d79b553852
Model: fpadovani/hin-deva-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2881844380403458,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"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
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 104090,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.0541794369536e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|