d79b553852
Model: fpadovani/hin-deva-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
42112 lines
1.1 MiB
42112 lines
1.1 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.0172910662824206,
|
|
"eval_steps": 3000,
|
|
"global_step": 21000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 7.3624264022016e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|