|
|
"num_tokens": 100220737.0,
|
|
"step": 43705
|
|
},
|
|
{
|
|
"entropy": 5.226188802719117,
|
|
"epoch": 4.198847262247838,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003348564017888488,
|
|
"loss": 4.6829,
|
|
"mean_token_accuracy": 0.25510213524103165,
|
|
"num_tokens": 100232330.0,
|
|
"step": 43710
|
|
},
|
|
{
|
|
"entropy": 5.1427490234375,
|
|
"epoch": 4.199327569644573,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00033482335294049735,
|
|
"loss": 4.5147,
|
|
"mean_token_accuracy": 0.2727921888232231,
|
|
"num_tokens": 100243092.0,
|
|
"step": 43715
|
|
},
|
|
{
|
|
"entropy": 5.176213073730469,
|
|
"epoch": 4.199807877041306,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003347903027032254,
|
|
"loss": 4.6592,
|
|
"mean_token_accuracy": 0.25258990824222566,
|
|
"num_tokens": 100254820.0,
|
|
"step": 43720
|
|
},
|
|
{
|
|
"entropy": 5.198156690597534,
|
|
"epoch": 4.20028818443804,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003347572510778001,
|
|
"loss": 4.6482,
|
|
"mean_token_accuracy": 0.25638597458601,
|
|
"num_tokens": 100267272.0,
|
|
"step": 43725
|
|
},
|
|
{
|
|
"entropy": 5.100559329986572,
|
|
"epoch": 4.200768491834774,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003347241980649889,
|
|
"loss": 4.5257,
|
|
"mean_token_accuracy": 0.27086175680160524,
|
|
"num_tokens": 100279813.0,
|
|
"step": 43730
|
|
},
|
|
{
|
|
"entropy": 5.0936016082763675,
|
|
"epoch": 4.201248799231508,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00033469114366555913,
|
|
"loss": 4.5717,
|
|
"mean_token_accuracy": 0.2563642367720604,
|
|
"num_tokens": 100292062.0,
|
|
"step": 43735
|
|
},
|
|
{
|
|
"entropy": 5.144769096374512,
|
|
"epoch": 4.2017291066282425,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00033465808788027824,
|
|
"loss": 4.6035,
|
|
"mean_token_accuracy": 0.2624837949872017,
|
|
"num_tokens": 100303595.0,
|
|
"step": 43740
|
|
},
|
|
{
|
|
"entropy": 5.067610502243042,
|
|
"epoch": 4.202209414024976,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00033462503070991374,
|
|
"loss": 4.531,
|
|
"mean_token_accuracy": 0.26710898280143736,
|
|
"num_tokens": 100315496.0,
|
|
"step": 43745
|
|
},
|
|
{
|
|
"entropy": 5.0852948188781735,
|
|
"epoch": 4.20268972142171,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003345919721552331,
|
|
"loss": 4.5219,
|
|
"mean_token_accuracy": 0.2640274927020073,
|
|
"num_tokens": 100326999.0,
|
|
"step": 43750
|
|
},
|
|
{
|
|
"entropy": 5.107030820846558,
|
|
"epoch": 4.203170028818444,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00033455891221700375,
|
|
"loss": 4.5693,
|
|
"mean_token_accuracy": 0.26914894580841064,
|
|
"num_tokens": 100339168.0,
|
|
"step": 43755
|
|
},
|
|
{
|
|
"entropy": 5.159598302841187,
|
|
"epoch": 4.203650336215178,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003345258508959933,
|
|
"loss": 4.523,
|
|
"mean_token_accuracy": 0.2620000928640366,
|
|
"num_tokens": 100350522.0,
|
|
"step": 43760
|
|
},
|
|
{
|
|
"entropy": 5.06691312789917,
|
|
"epoch": 4.2041306436119115,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003344927881929695,
|
|
"loss": 4.5146,
|
|
"mean_token_accuracy": 0.26211913079023363,
|
|
"num_tokens": 100361852.0,
|
|
"step": 43765
|
|
},
|
|
{
|
|
"entropy": 5.1268205642700195,
|
|
"epoch": 4.204610951008646,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00033445972410869955,
|
|
"loss": 4.6207,
|
|
"mean_token_accuracy": 0.25598797351121905,
|
|
"num_tokens": 100372276.0,
|
|
"step": 43770
|
|
},
|
|
{
|
|
"entropy": 5.079210996627808,
|
|
"epoch": 4.205091258405379,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003344266586439516,
|
|
"loss": 4.5358,
|
|
"mean_token_accuracy": 0.2638391569256783,
|
|
"num_tokens": 100383363.0,
|
|
"step": 43775
|
|
},
|
|
{
|
|
"entropy": 5.184072780609131,
|
|
"epoch": 4.2055715658021136,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00033439359179949303,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.2580594375729561,
|
|
"num_tokens": 100395912.0,
|
|
"step": 43780
|
|
},
|
|
{
|
|
"entropy": 5.102089309692383,
|
|
"epoch": 4.206051873198847,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00033436052357609157,
|
|
"loss": 4.5205,
|
|
"mean_token_accuracy": 0.2613869771361351,
|
|
"num_tokens": 100405798.0,
|
|
"step": 43785
|
|
},
|
|
{
|
|
"entropy": 5.103561115264893,
|
|
"epoch": 4.206532180595581,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003343274539745151,
|
|
"loss": 4.5533,
|
|
"mean_token_accuracy": 0.2675723686814308,
|
|
"num_tokens": 100416457.0,
|
|
"step": 43790
|
|
},
|
|
{
|
|
"entropy": 5.096428251266479,
|
|
"epoch": 4.207012487992315,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003342943829955313,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.25041820406913756,
|
|
"num_tokens": 100427799.0,
|
|
"step": 43795
|
|
},
|
|
{
|
|
"entropy": 5.098986196517944,
|
|
"epoch": 4.207492795389049,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00033426131063990787,
|
|
"loss": 4.555,
|
|
"mean_token_accuracy": 0.2606707066297531,
|
|
"num_tokens": 100439035.0,
|
|
"step": 43800
|
|
},
|
|
{
|
|
"entropy": 5.092434310913086,
|
|
"epoch": 4.2079731027857825,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00033422823690841286,
|
|
"loss": 4.5355,
|
|
"mean_token_accuracy": 0.2659346967935562,
|
|
"num_tokens": 100450490.0,
|
|
"step": 43805
|
|
},
|
|
{
|
|
"entropy": 5.080999088287354,
|
|
"epoch": 4.208453410182517,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003341951618018141,
|
|
"loss": 4.5305,
|
|
"mean_token_accuracy": 0.26320123076438906,
|
|
"num_tokens": 100461426.0,
|
|
"step": 43810
|
|
},
|
|
{
|
|
"entropy": 5.164848327636719,
|
|
"epoch": 4.208933717579251,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00033416208532087937,
|
|
"loss": 4.5949,
|
|
"mean_token_accuracy": 0.2581640124320984,
|
|
"num_tokens": 100473051.0,
|
|
"step": 43815
|
|
},
|
|
{
|
|
"entropy": 5.072110748291015,
|
|
"epoch": 4.209414024975985,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003341290074663768,
|
|
"loss": 4.5416,
|
|
"mean_token_accuracy": 0.267560775578022,
|
|
"num_tokens": 100484269.0,
|
|
"step": 43820
|
|
},
|
|
{
|
|
"entropy": 5.114563894271851,
|
|
"epoch": 4.209894332372719,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003340959282390742,
|
|
"loss": 4.6018,
|
|
"mean_token_accuracy": 0.2560203969478607,
|
|
"num_tokens": 100495928.0,
|
|
"step": 43825
|
|
},
|
|
{
|
|
"entropy": 5.130320501327515,
|
|
"epoch": 4.210374639769452,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00033406284763973964,
|
|
"loss": 4.5354,
|
|
"mean_token_accuracy": 0.26758991181850433,
|
|
"num_tokens": 100507132.0,
|
|
"step": 43830
|
|
},
|
|
{
|
|
"entropy": 5.174654817581176,
|
|
"epoch": 4.210854947166187,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003340297656691411,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.2623978093266487,
|
|
"num_tokens": 100518414.0,
|
|
"step": 43835
|
|
},
|
|
{
|
|
"entropy": 5.1245753288269045,
|
|
"epoch": 4.21133525456292,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003339966823280467,
|
|
"loss": 4.5433,
|
|
"mean_token_accuracy": 0.26819336116313935,
|
|
"num_tokens": 100528809.0,
|
|
"step": 43840
|
|
},
|
|
{
|
|
"entropy": 5.153884172439575,
|
|
"epoch": 4.2118155619596545,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033396359761722453,
|
|
"loss": 4.5874,
|
|
"mean_token_accuracy": 0.2537555664777756,
|
|
"num_tokens": 100539224.0,
|
|
"step": 43845
|
|
},
|
|
{
|
|
"entropy": 5.188582420349121,
|
|
"epoch": 4.212295869356388,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00033393051153744274,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.2544417679309845,
|
|
"num_tokens": 100550984.0,
|
|
"step": 43850
|
|
},
|
|
{
|
|
"entropy": 5.204317331314087,
|
|
"epoch": 4.212776176753122,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00033389742408946937,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.2549692511558533,
|
|
"num_tokens": 100562786.0,
|
|
"step": 43855
|
|
},
|
|
{
|
|
"entropy": 5.130901718139649,
|
|
"epoch": 4.213256484149856,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003338643352740728,
|
|
"loss": 4.527,
|
|
"mean_token_accuracy": 0.26279019713401797,
|
|
"num_tokens": 100573966.0,
|
|
"step": 43860
|
|
},
|
|
{
|
|
"entropy": 5.193920421600342,
|
|
"epoch": 4.21373679154659,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003338312450920211,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.25082436949014664,
|
|
"num_tokens": 100586451.0,
|
|
"step": 43865
|
|
},
|
|
{
|
|
"entropy": 5.210236692428589,
|
|
"epoch": 4.214217098943323,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003337981535440826,
|
|
"loss": 4.6815,
|
|
"mean_token_accuracy": 0.25154101103544235,
|
|
"num_tokens": 100597820.0,
|
|
"step": 43870
|
|
},
|
|
{
|
|
"entropy": 5.149127435684204,
|
|
"epoch": 4.214697406340058,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00033376506063102556,
|
|
"loss": 4.644,
|
|
"mean_token_accuracy": 0.25301697850227356,
|
|
"num_tokens": 100611423.0,
|
|
"step": 43875
|
|
},
|
|
{
|
|
"entropy": 5.178092765808105,
|
|
"epoch": 4.215177713736791,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003337319663536183,
|
|
"loss": 4.6712,
|
|
"mean_token_accuracy": 0.2540985032916069,
|
|
"num_tokens": 100623220.0,
|
|
"step": 43880
|
|
},
|
|
{
|
|
"entropy": 5.1439351558685305,
|
|
"epoch": 4.2156580211335255,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003336988707126293,
|
|
"loss": 4.5603,
|
|
"mean_token_accuracy": 0.2652034118771553,
|
|
"num_tokens": 100634317.0,
|
|
"step": 43885
|
|
},
|
|
{
|
|
"entropy": 5.217324924468994,
|
|
"epoch": 4.216138328530259,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003336657737088267,
|
|
"loss": 4.6517,
|
|
"mean_token_accuracy": 0.25750004351139066,
|
|
"num_tokens": 100645743.0,
|
|
"step": 43890
|
|
},
|
|
{
|
|
"entropy": 5.123615503311157,
|
|
"epoch": 4.216618635926993,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00033363267534297896,
|
|
"loss": 4.631,
|
|
"mean_token_accuracy": 0.2627718672156334,
|
|
"num_tokens": 100658240.0,
|
|
"step": 43895
|
|
},
|
|
{
|
|
"entropy": 5.164013338088989,
|
|
"epoch": 4.217098943323728,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003335995756158548,
|
|
"loss": 4.6309,
|
|
"mean_token_accuracy": 0.26262784004211426,
|
|
"num_tokens": 100669096.0,
|
|
"step": 43900
|
|
},
|
|
{
|
|
"entropy": 5.114154195785522,
|
|
"epoch": 4.217579250720461,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00033356647452822236,
|
|
"loss": 4.5161,
|
|
"mean_token_accuracy": 0.266518147289753,
|
|
"num_tokens": 100682389.0,
|
|
"step": 43905
|
|
},
|
|
{
|
|
"entropy": 5.1481414318084715,
|
|
"epoch": 4.218059558117195,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00033353337208085035,
|
|
"loss": 4.5477,
|
|
"mean_token_accuracy": 0.2632542595267296,
|
|
"num_tokens": 100693896.0,
|
|
"step": 43910
|
|
},
|
|
{
|
|
"entropy": 5.1328905582427975,
|
|
"epoch": 4.218539865513929,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003335002682745072,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.25830995440483095,
|
|
"num_tokens": 100704997.0,
|
|
"step": 43915
|
|
},
|
|
{
|
|
"entropy": 5.120449066162109,
|
|
"epoch": 4.219020172910663,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003334671631099615,
|
|
"loss": 4.585,
|
|
"mean_token_accuracy": 0.2581783875823021,
|
|
"num_tokens": 100716340.0,
|
|
"step": 43920
|
|
},
|
|
{
|
|
"entropy": 5.120770978927612,
|
|
"epoch": 4.2195004803073966,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000333434056587982,
|
|
"loss": 4.5718,
|
|
"mean_token_accuracy": 0.2604472771286964,
|
|
"num_tokens": 100727897.0,
|
|
"step": 43925
|
|
},
|
|
{
|
|
"entropy": 5.171991539001465,
|
|
"epoch": 4.219980787704131,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00033340094870933714,
|
|
"loss": 4.6036,
|
|
"mean_token_accuracy": 0.2616860643029213,
|
|
"num_tokens": 100738848.0,
|
|
"step": 43930
|
|
},
|
|
{
|
|
"entropy": 5.106797122955323,
|
|
"epoch": 4.220461095100864,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00033336783947479566,
|
|
"loss": 4.5633,
|
|
"mean_token_accuracy": 0.2713521867990494,
|
|
"num_tokens": 100750029.0,
|
|
"step": 43935
|
|
},
|
|
{
|
|
"entropy": 5.145637893676758,
|
|
"epoch": 4.220941402497599,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00033333472888512626,
|
|
"loss": 4.6205,
|
|
"mean_token_accuracy": 0.25325959026813505,
|
|
"num_tokens": 100762037.0,
|
|
"step": 43940
|
|
},
|
|
{
|
|
"entropy": 5.26365180015564,
|
|
"epoch": 4.221421709894332,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003333016169410978,
|
|
"loss": 4.7064,
|
|
"mean_token_accuracy": 0.2529000237584114,
|
|
"num_tokens": 100774269.0,
|
|
"step": 43945
|
|
},
|
|
{
|
|
"entropy": 5.130728387832642,
|
|
"epoch": 4.221902017291066,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00033326850364347876,
|
|
"loss": 4.5588,
|
|
"mean_token_accuracy": 0.26223920583724974,
|
|
"num_tokens": 100785940.0,
|
|
"step": 43950
|
|
},
|
|
{
|
|
"entropy": 5.100719165802002,
|
|
"epoch": 4.2223823246878,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003332353889930381,
|
|
"loss": 4.5951,
|
|
"mean_token_accuracy": 0.25863992273807523,
|
|
"num_tokens": 100797281.0,
|
|
"step": 43955
|
|
},
|
|
{
|
|
"entropy": 5.1036780834197994,
|
|
"epoch": 4.222862632084534,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003332022729905448,
|
|
"loss": 4.6372,
|
|
"mean_token_accuracy": 0.2618627890944481,
|
|
"num_tokens": 100807585.0,
|
|
"step": 43960
|
|
},
|
|
{
|
|
"entropy": 5.097433233261109,
|
|
"epoch": 4.223342939481268,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003331691556367674,
|
|
"loss": 4.5186,
|
|
"mean_token_accuracy": 0.26853505820035933,
|
|
"num_tokens": 100818235.0,
|
|
"step": 43965
|
|
},
|
|
{
|
|
"entropy": 5.145977735519409,
|
|
"epoch": 4.223823246878002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003331360369324749,
|
|
"loss": 4.5943,
|
|
"mean_token_accuracy": 0.2596130296587944,
|
|
"num_tokens": 100829844.0,
|
|
"step": 43970
|
|
},
|
|
{
|
|
"entropy": 5.0564440250396725,
|
|
"epoch": 4.224303554274736,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003331029168784363,
|
|
"loss": 4.5279,
|
|
"mean_token_accuracy": 0.26842936128377914,
|
|
"num_tokens": 100841983.0,
|
|
"step": 43975
|
|
},
|
|
{
|
|
"entropy": 5.176312589645386,
|
|
"epoch": 4.22478386167147,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00033306979547542047,
|
|
"loss": 4.5915,
|
|
"mean_token_accuracy": 0.25751717686653136,
|
|
"num_tokens": 100853683.0,
|
|
"step": 43980
|
|
},
|
|
{
|
|
"entropy": 5.1147442817687985,
|
|
"epoch": 4.225264169068204,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003330366727241965,
|
|
"loss": 4.5326,
|
|
"mean_token_accuracy": 0.2577591747045517,
|
|
"num_tokens": 100865583.0,
|
|
"step": 43985
|
|
},
|
|
{
|
|
"entropy": 5.178786373138427,
|
|
"epoch": 4.2257444764649374,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003330035486255333,
|
|
"loss": 4.6282,
|
|
"mean_token_accuracy": 0.2619468688964844,
|
|
"num_tokens": 100876486.0,
|
|
"step": 43990
|
|
},
|
|
{
|
|
"entropy": 5.112397289276123,
|
|
"epoch": 4.226224783861672,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00033297042318019995,
|
|
"loss": 4.4852,
|
|
"mean_token_accuracy": 0.25942614674568176,
|
|
"num_tokens": 100887630.0,
|
|
"step": 43995
|
|
},
|
|
{
|
|
"entropy": 5.1102439880371096,
|
|
"epoch": 4.226705091258405,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003329372963889654,
|
|
"loss": 4.5686,
|
|
"mean_token_accuracy": 0.2627726525068283,
|
|
"num_tokens": 100899666.0,
|
|
"step": 44000
|
|
},
|
|
{
|
|
"entropy": 5.0690450191497805,
|
|
"epoch": 4.2271853986551395,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000332904168252599,
|
|
"loss": 4.5066,
|
|
"mean_token_accuracy": 0.2688013672828674,
|
|
"num_tokens": 100911066.0,
|
|
"step": 44005
|
|
},
|
|
{
|
|
"entropy": 5.048458099365234,
|
|
"epoch": 4.227665706051873,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00033287103877186966,
|
|
"loss": 4.5216,
|
|
"mean_token_accuracy": 0.26594326496124265,
|
|
"num_tokens": 100923241.0,
|
|
"step": 44010
|
|
},
|
|
{
|
|
"entropy": 5.17834210395813,
|
|
"epoch": 4.228146013448607,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003328379079475466,
|
|
"loss": 4.635,
|
|
"mean_token_accuracy": 0.26005504578351973,
|
|
"num_tokens": 100935203.0,
|
|
"step": 44015
|
|
},
|
|
{
|
|
"entropy": 5.051032209396363,
|
|
"epoch": 4.228626320845341,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003328047757803992,
|
|
"loss": 4.528,
|
|
"mean_token_accuracy": 0.26382261514663696,
|
|
"num_tokens": 100948133.0,
|
|
"step": 44020
|
|
},
|
|
{
|
|
"entropy": 5.2524744987487795,
|
|
"epoch": 4.229106628242075,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003327716422711965,
|
|
"loss": 4.6878,
|
|
"mean_token_accuracy": 0.24755023121833802,
|
|
"num_tokens": 100960448.0,
|
|
"step": 44025
|
|
},
|
|
{
|
|
"entropy": 5.208824396133423,
|
|
"epoch": 4.2295869356388085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00033273850742070784,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.2653436973690987,
|
|
"num_tokens": 100971372.0,
|
|
"step": 44030
|
|
},
|
|
{
|
|
"entropy": 5.171935653686523,
|
|
"epoch": 4.230067243035543,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003327053712297024,
|
|
"loss": 4.6215,
|
|
"mean_token_accuracy": 0.2563817992806435,
|
|
"num_tokens": 100982656.0,
|
|
"step": 44035
|
|
},
|
|
{
|
|
"entropy": 5.15868558883667,
|
|
"epoch": 4.230547550432276,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003326722336989497,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.25289675742387774,
|
|
"num_tokens": 100994410.0,
|
|
"step": 44040
|
|
},
|
|
{
|
|
"entropy": 5.136924982070923,
|
|
"epoch": 4.231027857829011,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003326390948292189,
|
|
"loss": 4.5948,
|
|
"mean_token_accuracy": 0.25270399898290635,
|
|
"num_tokens": 101007345.0,
|
|
"step": 44045
|
|
},
|
|
{
|
|
"entropy": 5.230977153778076,
|
|
"epoch": 4.231508165225744,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003326059546212795,
|
|
"loss": 4.7236,
|
|
"mean_token_accuracy": 0.251910588145256,
|
|
"num_tokens": 101018780.0,
|
|
"step": 44050
|
|
},
|
|
{
|
|
"entropy": 5.168277788162231,
|
|
"epoch": 4.231988472622478,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003325728130759009,
|
|
"loss": 4.595,
|
|
"mean_token_accuracy": 0.26412287801504136,
|
|
"num_tokens": 101030221.0,
|
|
"step": 44055
|
|
},
|
|
{
|
|
"entropy": 5.075335693359375,
|
|
"epoch": 4.232468780019213,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003325396701938525,
|
|
"loss": 4.5377,
|
|
"mean_token_accuracy": 0.2685953930020332,
|
|
"num_tokens": 101041877.0,
|
|
"step": 44060
|
|
},
|
|
{
|
|
"entropy": 5.162394952774048,
|
|
"epoch": 4.232949087415946,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003325065259759039,
|
|
"loss": 4.537,
|
|
"mean_token_accuracy": 0.26659135669469836,
|
|
"num_tokens": 101052331.0,
|
|
"step": 44065
|
|
},
|
|
{
|
|
"entropy": 5.0792640209197994,
|
|
"epoch": 4.23342939481268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003324733804228244,
|
|
"loss": 4.5089,
|
|
"mean_token_accuracy": 0.26141063421964644,
|
|
"num_tokens": 101063211.0,
|
|
"step": 44070
|
|
},
|
|
{
|
|
"entropy": 5.064570569992066,
|
|
"epoch": 4.233909702209414,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00033244023353538367,
|
|
"loss": 4.5875,
|
|
"mean_token_accuracy": 0.2657713368535042,
|
|
"num_tokens": 101074245.0,
|
|
"step": 44075
|
|
},
|
|
{
|
|
"entropy": 5.095441150665283,
|
|
"epoch": 4.234390009606148,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003324070853143514,
|
|
"loss": 4.4847,
|
|
"mean_token_accuracy": 0.2721761718392372,
|
|
"num_tokens": 101084232.0,
|
|
"step": 44080
|
|
},
|
|
{
|
|
"entropy": 5.2179030418396,
|
|
"epoch": 4.234870317002882,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033237393576049704,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.24742990881204605,
|
|
"num_tokens": 101094433.0,
|
|
"step": 44085
|
|
},
|
|
{
|
|
"entropy": 5.130776214599609,
|
|
"epoch": 4.235350624399616,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033234078487459016,
|
|
"loss": 4.5914,
|
|
"mean_token_accuracy": 0.2676608800888062,
|
|
"num_tokens": 101106895.0,
|
|
"step": 44090
|
|
},
|
|
{
|
|
"entropy": 5.171599054336548,
|
|
"epoch": 4.235830931796349,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003323076326574006,
|
|
"loss": 4.6934,
|
|
"mean_token_accuracy": 0.25491967499256135,
|
|
"num_tokens": 101118572.0,
|
|
"step": 44095
|
|
},
|
|
{
|
|
"entropy": 5.216533565521241,
|
|
"epoch": 4.236311239193084,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000332274479109698,
|
|
"loss": 4.6347,
|
|
"mean_token_accuracy": 0.249405075609684,
|
|
"num_tokens": 101129257.0,
|
|
"step": 44100
|
|
},
|
|
{
|
|
"entropy": 5.222848224639892,
|
|
"epoch": 4.236791546589817,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000332241324232252,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.26351688206195834,
|
|
"num_tokens": 101140025.0,
|
|
"step": 44105
|
|
},
|
|
{
|
|
"entropy": 5.146128749847412,
|
|
"epoch": 4.2372718539865515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00033220816802583247,
|
|
"loss": 4.5883,
|
|
"mean_token_accuracy": 0.2624043390154839,
|
|
"num_tokens": 101151432.0,
|
|
"step": 44110
|
|
},
|
|
{
|
|
"entropy": 5.122774934768676,
|
|
"epoch": 4.237752161383285,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003321750104912092,
|
|
"loss": 4.587,
|
|
"mean_token_accuracy": 0.2623540535569191,
|
|
"num_tokens": 101162624.0,
|
|
"step": 44115
|
|
},
|
|
{
|
|
"entropy": 5.159358978271484,
|
|
"epoch": 4.238232468780019,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00033214185162915185,
|
|
"loss": 4.6475,
|
|
"mean_token_accuracy": 0.25966368764638903,
|
|
"num_tokens": 101175055.0,
|
|
"step": 44120
|
|
},
|
|
{
|
|
"entropy": 5.176003360748291,
|
|
"epoch": 4.238712776176753,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00033210869144043037,
|
|
"loss": 4.6607,
|
|
"mean_token_accuracy": 0.25821781158447266,
|
|
"num_tokens": 101186051.0,
|
|
"step": 44125
|
|
},
|
|
{
|
|
"entropy": 5.161202669143677,
|
|
"epoch": 4.239193083573487,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033207552992581474,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.259974367916584,
|
|
"num_tokens": 101198009.0,
|
|
"step": 44130
|
|
},
|
|
{
|
|
"entropy": 5.089166307449341,
|
|
"epoch": 4.239673390970221,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00033204236708607476,
|
|
"loss": 4.5415,
|
|
"mean_token_accuracy": 0.27428484708070755,
|
|
"num_tokens": 101208950.0,
|
|
"step": 44135
|
|
},
|
|
{
|
|
"entropy": 5.127572250366211,
|
|
"epoch": 4.240153698366955,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003320092029219804,
|
|
"loss": 4.6141,
|
|
"mean_token_accuracy": 0.2601440727710724,
|
|
"num_tokens": 101220673.0,
|
|
"step": 44140
|
|
},
|
|
{
|
|
"entropy": 5.141301059722901,
|
|
"epoch": 4.240634005763689,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003319760374343016,
|
|
"loss": 4.5946,
|
|
"mean_token_accuracy": 0.2655756339430809,
|
|
"num_tokens": 101233629.0,
|
|
"step": 44145
|
|
},
|
|
{
|
|
"entropy": 5.076479721069336,
|
|
"epoch": 4.2411143131604225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003319428706238085,
|
|
"loss": 4.5017,
|
|
"mean_token_accuracy": 0.2777819186449051,
|
|
"num_tokens": 101245395.0,
|
|
"step": 44150
|
|
},
|
|
{
|
|
"entropy": 5.125197887420654,
|
|
"epoch": 4.241594620557157,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003319097024912709,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.2572517916560173,
|
|
"num_tokens": 101257504.0,
|
|
"step": 44155
|
|
},
|
|
{
|
|
"entropy": 5.146390771865844,
|
|
"epoch": 4.24207492795389,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000331876533037459,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.25102933049201964,
|
|
"num_tokens": 101268418.0,
|
|
"step": 44160
|
|
},
|
|
{
|
|
"entropy": 5.0719156742095945,
|
|
"epoch": 4.242555235350625,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000331843362263143,
|
|
"loss": 4.517,
|
|
"mean_token_accuracy": 0.27079734653234483,
|
|
"num_tokens": 101280509.0,
|
|
"step": 44165
|
|
},
|
|
{
|
|
"entropy": 5.17478837966919,
|
|
"epoch": 4.243035542747358,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00033181019016909286,
|
|
"loss": 4.6167,
|
|
"mean_token_accuracy": 0.25984034687280655,
|
|
"num_tokens": 101292869.0,
|
|
"step": 44170
|
|
},
|
|
{
|
|
"entropy": 5.198108720779419,
|
|
"epoch": 4.243515850144092,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003317770167560788,
|
|
"loss": 4.5358,
|
|
"mean_token_accuracy": 0.26767932176589965,
|
|
"num_tokens": 101304772.0,
|
|
"step": 44175
|
|
},
|
|
{
|
|
"entropy": 5.110682773590088,
|
|
"epoch": 4.243996157540826,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033174384202487096,
|
|
"loss": 4.5978,
|
|
"mean_token_accuracy": 0.2581408485770226,
|
|
"num_tokens": 101315445.0,
|
|
"step": 44180
|
|
},
|
|
{
|
|
"entropy": 5.053160333633423,
|
|
"epoch": 4.24447646493756,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003317106659762397,
|
|
"loss": 4.5376,
|
|
"mean_token_accuracy": 0.26296316981315615,
|
|
"num_tokens": 101326102.0,
|
|
"step": 44185
|
|
},
|
|
{
|
|
"entropy": 5.094948625564575,
|
|
"epoch": 4.244956772334294,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00033167748861095503,
|
|
"loss": 4.5307,
|
|
"mean_token_accuracy": 0.25906773954629897,
|
|
"num_tokens": 101337419.0,
|
|
"step": 44190
|
|
},
|
|
{
|
|
"entropy": 5.205678844451905,
|
|
"epoch": 4.245437079731028,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003316443099297874,
|
|
"loss": 4.601,
|
|
"mean_token_accuracy": 0.25920635312795637,
|
|
"num_tokens": 101348630.0,
|
|
"step": 44195
|
|
},
|
|
{
|
|
"entropy": 5.083158731460571,
|
|
"epoch": 4.245917387127761,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00033161112993350725,
|
|
"loss": 4.5087,
|
|
"mean_token_accuracy": 0.2585090473294258,
|
|
"num_tokens": 101361357.0,
|
|
"step": 44200
|
|
},
|
|
{
|
|
"entropy": 5.141242218017578,
|
|
"epoch": 4.246397694524496,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00033157794862288467,
|
|
"loss": 4.5275,
|
|
"mean_token_accuracy": 0.2679761290550232,
|
|
"num_tokens": 101372155.0,
|
|
"step": 44205
|
|
},
|
|
{
|
|
"entropy": 5.036495494842529,
|
|
"epoch": 4.24687800192123,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00033154476599869006,
|
|
"loss": 4.4471,
|
|
"mean_token_accuracy": 0.27095719128847123,
|
|
"num_tokens": 101383011.0,
|
|
"step": 44210
|
|
},
|
|
{
|
|
"entropy": 5.0833944320678714,
|
|
"epoch": 4.247358309317963,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000331511582061694,
|
|
"loss": 4.5209,
|
|
"mean_token_accuracy": 0.2646331563591957,
|
|
"num_tokens": 101394741.0,
|
|
"step": 44215
|
|
},
|
|
{
|
|
"entropy": 5.165009260177612,
|
|
"epoch": 4.247838616714698,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003314783968126667,
|
|
"loss": 4.6529,
|
|
"mean_token_accuracy": 0.26072234511375425,
|
|
"num_tokens": 101405719.0,
|
|
"step": 44220
|
|
},
|
|
{
|
|
"entropy": 5.073537111282349,
|
|
"epoch": 4.248318924111431,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003314452102523788,
|
|
"loss": 4.5333,
|
|
"mean_token_accuracy": 0.2632041037082672,
|
|
"num_tokens": 101417073.0,
|
|
"step": 44225
|
|
},
|
|
{
|
|
"entropy": 5.185058164596557,
|
|
"epoch": 4.2487992315081655,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00033141202238160075,
|
|
"loss": 4.6489,
|
|
"mean_token_accuracy": 0.2544869214296341,
|
|
"num_tokens": 101429674.0,
|
|
"step": 44230
|
|
},
|
|
{
|
|
"entropy": 5.163464879989624,
|
|
"epoch": 4.249279538904899,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00033137883320110296,
|
|
"loss": 4.5683,
|
|
"mean_token_accuracy": 0.2588696271181107,
|
|
"num_tokens": 101441841.0,
|
|
"step": 44235
|
|
},
|
|
{
|
|
"entropy": 5.1454192161560055,
|
|
"epoch": 4.249759846301633,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003313456427116561,
|
|
"loss": 4.6113,
|
|
"mean_token_accuracy": 0.25798132866621015,
|
|
"num_tokens": 101452946.0,
|
|
"step": 44240
|
|
},
|
|
{
|
|
"entropy": 5.190009880065918,
|
|
"epoch": 4.250240153698367,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003313124509140308,
|
|
"loss": 4.6097,
|
|
"mean_token_accuracy": 0.25852348655462265,
|
|
"num_tokens": 101462919.0,
|
|
"step": 44245
|
|
},
|
|
{
|
|
"entropy": 5.032107496261597,
|
|
"epoch": 4.250720461095101,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00033127925780899754,
|
|
"loss": 4.4654,
|
|
"mean_token_accuracy": 0.26949589103460314,
|
|
"num_tokens": 101474718.0,
|
|
"step": 44250
|
|
},
|
|
{
|
|
"entropy": 5.057794046401978,
|
|
"epoch": 4.2512007684918345,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000331246063397327,
|
|
"loss": 4.5554,
|
|
"mean_token_accuracy": 0.2621978551149368,
|
|
"num_tokens": 101487179.0,
|
|
"step": 44255
|
|
},
|
|
{
|
|
"entropy": 5.087724351882935,
|
|
"epoch": 4.251681075888569,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033121286767979,
|
|
"loss": 4.5623,
|
|
"mean_token_accuracy": 0.2672914981842041,
|
|
"num_tokens": 101498816.0,
|
|
"step": 44260
|
|
},
|
|
{
|
|
"entropy": 5.115346384048462,
|
|
"epoch": 4.252161383285302,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000331179670657157,
|
|
"loss": 4.5963,
|
|
"mean_token_accuracy": 0.2570624351501465,
|
|
"num_tokens": 101510945.0,
|
|
"step": 44265
|
|
},
|
|
{
|
|
"entropy": 5.094194030761718,
|
|
"epoch": 4.252641690682037,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003311464723301989,
|
|
"loss": 4.5571,
|
|
"mean_token_accuracy": 0.2608169659972191,
|
|
"num_tokens": 101522344.0,
|
|
"step": 44270
|
|
},
|
|
{
|
|
"entropy": 5.111892461776733,
|
|
"epoch": 4.25312199807877,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003311132726996866,
|
|
"loss": 4.5739,
|
|
"mean_token_accuracy": 0.2626839026808739,
|
|
"num_tokens": 101534071.0,
|
|
"step": 44275
|
|
},
|
|
{
|
|
"entropy": 5.112270402908325,
|
|
"epoch": 4.253602305475504,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003310800717663905,
|
|
"loss": 4.5623,
|
|
"mean_token_accuracy": 0.26017716377973554,
|
|
"num_tokens": 101546418.0,
|
|
"step": 44280
|
|
},
|
|
{
|
|
"entropy": 5.087921142578125,
|
|
"epoch": 4.254082612872239,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00033104686953108173,
|
|
"loss": 4.5672,
|
|
"mean_token_accuracy": 0.26183846443891523,
|
|
"num_tokens": 101559423.0,
|
|
"step": 44285
|
|
},
|
|
{
|
|
"entropy": 5.12047700881958,
|
|
"epoch": 4.254562920268972,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003310136659945311,
|
|
"loss": 4.5707,
|
|
"mean_token_accuracy": 0.26419502049684523,
|
|
"num_tokens": 101570308.0,
|
|
"step": 44290
|
|
},
|
|
{
|
|
"entropy": 5.087884521484375,
|
|
"epoch": 4.255043227665706,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00033098046115750946,
|
|
"loss": 4.5178,
|
|
"mean_token_accuracy": 0.26265201568603513,
|
|
"num_tokens": 101582689.0,
|
|
"step": 44295
|
|
},
|
|
{
|
|
"entropy": 5.02780590057373,
|
|
"epoch": 4.25552353506244,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003309472550207877,
|
|
"loss": 4.4619,
|
|
"mean_token_accuracy": 0.28208173215389254,
|
|
"num_tokens": 101593675.0,
|
|
"step": 44300
|
|
},
|
|
{
|
|
"entropy": 5.035257816314697,
|
|
"epoch": 4.256003842459174,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00033091404758513686,
|
|
"loss": 4.4807,
|
|
"mean_token_accuracy": 0.27588237076997757,
|
|
"num_tokens": 101604057.0,
|
|
"step": 44305
|
|
},
|
|
{
|
|
"entropy": 5.139220142364502,
|
|
"epoch": 4.256484149855908,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033088083885132784,
|
|
"loss": 4.5423,
|
|
"mean_token_accuracy": 0.2657954692840576,
|
|
"num_tokens": 101615063.0,
|
|
"step": 44310
|
|
},
|
|
{
|
|
"entropy": 5.047278022766113,
|
|
"epoch": 4.256964457252642,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033084762882013176,
|
|
"loss": 4.4819,
|
|
"mean_token_accuracy": 0.26556218713521956,
|
|
"num_tokens": 101626059.0,
|
|
"step": 44315
|
|
},
|
|
{
|
|
"entropy": 5.123217248916626,
|
|
"epoch": 4.257444764649375,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00033081441749231944,
|
|
"loss": 4.6059,
|
|
"mean_token_accuracy": 0.25653844326734543,
|
|
"num_tokens": 101637799.0,
|
|
"step": 44320
|
|
},
|
|
{
|
|
"entropy": 5.101638078689575,
|
|
"epoch": 4.25792507204611,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003307812048686621,
|
|
"loss": 4.5063,
|
|
"mean_token_accuracy": 0.27328974157571795,
|
|
"num_tokens": 101648863.0,
|
|
"step": 44325
|
|
},
|
|
{
|
|
"entropy": 5.077841663360596,
|
|
"epoch": 4.258405379442843,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003307479909499309,
|
|
"loss": 4.5119,
|
|
"mean_token_accuracy": 0.26525905430316926,
|
|
"num_tokens": 101660144.0,
|
|
"step": 44330
|
|
},
|
|
{
|
|
"entropy": 5.144623565673828,
|
|
"epoch": 4.2588856868395775,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003307147757368969,
|
|
"loss": 4.5754,
|
|
"mean_token_accuracy": 0.25960921198129655,
|
|
"num_tokens": 101671388.0,
|
|
"step": 44335
|
|
},
|
|
{
|
|
"entropy": 5.088678216934204,
|
|
"epoch": 4.259365994236311,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00033068155923033114,
|
|
"loss": 4.5646,
|
|
"mean_token_accuracy": 0.26358651369810104,
|
|
"num_tokens": 101682542.0,
|
|
"step": 44340
|
|
},
|
|
{
|
|
"entropy": 5.128240156173706,
|
|
"epoch": 4.259846301633045,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033064834143100495,
|
|
"loss": 4.5538,
|
|
"mean_token_accuracy": 0.2680211067199707,
|
|
"num_tokens": 101692683.0,
|
|
"step": 44345
|
|
},
|
|
{
|
|
"entropy": 5.14046459197998,
|
|
"epoch": 4.260326609029779,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003306151223396896,
|
|
"loss": 4.6121,
|
|
"mean_token_accuracy": 0.2541263610124588,
|
|
"num_tokens": 101704566.0,
|
|
"step": 44350
|
|
},
|
|
{
|
|
"entropy": 5.152146720886231,
|
|
"epoch": 4.260806916426513,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003305819019571562,
|
|
"loss": 4.6236,
|
|
"mean_token_accuracy": 0.25131349712610246,
|
|
"num_tokens": 101716751.0,
|
|
"step": 44355
|
|
},
|
|
{
|
|
"entropy": 5.20406141281128,
|
|
"epoch": 4.261287223823247,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033054868028417606,
|
|
"loss": 4.6507,
|
|
"mean_token_accuracy": 0.2578595161437988,
|
|
"num_tokens": 101728614.0,
|
|
"step": 44360
|
|
},
|
|
{
|
|
"entropy": 5.201860570907593,
|
|
"epoch": 4.261767531219981,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033051545732152047,
|
|
"loss": 4.6262,
|
|
"mean_token_accuracy": 0.2585292235016823,
|
|
"num_tokens": 101739740.0,
|
|
"step": 44365
|
|
},
|
|
{
|
|
"entropy": 5.072698354721069,
|
|
"epoch": 4.262247838616715,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003304822330699609,
|
|
"loss": 4.5132,
|
|
"mean_token_accuracy": 0.2739124298095703,
|
|
"num_tokens": 101750971.0,
|
|
"step": 44370
|
|
},
|
|
{
|
|
"entropy": 5.069994735717773,
|
|
"epoch": 4.2627281460134485,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003304490075302686,
|
|
"loss": 4.5043,
|
|
"mean_token_accuracy": 0.2642792209982872,
|
|
"num_tokens": 101762955.0,
|
|
"step": 44375
|
|
},
|
|
{
|
|
"entropy": 5.060191965103149,
|
|
"epoch": 4.263208453410183,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033041578070321494,
|
|
"loss": 4.4835,
|
|
"mean_token_accuracy": 0.27152019590139387,
|
|
"num_tokens": 101773314.0,
|
|
"step": 44380
|
|
},
|
|
{
|
|
"entropy": 5.041294240951538,
|
|
"epoch": 4.263688760806916,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003303825525895714,
|
|
"loss": 4.5264,
|
|
"mean_token_accuracy": 0.2627903252840042,
|
|
"num_tokens": 101784006.0,
|
|
"step": 44385
|
|
},
|
|
{
|
|
"entropy": 5.125041580200195,
|
|
"epoch": 4.264169068203651,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00033034932319010946,
|
|
"loss": 4.5438,
|
|
"mean_token_accuracy": 0.2627210170030594,
|
|
"num_tokens": 101795585.0,
|
|
"step": 44390
|
|
},
|
|
{
|
|
"entropy": 5.180232858657837,
|
|
"epoch": 4.264649375600384,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00033031609250560066,
|
|
"loss": 4.633,
|
|
"mean_token_accuracy": 0.2554085686802864,
|
|
"num_tokens": 101806672.0,
|
|
"step": 44395
|
|
},
|
|
{
|
|
"entropy": 5.196695041656494,
|
|
"epoch": 4.265129682997118,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003302828605368164,
|
|
"loss": 4.6457,
|
|
"mean_token_accuracy": 0.2506922289729118,
|
|
"num_tokens": 101819353.0,
|
|
"step": 44400
|
|
},
|
|
{
|
|
"entropy": 5.173883056640625,
|
|
"epoch": 4.265609990393852,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00033024962728452826,
|
|
"loss": 4.5896,
|
|
"mean_token_accuracy": 0.25959356874227524,
|
|
"num_tokens": 101830739.0,
|
|
"step": 44405
|
|
},
|
|
{
|
|
"entropy": 5.111999082565307,
|
|
"epoch": 4.266090297790586,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003302163927495078,
|
|
"loss": 4.6248,
|
|
"mean_token_accuracy": 0.2553132981061935,
|
|
"num_tokens": 101842484.0,
|
|
"step": 44410
|
|
},
|
|
{
|
|
"entropy": 5.125500679016113,
|
|
"epoch": 4.26657060518732,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003301831569325267,
|
|
"loss": 4.6058,
|
|
"mean_token_accuracy": 0.25592657178640366,
|
|
"num_tokens": 101854393.0,
|
|
"step": 44415
|
|
},
|
|
{
|
|
"entropy": 5.087772035598755,
|
|
"epoch": 4.267050912584054,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00033014991983435654,
|
|
"loss": 4.4698,
|
|
"mean_token_accuracy": 0.2690632000565529,
|
|
"num_tokens": 101866266.0,
|
|
"step": 44420
|
|
},
|
|
{
|
|
"entropy": 5.084116744995117,
|
|
"epoch": 4.267531219980787,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003301166814557691,
|
|
"loss": 4.4925,
|
|
"mean_token_accuracy": 0.2711788922548294,
|
|
"num_tokens": 101876727.0,
|
|
"step": 44425
|
|
},
|
|
{
|
|
"entropy": 5.176114320755005,
|
|
"epoch": 4.268011527377522,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00033008344179753584,
|
|
"loss": 4.6232,
|
|
"mean_token_accuracy": 0.2606009006500244,
|
|
"num_tokens": 101887996.0,
|
|
"step": 44430
|
|
},
|
|
{
|
|
"entropy": 5.142423105239868,
|
|
"epoch": 4.268491834774256,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00033005020086042874,
|
|
"loss": 4.5843,
|
|
"mean_token_accuracy": 0.2617508426308632,
|
|
"num_tokens": 101899676.0,
|
|
"step": 44435
|
|
},
|
|
{
|
|
"entropy": 5.106353425979615,
|
|
"epoch": 4.268972142170989,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00033001695864521934,
|
|
"loss": 4.5802,
|
|
"mean_token_accuracy": 0.26251686066389085,
|
|
"num_tokens": 101910709.0,
|
|
"step": 44440
|
|
},
|
|
{
|
|
"entropy": 5.131693172454834,
|
|
"epoch": 4.269452449567724,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00032998371515267954,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.26037808060646056,
|
|
"num_tokens": 101921375.0,
|
|
"step": 44445
|
|
},
|
|
{
|
|
"entropy": 5.128436136245727,
|
|
"epoch": 4.269932756964457,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003299504703835812,
|
|
"loss": 4.5447,
|
|
"mean_token_accuracy": 0.2621429145336151,
|
|
"num_tokens": 101932899.0,
|
|
"step": 44450
|
|
},
|
|
{
|
|
"entropy": 5.185178613662719,
|
|
"epoch": 4.2704130643611915,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003299172243386961,
|
|
"loss": 4.6217,
|
|
"mean_token_accuracy": 0.25882608741521834,
|
|
"num_tokens": 101943749.0,
|
|
"step": 44455
|
|
},
|
|
{
|
|
"entropy": 5.119780874252319,
|
|
"epoch": 4.270893371757925,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003298839770187961,
|
|
"loss": 4.5531,
|
|
"mean_token_accuracy": 0.25963550209999087,
|
|
"num_tokens": 101955166.0,
|
|
"step": 44460
|
|
},
|
|
{
|
|
"entropy": 5.118280839920044,
|
|
"epoch": 4.271373679154659,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032985072842465314,
|
|
"loss": 4.5869,
|
|
"mean_token_accuracy": 0.25487079471349716,
|
|
"num_tokens": 101966875.0,
|
|
"step": 44465
|
|
},
|
|
{
|
|
"entropy": 5.210586929321289,
|
|
"epoch": 4.271853986551393,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00032981747855703915,
|
|
"loss": 4.6275,
|
|
"mean_token_accuracy": 0.25383820235729215,
|
|
"num_tokens": 101978137.0,
|
|
"step": 44470
|
|
},
|
|
{
|
|
"entropy": 5.090311098098755,
|
|
"epoch": 4.272334293948127,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00032978422741672603,
|
|
"loss": 4.5068,
|
|
"mean_token_accuracy": 0.2664637118577957,
|
|
"num_tokens": 101988953.0,
|
|
"step": 44475
|
|
},
|
|
{
|
|
"entropy": 5.1888580322265625,
|
|
"epoch": 4.2728146013448605,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003297509750044858,
|
|
"loss": 4.6738,
|
|
"mean_token_accuracy": 0.2546827673912048,
|
|
"num_tokens": 102001298.0,
|
|
"step": 44480
|
|
},
|
|
{
|
|
"entropy": 5.153652286529541,
|
|
"epoch": 4.273294908741595,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003297177213210907,
|
|
"loss": 4.5357,
|
|
"mean_token_accuracy": 0.2632442131638527,
|
|
"num_tokens": 102012934.0,
|
|
"step": 44485
|
|
},
|
|
{
|
|
"entropy": 5.094034337997437,
|
|
"epoch": 4.273775216138328,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003296844663673124,
|
|
"loss": 4.5034,
|
|
"mean_token_accuracy": 0.26876782476902006,
|
|
"num_tokens": 102023863.0,
|
|
"step": 44490
|
|
},
|
|
{
|
|
"entropy": 5.0535942077636715,
|
|
"epoch": 4.2742555235350626,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003296512101439232,
|
|
"loss": 4.445,
|
|
"mean_token_accuracy": 0.27091426253318784,
|
|
"num_tokens": 102034586.0,
|
|
"step": 44495
|
|
},
|
|
{
|
|
"entropy": 5.005676555633545,
|
|
"epoch": 4.274735830931796,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032961795265169525,
|
|
"loss": 4.5059,
|
|
"mean_token_accuracy": 0.27076555788517,
|
|
"num_tokens": 102044933.0,
|
|
"step": 44500
|
|
},
|
|
{
|
|
"entropy": 5.177567338943481,
|
|
"epoch": 4.27521613832853,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003295846938914005,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.25556394308805463,
|
|
"num_tokens": 102056370.0,
|
|
"step": 44505
|
|
},
|
|
{
|
|
"entropy": 5.152410697937012,
|
|
"epoch": 4.275696445725265,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003295514338638114,
|
|
"loss": 4.5924,
|
|
"mean_token_accuracy": 0.25926061123609545,
|
|
"num_tokens": 102067428.0,
|
|
"step": 44510
|
|
},
|
|
{
|
|
"entropy": 5.082250928878784,
|
|
"epoch": 4.276176753121998,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003295181725696999,
|
|
"loss": 4.5032,
|
|
"mean_token_accuracy": 0.2724078819155693,
|
|
"num_tokens": 102079262.0,
|
|
"step": 44515
|
|
},
|
|
{
|
|
"entropy": 5.088791465759277,
|
|
"epoch": 4.276657060518732,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003294849100098383,
|
|
"loss": 4.5335,
|
|
"mean_token_accuracy": 0.26829028874635696,
|
|
"num_tokens": 102088835.0,
|
|
"step": 44520
|
|
},
|
|
{
|
|
"entropy": 5.199168109893799,
|
|
"epoch": 4.277137367915466,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003294516461849988,
|
|
"loss": 4.6639,
|
|
"mean_token_accuracy": 0.255409349501133,
|
|
"num_tokens": 102100119.0,
|
|
"step": 44525
|
|
},
|
|
{
|
|
"entropy": 5.163884830474854,
|
|
"epoch": 4.2776176753122,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000329418381095954,
|
|
"loss": 4.6284,
|
|
"mean_token_accuracy": 0.2605076342821121,
|
|
"num_tokens": 102111279.0,
|
|
"step": 44530
|
|
},
|
|
{
|
|
"entropy": 5.093370819091797,
|
|
"epoch": 4.278097982708934,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003293851147434758,
|
|
"loss": 4.5492,
|
|
"mean_token_accuracy": 0.2651337057352066,
|
|
"num_tokens": 102122977.0,
|
|
"step": 44535
|
|
},
|
|
{
|
|
"entropy": 5.18222975730896,
|
|
"epoch": 4.278578290105668,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00032935184712833674,
|
|
"loss": 4.6729,
|
|
"mean_token_accuracy": 0.25804210901260377,
|
|
"num_tokens": 102135343.0,
|
|
"step": 44540
|
|
},
|
|
{
|
|
"entropy": 5.155241775512695,
|
|
"epoch": 4.279058597502401,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003293185782513093,
|
|
"loss": 4.5617,
|
|
"mean_token_accuracy": 0.2588619694113731,
|
|
"num_tokens": 102148331.0,
|
|
"step": 44545
|
|
},
|
|
{
|
|
"entropy": 5.113495302200318,
|
|
"epoch": 4.279538904899136,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032928530811316564,
|
|
"loss": 4.5217,
|
|
"mean_token_accuracy": 0.2649267166852951,
|
|
"num_tokens": 102159720.0,
|
|
"step": 44550
|
|
},
|
|
{
|
|
"entropy": 5.175276088714599,
|
|
"epoch": 4.280019212295869,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003292520367146784,
|
|
"loss": 4.6408,
|
|
"mean_token_accuracy": 0.2535011380910873,
|
|
"num_tokens": 102172323.0,
|
|
"step": 44555
|
|
},
|
|
{
|
|
"entropy": 5.142466926574707,
|
|
"epoch": 4.2804995196926034,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003292187640566199,
|
|
"loss": 4.515,
|
|
"mean_token_accuracy": 0.27107624560594556,
|
|
"num_tokens": 102183998.0,
|
|
"step": 44560
|
|
},
|
|
{
|
|
"entropy": 5.113651990890503,
|
|
"epoch": 4.280979827089337,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00032918549013976267,
|
|
"loss": 4.5265,
|
|
"mean_token_accuracy": 0.2647775948047638,
|
|
"num_tokens": 102196193.0,
|
|
"step": 44565
|
|
},
|
|
{
|
|
"entropy": 5.077427768707276,
|
|
"epoch": 4.281460134486071,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003291522149648794,
|
|
"loss": 4.4929,
|
|
"mean_token_accuracy": 0.26910130530595777,
|
|
"num_tokens": 102208042.0,
|
|
"step": 44570
|
|
},
|
|
{
|
|
"entropy": 5.137736368179321,
|
|
"epoch": 4.281940441882805,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00032911893853274234,
|
|
"loss": 4.5694,
|
|
"mean_token_accuracy": 0.26598591059446336,
|
|
"num_tokens": 102219006.0,
|
|
"step": 44575
|
|
},
|
|
{
|
|
"entropy": 5.113501930236817,
|
|
"epoch": 4.282420749279539,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003290856608441243,
|
|
"loss": 4.5717,
|
|
"mean_token_accuracy": 0.26840897351503373,
|
|
"num_tokens": 102230733.0,
|
|
"step": 44580
|
|
},
|
|
{
|
|
"entropy": 5.121811389923096,
|
|
"epoch": 4.282901056676272,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003290523818997978,
|
|
"loss": 4.616,
|
|
"mean_token_accuracy": 0.2618367329239845,
|
|
"num_tokens": 102240871.0,
|
|
"step": 44585
|
|
},
|
|
{
|
|
"entropy": 5.083138465881348,
|
|
"epoch": 4.283381364073007,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00032901910170053553,
|
|
"loss": 4.4716,
|
|
"mean_token_accuracy": 0.26657651364803314,
|
|
"num_tokens": 102252427.0,
|
|
"step": 44590
|
|
},
|
|
{
|
|
"entropy": 5.169166612625122,
|
|
"epoch": 4.28386167146974,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003289858202471101,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.26465784907341006,
|
|
"num_tokens": 102263576.0,
|
|
"step": 44595
|
|
},
|
|
{
|
|
"entropy": 5.19939284324646,
|
|
"epoch": 4.2843419788664745,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00032895253754029415,
|
|
"loss": 4.5362,
|
|
"mean_token_accuracy": 0.2663922429084778,
|
|
"num_tokens": 102275475.0,
|
|
"step": 44600
|
|
},
|
|
{
|
|
"entropy": 5.128120040893554,
|
|
"epoch": 4.284822286263209,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00032891925358086063,
|
|
"loss": 4.5966,
|
|
"mean_token_accuracy": 0.25345665365457537,
|
|
"num_tokens": 102287757.0,
|
|
"step": 44605
|
|
},
|
|
{
|
|
"entropy": 5.108875036239624,
|
|
"epoch": 4.285302593659942,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00032888596836958206,
|
|
"loss": 4.5146,
|
|
"mean_token_accuracy": 0.2618876099586487,
|
|
"num_tokens": 102298732.0,
|
|
"step": 44610
|
|
},
|
|
{
|
|
"entropy": 5.16659574508667,
|
|
"epoch": 4.285782901056677,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032885268190723134,
|
|
"loss": 4.6124,
|
|
"mean_token_accuracy": 0.26250521242618563,
|
|
"num_tokens": 102310061.0,
|
|
"step": 44615
|
|
},
|
|
{
|
|
"entropy": 5.1371876239776615,
|
|
"epoch": 4.28626320845341,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003288193941945812,
|
|
"loss": 4.6034,
|
|
"mean_token_accuracy": 0.2603632867336273,
|
|
"num_tokens": 102320937.0,
|
|
"step": 44620
|
|
},
|
|
{
|
|
"entropy": 5.163876724243164,
|
|
"epoch": 4.286743515850144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003287861052324047,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.24957939684391023,
|
|
"num_tokens": 102331849.0,
|
|
"step": 44625
|
|
},
|
|
{
|
|
"entropy": 5.1822202682495115,
|
|
"epoch": 4.287223823246878,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003287528150214744,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.25818738639354705,
|
|
"num_tokens": 102343504.0,
|
|
"step": 44630
|
|
},
|
|
{
|
|
"entropy": 5.182325220108032,
|
|
"epoch": 4.287704130643612,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032871952356256336,
|
|
"loss": 4.6166,
|
|
"mean_token_accuracy": 0.25717896074056623,
|
|
"num_tokens": 102354476.0,
|
|
"step": 44635
|
|
},
|
|
{
|
|
"entropy": 5.087769842147827,
|
|
"epoch": 4.2881844380403455,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003286862308564445,
|
|
"loss": 4.4881,
|
|
"mean_token_accuracy": 0.2678326353430748,
|
|
"num_tokens": 102365733.0,
|
|
"step": 44640
|
|
},
|
|
{
|
|
"entropy": 5.190534019470215,
|
|
"epoch": 4.28866474543708,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032865293690389076,
|
|
"loss": 4.6259,
|
|
"mean_token_accuracy": 0.25808544605970385,
|
|
"num_tokens": 102377954.0,
|
|
"step": 44645
|
|
},
|
|
{
|
|
"entropy": 5.220541620254517,
|
|
"epoch": 4.289145052833813,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003286196417056752,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.2642436146736145,
|
|
"num_tokens": 102388378.0,
|
|
"step": 44650
|
|
},
|
|
{
|
|
"entropy": 5.057265329360962,
|
|
"epoch": 4.289625360230548,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00032858634526257077,
|
|
"loss": 4.563,
|
|
"mean_token_accuracy": 0.2622140184044838,
|
|
"num_tokens": 102399702.0,
|
|
"step": 44655
|
|
},
|
|
{
|
|
"entropy": 5.174660015106201,
|
|
"epoch": 4.290105667627281,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003285530475753505,
|
|
"loss": 4.5909,
|
|
"mean_token_accuracy": 0.2586690843105316,
|
|
"num_tokens": 102410393.0,
|
|
"step": 44660
|
|
},
|
|
{
|
|
"entropy": 5.161046981811523,
|
|
"epoch": 4.290585975024015,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032851974864478743,
|
|
"loss": 4.6245,
|
|
"mean_token_accuracy": 0.2693096220493317,
|
|
"num_tokens": 102423463.0,
|
|
"step": 44665
|
|
},
|
|
{
|
|
"entropy": 5.143670892715454,
|
|
"epoch": 4.291066282420749,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032848644847165484,
|
|
"loss": 4.5442,
|
|
"mean_token_accuracy": 0.2667084723711014,
|
|
"num_tokens": 102434822.0,
|
|
"step": 44670
|
|
},
|
|
{
|
|
"entropy": 5.1083659648895265,
|
|
"epoch": 4.291546589817483,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003284531470567256,
|
|
"loss": 4.5149,
|
|
"mean_token_accuracy": 0.2633934810757637,
|
|
"num_tokens": 102446302.0,
|
|
"step": 44675
|
|
},
|
|
{
|
|
"entropy": 5.076317691802979,
|
|
"epoch": 4.2920268972142175,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003284198444007731,
|
|
"loss": 4.5426,
|
|
"mean_token_accuracy": 0.26601305305957795,
|
|
"num_tokens": 102456866.0,
|
|
"step": 44680
|
|
},
|
|
{
|
|
"entropy": 5.121196031570435,
|
|
"epoch": 4.292507204610951,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00032838654050457047,
|
|
"loss": 4.6502,
|
|
"mean_token_accuracy": 0.25976801067590716,
|
|
"num_tokens": 102468498.0,
|
|
"step": 44685
|
|
},
|
|
{
|
|
"entropy": 5.117233848571777,
|
|
"epoch": 4.292987512007685,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003283532353688908,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.26538130193948745,
|
|
"num_tokens": 102481723.0,
|
|
"step": 44690
|
|
},
|
|
{
|
|
"entropy": 5.1694258689880375,
|
|
"epoch": 4.293467819404419,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00032831992899450745,
|
|
"loss": 4.5652,
|
|
"mean_token_accuracy": 0.2649147197604179,
|
|
"num_tokens": 102492828.0,
|
|
"step": 44695
|
|
},
|
|
{
|
|
"entropy": 5.088517904281616,
|
|
"epoch": 4.293948126801153,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00032828662138219375,
|
|
"loss": 4.5318,
|
|
"mean_token_accuracy": 0.26690212488174436,
|
|
"num_tokens": 102503261.0,
|
|
"step": 44700
|
|
},
|
|
{
|
|
"entropy": 4.974819087982178,
|
|
"epoch": 4.2944284341978864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003282533125327228,
|
|
"loss": 4.4442,
|
|
"mean_token_accuracy": 0.266689133644104,
|
|
"num_tokens": 102514383.0,
|
|
"step": 44705
|
|
},
|
|
{
|
|
"entropy": 5.089702844619751,
|
|
"epoch": 4.294908741594621,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003282200024468682,
|
|
"loss": 4.5867,
|
|
"mean_token_accuracy": 0.2601526528596878,
|
|
"num_tokens": 102524441.0,
|
|
"step": 44710
|
|
},
|
|
{
|
|
"entropy": 5.192356443405151,
|
|
"epoch": 4.295389048991354,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003281866911254031,
|
|
"loss": 4.5661,
|
|
"mean_token_accuracy": 0.2629459246993065,
|
|
"num_tokens": 102534785.0,
|
|
"step": 44715
|
|
},
|
|
{
|
|
"entropy": 5.101460075378418,
|
|
"epoch": 4.2958693563880885,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000328153378569101,
|
|
"loss": 4.4961,
|
|
"mean_token_accuracy": 0.2741661459207535,
|
|
"num_tokens": 102546596.0,
|
|
"step": 44720
|
|
},
|
|
{
|
|
"entropy": 5.0812310695648195,
|
|
"epoch": 4.296349663784822,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003281200647787352,
|
|
"loss": 4.5248,
|
|
"mean_token_accuracy": 0.2656964108347893,
|
|
"num_tokens": 102557035.0,
|
|
"step": 44725
|
|
},
|
|
{
|
|
"entropy": 5.129586935043335,
|
|
"epoch": 4.296829971181556,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032808674975507937,
|
|
"loss": 4.6208,
|
|
"mean_token_accuracy": 0.25619756281375883,
|
|
"num_tokens": 102568580.0,
|
|
"step": 44730
|
|
},
|
|
{
|
|
"entropy": 5.253832006454468,
|
|
"epoch": 4.29731027857829,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003280534334989067,
|
|
"loss": 4.662,
|
|
"mean_token_accuracy": 0.2572277307510376,
|
|
"num_tokens": 102578858.0,
|
|
"step": 44735
|
|
},
|
|
{
|
|
"entropy": 5.151888513565064,
|
|
"epoch": 4.297790585975024,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00032802011601099095,
|
|
"loss": 4.5898,
|
|
"mean_token_accuracy": 0.26046783328056333,
|
|
"num_tokens": 102590855.0,
|
|
"step": 44740
|
|
},
|
|
{
|
|
"entropy": 5.050632572174072,
|
|
"epoch": 4.2982708933717575,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032798679729210555,
|
|
"loss": 4.5337,
|
|
"mean_token_accuracy": 0.26463558077812194,
|
|
"num_tokens": 102602548.0,
|
|
"step": 44745
|
|
},
|
|
{
|
|
"entropy": 5.13556022644043,
|
|
"epoch": 4.298751200768492,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000327953477343024,
|
|
"loss": 4.6417,
|
|
"mean_token_accuracy": 0.25374044477939606,
|
|
"num_tokens": 102613635.0,
|
|
"step": 44750
|
|
},
|
|
{
|
|
"entropy": 5.186384630203247,
|
|
"epoch": 4.299231508165226,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032792015616452,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.252178381383419,
|
|
"num_tokens": 102624958.0,
|
|
"step": 44755
|
|
},
|
|
{
|
|
"entropy": 5.110157537460327,
|
|
"epoch": 4.29971181556196,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000327886833757367,
|
|
"loss": 4.5178,
|
|
"mean_token_accuracy": 0.2628400906920433,
|
|
"num_tokens": 102635616.0,
|
|
"step": 44760
|
|
},
|
|
{
|
|
"entropy": 5.145062112808228,
|
|
"epoch": 4.300192122958694,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003278535101223388,
|
|
"loss": 4.5858,
|
|
"mean_token_accuracy": 0.25855313390493395,
|
|
"num_tokens": 102646654.0,
|
|
"step": 44765
|
|
},
|
|
{
|
|
"entropy": 5.1810565948486325,
|
|
"epoch": 4.300672430355427,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003278201852602091,
|
|
"loss": 4.5607,
|
|
"mean_token_accuracy": 0.2679824814200401,
|
|
"num_tokens": 102657624.0,
|
|
"step": 44770
|
|
},
|
|
{
|
|
"entropy": 5.082175779342651,
|
|
"epoch": 4.301152737752162,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032778685917175153,
|
|
"loss": 4.5327,
|
|
"mean_token_accuracy": 0.2667741969227791,
|
|
"num_tokens": 102668931.0,
|
|
"step": 44775
|
|
},
|
|
{
|
|
"entropy": 5.1137247562408445,
|
|
"epoch": 4.301633045148895,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032775353185773983,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.26058492362499236,
|
|
"num_tokens": 102680680.0,
|
|
"step": 44780
|
|
},
|
|
{
|
|
"entropy": 5.117826128005982,
|
|
"epoch": 4.302113352545629,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032772020331894776,
|
|
"loss": 4.5881,
|
|
"mean_token_accuracy": 0.2585404947400093,
|
|
"num_tokens": 102692972.0,
|
|
"step": 44785
|
|
},
|
|
{
|
|
"entropy": 5.1412575244903564,
|
|
"epoch": 4.302593659942363,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003276868735561491,
|
|
"loss": 4.5365,
|
|
"mean_token_accuracy": 0.2551713988184929,
|
|
"num_tokens": 102705739.0,
|
|
"step": 44790
|
|
},
|
|
{
|
|
"entropy": 5.1232420921325685,
|
|
"epoch": 4.303073967339097,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032765354257011765,
|
|
"loss": 4.5381,
|
|
"mean_token_accuracy": 0.26305015981197355,
|
|
"num_tokens": 102716368.0,
|
|
"step": 44795
|
|
},
|
|
{
|
|
"entropy": 5.1053508758544925,
|
|
"epoch": 4.303554274735831,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00032762021036162735,
|
|
"loss": 4.6388,
|
|
"mean_token_accuracy": 0.2560013860464096,
|
|
"num_tokens": 102729920.0,
|
|
"step": 44800
|
|
},
|
|
{
|
|
"entropy": 5.164723348617554,
|
|
"epoch": 4.304034582132565,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003275868769314521,
|
|
"loss": 4.606,
|
|
"mean_token_accuracy": 0.25620581656694413,
|
|
"num_tokens": 102740374.0,
|
|
"step": 44805
|
|
},
|
|
{
|
|
"entropy": 5.175257921218872,
|
|
"epoch": 4.304514889529298,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00032755354228036554,
|
|
"loss": 4.6361,
|
|
"mean_token_accuracy": 0.25305969417095187,
|
|
"num_tokens": 102750820.0,
|
|
"step": 44810
|
|
},
|
|
{
|
|
"entropy": 5.161873149871826,
|
|
"epoch": 4.304995196926033,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003275202064091419,
|
|
"loss": 4.592,
|
|
"mean_token_accuracy": 0.25879642069339753,
|
|
"num_tokens": 102761312.0,
|
|
"step": 44815
|
|
},
|
|
{
|
|
"entropy": 5.123553609848022,
|
|
"epoch": 4.305475504322766,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00032748686931855495,
|
|
"loss": 4.5748,
|
|
"mean_token_accuracy": 0.25947224646806716,
|
|
"num_tokens": 102772288.0,
|
|
"step": 44820
|
|
},
|
|
{
|
|
"entropy": 5.139647960662842,
|
|
"epoch": 4.3059558117195005,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003274535310093788,
|
|
"loss": 4.5193,
|
|
"mean_token_accuracy": 0.26460920870304105,
|
|
"num_tokens": 102783533.0,
|
|
"step": 44825
|
|
},
|
|
{
|
|
"entropy": 5.162225341796875,
|
|
"epoch": 4.306436119116235,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003274201914823874,
|
|
"loss": 4.5761,
|
|
"mean_token_accuracy": 0.2662114813923836,
|
|
"num_tokens": 102795940.0,
|
|
"step": 44830
|
|
},
|
|
{
|
|
"entropy": 5.084526443481446,
|
|
"epoch": 4.306916426512968,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032738685073835475,
|
|
"loss": 4.5692,
|
|
"mean_token_accuracy": 0.2667840138077736,
|
|
"num_tokens": 102807507.0,
|
|
"step": 44835
|
|
},
|
|
{
|
|
"entropy": 5.0698121070861815,
|
|
"epoch": 4.307396733909703,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000327353508778055,
|
|
"loss": 4.4963,
|
|
"mean_token_accuracy": 0.26962788552045824,
|
|
"num_tokens": 102817895.0,
|
|
"step": 44840
|
|
},
|
|
{
|
|
"entropy": 5.158780288696289,
|
|
"epoch": 4.307877041306436,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00032732016560226235,
|
|
"loss": 4.5845,
|
|
"mean_token_accuracy": 0.2541725650429726,
|
|
"num_tokens": 102829141.0,
|
|
"step": 44845
|
|
},
|
|
{
|
|
"entropy": 5.1288471698760985,
|
|
"epoch": 4.30835734870317,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00032728682121175077,
|
|
"loss": 4.5834,
|
|
"mean_token_accuracy": 0.26409475654363634,
|
|
"num_tokens": 102841488.0,
|
|
"step": 44850
|
|
},
|
|
{
|
|
"entropy": 5.099828147888184,
|
|
"epoch": 4.308837656099904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032725347560729433,
|
|
"loss": 4.6051,
|
|
"mean_token_accuracy": 0.2601136893033981,
|
|
"num_tokens": 102853276.0,
|
|
"step": 44855
|
|
},
|
|
{
|
|
"entropy": 5.099416637420655,
|
|
"epoch": 4.309317963496638,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00032722012878966744,
|
|
"loss": 4.5613,
|
|
"mean_token_accuracy": 0.2594709530472755,
|
|
"num_tokens": 102864850.0,
|
|
"step": 44860
|
|
},
|
|
{
|
|
"entropy": 5.140852355957032,
|
|
"epoch": 4.3097982708933715,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032718678075964425,
|
|
"loss": 4.591,
|
|
"mean_token_accuracy": 0.257270647585392,
|
|
"num_tokens": 102876692.0,
|
|
"step": 44865
|
|
},
|
|
{
|
|
"entropy": 5.1164299011230465,
|
|
"epoch": 4.310278578290106,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003271534315179989,
|
|
"loss": 4.5465,
|
|
"mean_token_accuracy": 0.2640973970293999,
|
|
"num_tokens": 102887693.0,
|
|
"step": 44870
|
|
},
|
|
{
|
|
"entropy": 5.119435167312622,
|
|
"epoch": 4.310758885686839,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00032712008106550584,
|
|
"loss": 4.5993,
|
|
"mean_token_accuracy": 0.25915137976408004,
|
|
"num_tokens": 102900493.0,
|
|
"step": 44875
|
|
},
|
|
{
|
|
"entropy": 5.160337018966675,
|
|
"epoch": 4.311239193083574,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00032708672940293923,
|
|
"loss": 4.5914,
|
|
"mean_token_accuracy": 0.259625555574894,
|
|
"num_tokens": 102911983.0,
|
|
"step": 44880
|
|
},
|
|
{
|
|
"entropy": 5.109876441955566,
|
|
"epoch": 4.311719500480307,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00032705337653107336,
|
|
"loss": 4.5021,
|
|
"mean_token_accuracy": 0.27168766856193544,
|
|
"num_tokens": 102923204.0,
|
|
"step": 44885
|
|
},
|
|
{
|
|
"entropy": 5.144802188873291,
|
|
"epoch": 4.312199807877041,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00032702002245068267,
|
|
"loss": 4.6203,
|
|
"mean_token_accuracy": 0.25144919455051423,
|
|
"num_tokens": 102934091.0,
|
|
"step": 44890
|
|
},
|
|
{
|
|
"entropy": 5.08544511795044,
|
|
"epoch": 4.312680115273775,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00032698666716254155,
|
|
"loss": 4.4882,
|
|
"mean_token_accuracy": 0.26623758524656294,
|
|
"num_tokens": 102946044.0,
|
|
"step": 44895
|
|
},
|
|
{
|
|
"entropy": 5.249974536895752,
|
|
"epoch": 4.313160422670509,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003269533106674244,
|
|
"loss": 4.7258,
|
|
"mean_token_accuracy": 0.25205339938402177,
|
|
"num_tokens": 102957399.0,
|
|
"step": 44900
|
|
},
|
|
{
|
|
"entropy": 5.130836391448975,
|
|
"epoch": 4.3136407300672435,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00032691995296610566,
|
|
"loss": 4.545,
|
|
"mean_token_accuracy": 0.2658742070198059,
|
|
"num_tokens": 102968757.0,
|
|
"step": 44905
|
|
},
|
|
{
|
|
"entropy": 5.091643047332764,
|
|
"epoch": 4.314121037463977,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00032688659405935973,
|
|
"loss": 4.51,
|
|
"mean_token_accuracy": 0.2669142097234726,
|
|
"num_tokens": 102980128.0,
|
|
"step": 44910
|
|
},
|
|
{
|
|
"entropy": 5.144875335693359,
|
|
"epoch": 4.314601344860711,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003268532339479612,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.25975285321474073,
|
|
"num_tokens": 102990951.0,
|
|
"step": 44915
|
|
},
|
|
{
|
|
"entropy": 5.060215139389038,
|
|
"epoch": 4.315081652257445,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003268198726326846,
|
|
"loss": 4.563,
|
|
"mean_token_accuracy": 0.26363605856895445,
|
|
"num_tokens": 103003911.0,
|
|
"step": 44920
|
|
},
|
|
{
|
|
"entropy": 5.176715230941772,
|
|
"epoch": 4.315561959654179,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003267865101143043,
|
|
"loss": 4.5652,
|
|
"mean_token_accuracy": 0.2644235551357269,
|
|
"num_tokens": 103015584.0,
|
|
"step": 44925
|
|
},
|
|
{
|
|
"entropy": 5.1711273193359375,
|
|
"epoch": 4.316042267050912,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032675314639359505,
|
|
"loss": 4.6022,
|
|
"mean_token_accuracy": 0.2720270067453384,
|
|
"num_tokens": 103027632.0,
|
|
"step": 44930
|
|
},
|
|
{
|
|
"entropy": 5.124931859970093,
|
|
"epoch": 4.316522574447647,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003267197814713315,
|
|
"loss": 4.5505,
|
|
"mean_token_accuracy": 0.26373723447322844,
|
|
"num_tokens": 103037784.0,
|
|
"step": 44935
|
|
},
|
|
{
|
|
"entropy": 5.091759967803955,
|
|
"epoch": 4.31700288184438,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032668641534828807,
|
|
"loss": 4.5264,
|
|
"mean_token_accuracy": 0.2652961537241936,
|
|
"num_tokens": 103048753.0,
|
|
"step": 44940
|
|
},
|
|
{
|
|
"entropy": 5.089973020553589,
|
|
"epoch": 4.3174831892411145,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00032665304802523965,
|
|
"loss": 4.6008,
|
|
"mean_token_accuracy": 0.25773108154535296,
|
|
"num_tokens": 103061372.0,
|
|
"step": 44945
|
|
},
|
|
{
|
|
"entropy": 5.119861698150634,
|
|
"epoch": 4.317963496637848,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00032661967950296084,
|
|
"loss": 4.5701,
|
|
"mean_token_accuracy": 0.2638323500752449,
|
|
"num_tokens": 103074791.0,
|
|
"step": 44950
|
|
},
|
|
{
|
|
"entropy": 5.119975900650024,
|
|
"epoch": 4.318443804034582,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003265863097822263,
|
|
"loss": 4.5813,
|
|
"mean_token_accuracy": 0.26476564109325407,
|
|
"num_tokens": 103086790.0,
|
|
"step": 44955
|
|
},
|
|
{
|
|
"entropy": 5.132070636749267,
|
|
"epoch": 4.318924111431316,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032655293886381083,
|
|
"loss": 4.5615,
|
|
"mean_token_accuracy": 0.2582272306084633,
|
|
"num_tokens": 103097819.0,
|
|
"step": 44960
|
|
},
|
|
{
|
|
"entropy": 5.136992597579956,
|
|
"epoch": 4.31940441882805,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003265195667484892,
|
|
"loss": 4.6325,
|
|
"mean_token_accuracy": 0.2597150862216949,
|
|
"num_tokens": 103110071.0,
|
|
"step": 44965
|
|
},
|
|
{
|
|
"entropy": 5.095218515396118,
|
|
"epoch": 4.3198847262247835,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00032648619343703626,
|
|
"loss": 4.5625,
|
|
"mean_token_accuracy": 0.27041689604520797,
|
|
"num_tokens": 103122586.0,
|
|
"step": 44970
|
|
},
|
|
{
|
|
"entropy": 5.13352484703064,
|
|
"epoch": 4.320365033621518,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003264528189302267,
|
|
"loss": 4.5425,
|
|
"mean_token_accuracy": 0.26552431136369703,
|
|
"num_tokens": 103133531.0,
|
|
"step": 44975
|
|
},
|
|
{
|
|
"entropy": 5.058735704421997,
|
|
"epoch": 4.320845341018252,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00032641944322883557,
|
|
"loss": 4.4867,
|
|
"mean_token_accuracy": 0.27394428849220276,
|
|
"num_tokens": 103144099.0,
|
|
"step": 44980
|
|
},
|
|
{
|
|
"entropy": 5.072891664505005,
|
|
"epoch": 4.321325648414986,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003263860663336376,
|
|
"loss": 4.524,
|
|
"mean_token_accuracy": 0.2638663798570633,
|
|
"num_tokens": 103156221.0,
|
|
"step": 44985
|
|
},
|
|
{
|
|
"entropy": 5.113881397247314,
|
|
"epoch": 4.32180595581172,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00032635268824540774,
|
|
"loss": 4.4841,
|
|
"mean_token_accuracy": 0.2756052166223526,
|
|
"num_tokens": 103167121.0,
|
|
"step": 44990
|
|
},
|
|
{
|
|
"entropy": 5.225774574279785,
|
|
"epoch": 4.322286263208453,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00032631930896492097,
|
|
"loss": 4.656,
|
|
"mean_token_accuracy": 0.25423858761787416,
|
|
"num_tokens": 103178169.0,
|
|
"step": 44995
|
|
},
|
|
{
|
|
"entropy": 5.131777000427246,
|
|
"epoch": 4.322766570605188,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003262859284929522,
|
|
"loss": 4.6059,
|
|
"mean_token_accuracy": 0.2567624270915985,
|
|
"num_tokens": 103190790.0,
|
|
"step": 45000
|
|
},
|
|
{
|
|
"epoch": 4.322766570605188,
|
|
"eval_entropy": 4.9327421295881155,
|
|
"eval_loss": 4.727368354797363,
|
|
"eval_mean_token_accuracy": 0.2603322069071186,
|
|
"eval_num_tokens": 103190790.0,
|
|
"eval_runtime": 26.5575,
|
|
"eval_samples_per_second": 1235.62,
|
|
"eval_steps_per_second": 154.457,
|
|
"step": 45000
|
|
},
|
|
{
|
|
"entropy": 5.121899795532227,
|
|
"epoch": 4.323246878001921,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003262525468302765,
|
|
"loss": 4.54,
|
|
"mean_token_accuracy": 0.2681977942585945,
|
|
"num_tokens": 103201993.0,
|
|
"step": 45005
|
|
},
|
|
{
|
|
"entropy": 5.1229323387146,
|
|
"epoch": 4.323727185398655,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003262191639776689,
|
|
"loss": 4.5513,
|
|
"mean_token_accuracy": 0.26631470769643784,
|
|
"num_tokens": 103213938.0,
|
|
"step": 45010
|
|
},
|
|
{
|
|
"entropy": 5.089220428466797,
|
|
"epoch": 4.324207492795389,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003261857799359043,
|
|
"loss": 4.5287,
|
|
"mean_token_accuracy": 0.2605724647641182,
|
|
"num_tokens": 103227098.0,
|
|
"step": 45015
|
|
},
|
|
{
|
|
"entropy": 5.116297483444214,
|
|
"epoch": 4.324687800192123,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003261523947057579,
|
|
"loss": 4.5783,
|
|
"mean_token_accuracy": 0.2577955797314644,
|
|
"num_tokens": 103239811.0,
|
|
"step": 45020
|
|
},
|
|
{
|
|
"entropy": 5.227082252502441,
|
|
"epoch": 4.325168107588857,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003261190082880048,
|
|
"loss": 4.7028,
|
|
"mean_token_accuracy": 0.25196167081594467,
|
|
"num_tokens": 103252160.0,
|
|
"step": 45025
|
|
},
|
|
{
|
|
"entropy": 5.2306548118591305,
|
|
"epoch": 4.325648414985591,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003260856206834201,
|
|
"loss": 4.6944,
|
|
"mean_token_accuracy": 0.25642327666282655,
|
|
"num_tokens": 103262752.0,
|
|
"step": 45030
|
|
},
|
|
{
|
|
"entropy": 5.126266622543335,
|
|
"epoch": 4.326128722382324,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032605223189277903,
|
|
"loss": 4.5938,
|
|
"mean_token_accuracy": 0.2624508231878281,
|
|
"num_tokens": 103274539.0,
|
|
"step": 45035
|
|
},
|
|
{
|
|
"entropy": 5.225788545608521,
|
|
"epoch": 4.326609029779059,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003260188419168568,
|
|
"loss": 4.6497,
|
|
"mean_token_accuracy": 0.255837045609951,
|
|
"num_tokens": 103285929.0,
|
|
"step": 45040
|
|
},
|
|
{
|
|
"entropy": 5.164557027816772,
|
|
"epoch": 4.327089337175792,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00032598545075642843,
|
|
"loss": 4.5789,
|
|
"mean_token_accuracy": 0.2552909359335899,
|
|
"num_tokens": 103297710.0,
|
|
"step": 45045
|
|
},
|
|
{
|
|
"entropy": 5.1637955665588375,
|
|
"epoch": 4.3275696445725265,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003259520584122693,
|
|
"loss": 4.6244,
|
|
"mean_token_accuracy": 0.2581389665603638,
|
|
"num_tokens": 103310080.0,
|
|
"step": 45050
|
|
},
|
|
{
|
|
"entropy": 5.1675488471984865,
|
|
"epoch": 4.328049951969261,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003259186648851547,
|
|
"loss": 4.5925,
|
|
"mean_token_accuracy": 0.266055591404438,
|
|
"num_tokens": 103322660.0,
|
|
"step": 45055
|
|
},
|
|
{
|
|
"entropy": 5.141082811355591,
|
|
"epoch": 4.328530259365994,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003258852701758599,
|
|
"loss": 4.5621,
|
|
"mean_token_accuracy": 0.260493566095829,
|
|
"num_tokens": 103335302.0,
|
|
"step": 45060
|
|
},
|
|
{
|
|
"entropy": 5.110651683807373,
|
|
"epoch": 4.3290105667627286,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003258518742851602,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.26515663266181944,
|
|
"num_tokens": 103346957.0,
|
|
"step": 45065
|
|
},
|
|
{
|
|
"entropy": 5.163241672515869,
|
|
"epoch": 4.329490874159462,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000325818477213831,
|
|
"loss": 4.5827,
|
|
"mean_token_accuracy": 0.26180239021778107,
|
|
"num_tokens": 103359003.0,
|
|
"step": 45070
|
|
},
|
|
{
|
|
"entropy": 5.14492826461792,
|
|
"epoch": 4.329971181556196,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003257850789626477,
|
|
"loss": 4.6248,
|
|
"mean_token_accuracy": 0.26651097685098646,
|
|
"num_tokens": 103370407.0,
|
|
"step": 45075
|
|
},
|
|
{
|
|
"entropy": 5.221707201004028,
|
|
"epoch": 4.33045148895293,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003257516795323856,
|
|
"loss": 4.7319,
|
|
"mean_token_accuracy": 0.24721643477678298,
|
|
"num_tokens": 103382524.0,
|
|
"step": 45080
|
|
},
|
|
{
|
|
"entropy": 5.2844781398773195,
|
|
"epoch": 4.330931796349664,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032571827892382014,
|
|
"loss": 4.6937,
|
|
"mean_token_accuracy": 0.2572362646460533,
|
|
"num_tokens": 103393685.0,
|
|
"step": 45085
|
|
},
|
|
{
|
|
"entropy": 5.09454574584961,
|
|
"epoch": 4.3314121037463975,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000325684877137727,
|
|
"loss": 4.4577,
|
|
"mean_token_accuracy": 0.26369232684373856,
|
|
"num_tokens": 103404105.0,
|
|
"step": 45090
|
|
},
|
|
{
|
|
"entropy": 5.176066827774048,
|
|
"epoch": 4.331892411143132,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003256514741748814,
|
|
"loss": 4.6987,
|
|
"mean_token_accuracy": 0.25466942191123965,
|
|
"num_tokens": 103415765.0,
|
|
"step": 45095
|
|
},
|
|
{
|
|
"entropy": 5.076482629776001,
|
|
"epoch": 4.332372718539865,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003256180700360591,
|
|
"loss": 4.5688,
|
|
"mean_token_accuracy": 0.26159380227327345,
|
|
"num_tokens": 103426490.0,
|
|
"step": 45100
|
|
},
|
|
{
|
|
"entropy": 5.125519561767578,
|
|
"epoch": 4.3328530259366,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003255846647220354,
|
|
"loss": 4.524,
|
|
"mean_token_accuracy": 0.2642716631293297,
|
|
"num_tokens": 103437864.0,
|
|
"step": 45105
|
|
},
|
|
{
|
|
"entropy": 5.1267036437988285,
|
|
"epoch": 4.333333333333333,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00032555125823358603,
|
|
"loss": 4.5642,
|
|
"mean_token_accuracy": 0.26120612025260925,
|
|
"num_tokens": 103450119.0,
|
|
"step": 45110
|
|
},
|
|
{
|
|
"entropy": 5.112438154220581,
|
|
"epoch": 4.333813640730067,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003255178505714866,
|
|
"loss": 4.5569,
|
|
"mean_token_accuracy": 0.2649544060230255,
|
|
"num_tokens": 103461220.0,
|
|
"step": 45115
|
|
},
|
|
{
|
|
"entropy": 5.190648412704467,
|
|
"epoch": 4.334293948126801,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003254844417365126,
|
|
"loss": 4.61,
|
|
"mean_token_accuracy": 0.2625638872385025,
|
|
"num_tokens": 103473375.0,
|
|
"step": 45120
|
|
},
|
|
{
|
|
"entropy": 5.10969181060791,
|
|
"epoch": 4.334774255523535,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003254510317294398,
|
|
"loss": 4.5644,
|
|
"mean_token_accuracy": 0.2615906223654747,
|
|
"num_tokens": 103484575.0,
|
|
"step": 45125
|
|
},
|
|
{
|
|
"entropy": 5.106466674804688,
|
|
"epoch": 4.335254562920269,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032541762055104386,
|
|
"loss": 4.557,
|
|
"mean_token_accuracy": 0.25995701998472215,
|
|
"num_tokens": 103496005.0,
|
|
"step": 45130
|
|
},
|
|
{
|
|
"entropy": 5.107123994827271,
|
|
"epoch": 4.335734870317003,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00032538420820210054,
|
|
"loss": 4.5166,
|
|
"mean_token_accuracy": 0.26864760369062424,
|
|
"num_tokens": 103506795.0,
|
|
"step": 45135
|
|
},
|
|
{
|
|
"entropy": 5.10040249824524,
|
|
"epoch": 4.336215177713736,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003253507946833854,
|
|
"loss": 4.5445,
|
|
"mean_token_accuracy": 0.2599660575389862,
|
|
"num_tokens": 103518698.0,
|
|
"step": 45140
|
|
},
|
|
{
|
|
"entropy": 5.174502992630005,
|
|
"epoch": 4.336695485110471,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003253173799956744,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.2648267596960068,
|
|
"num_tokens": 103529261.0,
|
|
"step": 45145
|
|
},
|
|
{
|
|
"entropy": 5.142105293273926,
|
|
"epoch": 4.337175792507205,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003252839641397432,
|
|
"loss": 4.5673,
|
|
"mean_token_accuracy": 0.26696389764547346,
|
|
"num_tokens": 103540823.0,
|
|
"step": 45150
|
|
},
|
|
{
|
|
"entropy": 5.055416107177734,
|
|
"epoch": 4.337656099903938,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003252505471163677,
|
|
"loss": 4.529,
|
|
"mean_token_accuracy": 0.26533314138650893,
|
|
"num_tokens": 103552097.0,
|
|
"step": 45155
|
|
},
|
|
{
|
|
"entropy": 5.145941162109375,
|
|
"epoch": 4.338136407300673,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00032521712892632365,
|
|
"loss": 4.5921,
|
|
"mean_token_accuracy": 0.25678353011608124,
|
|
"num_tokens": 103563836.0,
|
|
"step": 45160
|
|
},
|
|
{
|
|
"entropy": 5.075289344787597,
|
|
"epoch": 4.338616714697406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003251837095703871,
|
|
"loss": 4.4592,
|
|
"mean_token_accuracy": 0.2743435978889465,
|
|
"num_tokens": 103574925.0,
|
|
"step": 45165
|
|
},
|
|
{
|
|
"entropy": 5.235349988937378,
|
|
"epoch": 4.3390970220941405,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00032515028904933375,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.2508653953671455,
|
|
"num_tokens": 103586304.0,
|
|
"step": 45170
|
|
},
|
|
{
|
|
"entropy": 5.167155647277832,
|
|
"epoch": 4.339577329490874,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003251168673639396,
|
|
"loss": 4.5511,
|
|
"mean_token_accuracy": 0.26754301935434344,
|
|
"num_tokens": 103597326.0,
|
|
"step": 45175
|
|
},
|
|
{
|
|
"entropy": 5.149952983856201,
|
|
"epoch": 4.340057636887608,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00032508344451498064,
|
|
"loss": 4.6478,
|
|
"mean_token_accuracy": 0.2510245144367218,
|
|
"num_tokens": 103608688.0,
|
|
"step": 45180
|
|
},
|
|
{
|
|
"entropy": 5.126709127426148,
|
|
"epoch": 4.340537944284342,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003250500205032328,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.2650327533483505,
|
|
"num_tokens": 103619521.0,
|
|
"step": 45185
|
|
},
|
|
{
|
|
"entropy": 5.159747314453125,
|
|
"epoch": 4.341018251681076,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032501659532947205,
|
|
"loss": 4.5665,
|
|
"mean_token_accuracy": 0.2604525551199913,
|
|
"num_tokens": 103631829.0,
|
|
"step": 45190
|
|
},
|
|
{
|
|
"entropy": 5.191273546218872,
|
|
"epoch": 4.3414985590778095,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00032498316899447454,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.25226098150014875,
|
|
"num_tokens": 103642417.0,
|
|
"step": 45195
|
|
},
|
|
{
|
|
"entropy": 5.06522274017334,
|
|
"epoch": 4.341978866474544,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032494974149901626,
|
|
"loss": 4.5016,
|
|
"mean_token_accuracy": 0.2691427022218704,
|
|
"num_tokens": 103653921.0,
|
|
"step": 45200
|
|
},
|
|
{
|
|
"entropy": 5.0457048416137695,
|
|
"epoch": 4.342459173871277,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003249163128438732,
|
|
"loss": 4.498,
|
|
"mean_token_accuracy": 0.2706316590309143,
|
|
"num_tokens": 103665917.0,
|
|
"step": 45205
|
|
},
|
|
{
|
|
"entropy": 5.124253463745117,
|
|
"epoch": 4.3429394812680115,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032488288302982176,
|
|
"loss": 4.5895,
|
|
"mean_token_accuracy": 0.25963430404663085,
|
|
"num_tokens": 103676353.0,
|
|
"step": 45210
|
|
},
|
|
{
|
|
"entropy": 5.193014192581177,
|
|
"epoch": 4.343419788664745,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003248494520576378,
|
|
"loss": 4.634,
|
|
"mean_token_accuracy": 0.25765449106693267,
|
|
"num_tokens": 103688334.0,
|
|
"step": 45215
|
|
},
|
|
{
|
|
"entropy": 5.13427472114563,
|
|
"epoch": 4.343900096061479,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032481601992809754,
|
|
"loss": 4.5256,
|
|
"mean_token_accuracy": 0.263341423869133,
|
|
"num_tokens": 103699853.0,
|
|
"step": 45220
|
|
},
|
|
{
|
|
"entropy": 5.154639196395874,
|
|
"epoch": 4.344380403458214,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003247825866419773,
|
|
"loss": 4.5116,
|
|
"mean_token_accuracy": 0.26057074069976804,
|
|
"num_tokens": 103709891.0,
|
|
"step": 45225
|
|
},
|
|
{
|
|
"entropy": 5.0653440952301025,
|
|
"epoch": 4.344860710854947,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00032474915220005317,
|
|
"loss": 4.5216,
|
|
"mean_token_accuracy": 0.26916786581277846,
|
|
"num_tokens": 103721154.0,
|
|
"step": 45230
|
|
},
|
|
{
|
|
"entropy": 5.190094232559204,
|
|
"epoch": 4.345341018251681,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00032471571660310145,
|
|
"loss": 4.6359,
|
|
"mean_token_accuracy": 0.25880090296268465,
|
|
"num_tokens": 103732831.0,
|
|
"step": 45235
|
|
},
|
|
{
|
|
"entropy": 5.112931442260742,
|
|
"epoch": 4.345821325648415,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003246822798518985,
|
|
"loss": 4.5167,
|
|
"mean_token_accuracy": 0.2637990042567253,
|
|
"num_tokens": 103745392.0,
|
|
"step": 45240
|
|
},
|
|
{
|
|
"entropy": 5.129172992706299,
|
|
"epoch": 4.346301633045149,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032464884194722046,
|
|
"loss": 4.546,
|
|
"mean_token_accuracy": 0.258742056787014,
|
|
"num_tokens": 103757191.0,
|
|
"step": 45245
|
|
},
|
|
{
|
|
"entropy": 5.124163103103638,
|
|
"epoch": 4.346781940441883,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032461540288984377,
|
|
"loss": 4.6006,
|
|
"mean_token_accuracy": 0.2587746247649193,
|
|
"num_tokens": 103769434.0,
|
|
"step": 45250
|
|
},
|
|
{
|
|
"entropy": 5.19899263381958,
|
|
"epoch": 4.347262247838617,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003245819626805447,
|
|
"loss": 4.6959,
|
|
"mean_token_accuracy": 0.25629512369632723,
|
|
"num_tokens": 103780906.0,
|
|
"step": 45255
|
|
},
|
|
{
|
|
"entropy": 5.142866754531861,
|
|
"epoch": 4.34774255523535,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00032454852132009974,
|
|
"loss": 4.5904,
|
|
"mean_token_accuracy": 0.2595141351222992,
|
|
"num_tokens": 103791998.0,
|
|
"step": 45260
|
|
},
|
|
{
|
|
"entropy": 5.11989541053772,
|
|
"epoch": 4.348222862632085,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003245150788092852,
|
|
"loss": 4.54,
|
|
"mean_token_accuracy": 0.266022139787674,
|
|
"num_tokens": 103804401.0,
|
|
"step": 45265
|
|
},
|
|
{
|
|
"entropy": 5.112265348434448,
|
|
"epoch": 4.348703170028818,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00032448163514887756,
|
|
"loss": 4.5527,
|
|
"mean_token_accuracy": 0.2612640172243118,
|
|
"num_tokens": 103815774.0,
|
|
"step": 45270
|
|
},
|
|
{
|
|
"entropy": 5.148935031890869,
|
|
"epoch": 4.3491834774255524,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003244481903396533,
|
|
"loss": 4.5543,
|
|
"mean_token_accuracy": 0.2598469197750092,
|
|
"num_tokens": 103827370.0,
|
|
"step": 45275
|
|
},
|
|
{
|
|
"entropy": 5.1398584842681885,
|
|
"epoch": 4.349663784822286,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032441474438238893,
|
|
"loss": 4.5398,
|
|
"mean_token_accuracy": 0.2674246788024902,
|
|
"num_tokens": 103839102.0,
|
|
"step": 45280
|
|
},
|
|
{
|
|
"entropy": 5.1250945091247555,
|
|
"epoch": 4.35014409221902,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003243812972778609,
|
|
"loss": 4.5937,
|
|
"mean_token_accuracy": 0.2571921080350876,
|
|
"num_tokens": 103852014.0,
|
|
"step": 45285
|
|
},
|
|
{
|
|
"entropy": 5.086808919906616,
|
|
"epoch": 4.350624399615754,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00032434784902684574,
|
|
"loss": 4.5344,
|
|
"mean_token_accuracy": 0.26778060346841814,
|
|
"num_tokens": 103865308.0,
|
|
"step": 45290
|
|
},
|
|
{
|
|
"entropy": 5.12885422706604,
|
|
"epoch": 4.351104707012488,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00032431439963012004,
|
|
"loss": 4.5731,
|
|
"mean_token_accuracy": 0.2581255570054054,
|
|
"num_tokens": 103877961.0,
|
|
"step": 45295
|
|
},
|
|
{
|
|
"entropy": 5.086838674545288,
|
|
"epoch": 4.351585014409222,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003242809490884605,
|
|
"loss": 4.5254,
|
|
"mean_token_accuracy": 0.2624689728021622,
|
|
"num_tokens": 103888625.0,
|
|
"step": 45300
|
|
},
|
|
{
|
|
"entropy": 5.015859889984131,
|
|
"epoch": 4.352065321805956,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003242474974026436,
|
|
"loss": 4.4669,
|
|
"mean_token_accuracy": 0.2705911919474602,
|
|
"num_tokens": 103899177.0,
|
|
"step": 45305
|
|
},
|
|
{
|
|
"entropy": 5.120817470550537,
|
|
"epoch": 4.35254562920269,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003242140445734461,
|
|
"loss": 4.5377,
|
|
"mean_token_accuracy": 0.2719808667898178,
|
|
"num_tokens": 103909687.0,
|
|
"step": 45310
|
|
},
|
|
{
|
|
"entropy": 5.104394245147705,
|
|
"epoch": 4.3530259365994235,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032418059060164455,
|
|
"loss": 4.5939,
|
|
"mean_token_accuracy": 0.26220355182886124,
|
|
"num_tokens": 103921137.0,
|
|
"step": 45315
|
|
},
|
|
{
|
|
"entropy": 5.174837923049926,
|
|
"epoch": 4.353506243996158,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032414713548801577,
|
|
"loss": 4.6449,
|
|
"mean_token_accuracy": 0.25304549038410185,
|
|
"num_tokens": 103934014.0,
|
|
"step": 45320
|
|
},
|
|
{
|
|
"entropy": 5.175307416915894,
|
|
"epoch": 4.353986551392891,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00032411367923333646,
|
|
"loss": 4.5348,
|
|
"mean_token_accuracy": 0.2667503371834755,
|
|
"num_tokens": 103945824.0,
|
|
"step": 45325
|
|
},
|
|
{
|
|
"entropy": 5.1679408073425295,
|
|
"epoch": 4.354466858789626,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00032408022183838336,
|
|
"loss": 4.4661,
|
|
"mean_token_accuracy": 0.2682728886604309,
|
|
"num_tokens": 103956880.0,
|
|
"step": 45330
|
|
},
|
|
{
|
|
"entropy": 5.104145574569702,
|
|
"epoch": 4.354947166186359,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00032404676330393317,
|
|
"loss": 4.5395,
|
|
"mean_token_accuracy": 0.2667120024561882,
|
|
"num_tokens": 103967663.0,
|
|
"step": 45335
|
|
},
|
|
{
|
|
"entropy": 5.139591264724731,
|
|
"epoch": 4.355427473583093,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003240133036307628,
|
|
"loss": 4.6637,
|
|
"mean_token_accuracy": 0.24927813559770584,
|
|
"num_tokens": 103978736.0,
|
|
"step": 45340
|
|
},
|
|
{
|
|
"entropy": 5.056731796264648,
|
|
"epoch": 4.355907780979827,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003239798428196491,
|
|
"loss": 4.5193,
|
|
"mean_token_accuracy": 0.26448694318532945,
|
|
"num_tokens": 103990777.0,
|
|
"step": 45345
|
|
},
|
|
{
|
|
"entropy": 5.123390007019043,
|
|
"epoch": 4.356388088376561,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00032394638087136887,
|
|
"loss": 4.5751,
|
|
"mean_token_accuracy": 0.26253298819065096,
|
|
"num_tokens": 104002563.0,
|
|
"step": 45350
|
|
},
|
|
{
|
|
"entropy": 5.110266780853271,
|
|
"epoch": 4.3568683957732945,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000323912917786699,
|
|
"loss": 4.5618,
|
|
"mean_token_accuracy": 0.25790089964866636,
|
|
"num_tokens": 104013955.0,
|
|
"step": 45355
|
|
},
|
|
{
|
|
"entropy": 5.151379632949829,
|
|
"epoch": 4.357348703170029,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00032387945356641653,
|
|
"loss": 4.5972,
|
|
"mean_token_accuracy": 0.25633339285850526,
|
|
"num_tokens": 104026086.0,
|
|
"step": 45360
|
|
},
|
|
{
|
|
"entropy": 5.223532819747925,
|
|
"epoch": 4.357829010566762,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003238459882112981,
|
|
"loss": 4.6753,
|
|
"mean_token_accuracy": 0.2584083124995232,
|
|
"num_tokens": 104038235.0,
|
|
"step": 45365
|
|
},
|
|
{
|
|
"entropy": 5.053296804428101,
|
|
"epoch": 4.358309317963497,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000323812521722121,
|
|
"loss": 4.488,
|
|
"mean_token_accuracy": 0.27229219675064087,
|
|
"num_tokens": 104049574.0,
|
|
"step": 45370
|
|
},
|
|
{
|
|
"entropy": 5.046627950668335,
|
|
"epoch": 4.358789625360231,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003237790540996621,
|
|
"loss": 4.5486,
|
|
"mean_token_accuracy": 0.2661864012479782,
|
|
"num_tokens": 104060715.0,
|
|
"step": 45375
|
|
},
|
|
{
|
|
"entropy": 5.0970665454864506,
|
|
"epoch": 4.359269932756964,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00032374558534469834,
|
|
"loss": 4.5657,
|
|
"mean_token_accuracy": 0.26388305276632307,
|
|
"num_tokens": 104074234.0,
|
|
"step": 45380
|
|
},
|
|
{
|
|
"entropy": 5.149909830093383,
|
|
"epoch": 4.359750240153699,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003237121154580068,
|
|
"loss": 4.5641,
|
|
"mean_token_accuracy": 0.26326156556606295,
|
|
"num_tokens": 104084725.0,
|
|
"step": 45385
|
|
},
|
|
{
|
|
"entropy": 5.085016345977783,
|
|
"epoch": 4.360230547550432,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00032367864444036467,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.26648872196674345,
|
|
"num_tokens": 104096816.0,
|
|
"step": 45390
|
|
},
|
|
{
|
|
"entropy": 5.2156431674957275,
|
|
"epoch": 4.3607108549471665,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00032364517229254894,
|
|
"loss": 4.696,
|
|
"mean_token_accuracy": 0.2454624131321907,
|
|
"num_tokens": 104108869.0,
|
|
"step": 45395
|
|
},
|
|
{
|
|
"entropy": 5.203935384750366,
|
|
"epoch": 4.3611911623439,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00032361169901533673,
|
|
"loss": 4.6379,
|
|
"mean_token_accuracy": 0.2618664145469666,
|
|
"num_tokens": 104120556.0,
|
|
"step": 45400
|
|
},
|
|
{
|
|
"entropy": 5.100205516815185,
|
|
"epoch": 4.361671469740634,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032357822460950524,
|
|
"loss": 4.5145,
|
|
"mean_token_accuracy": 0.2658519342541695,
|
|
"num_tokens": 104132253.0,
|
|
"step": 45405
|
|
},
|
|
{
|
|
"entropy": 5.1291344165802,
|
|
"epoch": 4.362151777137368,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003235447490758316,
|
|
"loss": 4.5949,
|
|
"mean_token_accuracy": 0.25924462229013445,
|
|
"num_tokens": 104143211.0,
|
|
"step": 45410
|
|
},
|
|
{
|
|
"entropy": 5.099362087249756,
|
|
"epoch": 4.362632084534102,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032351127241509305,
|
|
"loss": 4.4485,
|
|
"mean_token_accuracy": 0.27153968513011933,
|
|
"num_tokens": 104154482.0,
|
|
"step": 45415
|
|
},
|
|
{
|
|
"entropy": 5.2169393539428714,
|
|
"epoch": 4.363112391930835,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003234777946280668,
|
|
"loss": 4.6382,
|
|
"mean_token_accuracy": 0.25826959758996965,
|
|
"num_tokens": 104165681.0,
|
|
"step": 45420
|
|
},
|
|
{
|
|
"entropy": 5.101114940643311,
|
|
"epoch": 4.36359269932757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032344431571553004,
|
|
"loss": 4.5129,
|
|
"mean_token_accuracy": 0.266998727619648,
|
|
"num_tokens": 104177363.0,
|
|
"step": 45425
|
|
},
|
|
{
|
|
"entropy": 5.070892286300659,
|
|
"epoch": 4.364073006724303,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032341083567826026,
|
|
"loss": 4.5749,
|
|
"mean_token_accuracy": 0.257857945561409,
|
|
"num_tokens": 104188521.0,
|
|
"step": 45430
|
|
},
|
|
{
|
|
"entropy": 5.133299350738525,
|
|
"epoch": 4.3645533141210375,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00032337735451703456,
|
|
"loss": 4.6364,
|
|
"mean_token_accuracy": 0.2541172608733177,
|
|
"num_tokens": 104200597.0,
|
|
"step": 45435
|
|
},
|
|
{
|
|
"entropy": 5.245034456253052,
|
|
"epoch": 4.365033621517771,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032334387223263033,
|
|
"loss": 4.6821,
|
|
"mean_token_accuracy": 0.25024382919073107,
|
|
"num_tokens": 104213528.0,
|
|
"step": 45440
|
|
},
|
|
{
|
|
"entropy": 5.189302396774292,
|
|
"epoch": 4.365513928914505,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00032331038882582494,
|
|
"loss": 4.6127,
|
|
"mean_token_accuracy": 0.26343220472335815,
|
|
"num_tokens": 104224314.0,
|
|
"step": 45445
|
|
},
|
|
{
|
|
"entropy": 5.104165410995483,
|
|
"epoch": 4.36599423631124,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003232769042973958,
|
|
"loss": 4.5273,
|
|
"mean_token_accuracy": 0.26485229581594466,
|
|
"num_tokens": 104235369.0,
|
|
"step": 45450
|
|
},
|
|
{
|
|
"entropy": 5.060838413238526,
|
|
"epoch": 4.366474543707973,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003232434186481203,
|
|
"loss": 4.5257,
|
|
"mean_token_accuracy": 0.2655483841896057,
|
|
"num_tokens": 104246430.0,
|
|
"step": 45455
|
|
},
|
|
{
|
|
"entropy": 5.232622337341309,
|
|
"epoch": 4.366954851104707,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003232099318787758,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.25075364112854004,
|
|
"num_tokens": 104257904.0,
|
|
"step": 45460
|
|
},
|
|
{
|
|
"entropy": 5.150749683380127,
|
|
"epoch": 4.367435158501441,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003231764439901399,
|
|
"loss": 4.5333,
|
|
"mean_token_accuracy": 0.2670939743518829,
|
|
"num_tokens": 104268546.0,
|
|
"step": 45465
|
|
},
|
|
{
|
|
"entropy": 5.135833501815796,
|
|
"epoch": 4.367915465898175,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032314295498298993,
|
|
"loss": 4.5909,
|
|
"mean_token_accuracy": 0.26076351553201677,
|
|
"num_tokens": 104279630.0,
|
|
"step": 45470
|
|
},
|
|
{
|
|
"entropy": 5.054386615753174,
|
|
"epoch": 4.368395773294909,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00032310946485810364,
|
|
"loss": 4.4536,
|
|
"mean_token_accuracy": 0.2705288127064705,
|
|
"num_tokens": 104291700.0,
|
|
"step": 45475
|
|
},
|
|
{
|
|
"entropy": 5.156134176254272,
|
|
"epoch": 4.368876080691643,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00032307597361625834,
|
|
"loss": 4.6034,
|
|
"mean_token_accuracy": 0.2612276077270508,
|
|
"num_tokens": 104304458.0,
|
|
"step": 45480
|
|
},
|
|
{
|
|
"entropy": 5.0701916217803955,
|
|
"epoch": 4.369356388088376,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003230424812582318,
|
|
"loss": 4.5792,
|
|
"mean_token_accuracy": 0.26679258048534393,
|
|
"num_tokens": 104315276.0,
|
|
"step": 45485
|
|
},
|
|
{
|
|
"entropy": 5.1079936027526855,
|
|
"epoch": 4.369836695485111,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00032300898778480134,
|
|
"loss": 4.4635,
|
|
"mean_token_accuracy": 0.2722545385360718,
|
|
"num_tokens": 104327261.0,
|
|
"step": 45490
|
|
},
|
|
{
|
|
"entropy": 5.1456502914428714,
|
|
"epoch": 4.370317002881844,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00032297549319674487,
|
|
"loss": 4.5869,
|
|
"mean_token_accuracy": 0.25614322870969775,
|
|
"num_tokens": 104338756.0,
|
|
"step": 45495
|
|
},
|
|
{
|
|
"entropy": 5.135026597976685,
|
|
"epoch": 4.370797310278578,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00032294199749483986,
|
|
"loss": 4.5277,
|
|
"mean_token_accuracy": 0.2661177173256874,
|
|
"num_tokens": 104350041.0,
|
|
"step": 45500
|
|
},
|
|
{
|
|
"entropy": 5.255821228027344,
|
|
"epoch": 4.371277617675312,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000322908500679864,
|
|
"loss": 4.7645,
|
|
"mean_token_accuracy": 0.250325982272625,
|
|
"num_tokens": 104360418.0,
|
|
"step": 45505
|
|
},
|
|
{
|
|
"entropy": 5.143115568161011,
|
|
"epoch": 4.371757925072046,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00032287500275259506,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.25869383811950686,
|
|
"num_tokens": 104372099.0,
|
|
"step": 45510
|
|
},
|
|
{
|
|
"entropy": 5.051568603515625,
|
|
"epoch": 4.37223823246878,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00032284150371381066,
|
|
"loss": 4.5145,
|
|
"mean_token_accuracy": 0.26879614442586897,
|
|
"num_tokens": 104382223.0,
|
|
"step": 45515
|
|
},
|
|
{
|
|
"entropy": 5.225290250778198,
|
|
"epoch": 4.372718539865514,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003228080035642886,
|
|
"loss": 4.6486,
|
|
"mean_token_accuracy": 0.2612853214144707,
|
|
"num_tokens": 104393377.0,
|
|
"step": 45520
|
|
},
|
|
{
|
|
"entropy": 5.167923450469971,
|
|
"epoch": 4.373198847262248,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003227745023048067,
|
|
"loss": 4.5897,
|
|
"mean_token_accuracy": 0.2625266596674919,
|
|
"num_tokens": 104405474.0,
|
|
"step": 45525
|
|
},
|
|
{
|
|
"entropy": 5.143651151657105,
|
|
"epoch": 4.373679154658982,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00032274099993614275,
|
|
"loss": 4.6644,
|
|
"mean_token_accuracy": 0.25910359621047974,
|
|
"num_tokens": 104416381.0,
|
|
"step": 45530
|
|
},
|
|
{
|
|
"entropy": 5.06919755935669,
|
|
"epoch": 4.374159462055716,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032270749645907447,
|
|
"loss": 4.522,
|
|
"mean_token_accuracy": 0.26758855730295183,
|
|
"num_tokens": 104426410.0,
|
|
"step": 45535
|
|
},
|
|
{
|
|
"entropy": 5.2298798084259035,
|
|
"epoch": 4.3746397694524495,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00032267399187437977,
|
|
"loss": 4.6713,
|
|
"mean_token_accuracy": 0.254672734439373,
|
|
"num_tokens": 104437800.0,
|
|
"step": 45540
|
|
},
|
|
{
|
|
"entropy": 5.119253301620484,
|
|
"epoch": 4.375120076849184,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003226404861828366,
|
|
"loss": 4.5422,
|
|
"mean_token_accuracy": 0.27076318562030793,
|
|
"num_tokens": 104449467.0,
|
|
"step": 45545
|
|
},
|
|
{
|
|
"entropy": 5.072513198852539,
|
|
"epoch": 4.375600384245917,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003226069793852229,
|
|
"loss": 4.4847,
|
|
"mean_token_accuracy": 0.2680541634559631,
|
|
"num_tokens": 104460057.0,
|
|
"step": 45550
|
|
},
|
|
{
|
|
"entropy": 5.173928546905517,
|
|
"epoch": 4.376080691642652,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003225734714823163,
|
|
"loss": 4.6833,
|
|
"mean_token_accuracy": 0.2542357534170151,
|
|
"num_tokens": 104471251.0,
|
|
"step": 45555
|
|
},
|
|
{
|
|
"entropy": 5.145833349227905,
|
|
"epoch": 4.376560999039385,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003225399624748951,
|
|
"loss": 4.5511,
|
|
"mean_token_accuracy": 0.2627959132194519,
|
|
"num_tokens": 104482340.0,
|
|
"step": 45560
|
|
},
|
|
{
|
|
"entropy": 5.155253458023071,
|
|
"epoch": 4.377041306436119,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003225064523637371,
|
|
"loss": 4.5874,
|
|
"mean_token_accuracy": 0.26339668333530425,
|
|
"num_tokens": 104493163.0,
|
|
"step": 45565
|
|
},
|
|
{
|
|
"entropy": 5.109092330932617,
|
|
"epoch": 4.377521613832853,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003224729411496203,
|
|
"loss": 4.555,
|
|
"mean_token_accuracy": 0.2622312307357788,
|
|
"num_tokens": 104505240.0,
|
|
"step": 45570
|
|
},
|
|
{
|
|
"entropy": 5.055011224746704,
|
|
"epoch": 4.378001921229587,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003224394288333228,
|
|
"loss": 4.4846,
|
|
"mean_token_accuracy": 0.2676144316792488,
|
|
"num_tokens": 104516594.0,
|
|
"step": 45575
|
|
},
|
|
{
|
|
"entropy": 5.061791515350341,
|
|
"epoch": 4.3784822286263205,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0003224059154156226,
|
|
"loss": 4.4778,
|
|
"mean_token_accuracy": 0.2708950608968735,
|
|
"num_tokens": 104529335.0,
|
|
"step": 45580
|
|
},
|
|
{
|
|
"entropy": 5.088927984237671,
|
|
"epoch": 4.378962536023055,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032237240089729786,
|
|
"loss": 4.4914,
|
|
"mean_token_accuracy": 0.27170187830924986,
|
|
"num_tokens": 104540795.0,
|
|
"step": 45585
|
|
},
|
|
{
|
|
"entropy": 5.118281984329224,
|
|
"epoch": 4.379442843419788,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00032233888527912657,
|
|
"loss": 4.5735,
|
|
"mean_token_accuracy": 0.261329185962677,
|
|
"num_tokens": 104551834.0,
|
|
"step": 45590
|
|
},
|
|
{
|
|
"entropy": 5.081873655319214,
|
|
"epoch": 4.379923150816523,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000322305368561887,
|
|
"loss": 4.5801,
|
|
"mean_token_accuracy": 0.253522689640522,
|
|
"num_tokens": 104564931.0,
|
|
"step": 45595
|
|
},
|
|
{
|
|
"entropy": 5.1328658103942875,
|
|
"epoch": 4.380403458213257,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003222718507463572,
|
|
"loss": 4.5229,
|
|
"mean_token_accuracy": 0.26923811435699463,
|
|
"num_tokens": 104576865.0,
|
|
"step": 45600
|
|
},
|
|
{
|
|
"entropy": 5.099488687515259,
|
|
"epoch": 4.38088376560999,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00032223833183331546,
|
|
"loss": 4.5431,
|
|
"mean_token_accuracy": 0.2650283545255661,
|
|
"num_tokens": 104587831.0,
|
|
"step": 45605
|
|
},
|
|
{
|
|
"entropy": 5.15819034576416,
|
|
"epoch": 4.381364073006725,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00032220481182353985,
|
|
"loss": 4.6125,
|
|
"mean_token_accuracy": 0.2554700389504433,
|
|
"num_tokens": 104598722.0,
|
|
"step": 45610
|
|
},
|
|
{
|
|
"entropy": 5.190732192993164,
|
|
"epoch": 4.381844380403458,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00032217129071780877,
|
|
"loss": 4.611,
|
|
"mean_token_accuracy": 0.25737455785274505,
|
|
"num_tokens": 104609709.0,
|
|
"step": 45615
|
|
},
|
|
{
|
|
"entropy": 5.136327695846558,
|
|
"epoch": 4.3823246878001925,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003221377685169003,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.2613217979669571,
|
|
"num_tokens": 104620893.0,
|
|
"step": 45620
|
|
},
|
|
{
|
|
"entropy": 5.105958366394043,
|
|
"epoch": 4.382804995196926,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003221042452215928,
|
|
"loss": 4.5887,
|
|
"mean_token_accuracy": 0.2502520248293877,
|
|
"num_tokens": 104633273.0,
|
|
"step": 45625
|
|
},
|
|
{
|
|
"entropy": 5.1221541404724125,
|
|
"epoch": 4.38328530259366,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003220707208326647,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.26200267374515535,
|
|
"num_tokens": 104643741.0,
|
|
"step": 45630
|
|
},
|
|
{
|
|
"entropy": 5.1292651176452635,
|
|
"epoch": 4.383765609990394,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032203719535089416,
|
|
"loss": 4.5353,
|
|
"mean_token_accuracy": 0.26522727161645887,
|
|
"num_tokens": 104655515.0,
|
|
"step": 45635
|
|
},
|
|
{
|
|
"entropy": 5.233200597763061,
|
|
"epoch": 4.384245917387128,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003220036687770596,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.25871542096138,
|
|
"num_tokens": 104666234.0,
|
|
"step": 45640
|
|
},
|
|
{
|
|
"entropy": 5.182831573486328,
|
|
"epoch": 4.384726224783861,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003219701411119395,
|
|
"loss": 4.6266,
|
|
"mean_token_accuracy": 0.2581789344549179,
|
|
"num_tokens": 104677610.0,
|
|
"step": 45645
|
|
},
|
|
{
|
|
"entropy": 5.092544412612915,
|
|
"epoch": 4.385206532180596,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00032193661235631213,
|
|
"loss": 4.5029,
|
|
"mean_token_accuracy": 0.2646935015916824,
|
|
"num_tokens": 104688453.0,
|
|
"step": 45650
|
|
},
|
|
{
|
|
"entropy": 5.05845422744751,
|
|
"epoch": 4.385686839577329,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032190308251095603,
|
|
"loss": 4.4834,
|
|
"mean_token_accuracy": 0.27199751138687134,
|
|
"num_tokens": 104700014.0,
|
|
"step": 45655
|
|
},
|
|
{
|
|
"entropy": 5.152735471725464,
|
|
"epoch": 4.3861671469740635,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003218695515766496,
|
|
"loss": 4.5807,
|
|
"mean_token_accuracy": 0.26105709820985795,
|
|
"num_tokens": 104711320.0,
|
|
"step": 45660
|
|
},
|
|
{
|
|
"entropy": 5.096170949935913,
|
|
"epoch": 4.386647454370797,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00032183601955417137,
|
|
"loss": 4.5241,
|
|
"mean_token_accuracy": 0.2634144574403763,
|
|
"num_tokens": 104721971.0,
|
|
"step": 45665
|
|
},
|
|
{
|
|
"entropy": 5.1722148895263675,
|
|
"epoch": 4.387127761767531,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003218024864442998,
|
|
"loss": 4.6588,
|
|
"mean_token_accuracy": 0.25580379366874695,
|
|
"num_tokens": 104733875.0,
|
|
"step": 45670
|
|
},
|
|
{
|
|
"entropy": 5.118529415130615,
|
|
"epoch": 4.387608069164266,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00032176895224781353,
|
|
"loss": 4.5021,
|
|
"mean_token_accuracy": 0.26744468212127687,
|
|
"num_tokens": 104744575.0,
|
|
"step": 45675
|
|
},
|
|
{
|
|
"entropy": 4.990486145019531,
|
|
"epoch": 4.388088376560999,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003217354169654911,
|
|
"loss": 4.4187,
|
|
"mean_token_accuracy": 0.27119932472705843,
|
|
"num_tokens": 104755703.0,
|
|
"step": 45680
|
|
},
|
|
{
|
|
"entropy": 5.114738655090332,
|
|
"epoch": 4.388568683957733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00032170188059811095,
|
|
"loss": 4.5649,
|
|
"mean_token_accuracy": 0.2622253239154816,
|
|
"num_tokens": 104766334.0,
|
|
"step": 45685
|
|
},
|
|
{
|
|
"entropy": 5.098346090316772,
|
|
"epoch": 4.389048991354467,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00032166834314645184,
|
|
"loss": 4.5562,
|
|
"mean_token_accuracy": 0.2690630108118057,
|
|
"num_tokens": 104778326.0,
|
|
"step": 45690
|
|
},
|
|
{
|
|
"entropy": 5.096229076385498,
|
|
"epoch": 4.389529298751201,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0003216348046112924,
|
|
"loss": 4.5653,
|
|
"mean_token_accuracy": 0.25981355011463164,
|
|
"num_tokens": 104789936.0,
|
|
"step": 45695
|
|
},
|
|
{
|
|
"entropy": 5.206054258346557,
|
|
"epoch": 4.390009606147935,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032160126499341125,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.2524106904864311,
|
|
"num_tokens": 104801539.0,
|
|
"step": 45700
|
|
},
|
|
{
|
|
"entropy": 5.124052619934082,
|
|
"epoch": 4.390489913544669,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00032156772429358716,
|
|
"loss": 4.5546,
|
|
"mean_token_accuracy": 0.26163007467985155,
|
|
"num_tokens": 104813889.0,
|
|
"step": 45705
|
|
},
|
|
{
|
|
"entropy": 5.228113794326783,
|
|
"epoch": 4.390970220941402,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00032153418251259873,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.24689160883426667,
|
|
"num_tokens": 104826116.0,
|
|
"step": 45710
|
|
},
|
|
{
|
|
"entropy": 5.1594500064849855,
|
|
"epoch": 4.391450528338137,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00032150063965122485,
|
|
"loss": 4.5431,
|
|
"mean_token_accuracy": 0.2555230587720871,
|
|
"num_tokens": 104837350.0,
|
|
"step": 45715
|
|
},
|
|
{
|
|
"entropy": 5.061306142807007,
|
|
"epoch": 4.39193083573487,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00032146709571024407,
|
|
"loss": 4.4928,
|
|
"mean_token_accuracy": 0.2726113095879555,
|
|
"num_tokens": 104848382.0,
|
|
"step": 45720
|
|
},
|
|
{
|
|
"entropy": 5.0838707447052,
|
|
"epoch": 4.392411143131604,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003214335506904354,
|
|
"loss": 4.5513,
|
|
"mean_token_accuracy": 0.26795431822538374,
|
|
"num_tokens": 104859598.0,
|
|
"step": 45725
|
|
},
|
|
{
|
|
"entropy": 5.027521324157715,
|
|
"epoch": 4.392891450528338,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00032140000459257757,
|
|
"loss": 4.4609,
|
|
"mean_token_accuracy": 0.26613447070121765,
|
|
"num_tokens": 104871070.0,
|
|
"step": 45730
|
|
},
|
|
{
|
|
"entropy": 5.032740116119385,
|
|
"epoch": 4.393371757925072,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00032136645741744936,
|
|
"loss": 4.5231,
|
|
"mean_token_accuracy": 0.26331174522638323,
|
|
"num_tokens": 104883811.0,
|
|
"step": 45735
|
|
},
|
|
{
|
|
"entropy": 5.262583160400391,
|
|
"epoch": 4.393852065321806,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00032133290916582966,
|
|
"loss": 4.6828,
|
|
"mean_token_accuracy": 0.2568641945719719,
|
|
"num_tokens": 104894100.0,
|
|
"step": 45740
|
|
},
|
|
{
|
|
"entropy": 5.221535634994507,
|
|
"epoch": 4.39433237271854,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003212993598384975,
|
|
"loss": 4.5543,
|
|
"mean_token_accuracy": 0.26559454798698423,
|
|
"num_tokens": 104906353.0,
|
|
"step": 45745
|
|
},
|
|
{
|
|
"entropy": 5.08131971359253,
|
|
"epoch": 4.394812680115273,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003212658094362316,
|
|
"loss": 4.429,
|
|
"mean_token_accuracy": 0.270783868432045,
|
|
"num_tokens": 104916810.0,
|
|
"step": 45750
|
|
},
|
|
{
|
|
"entropy": 5.070665073394776,
|
|
"epoch": 4.395292987512008,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00032123225795981097,
|
|
"loss": 4.5307,
|
|
"mean_token_accuracy": 0.2627947613596916,
|
|
"num_tokens": 104927904.0,
|
|
"step": 45755
|
|
},
|
|
{
|
|
"entropy": 5.112456178665161,
|
|
"epoch": 4.395773294908741,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032119870541001466,
|
|
"loss": 4.6134,
|
|
"mean_token_accuracy": 0.2622941181063652,
|
|
"num_tokens": 104939993.0,
|
|
"step": 45760
|
|
},
|
|
{
|
|
"entropy": 5.152918148040771,
|
|
"epoch": 4.3962536023054755,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003211651517876216,
|
|
"loss": 4.6119,
|
|
"mean_token_accuracy": 0.25903441905975344,
|
|
"num_tokens": 104951004.0,
|
|
"step": 45765
|
|
},
|
|
{
|
|
"entropy": 5.179847955703735,
|
|
"epoch": 4.39673390970221,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00032113159709341074,
|
|
"loss": 4.5891,
|
|
"mean_token_accuracy": 0.26640380173921585,
|
|
"num_tokens": 104963684.0,
|
|
"step": 45770
|
|
},
|
|
{
|
|
"entropy": 5.195500278472901,
|
|
"epoch": 4.397214217098943,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00032109804132816113,
|
|
"loss": 4.5697,
|
|
"mean_token_accuracy": 0.25529671311378477,
|
|
"num_tokens": 104975943.0,
|
|
"step": 45775
|
|
},
|
|
{
|
|
"entropy": 5.119776439666748,
|
|
"epoch": 4.3976945244956775,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000321064484492652,
|
|
"loss": 4.5402,
|
|
"mean_token_accuracy": 0.26900755167007445,
|
|
"num_tokens": 104987775.0,
|
|
"step": 45780
|
|
},
|
|
{
|
|
"entropy": 5.053851795196533,
|
|
"epoch": 4.398174831892411,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00032103092658766226,
|
|
"loss": 4.4605,
|
|
"mean_token_accuracy": 0.27257313281297685,
|
|
"num_tokens": 104999420.0,
|
|
"step": 45785
|
|
},
|
|
{
|
|
"entropy": 5.179697942733765,
|
|
"epoch": 4.398655139289145,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00032099736761397106,
|
|
"loss": 4.6235,
|
|
"mean_token_accuracy": 0.26337589472532275,
|
|
"num_tokens": 105010759.0,
|
|
"step": 45790
|
|
},
|
|
{
|
|
"entropy": 5.139425659179688,
|
|
"epoch": 4.399135446685879,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00032096380757235774,
|
|
"loss": 4.5523,
|
|
"mean_token_accuracy": 0.2598624721169472,
|
|
"num_tokens": 105021386.0,
|
|
"step": 45795
|
|
},
|
|
{
|
|
"entropy": 5.1203837394714355,
|
|
"epoch": 4.399615754082613,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003209302464636011,
|
|
"loss": 4.5289,
|
|
"mean_token_accuracy": 0.26791180670261383,
|
|
"num_tokens": 105031917.0,
|
|
"step": 45800
|
|
},
|
|
{
|
|
"entropy": 5.057725524902343,
|
|
"epoch": 4.4000960614793465,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003208966842884806,
|
|
"loss": 4.5391,
|
|
"mean_token_accuracy": 0.26459486931562426,
|
|
"num_tokens": 105043020.0,
|
|
"step": 45805
|
|
},
|
|
{
|
|
"entropy": 5.167314863204956,
|
|
"epoch": 4.400576368876081,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003208631210477754,
|
|
"loss": 4.642,
|
|
"mean_token_accuracy": 0.2538474276661873,
|
|
"num_tokens": 105053453.0,
|
|
"step": 45810
|
|
},
|
|
{
|
|
"entropy": 5.209726572036743,
|
|
"epoch": 4.401056676272814,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003208295567422646,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.2598818838596344,
|
|
"num_tokens": 105064268.0,
|
|
"step": 45815
|
|
},
|
|
{
|
|
"entropy": 5.114302158355713,
|
|
"epoch": 4.401536983669549,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003207959913727277,
|
|
"loss": 4.5218,
|
|
"mean_token_accuracy": 0.27419553846120837,
|
|
"num_tokens": 105075797.0,
|
|
"step": 45820
|
|
},
|
|
{
|
|
"entropy": 5.040086364746093,
|
|
"epoch": 4.402017291066282,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032076242493994374,
|
|
"loss": 4.5464,
|
|
"mean_token_accuracy": 0.27010983526706694,
|
|
"num_tokens": 105088310.0,
|
|
"step": 45825
|
|
},
|
|
{
|
|
"entropy": 5.132437610626221,
|
|
"epoch": 4.402497598463016,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003207288574446923,
|
|
"loss": 4.5171,
|
|
"mean_token_accuracy": 0.2679715514183044,
|
|
"num_tokens": 105099240.0,
|
|
"step": 45830
|
|
},
|
|
{
|
|
"entropy": 5.147053337097168,
|
|
"epoch": 4.40297790585975,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032069528888775244,
|
|
"loss": 4.5517,
|
|
"mean_token_accuracy": 0.2645579129457474,
|
|
"num_tokens": 105109433.0,
|
|
"step": 45835
|
|
},
|
|
{
|
|
"entropy": 5.163902854919433,
|
|
"epoch": 4.403458213256484,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003206617192699038,
|
|
"loss": 4.6609,
|
|
"mean_token_accuracy": 0.26288862973451615,
|
|
"num_tokens": 105121098.0,
|
|
"step": 45840
|
|
},
|
|
{
|
|
"entropy": 5.159773540496826,
|
|
"epoch": 4.4039385206532184,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00032062814859192554,
|
|
"loss": 4.6287,
|
|
"mean_token_accuracy": 0.25766219645738603,
|
|
"num_tokens": 105132978.0,
|
|
"step": 45845
|
|
},
|
|
{
|
|
"entropy": 5.080546903610229,
|
|
"epoch": 4.404418828049952,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003205945768545972,
|
|
"loss": 4.5079,
|
|
"mean_token_accuracy": 0.26617671698331835,
|
|
"num_tokens": 105145917.0,
|
|
"step": 45850
|
|
},
|
|
{
|
|
"entropy": 5.099824094772339,
|
|
"epoch": 4.404899135446686,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003205610040586981,
|
|
"loss": 4.4711,
|
|
"mean_token_accuracy": 0.27725717425346375,
|
|
"num_tokens": 105157444.0,
|
|
"step": 45855
|
|
},
|
|
{
|
|
"entropy": 5.160588312149048,
|
|
"epoch": 4.40537944284342,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003205274302050078,
|
|
"loss": 4.5885,
|
|
"mean_token_accuracy": 0.256675611436367,
|
|
"num_tokens": 105168784.0,
|
|
"step": 45860
|
|
},
|
|
{
|
|
"entropy": 5.076707983016968,
|
|
"epoch": 4.405859750240154,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003204938552943058,
|
|
"loss": 4.5327,
|
|
"mean_token_accuracy": 0.2685825005173683,
|
|
"num_tokens": 105178964.0,
|
|
"step": 45865
|
|
},
|
|
{
|
|
"entropy": 5.140727376937866,
|
|
"epoch": 4.406340057636887,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003204602793273716,
|
|
"loss": 4.4844,
|
|
"mean_token_accuracy": 0.27025315910577774,
|
|
"num_tokens": 105189057.0,
|
|
"step": 45870
|
|
},
|
|
{
|
|
"entropy": 5.108584594726563,
|
|
"epoch": 4.406820365033622,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00032042670230498463,
|
|
"loss": 4.5829,
|
|
"mean_token_accuracy": 0.26054890751838683,
|
|
"num_tokens": 105199477.0,
|
|
"step": 45875
|
|
},
|
|
{
|
|
"entropy": 5.0159361362457275,
|
|
"epoch": 4.407300672430355,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003203931242279245,
|
|
"loss": 4.451,
|
|
"mean_token_accuracy": 0.27328249216079714,
|
|
"num_tokens": 105212348.0,
|
|
"step": 45880
|
|
},
|
|
{
|
|
"entropy": 5.098543405532837,
|
|
"epoch": 4.4077809798270895,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003203595450969709,
|
|
"loss": 4.5542,
|
|
"mean_token_accuracy": 0.2635463461279869,
|
|
"num_tokens": 105223956.0,
|
|
"step": 45885
|
|
},
|
|
{
|
|
"entropy": 5.169216918945312,
|
|
"epoch": 4.408261287223823,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003203259649129033,
|
|
"loss": 4.5979,
|
|
"mean_token_accuracy": 0.25554895401000977,
|
|
"num_tokens": 105234848.0,
|
|
"step": 45890
|
|
},
|
|
{
|
|
"entropy": 5.139582824707031,
|
|
"epoch": 4.408741594620557,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00032029238367650145,
|
|
"loss": 4.6127,
|
|
"mean_token_accuracy": 0.25977408289909365,
|
|
"num_tokens": 105246442.0,
|
|
"step": 45895
|
|
},
|
|
{
|
|
"entropy": 5.190680646896363,
|
|
"epoch": 4.409221902017291,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003202588013885449,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.2607897788286209,
|
|
"num_tokens": 105258183.0,
|
|
"step": 45900
|
|
},
|
|
{
|
|
"entropy": 5.1081194400787355,
|
|
"epoch": 4.409702209414025,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032022521804981333,
|
|
"loss": 4.5448,
|
|
"mean_token_accuracy": 0.260592982172966,
|
|
"num_tokens": 105269964.0,
|
|
"step": 45905
|
|
},
|
|
{
|
|
"entropy": 5.101026773452759,
|
|
"epoch": 4.4101825168107585,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032019163366108654,
|
|
"loss": 4.5453,
|
|
"mean_token_accuracy": 0.2754780799150467,
|
|
"num_tokens": 105282238.0,
|
|
"step": 45910
|
|
},
|
|
{
|
|
"entropy": 5.099481678009033,
|
|
"epoch": 4.410662824207493,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003201580482231442,
|
|
"loss": 4.547,
|
|
"mean_token_accuracy": 0.26454608142375946,
|
|
"num_tokens": 105294841.0,
|
|
"step": 45915
|
|
},
|
|
{
|
|
"entropy": 5.121626138687134,
|
|
"epoch": 4.411143131604227,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003201244617367661,
|
|
"loss": 4.5138,
|
|
"mean_token_accuracy": 0.2644935712218285,
|
|
"num_tokens": 105305397.0,
|
|
"step": 45920
|
|
},
|
|
{
|
|
"entropy": 5.120534181594849,
|
|
"epoch": 4.4116234390009605,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003200908742027319,
|
|
"loss": 4.5631,
|
|
"mean_token_accuracy": 0.26231343001127244,
|
|
"num_tokens": 105318601.0,
|
|
"step": 45925
|
|
},
|
|
{
|
|
"entropy": 5.149291324615478,
|
|
"epoch": 4.412103746397695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003200572856218216,
|
|
"loss": 4.5911,
|
|
"mean_token_accuracy": 0.2621267005801201,
|
|
"num_tokens": 105329798.0,
|
|
"step": 45930
|
|
},
|
|
{
|
|
"entropy": 5.113547134399414,
|
|
"epoch": 4.412584053794428,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032002369599481485,
|
|
"loss": 4.5391,
|
|
"mean_token_accuracy": 0.26487005352973936,
|
|
"num_tokens": 105340646.0,
|
|
"step": 45935
|
|
},
|
|
{
|
|
"entropy": 5.143807363510132,
|
|
"epoch": 4.413064361191163,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003199901053224916,
|
|
"loss": 4.5872,
|
|
"mean_token_accuracy": 0.25932212322950365,
|
|
"num_tokens": 105353026.0,
|
|
"step": 45940
|
|
},
|
|
{
|
|
"entropy": 5.117081165313721,
|
|
"epoch": 4.413544668587896,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00031995651360563164,
|
|
"loss": 4.5918,
|
|
"mean_token_accuracy": 0.26118834465742113,
|
|
"num_tokens": 105364394.0,
|
|
"step": 45945
|
|
},
|
|
{
|
|
"entropy": 5.074423837661743,
|
|
"epoch": 4.41402497598463,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00031992292084501503,
|
|
"loss": 4.5438,
|
|
"mean_token_accuracy": 0.2673288494348526,
|
|
"num_tokens": 105375630.0,
|
|
"step": 45950
|
|
},
|
|
{
|
|
"entropy": 5.118613767623901,
|
|
"epoch": 4.414505283381364,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00031988932704142146,
|
|
"loss": 4.6254,
|
|
"mean_token_accuracy": 0.2597615957260132,
|
|
"num_tokens": 105387036.0,
|
|
"step": 45955
|
|
},
|
|
{
|
|
"entropy": 5.096648168563843,
|
|
"epoch": 4.414985590778098,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003198557321956312,
|
|
"loss": 4.521,
|
|
"mean_token_accuracy": 0.2633259207010269,
|
|
"num_tokens": 105398752.0,
|
|
"step": 45960
|
|
},
|
|
{
|
|
"entropy": 5.0868847370147705,
|
|
"epoch": 4.415465898174832,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003198221363084239,
|
|
"loss": 4.5172,
|
|
"mean_token_accuracy": 0.27148755341768266,
|
|
"num_tokens": 105410843.0,
|
|
"step": 45965
|
|
},
|
|
{
|
|
"entropy": 5.19502534866333,
|
|
"epoch": 4.415946205571566,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003197885393805797,
|
|
"loss": 4.6447,
|
|
"mean_token_accuracy": 0.26127131581306456,
|
|
"num_tokens": 105421999.0,
|
|
"step": 45970
|
|
},
|
|
{
|
|
"entropy": 5.174193811416626,
|
|
"epoch": 4.416426512968299,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031975494141287864,
|
|
"loss": 4.5773,
|
|
"mean_token_accuracy": 0.2614168390631676,
|
|
"num_tokens": 105433864.0,
|
|
"step": 45975
|
|
},
|
|
{
|
|
"entropy": 5.163908863067627,
|
|
"epoch": 4.416906820365034,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003197213424061007,
|
|
"loss": 4.5971,
|
|
"mean_token_accuracy": 0.2602779820561409,
|
|
"num_tokens": 105444924.0,
|
|
"step": 45980
|
|
},
|
|
{
|
|
"entropy": 5.129870796203614,
|
|
"epoch": 4.417387127761767,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000319687742361026,
|
|
"loss": 4.5696,
|
|
"mean_token_accuracy": 0.2584484741091728,
|
|
"num_tokens": 105455922.0,
|
|
"step": 45985
|
|
},
|
|
{
|
|
"entropy": 5.14023790359497,
|
|
"epoch": 4.417867435158501,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00031965414127843464,
|
|
"loss": 4.6042,
|
|
"mean_token_accuracy": 0.2642209783196449,
|
|
"num_tokens": 105468352.0,
|
|
"step": 45990
|
|
},
|
|
{
|
|
"entropy": 5.159504556655884,
|
|
"epoch": 4.418347742555236,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00031962053915910664,
|
|
"loss": 4.6011,
|
|
"mean_token_accuracy": 0.26114796847105026,
|
|
"num_tokens": 105479453.0,
|
|
"step": 45995
|
|
},
|
|
{
|
|
"entropy": 5.106597995758056,
|
|
"epoch": 4.418828049951969,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00031958693600382226,
|
|
"loss": 4.5608,
|
|
"mean_token_accuracy": 0.2608883768320084,
|
|
"num_tokens": 105491512.0,
|
|
"step": 46000
|
|
},
|
|
{
|
|
"entropy": 5.1558863639831545,
|
|
"epoch": 4.4193083573487035,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003195533318133617,
|
|
"loss": 4.6339,
|
|
"mean_token_accuracy": 0.26474606841802595,
|
|
"num_tokens": 105503159.0,
|
|
"step": 46005
|
|
},
|
|
{
|
|
"entropy": 5.118121576309204,
|
|
"epoch": 4.419788664745437,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00031951972658850495,
|
|
"loss": 4.5975,
|
|
"mean_token_accuracy": 0.2606734722852707,
|
|
"num_tokens": 105514748.0,
|
|
"step": 46010
|
|
},
|
|
{
|
|
"entropy": 5.146634912490844,
|
|
"epoch": 4.420268972142171,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00031948612033003246,
|
|
"loss": 4.5451,
|
|
"mean_token_accuracy": 0.2671597883105278,
|
|
"num_tokens": 105526046.0,
|
|
"step": 46015
|
|
},
|
|
{
|
|
"entropy": 5.12623815536499,
|
|
"epoch": 4.420749279538905,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00031945251303872426,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.2543672114610672,
|
|
"num_tokens": 105539565.0,
|
|
"step": 46020
|
|
},
|
|
{
|
|
"entropy": 5.206678867340088,
|
|
"epoch": 4.421229586935639,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00031941890471536076,
|
|
"loss": 4.611,
|
|
"mean_token_accuracy": 0.25911247581243513,
|
|
"num_tokens": 105550562.0,
|
|
"step": 46025
|
|
},
|
|
{
|
|
"entropy": 5.198658180236817,
|
|
"epoch": 4.4217098943323725,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00031938529536072215,
|
|
"loss": 4.5803,
|
|
"mean_token_accuracy": 0.2663537472486496,
|
|
"num_tokens": 105561715.0,
|
|
"step": 46030
|
|
},
|
|
{
|
|
"entropy": 5.143539571762085,
|
|
"epoch": 4.422190201729107,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003193516849755888,
|
|
"loss": 4.534,
|
|
"mean_token_accuracy": 0.25757167786359786,
|
|
"num_tokens": 105572694.0,
|
|
"step": 46035
|
|
},
|
|
{
|
|
"entropy": 5.164249420166016,
|
|
"epoch": 4.42267050912584,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000319318073560741,
|
|
"loss": 4.6127,
|
|
"mean_token_accuracy": 0.2617600873112679,
|
|
"num_tokens": 105584586.0,
|
|
"step": 46040
|
|
},
|
|
{
|
|
"entropy": 5.060247564315796,
|
|
"epoch": 4.423150816522575,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00031928446111695915,
|
|
"loss": 4.4595,
|
|
"mean_token_accuracy": 0.27656892836093905,
|
|
"num_tokens": 105595778.0,
|
|
"step": 46045
|
|
},
|
|
{
|
|
"entropy": 5.001118326187134,
|
|
"epoch": 4.423631123919308,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003192508476450236,
|
|
"loss": 4.4348,
|
|
"mean_token_accuracy": 0.27226472496986387,
|
|
"num_tokens": 105607986.0,
|
|
"step": 46050
|
|
},
|
|
{
|
|
"entropy": 5.096542739868164,
|
|
"epoch": 4.424111431316042,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00031921723314571476,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.2565011754631996,
|
|
"num_tokens": 105620933.0,
|
|
"step": 46055
|
|
},
|
|
{
|
|
"entropy": 5.201545667648316,
|
|
"epoch": 4.424591738712776,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00031918361761981305,
|
|
"loss": 4.6851,
|
|
"mean_token_accuracy": 0.2509350135922432,
|
|
"num_tokens": 105632113.0,
|
|
"step": 46060
|
|
},
|
|
{
|
|
"entropy": 5.195016288757325,
|
|
"epoch": 4.42507204610951,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00031915000106809904,
|
|
"loss": 4.6113,
|
|
"mean_token_accuracy": 0.26431494653224946,
|
|
"num_tokens": 105643978.0,
|
|
"step": 46065
|
|
},
|
|
{
|
|
"entropy": 5.064186382293701,
|
|
"epoch": 4.425552353506244,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000319116383491353,
|
|
"loss": 4.4517,
|
|
"mean_token_accuracy": 0.27240680903196335,
|
|
"num_tokens": 105655193.0,
|
|
"step": 46070
|
|
},
|
|
{
|
|
"entropy": 5.107187700271607,
|
|
"epoch": 4.426032660902978,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003190827648903555,
|
|
"loss": 4.5796,
|
|
"mean_token_accuracy": 0.25411265939474104,
|
|
"num_tokens": 105667144.0,
|
|
"step": 46075
|
|
},
|
|
{
|
|
"entropy": 5.1789998531341555,
|
|
"epoch": 4.426512968299712,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003190491452658872,
|
|
"loss": 4.6324,
|
|
"mean_token_accuracy": 0.2592462569475174,
|
|
"num_tokens": 105679836.0,
|
|
"step": 46080
|
|
},
|
|
{
|
|
"entropy": 5.197906112670898,
|
|
"epoch": 4.426993275696446,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003190155246187286,
|
|
"loss": 4.5875,
|
|
"mean_token_accuracy": 0.26050018072128295,
|
|
"num_tokens": 105690437.0,
|
|
"step": 46085
|
|
},
|
|
{
|
|
"entropy": 5.149704885482788,
|
|
"epoch": 4.42747358309318,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00031898190294966006,
|
|
"loss": 4.6255,
|
|
"mean_token_accuracy": 0.2604544788599014,
|
|
"num_tokens": 105701614.0,
|
|
"step": 46090
|
|
},
|
|
{
|
|
"entropy": 5.225094747543335,
|
|
"epoch": 4.427953890489913,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003189482802594624,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.25073224902153013,
|
|
"num_tokens": 105713725.0,
|
|
"step": 46095
|
|
},
|
|
{
|
|
"entropy": 5.163835525512695,
|
|
"epoch": 4.428434197886648,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00031891465654891615,
|
|
"loss": 4.5906,
|
|
"mean_token_accuracy": 0.25934525281190873,
|
|
"num_tokens": 105726397.0,
|
|
"step": 46100
|
|
},
|
|
{
|
|
"entropy": 5.060735893249512,
|
|
"epoch": 4.428914505283381,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000318881031818802,
|
|
"loss": 4.4436,
|
|
"mean_token_accuracy": 0.2748713821172714,
|
|
"num_tokens": 105738401.0,
|
|
"step": 46105
|
|
},
|
|
{
|
|
"entropy": 5.092563104629517,
|
|
"epoch": 4.4293948126801155,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031884740606990056,
|
|
"loss": 4.4756,
|
|
"mean_token_accuracy": 0.2793571949005127,
|
|
"num_tokens": 105749529.0,
|
|
"step": 46110
|
|
},
|
|
{
|
|
"entropy": 5.042314624786377,
|
|
"epoch": 4.429875120076849,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00031881377930299256,
|
|
"loss": 4.5067,
|
|
"mean_token_accuracy": 0.2721372991800308,
|
|
"num_tokens": 105761965.0,
|
|
"step": 46115
|
|
},
|
|
{
|
|
"entropy": 5.048228597640991,
|
|
"epoch": 4.430355427473583,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003187801515188588,
|
|
"loss": 4.529,
|
|
"mean_token_accuracy": 0.2686693623661995,
|
|
"num_tokens": 105773358.0,
|
|
"step": 46120
|
|
},
|
|
{
|
|
"entropy": 5.1094982624053955,
|
|
"epoch": 4.430835734870317,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003187465227182798,
|
|
"loss": 4.5927,
|
|
"mean_token_accuracy": 0.264643532037735,
|
|
"num_tokens": 105784815.0,
|
|
"step": 46125
|
|
},
|
|
{
|
|
"entropy": 5.077403402328491,
|
|
"epoch": 4.431316042267051,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00031871289290203646,
|
|
"loss": 4.5237,
|
|
"mean_token_accuracy": 0.26071093827486036,
|
|
"num_tokens": 105796383.0,
|
|
"step": 46130
|
|
},
|
|
{
|
|
"entropy": 5.128030157089233,
|
|
"epoch": 4.431796349663784,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00031867926207090956,
|
|
"loss": 4.6052,
|
|
"mean_token_accuracy": 0.2629505529999733,
|
|
"num_tokens": 105808287.0,
|
|
"step": 46135
|
|
},
|
|
{
|
|
"entropy": 5.156347417831421,
|
|
"epoch": 4.432276657060519,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003186456302256799,
|
|
"loss": 4.5421,
|
|
"mean_token_accuracy": 0.2633710116147995,
|
|
"num_tokens": 105819111.0,
|
|
"step": 46140
|
|
},
|
|
{
|
|
"entropy": 5.115845823287964,
|
|
"epoch": 4.432756964457253,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003186119973671283,
|
|
"loss": 4.5705,
|
|
"mean_token_accuracy": 0.26309469938278196,
|
|
"num_tokens": 105830656.0,
|
|
"step": 46145
|
|
},
|
|
{
|
|
"entropy": 5.084657526016235,
|
|
"epoch": 4.4332372718539865,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00031857836349603565,
|
|
"loss": 4.5139,
|
|
"mean_token_accuracy": 0.2669952228665352,
|
|
"num_tokens": 105843773.0,
|
|
"step": 46150
|
|
},
|
|
{
|
|
"entropy": 5.062774419784546,
|
|
"epoch": 4.433717579250721,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00031854472861318284,
|
|
"loss": 4.5179,
|
|
"mean_token_accuracy": 0.2680308982729912,
|
|
"num_tokens": 105855031.0,
|
|
"step": 46155
|
|
},
|
|
{
|
|
"entropy": 5.069306659698486,
|
|
"epoch": 4.434197886647454,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00031851109271935064,
|
|
"loss": 4.5408,
|
|
"mean_token_accuracy": 0.2622329831123352,
|
|
"num_tokens": 105865604.0,
|
|
"step": 46160
|
|
},
|
|
{
|
|
"entropy": 5.132381582260132,
|
|
"epoch": 4.434678194044189,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003184774558153201,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.2660390570759773,
|
|
"num_tokens": 105877406.0,
|
|
"step": 46165
|
|
},
|
|
{
|
|
"entropy": 5.068622207641601,
|
|
"epoch": 4.435158501440922,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00031844381790187217,
|
|
"loss": 4.543,
|
|
"mean_token_accuracy": 0.2688652753829956,
|
|
"num_tokens": 105889379.0,
|
|
"step": 46170
|
|
},
|
|
{
|
|
"entropy": 5.154178619384766,
|
|
"epoch": 4.435638808837656,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00031841017897978773,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.2595172166824341,
|
|
"num_tokens": 105900712.0,
|
|
"step": 46175
|
|
},
|
|
{
|
|
"entropy": 5.132070159912109,
|
|
"epoch": 4.43611911623439,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00031837653904984793,
|
|
"loss": 4.606,
|
|
"mean_token_accuracy": 0.2632488414645195,
|
|
"num_tokens": 105912388.0,
|
|
"step": 46180
|
|
},
|
|
{
|
|
"entropy": 5.191107654571534,
|
|
"epoch": 4.436599423631124,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003183428981128336,
|
|
"loss": 4.6126,
|
|
"mean_token_accuracy": 0.25814709067344666,
|
|
"num_tokens": 105922391.0,
|
|
"step": 46185
|
|
},
|
|
{
|
|
"entropy": 5.100333261489868,
|
|
"epoch": 4.437079731027858,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00031830925616952593,
|
|
"loss": 4.451,
|
|
"mean_token_accuracy": 0.26722904294729233,
|
|
"num_tokens": 105932856.0,
|
|
"step": 46190
|
|
},
|
|
{
|
|
"entropy": 5.185663366317749,
|
|
"epoch": 4.437560038424592,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003182756132207059,
|
|
"loss": 4.6717,
|
|
"mean_token_accuracy": 0.2523951783776283,
|
|
"num_tokens": 105944703.0,
|
|
"step": 46195
|
|
},
|
|
{
|
|
"entropy": 5.074661064147949,
|
|
"epoch": 4.438040345821325,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003182419692671547,
|
|
"loss": 4.4697,
|
|
"mean_token_accuracy": 0.27878889739513396,
|
|
"num_tokens": 105956734.0,
|
|
"step": 46200
|
|
},
|
|
{
|
|
"entropy": 5.051645088195801,
|
|
"epoch": 4.43852065321806,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00031820832430965335,
|
|
"loss": 4.5395,
|
|
"mean_token_accuracy": 0.2706503003835678,
|
|
"num_tokens": 105967937.0,
|
|
"step": 46205
|
|
},
|
|
{
|
|
"entropy": 5.162596845626831,
|
|
"epoch": 4.439000960614793,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003181746783489829,
|
|
"loss": 4.5764,
|
|
"mean_token_accuracy": 0.2638874724507332,
|
|
"num_tokens": 105978505.0,
|
|
"step": 46210
|
|
},
|
|
{
|
|
"entropy": 5.168252801895141,
|
|
"epoch": 4.439481268011527,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031814103138592476,
|
|
"loss": 4.6037,
|
|
"mean_token_accuracy": 0.2604906901717186,
|
|
"num_tokens": 105990267.0,
|
|
"step": 46215
|
|
},
|
|
{
|
|
"entropy": 5.190238952636719,
|
|
"epoch": 4.439961575408262,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00031810738342125995,
|
|
"loss": 4.6155,
|
|
"mean_token_accuracy": 0.2580695629119873,
|
|
"num_tokens": 106002001.0,
|
|
"step": 46220
|
|
},
|
|
{
|
|
"entropy": 5.1810383796691895,
|
|
"epoch": 4.440441882804995,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003180737344557696,
|
|
"loss": 4.6409,
|
|
"mean_token_accuracy": 0.25515676438808443,
|
|
"num_tokens": 106012769.0,
|
|
"step": 46225
|
|
},
|
|
{
|
|
"entropy": 5.135845184326172,
|
|
"epoch": 4.4409221902017295,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003180400844902352,
|
|
"loss": 4.5859,
|
|
"mean_token_accuracy": 0.26305958777666094,
|
|
"num_tokens": 106024317.0,
|
|
"step": 46230
|
|
},
|
|
{
|
|
"entropy": 5.100096607208252,
|
|
"epoch": 4.441402497598463,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00031800643352543773,
|
|
"loss": 4.5787,
|
|
"mean_token_accuracy": 0.25977704524993894,
|
|
"num_tokens": 106035589.0,
|
|
"step": 46235
|
|
},
|
|
{
|
|
"entropy": 5.155864810943603,
|
|
"epoch": 4.441882804995197,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003179727815621586,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.25234733819961547,
|
|
"num_tokens": 106047897.0,
|
|
"step": 46240
|
|
},
|
|
{
|
|
"entropy": 5.097609519958496,
|
|
"epoch": 4.442363112391931,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00031793912860117907,
|
|
"loss": 4.5011,
|
|
"mean_token_accuracy": 0.2687606528401375,
|
|
"num_tokens": 106059162.0,
|
|
"step": 46245
|
|
},
|
|
{
|
|
"entropy": 5.19970817565918,
|
|
"epoch": 4.442843419788665,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003179054746432805,
|
|
"loss": 4.6804,
|
|
"mean_token_accuracy": 0.2500298246741295,
|
|
"num_tokens": 106071442.0,
|
|
"step": 46250
|
|
},
|
|
{
|
|
"entropy": 5.158568334579468,
|
|
"epoch": 4.4433237271853985,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00031787181968924417,
|
|
"loss": 4.5774,
|
|
"mean_token_accuracy": 0.2625577196478844,
|
|
"num_tokens": 106081696.0,
|
|
"step": 46255
|
|
},
|
|
{
|
|
"entropy": 5.129904890060425,
|
|
"epoch": 4.443804034582133,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003178381637398515,
|
|
"loss": 4.5822,
|
|
"mean_token_accuracy": 0.2576949164271355,
|
|
"num_tokens": 106093100.0,
|
|
"step": 46260
|
|
},
|
|
{
|
|
"entropy": 5.140468692779541,
|
|
"epoch": 4.444284341978866,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00031780450679588394,
|
|
"loss": 4.5593,
|
|
"mean_token_accuracy": 0.2590827450156212,
|
|
"num_tokens": 106104700.0,
|
|
"step": 46265
|
|
},
|
|
{
|
|
"entropy": 5.184973526000976,
|
|
"epoch": 4.444764649375601,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003177708488581227,
|
|
"loss": 4.5868,
|
|
"mean_token_accuracy": 0.26370437294244764,
|
|
"num_tokens": 106116593.0,
|
|
"step": 46270
|
|
},
|
|
{
|
|
"entropy": 5.167366695404053,
|
|
"epoch": 4.445244956772334,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003177371899273496,
|
|
"loss": 4.6485,
|
|
"mean_token_accuracy": 0.2579072341322899,
|
|
"num_tokens": 106128558.0,
|
|
"step": 46275
|
|
},
|
|
{
|
|
"entropy": 5.253427028656006,
|
|
"epoch": 4.445725264169068,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00031770353000434566,
|
|
"loss": 4.6945,
|
|
"mean_token_accuracy": 0.24707548469305038,
|
|
"num_tokens": 106139309.0,
|
|
"step": 46280
|
|
},
|
|
{
|
|
"entropy": 5.0677062511444095,
|
|
"epoch": 4.446205571565802,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003176698690898925,
|
|
"loss": 4.5399,
|
|
"mean_token_accuracy": 0.26322081983089446,
|
|
"num_tokens": 106150812.0,
|
|
"step": 46285
|
|
},
|
|
{
|
|
"entropy": 5.116785860061645,
|
|
"epoch": 4.446685878962536,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003176362071847719,
|
|
"loss": 4.558,
|
|
"mean_token_accuracy": 0.26739264875650404,
|
|
"num_tokens": 106160986.0,
|
|
"step": 46290
|
|
},
|
|
{
|
|
"entropy": 5.075601387023926,
|
|
"epoch": 4.4471661863592695,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000317602544289765,
|
|
"loss": 4.528,
|
|
"mean_token_accuracy": 0.2680457681417465,
|
|
"num_tokens": 106172125.0,
|
|
"step": 46295
|
|
},
|
|
{
|
|
"entropy": 5.149677991867065,
|
|
"epoch": 4.447646493756004,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00031756888040565355,
|
|
"loss": 4.6191,
|
|
"mean_token_accuracy": 0.2605952173471451,
|
|
"num_tokens": 106185405.0,
|
|
"step": 46300
|
|
},
|
|
{
|
|
"entropy": 5.1604859828948975,
|
|
"epoch": 4.448126801152737,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003175352155332192,
|
|
"loss": 4.5846,
|
|
"mean_token_accuracy": 0.2651383921504021,
|
|
"num_tokens": 106196144.0,
|
|
"step": 46305
|
|
},
|
|
{
|
|
"entropy": 5.081415319442749,
|
|
"epoch": 4.448607108549472,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00031750154967324337,
|
|
"loss": 4.5313,
|
|
"mean_token_accuracy": 0.2685970991849899,
|
|
"num_tokens": 106207708.0,
|
|
"step": 46310
|
|
},
|
|
{
|
|
"entropy": 5.188068437576294,
|
|
"epoch": 4.449087415946206,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00031746788282650774,
|
|
"loss": 4.6492,
|
|
"mean_token_accuracy": 0.26326791048049925,
|
|
"num_tokens": 106218568.0,
|
|
"step": 46315
|
|
},
|
|
{
|
|
"entropy": 5.126815319061279,
|
|
"epoch": 4.449567723342939,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000317434214993794,
|
|
"loss": 4.5639,
|
|
"mean_token_accuracy": 0.2688142225146294,
|
|
"num_tokens": 106231188.0,
|
|
"step": 46320
|
|
},
|
|
{
|
|
"entropy": 5.147946119308472,
|
|
"epoch": 4.450048030739674,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003174005461758838,
|
|
"loss": 4.5909,
|
|
"mean_token_accuracy": 0.26252841353416445,
|
|
"num_tokens": 106242158.0,
|
|
"step": 46325
|
|
},
|
|
{
|
|
"entropy": 5.150395679473877,
|
|
"epoch": 4.450528338136407,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003173668763735588,
|
|
"loss": 4.548,
|
|
"mean_token_accuracy": 0.2647362038493156,
|
|
"num_tokens": 106252382.0,
|
|
"step": 46330
|
|
},
|
|
{
|
|
"entropy": 5.115855741500854,
|
|
"epoch": 4.4510086455331415,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00031733320558760076,
|
|
"loss": 4.6173,
|
|
"mean_token_accuracy": 0.256987065076828,
|
|
"num_tokens": 106265033.0,
|
|
"step": 46335
|
|
},
|
|
{
|
|
"entropy": 5.109643125534058,
|
|
"epoch": 4.451488952929875,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00031729953381879136,
|
|
"loss": 4.6004,
|
|
"mean_token_accuracy": 0.2589674428105354,
|
|
"num_tokens": 106277776.0,
|
|
"step": 46340
|
|
},
|
|
{
|
|
"entropy": 5.035280323028564,
|
|
"epoch": 4.451969260326609,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003172658610679124,
|
|
"loss": 4.5102,
|
|
"mean_token_accuracy": 0.25760049670934676,
|
|
"num_tokens": 106290031.0,
|
|
"step": 46345
|
|
},
|
|
{
|
|
"entropy": 5.158557462692261,
|
|
"epoch": 4.452449567723343,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003172321873357457,
|
|
"loss": 4.6298,
|
|
"mean_token_accuracy": 0.2568785175681114,
|
|
"num_tokens": 106300889.0,
|
|
"step": 46350
|
|
},
|
|
{
|
|
"entropy": 5.179298830032349,
|
|
"epoch": 4.452929875120077,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00031719851262307293,
|
|
"loss": 4.5912,
|
|
"mean_token_accuracy": 0.25777569264173505,
|
|
"num_tokens": 106314321.0,
|
|
"step": 46355
|
|
},
|
|
{
|
|
"entropy": 5.155284118652344,
|
|
"epoch": 4.45341018251681,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000317164836930676,
|
|
"loss": 4.61,
|
|
"mean_token_accuracy": 0.26556937098503114,
|
|
"num_tokens": 106325930.0,
|
|
"step": 46360
|
|
},
|
|
{
|
|
"entropy": 5.170592546463013,
|
|
"epoch": 4.453890489913545,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00031713116025933684,
|
|
"loss": 4.6212,
|
|
"mean_token_accuracy": 0.26732411831617353,
|
|
"num_tokens": 106338295.0,
|
|
"step": 46365
|
|
},
|
|
{
|
|
"entropy": 5.002178621292114,
|
|
"epoch": 4.454370797310278,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031709748260983726,
|
|
"loss": 4.4723,
|
|
"mean_token_accuracy": 0.26599024832248686,
|
|
"num_tokens": 106350140.0,
|
|
"step": 46370
|
|
},
|
|
{
|
|
"entropy": 5.115383768081665,
|
|
"epoch": 4.4548511047070125,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00031706380398295895,
|
|
"loss": 4.5575,
|
|
"mean_token_accuracy": 0.26796778589487075,
|
|
"num_tokens": 106362923.0,
|
|
"step": 46375
|
|
},
|
|
{
|
|
"entropy": 5.106572771072388,
|
|
"epoch": 4.455331412103746,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003170301243794842,
|
|
"loss": 4.616,
|
|
"mean_token_accuracy": 0.25994604974985125,
|
|
"num_tokens": 106374447.0,
|
|
"step": 46380
|
|
},
|
|
{
|
|
"entropy": 5.090517663955689,
|
|
"epoch": 4.45581171950048,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003169964438001948,
|
|
"loss": 4.5328,
|
|
"mean_token_accuracy": 0.27124888747930526,
|
|
"num_tokens": 106386543.0,
|
|
"step": 46385
|
|
},
|
|
{
|
|
"entropy": 5.1520751953125,
|
|
"epoch": 4.456292026897215,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003169627622458725,
|
|
"loss": 4.6298,
|
|
"mean_token_accuracy": 0.2602701738476753,
|
|
"num_tokens": 106397805.0,
|
|
"step": 46390
|
|
},
|
|
{
|
|
"entropy": 5.179045867919922,
|
|
"epoch": 4.456772334293948,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003169290797172996,
|
|
"loss": 4.6573,
|
|
"mean_token_accuracy": 0.25995814949274065,
|
|
"num_tokens": 106409208.0,
|
|
"step": 46395
|
|
},
|
|
{
|
|
"entropy": 5.129957056045532,
|
|
"epoch": 4.457252641690682,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003168953962152578,
|
|
"loss": 4.5271,
|
|
"mean_token_accuracy": 0.2659784182906151,
|
|
"num_tokens": 106421159.0,
|
|
"step": 46400
|
|
},
|
|
{
|
|
"entropy": 5.129201745986938,
|
|
"epoch": 4.457732949087416,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003168617117405295,
|
|
"loss": 4.5881,
|
|
"mean_token_accuracy": 0.2587573692202568,
|
|
"num_tokens": 106432826.0,
|
|
"step": 46405
|
|
},
|
|
{
|
|
"entropy": 5.071657657623291,
|
|
"epoch": 4.45821325648415,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003168280262938965,
|
|
"loss": 4.5097,
|
|
"mean_token_accuracy": 0.26646527647972107,
|
|
"num_tokens": 106443959.0,
|
|
"step": 46410
|
|
},
|
|
{
|
|
"entropy": 5.100129652023315,
|
|
"epoch": 4.458693563880884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003167943398761409,
|
|
"loss": 4.5176,
|
|
"mean_token_accuracy": 0.26846677511930467,
|
|
"num_tokens": 106455087.0,
|
|
"step": 46415
|
|
},
|
|
{
|
|
"entropy": 5.1037146091461185,
|
|
"epoch": 4.459173871277618,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00031676065248804485,
|
|
"loss": 4.4983,
|
|
"mean_token_accuracy": 0.26856127828359605,
|
|
"num_tokens": 106466296.0,
|
|
"step": 46420
|
|
},
|
|
{
|
|
"entropy": 5.152695846557617,
|
|
"epoch": 4.459654178674351,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00031672696413039046,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.2580264866352081,
|
|
"num_tokens": 106476072.0,
|
|
"step": 46425
|
|
},
|
|
{
|
|
"entropy": 5.173234987258911,
|
|
"epoch": 4.460134486071086,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00031669327480395986,
|
|
"loss": 4.6166,
|
|
"mean_token_accuracy": 0.25273537188768386,
|
|
"num_tokens": 106487309.0,
|
|
"step": 46430
|
|
},
|
|
{
|
|
"entropy": 5.189549684524536,
|
|
"epoch": 4.460614793467819,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003166595845095352,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.25258953869342804,
|
|
"num_tokens": 106498661.0,
|
|
"step": 46435
|
|
},
|
|
{
|
|
"entropy": 5.174593162536621,
|
|
"epoch": 4.461095100864553,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00031662589324789873,
|
|
"loss": 4.5895,
|
|
"mean_token_accuracy": 0.2578044295310974,
|
|
"num_tokens": 106509809.0,
|
|
"step": 46440
|
|
},
|
|
{
|
|
"entropy": 5.04389123916626,
|
|
"epoch": 4.461575408261287,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003165922010198326,
|
|
"loss": 4.5288,
|
|
"mean_token_accuracy": 0.268156909942627,
|
|
"num_tokens": 106522662.0,
|
|
"step": 46445
|
|
},
|
|
{
|
|
"entropy": 5.131629562377929,
|
|
"epoch": 4.462055715658021,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00031655850782611903,
|
|
"loss": 4.5581,
|
|
"mean_token_accuracy": 0.2611506417393684,
|
|
"num_tokens": 106534176.0,
|
|
"step": 46450
|
|
},
|
|
{
|
|
"entropy": 5.104534053802491,
|
|
"epoch": 4.462536023054755,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00031652481366754046,
|
|
"loss": 4.5164,
|
|
"mean_token_accuracy": 0.2677989348769188,
|
|
"num_tokens": 106544626.0,
|
|
"step": 46455
|
|
},
|
|
{
|
|
"entropy": 5.1614992141723635,
|
|
"epoch": 4.463016330451489,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003164911185448789,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.2472800761461258,
|
|
"num_tokens": 106557112.0,
|
|
"step": 46460
|
|
},
|
|
{
|
|
"entropy": 5.1936804294586185,
|
|
"epoch": 4.463496637848223,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003164574224589168,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.25661896020174024,
|
|
"num_tokens": 106568226.0,
|
|
"step": 46465
|
|
},
|
|
{
|
|
"entropy": 5.19011344909668,
|
|
"epoch": 4.463976945244957,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0003164237254104364,
|
|
"loss": 4.6087,
|
|
"mean_token_accuracy": 0.2564620167016983,
|
|
"num_tokens": 106580592.0,
|
|
"step": 46470
|
|
},
|
|
{
|
|
"entropy": 5.184396648406983,
|
|
"epoch": 4.464457252641691,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00031639002740022017,
|
|
"loss": 4.6644,
|
|
"mean_token_accuracy": 0.25209841132164,
|
|
"num_tokens": 106591655.0,
|
|
"step": 46475
|
|
},
|
|
{
|
|
"entropy": 5.2232012271881105,
|
|
"epoch": 4.4649375600384245,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003163563284290504,
|
|
"loss": 4.5861,
|
|
"mean_token_accuracy": 0.25850689858198167,
|
|
"num_tokens": 106603852.0,
|
|
"step": 46480
|
|
},
|
|
{
|
|
"entropy": 5.167948150634766,
|
|
"epoch": 4.465417867435159,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00031632262849770945,
|
|
"loss": 4.6248,
|
|
"mean_token_accuracy": 0.25860668271780013,
|
|
"num_tokens": 106616237.0,
|
|
"step": 46485
|
|
},
|
|
{
|
|
"entropy": 5.131333303451538,
|
|
"epoch": 4.465898174831892,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00031628892760697974,
|
|
"loss": 4.6038,
|
|
"mean_token_accuracy": 0.26072167307138444,
|
|
"num_tokens": 106626812.0,
|
|
"step": 46490
|
|
},
|
|
{
|
|
"entropy": 5.092088651657105,
|
|
"epoch": 4.4663784822286265,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00031625522575764374,
|
|
"loss": 4.5462,
|
|
"mean_token_accuracy": 0.2631259098649025,
|
|
"num_tokens": 106636791.0,
|
|
"step": 46495
|
|
},
|
|
{
|
|
"entropy": 5.230707454681396,
|
|
"epoch": 4.46685878962536,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000316221522950484,
|
|
"loss": 4.6652,
|
|
"mean_token_accuracy": 0.2538544699549675,
|
|
"num_tokens": 106647838.0,
|
|
"step": 46500
|
|
},
|
|
{
|
|
"entropy": 5.133999490737915,
|
|
"epoch": 4.467339097022094,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003161878191862829,
|
|
"loss": 4.5277,
|
|
"mean_token_accuracy": 0.26294266134500505,
|
|
"num_tokens": 106659128.0,
|
|
"step": 46505
|
|
},
|
|
{
|
|
"entropy": 5.165821123123169,
|
|
"epoch": 4.467819404418828,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003161541144658228,
|
|
"loss": 4.6339,
|
|
"mean_token_accuracy": 0.26410067081451416,
|
|
"num_tokens": 106670276.0,
|
|
"step": 46510
|
|
},
|
|
{
|
|
"entropy": 5.139694452285767,
|
|
"epoch": 4.468299711815562,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00031612040878988647,
|
|
"loss": 4.573,
|
|
"mean_token_accuracy": 0.2577462956309319,
|
|
"num_tokens": 106681199.0,
|
|
"step": 46515
|
|
},
|
|
{
|
|
"entropy": 5.112558269500733,
|
|
"epoch": 4.4687800192122955,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00031608670215925634,
|
|
"loss": 4.592,
|
|
"mean_token_accuracy": 0.2614708334207535,
|
|
"num_tokens": 106693544.0,
|
|
"step": 46520
|
|
},
|
|
{
|
|
"entropy": 5.050999736785888,
|
|
"epoch": 4.46926032660903,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031605299457471495,
|
|
"loss": 4.5124,
|
|
"mean_token_accuracy": 0.2678926408290863,
|
|
"num_tokens": 106704390.0,
|
|
"step": 46525
|
|
},
|
|
{
|
|
"entropy": 5.208313798904419,
|
|
"epoch": 4.469740634005763,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003160192860370449,
|
|
"loss": 4.6168,
|
|
"mean_token_accuracy": 0.2595024600625038,
|
|
"num_tokens": 106715620.0,
|
|
"step": 46530
|
|
},
|
|
{
|
|
"entropy": 5.2211864471435545,
|
|
"epoch": 4.470220941402498,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00031598557654702894,
|
|
"loss": 4.6825,
|
|
"mean_token_accuracy": 0.24961092919111252,
|
|
"num_tokens": 106726541.0,
|
|
"step": 46535
|
|
},
|
|
{
|
|
"entropy": 5.148000192642212,
|
|
"epoch": 4.470701248799232,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00031595186610544954,
|
|
"loss": 4.6239,
|
|
"mean_token_accuracy": 0.2554412856698036,
|
|
"num_tokens": 106737317.0,
|
|
"step": 46540
|
|
},
|
|
{
|
|
"entropy": 5.110741710662841,
|
|
"epoch": 4.471181556195965,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00031591815471308945,
|
|
"loss": 4.5011,
|
|
"mean_token_accuracy": 0.266099688410759,
|
|
"num_tokens": 106749634.0,
|
|
"step": 46545
|
|
},
|
|
{
|
|
"entropy": 5.103863191604614,
|
|
"epoch": 4.4716618635927,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003158844423707312,
|
|
"loss": 4.5895,
|
|
"mean_token_accuracy": 0.2627899721264839,
|
|
"num_tokens": 106760674.0,
|
|
"step": 46550
|
|
},
|
|
{
|
|
"entropy": 5.257110548019409,
|
|
"epoch": 4.472142170989433,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003158507290791577,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.25021951347589494,
|
|
"num_tokens": 106772783.0,
|
|
"step": 46555
|
|
},
|
|
{
|
|
"entropy": 5.094980096817016,
|
|
"epoch": 4.472622478386167,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00031581701483915153,
|
|
"loss": 4.4848,
|
|
"mean_token_accuracy": 0.27870102077722547,
|
|
"num_tokens": 106785379.0,
|
|
"step": 46560
|
|
},
|
|
{
|
|
"entropy": 5.092818975448608,
|
|
"epoch": 4.473102785782901,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00031578329965149544,
|
|
"loss": 4.5622,
|
|
"mean_token_accuracy": 0.2677202865481377,
|
|
"num_tokens": 106796185.0,
|
|
"step": 46565
|
|
},
|
|
{
|
|
"entropy": 5.163872480392456,
|
|
"epoch": 4.473583093179635,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003157495835169723,
|
|
"loss": 4.6535,
|
|
"mean_token_accuracy": 0.2587351143360138,
|
|
"num_tokens": 106807880.0,
|
|
"step": 46570
|
|
},
|
|
{
|
|
"entropy": 5.155999422073364,
|
|
"epoch": 4.474063400576369,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003157158664363648,
|
|
"loss": 4.4734,
|
|
"mean_token_accuracy": 0.2736100241541862,
|
|
"num_tokens": 106818837.0,
|
|
"step": 46575
|
|
},
|
|
{
|
|
"entropy": 5.069994783401489,
|
|
"epoch": 4.474543707973103,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00031568214841045576,
|
|
"loss": 4.5403,
|
|
"mean_token_accuracy": 0.2658812403678894,
|
|
"num_tokens": 106829606.0,
|
|
"step": 46580
|
|
},
|
|
{
|
|
"entropy": 5.018946409225464,
|
|
"epoch": 4.475024015369836,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003156484294400281,
|
|
"loss": 4.5129,
|
|
"mean_token_accuracy": 0.2635155215859413,
|
|
"num_tokens": 106840218.0,
|
|
"step": 46585
|
|
},
|
|
{
|
|
"entropy": 5.08992829322815,
|
|
"epoch": 4.475504322766571,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003156147095258646,
|
|
"loss": 4.5449,
|
|
"mean_token_accuracy": 0.26863447576761246,
|
|
"num_tokens": 106852020.0,
|
|
"step": 46590
|
|
},
|
|
{
|
|
"entropy": 5.15488076210022,
|
|
"epoch": 4.475984630163304,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00031558098866874814,
|
|
"loss": 4.5802,
|
|
"mean_token_accuracy": 0.26343035101890566,
|
|
"num_tokens": 106863068.0,
|
|
"step": 46595
|
|
},
|
|
{
|
|
"entropy": 5.178683710098267,
|
|
"epoch": 4.4764649375600385,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00031554726686946154,
|
|
"loss": 4.6191,
|
|
"mean_token_accuracy": 0.2631751671433449,
|
|
"num_tokens": 106874319.0,
|
|
"step": 46600
|
|
},
|
|
{
|
|
"entropy": 5.17664065361023,
|
|
"epoch": 4.476945244956772,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000315513544128788,
|
|
"loss": 4.5648,
|
|
"mean_token_accuracy": 0.2710418522357941,
|
|
"num_tokens": 106886332.0,
|
|
"step": 46605
|
|
},
|
|
{
|
|
"entropy": 5.144386672973633,
|
|
"epoch": 4.477425552353506,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003154798204475101,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.25903773605823516,
|
|
"num_tokens": 106898976.0,
|
|
"step": 46610
|
|
},
|
|
{
|
|
"entropy": 5.175751161575318,
|
|
"epoch": 4.477905859750241,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003154460958264109,
|
|
"loss": 4.5538,
|
|
"mean_token_accuracy": 0.265854586660862,
|
|
"num_tokens": 106911078.0,
|
|
"step": 46615
|
|
},
|
|
{
|
|
"entropy": 5.185583972930909,
|
|
"epoch": 4.478386167146974,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003154123702662737,
|
|
"loss": 4.6146,
|
|
"mean_token_accuracy": 0.26666151732206345,
|
|
"num_tokens": 106922980.0,
|
|
"step": 46620
|
|
},
|
|
{
|
|
"entropy": 5.176249933242798,
|
|
"epoch": 4.478866474543708,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003153786437678811,
|
|
"loss": 4.6596,
|
|
"mean_token_accuracy": 0.25529248267412186,
|
|
"num_tokens": 106935361.0,
|
|
"step": 46625
|
|
},
|
|
{
|
|
"entropy": 5.073743677139282,
|
|
"epoch": 4.479346781940442,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003153449163320163,
|
|
"loss": 4.4435,
|
|
"mean_token_accuracy": 0.2717399924993515,
|
|
"num_tokens": 106947104.0,
|
|
"step": 46630
|
|
},
|
|
{
|
|
"entropy": 5.2034321308135985,
|
|
"epoch": 4.479827089337176,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003153111879594623,
|
|
"loss": 4.6538,
|
|
"mean_token_accuracy": 0.2516124129295349,
|
|
"num_tokens": 106958886.0,
|
|
"step": 46635
|
|
},
|
|
{
|
|
"entropy": 5.050293684005737,
|
|
"epoch": 4.4803073967339095,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003152774586510023,
|
|
"loss": 4.4503,
|
|
"mean_token_accuracy": 0.27442231476306916,
|
|
"num_tokens": 106970156.0,
|
|
"step": 46640
|
|
},
|
|
{
|
|
"entropy": 5.1299420356750485,
|
|
"epoch": 4.480787704130644,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003152437284074193,
|
|
"loss": 4.6029,
|
|
"mean_token_accuracy": 0.2569826185703278,
|
|
"num_tokens": 106980426.0,
|
|
"step": 46645
|
|
},
|
|
{
|
|
"entropy": 5.08372220993042,
|
|
"epoch": 4.481268011527377,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003152099972294964,
|
|
"loss": 4.5179,
|
|
"mean_token_accuracy": 0.27336700558662413,
|
|
"num_tokens": 106991348.0,
|
|
"step": 46650
|
|
},
|
|
{
|
|
"entropy": 5.101139926910401,
|
|
"epoch": 4.481748318924112,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003151762651180168,
|
|
"loss": 4.4942,
|
|
"mean_token_accuracy": 0.2745892956852913,
|
|
"num_tokens": 107002414.0,
|
|
"step": 46655
|
|
},
|
|
{
|
|
"entropy": 5.062525987625122,
|
|
"epoch": 4.482228626320845,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00031514253207376355,
|
|
"loss": 4.5264,
|
|
"mean_token_accuracy": 0.2686831921339035,
|
|
"num_tokens": 107014729.0,
|
|
"step": 46660
|
|
},
|
|
{
|
|
"entropy": 5.131894302368164,
|
|
"epoch": 4.482708933717579,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00031510879809751996,
|
|
"loss": 4.5935,
|
|
"mean_token_accuracy": 0.2645442247390747,
|
|
"num_tokens": 107026699.0,
|
|
"step": 46665
|
|
},
|
|
{
|
|
"entropy": 5.09635739326477,
|
|
"epoch": 4.483189241114313,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00031507506319006917,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.25910301208496095,
|
|
"num_tokens": 107038474.0,
|
|
"step": 46670
|
|
},
|
|
{
|
|
"entropy": 5.149727392196655,
|
|
"epoch": 4.483669548511047,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00031504132735219435,
|
|
"loss": 4.6245,
|
|
"mean_token_accuracy": 0.26294084787368777,
|
|
"num_tokens": 107049459.0,
|
|
"step": 46675
|
|
},
|
|
{
|
|
"entropy": 5.066495943069458,
|
|
"epoch": 4.484149855907781,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00031500759058467894,
|
|
"loss": 4.5145,
|
|
"mean_token_accuracy": 0.269680018723011,
|
|
"num_tokens": 107060162.0,
|
|
"step": 46680
|
|
},
|
|
{
|
|
"entropy": 5.1414875984191895,
|
|
"epoch": 4.484630163304515,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000314973852888306,
|
|
"loss": 4.6176,
|
|
"mean_token_accuracy": 0.2615502431988716,
|
|
"num_tokens": 107072532.0,
|
|
"step": 46685
|
|
},
|
|
{
|
|
"entropy": 5.111404943466186,
|
|
"epoch": 4.485110470701249,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003149401142638589,
|
|
"loss": 4.5062,
|
|
"mean_token_accuracy": 0.2642358556389809,
|
|
"num_tokens": 107084070.0,
|
|
"step": 46690
|
|
},
|
|
{
|
|
"entropy": 5.135853099822998,
|
|
"epoch": 4.485590778097983,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00031490637471212087,
|
|
"loss": 4.6003,
|
|
"mean_token_accuracy": 0.27117839008569716,
|
|
"num_tokens": 107096089.0,
|
|
"step": 46695
|
|
},
|
|
{
|
|
"entropy": 5.242606496810913,
|
|
"epoch": 4.486071085494717,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00031487263423387544,
|
|
"loss": 4.6342,
|
|
"mean_token_accuracy": 0.25787136554718015,
|
|
"num_tokens": 107107596.0,
|
|
"step": 46700
|
|
},
|
|
{
|
|
"entropy": 5.15226731300354,
|
|
"epoch": 4.48655139289145,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00031483889282990567,
|
|
"loss": 4.5981,
|
|
"mean_token_accuracy": 0.25746562629938125,
|
|
"num_tokens": 107119205.0,
|
|
"step": 46705
|
|
},
|
|
{
|
|
"entropy": 5.131657552719116,
|
|
"epoch": 4.487031700288185,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00031480515050099527,
|
|
"loss": 4.5994,
|
|
"mean_token_accuracy": 0.2581554800271988,
|
|
"num_tokens": 107131341.0,
|
|
"step": 46710
|
|
},
|
|
{
|
|
"entropy": 5.13301420211792,
|
|
"epoch": 4.487512007684918,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003147714072479275,
|
|
"loss": 4.5718,
|
|
"mean_token_accuracy": 0.25658624023199084,
|
|
"num_tokens": 107142846.0,
|
|
"step": 46715
|
|
},
|
|
{
|
|
"entropy": 5.175748252868653,
|
|
"epoch": 4.4879923150816525,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003147376630714856,
|
|
"loss": 4.7056,
|
|
"mean_token_accuracy": 0.24445035606622695,
|
|
"num_tokens": 107154300.0,
|
|
"step": 46720
|
|
},
|
|
{
|
|
"entropy": 5.208631896972657,
|
|
"epoch": 4.488472622478386,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003147039179724533,
|
|
"loss": 4.6218,
|
|
"mean_token_accuracy": 0.26329073309898376,
|
|
"num_tokens": 107166387.0,
|
|
"step": 46725
|
|
},
|
|
{
|
|
"entropy": 5.290952110290528,
|
|
"epoch": 4.48895292987512,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00031467017195161383,
|
|
"loss": 4.753,
|
|
"mean_token_accuracy": 0.25371029824018476,
|
|
"num_tokens": 107179848.0,
|
|
"step": 46730
|
|
},
|
|
{
|
|
"entropy": 5.123053312301636,
|
|
"epoch": 4.489433237271854,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003146364250097508,
|
|
"loss": 4.6288,
|
|
"mean_token_accuracy": 0.2669411689043045,
|
|
"num_tokens": 107192837.0,
|
|
"step": 46735
|
|
},
|
|
{
|
|
"entropy": 5.129690456390381,
|
|
"epoch": 4.489913544668588,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003146026771476476,
|
|
"loss": 4.5418,
|
|
"mean_token_accuracy": 0.2610920801758766,
|
|
"num_tokens": 107204055.0,
|
|
"step": 46740
|
|
},
|
|
{
|
|
"entropy": 5.139398574829102,
|
|
"epoch": 4.4903938520653215,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00031456892836608793,
|
|
"loss": 4.5754,
|
|
"mean_token_accuracy": 0.2652928903698921,
|
|
"num_tokens": 107216144.0,
|
|
"step": 46745
|
|
},
|
|
{
|
|
"entropy": 5.162866306304932,
|
|
"epoch": 4.490874159462056,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00031453517866585523,
|
|
"loss": 4.5183,
|
|
"mean_token_accuracy": 0.2637603208422661,
|
|
"num_tokens": 107227970.0,
|
|
"step": 46750
|
|
},
|
|
{
|
|
"entropy": 5.096026515960693,
|
|
"epoch": 4.491354466858789,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000314501428047733,
|
|
"loss": 4.5749,
|
|
"mean_token_accuracy": 0.264169254899025,
|
|
"num_tokens": 107237765.0,
|
|
"step": 46755
|
|
},
|
|
{
|
|
"entropy": 5.156500911712646,
|
|
"epoch": 4.491834774255524,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00031446767651250495,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.2579173818230629,
|
|
"num_tokens": 107249298.0,
|
|
"step": 46760
|
|
},
|
|
{
|
|
"entropy": 5.2402420997619625,
|
|
"epoch": 4.492315081652258,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00031443392406095474,
|
|
"loss": 4.7002,
|
|
"mean_token_accuracy": 0.2565635025501251,
|
|
"num_tokens": 107260856.0,
|
|
"step": 46765
|
|
},
|
|
{
|
|
"entropy": 5.1603728294372555,
|
|
"epoch": 4.492795389048991,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003144001706938658,
|
|
"loss": 4.6299,
|
|
"mean_token_accuracy": 0.2603905752301216,
|
|
"num_tokens": 107272027.0,
|
|
"step": 46770
|
|
},
|
|
{
|
|
"entropy": 5.1024336338043215,
|
|
"epoch": 4.493275696445726,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003143664164120219,
|
|
"loss": 4.5483,
|
|
"mean_token_accuracy": 0.2689643755555153,
|
|
"num_tokens": 107284918.0,
|
|
"step": 46775
|
|
},
|
|
{
|
|
"entropy": 5.159958410263061,
|
|
"epoch": 4.493756003842459,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00031433266121620675,
|
|
"loss": 4.5522,
|
|
"mean_token_accuracy": 0.26106765270233157,
|
|
"num_tokens": 107297270.0,
|
|
"step": 46780
|
|
},
|
|
{
|
|
"entropy": 5.17169156074524,
|
|
"epoch": 4.494236311239193,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00031429890510720394,
|
|
"loss": 4.5761,
|
|
"mean_token_accuracy": 0.2559016510844231,
|
|
"num_tokens": 107308846.0,
|
|
"step": 46785
|
|
},
|
|
{
|
|
"entropy": 5.113909482955933,
|
|
"epoch": 4.494716618635927,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003142651480857973,
|
|
"loss": 4.5442,
|
|
"mean_token_accuracy": 0.2633185416460037,
|
|
"num_tokens": 107319958.0,
|
|
"step": 46790
|
|
},
|
|
{
|
|
"entropy": 5.099543857574463,
|
|
"epoch": 4.495196926032661,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003142313901527705,
|
|
"loss": 4.5401,
|
|
"mean_token_accuracy": 0.2621121063828468,
|
|
"num_tokens": 107329451.0,
|
|
"step": 46795
|
|
},
|
|
{
|
|
"entropy": 5.157245063781739,
|
|
"epoch": 4.495677233429395,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003141976313089073,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.26905693113803864,
|
|
"num_tokens": 107340362.0,
|
|
"step": 46800
|
|
},
|
|
{
|
|
"entropy": 5.1453570365905765,
|
|
"epoch": 4.496157540826129,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003141638715549915,
|
|
"loss": 4.5954,
|
|
"mean_token_accuracy": 0.2601718693971634,
|
|
"num_tokens": 107351765.0,
|
|
"step": 46805
|
|
},
|
|
{
|
|
"entropy": 5.175242614746094,
|
|
"epoch": 4.496637848222862,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003141301108918069,
|
|
"loss": 4.5918,
|
|
"mean_token_accuracy": 0.254553858935833,
|
|
"num_tokens": 107362506.0,
|
|
"step": 46810
|
|
},
|
|
{
|
|
"entropy": 5.160025501251221,
|
|
"epoch": 4.497118155619597,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003140963493201373,
|
|
"loss": 4.6393,
|
|
"mean_token_accuracy": 0.2614226952195168,
|
|
"num_tokens": 107374671.0,
|
|
"step": 46815
|
|
},
|
|
{
|
|
"entropy": 5.0634352684021,
|
|
"epoch": 4.49759846301633,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003140625868407666,
|
|
"loss": 4.5121,
|
|
"mean_token_accuracy": 0.2637395352125168,
|
|
"num_tokens": 107387183.0,
|
|
"step": 46820
|
|
},
|
|
{
|
|
"entropy": 5.164198732376098,
|
|
"epoch": 4.4980787704130645,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003140288234544786,
|
|
"loss": 4.6422,
|
|
"mean_token_accuracy": 0.2618013069033623,
|
|
"num_tokens": 107399194.0,
|
|
"step": 46825
|
|
},
|
|
{
|
|
"entropy": 5.205396127700806,
|
|
"epoch": 4.498559077809798,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00031399505916205716,
|
|
"loss": 4.6708,
|
|
"mean_token_accuracy": 0.25112498849630355,
|
|
"num_tokens": 107411359.0,
|
|
"step": 46830
|
|
},
|
|
{
|
|
"entropy": 5.073951339721679,
|
|
"epoch": 4.499039385206532,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00031396129396428637,
|
|
"loss": 4.4924,
|
|
"mean_token_accuracy": 0.2727199882268906,
|
|
"num_tokens": 107422175.0,
|
|
"step": 46835
|
|
},
|
|
{
|
|
"entropy": 5.163666820526123,
|
|
"epoch": 4.499519692603266,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003139275278619499,
|
|
"loss": 4.6047,
|
|
"mean_token_accuracy": 0.26017808765172956,
|
|
"num_tokens": 107433774.0,
|
|
"step": 46840
|
|
},
|
|
{
|
|
"entropy": 5.094046401977539,
|
|
"epoch": 4.5,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00031389376085583183,
|
|
"loss": 4.5019,
|
|
"mean_token_accuracy": 0.27058389633893964,
|
|
"num_tokens": 107444913.0,
|
|
"step": 46845
|
|
},
|
|
{
|
|
"entropy": 5.012411069869995,
|
|
"epoch": 4.500480307396733,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00031385999294671627,
|
|
"loss": 4.4815,
|
|
"mean_token_accuracy": 0.2694822669029236,
|
|
"num_tokens": 107456049.0,
|
|
"step": 46850
|
|
},
|
|
{
|
|
"entropy": 5.103353261947632,
|
|
"epoch": 4.500960614793468,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031382622413538686,
|
|
"loss": 4.4664,
|
|
"mean_token_accuracy": 0.26912141889333724,
|
|
"num_tokens": 107466889.0,
|
|
"step": 46855
|
|
},
|
|
{
|
|
"entropy": 5.07802448272705,
|
|
"epoch": 4.501440922190202,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003137924544226279,
|
|
"loss": 4.4919,
|
|
"mean_token_accuracy": 0.26420239806175233,
|
|
"num_tokens": 107477470.0,
|
|
"step": 46860
|
|
},
|
|
{
|
|
"entropy": 5.258159494400024,
|
|
"epoch": 4.5019212295869355,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003137586838092234,
|
|
"loss": 4.6408,
|
|
"mean_token_accuracy": 0.25742229670286176,
|
|
"num_tokens": 107488277.0,
|
|
"step": 46865
|
|
},
|
|
{
|
|
"entropy": 5.092199516296387,
|
|
"epoch": 4.50240153698367,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003137249122959573,
|
|
"loss": 4.4928,
|
|
"mean_token_accuracy": 0.2689651295542717,
|
|
"num_tokens": 107499986.0,
|
|
"step": 46870
|
|
},
|
|
{
|
|
"entropy": 5.143657636642456,
|
|
"epoch": 4.502881844380403,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003136911398836137,
|
|
"loss": 4.605,
|
|
"mean_token_accuracy": 0.25678486824035646,
|
|
"num_tokens": 107511645.0,
|
|
"step": 46875
|
|
},
|
|
{
|
|
"entropy": 5.045027399063111,
|
|
"epoch": 4.503362151777138,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003136573665729768,
|
|
"loss": 4.4524,
|
|
"mean_token_accuracy": 0.27436264902353286,
|
|
"num_tokens": 107523128.0,
|
|
"step": 46880
|
|
},
|
|
{
|
|
"entropy": 5.175086259841919,
|
|
"epoch": 4.503842459173871,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00031362359236483054,
|
|
"loss": 4.5827,
|
|
"mean_token_accuracy": 0.2630594775080681,
|
|
"num_tokens": 107533403.0,
|
|
"step": 46885
|
|
},
|
|
{
|
|
"entropy": 5.171788024902344,
|
|
"epoch": 4.504322766570605,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003135898172599592,
|
|
"loss": 4.6561,
|
|
"mean_token_accuracy": 0.2559518158435822,
|
|
"num_tokens": 107545351.0,
|
|
"step": 46890
|
|
},
|
|
{
|
|
"entropy": 5.153297328948975,
|
|
"epoch": 4.504803073967339,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003135560412591469,
|
|
"loss": 4.5999,
|
|
"mean_token_accuracy": 0.26324855387210844,
|
|
"num_tokens": 107557373.0,
|
|
"step": 46895
|
|
},
|
|
{
|
|
"entropy": 5.163750219345093,
|
|
"epoch": 4.505283381364073,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00031352226436317783,
|
|
"loss": 4.6212,
|
|
"mean_token_accuracy": 0.2686105862259865,
|
|
"num_tokens": 107567797.0,
|
|
"step": 46900
|
|
},
|
|
{
|
|
"entropy": 5.1416443347930905,
|
|
"epoch": 4.505763688760807,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003134884865728361,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.2655664995312691,
|
|
"num_tokens": 107580180.0,
|
|
"step": 46905
|
|
},
|
|
{
|
|
"entropy": 5.157508182525635,
|
|
"epoch": 4.506243996157541,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003134547078889061,
|
|
"loss": 4.5471,
|
|
"mean_token_accuracy": 0.26428724378347396,
|
|
"num_tokens": 107591774.0,
|
|
"step": 46910
|
|
},
|
|
{
|
|
"entropy": 5.128235530853272,
|
|
"epoch": 4.506724303554275,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003134209283121719,
|
|
"loss": 4.5438,
|
|
"mean_token_accuracy": 0.2670888140797615,
|
|
"num_tokens": 107602666.0,
|
|
"step": 46915
|
|
},
|
|
{
|
|
"entropy": 5.135719251632691,
|
|
"epoch": 4.507204610951009,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00031338714784341783,
|
|
"loss": 4.6012,
|
|
"mean_token_accuracy": 0.2660928711295128,
|
|
"num_tokens": 107614178.0,
|
|
"step": 46920
|
|
},
|
|
{
|
|
"entropy": 5.162547302246094,
|
|
"epoch": 4.507684918347742,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003133533664834282,
|
|
"loss": 4.5987,
|
|
"mean_token_accuracy": 0.2658671885728836,
|
|
"num_tokens": 107625317.0,
|
|
"step": 46925
|
|
},
|
|
{
|
|
"entropy": 5.124245071411133,
|
|
"epoch": 4.508165225744476,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00031331958423298724,
|
|
"loss": 4.5205,
|
|
"mean_token_accuracy": 0.2693567767739296,
|
|
"num_tokens": 107635541.0,
|
|
"step": 46930
|
|
},
|
|
{
|
|
"entropy": 5.12055778503418,
|
|
"epoch": 4.508645533141211,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003132858010928794,
|
|
"loss": 4.5544,
|
|
"mean_token_accuracy": 0.26346999406814575,
|
|
"num_tokens": 107646236.0,
|
|
"step": 46935
|
|
},
|
|
{
|
|
"entropy": 5.166465854644775,
|
|
"epoch": 4.509125840537944,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00031325201706388885,
|
|
"loss": 4.5689,
|
|
"mean_token_accuracy": 0.27133465856313704,
|
|
"num_tokens": 107656488.0,
|
|
"step": 46940
|
|
},
|
|
{
|
|
"entropy": 5.167819595336914,
|
|
"epoch": 4.5096061479346785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00031321823214680014,
|
|
"loss": 4.6388,
|
|
"mean_token_accuracy": 0.25563739985227585,
|
|
"num_tokens": 107668909.0,
|
|
"step": 46945
|
|
},
|
|
{
|
|
"entropy": 5.2417436122894285,
|
|
"epoch": 4.510086455331412,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00031318444634239744,
|
|
"loss": 4.6704,
|
|
"mean_token_accuracy": 0.2572039529681206,
|
|
"num_tokens": 107680777.0,
|
|
"step": 46950
|
|
},
|
|
{
|
|
"entropy": 5.08076491355896,
|
|
"epoch": 4.510566762728146,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003131506596514654,
|
|
"loss": 4.5381,
|
|
"mean_token_accuracy": 0.26299232691526414,
|
|
"num_tokens": 107692004.0,
|
|
"step": 46955
|
|
},
|
|
{
|
|
"entropy": 5.068270683288574,
|
|
"epoch": 4.51104707012488,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003131168720747883,
|
|
"loss": 4.4821,
|
|
"mean_token_accuracy": 0.27404215931892395,
|
|
"num_tokens": 107703743.0,
|
|
"step": 46960
|
|
},
|
|
{
|
|
"entropy": 5.155953741073608,
|
|
"epoch": 4.511527377521614,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003130830836131505,
|
|
"loss": 4.6479,
|
|
"mean_token_accuracy": 0.2510222628712654,
|
|
"num_tokens": 107715703.0,
|
|
"step": 46965
|
|
},
|
|
{
|
|
"entropy": 5.188218450546264,
|
|
"epoch": 4.5120076849183475,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003130492942673367,
|
|
"loss": 4.5715,
|
|
"mean_token_accuracy": 0.25861710458993914,
|
|
"num_tokens": 107726548.0,
|
|
"step": 46970
|
|
},
|
|
{
|
|
"entropy": 5.190022134780884,
|
|
"epoch": 4.512487992315082,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031301550403813126,
|
|
"loss": 4.6003,
|
|
"mean_token_accuracy": 0.26696711778640747,
|
|
"num_tokens": 107737863.0,
|
|
"step": 46975
|
|
},
|
|
{
|
|
"entropy": 5.159373331069946,
|
|
"epoch": 4.512968299711815,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003129817129263188,
|
|
"loss": 4.6075,
|
|
"mean_token_accuracy": 0.25776650458574296,
|
|
"num_tokens": 107750049.0,
|
|
"step": 46980
|
|
},
|
|
{
|
|
"entropy": 5.151925849914551,
|
|
"epoch": 4.51344860710855,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003129479209326835,
|
|
"loss": 4.5637,
|
|
"mean_token_accuracy": 0.2665475532412529,
|
|
"num_tokens": 107761970.0,
|
|
"step": 46985
|
|
},
|
|
{
|
|
"entropy": 5.1686547756195065,
|
|
"epoch": 4.513928914505283,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00031291412805801034,
|
|
"loss": 4.6338,
|
|
"mean_token_accuracy": 0.25809730738401415,
|
|
"num_tokens": 107773391.0,
|
|
"step": 46990
|
|
},
|
|
{
|
|
"entropy": 5.11414794921875,
|
|
"epoch": 4.514409221902017,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003128803343030836,
|
|
"loss": 4.5763,
|
|
"mean_token_accuracy": 0.2590529501438141,
|
|
"num_tokens": 107785077.0,
|
|
"step": 46995
|
|
},
|
|
{
|
|
"entropy": 5.1427209854125975,
|
|
"epoch": 4.514889529298751,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00031284653966868813,
|
|
"loss": 4.6042,
|
|
"mean_token_accuracy": 0.26207347512245177,
|
|
"num_tokens": 107795969.0,
|
|
"step": 47000
|
|
},
|
|
{
|
|
"entropy": 5.120113277435303,
|
|
"epoch": 4.515369836695485,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00031281274415560827,
|
|
"loss": 4.4651,
|
|
"mean_token_accuracy": 0.2782075583934784,
|
|
"num_tokens": 107806547.0,
|
|
"step": 47005
|
|
},
|
|
{
|
|
"entropy": 5.203797626495361,
|
|
"epoch": 4.515850144092219,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003127789477646288,
|
|
"loss": 4.6499,
|
|
"mean_token_accuracy": 0.259654675424099,
|
|
"num_tokens": 107818131.0,
|
|
"step": 47010
|
|
},
|
|
{
|
|
"entropy": 5.0914306640625,
|
|
"epoch": 4.516330451488953,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003127451504965344,
|
|
"loss": 4.5762,
|
|
"mean_token_accuracy": 0.26542615592479707,
|
|
"num_tokens": 107830346.0,
|
|
"step": 47015
|
|
},
|
|
{
|
|
"entropy": 5.063179683685303,
|
|
"epoch": 4.516810758885687,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003127113523521096,
|
|
"loss": 4.6021,
|
|
"mean_token_accuracy": 0.25794881731271746,
|
|
"num_tokens": 107841094.0,
|
|
"step": 47020
|
|
},
|
|
{
|
|
"entropy": 5.130602550506592,
|
|
"epoch": 4.517291066282421,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003126775533321392,
|
|
"loss": 4.6137,
|
|
"mean_token_accuracy": 0.25916487723588943,
|
|
"num_tokens": 107852951.0,
|
|
"step": 47025
|
|
},
|
|
{
|
|
"entropy": 5.130568122863769,
|
|
"epoch": 4.517771373679155,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000312643753437408,
|
|
"loss": 4.5248,
|
|
"mean_token_accuracy": 0.26682072430849074,
|
|
"num_tokens": 107864008.0,
|
|
"step": 47030
|
|
},
|
|
{
|
|
"entropy": 5.059652280807495,
|
|
"epoch": 4.518251681075888,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003126099526687005,
|
|
"loss": 4.4644,
|
|
"mean_token_accuracy": 0.2711885213851929,
|
|
"num_tokens": 107874522.0,
|
|
"step": 47035
|
|
},
|
|
{
|
|
"entropy": 5.072616386413574,
|
|
"epoch": 4.518731988472623,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00031257615102680154,
|
|
"loss": 4.5657,
|
|
"mean_token_accuracy": 0.25990397334098814,
|
|
"num_tokens": 107886832.0,
|
|
"step": 47040
|
|
},
|
|
{
|
|
"entropy": 5.175554990768433,
|
|
"epoch": 4.519212295869356,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00031254234851249606,
|
|
"loss": 4.6097,
|
|
"mean_token_accuracy": 0.26119676530361174,
|
|
"num_tokens": 107897361.0,
|
|
"step": 47045
|
|
},
|
|
{
|
|
"entropy": 5.1662712574005125,
|
|
"epoch": 4.5196926032660905,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00031250854512656864,
|
|
"loss": 4.5302,
|
|
"mean_token_accuracy": 0.2708177015185356,
|
|
"num_tokens": 107908097.0,
|
|
"step": 47050
|
|
},
|
|
{
|
|
"entropy": 5.1787714004516605,
|
|
"epoch": 4.520172910662824,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003124747408698042,
|
|
"loss": 4.5839,
|
|
"mean_token_accuracy": 0.2660163462162018,
|
|
"num_tokens": 107919317.0,
|
|
"step": 47055
|
|
},
|
|
{
|
|
"entropy": 5.223200559616089,
|
|
"epoch": 4.520653218059558,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003124409357429876,
|
|
"loss": 4.6538,
|
|
"mean_token_accuracy": 0.2600343689322472,
|
|
"num_tokens": 107930459.0,
|
|
"step": 47060
|
|
},
|
|
{
|
|
"entropy": 5.200553274154663,
|
|
"epoch": 4.521133525456292,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031240712974690355,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.25732541382312774,
|
|
"num_tokens": 107942292.0,
|
|
"step": 47065
|
|
},
|
|
{
|
|
"entropy": 5.131164312362671,
|
|
"epoch": 4.521613832853026,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00031237332288233704,
|
|
"loss": 4.5542,
|
|
"mean_token_accuracy": 0.26368818879127504,
|
|
"num_tokens": 107954348.0,
|
|
"step": 47070
|
|
},
|
|
{
|
|
"entropy": 5.120088672637939,
|
|
"epoch": 4.522094140249759,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00031233951515007306,
|
|
"loss": 4.5902,
|
|
"mean_token_accuracy": 0.25970966219902036,
|
|
"num_tokens": 107966068.0,
|
|
"step": 47075
|
|
},
|
|
{
|
|
"entropy": 5.165735721588135,
|
|
"epoch": 4.522574447646494,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003123057065508964,
|
|
"loss": 4.5838,
|
|
"mean_token_accuracy": 0.26268898248672484,
|
|
"num_tokens": 107977001.0,
|
|
"step": 47080
|
|
},
|
|
{
|
|
"entropy": 5.130688238143921,
|
|
"epoch": 4.523054755043228,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003122718970855918,
|
|
"loss": 4.5039,
|
|
"mean_token_accuracy": 0.26749507933855055,
|
|
"num_tokens": 107989016.0,
|
|
"step": 47085
|
|
},
|
|
{
|
|
"entropy": 5.148554992675781,
|
|
"epoch": 4.5235350624399615,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003122380867549447,
|
|
"loss": 4.6243,
|
|
"mean_token_accuracy": 0.25620309710502626,
|
|
"num_tokens": 107998828.0,
|
|
"step": 47090
|
|
},
|
|
{
|
|
"entropy": 5.1195981979370115,
|
|
"epoch": 4.524015369836696,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00031220427555973964,
|
|
"loss": 4.5572,
|
|
"mean_token_accuracy": 0.2617711767554283,
|
|
"num_tokens": 108010038.0,
|
|
"step": 47095
|
|
},
|
|
{
|
|
"entropy": 5.118233489990234,
|
|
"epoch": 4.524495677233429,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00031217046350076177,
|
|
"loss": 4.5557,
|
|
"mean_token_accuracy": 0.2632151022553444,
|
|
"num_tokens": 108022036.0,
|
|
"step": 47100
|
|
},
|
|
{
|
|
"entropy": 5.126165437698364,
|
|
"epoch": 4.524975984630164,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00031213665057879615,
|
|
"loss": 4.5603,
|
|
"mean_token_accuracy": 0.2616350457072258,
|
|
"num_tokens": 108033956.0,
|
|
"step": 47105
|
|
},
|
|
{
|
|
"entropy": 5.18181734085083,
|
|
"epoch": 4.525456292026897,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003121028367946278,
|
|
"loss": 4.5947,
|
|
"mean_token_accuracy": 0.2607933789491653,
|
|
"num_tokens": 108045706.0,
|
|
"step": 47110
|
|
},
|
|
{
|
|
"entropy": 5.156432199478149,
|
|
"epoch": 4.525936599423631,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003120690221490417,
|
|
"loss": 4.5808,
|
|
"mean_token_accuracy": 0.25674223750829694,
|
|
"num_tokens": 108057780.0,
|
|
"step": 47115
|
|
},
|
|
{
|
|
"entropy": 5.124602270126343,
|
|
"epoch": 4.526416906820365,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003120352066428231,
|
|
"loss": 4.5189,
|
|
"mean_token_accuracy": 0.2634192809462547,
|
|
"num_tokens": 108068782.0,
|
|
"step": 47120
|
|
},
|
|
{
|
|
"entropy": 5.0537327289581295,
|
|
"epoch": 4.526897214217099,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00031200139027675683,
|
|
"loss": 4.4643,
|
|
"mean_token_accuracy": 0.26244649291038513,
|
|
"num_tokens": 108080639.0,
|
|
"step": 47125
|
|
},
|
|
{
|
|
"entropy": 5.118510293960571,
|
|
"epoch": 4.527377521613833,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00031196757305162814,
|
|
"loss": 4.5545,
|
|
"mean_token_accuracy": 0.2654070556163788,
|
|
"num_tokens": 108092513.0,
|
|
"step": 47130
|
|
},
|
|
{
|
|
"entropy": 5.073121833801269,
|
|
"epoch": 4.527857829010567,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003119337549682223,
|
|
"loss": 4.4687,
|
|
"mean_token_accuracy": 0.2697503209114075,
|
|
"num_tokens": 108104590.0,
|
|
"step": 47135
|
|
},
|
|
{
|
|
"entropy": 5.064039945602417,
|
|
"epoch": 4.5283381364073,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003118999360273243,
|
|
"loss": 4.4672,
|
|
"mean_token_accuracy": 0.27153645157814027,
|
|
"num_tokens": 108116781.0,
|
|
"step": 47140
|
|
},
|
|
{
|
|
"entropy": 5.058578443527222,
|
|
"epoch": 4.528818443804035,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00031186611622971926,
|
|
"loss": 4.5112,
|
|
"mean_token_accuracy": 0.2675530448555946,
|
|
"num_tokens": 108127823.0,
|
|
"step": 47145
|
|
},
|
|
{
|
|
"entropy": 5.127905941009521,
|
|
"epoch": 4.529298751200768,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031183229557619265,
|
|
"loss": 4.5133,
|
|
"mean_token_accuracy": 0.26441842019557954,
|
|
"num_tokens": 108138546.0,
|
|
"step": 47150
|
|
},
|
|
{
|
|
"entropy": 5.059993696212769,
|
|
"epoch": 4.529779058597502,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003117984740675294,
|
|
"loss": 4.4222,
|
|
"mean_token_accuracy": 0.2738816365599632,
|
|
"num_tokens": 108148962.0,
|
|
"step": 47155
|
|
},
|
|
{
|
|
"entropy": 5.127397060394287,
|
|
"epoch": 4.530259365994237,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003117646517045148,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.2677201434969902,
|
|
"num_tokens": 108160997.0,
|
|
"step": 47160
|
|
},
|
|
{
|
|
"entropy": 5.084800767898559,
|
|
"epoch": 4.53073967339097,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003117308284879342,
|
|
"loss": 4.5701,
|
|
"mean_token_accuracy": 0.26330782622098925,
|
|
"num_tokens": 108172503.0,
|
|
"step": 47165
|
|
},
|
|
{
|
|
"entropy": 5.096940326690674,
|
|
"epoch": 4.5312199807877045,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003116970044185728,
|
|
"loss": 4.5372,
|
|
"mean_token_accuracy": 0.2612439587712288,
|
|
"num_tokens": 108184515.0,
|
|
"step": 47170
|
|
},
|
|
{
|
|
"entropy": 5.1278728485107425,
|
|
"epoch": 4.531700288184438,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000311663179497216,
|
|
"loss": 4.523,
|
|
"mean_token_accuracy": 0.2712788164615631,
|
|
"num_tokens": 108196003.0,
|
|
"step": 47175
|
|
},
|
|
{
|
|
"entropy": 5.198092699050903,
|
|
"epoch": 4.532180595581172,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000311629353724649,
|
|
"loss": 4.6387,
|
|
"mean_token_accuracy": 0.2639390632510185,
|
|
"num_tokens": 108207467.0,
|
|
"step": 47180
|
|
},
|
|
{
|
|
"entropy": 5.153549337387085,
|
|
"epoch": 4.532660902977906,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00031159552710165715,
|
|
"loss": 4.6266,
|
|
"mean_token_accuracy": 0.26497540920972823,
|
|
"num_tokens": 108218608.0,
|
|
"step": 47185
|
|
},
|
|
{
|
|
"entropy": 5.156255912780762,
|
|
"epoch": 4.53314121037464,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00031156169962902585,
|
|
"loss": 4.6266,
|
|
"mean_token_accuracy": 0.26206309348344803,
|
|
"num_tokens": 108230684.0,
|
|
"step": 47190
|
|
},
|
|
{
|
|
"entropy": 5.140228033065796,
|
|
"epoch": 4.5336215177713735,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003115278713075405,
|
|
"loss": 4.6221,
|
|
"mean_token_accuracy": 0.26204086244106295,
|
|
"num_tokens": 108242127.0,
|
|
"step": 47195
|
|
},
|
|
{
|
|
"entropy": 5.051026439666748,
|
|
"epoch": 4.534101825168108,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003114940421379864,
|
|
"loss": 4.4865,
|
|
"mean_token_accuracy": 0.27066550552845003,
|
|
"num_tokens": 108253491.0,
|
|
"step": 47200
|
|
},
|
|
{
|
|
"entropy": 5.137141942977905,
|
|
"epoch": 4.534582132564841,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000311460212121149,
|
|
"loss": 4.5769,
|
|
"mean_token_accuracy": 0.263887383043766,
|
|
"num_tokens": 108267164.0,
|
|
"step": 47205
|
|
},
|
|
{
|
|
"entropy": 5.105214166641235,
|
|
"epoch": 4.5350624399615755,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00031142638125781374,
|
|
"loss": 4.518,
|
|
"mean_token_accuracy": 0.2733027786016464,
|
|
"num_tokens": 108278506.0,
|
|
"step": 47210
|
|
},
|
|
{
|
|
"entropy": 5.174118614196777,
|
|
"epoch": 4.535542747358309,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00031139254954876605,
|
|
"loss": 4.6184,
|
|
"mean_token_accuracy": 0.25754703879356383,
|
|
"num_tokens": 108288766.0,
|
|
"step": 47215
|
|
},
|
|
{
|
|
"entropy": 5.125053977966308,
|
|
"epoch": 4.536023054755043,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003113587169947914,
|
|
"loss": 4.5631,
|
|
"mean_token_accuracy": 0.26273053884506226,
|
|
"num_tokens": 108300632.0,
|
|
"step": 47220
|
|
},
|
|
{
|
|
"entropy": 5.152884244918823,
|
|
"epoch": 4.536503362151777,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00031132488359667546,
|
|
"loss": 4.5802,
|
|
"mean_token_accuracy": 0.26099313944578173,
|
|
"num_tokens": 108312168.0,
|
|
"step": 47225
|
|
},
|
|
{
|
|
"entropy": 5.153535413742065,
|
|
"epoch": 4.536983669548511,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003112910493552034,
|
|
"loss": 4.5464,
|
|
"mean_token_accuracy": 0.2681678652763367,
|
|
"num_tokens": 108323214.0,
|
|
"step": 47230
|
|
},
|
|
{
|
|
"entropy": 5.099399995803833,
|
|
"epoch": 4.537463976945245,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00031125721427116104,
|
|
"loss": 4.5014,
|
|
"mean_token_accuracy": 0.2689922347664833,
|
|
"num_tokens": 108334329.0,
|
|
"step": 47235
|
|
},
|
|
{
|
|
"entropy": 5.1619500637054445,
|
|
"epoch": 4.537944284341979,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00031122337834533375,
|
|
"loss": 4.6013,
|
|
"mean_token_accuracy": 0.26304192245006563,
|
|
"num_tokens": 108345402.0,
|
|
"step": 47240
|
|
},
|
|
{
|
|
"entropy": 5.095040035247803,
|
|
"epoch": 4.538424591738713,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003111895415785073,
|
|
"loss": 4.5323,
|
|
"mean_token_accuracy": 0.26139224171638487,
|
|
"num_tokens": 108356807.0,
|
|
"step": 47245
|
|
},
|
|
{
|
|
"entropy": 5.235645198822022,
|
|
"epoch": 4.538904899135447,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003111557039714671,
|
|
"loss": 4.7063,
|
|
"mean_token_accuracy": 0.255018350481987,
|
|
"num_tokens": 108367804.0,
|
|
"step": 47250
|
|
},
|
|
{
|
|
"entropy": 5.1336016178131105,
|
|
"epoch": 4.539385206532181,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00031112186552499876,
|
|
"loss": 4.5115,
|
|
"mean_token_accuracy": 0.26113060414791106,
|
|
"num_tokens": 108380201.0,
|
|
"step": 47255
|
|
},
|
|
{
|
|
"entropy": 5.057387447357177,
|
|
"epoch": 4.539865513928914,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000311088026239888,
|
|
"loss": 4.3926,
|
|
"mean_token_accuracy": 0.281427201628685,
|
|
"num_tokens": 108391767.0,
|
|
"step": 47260
|
|
},
|
|
{
|
|
"entropy": 5.120457983016967,
|
|
"epoch": 4.540345821325649,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00031105418611692044,
|
|
"loss": 4.5602,
|
|
"mean_token_accuracy": 0.25921406000852587,
|
|
"num_tokens": 108402532.0,
|
|
"step": 47265
|
|
},
|
|
{
|
|
"entropy": 5.195370054244995,
|
|
"epoch": 4.540826128722382,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003110203451568817,
|
|
"loss": 4.6131,
|
|
"mean_token_accuracy": 0.2581531271338463,
|
|
"num_tokens": 108413136.0,
|
|
"step": 47270
|
|
},
|
|
{
|
|
"entropy": 5.101593351364135,
|
|
"epoch": 4.541306436119116,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003109865033605575,
|
|
"loss": 4.5039,
|
|
"mean_token_accuracy": 0.2711345762014389,
|
|
"num_tokens": 108425101.0,
|
|
"step": 47275
|
|
},
|
|
{
|
|
"entropy": 5.073408555984497,
|
|
"epoch": 4.54178674351585,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003109526607287336,
|
|
"loss": 4.4968,
|
|
"mean_token_accuracy": 0.2767541244626045,
|
|
"num_tokens": 108436258.0,
|
|
"step": 47280
|
|
},
|
|
{
|
|
"entropy": 5.134799289703369,
|
|
"epoch": 4.542267050912584,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00031091881726219567,
|
|
"loss": 4.5424,
|
|
"mean_token_accuracy": 0.2656813532114029,
|
|
"num_tokens": 108447697.0,
|
|
"step": 47285
|
|
},
|
|
{
|
|
"entropy": 5.102523279190064,
|
|
"epoch": 4.542747358309318,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003108849729617294,
|
|
"loss": 4.5567,
|
|
"mean_token_accuracy": 0.26458117365837097,
|
|
"num_tokens": 108459414.0,
|
|
"step": 47290
|
|
},
|
|
{
|
|
"entropy": 5.152473402023316,
|
|
"epoch": 4.543227665706052,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00031085112782812066,
|
|
"loss": 4.6505,
|
|
"mean_token_accuracy": 0.25725713223218916,
|
|
"num_tokens": 108469182.0,
|
|
"step": 47295
|
|
},
|
|
{
|
|
"entropy": 5.131193399429321,
|
|
"epoch": 4.543707973102785,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003108172818621552,
|
|
"loss": 4.6022,
|
|
"mean_token_accuracy": 0.25571873486042024,
|
|
"num_tokens": 108481824.0,
|
|
"step": 47300
|
|
},
|
|
{
|
|
"entropy": 5.074766159057617,
|
|
"epoch": 4.54418828049952,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003107834350646188,
|
|
"loss": 4.5105,
|
|
"mean_token_accuracy": 0.27162993252277373,
|
|
"num_tokens": 108491954.0,
|
|
"step": 47305
|
|
},
|
|
{
|
|
"entropy": 5.100836896896363,
|
|
"epoch": 4.544668587896254,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003107495874362973,
|
|
"loss": 4.5859,
|
|
"mean_token_accuracy": 0.25762839019298556,
|
|
"num_tokens": 108502828.0,
|
|
"step": 47310
|
|
},
|
|
{
|
|
"entropy": 5.126336717605591,
|
|
"epoch": 4.5451488952929875,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003107157389779765,
|
|
"loss": 4.5291,
|
|
"mean_token_accuracy": 0.26707605123519895,
|
|
"num_tokens": 108513781.0,
|
|
"step": 47315
|
|
},
|
|
{
|
|
"entropy": 5.086613988876342,
|
|
"epoch": 4.545629202689721,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003106818896904423,
|
|
"loss": 4.4873,
|
|
"mean_token_accuracy": 0.2697212934494019,
|
|
"num_tokens": 108524315.0,
|
|
"step": 47320
|
|
},
|
|
{
|
|
"entropy": 5.092767238616943,
|
|
"epoch": 4.546109510086455,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031064803957448064,
|
|
"loss": 4.5533,
|
|
"mean_token_accuracy": 0.26504376977682115,
|
|
"num_tokens": 108534972.0,
|
|
"step": 47325
|
|
},
|
|
{
|
|
"entropy": 5.276246690750122,
|
|
"epoch": 4.54658981748319,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003106141886308773,
|
|
"loss": 4.702,
|
|
"mean_token_accuracy": 0.24844993203878402,
|
|
"num_tokens": 108545571.0,
|
|
"step": 47330
|
|
},
|
|
{
|
|
"entropy": 5.174099349975586,
|
|
"epoch": 4.547070124879923,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003105803368604183,
|
|
"loss": 4.625,
|
|
"mean_token_accuracy": 0.25347424000501634,
|
|
"num_tokens": 108557643.0,
|
|
"step": 47335
|
|
},
|
|
{
|
|
"entropy": 5.176977062225342,
|
|
"epoch": 4.547550432276657,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00031054648426388944,
|
|
"loss": 4.576,
|
|
"mean_token_accuracy": 0.2606795594096184,
|
|
"num_tokens": 108569872.0,
|
|
"step": 47340
|
|
},
|
|
{
|
|
"entropy": 5.1459180355072025,
|
|
"epoch": 4.548030739673391,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00031051263084207686,
|
|
"loss": 4.5714,
|
|
"mean_token_accuracy": 0.2643096476793289,
|
|
"num_tokens": 108583387.0,
|
|
"step": 47345
|
|
},
|
|
{
|
|
"entropy": 5.051159524917603,
|
|
"epoch": 4.548511047070125,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00031047877659576636,
|
|
"loss": 4.4836,
|
|
"mean_token_accuracy": 0.27595382928848267,
|
|
"num_tokens": 108595474.0,
|
|
"step": 47350
|
|
},
|
|
{
|
|
"entropy": 5.1037633419036865,
|
|
"epoch": 4.5489913544668585,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00031044492152574406,
|
|
"loss": 4.4843,
|
|
"mean_token_accuracy": 0.27585899382829665,
|
|
"num_tokens": 108606386.0,
|
|
"step": 47355
|
|
},
|
|
{
|
|
"entropy": 5.129443216323852,
|
|
"epoch": 4.549471661863593,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000310411065632796,
|
|
"loss": 4.5661,
|
|
"mean_token_accuracy": 0.26202376931905746,
|
|
"num_tokens": 108617492.0,
|
|
"step": 47360
|
|
},
|
|
{
|
|
"entropy": 5.079879236221314,
|
|
"epoch": 4.549951969260326,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00031037720891770803,
|
|
"loss": 4.5053,
|
|
"mean_token_accuracy": 0.2664754524827003,
|
|
"num_tokens": 108628956.0,
|
|
"step": 47365
|
|
},
|
|
{
|
|
"entropy": 5.058595800399781,
|
|
"epoch": 4.550432276657061,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003103433513812663,
|
|
"loss": 4.4755,
|
|
"mean_token_accuracy": 0.26668486297130584,
|
|
"num_tokens": 108639238.0,
|
|
"step": 47370
|
|
},
|
|
{
|
|
"entropy": 5.125932598114014,
|
|
"epoch": 4.550912584053794,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00031030949302425704,
|
|
"loss": 4.5792,
|
|
"mean_token_accuracy": 0.2587164506316185,
|
|
"num_tokens": 108650323.0,
|
|
"step": 47375
|
|
},
|
|
{
|
|
"entropy": 5.119015455245972,
|
|
"epoch": 4.551392891450528,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003102756338474661,
|
|
"loss": 4.4907,
|
|
"mean_token_accuracy": 0.2722952350974083,
|
|
"num_tokens": 108662231.0,
|
|
"step": 47380
|
|
},
|
|
{
|
|
"entropy": 5.101621818542481,
|
|
"epoch": 4.551873198847263,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003102417738516797,
|
|
"loss": 4.5299,
|
|
"mean_token_accuracy": 0.26228425204753875,
|
|
"num_tokens": 108672571.0,
|
|
"step": 47385
|
|
},
|
|
{
|
|
"entropy": 5.133727645874023,
|
|
"epoch": 4.552353506243996,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000310207913037684,
|
|
"loss": 4.6191,
|
|
"mean_token_accuracy": 0.2569893077015877,
|
|
"num_tokens": 108683631.0,
|
|
"step": 47390
|
|
},
|
|
{
|
|
"entropy": 5.151570415496826,
|
|
"epoch": 4.55283381364073,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00031017405140626507,
|
|
"loss": 4.5788,
|
|
"mean_token_accuracy": 0.2653321802616119,
|
|
"num_tokens": 108693986.0,
|
|
"step": 47395
|
|
},
|
|
{
|
|
"entropy": 5.198937129974365,
|
|
"epoch": 4.553314121037464,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00031014018895820903,
|
|
"loss": 4.6194,
|
|
"mean_token_accuracy": 0.25474264323711393,
|
|
"num_tokens": 108705987.0,
|
|
"step": 47400
|
|
},
|
|
{
|
|
"entropy": 5.155593967437744,
|
|
"epoch": 4.553794428434198,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003101063256943023,
|
|
"loss": 4.6195,
|
|
"mean_token_accuracy": 0.2573117583990097,
|
|
"num_tokens": 108717154.0,
|
|
"step": 47405
|
|
},
|
|
{
|
|
"entropy": 5.15795931816101,
|
|
"epoch": 4.554274735830932,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00031007246161533086,
|
|
"loss": 4.6111,
|
|
"mean_token_accuracy": 0.2640398994088173,
|
|
"num_tokens": 108728225.0,
|
|
"step": 47410
|
|
},
|
|
{
|
|
"entropy": 5.11424503326416,
|
|
"epoch": 4.554755043227666,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000310038596722081,
|
|
"loss": 4.5372,
|
|
"mean_token_accuracy": 0.2688407897949219,
|
|
"num_tokens": 108739616.0,
|
|
"step": 47415
|
|
},
|
|
{
|
|
"entropy": 5.151162147521973,
|
|
"epoch": 4.555235350624399,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000310004731015339,
|
|
"loss": 4.5728,
|
|
"mean_token_accuracy": 0.262941911816597,
|
|
"num_tokens": 108751409.0,
|
|
"step": 47420
|
|
},
|
|
{
|
|
"entropy": 5.166354370117188,
|
|
"epoch": 4.555715658021134,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00030997086449589107,
|
|
"loss": 4.5709,
|
|
"mean_token_accuracy": 0.26047337651252744,
|
|
"num_tokens": 108762260.0,
|
|
"step": 47425
|
|
},
|
|
{
|
|
"entropy": 5.17701563835144,
|
|
"epoch": 4.556195965417867,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00030993699716452345,
|
|
"loss": 4.5779,
|
|
"mean_token_accuracy": 0.269562891125679,
|
|
"num_tokens": 108774283.0,
|
|
"step": 47430
|
|
},
|
|
{
|
|
"entropy": 5.084968137741089,
|
|
"epoch": 4.5566762728146015,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003099031290220226,
|
|
"loss": 4.5347,
|
|
"mean_token_accuracy": 0.26797704249620435,
|
|
"num_tokens": 108786081.0,
|
|
"step": 47435
|
|
},
|
|
{
|
|
"entropy": 5.131486701965332,
|
|
"epoch": 4.557156580211335,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00030986926006917463,
|
|
"loss": 4.6018,
|
|
"mean_token_accuracy": 0.2639128163456917,
|
|
"num_tokens": 108798409.0,
|
|
"step": 47440
|
|
},
|
|
{
|
|
"entropy": 5.165375089645385,
|
|
"epoch": 4.557636887608069,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003098353903067661,
|
|
"loss": 4.5705,
|
|
"mean_token_accuracy": 0.25443410128355026,
|
|
"num_tokens": 108808807.0,
|
|
"step": 47445
|
|
},
|
|
{
|
|
"entropy": 5.125714826583862,
|
|
"epoch": 4.558117195004803,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003098015197355832,
|
|
"loss": 4.5564,
|
|
"mean_token_accuracy": 0.2600970849394798,
|
|
"num_tokens": 108820308.0,
|
|
"step": 47450
|
|
},
|
|
{
|
|
"entropy": 5.10605149269104,
|
|
"epoch": 4.558597502401537,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003097676483564123,
|
|
"loss": 4.4908,
|
|
"mean_token_accuracy": 0.2713464483618736,
|
|
"num_tokens": 108832242.0,
|
|
"step": 47455
|
|
},
|
|
{
|
|
"entropy": 5.162860345840454,
|
|
"epoch": 4.559077809798271,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003097337761700399,
|
|
"loss": 4.5873,
|
|
"mean_token_accuracy": 0.26461549699306486,
|
|
"num_tokens": 108843044.0,
|
|
"step": 47460
|
|
},
|
|
{
|
|
"entropy": 5.195649480819702,
|
|
"epoch": 4.559558117195005,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003096999031772523,
|
|
"loss": 4.6648,
|
|
"mean_token_accuracy": 0.2523036301136017,
|
|
"num_tokens": 108855245.0,
|
|
"step": 47465
|
|
},
|
|
{
|
|
"entropy": 5.157483148574829,
|
|
"epoch": 4.560038424591738,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00030966602937883606,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.2605309411883354,
|
|
"num_tokens": 108866991.0,
|
|
"step": 47470
|
|
},
|
|
{
|
|
"entropy": 5.069686031341552,
|
|
"epoch": 4.560518731988473,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003096321547755775,
|
|
"loss": 4.4954,
|
|
"mean_token_accuracy": 0.2662887617945671,
|
|
"num_tokens": 108878341.0,
|
|
"step": 47475
|
|
},
|
|
{
|
|
"entropy": 5.126570081710815,
|
|
"epoch": 4.560999039385207,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003095982793682632,
|
|
"loss": 4.551,
|
|
"mean_token_accuracy": 0.2676275700330734,
|
|
"num_tokens": 108889595.0,
|
|
"step": 47480
|
|
},
|
|
{
|
|
"entropy": 5.058455276489258,
|
|
"epoch": 4.56147934678194,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003095644031576795,
|
|
"loss": 4.4951,
|
|
"mean_token_accuracy": 0.26795304119586943,
|
|
"num_tokens": 108901336.0,
|
|
"step": 47485
|
|
},
|
|
{
|
|
"entropy": 5.1210356712341305,
|
|
"epoch": 4.561959654178675,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00030953052614461304,
|
|
"loss": 4.5443,
|
|
"mean_token_accuracy": 0.26489208489656446,
|
|
"num_tokens": 108912163.0,
|
|
"step": 47490
|
|
},
|
|
{
|
|
"entropy": 5.106991338729858,
|
|
"epoch": 4.562439961575408,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003094966483298503,
|
|
"loss": 4.5813,
|
|
"mean_token_accuracy": 0.26412580758333204,
|
|
"num_tokens": 108923876.0,
|
|
"step": 47495
|
|
},
|
|
{
|
|
"entropy": 5.149797248840332,
|
|
"epoch": 4.562920268972142,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00030946276971417785,
|
|
"loss": 4.5636,
|
|
"mean_token_accuracy": 0.2634605512022972,
|
|
"num_tokens": 108935529.0,
|
|
"step": 47500
|
|
},
|
|
{
|
|
"entropy": 5.227808141708374,
|
|
"epoch": 4.563400576368876,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00030942889029838216,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.24785899817943574,
|
|
"num_tokens": 108947524.0,
|
|
"step": 47505
|
|
},
|
|
{
|
|
"entropy": 5.167554712295532,
|
|
"epoch": 4.56388088376561,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00030939501008324995,
|
|
"loss": 4.5698,
|
|
"mean_token_accuracy": 0.26431190222501755,
|
|
"num_tokens": 108958890.0,
|
|
"step": 47510
|
|
},
|
|
{
|
|
"entropy": 5.106609439849853,
|
|
"epoch": 4.564361191162344,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00030936112906956766,
|
|
"loss": 4.548,
|
|
"mean_token_accuracy": 0.2650309205055237,
|
|
"num_tokens": 108971483.0,
|
|
"step": 47515
|
|
},
|
|
{
|
|
"entropy": 5.2126007080078125,
|
|
"epoch": 4.564841498559078,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000309327247258122,
|
|
"loss": 4.6483,
|
|
"mean_token_accuracy": 0.2553721085190773,
|
|
"num_tokens": 108983127.0,
|
|
"step": 47520
|
|
},
|
|
{
|
|
"entropy": 5.158351993560791,
|
|
"epoch": 4.565321805955811,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003092933646496996,
|
|
"loss": 4.6338,
|
|
"mean_token_accuracy": 0.26080906242132185,
|
|
"num_tokens": 108994764.0,
|
|
"step": 47525
|
|
},
|
|
{
|
|
"entropy": 5.161788415908814,
|
|
"epoch": 4.565802113352546,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003092594812450871,
|
|
"loss": 4.559,
|
|
"mean_token_accuracy": 0.2652206182479858,
|
|
"num_tokens": 109005806.0,
|
|
"step": 47530
|
|
},
|
|
{
|
|
"entropy": 5.143473482131958,
|
|
"epoch": 4.56628242074928,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003092255970450712,
|
|
"loss": 4.6111,
|
|
"mean_token_accuracy": 0.2557887151837349,
|
|
"num_tokens": 109017819.0,
|
|
"step": 47535
|
|
},
|
|
{
|
|
"entropy": 5.075616025924683,
|
|
"epoch": 4.5667627281460135,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003091917120504385,
|
|
"loss": 4.4763,
|
|
"mean_token_accuracy": 0.26909418404102325,
|
|
"num_tokens": 109031049.0,
|
|
"step": 47540
|
|
},
|
|
{
|
|
"entropy": 5.08600115776062,
|
|
"epoch": 4.567243035542747,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003091578262619758,
|
|
"loss": 4.5496,
|
|
"mean_token_accuracy": 0.26530735194683075,
|
|
"num_tokens": 109042206.0,
|
|
"step": 47545
|
|
},
|
|
{
|
|
"entropy": 5.089645290374756,
|
|
"epoch": 4.567723342939481,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00030912393968046984,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.26079285740852354,
|
|
"num_tokens": 109054340.0,
|
|
"step": 47550
|
|
},
|
|
{
|
|
"entropy": 5.059378051757813,
|
|
"epoch": 4.568203650336216,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00030909005230670734,
|
|
"loss": 4.5327,
|
|
"mean_token_accuracy": 0.27314906418323515,
|
|
"num_tokens": 109065450.0,
|
|
"step": 47555
|
|
},
|
|
{
|
|
"entropy": 5.129133224487305,
|
|
"epoch": 4.568683957732949,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00030905616414147503,
|
|
"loss": 4.557,
|
|
"mean_token_accuracy": 0.25919261425733564,
|
|
"num_tokens": 109075649.0,
|
|
"step": 47560
|
|
},
|
|
{
|
|
"entropy": 5.065858459472656,
|
|
"epoch": 4.569164265129683,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00030902227518555967,
|
|
"loss": 4.5378,
|
|
"mean_token_accuracy": 0.2647052124142647,
|
|
"num_tokens": 109085403.0,
|
|
"step": 47565
|
|
},
|
|
{
|
|
"entropy": 5.117908763885498,
|
|
"epoch": 4.569644572526417,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00030898838543974816,
|
|
"loss": 4.5697,
|
|
"mean_token_accuracy": 0.26190465986728667,
|
|
"num_tokens": 109096047.0,
|
|
"step": 47570
|
|
},
|
|
{
|
|
"entropy": 5.194018602371216,
|
|
"epoch": 4.570124879923151,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00030895449490482725,
|
|
"loss": 4.5449,
|
|
"mean_token_accuracy": 0.26547937989234927,
|
|
"num_tokens": 109107543.0,
|
|
"step": 47575
|
|
},
|
|
{
|
|
"entropy": 5.042172908782959,
|
|
"epoch": 4.5706051873198845,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00030892060358158376,
|
|
"loss": 4.4787,
|
|
"mean_token_accuracy": 0.2719161093235016,
|
|
"num_tokens": 109119099.0,
|
|
"step": 47580
|
|
},
|
|
{
|
|
"entropy": 5.035979700088501,
|
|
"epoch": 4.571085494716619,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00030888671147080466,
|
|
"loss": 4.5183,
|
|
"mean_token_accuracy": 0.26327391862869265,
|
|
"num_tokens": 109130362.0,
|
|
"step": 47585
|
|
},
|
|
{
|
|
"entropy": 5.130936908721924,
|
|
"epoch": 4.571565802113352,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003088528185732767,
|
|
"loss": 4.6113,
|
|
"mean_token_accuracy": 0.26160443276166917,
|
|
"num_tokens": 109141632.0,
|
|
"step": 47590
|
|
},
|
|
{
|
|
"entropy": 5.176645994186401,
|
|
"epoch": 4.572046109510087,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00030881892488978676,
|
|
"loss": 4.608,
|
|
"mean_token_accuracy": 0.26237633526325227,
|
|
"num_tokens": 109153422.0,
|
|
"step": 47595
|
|
},
|
|
{
|
|
"entropy": 5.197389078140259,
|
|
"epoch": 4.57252641690682,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00030878503042112184,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.25594004839658735,
|
|
"num_tokens": 109165412.0,
|
|
"step": 47600
|
|
},
|
|
{
|
|
"entropy": 5.09137716293335,
|
|
"epoch": 4.573006724303554,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00030875113516806886,
|
|
"loss": 4.5229,
|
|
"mean_token_accuracy": 0.2715741455554962,
|
|
"num_tokens": 109176419.0,
|
|
"step": 47605
|
|
},
|
|
{
|
|
"entropy": 5.061334037780762,
|
|
"epoch": 4.573487031700288,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003087172391314147,
|
|
"loss": 4.5461,
|
|
"mean_token_accuracy": 0.2667273372411728,
|
|
"num_tokens": 109187456.0,
|
|
"step": 47610
|
|
},
|
|
{
|
|
"entropy": 5.169728565216064,
|
|
"epoch": 4.573967339097022,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00030868334231194645,
|
|
"loss": 4.5967,
|
|
"mean_token_accuracy": 0.2596428096294403,
|
|
"num_tokens": 109198687.0,
|
|
"step": 47615
|
|
},
|
|
{
|
|
"entropy": 5.191084957122802,
|
|
"epoch": 4.574447646493756,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003086494447104509,
|
|
"loss": 4.5624,
|
|
"mean_token_accuracy": 0.2666180580854416,
|
|
"num_tokens": 109211091.0,
|
|
"step": 47620
|
|
},
|
|
{
|
|
"entropy": 5.099287366867065,
|
|
"epoch": 4.57492795389049,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003086155463277152,
|
|
"loss": 4.563,
|
|
"mean_token_accuracy": 0.2638876214623451,
|
|
"num_tokens": 109222767.0,
|
|
"step": 47625
|
|
},
|
|
{
|
|
"entropy": 5.096934652328491,
|
|
"epoch": 4.575408261287224,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003085816471645264,
|
|
"loss": 4.5629,
|
|
"mean_token_accuracy": 0.2679818168282509,
|
|
"num_tokens": 109234030.0,
|
|
"step": 47630
|
|
},
|
|
{
|
|
"entropy": 5.149368143081665,
|
|
"epoch": 4.575888568683958,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003085477472216714,
|
|
"loss": 4.605,
|
|
"mean_token_accuracy": 0.2619804874062538,
|
|
"num_tokens": 109245453.0,
|
|
"step": 47635
|
|
},
|
|
{
|
|
"entropy": 5.104490947723389,
|
|
"epoch": 4.576368876080692,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003085138464999373,
|
|
"loss": 4.4592,
|
|
"mean_token_accuracy": 0.27366061955690385,
|
|
"num_tokens": 109257322.0,
|
|
"step": 47640
|
|
},
|
|
{
|
|
"entropy": 5.120248413085937,
|
|
"epoch": 4.576849183477425,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003084799450001113,
|
|
"loss": 4.5835,
|
|
"mean_token_accuracy": 0.2529555022716522,
|
|
"num_tokens": 109270696.0,
|
|
"step": 47645
|
|
},
|
|
{
|
|
"entropy": 5.070396995544433,
|
|
"epoch": 4.57732949087416,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003084460427229803,
|
|
"loss": 4.5126,
|
|
"mean_token_accuracy": 0.267900837957859,
|
|
"num_tokens": 109282505.0,
|
|
"step": 47650
|
|
},
|
|
{
|
|
"entropy": 5.099229621887207,
|
|
"epoch": 4.577809798270893,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003084121396693316,
|
|
"loss": 4.5429,
|
|
"mean_token_accuracy": 0.2721424847841263,
|
|
"num_tokens": 109292984.0,
|
|
"step": 47655
|
|
},
|
|
{
|
|
"entropy": 5.127323150634766,
|
|
"epoch": 4.5782901056676275,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00030837823583995216,
|
|
"loss": 4.5854,
|
|
"mean_token_accuracy": 0.2600159227848053,
|
|
"num_tokens": 109303797.0,
|
|
"step": 47660
|
|
},
|
|
{
|
|
"entropy": 5.166588354110718,
|
|
"epoch": 4.578770413064361,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003083443312356292,
|
|
"loss": 4.5808,
|
|
"mean_token_accuracy": 0.26879640519618986,
|
|
"num_tokens": 109315535.0,
|
|
"step": 47665
|
|
},
|
|
{
|
|
"entropy": 5.115264081954956,
|
|
"epoch": 4.579250720461095,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00030831042585714984,
|
|
"loss": 4.4822,
|
|
"mean_token_accuracy": 0.26756221055984497,
|
|
"num_tokens": 109326773.0,
|
|
"step": 47670
|
|
},
|
|
{
|
|
"entropy": 5.153048896789551,
|
|
"epoch": 4.579731027857829,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00030827651970530143,
|
|
"loss": 4.572,
|
|
"mean_token_accuracy": 0.2626937448978424,
|
|
"num_tokens": 109337153.0,
|
|
"step": 47675
|
|
},
|
|
{
|
|
"entropy": 5.112549304962158,
|
|
"epoch": 4.580211335254563,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003082426127808709,
|
|
"loss": 4.5853,
|
|
"mean_token_accuracy": 0.26250957548618314,
|
|
"num_tokens": 109348854.0,
|
|
"step": 47680
|
|
},
|
|
{
|
|
"entropy": 5.053353214263916,
|
|
"epoch": 4.5806916426512965,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003082087050846457,
|
|
"loss": 4.5009,
|
|
"mean_token_accuracy": 0.2742883160710335,
|
|
"num_tokens": 109360902.0,
|
|
"step": 47685
|
|
},
|
|
{
|
|
"entropy": 5.187335109710693,
|
|
"epoch": 4.581171950048031,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003081747966174129,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.26017876863479616,
|
|
"num_tokens": 109372372.0,
|
|
"step": 47690
|
|
},
|
|
{
|
|
"entropy": 5.126912021636963,
|
|
"epoch": 4.581652257444764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003081408873799599,
|
|
"loss": 4.5094,
|
|
"mean_token_accuracy": 0.26783068627119067,
|
|
"num_tokens": 109383807.0,
|
|
"step": 47695
|
|
},
|
|
{
|
|
"entropy": 5.1012226104736325,
|
|
"epoch": 4.582132564841499,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003081069773730739,
|
|
"loss": 4.4741,
|
|
"mean_token_accuracy": 0.2733543172478676,
|
|
"num_tokens": 109396344.0,
|
|
"step": 47700
|
|
},
|
|
{
|
|
"entropy": 5.122701787948609,
|
|
"epoch": 4.582612872238233,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003080730665975423,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.27239942997694017,
|
|
"num_tokens": 109408102.0,
|
|
"step": 47705
|
|
},
|
|
{
|
|
"entropy": 5.1147528171539305,
|
|
"epoch": 4.583093179634966,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003080391550541521,
|
|
"loss": 4.615,
|
|
"mean_token_accuracy": 0.2544156014919281,
|
|
"num_tokens": 109418352.0,
|
|
"step": 47710
|
|
},
|
|
{
|
|
"entropy": 5.235293674468994,
|
|
"epoch": 4.583573487031701,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003080052427436909,
|
|
"loss": 4.6103,
|
|
"mean_token_accuracy": 0.26256694197654723,
|
|
"num_tokens": 109429176.0,
|
|
"step": 47715
|
|
},
|
|
{
|
|
"entropy": 5.147740888595581,
|
|
"epoch": 4.584053794428434,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000307971329666946,
|
|
"loss": 4.5194,
|
|
"mean_token_accuracy": 0.27089965492486956,
|
|
"num_tokens": 109440370.0,
|
|
"step": 47720
|
|
},
|
|
{
|
|
"entropy": 5.255547285079956,
|
|
"epoch": 4.584534101825168,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003079374158247047,
|
|
"loss": 4.6964,
|
|
"mean_token_accuracy": 0.2533582508563995,
|
|
"num_tokens": 109452268.0,
|
|
"step": 47725
|
|
},
|
|
{
|
|
"entropy": 5.142424869537353,
|
|
"epoch": 4.585014409221902,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003079035012177544,
|
|
"loss": 4.5658,
|
|
"mean_token_accuracy": 0.2620267614722252,
|
|
"num_tokens": 109463398.0,
|
|
"step": 47730
|
|
},
|
|
{
|
|
"entropy": 5.168890190124512,
|
|
"epoch": 4.585494716618636,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003078695858468825,
|
|
"loss": 4.6231,
|
|
"mean_token_accuracy": 0.25383667051792147,
|
|
"num_tokens": 109475860.0,
|
|
"step": 47735
|
|
},
|
|
{
|
|
"entropy": 5.067696809768677,
|
|
"epoch": 4.58597502401537,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003078356697128765,
|
|
"loss": 4.4989,
|
|
"mean_token_accuracy": 0.2694362044334412,
|
|
"num_tokens": 109487355.0,
|
|
"step": 47740
|
|
},
|
|
{
|
|
"entropy": 5.064057779312134,
|
|
"epoch": 4.586455331412104,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003078017528165236,
|
|
"loss": 4.4755,
|
|
"mean_token_accuracy": 0.2782034009695053,
|
|
"num_tokens": 109498477.0,
|
|
"step": 47745
|
|
},
|
|
{
|
|
"entropy": 5.230288887023926,
|
|
"epoch": 4.586935638808837,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00030776783515861156,
|
|
"loss": 4.6339,
|
|
"mean_token_accuracy": 0.2631696373224258,
|
|
"num_tokens": 109508997.0,
|
|
"step": 47750
|
|
},
|
|
{
|
|
"entropy": 5.077343559265136,
|
|
"epoch": 4.587415946205572,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00030773391673992754,
|
|
"loss": 4.5496,
|
|
"mean_token_accuracy": 0.2600509747862816,
|
|
"num_tokens": 109520271.0,
|
|
"step": 47755
|
|
},
|
|
{
|
|
"entropy": 5.1684483051300045,
|
|
"epoch": 4.587896253602305,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003076999975612593,
|
|
"loss": 4.5979,
|
|
"mean_token_accuracy": 0.25219203978776933,
|
|
"num_tokens": 109532118.0,
|
|
"step": 47760
|
|
},
|
|
{
|
|
"entropy": 5.165430307388306,
|
|
"epoch": 4.5883765609990395,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003076660776233942,
|
|
"loss": 4.5993,
|
|
"mean_token_accuracy": 0.2631613850593567,
|
|
"num_tokens": 109542936.0,
|
|
"step": 47765
|
|
},
|
|
{
|
|
"entropy": 5.161387729644775,
|
|
"epoch": 4.588856868395773,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003076321569271197,
|
|
"loss": 4.5692,
|
|
"mean_token_accuracy": 0.26490758061409,
|
|
"num_tokens": 109555542.0,
|
|
"step": 47770
|
|
},
|
|
{
|
|
"entropy": 5.14201135635376,
|
|
"epoch": 4.589337175792507,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00030759823547322346,
|
|
"loss": 4.5991,
|
|
"mean_token_accuracy": 0.2627615869045258,
|
|
"num_tokens": 109566347.0,
|
|
"step": 47775
|
|
},
|
|
{
|
|
"entropy": 5.1019689559936525,
|
|
"epoch": 4.5898174831892415,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000307564313262493,
|
|
"loss": 4.4672,
|
|
"mean_token_accuracy": 0.27208470106124877,
|
|
"num_tokens": 109577263.0,
|
|
"step": 47780
|
|
},
|
|
{
|
|
"entropy": 5.1527422904968265,
|
|
"epoch": 4.590297790585975,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00030753039029571586,
|
|
"loss": 4.6121,
|
|
"mean_token_accuracy": 0.26208071410655975,
|
|
"num_tokens": 109587998.0,
|
|
"step": 47785
|
|
},
|
|
{
|
|
"entropy": 5.104936838150024,
|
|
"epoch": 4.590778097982709,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00030749646657367963,
|
|
"loss": 4.5283,
|
|
"mean_token_accuracy": 0.2699911966919899,
|
|
"num_tokens": 109600419.0,
|
|
"step": 47790
|
|
},
|
|
{
|
|
"entropy": 5.1115013599395756,
|
|
"epoch": 4.591258405379443,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000307462542097172,
|
|
"loss": 4.5333,
|
|
"mean_token_accuracy": 0.274997353553772,
|
|
"num_tokens": 109612100.0,
|
|
"step": 47795
|
|
},
|
|
{
|
|
"entropy": 5.131185388565063,
|
|
"epoch": 4.591738712776177,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00030742861686698056,
|
|
"loss": 4.5184,
|
|
"mean_token_accuracy": 0.26595777124166486,
|
|
"num_tokens": 109624163.0,
|
|
"step": 47800
|
|
},
|
|
{
|
|
"entropy": 5.2101224899292,
|
|
"epoch": 4.5922190201729105,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003073946908838928,
|
|
"loss": 4.6365,
|
|
"mean_token_accuracy": 0.25852447301149367,
|
|
"num_tokens": 109634751.0,
|
|
"step": 47805
|
|
},
|
|
{
|
|
"entropy": 5.1608555793762205,
|
|
"epoch": 4.592699327569645,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003073607641486966,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.26313447654247285,
|
|
"num_tokens": 109645681.0,
|
|
"step": 47810
|
|
},
|
|
{
|
|
"entropy": 5.1591675758361815,
|
|
"epoch": 4.593179634966378,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00030732683666217955,
|
|
"loss": 4.608,
|
|
"mean_token_accuracy": 0.26453863084316254,
|
|
"num_tokens": 109657817.0,
|
|
"step": 47815
|
|
},
|
|
{
|
|
"entropy": 5.138768577575684,
|
|
"epoch": 4.593659942363113,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00030729290842512936,
|
|
"loss": 4.5076,
|
|
"mean_token_accuracy": 0.27696597427129743,
|
|
"num_tokens": 109668520.0,
|
|
"step": 47820
|
|
},
|
|
{
|
|
"entropy": 5.168826866149902,
|
|
"epoch": 4.594140249759846,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00030725897943833364,
|
|
"loss": 4.6311,
|
|
"mean_token_accuracy": 0.2604676976799965,
|
|
"num_tokens": 109678856.0,
|
|
"step": 47825
|
|
},
|
|
{
|
|
"entropy": 5.151949644088745,
|
|
"epoch": 4.59462055715658,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00030722504970258027,
|
|
"loss": 4.5557,
|
|
"mean_token_accuracy": 0.273771259188652,
|
|
"num_tokens": 109690610.0,
|
|
"step": 47830
|
|
},
|
|
{
|
|
"entropy": 5.097300910949707,
|
|
"epoch": 4.595100864553314,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00030719111921865687,
|
|
"loss": 4.5267,
|
|
"mean_token_accuracy": 0.2667505666613579,
|
|
"num_tokens": 109702473.0,
|
|
"step": 47835
|
|
},
|
|
{
|
|
"entropy": 5.117015647888183,
|
|
"epoch": 4.595581171950048,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003071571879873514,
|
|
"loss": 4.4936,
|
|
"mean_token_accuracy": 0.2666104182600975,
|
|
"num_tokens": 109713802.0,
|
|
"step": 47840
|
|
},
|
|
{
|
|
"entropy": 5.058982086181641,
|
|
"epoch": 4.5960614793467816,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003071232560094514,
|
|
"loss": 4.5267,
|
|
"mean_token_accuracy": 0.26811015903949736,
|
|
"num_tokens": 109725801.0,
|
|
"step": 47845
|
|
},
|
|
{
|
|
"entropy": 5.203838872909546,
|
|
"epoch": 4.596541786743516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00030708932328574477,
|
|
"loss": 4.6193,
|
|
"mean_token_accuracy": 0.25805127918720244,
|
|
"num_tokens": 109737570.0,
|
|
"step": 47850
|
|
},
|
|
{
|
|
"entropy": 5.102561616897583,
|
|
"epoch": 4.59702209414025,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00030705538981701946,
|
|
"loss": 4.4868,
|
|
"mean_token_accuracy": 0.2692680686712265,
|
|
"num_tokens": 109749535.0,
|
|
"step": 47855
|
|
},
|
|
{
|
|
"entropy": 5.037671518325806,
|
|
"epoch": 4.597502401536984,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00030702145560406314,
|
|
"loss": 4.4917,
|
|
"mean_token_accuracy": 0.2677430406212807,
|
|
"num_tokens": 109761020.0,
|
|
"step": 47860
|
|
},
|
|
{
|
|
"entropy": 5.1181893825531,
|
|
"epoch": 4.597982708933718,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00030698752064766365,
|
|
"loss": 4.6142,
|
|
"mean_token_accuracy": 0.257651099562645,
|
|
"num_tokens": 109773669.0,
|
|
"step": 47865
|
|
},
|
|
{
|
|
"entropy": 5.248726320266724,
|
|
"epoch": 4.598463016330451,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000306953584948609,
|
|
"loss": 4.6604,
|
|
"mean_token_accuracy": 0.24743512123823166,
|
|
"num_tokens": 109784306.0,
|
|
"step": 47870
|
|
},
|
|
{
|
|
"entropy": 5.155737257003784,
|
|
"epoch": 4.598943323727186,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003069196485076869,
|
|
"loss": 4.5978,
|
|
"mean_token_accuracy": 0.260567906498909,
|
|
"num_tokens": 109796794.0,
|
|
"step": 47875
|
|
},
|
|
{
|
|
"entropy": 5.109196186065674,
|
|
"epoch": 4.599423631123919,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003068857113256854,
|
|
"loss": 4.4584,
|
|
"mean_token_accuracy": 0.27384387999773024,
|
|
"num_tokens": 109809139.0,
|
|
"step": 47880
|
|
},
|
|
{
|
|
"entropy": 5.129623889923096,
|
|
"epoch": 4.5999039385206535,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003068517734033923,
|
|
"loss": 4.5923,
|
|
"mean_token_accuracy": 0.2629143074154854,
|
|
"num_tokens": 109821791.0,
|
|
"step": 47885
|
|
},
|
|
{
|
|
"entropy": 5.11292667388916,
|
|
"epoch": 4.600384245917387,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00030681783474159564,
|
|
"loss": 4.4637,
|
|
"mean_token_accuracy": 0.2728829562664032,
|
|
"num_tokens": 109832600.0,
|
|
"step": 47890
|
|
},
|
|
{
|
|
"entropy": 5.097394323348999,
|
|
"epoch": 4.600864553314121,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003067838953410833,
|
|
"loss": 4.5303,
|
|
"mean_token_accuracy": 0.2635126993060112,
|
|
"num_tokens": 109844035.0,
|
|
"step": 47895
|
|
},
|
|
{
|
|
"entropy": 5.093394327163696,
|
|
"epoch": 4.601344860710855,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00030674995520264337,
|
|
"loss": 4.5713,
|
|
"mean_token_accuracy": 0.26746260523796084,
|
|
"num_tokens": 109856278.0,
|
|
"step": 47900
|
|
},
|
|
{
|
|
"entropy": 5.134031581878662,
|
|
"epoch": 4.601825168107589,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00030671601432706374,
|
|
"loss": 4.5393,
|
|
"mean_token_accuracy": 0.26587103456258776,
|
|
"num_tokens": 109867093.0,
|
|
"step": 47905
|
|
},
|
|
{
|
|
"entropy": 5.120401525497437,
|
|
"epoch": 4.6023054755043225,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003066820727151324,
|
|
"loss": 4.5846,
|
|
"mean_token_accuracy": 0.2606979563832283,
|
|
"num_tokens": 109878304.0,
|
|
"step": 47910
|
|
},
|
|
{
|
|
"entropy": 5.164589071273804,
|
|
"epoch": 4.602785782901057,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00030664813036763744,
|
|
"loss": 4.5762,
|
|
"mean_token_accuracy": 0.261316654086113,
|
|
"num_tokens": 109889067.0,
|
|
"step": 47915
|
|
},
|
|
{
|
|
"entropy": 5.114986610412598,
|
|
"epoch": 4.60326609029779,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003066141872853668,
|
|
"loss": 4.4756,
|
|
"mean_token_accuracy": 0.270066699385643,
|
|
"num_tokens": 109899802.0,
|
|
"step": 47920
|
|
},
|
|
{
|
|
"entropy": 5.154208564758301,
|
|
"epoch": 4.6037463976945245,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003065802434691087,
|
|
"loss": 4.6004,
|
|
"mean_token_accuracy": 0.25878443717956545,
|
|
"num_tokens": 109910510.0,
|
|
"step": 47925
|
|
},
|
|
{
|
|
"entropy": 5.111742639541626,
|
|
"epoch": 4.604226705091259,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00030654629891965106,
|
|
"loss": 4.6009,
|
|
"mean_token_accuracy": 0.2642818033695221,
|
|
"num_tokens": 109922493.0,
|
|
"step": 47930
|
|
},
|
|
{
|
|
"entropy": 5.114192914962769,
|
|
"epoch": 4.604707012487992,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003065123536377821,
|
|
"loss": 4.5855,
|
|
"mean_token_accuracy": 0.2662153661251068,
|
|
"num_tokens": 109934256.0,
|
|
"step": 47935
|
|
},
|
|
{
|
|
"entropy": 5.138178777694702,
|
|
"epoch": 4.605187319884726,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003064784076242897,
|
|
"loss": 4.5271,
|
|
"mean_token_accuracy": 0.27374497056007385,
|
|
"num_tokens": 109945982.0,
|
|
"step": 47940
|
|
},
|
|
{
|
|
"entropy": 5.156451320648193,
|
|
"epoch": 4.60566762728146,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003064444608799623,
|
|
"loss": 4.5969,
|
|
"mean_token_accuracy": 0.2592488512396812,
|
|
"num_tokens": 109956838.0,
|
|
"step": 47945
|
|
},
|
|
{
|
|
"entropy": 5.105519008636475,
|
|
"epoch": 4.606147934678194,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00030641051340558786,
|
|
"loss": 4.6358,
|
|
"mean_token_accuracy": 0.2566707879304886,
|
|
"num_tokens": 109968750.0,
|
|
"step": 47950
|
|
},
|
|
{
|
|
"entropy": 5.130354690551758,
|
|
"epoch": 4.606628242074928,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00030637656520195454,
|
|
"loss": 4.5874,
|
|
"mean_token_accuracy": 0.2694664478302002,
|
|
"num_tokens": 109979146.0,
|
|
"step": 47955
|
|
},
|
|
{
|
|
"entropy": 5.192568349838257,
|
|
"epoch": 4.607108549471662,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003063426162698506,
|
|
"loss": 4.6383,
|
|
"mean_token_accuracy": 0.2609327271580696,
|
|
"num_tokens": 109991331.0,
|
|
"step": 47960
|
|
},
|
|
{
|
|
"entropy": 5.165323400497437,
|
|
"epoch": 4.607588856868396,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003063086666100641,
|
|
"loss": 4.5947,
|
|
"mean_token_accuracy": 0.2691725671291351,
|
|
"num_tokens": 110002819.0,
|
|
"step": 47965
|
|
},
|
|
{
|
|
"entropy": 5.008587217330932,
|
|
"epoch": 4.60806916426513,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003062747162233834,
|
|
"loss": 4.4837,
|
|
"mean_token_accuracy": 0.26972082406282427,
|
|
"num_tokens": 110013888.0,
|
|
"step": 47970
|
|
},
|
|
{
|
|
"entropy": 5.112602090835571,
|
|
"epoch": 4.608549471661863,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003062407651105966,
|
|
"loss": 4.5555,
|
|
"mean_token_accuracy": 0.2564640060067177,
|
|
"num_tokens": 110026536.0,
|
|
"step": 47975
|
|
},
|
|
{
|
|
"entropy": 5.162768983840943,
|
|
"epoch": 4.609029779058598,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000306206813272492,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.26398636400699615,
|
|
"num_tokens": 110038470.0,
|
|
"step": 47980
|
|
},
|
|
{
|
|
"entropy": 5.090512228012085,
|
|
"epoch": 4.609510086455331,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003061728607098579,
|
|
"loss": 4.489,
|
|
"mean_token_accuracy": 0.2692642644047737,
|
|
"num_tokens": 110049087.0,
|
|
"step": 47985
|
|
},
|
|
{
|
|
"entropy": 5.1301126956939695,
|
|
"epoch": 4.609990393852065,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003061389074234825,
|
|
"loss": 4.5486,
|
|
"mean_token_accuracy": 0.2672876849770546,
|
|
"num_tokens": 110060515.0,
|
|
"step": 47990
|
|
},
|
|
{
|
|
"entropy": 5.1820080280303955,
|
|
"epoch": 4.610470701248799,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003061049534141542,
|
|
"loss": 4.6232,
|
|
"mean_token_accuracy": 0.26124498546123504,
|
|
"num_tokens": 110071180.0,
|
|
"step": 47995
|
|
},
|
|
{
|
|
"entropy": 5.132456731796265,
|
|
"epoch": 4.610951008645533,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003060709986826612,
|
|
"loss": 4.567,
|
|
"mean_token_accuracy": 0.2616379722952843,
|
|
"num_tokens": 110083288.0,
|
|
"step": 48000
|
|
},
|
|
{
|
|
"epoch": 4.610951008645533,
|
|
"eval_entropy": 4.929117013860598,
|
|
"eval_loss": 4.706631183624268,
|
|
"eval_mean_token_accuracy": 0.26336356124199056,
|
|
"eval_num_tokens": 110083288.0,
|
|
"eval_runtime": 26.4757,
|
|
"eval_samples_per_second": 1239.436,
|
|
"eval_steps_per_second": 154.934,
|
|
"step": 48000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 104090,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.68254621240832e+17,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|