6035 lines
164 KiB
JSON
6035 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.3942699434879748,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.691970920562744,
|
||
|
|
"epoch": 0.000657116572479958,
|
||
|
|
"grad_norm": 11.375,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.9102,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 18160.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.69195909500122,
|
||
|
|
"epoch": 0.001314233144959916,
|
||
|
|
"grad_norm": 11.8125,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.8426,
|
||
|
|
"mean_token_accuracy": 0.00034901105682365595,
|
||
|
|
"num_tokens": 34700.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.689266014099122,
|
||
|
|
"epoch": 0.001971349717439874,
|
||
|
|
"grad_norm": 8.375,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.5846,
|
||
|
|
"mean_token_accuracy": 0.0499508892185986,
|
||
|
|
"num_tokens": 52678.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.562198734283447,
|
||
|
|
"epoch": 0.002628466289919832,
|
||
|
|
"grad_norm": 5.40625,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.3172,
|
||
|
|
"mean_token_accuracy": 0.0605622336268425,
|
||
|
|
"num_tokens": 69607.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.345282936096192,
|
||
|
|
"epoch": 0.0032855828623997896,
|
||
|
|
"grad_norm": 3.71875,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 10.0938,
|
||
|
|
"mean_token_accuracy": 0.06148592121899128,
|
||
|
|
"num_tokens": 88068.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.521661567687989,
|
||
|
|
"epoch": 0.003942699434879748,
|
||
|
|
"grad_norm": 3.171875,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 9.9441,
|
||
|
|
"mean_token_accuracy": 0.06816631071269512,
|
||
|
|
"num_tokens": 105839.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.302499389648437,
|
||
|
|
"epoch": 0.004599816007359705,
|
||
|
|
"grad_norm": 2.375,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 9.899,
|
||
|
|
"mean_token_accuracy": 0.0670669324696064,
|
||
|
|
"num_tokens": 125068.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.426428699493409,
|
||
|
|
"epoch": 0.005256932579839664,
|
||
|
|
"grad_norm": 2.765625,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 9.8561,
|
||
|
|
"mean_token_accuracy": 0.06749101914465427,
|
||
|
|
"num_tokens": 143271.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.273355770111085,
|
||
|
|
"epoch": 0.0059140491523196215,
|
||
|
|
"grad_norm": 2.0,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 9.8657,
|
||
|
|
"mean_token_accuracy": 0.06502391099929809,
|
||
|
|
"num_tokens": 160886.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.348071479797364,
|
||
|
|
"epoch": 0.006571165724799579,
|
||
|
|
"grad_norm": 2.359375,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.7845,
|
||
|
|
"mean_token_accuracy": 0.06918984390795231,
|
||
|
|
"num_tokens": 179036.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.29029483795166,
|
||
|
|
"epoch": 0.007228282297279538,
|
||
|
|
"grad_norm": 1.7578125,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.731,
|
||
|
|
"mean_token_accuracy": 0.07089065425097943,
|
||
|
|
"num_tokens": 195478.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.25726251602173,
|
||
|
|
"epoch": 0.007885398869759495,
|
||
|
|
"grad_norm": 2.296875,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.7119,
|
||
|
|
"mean_token_accuracy": 0.0690944753587246,
|
||
|
|
"num_tokens": 213003.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.302559661865235,
|
||
|
|
"epoch": 0.008542515442239454,
|
||
|
|
"grad_norm": 2.265625,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.6475,
|
||
|
|
"mean_token_accuracy": 0.07418905831873417,
|
||
|
|
"num_tokens": 230223.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.087755107879639,
|
||
|
|
"epoch": 0.00919963201471941,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.5049,
|
||
|
|
"mean_token_accuracy": 0.0840003713965416,
|
||
|
|
"num_tokens": 246555.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.160563468933105,
|
||
|
|
"epoch": 0.00985674858719937,
|
||
|
|
"grad_norm": 1.7109375,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.4854,
|
||
|
|
"mean_token_accuracy": 0.07695499211549758,
|
||
|
|
"num_tokens": 262985.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.03568115234375,
|
||
|
|
"epoch": 0.010513865159679328,
|
||
|
|
"grad_norm": 2.140625,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.3528,
|
||
|
|
"mean_token_accuracy": 0.08797612711787224,
|
||
|
|
"num_tokens": 281701.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.050819873809814,
|
||
|
|
"epoch": 0.011170981732159285,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.3271,
|
||
|
|
"mean_token_accuracy": 0.08114923164248466,
|
||
|
|
"num_tokens": 298432.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.067263984680176,
|
||
|
|
"epoch": 0.011828098304639243,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.2657,
|
||
|
|
"mean_token_accuracy": 0.08178326860070229,
|
||
|
|
"num_tokens": 315559.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.996760272979737,
|
||
|
|
"epoch": 0.012485214877119202,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.174,
|
||
|
|
"mean_token_accuracy": 0.08735092431306839,
|
||
|
|
"num_tokens": 332959.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.032902812957763,
|
||
|
|
"epoch": 0.013142331449599158,
|
||
|
|
"grad_norm": 1.9609375,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.1565,
|
||
|
|
"mean_token_accuracy": 0.07826860286295415,
|
||
|
|
"num_tokens": 349872.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.87295093536377,
|
||
|
|
"epoch": 0.013799448022079117,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.0779,
|
||
|
|
"mean_token_accuracy": 0.07845050990581512,
|
||
|
|
"num_tokens": 365952.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.94616346359253,
|
||
|
|
"epoch": 0.014456564594559075,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 8.9723,
|
||
|
|
"mean_token_accuracy": 0.0847774550318718,
|
||
|
|
"num_tokens": 382830.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.765446853637695,
|
||
|
|
"epoch": 0.015113681167039032,
|
||
|
|
"grad_norm": 1.6796875,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.8959,
|
||
|
|
"mean_token_accuracy": 0.08348627090454101,
|
||
|
|
"num_tokens": 401729.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.696452522277832,
|
||
|
|
"epoch": 0.01577079773951899,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.7663,
|
||
|
|
"mean_token_accuracy": 0.0866998441517353,
|
||
|
|
"num_tokens": 419094.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.62384328842163,
|
||
|
|
"epoch": 0.01642791431199895,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.7123,
|
||
|
|
"mean_token_accuracy": 0.08670503944158554,
|
||
|
|
"num_tokens": 438632.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.458528423309327,
|
||
|
|
"epoch": 0.017085030884478908,
|
||
|
|
"grad_norm": 2.109375,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.5991,
|
||
|
|
"mean_token_accuracy": 0.08925274014472961,
|
||
|
|
"num_tokens": 456025.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.395387935638428,
|
||
|
|
"epoch": 0.017742147456958863,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.5874,
|
||
|
|
"mean_token_accuracy": 0.08284339755773544,
|
||
|
|
"num_tokens": 473414.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.288764190673827,
|
||
|
|
"epoch": 0.01839926402943882,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.484,
|
||
|
|
"mean_token_accuracy": 0.08540036529302597,
|
||
|
|
"num_tokens": 490039.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.080249691009522,
|
||
|
|
"epoch": 0.01905638060191878,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.4185,
|
||
|
|
"mean_token_accuracy": 0.09069929495453835,
|
||
|
|
"num_tokens": 506896.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.990424156188965,
|
||
|
|
"epoch": 0.01971349717439874,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.3134,
|
||
|
|
"mean_token_accuracy": 0.0939207799732685,
|
||
|
|
"num_tokens": 523544.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.895142555236816,
|
||
|
|
"epoch": 0.020370613746878697,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.3193,
|
||
|
|
"mean_token_accuracy": 0.0861300639808178,
|
||
|
|
"num_tokens": 540240.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.84927806854248,
|
||
|
|
"epoch": 0.021027730319358656,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 8.3388,
|
||
|
|
"mean_token_accuracy": 0.08859094232320786,
|
||
|
|
"num_tokens": 558460.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.804749298095704,
|
||
|
|
"epoch": 0.02168484689183861,
|
||
|
|
"grad_norm": 1.671875,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 8.3132,
|
||
|
|
"mean_token_accuracy": 0.08978721722960473,
|
||
|
|
"num_tokens": 577356.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.755771827697753,
|
||
|
|
"epoch": 0.02234196346431857,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 8.3233,
|
||
|
|
"mean_token_accuracy": 0.08325318172574044,
|
||
|
|
"num_tokens": 594702.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.61918659210205,
|
||
|
|
"epoch": 0.022999080036798528,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 8.2927,
|
||
|
|
"mean_token_accuracy": 0.08967687636613846,
|
||
|
|
"num_tokens": 612005.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.692005062103272,
|
||
|
|
"epoch": 0.023656196609278486,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 8.2979,
|
||
|
|
"mean_token_accuracy": 0.08311463445425034,
|
||
|
|
"num_tokens": 629271.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.543895149230957,
|
||
|
|
"epoch": 0.024313313181758445,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 8.2711,
|
||
|
|
"mean_token_accuracy": 0.09236689656972885,
|
||
|
|
"num_tokens": 646273.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.623021125793457,
|
||
|
|
"epoch": 0.024970429754238403,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 8.2622,
|
||
|
|
"mean_token_accuracy": 0.08237618803977967,
|
||
|
|
"num_tokens": 663263.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.503989696502686,
|
||
|
|
"epoch": 0.02562754632671836,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 8.1725,
|
||
|
|
"mean_token_accuracy": 0.09226469621062279,
|
||
|
|
"num_tokens": 681032.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.496358585357665,
|
||
|
|
"epoch": 0.026284662899198317,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 8.2157,
|
||
|
|
"mean_token_accuracy": 0.08867634385824204,
|
||
|
|
"num_tokens": 699353.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.597747421264648,
|
||
|
|
"epoch": 0.026941779471678275,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 8.2941,
|
||
|
|
"mean_token_accuracy": 0.08325276263058186,
|
||
|
|
"num_tokens": 717777.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.493968677520751,
|
||
|
|
"epoch": 0.027598896044158234,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 8.2395,
|
||
|
|
"mean_token_accuracy": 0.08642884120345115,
|
||
|
|
"num_tokens": 733831.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.45910186767578,
|
||
|
|
"epoch": 0.028256012616638192,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 8.202,
|
||
|
|
"mean_token_accuracy": 0.0875705562531948,
|
||
|
|
"num_tokens": 750057.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.502654266357421,
|
||
|
|
"epoch": 0.02891312918911815,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 8.2335,
|
||
|
|
"mean_token_accuracy": 0.08846379294991494,
|
||
|
|
"num_tokens": 767590.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.471471691131592,
|
||
|
|
"epoch": 0.029570245761598106,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 8.1997,
|
||
|
|
"mean_token_accuracy": 0.0836844079196453,
|
||
|
|
"num_tokens": 784496.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.473236179351806,
|
||
|
|
"epoch": 0.030227362334078064,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 8.22,
|
||
|
|
"mean_token_accuracy": 0.08451615646481514,
|
||
|
|
"num_tokens": 802589.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.466453552246094,
|
||
|
|
"epoch": 0.030884478906558023,
|
||
|
|
"grad_norm": 0.68359375,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 8.2459,
|
||
|
|
"mean_token_accuracy": 0.08304352685809135,
|
||
|
|
"num_tokens": 820375.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.500118160247803,
|
||
|
|
"epoch": 0.03154159547903798,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 8.1952,
|
||
|
|
"mean_token_accuracy": 0.08304070755839348,
|
||
|
|
"num_tokens": 838658.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.381299304962159,
|
||
|
|
"epoch": 0.03219871205151794,
|
||
|
|
"grad_norm": 0.78515625,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 8.205,
|
||
|
|
"mean_token_accuracy": 0.0860319972038269,
|
||
|
|
"num_tokens": 856534.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.390718936920166,
|
||
|
|
"epoch": 0.0328558286239979,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 8.1696,
|
||
|
|
"mean_token_accuracy": 0.09368039518594742,
|
||
|
|
"num_tokens": 872813.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.36027283668518,
|
||
|
|
"epoch": 0.03351294519647786,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 8.1428,
|
||
|
|
"mean_token_accuracy": 0.09875724688172341,
|
||
|
|
"num_tokens": 891675.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.41018009185791,
|
||
|
|
"epoch": 0.034170061768957816,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 8.1972,
|
||
|
|
"mean_token_accuracy": 0.08137553408741952,
|
||
|
|
"num_tokens": 907440.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.448321056365966,
|
||
|
|
"epoch": 0.034827178341437774,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 8.2255,
|
||
|
|
"mean_token_accuracy": 0.08277432322502136,
|
||
|
|
"num_tokens": 923909.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.386664962768554,
|
||
|
|
"epoch": 0.035484294913917726,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 8.1077,
|
||
|
|
"mean_token_accuracy": 0.09150323122739792,
|
||
|
|
"num_tokens": 940658.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.34205665588379,
|
||
|
|
"epoch": 0.036141411486397684,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 8.1535,
|
||
|
|
"mean_token_accuracy": 0.08561521768569946,
|
||
|
|
"num_tokens": 959095.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.375339221954345,
|
||
|
|
"epoch": 0.03679852805887764,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 8.1774,
|
||
|
|
"mean_token_accuracy": 0.08340813145041466,
|
||
|
|
"num_tokens": 976656.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.368755626678468,
|
||
|
|
"epoch": 0.0374556446313576,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 8.2048,
|
||
|
|
"mean_token_accuracy": 0.08358296155929565,
|
||
|
|
"num_tokens": 994326.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.306324100494384,
|
||
|
|
"epoch": 0.03811276120383756,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 8.1147,
|
||
|
|
"mean_token_accuracy": 0.0932599276304245,
|
||
|
|
"num_tokens": 1011859.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.31154556274414,
|
||
|
|
"epoch": 0.03876987777631752,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 8.142,
|
||
|
|
"mean_token_accuracy": 0.08438249453902244,
|
||
|
|
"num_tokens": 1028329.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.38582706451416,
|
||
|
|
"epoch": 0.03942699434879748,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 8.1226,
|
||
|
|
"mean_token_accuracy": 0.08788742870092392,
|
||
|
|
"num_tokens": 1045519.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.42501277923584,
|
||
|
|
"epoch": 0.040084110921277435,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 8.1104,
|
||
|
|
"mean_token_accuracy": 0.09161722511053086,
|
||
|
|
"num_tokens": 1063832.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.180773544311524,
|
||
|
|
"epoch": 0.040741227493757394,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 8.0692,
|
||
|
|
"mean_token_accuracy": 0.09160381332039833,
|
||
|
|
"num_tokens": 1081062.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.319191455841064,
|
||
|
|
"epoch": 0.04139834406623735,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 8.1206,
|
||
|
|
"mean_token_accuracy": 0.08650392666459084,
|
||
|
|
"num_tokens": 1100139.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.339826774597167,
|
||
|
|
"epoch": 0.04205546063871731,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 8.0878,
|
||
|
|
"mean_token_accuracy": 0.08833744451403618,
|
||
|
|
"num_tokens": 1117100.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.358532238006593,
|
||
|
|
"epoch": 0.04271257721119727,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 8.1339,
|
||
|
|
"mean_token_accuracy": 0.08414132967591285,
|
||
|
|
"num_tokens": 1136607.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.360890769958496,
|
||
|
|
"epoch": 0.04336969378367722,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 8.1636,
|
||
|
|
"mean_token_accuracy": 0.08001711294054985,
|
||
|
|
"num_tokens": 1154463.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.302077484130859,
|
||
|
|
"epoch": 0.04402681035615718,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 8.0492,
|
||
|
|
"mean_token_accuracy": 0.08888905569911003,
|
||
|
|
"num_tokens": 1172540.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.284979152679444,
|
||
|
|
"epoch": 0.04468392692863714,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 8.089,
|
||
|
|
"mean_token_accuracy": 0.08480592146515846,
|
||
|
|
"num_tokens": 1189393.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.305260276794433,
|
||
|
|
"epoch": 0.0453410435011171,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 8.0804,
|
||
|
|
"mean_token_accuracy": 0.087804014980793,
|
||
|
|
"num_tokens": 1205232.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.235641956329346,
|
||
|
|
"epoch": 0.045998160073597055,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 8.0386,
|
||
|
|
"mean_token_accuracy": 0.08915610313415527,
|
||
|
|
"num_tokens": 1222020.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.296236038208008,
|
||
|
|
"epoch": 0.046655276646077014,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 8.0122,
|
||
|
|
"mean_token_accuracy": 0.09561690092086791,
|
||
|
|
"num_tokens": 1239201.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.312324523925781,
|
||
|
|
"epoch": 0.04731239321855697,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 8.0528,
|
||
|
|
"mean_token_accuracy": 0.09137414395809174,
|
||
|
|
"num_tokens": 1256715.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.276749324798583,
|
||
|
|
"epoch": 0.04796950979103693,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 8.0682,
|
||
|
|
"mean_token_accuracy": 0.08286751359701157,
|
||
|
|
"num_tokens": 1273800.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.162324810028077,
|
||
|
|
"epoch": 0.04862662636351689,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 8.0052,
|
||
|
|
"mean_token_accuracy": 0.09242228120565414,
|
||
|
|
"num_tokens": 1291181.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.235886669158935,
|
||
|
|
"epoch": 0.04928374293599685,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 8.088,
|
||
|
|
"mean_token_accuracy": 0.08434378504753112,
|
||
|
|
"num_tokens": 1309264.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.252655410766602,
|
||
|
|
"epoch": 0.049940859508476806,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.9823,
|
||
|
|
"mean_token_accuracy": 0.08949511088430881,
|
||
|
|
"num_tokens": 1327117.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.148046970367432,
|
||
|
|
"epoch": 0.050597976080956765,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 8.0288,
|
||
|
|
"mean_token_accuracy": 0.08982144668698311,
|
||
|
|
"num_tokens": 1343972.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.245464324951172,
|
||
|
|
"epoch": 0.05125509265343672,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 7.9572,
|
||
|
|
"mean_token_accuracy": 0.08928473889827729,
|
||
|
|
"num_tokens": 1361432.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.094884061813355,
|
||
|
|
"epoch": 0.051912209225916675,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.9669,
|
||
|
|
"mean_token_accuracy": 0.09419442862272262,
|
||
|
|
"num_tokens": 1378191.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.211234951019287,
|
||
|
|
"epoch": 0.052569325798396634,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 7.9813,
|
||
|
|
"mean_token_accuracy": 0.08906673565506935,
|
||
|
|
"num_tokens": 1395872.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.18825888633728,
|
||
|
|
"epoch": 0.05322644237087659,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.9578,
|
||
|
|
"mean_token_accuracy": 0.09145129919052124,
|
||
|
|
"num_tokens": 1412816.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.134449100494384,
|
||
|
|
"epoch": 0.05388355894335655,
|
||
|
|
"grad_norm": 2.1875,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 7.8935,
|
||
|
|
"mean_token_accuracy": 0.10044471621513366,
|
||
|
|
"num_tokens": 1430644.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.148541164398193,
|
||
|
|
"epoch": 0.05454067551583651,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 7.9432,
|
||
|
|
"mean_token_accuracy": 0.09160158559679984,
|
||
|
|
"num_tokens": 1448021.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.23169984817505,
|
||
|
|
"epoch": 0.05519779208831647,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 7.9585,
|
||
|
|
"mean_token_accuracy": 0.09313838183879852,
|
||
|
|
"num_tokens": 1466428.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.167637252807618,
|
||
|
|
"epoch": 0.055854908660796426,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 7.8798,
|
||
|
|
"mean_token_accuracy": 0.09942131265997886,
|
||
|
|
"num_tokens": 1484554.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.104038047790528,
|
||
|
|
"epoch": 0.056512025233276385,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 7.8905,
|
||
|
|
"mean_token_accuracy": 0.09655392467975617,
|
||
|
|
"num_tokens": 1500452.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.07980990409851,
|
||
|
|
"epoch": 0.05716914180575634,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 7.9718,
|
||
|
|
"mean_token_accuracy": 0.0888563945889473,
|
||
|
|
"num_tokens": 1518482.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.099183750152587,
|
||
|
|
"epoch": 0.0578262583782363,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 7.9304,
|
||
|
|
"mean_token_accuracy": 0.0907039225101471,
|
||
|
|
"num_tokens": 1536107.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.13019618988037,
|
||
|
|
"epoch": 0.05848337495071626,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 7.9209,
|
||
|
|
"mean_token_accuracy": 0.08752450793981552,
|
||
|
|
"num_tokens": 1553722.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.061606645584106,
|
||
|
|
"epoch": 0.05914049152319621,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 7.878,
|
||
|
|
"mean_token_accuracy": 0.09788650721311569,
|
||
|
|
"num_tokens": 1571959.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.092618274688721,
|
||
|
|
"epoch": 0.05979760809567617,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 7.965,
|
||
|
|
"mean_token_accuracy": 0.08797019943594933,
|
||
|
|
"num_tokens": 1588595.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.051505088806152,
|
||
|
|
"epoch": 0.06045472466815613,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 7.8329,
|
||
|
|
"mean_token_accuracy": 0.08995860144495964,
|
||
|
|
"num_tokens": 1605185.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.061400985717773,
|
||
|
|
"epoch": 0.06111184124063609,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 7.8334,
|
||
|
|
"mean_token_accuracy": 0.0945149227976799,
|
||
|
|
"num_tokens": 1622966.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.077755498886109,
|
||
|
|
"epoch": 0.061768957813116046,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 7.8267,
|
||
|
|
"mean_token_accuracy": 0.09398441277444362,
|
||
|
|
"num_tokens": 1639697.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.02926688194275,
|
||
|
|
"epoch": 0.062426074385596005,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 7.851,
|
||
|
|
"mean_token_accuracy": 0.09462198317050934,
|
||
|
|
"num_tokens": 1656342.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.030053997039795,
|
||
|
|
"epoch": 0.06308319095807596,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 7.9004,
|
||
|
|
"mean_token_accuracy": 0.09348834380507469,
|
||
|
|
"num_tokens": 1673829.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.142562198638917,
|
||
|
|
"epoch": 0.06374030753055591,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 7.9383,
|
||
|
|
"mean_token_accuracy": 0.08797306269407272,
|
||
|
|
"num_tokens": 1691938.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.987461423873901,
|
||
|
|
"epoch": 0.06439742410303588,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 7.8913,
|
||
|
|
"mean_token_accuracy": 0.09134467840194702,
|
||
|
|
"num_tokens": 1708545.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.951012325286865,
|
||
|
|
"epoch": 0.06505454067551583,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 7.8445,
|
||
|
|
"mean_token_accuracy": 0.09492667466402054,
|
||
|
|
"num_tokens": 1725199.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.079988193511962,
|
||
|
|
"epoch": 0.0657116572479958,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 7.8607,
|
||
|
|
"mean_token_accuracy": 0.09226195812225342,
|
||
|
|
"num_tokens": 1742893.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.04035177230835,
|
||
|
|
"epoch": 0.06636877382047575,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 7.8558,
|
||
|
|
"mean_token_accuracy": 0.09375119879841805,
|
||
|
|
"num_tokens": 1759540.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.108158254623413,
|
||
|
|
"epoch": 0.06702589039295571,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 7.8746,
|
||
|
|
"mean_token_accuracy": 0.0892824463546276,
|
||
|
|
"num_tokens": 1776617.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.932979726791382,
|
||
|
|
"epoch": 0.06768300696543567,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 7.8364,
|
||
|
|
"mean_token_accuracy": 0.0924128919839859,
|
||
|
|
"num_tokens": 1795065.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.049097728729247,
|
||
|
|
"epoch": 0.06834012353791563,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 7.8169,
|
||
|
|
"mean_token_accuracy": 0.08902051150798798,
|
||
|
|
"num_tokens": 1811477.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.031516742706298,
|
||
|
|
"epoch": 0.06899724011039558,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 7.8404,
|
||
|
|
"mean_token_accuracy": 0.09564107805490493,
|
||
|
|
"num_tokens": 1829272.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.003777980804443,
|
||
|
|
"epoch": 0.06965435668287555,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 7.8549,
|
||
|
|
"mean_token_accuracy": 0.08890713900327682,
|
||
|
|
"num_tokens": 1845882.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.024421834945679,
|
||
|
|
"epoch": 0.0703114732553555,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 7.8113,
|
||
|
|
"mean_token_accuracy": 0.09261564016342164,
|
||
|
|
"num_tokens": 1861000.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.050934314727783,
|
||
|
|
"epoch": 0.07096858982783545,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 7.8551,
|
||
|
|
"mean_token_accuracy": 0.08385444208979606,
|
||
|
|
"num_tokens": 1876979.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.997040605545044,
|
||
|
|
"epoch": 0.07162570640031542,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 7.8555,
|
||
|
|
"mean_token_accuracy": 0.08732549175620079,
|
||
|
|
"num_tokens": 1895191.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.934540605545044,
|
||
|
|
"epoch": 0.07228282297279537,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 7.7701,
|
||
|
|
"mean_token_accuracy": 0.08872183412313461,
|
||
|
|
"num_tokens": 1912466.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.969846534729004,
|
||
|
|
"epoch": 0.07293993954527533,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 7.7246,
|
||
|
|
"mean_token_accuracy": 0.09994208216667175,
|
||
|
|
"num_tokens": 1932285.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.008286952972412,
|
||
|
|
"epoch": 0.07359705611775529,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 7.7973,
|
||
|
|
"mean_token_accuracy": 0.08675110414624214,
|
||
|
|
"num_tokens": 1948437.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.939477729797363,
|
||
|
|
"epoch": 0.07425417269023525,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 7.8076,
|
||
|
|
"mean_token_accuracy": 0.08641846030950547,
|
||
|
|
"num_tokens": 1964579.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.910443115234375,
|
||
|
|
"epoch": 0.0749112892627152,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 7.7054,
|
||
|
|
"mean_token_accuracy": 0.10115818828344345,
|
||
|
|
"num_tokens": 1981247.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.956994104385376,
|
||
|
|
"epoch": 0.07556840583519517,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 7.7938,
|
||
|
|
"mean_token_accuracy": 0.09043643400073051,
|
||
|
|
"num_tokens": 1999031.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.981093311309815,
|
||
|
|
"epoch": 0.07622552240767512,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 7.7212,
|
||
|
|
"mean_token_accuracy": 0.09121812731027604,
|
||
|
|
"num_tokens": 2015715.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.911635208129883,
|
||
|
|
"epoch": 0.07688263898015509,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 7.7238,
|
||
|
|
"mean_token_accuracy": 0.09262361451983452,
|
||
|
|
"num_tokens": 2032235.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.910367107391357,
|
||
|
|
"epoch": 0.07753975555263504,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 7.7125,
|
||
|
|
"mean_token_accuracy": 0.09460373297333717,
|
||
|
|
"num_tokens": 2050378.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8812439918518065,
|
||
|
|
"epoch": 0.078196872125115,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 7.7713,
|
||
|
|
"mean_token_accuracy": 0.08955961838364601,
|
||
|
|
"num_tokens": 2067713.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.799747514724731,
|
||
|
|
"epoch": 0.07885398869759495,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 7.6174,
|
||
|
|
"mean_token_accuracy": 0.09769630283117295,
|
||
|
|
"num_tokens": 2086602.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.92856650352478,
|
||
|
|
"epoch": 0.0795111052700749,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 7.5796,
|
||
|
|
"mean_token_accuracy": 0.09621628671884537,
|
||
|
|
"num_tokens": 2103142.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.727544260025025,
|
||
|
|
"epoch": 0.08016822184255487,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 7.5822,
|
||
|
|
"mean_token_accuracy": 0.09833648353815079,
|
||
|
|
"num_tokens": 2120792.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.851658725738526,
|
||
|
|
"epoch": 0.08082533841503482,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 7.6633,
|
||
|
|
"mean_token_accuracy": 0.1018780030310154,
|
||
|
|
"num_tokens": 2137688.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.81537652015686,
|
||
|
|
"epoch": 0.08148245498751479,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 7.7289,
|
||
|
|
"mean_token_accuracy": 0.0900080993771553,
|
||
|
|
"num_tokens": 2155353.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8868913650512695,
|
||
|
|
"epoch": 0.08213957155999474,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 7.6782,
|
||
|
|
"mean_token_accuracy": 0.09196878299117088,
|
||
|
|
"num_tokens": 2173999.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.794561433792114,
|
||
|
|
"epoch": 0.0827966881324747,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 7.6572,
|
||
|
|
"mean_token_accuracy": 0.0915692389011383,
|
||
|
|
"num_tokens": 2190657.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.878007602691651,
|
||
|
|
"epoch": 0.08345380470495466,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 7.6938,
|
||
|
|
"mean_token_accuracy": 0.09030900672078132,
|
||
|
|
"num_tokens": 2207512.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.812237787246704,
|
||
|
|
"epoch": 0.08411092127743462,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 7.6791,
|
||
|
|
"mean_token_accuracy": 0.09167201295495034,
|
||
|
|
"num_tokens": 2224911.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.797879552841186,
|
||
|
|
"epoch": 0.08476803784991457,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 7.6568,
|
||
|
|
"mean_token_accuracy": 0.0889101818203926,
|
||
|
|
"num_tokens": 2244030.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.85651330947876,
|
||
|
|
"epoch": 0.08542515442239454,
|
||
|
|
"grad_norm": 1.546875,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 7.6423,
|
||
|
|
"mean_token_accuracy": 0.0900063842535019,
|
||
|
|
"num_tokens": 2260550.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.780899906158448,
|
||
|
|
"epoch": 0.08608227099487449,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 7.7007,
|
||
|
|
"mean_token_accuracy": 0.0889291986823082,
|
||
|
|
"num_tokens": 2277732.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.779685974121094,
|
||
|
|
"epoch": 0.08673938756735444,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 7.58,
|
||
|
|
"mean_token_accuracy": 0.09410673379898071,
|
||
|
|
"num_tokens": 2294074.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.794468116760254,
|
||
|
|
"epoch": 0.08739650413983441,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 7.6426,
|
||
|
|
"mean_token_accuracy": 0.09421529322862625,
|
||
|
|
"num_tokens": 2309118.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.813050365447998,
|
||
|
|
"epoch": 0.08805362071231436,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 7.6292,
|
||
|
|
"mean_token_accuracy": 0.09069699347019196,
|
||
|
|
"num_tokens": 2327193.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.743873262405396,
|
||
|
|
"epoch": 0.08871073728479432,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 7.5902,
|
||
|
|
"mean_token_accuracy": 0.09050673618912697,
|
||
|
|
"num_tokens": 2344357.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.736028623580933,
|
||
|
|
"epoch": 0.08936785385727428,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 7.5732,
|
||
|
|
"mean_token_accuracy": 0.09712009504437447,
|
||
|
|
"num_tokens": 2361933.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.702030611038208,
|
||
|
|
"epoch": 0.09002497042975424,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 7.5759,
|
||
|
|
"mean_token_accuracy": 0.09285529553890229,
|
||
|
|
"num_tokens": 2377774.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.651546764373779,
|
||
|
|
"epoch": 0.0906820870022342,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 7.4294,
|
||
|
|
"mean_token_accuracy": 0.11124403774738312,
|
||
|
|
"num_tokens": 2395363.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.507357358932495,
|
||
|
|
"epoch": 0.09133920357471416,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 7.4995,
|
||
|
|
"mean_token_accuracy": 0.1047697126865387,
|
||
|
|
"num_tokens": 2413270.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.713213491439819,
|
||
|
|
"epoch": 0.09199632014719411,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 7.5303,
|
||
|
|
"mean_token_accuracy": 0.09587173163890839,
|
||
|
|
"num_tokens": 2432077.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.674976873397827,
|
||
|
|
"epoch": 0.09265343671967408,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 7.6357,
|
||
|
|
"mean_token_accuracy": 0.09107815846800804,
|
||
|
|
"num_tokens": 2449541.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.67608757019043,
|
||
|
|
"epoch": 0.09331055329215403,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 7.5318,
|
||
|
|
"mean_token_accuracy": 0.09878497794270516,
|
||
|
|
"num_tokens": 2466375.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.702895450592041,
|
||
|
|
"epoch": 0.09396766986463398,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 7.6132,
|
||
|
|
"mean_token_accuracy": 0.0879031240940094,
|
||
|
|
"num_tokens": 2483793.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7163526058197025,
|
||
|
|
"epoch": 0.09462478643711394,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 7.5686,
|
||
|
|
"mean_token_accuracy": 0.0924137331545353,
|
||
|
|
"num_tokens": 2500689.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.652881479263305,
|
||
|
|
"epoch": 0.0952819030095939,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 7.4627,
|
||
|
|
"mean_token_accuracy": 0.10279997587203979,
|
||
|
|
"num_tokens": 2517867.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.693321084976196,
|
||
|
|
"epoch": 0.09593901958207386,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 7.5954,
|
||
|
|
"mean_token_accuracy": 0.09244397953152657,
|
||
|
|
"num_tokens": 2536356.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.569602060317993,
|
||
|
|
"epoch": 0.09659613615455381,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 7.4796,
|
||
|
|
"mean_token_accuracy": 0.09813716039061546,
|
||
|
|
"num_tokens": 2552821.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.72858157157898,
|
||
|
|
"epoch": 0.09725325272703378,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 7.595,
|
||
|
|
"mean_token_accuracy": 0.09159181639552116,
|
||
|
|
"num_tokens": 2570098.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5410655498504635,
|
||
|
|
"epoch": 0.09791036929951373,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 7.3465,
|
||
|
|
"mean_token_accuracy": 0.11115500703454018,
|
||
|
|
"num_tokens": 2587508.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.601456546783448,
|
||
|
|
"epoch": 0.0985674858719937,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 7.5464,
|
||
|
|
"mean_token_accuracy": 0.09635312631726264,
|
||
|
|
"num_tokens": 2604845.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.641898345947266,
|
||
|
|
"epoch": 0.09922460244447365,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 7.5835,
|
||
|
|
"mean_token_accuracy": 0.0863256387412548,
|
||
|
|
"num_tokens": 2623281.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.665192556381226,
|
||
|
|
"epoch": 0.09988171901695361,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 7.5832,
|
||
|
|
"mean_token_accuracy": 0.09262030571699142,
|
||
|
|
"num_tokens": 2641315.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.523155879974365,
|
||
|
|
"epoch": 0.10053883558943356,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 7.4307,
|
||
|
|
"mean_token_accuracy": 0.11434739604592323,
|
||
|
|
"num_tokens": 2658404.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.55363826751709,
|
||
|
|
"epoch": 0.10119595216191353,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 7.4513,
|
||
|
|
"mean_token_accuracy": 0.10143931359052658,
|
||
|
|
"num_tokens": 2675980.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.607959318161011,
|
||
|
|
"epoch": 0.10185306873439348,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 7.4692,
|
||
|
|
"mean_token_accuracy": 0.10197424218058586,
|
||
|
|
"num_tokens": 2694290.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.581793880462646,
|
||
|
|
"epoch": 0.10251018530687343,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 7.5235,
|
||
|
|
"mean_token_accuracy": 0.09472638443112373,
|
||
|
|
"num_tokens": 2710661.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.651349306106567,
|
||
|
|
"epoch": 0.1031673018793534,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 7.523,
|
||
|
|
"mean_token_accuracy": 0.09317268952727317,
|
||
|
|
"num_tokens": 2728660.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.531972074508667,
|
||
|
|
"epoch": 0.10382441845183335,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 7.4728,
|
||
|
|
"mean_token_accuracy": 0.09988932237029076,
|
||
|
|
"num_tokens": 2745130.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.562900590896606,
|
||
|
|
"epoch": 0.10448153502431332,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 7.4529,
|
||
|
|
"mean_token_accuracy": 0.0973394624888897,
|
||
|
|
"num_tokens": 2762001.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.580878829956054,
|
||
|
|
"epoch": 0.10513865159679327,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 7.4957,
|
||
|
|
"mean_token_accuracy": 0.09426558315753937,
|
||
|
|
"num_tokens": 2778634.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.577242612838745,
|
||
|
|
"epoch": 0.10579576816927323,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 7.5104,
|
||
|
|
"mean_token_accuracy": 0.0927124135196209,
|
||
|
|
"num_tokens": 2795207.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.537419080734253,
|
||
|
|
"epoch": 0.10645288474175318,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 7.3978,
|
||
|
|
"mean_token_accuracy": 0.10554074496030807,
|
||
|
|
"num_tokens": 2813506.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.516330528259277,
|
||
|
|
"epoch": 0.10711000131423315,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 7.4253,
|
||
|
|
"mean_token_accuracy": 0.0940089389681816,
|
||
|
|
"num_tokens": 2829732.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.539044332504273,
|
||
|
|
"epoch": 0.1077671178867131,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 7.46,
|
||
|
|
"mean_token_accuracy": 0.09880606159567833,
|
||
|
|
"num_tokens": 2846436.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.575464391708374,
|
||
|
|
"epoch": 0.10842423445919307,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 7.491,
|
||
|
|
"mean_token_accuracy": 0.09248777329921723,
|
||
|
|
"num_tokens": 2864719.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.577031135559082,
|
||
|
|
"epoch": 0.10908135103167302,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 7.4707,
|
||
|
|
"mean_token_accuracy": 0.09447416216135025,
|
||
|
|
"num_tokens": 2881566.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.481828498840332,
|
||
|
|
"epoch": 0.10973846760415297,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 7.3937,
|
||
|
|
"mean_token_accuracy": 0.09647827595472336,
|
||
|
|
"num_tokens": 2899034.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.493137073516846,
|
||
|
|
"epoch": 0.11039558417663294,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 7.4897,
|
||
|
|
"mean_token_accuracy": 0.09726456999778747,
|
||
|
|
"num_tokens": 2915773.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.474357795715332,
|
||
|
|
"epoch": 0.11105270074911289,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 7.4534,
|
||
|
|
"mean_token_accuracy": 0.08885478526353836,
|
||
|
|
"num_tokens": 2933718.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.565765857696533,
|
||
|
|
"epoch": 0.11170981732159285,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 7.4222,
|
||
|
|
"mean_token_accuracy": 0.09584522470831872,
|
||
|
|
"num_tokens": 2951690.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.415678358078003,
|
||
|
|
"epoch": 0.1123669338940728,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 7.4284,
|
||
|
|
"mean_token_accuracy": 0.10300374701619149,
|
||
|
|
"num_tokens": 2969331.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.552033138275147,
|
||
|
|
"epoch": 0.11302405046655277,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 7.4741,
|
||
|
|
"mean_token_accuracy": 0.09474552050232887,
|
||
|
|
"num_tokens": 2985229.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.461298561096191,
|
||
|
|
"epoch": 0.11368116703903272,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 7.4336,
|
||
|
|
"mean_token_accuracy": 0.08998932093381881,
|
||
|
|
"num_tokens": 3001075.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.452679061889649,
|
||
|
|
"epoch": 0.11433828361151269,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 7.3945,
|
||
|
|
"mean_token_accuracy": 0.09610669687390327,
|
||
|
|
"num_tokens": 3018095.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.448093366622925,
|
||
|
|
"epoch": 0.11499540018399264,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 7.3951,
|
||
|
|
"mean_token_accuracy": 0.1022491253912449,
|
||
|
|
"num_tokens": 3035726.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.428170299530029,
|
||
|
|
"epoch": 0.1156525167564726,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 7.3273,
|
||
|
|
"mean_token_accuracy": 0.10195292830467224,
|
||
|
|
"num_tokens": 3052054.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.476611471176147,
|
||
|
|
"epoch": 0.11630963332895256,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 7.4027,
|
||
|
|
"mean_token_accuracy": 0.09874287694692611,
|
||
|
|
"num_tokens": 3069350.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.442331171035766,
|
||
|
|
"epoch": 0.11696674990143252,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 7.3826,
|
||
|
|
"mean_token_accuracy": 0.09821617379784583,
|
||
|
|
"num_tokens": 3085891.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.453686094284057,
|
||
|
|
"epoch": 0.11762386647391247,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 7.4196,
|
||
|
|
"mean_token_accuracy": 0.09896242916584015,
|
||
|
|
"num_tokens": 3103571.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.417425680160522,
|
||
|
|
"epoch": 0.11828098304639242,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 7.3775,
|
||
|
|
"mean_token_accuracy": 0.1023717314004898,
|
||
|
|
"num_tokens": 3120883.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.509283113479614,
|
||
|
|
"epoch": 0.11893809961887239,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 7.4598,
|
||
|
|
"mean_token_accuracy": 0.09272672832012177,
|
||
|
|
"num_tokens": 3140137.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.376467370986939,
|
||
|
|
"epoch": 0.11959521619135234,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 7.3768,
|
||
|
|
"mean_token_accuracy": 0.09941514804959298,
|
||
|
|
"num_tokens": 3157118.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.486584043502807,
|
||
|
|
"epoch": 0.1202523327638323,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 7.4627,
|
||
|
|
"mean_token_accuracy": 0.089472546428442,
|
||
|
|
"num_tokens": 3174967.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.364890909194946,
|
||
|
|
"epoch": 0.12090944933631226,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 7.3251,
|
||
|
|
"mean_token_accuracy": 0.10790883004665375,
|
||
|
|
"num_tokens": 3193791.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.424156236648559,
|
||
|
|
"epoch": 0.12156656590879222,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 7.3888,
|
||
|
|
"mean_token_accuracy": 0.10138912200927734,
|
||
|
|
"num_tokens": 3212807.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.483264064788818,
|
||
|
|
"epoch": 0.12222368248127218,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 7.4603,
|
||
|
|
"mean_token_accuracy": 0.09148271009325981,
|
||
|
|
"num_tokens": 3229945.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.443746614456177,
|
||
|
|
"epoch": 0.12288079905375214,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 7.4491,
|
||
|
|
"mean_token_accuracy": 0.0934921719133854,
|
||
|
|
"num_tokens": 3248333.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.459245109558106,
|
||
|
|
"epoch": 0.12353791562623209,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 7.3967,
|
||
|
|
"mean_token_accuracy": 0.09736947789788246,
|
||
|
|
"num_tokens": 3266344.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.429486465454102,
|
||
|
|
"epoch": 0.12419503219871206,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 7.4148,
|
||
|
|
"mean_token_accuracy": 0.10019433051347733,
|
||
|
|
"num_tokens": 3283346.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.285105895996094,
|
||
|
|
"epoch": 0.12485214877119201,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 7.1709,
|
||
|
|
"mean_token_accuracy": 0.11596085354685784,
|
||
|
|
"num_tokens": 3301983.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.412484455108642,
|
||
|
|
"epoch": 0.12550926534367196,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 7.3552,
|
||
|
|
"mean_token_accuracy": 0.10020338520407676,
|
||
|
|
"num_tokens": 3320075.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.315499114990234,
|
||
|
|
"epoch": 0.12616638191615193,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 7.291,
|
||
|
|
"mean_token_accuracy": 0.09955885633826256,
|
||
|
|
"num_tokens": 3337782.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.315990972518921,
|
||
|
|
"epoch": 0.1268234984886319,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 7.3124,
|
||
|
|
"mean_token_accuracy": 0.09781972020864486,
|
||
|
|
"num_tokens": 3355114.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.252899885177612,
|
||
|
|
"epoch": 0.12748061506111183,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 7.1967,
|
||
|
|
"mean_token_accuracy": 0.10971798375248909,
|
||
|
|
"num_tokens": 3372664.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.372587108612061,
|
||
|
|
"epoch": 0.1281377316335918,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 7.2742,
|
||
|
|
"mean_token_accuracy": 0.10190480425953866,
|
||
|
|
"num_tokens": 3389687.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.19590539932251,
|
||
|
|
"epoch": 0.12879484820607176,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 7.2387,
|
||
|
|
"mean_token_accuracy": 0.10876442939043045,
|
||
|
|
"num_tokens": 3406613.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.346618175506592,
|
||
|
|
"epoch": 0.12945196477855173,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 7.4155,
|
||
|
|
"mean_token_accuracy": 0.09423026889562607,
|
||
|
|
"num_tokens": 3425530.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.372848224639893,
|
||
|
|
"epoch": 0.13010908135103166,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 7.3894,
|
||
|
|
"mean_token_accuracy": 0.09545382708311081,
|
||
|
|
"num_tokens": 3442988.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.38320107460022,
|
||
|
|
"epoch": 0.13076619792351163,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 7.3628,
|
||
|
|
"mean_token_accuracy": 0.09607246294617652,
|
||
|
|
"num_tokens": 3460763.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.417674016952515,
|
||
|
|
"epoch": 0.1314233144959916,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 7.3943,
|
||
|
|
"mean_token_accuracy": 0.09602649509906769,
|
||
|
|
"num_tokens": 3479425.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.343002462387085,
|
||
|
|
"epoch": 0.13208043106847156,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.000499998026082006,
|
||
|
|
"loss": 7.3564,
|
||
|
|
"mean_token_accuracy": 0.09569800049066543,
|
||
|
|
"num_tokens": 3497403.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.324274969100952,
|
||
|
|
"epoch": 0.1327375476409515,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004999900070995136,
|
||
|
|
"loss": 7.2737,
|
||
|
|
"mean_token_accuracy": 0.09939010664820672,
|
||
|
|
"num_tokens": 3514376.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.334035348892212,
|
||
|
|
"epoch": 0.13339466421343146,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004999758199023239,
|
||
|
|
"loss": 7.2586,
|
||
|
|
"mean_token_accuracy": 0.10601741299033166,
|
||
|
|
"num_tokens": 3532288.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.304716682434082,
|
||
|
|
"epoch": 0.13405178078591143,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004999554648793858,
|
||
|
|
"loss": 7.3554,
|
||
|
|
"mean_token_accuracy": 0.09575305506587029,
|
||
|
|
"num_tokens": 3549354.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.30626745223999,
|
||
|
|
"epoch": 0.13470889735839137,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.0004999289425887425,
|
||
|
|
"loss": 7.3139,
|
||
|
|
"mean_token_accuracy": 0.09804008454084397,
|
||
|
|
"num_tokens": 3569161.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.337455797195434,
|
||
|
|
"epoch": 0.13536601393087133,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004998962537575161,
|
||
|
|
"loss": 7.385,
|
||
|
|
"mean_token_accuracy": 0.09783728495240211,
|
||
|
|
"num_tokens": 3586165.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.395480298995972,
|
||
|
|
"epoch": 0.1360231305033513,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004998573992818874,
|
||
|
|
"loss": 7.3912,
|
||
|
|
"mean_token_accuracy": 0.09173386469483376,
|
||
|
|
"num_tokens": 3604938.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.343952703475952,
|
||
|
|
"epoch": 0.13668024707583126,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0004998123802270715,
|
||
|
|
"loss": 7.3583,
|
||
|
|
"mean_token_accuracy": 0.09979218170046807,
|
||
|
|
"num_tokens": 3621850.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.169143867492676,
|
||
|
|
"epoch": 0.1373373636483112,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004997611978272886,
|
||
|
|
"loss": 7.1837,
|
||
|
|
"mean_token_accuracy": 0.10983845517039299,
|
||
|
|
"num_tokens": 3641860.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.344118547439575,
|
||
|
|
"epoch": 0.13799448022079117,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997038534857298,
|
||
|
|
"loss": 7.2699,
|
||
|
|
"mean_token_accuracy": 0.09669720306992531,
|
||
|
|
"num_tokens": 3659086.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.209481334686279,
|
||
|
|
"epoch": 0.13865159679327113,
|
||
|
|
"grad_norm": 0.77734375,
|
||
|
|
"learning_rate": 0.0004996403487745194,
|
||
|
|
"loss": 7.3641,
|
||
|
|
"mean_token_accuracy": 0.09310299232602119,
|
||
|
|
"num_tokens": 3676971.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.406137371063233,
|
||
|
|
"epoch": 0.1393087133657511,
|
||
|
|
"grad_norm": 0.78515625,
|
||
|
|
"learning_rate": 0.000499570685434671,
|
||
|
|
"loss": 7.2983,
|
||
|
|
"mean_token_accuracy": 0.09514517113566398,
|
||
|
|
"num_tokens": 3696163.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.265346097946167,
|
||
|
|
"epoch": 0.13996582993823103,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004994948653760405,
|
||
|
|
"loss": 7.3231,
|
||
|
|
"mean_token_accuracy": 0.09595919102430343,
|
||
|
|
"num_tokens": 3713140.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.286369800567627,
|
||
|
|
"epoch": 0.140622946510711,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004994128906772729,
|
||
|
|
"loss": 7.2661,
|
||
|
|
"mean_token_accuracy": 0.09544462934136391,
|
||
|
|
"num_tokens": 3730600.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2847730159759525,
|
||
|
|
"epoch": 0.14128006308319097,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000499324763585746,
|
||
|
|
"loss": 7.3234,
|
||
|
|
"mean_token_accuracy": 0.10120683461427689,
|
||
|
|
"num_tokens": 3747866.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.184893703460693,
|
||
|
|
"epoch": 0.1419371796556709,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004992304865175085,
|
||
|
|
"loss": 7.1738,
|
||
|
|
"mean_token_accuracy": 0.11132644340395928,
|
||
|
|
"num_tokens": 3765444.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.333232975006103,
|
||
|
|
"epoch": 0.14259429622815087,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004991300620572138,
|
||
|
|
"loss": 7.3202,
|
||
|
|
"mean_token_accuracy": 0.09391410201787949,
|
||
|
|
"num_tokens": 3781970.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.304718732833862,
|
||
|
|
"epoch": 0.14325141280063083,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004990234929580494,
|
||
|
|
"loss": 7.2165,
|
||
|
|
"mean_token_accuracy": 0.10574242919683456,
|
||
|
|
"num_tokens": 3799884.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2470235347747805,
|
||
|
|
"epoch": 0.1439085293731108,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004989107821416609,
|
||
|
|
"loss": 7.261,
|
||
|
|
"mean_token_accuracy": 0.09376102611422539,
|
||
|
|
"num_tokens": 3816300.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.350685548782349,
|
||
|
|
"epoch": 0.14456564594559074,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.0004987919326980723,
|
||
|
|
"loss": 7.3215,
|
||
|
|
"mean_token_accuracy": 0.09178780242800713,
|
||
|
|
"num_tokens": 3835268.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.30710916519165,
|
||
|
|
"epoch": 0.1452227625180707,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004986669478856011,
|
||
|
|
"loss": 7.2716,
|
||
|
|
"mean_token_accuracy": 0.10289521887898445,
|
||
|
|
"num_tokens": 3852209.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.262703132629395,
|
||
|
|
"epoch": 0.14587987909055067,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004985358311307688,
|
||
|
|
"loss": 7.298,
|
||
|
|
"mean_token_accuracy": 0.09492710009217262,
|
||
|
|
"num_tokens": 3869024.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.169306993484497,
|
||
|
|
"epoch": 0.14653699566303063,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004983985860282081,
|
||
|
|
"loss": 7.1996,
|
||
|
|
"mean_token_accuracy": 0.1061355285346508,
|
||
|
|
"num_tokens": 3886897.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.180309152603149,
|
||
|
|
"epoch": 0.14719411223551057,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004982552163405623,
|
||
|
|
"loss": 7.1839,
|
||
|
|
"mean_token_accuracy": 0.10160853713750839,
|
||
|
|
"num_tokens": 3904397.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.284969186782837,
|
||
|
|
"epoch": 0.14785122880799054,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004981057259983839,
|
||
|
|
"loss": 7.2364,
|
||
|
|
"mean_token_accuracy": 0.09974497929215431,
|
||
|
|
"num_tokens": 3921792.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.175367546081543,
|
||
|
|
"epoch": 0.1485083453804705,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004979501191000262,
|
||
|
|
"loss": 7.1779,
|
||
|
|
"mean_token_accuracy": 0.10670020878314972,
|
||
|
|
"num_tokens": 3939896.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.243035173416137,
|
||
|
|
"epoch": 0.14916546195295044,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004977883999115311,
|
||
|
|
"loss": 7.2189,
|
||
|
|
"mean_token_accuracy": 0.09671530574560165,
|
||
|
|
"num_tokens": 3958019.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.291995239257813,
|
||
|
|
"epoch": 0.1498225785254304,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004976205728665113,
|
||
|
|
"loss": 7.3026,
|
||
|
|
"mean_token_accuracy": 0.1016198918223381,
|
||
|
|
"num_tokens": 3975880.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.189220190048218,
|
||
|
|
"epoch": 0.15047969509791037,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004974466425660307,
|
||
|
|
"loss": 7.1553,
|
||
|
|
"mean_token_accuracy": 0.10134812369942665,
|
||
|
|
"num_tokens": 3992649.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.181387281417846,
|
||
|
|
"epoch": 0.15113681167039034,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004972666137784759,
|
||
|
|
"loss": 7.1851,
|
||
|
|
"mean_token_accuracy": 0.10243008136749268,
|
||
|
|
"num_tokens": 4009641.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.194750642776489,
|
||
|
|
"epoch": 0.15179392824287027,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004970804914394271,
|
||
|
|
"loss": 7.2668,
|
||
|
|
"mean_token_accuracy": 0.09644793346524239,
|
||
|
|
"num_tokens": 4028324.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.255599069595337,
|
||
|
|
"epoch": 0.15245104481535024,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004968882806515225,
|
||
|
|
"loss": 7.2032,
|
||
|
|
"mean_token_accuracy": 0.10386807322502137,
|
||
|
|
"num_tokens": 4046547.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.242625427246094,
|
||
|
|
"epoch": 0.1531081613878302,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004966899866843177,
|
||
|
|
"loss": 7.2258,
|
||
|
|
"mean_token_accuracy": 0.1007157877087593,
|
||
|
|
"num_tokens": 4062227.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.163462209701538,
|
||
|
|
"epoch": 0.15376527796031017,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000496485614974142,
|
||
|
|
"loss": 7.1801,
|
||
|
|
"mean_token_accuracy": 0.10540101230144501,
|
||
|
|
"num_tokens": 4079046.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.251097249984741,
|
||
|
|
"epoch": 0.1544223945327901,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004962751711239492,
|
||
|
|
"loss": 7.244,
|
||
|
|
"mean_token_accuracy": 0.10471903905272484,
|
||
|
|
"num_tokens": 4096559.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.216784477233887,
|
||
|
|
"epoch": 0.15507951110527007,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004960586609031636,
|
||
|
|
"loss": 7.1556,
|
||
|
|
"mean_token_accuracy": 0.10767733827233314,
|
||
|
|
"num_tokens": 4113251.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.065131950378418,
|
||
|
|
"epoch": 0.15573662767775004,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004958360902475224,
|
||
|
|
"loss": 7.0617,
|
||
|
|
"mean_token_accuracy": 0.11634833589196206,
|
||
|
|
"num_tokens": 4133967.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.220524168014526,
|
||
|
|
"epoch": 0.15639374425023,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0004956074652589125,
|
||
|
|
"loss": 7.1619,
|
||
|
|
"mean_token_accuracy": 0.1012740470468998,
|
||
|
|
"num_tokens": 4150801.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.286528825759888,
|
||
|
|
"epoch": 0.15705086082270994,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.0004953727922052035,
|
||
|
|
"loss": 7.2604,
|
||
|
|
"mean_token_accuracy": 0.0940374843776226,
|
||
|
|
"num_tokens": 4168727.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.180148553848267,
|
||
|
|
"epoch": 0.1577079773951899,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004951320775200756,
|
||
|
|
"loss": 7.1508,
|
||
|
|
"mean_token_accuracy": 0.10601523295044898,
|
||
|
|
"num_tokens": 4187639.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.135108709335327,
|
||
|
|
"epoch": 0.15836509396766987,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.0004948853278028436,
|
||
|
|
"loss": 7.1612,
|
||
|
|
"mean_token_accuracy": 0.10450763776898384,
|
||
|
|
"num_tokens": 4204266.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2624317646026615,
|
||
|
|
"epoch": 0.1590222105401498,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004946325498182755,
|
||
|
|
"loss": 7.1404,
|
||
|
|
"mean_token_accuracy": 0.10236875712871552,
|
||
|
|
"num_tokens": 4221724.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.164175224304199,
|
||
|
|
"epoch": 0.15967932711262978,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0004943737504964076,
|
||
|
|
"loss": 7.2273,
|
||
|
|
"mean_token_accuracy": 0.10266198962926865,
|
||
|
|
"num_tokens": 4240729.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.121058464050293,
|
||
|
|
"epoch": 0.16033644368510974,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000494108936932354,
|
||
|
|
"loss": 7.1063,
|
||
|
|
"mean_token_accuracy": 0.11425342187285423,
|
||
|
|
"num_tokens": 4260604.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.142035484313965,
|
||
|
|
"epoch": 0.1609935602575897,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.0004938381163861124,
|
||
|
|
"loss": 7.1992,
|
||
|
|
"mean_token_accuracy": 0.10155246257781983,
|
||
|
|
"num_tokens": 4277763.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.209809589385986,
|
||
|
|
"epoch": 0.16165067683006965,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004935612962823645,
|
||
|
|
"loss": 7.2427,
|
||
|
|
"mean_token_accuracy": 0.09955391138792039,
|
||
|
|
"num_tokens": 4294625.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.154326152801514,
|
||
|
|
"epoch": 0.1623077934025496,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0004932784842102739,
|
||
|
|
"loss": 7.1676,
|
||
|
|
"mean_token_accuracy": 0.10906312316656112,
|
||
|
|
"num_tokens": 4312247.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.254214096069336,
|
||
|
|
"epoch": 0.16296490997502958,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0004929896879232758,
|
||
|
|
"loss": 7.2685,
|
||
|
|
"mean_token_accuracy": 0.09215258359909058,
|
||
|
|
"num_tokens": 4329618.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.223868036270142,
|
||
|
|
"epoch": 0.16362202654750954,
|
||
|
|
"grad_norm": 0.77734375,
|
||
|
|
"learning_rate": 0.0004926949153388668,
|
||
|
|
"loss": 7.2086,
|
||
|
|
"mean_token_accuracy": 0.1000858373939991,
|
||
|
|
"num_tokens": 4347702.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.246126794815064,
|
||
|
|
"epoch": 0.16427914311998948,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004923941745383859,
|
||
|
|
"loss": 7.1858,
|
||
|
|
"mean_token_accuracy": 0.09782344475388527,
|
||
|
|
"num_tokens": 4365116.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.171083784103393,
|
||
|
|
"epoch": 0.16493625969246944,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.000492087473766794,
|
||
|
|
"loss": 7.2512,
|
||
|
|
"mean_token_accuracy": 0.10115259513258934,
|
||
|
|
"num_tokens": 4382634.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.264097499847412,
|
||
|
|
"epoch": 0.1655933762649494,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000491774821432448,
|
||
|
|
"loss": 7.2555,
|
||
|
|
"mean_token_accuracy": 0.09854963570833206,
|
||
|
|
"num_tokens": 4400067.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.18475866317749,
|
||
|
|
"epoch": 0.16625049283742935,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004914562261068693,
|
||
|
|
"loss": 7.1363,
|
||
|
|
"mean_token_accuracy": 0.0983266532421112,
|
||
|
|
"num_tokens": 4415974.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.142167472839356,
|
||
|
|
"epoch": 0.1669076094099093,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004911316965245098,
|
||
|
|
"loss": 7.1565,
|
||
|
|
"mean_token_accuracy": 0.10286837294697762,
|
||
|
|
"num_tokens": 4433718.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.263294696807861,
|
||
|
|
"epoch": 0.16756472598238928,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.000490801241582512,
|
||
|
|
"loss": 7.2295,
|
||
|
|
"mean_token_accuracy": 0.09759362787008286,
|
||
|
|
"num_tokens": 4452327.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.116361236572265,
|
||
|
|
"epoch": 0.16822184255486924,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000490464870340465,
|
||
|
|
"loss": 7.112,
|
||
|
|
"mean_token_accuracy": 0.10486611649394036,
|
||
|
|
"num_tokens": 4468025.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.023391008377075,
|
||
|
|
"epoch": 0.16887895912734918,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004901225920201563,
|
||
|
|
"loss": 6.9262,
|
||
|
|
"mean_token_accuracy": 0.12515356317162513,
|
||
|
|
"num_tokens": 4486104.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.159882354736328,
|
||
|
|
"epoch": 0.16953607569982915,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.000489774416005319,
|
||
|
|
"loss": 7.2428,
|
||
|
|
"mean_token_accuracy": 0.09691546708345414,
|
||
|
|
"num_tokens": 4503776.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.169772386550903,
|
||
|
|
"epoch": 0.1701931922723091,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004894203518413742,
|
||
|
|
"loss": 7.2116,
|
||
|
|
"mean_token_accuracy": 0.1008364237844944,
|
||
|
|
"num_tokens": 4521574.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2007242202758786,
|
||
|
|
"epoch": 0.17085030884478908,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004890604092351701,
|
||
|
|
"loss": 7.1505,
|
||
|
|
"mean_token_accuracy": 0.11244964003562927,
|
||
|
|
"num_tokens": 4539276.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.171060848236084,
|
||
|
|
"epoch": 0.17150742541726902,
|
||
|
|
"grad_norm": 0.7265625,
|
||
|
|
"learning_rate": 0.000488694598054715,
|
||
|
|
"loss": 7.1326,
|
||
|
|
"mean_token_accuracy": 0.1008635438978672,
|
||
|
|
"num_tokens": 4557626.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.142626094818115,
|
||
|
|
"epoch": 0.17216454198974898,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004883229283289071,
|
||
|
|
"loss": 7.1549,
|
||
|
|
"mean_token_accuracy": 0.10123615637421608,
|
||
|
|
"num_tokens": 4574045.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.167723512649536,
|
||
|
|
"epoch": 0.17282165856222895,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.00048794541024725993,
|
||
|
|
"loss": 7.1759,
|
||
|
|
"mean_token_accuracy": 0.10515163168311119,
|
||
|
|
"num_tokens": 4590743.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.111159324645996,
|
||
|
|
"epoch": 0.17347877513470888,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.0004875620541596221,
|
||
|
|
"loss": 7.0989,
|
||
|
|
"mean_token_accuracy": 0.10333124399185181,
|
||
|
|
"num_tokens": 4607616.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.161529684066773,
|
||
|
|
"epoch": 0.17413589170718885,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00048717287057589454,
|
||
|
|
"loss": 7.0922,
|
||
|
|
"mean_token_accuracy": 0.10455577373504639,
|
||
|
|
"num_tokens": 4624723.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1527036190032955,
|
||
|
|
"epoch": 0.17479300827966882,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004867778701657417,
|
||
|
|
"loss": 7.1299,
|
||
|
|
"mean_token_accuracy": 0.09841537550091743,
|
||
|
|
"num_tokens": 4642535.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.17755012512207,
|
||
|
|
"epoch": 0.17545012485214878,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.00048637706375829955,
|
||
|
|
"loss": 7.1287,
|
||
|
|
"mean_token_accuracy": 0.09741237014532089,
|
||
|
|
"num_tokens": 4660068.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.029680061340332,
|
||
|
|
"epoch": 0.17610724142462872,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.000485970462341878,
|
||
|
|
"loss": 7.0628,
|
||
|
|
"mean_token_accuracy": 0.11555436253547668,
|
||
|
|
"num_tokens": 4678985.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.155279445648193,
|
||
|
|
"epoch": 0.17676435799710868,
|
||
|
|
"grad_norm": 0.77734375,
|
||
|
|
"learning_rate": 0.00048555807706366044,
|
||
|
|
"loss": 7.1287,
|
||
|
|
"mean_token_accuracy": 0.09945940226316452,
|
||
|
|
"num_tokens": 4697827.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.107897138595581,
|
||
|
|
"epoch": 0.17742147456958865,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.00048513991922939756,
|
||
|
|
"loss": 7.1291,
|
||
|
|
"mean_token_accuracy": 0.09734978899359703,
|
||
|
|
"num_tokens": 4716437.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.036555910110474,
|
||
|
|
"epoch": 0.17807859114206862,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00048471600030309744,
|
||
|
|
"loss": 7.0523,
|
||
|
|
"mean_token_accuracy": 0.10956270396709442,
|
||
|
|
"num_tokens": 4734528.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1375220775604244,
|
||
|
|
"epoch": 0.17873570771454855,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00048428633190671186,
|
||
|
|
"loss": 7.1495,
|
||
|
|
"mean_token_accuracy": 0.09941326081752777,
|
||
|
|
"num_tokens": 4752174.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.162973308563233,
|
||
|
|
"epoch": 0.17939282428702852,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004838509258198167,
|
||
|
|
"loss": 7.0365,
|
||
|
|
"mean_token_accuracy": 0.10331410691142082,
|
||
|
|
"num_tokens": 4769040.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.036287784576416,
|
||
|
|
"epoch": 0.18004994085950848,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.00048340979397929,
|
||
|
|
"loss": 7.1211,
|
||
|
|
"mean_token_accuracy": 0.10569187849760056,
|
||
|
|
"num_tokens": 4787769.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.198102760314941,
|
||
|
|
"epoch": 0.18070705743198842,
|
||
|
|
"grad_norm": 0.76953125,
|
||
|
|
"learning_rate": 0.00048296294847898386,
|
||
|
|
"loss": 7.1446,
|
||
|
|
"mean_token_accuracy": 0.09686194062232971,
|
||
|
|
"num_tokens": 4805730.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.123643064498902,
|
||
|
|
"epoch": 0.1813641740044684,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.0004825104015693934,
|
||
|
|
"loss": 7.1348,
|
||
|
|
"mean_token_accuracy": 0.10434755310416222,
|
||
|
|
"num_tokens": 4823518.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.153635454177857,
|
||
|
|
"epoch": 0.18202129057694835,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004820521656573208,
|
||
|
|
"loss": 7.1404,
|
||
|
|
"mean_token_accuracy": 0.10507838502526283,
|
||
|
|
"num_tokens": 4840332.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.123753452301026,
|
||
|
|
"epoch": 0.18267840714942832,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00048158825330553505,
|
||
|
|
"loss": 7.1231,
|
||
|
|
"mean_token_accuracy": 0.09961956813931465,
|
||
|
|
"num_tokens": 4857633.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.068319320678711,
|
||
|
|
"epoch": 0.18333552372190826,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00048111867723242763,
|
||
|
|
"loss": 7.0578,
|
||
|
|
"mean_token_accuracy": 0.10383191257715225,
|
||
|
|
"num_tokens": 4874145.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.05531587600708,
|
||
|
|
"epoch": 0.18399264029438822,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004806434503116637,
|
||
|
|
"loss": 6.9817,
|
||
|
|
"mean_token_accuracy": 0.10680583864450455,
|
||
|
|
"num_tokens": 4892231.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.049816274642945,
|
||
|
|
"epoch": 0.1846497568668682,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004801625855718296,
|
||
|
|
"loss": 7.1012,
|
||
|
|
"mean_token_accuracy": 0.10223743543028832,
|
||
|
|
"num_tokens": 4908095.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0817399501800535,
|
||
|
|
"epoch": 0.18530687343934815,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00047967609619607477,
|
||
|
|
"loss": 6.9911,
|
||
|
|
"mean_token_accuracy": 0.11124311462044716,
|
||
|
|
"num_tokens": 4926608.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9987890243530275,
|
||
|
|
"epoch": 0.1859639900118281,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004791839955217513,
|
||
|
|
"loss": 6.9371,
|
||
|
|
"mean_token_accuracy": 0.11885873302817344,
|
||
|
|
"num_tokens": 4943617.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.06851634979248,
|
||
|
|
"epoch": 0.18662110658430806,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00047868629704004786,
|
||
|
|
"loss": 7.0327,
|
||
|
|
"mean_token_accuracy": 0.1135017842054367,
|
||
|
|
"num_tokens": 4962255.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.001637077331543,
|
||
|
|
"epoch": 0.18727822315678802,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00047818301439561965,
|
||
|
|
"loss": 6.9265,
|
||
|
|
"mean_token_accuracy": 0.12256510108709336,
|
||
|
|
"num_tokens": 4980276.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.053653526306152,
|
||
|
|
"epoch": 0.18793533972926796,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00047767416138621454,
|
||
|
|
"loss": 7.0544,
|
||
|
|
"mean_token_accuracy": 0.10385716408491134,
|
||
|
|
"num_tokens": 4996244.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.084101438522339,
|
||
|
|
"epoch": 0.18859245630174792,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000477159751962295,
|
||
|
|
"loss": 7.0743,
|
||
|
|
"mean_token_accuracy": 0.1009013146162033,
|
||
|
|
"num_tokens": 5016070.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.109147834777832,
|
||
|
|
"epoch": 0.1892495728742279,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00047663980022665507,
|
||
|
|
"loss": 7.138,
|
||
|
|
"mean_token_accuracy": 0.0944010891020298,
|
||
|
|
"num_tokens": 5032302.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.157390308380127,
|
||
|
|
"epoch": 0.18990668944670785,
|
||
|
|
"grad_norm": 0.7421875,
|
||
|
|
"learning_rate": 0.00047611432043403437,
|
||
|
|
"loss": 7.0823,
|
||
|
|
"mean_token_accuracy": 0.10348261818289757,
|
||
|
|
"num_tokens": 5050474.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.962280035018921,
|
||
|
|
"epoch": 0.1905638060191878,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004755833269907267,
|
||
|
|
"loss": 7.0122,
|
||
|
|
"mean_token_accuracy": 0.10257056131958961,
|
||
|
|
"num_tokens": 5069626.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.163888025283813,
|
||
|
|
"epoch": 0.19122092259166776,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004750468344541857,
|
||
|
|
"loss": 7.1151,
|
||
|
|
"mean_token_accuracy": 0.0981297992169857,
|
||
|
|
"num_tokens": 5087126.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0553618431091305,
|
||
|
|
"epoch": 0.19187803916414772,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00047450485753262525,
|
||
|
|
"loss": 7.0958,
|
||
|
|
"mean_token_accuracy": 0.10250502526760101,
|
||
|
|
"num_tokens": 5105324.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1029359817504885,
|
||
|
|
"epoch": 0.1925351557366277,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00047395741108461633,
|
||
|
|
"loss": 7.1372,
|
||
|
|
"mean_token_accuracy": 0.1008988417685032,
|
||
|
|
"num_tokens": 5121832.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.041136693954468,
|
||
|
|
"epoch": 0.19319227230910763,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00047340451011867985,
|
||
|
|
"loss": 7.0571,
|
||
|
|
"mean_token_accuracy": 0.1045589379966259,
|
||
|
|
"num_tokens": 5138072.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.143003797531128,
|
||
|
|
"epoch": 0.1938493888815876,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.00047284616979287515,
|
||
|
|
"loss": 7.0829,
|
||
|
|
"mean_token_accuracy": 0.10569359660148621,
|
||
|
|
"num_tokens": 5154486.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.041785955429077,
|
||
|
|
"epoch": 0.19450650545406756,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00047228240541438433,
|
||
|
|
"loss": 7.0603,
|
||
|
|
"mean_token_accuracy": 0.10345918461680412,
|
||
|
|
"num_tokens": 5171995.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.947126388549805,
|
||
|
|
"epoch": 0.19516362202654752,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00047171323243909257,
|
||
|
|
"loss": 6.8975,
|
||
|
|
"mean_token_accuracy": 0.12085305452346802,
|
||
|
|
"num_tokens": 5190708.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.049253225326538,
|
||
|
|
"epoch": 0.19582073859902746,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.00047113866647116457,
|
||
|
|
"loss": 7.0137,
|
||
|
|
"mean_token_accuracy": 0.10840069875121117,
|
||
|
|
"num_tokens": 5207518.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.979583120346069,
|
||
|
|
"epoch": 0.19647785517150743,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004705587232626164,
|
||
|
|
"loss": 6.9889,
|
||
|
|
"mean_token_accuracy": 0.11757338047027588,
|
||
|
|
"num_tokens": 5225043.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.06225094795227,
|
||
|
|
"epoch": 0.1971349717439874,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.00046997341871288424,
|
||
|
|
"loss": 7.0219,
|
||
|
|
"mean_token_accuracy": 0.1079759307205677,
|
||
|
|
"num_tokens": 5242101.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.980389213562011,
|
||
|
|
"epoch": 0.19779208831646733,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004693827688683879,
|
||
|
|
"loss": 7.0307,
|
||
|
|
"mean_token_accuracy": 0.1121443621814251,
|
||
|
|
"num_tokens": 5261058.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.928413343429566,
|
||
|
|
"epoch": 0.1984492048889473,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004687867899220914,
|
||
|
|
"loss": 6.8492,
|
||
|
|
"mean_token_accuracy": 0.11927449703216553,
|
||
|
|
"num_tokens": 5278685.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0457886219024655,
|
||
|
|
"epoch": 0.19910632146142726,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00046818549821305846,
|
||
|
|
"loss": 7.0144,
|
||
|
|
"mean_token_accuracy": 0.1097822904586792,
|
||
|
|
"num_tokens": 5298594.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.00173716545105,
|
||
|
|
"epoch": 0.19976343803390723,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00046757891022600494,
|
||
|
|
"loss": 6.9281,
|
||
|
|
"mean_token_accuracy": 0.11321399658918381,
|
||
|
|
"num_tokens": 5317038.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.989265775680542,
|
||
|
|
"epoch": 0.20042055460638716,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004669670425908471,
|
||
|
|
"loss": 6.9594,
|
||
|
|
"mean_token_accuracy": 0.10878673940896988,
|
||
|
|
"num_tokens": 5333928.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.080010271072387,
|
||
|
|
"epoch": 0.20107767117886713,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004663499120822451,
|
||
|
|
"loss": 7.0495,
|
||
|
|
"mean_token_accuracy": 0.1020596168935299,
|
||
|
|
"num_tokens": 5350680.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1021839618682865,
|
||
|
|
"epoch": 0.2017347877513471,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004657275356191437,
|
||
|
|
"loss": 7.0213,
|
||
|
|
"mean_token_accuracy": 0.10890387147665023,
|
||
|
|
"num_tokens": 5367528.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0397826671600345,
|
||
|
|
"epoch": 0.20239190432382706,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.00046509993026430804,
|
||
|
|
"loss": 7.0363,
|
||
|
|
"mean_token_accuracy": 0.1016130954027176,
|
||
|
|
"num_tokens": 5383623.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.036032199859619,
|
||
|
|
"epoch": 0.203049020896307,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004644671132238558,
|
||
|
|
"loss": 7.0656,
|
||
|
|
"mean_token_accuracy": 0.10182826668024063,
|
||
|
|
"num_tokens": 5402596.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.990324640274048,
|
||
|
|
"epoch": 0.20370613746878696,
|
||
|
|
"grad_norm": 1.921875,
|
||
|
|
"learning_rate": 0.00046382910184678585,
|
||
|
|
"loss": 6.9334,
|
||
|
|
"mean_token_accuracy": 0.10728395134210586,
|
||
|
|
"num_tokens": 5419537.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.014930868148804,
|
||
|
|
"epoch": 0.20436325404126693,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.0004631859136245025,
|
||
|
|
"loss": 6.9174,
|
||
|
|
"mean_token_accuracy": 0.11006099134683608,
|
||
|
|
"num_tokens": 5436665.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.056590366363525,
|
||
|
|
"epoch": 0.20502037061374687,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.0004625375661903357,
|
||
|
|
"loss": 7.0661,
|
||
|
|
"mean_token_accuracy": 0.10458005070686341,
|
||
|
|
"num_tokens": 5453591.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9895727157592775,
|
||
|
|
"epoch": 0.20567748718622683,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00046188407731905787,
|
||
|
|
"loss": 6.942,
|
||
|
|
"mean_token_accuracy": 0.10817160606384277,
|
||
|
|
"num_tokens": 5470608.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.020028781890869,
|
||
|
|
"epoch": 0.2063346037587068,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.00046122546492639643,
|
||
|
|
"loss": 6.9833,
|
||
|
|
"mean_token_accuracy": 0.10391393676400185,
|
||
|
|
"num_tokens": 5488079.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.095751142501831,
|
||
|
|
"epoch": 0.20699172033118676,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.000460561747068543,
|
||
|
|
"loss": 7.0906,
|
||
|
|
"mean_token_accuracy": 0.10024550259113311,
|
||
|
|
"num_tokens": 5505682.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.929014778137207,
|
||
|
|
"epoch": 0.2076488369036667,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004598929419416578,
|
||
|
|
"loss": 6.9313,
|
||
|
|
"mean_token_accuracy": 0.10721118450164795,
|
||
|
|
"num_tokens": 5523202.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.037165927886963,
|
||
|
|
"epoch": 0.20830595347614667,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00045921906788137123,
|
||
|
|
"loss": 7.0807,
|
||
|
|
"mean_token_accuracy": 0.09975322857499122,
|
||
|
|
"num_tokens": 5540713.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.077455234527588,
|
||
|
|
"epoch": 0.20896307004862663,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00045854014336228115,
|
||
|
|
"loss": 7.048,
|
||
|
|
"mean_token_accuracy": 0.10766374170780182,
|
||
|
|
"num_tokens": 5558940.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.002238464355469,
|
||
|
|
"epoch": 0.2096201866211066,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.00045785618699744615,
|
||
|
|
"loss": 7.0195,
|
||
|
|
"mean_token_accuracy": 0.10779799818992615,
|
||
|
|
"num_tokens": 5577067.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.075734376907349,
|
||
|
|
"epoch": 0.21027730319358653,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.00045716721753787543,
|
||
|
|
"loss": 7.077,
|
||
|
|
"mean_token_accuracy": 0.10019223764538765,
|
||
|
|
"num_tokens": 5595177.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.095106887817383,
|
||
|
|
"epoch": 0.2109344197660665,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004564732538720148,
|
||
|
|
"loss": 7.0188,
|
||
|
|
"mean_token_accuracy": 0.10090450495481491,
|
||
|
|
"num_tokens": 5612144.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.027229070663452,
|
||
|
|
"epoch": 0.21159153633854647,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.00045577431502522877,
|
||
|
|
"loss": 6.9472,
|
||
|
|
"mean_token_accuracy": 0.10145832747220992,
|
||
|
|
"num_tokens": 5628601.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.96478271484375,
|
||
|
|
"epoch": 0.2122486529110264,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.0004550704201592787,
|
||
|
|
"loss": 6.9378,
|
||
|
|
"mean_token_accuracy": 0.10733082517981529,
|
||
|
|
"num_tokens": 5645050.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.011602449417114,
|
||
|
|
"epoch": 0.21290576948350637,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004543615885717981,
|
||
|
|
"loss": 7.0022,
|
||
|
|
"mean_token_accuracy": 0.11281452551484109,
|
||
|
|
"num_tokens": 5664190.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9639692306518555,
|
||
|
|
"epoch": 0.21356288605598633,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.00045364783969576296,
|
||
|
|
"loss": 7.0047,
|
||
|
|
"mean_token_accuracy": 0.10859131515026092,
|
||
|
|
"num_tokens": 5682983.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.943532133102417,
|
||
|
|
"epoch": 0.2142200026284663,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004529291930989592,
|
||
|
|
"loss": 6.9701,
|
||
|
|
"mean_token_accuracy": 0.10892121568322181,
|
||
|
|
"num_tokens": 5700462.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.088738346099854,
|
||
|
|
"epoch": 0.21487711920094624,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004522056684834464,
|
||
|
|
"loss": 7.0709,
|
||
|
|
"mean_token_accuracy": 0.10152970477938653,
|
||
|
|
"num_tokens": 5718311.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.980139350891113,
|
||
|
|
"epoch": 0.2155342357734262,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004514772856850173,
|
||
|
|
"loss": 6.919,
|
||
|
|
"mean_token_accuracy": 0.10068962797522545,
|
||
|
|
"num_tokens": 5735389.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.037415838241577,
|
||
|
|
"epoch": 0.21619135234590617,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004507440646726542,
|
||
|
|
"loss": 6.9574,
|
||
|
|
"mean_token_accuracy": 0.10025965794920921,
|
||
|
|
"num_tokens": 5754541.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.005382633209228,
|
||
|
|
"epoch": 0.21684846891838613,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004500060255479818,
|
||
|
|
"loss": 6.9929,
|
||
|
|
"mean_token_accuracy": 0.10590369552373886,
|
||
|
|
"num_tokens": 5774108.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.070339202880859,
|
||
|
|
"epoch": 0.21750558549086607,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004492631885447151,
|
||
|
|
"loss": 7.0669,
|
||
|
|
"mean_token_accuracy": 0.10116325989365578,
|
||
|
|
"num_tokens": 5792141.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.040534925460816,
|
||
|
|
"epoch": 0.21816270206334604,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.00044851557402810616,
|
||
|
|
"loss": 7.0361,
|
||
|
|
"mean_token_accuracy": 0.10267394408583641,
|
||
|
|
"num_tokens": 5810231.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.075697517395019,
|
||
|
|
"epoch": 0.218819818635826,
|
||
|
|
"grad_norm": 0.75390625,
|
||
|
|
"learning_rate": 0.00044776320249438444,
|
||
|
|
"loss": 7.0877,
|
||
|
|
"mean_token_accuracy": 0.10073644891381264,
|
||
|
|
"num_tokens": 5830031.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.06813325881958,
|
||
|
|
"epoch": 0.21947693520830594,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.00044700609457019565,
|
||
|
|
"loss": 7.0843,
|
||
|
|
"mean_token_accuracy": 0.10116546377539634,
|
||
|
|
"num_tokens": 5847771.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.046045923233033,
|
||
|
|
"epoch": 0.2201340517807859,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004462442710120359,
|
||
|
|
"loss": 7.0446,
|
||
|
|
"mean_token_accuracy": 0.10245904475450515,
|
||
|
|
"num_tokens": 5865561.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.913028287887573,
|
||
|
|
"epoch": 0.22079116835326587,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.000445477752705683,
|
||
|
|
"loss": 6.819,
|
||
|
|
"mean_token_accuracy": 0.11582144349813461,
|
||
|
|
"num_tokens": 5882488.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.090687465667725,
|
||
|
|
"epoch": 0.22144828492574584,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.00044470656066562336,
|
||
|
|
"loss": 6.9301,
|
||
|
|
"mean_token_accuracy": 0.10762658789753914,
|
||
|
|
"num_tokens": 5899817.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.833544683456421,
|
||
|
|
"epoch": 0.22210540149822577,
|
||
|
|
"grad_norm": 0.74609375,
|
||
|
|
"learning_rate": 0.0004439307160344765,
|
||
|
|
"loss": 6.9259,
|
||
|
|
"mean_token_accuracy": 0.11043619364500046,
|
||
|
|
"num_tokens": 5918548.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.926533174514771,
|
||
|
|
"epoch": 0.22276251807070574,
|
||
|
|
"grad_norm": 0.76953125,
|
||
|
|
"learning_rate": 0.00044315024008241473,
|
||
|
|
"loss": 6.9144,
|
||
|
|
"mean_token_accuracy": 0.11134300157427787,
|
||
|
|
"num_tokens": 5936658.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.003788185119629,
|
||
|
|
"epoch": 0.2234196346431857,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0004423651542065806,
|
||
|
|
"loss": 6.9099,
|
||
|
|
"mean_token_accuracy": 0.10790434181690216,
|
||
|
|
"num_tokens": 5954030.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.985163927078247,
|
||
|
|
"epoch": 0.22407675121566567,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.00044157547993050006,
|
||
|
|
"loss": 6.9461,
|
||
|
|
"mean_token_accuracy": 0.10844582244753838,
|
||
|
|
"num_tokens": 5971653.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.990438222885132,
|
||
|
|
"epoch": 0.2247338677881456,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00044078123890349227,
|
||
|
|
"loss": 7.0011,
|
||
|
|
"mean_token_accuracy": 0.10525092333555222,
|
||
|
|
"num_tokens": 5988304.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.007080888748169,
|
||
|
|
"epoch": 0.22539098436062557,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.00043998245290007606,
|
||
|
|
"loss": 6.9833,
|
||
|
|
"mean_token_accuracy": 0.10128033682703971,
|
||
|
|
"num_tokens": 6005829.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.941484022140503,
|
||
|
|
"epoch": 0.22604810093310554,
|
||
|
|
"grad_norm": 0.73046875,
|
||
|
|
"learning_rate": 0.00043917914381937323,
|
||
|
|
"loss": 6.8804,
|
||
|
|
"mean_token_accuracy": 0.1191004104912281,
|
||
|
|
"num_tokens": 6023234.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.996621465682983,
|
||
|
|
"epoch": 0.2267052175055855,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.00043837133368450815,
|
||
|
|
"loss": 6.9741,
|
||
|
|
"mean_token_accuracy": 0.1071186564862728,
|
||
|
|
"num_tokens": 6040144.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.042966318130493,
|
||
|
|
"epoch": 0.22736233407806544,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004375590446420037,
|
||
|
|
"loss": 7.0195,
|
||
|
|
"mean_token_accuracy": 0.10108131021261216,
|
||
|
|
"num_tokens": 6057625.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.953941297531128,
|
||
|
|
"epoch": 0.2280194506505454,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004367422989611743,
|
||
|
|
"loss": 6.8515,
|
||
|
|
"mean_token_accuracy": 0.11290154606103897,
|
||
|
|
"num_tokens": 6075483.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.944326496124267,
|
||
|
|
"epoch": 0.22867656722302537,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004359211190335153,
|
||
|
|
"loss": 6.8926,
|
||
|
|
"mean_token_accuracy": 0.11690908074378967,
|
||
|
|
"num_tokens": 6092352.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.005725955963134,
|
||
|
|
"epoch": 0.2293336837955053,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.00043509552737208923,
|
||
|
|
"loss": 6.885,
|
||
|
|
"mean_token_accuracy": 0.11574849113821983,
|
||
|
|
"num_tokens": 6108736.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.915209627151489,
|
||
|
|
"epoch": 0.22999080036798528,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.00043426554661090853,
|
||
|
|
"loss": 6.9139,
|
||
|
|
"mean_token_accuracy": 0.11076030135154724,
|
||
|
|
"num_tokens": 6125868.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.907050514221192,
|
||
|
|
"epoch": 0.23064791694046524,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.00043343119950431516,
|
||
|
|
"loss": 6.9093,
|
||
|
|
"mean_token_accuracy": 0.11406089663505554,
|
||
|
|
"num_tokens": 6144025.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.021928930282593,
|
||
|
|
"epoch": 0.2313050335129452,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.00043259250892635644,
|
||
|
|
"loss": 6.9704,
|
||
|
|
"mean_token_accuracy": 0.10295196995139122,
|
||
|
|
"num_tokens": 6161480.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.966275024414062,
|
||
|
|
"epoch": 0.23196215008542515,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004317494978701582,
|
||
|
|
"loss": 6.9792,
|
||
|
|
"mean_token_accuracy": 0.10593046993017197,
|
||
|
|
"num_tokens": 6179338.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.905800151824951,
|
||
|
|
"epoch": 0.2326192666579051,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.0004309021894472943,
|
||
|
|
"loss": 6.8742,
|
||
|
|
"mean_token_accuracy": 0.11467983648180961,
|
||
|
|
"num_tokens": 6196155.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.969728231430054,
|
||
|
|
"epoch": 0.23327638323038508,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0004300506068871534,
|
||
|
|
"loss": 6.92,
|
||
|
|
"mean_token_accuracy": 0.10850797519087792,
|
||
|
|
"num_tokens": 6212858.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.941912984848022,
|
||
|
|
"epoch": 0.23393349980286504,
|
||
|
|
"grad_norm": 1.6640625,
|
||
|
|
"learning_rate": 0.00042919477353630135,
|
||
|
|
"loss": 6.8367,
|
||
|
|
"mean_token_accuracy": 0.12004422172904014,
|
||
|
|
"num_tokens": 6231087.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.927156257629394,
|
||
|
|
"epoch": 0.23459061637534498,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.000428334712857842,
|
||
|
|
"loss": 6.9231,
|
||
|
|
"mean_token_accuracy": 0.10870739594101905,
|
||
|
|
"num_tokens": 6248811.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8959753036499025,
|
||
|
|
"epoch": 0.23524773294782494,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.00042747044843077304,
|
||
|
|
"loss": 6.8527,
|
||
|
|
"mean_token_accuracy": 0.11063326448202133,
|
||
|
|
"num_tokens": 6266199.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.949681282043457,
|
||
|
|
"epoch": 0.2359048495203049,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.00042660200394934047,
|
||
|
|
"loss": 6.8779,
|
||
|
|
"mean_token_accuracy": 0.11012318357825279,
|
||
|
|
"num_tokens": 6284944.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9984886169433596,
|
||
|
|
"epoch": 0.23656196609278485,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.00042572940322238844,
|
||
|
|
"loss": 6.9852,
|
||
|
|
"mean_token_accuracy": 0.10194452628493308,
|
||
|
|
"num_tokens": 6302707.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9384533882141115,
|
||
|
|
"epoch": 0.2372190826652648,
|
||
|
|
"grad_norm": 0.74609375,
|
||
|
|
"learning_rate": 0.00042485267017270664,
|
||
|
|
"loss": 6.9687,
|
||
|
|
"mean_token_accuracy": 0.10376290306448936,
|
||
|
|
"num_tokens": 6321624.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.927427148818969,
|
||
|
|
"epoch": 0.23787619923774478,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004239718288363745,
|
||
|
|
"loss": 6.7784,
|
||
|
|
"mean_token_accuracy": 0.12367406710982323,
|
||
|
|
"num_tokens": 6341220.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.881071424484253,
|
||
|
|
"epoch": 0.23853331581022474,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004230869033621023,
|
||
|
|
"loss": 6.8652,
|
||
|
|
"mean_token_accuracy": 0.10935963243246079,
|
||
|
|
"num_tokens": 6358777.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0531727313995365,
|
||
|
|
"epoch": 0.23919043238270468,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004221979180105688,
|
||
|
|
"loss": 6.9129,
|
||
|
|
"mean_token_accuracy": 0.10789643600583076,
|
||
|
|
"num_tokens": 6374526.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.907487869262695,
|
||
|
|
"epoch": 0.23984754895518465,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.00042130489715375645,
|
||
|
|
"loss": 6.9511,
|
||
|
|
"mean_token_accuracy": 0.10683519318699837,
|
||
|
|
"num_tokens": 6391347.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.945343494415283,
|
||
|
|
"epoch": 0.2405046655276646,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.00042040786527428335,
|
||
|
|
"loss": 6.7705,
|
||
|
|
"mean_token_accuracy": 0.1205411709845066,
|
||
|
|
"num_tokens": 6409435.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.887475776672363,
|
||
|
|
"epoch": 0.24116178210014458,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004195068469647315,
|
||
|
|
"loss": 6.8372,
|
||
|
|
"mean_token_accuracy": 0.1160741165280342,
|
||
|
|
"num_tokens": 6426762.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.970030927658081,
|
||
|
|
"epoch": 0.24181889867262452,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00041860186692697297,
|
||
|
|
"loss": 6.9123,
|
||
|
|
"mean_token_accuracy": 0.10643681660294532,
|
||
|
|
"num_tokens": 6444857.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.905347537994385,
|
||
|
|
"epoch": 0.24247601524510448,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.00041769294997149264,
|
||
|
|
"loss": 6.9326,
|
||
|
|
"mean_token_accuracy": 0.11031701341271401,
|
||
|
|
"num_tokens": 6463499.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.007981395721435,
|
||
|
|
"epoch": 0.24313313181758445,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004167801210167081,
|
||
|
|
"loss": 6.8641,
|
||
|
|
"mean_token_accuracy": 0.10970722213387489,
|
||
|
|
"num_tokens": 6480858.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.879305362701416,
|
||
|
|
"epoch": 0.24379024839006438,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004158634050882861,
|
||
|
|
"loss": 6.8869,
|
||
|
|
"mean_token_accuracy": 0.10903827100992203,
|
||
|
|
"num_tokens": 6497904.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.86187515258789,
|
||
|
|
"epoch": 0.24444736496254435,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0004149428273184569,
|
||
|
|
"loss": 6.926,
|
||
|
|
"mean_token_accuracy": 0.1059575229883194,
|
||
|
|
"num_tokens": 6517735.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8103538990020756,
|
||
|
|
"epoch": 0.24510448153502432,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004140184129453253,
|
||
|
|
"loss": 6.7155,
|
||
|
|
"mean_token_accuracy": 0.1302804581820965,
|
||
|
|
"num_tokens": 6535367.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8377917289733885,
|
||
|
|
"epoch": 0.24576159810750428,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000413090187312178,
|
||
|
|
"loss": 6.9113,
|
||
|
|
"mean_token_accuracy": 0.11013041213154792,
|
||
|
|
"num_tokens": 6553328.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.891385841369629,
|
||
|
|
"epoch": 0.24641871467998422,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004121581758667898,
|
||
|
|
"loss": 6.7812,
|
||
|
|
"mean_token_accuracy": 0.12063414230942726,
|
||
|
|
"num_tokens": 6571035.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.946118259429932,
|
||
|
|
"epoch": 0.24707583125246418,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.00041122240416072533,
|
||
|
|
"loss": 6.8349,
|
||
|
|
"mean_token_accuracy": 0.11449943482875824,
|
||
|
|
"num_tokens": 6588264.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7777854919433596,
|
||
|
|
"epoch": 0.24773294782494415,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0004102828978486385,
|
||
|
|
"loss": 6.821,
|
||
|
|
"mean_token_accuracy": 0.1108366720378399,
|
||
|
|
"num_tokens": 6607564.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.889178657531739,
|
||
|
|
"epoch": 0.24839006439742412,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004093396826875695,
|
||
|
|
"loss": 6.7937,
|
||
|
|
"mean_token_accuracy": 0.11969260424375534,
|
||
|
|
"num_tokens": 6624624.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.91100172996521,
|
||
|
|
"epoch": 0.24904718096990405,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00040839278453623837,
|
||
|
|
"loss": 6.8991,
|
||
|
|
"mean_token_accuracy": 0.11091609597206116,
|
||
|
|
"num_tokens": 6641121.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.946281814575196,
|
||
|
|
"epoch": 0.24970429754238402,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.0004074422293543363,
|
||
|
|
"loss": 6.8407,
|
||
|
|
"mean_token_accuracy": 0.11662452071905136,
|
||
|
|
"num_tokens": 6656577.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8977423191070555,
|
||
|
|
"epoch": 0.25036141411486396,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.0004064880432018137,
|
||
|
|
"loss": 6.8545,
|
||
|
|
"mean_token_accuracy": 0.108473851531744,
|
||
|
|
"num_tokens": 6672991.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9810668468475345,
|
||
|
|
"epoch": 0.2510185306873439,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00040553025223816615,
|
||
|
|
"loss": 6.8398,
|
||
|
|
"mean_token_accuracy": 0.1077457495033741,
|
||
|
|
"num_tokens": 6691888.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.810923385620117,
|
||
|
|
"epoch": 0.2516756472598239,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00040456888272171653,
|
||
|
|
"loss": 6.7895,
|
||
|
|
"mean_token_accuracy": 0.11482183784246444,
|
||
|
|
"num_tokens": 6708247.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.932204294204712,
|
||
|
|
"epoch": 0.25233276383230385,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.00040360396100889577,
|
||
|
|
"loss": 6.8751,
|
||
|
|
"mean_token_accuracy": 0.10380443185567856,
|
||
|
|
"num_tokens": 6726072.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.884418487548828,
|
||
|
|
"epoch": 0.2529898804047838,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004026355135535202,
|
||
|
|
"loss": 6.8112,
|
||
|
|
"mean_token_accuracy": 0.11244645118713378,
|
||
|
|
"num_tokens": 6743898.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9820952892303465,
|
||
|
|
"epoch": 0.2536469969772638,
|
||
|
|
"grad_norm": 0.75390625,
|
||
|
|
"learning_rate": 0.000401663566906066,
|
||
|
|
"loss": 6.9903,
|
||
|
|
"mean_token_accuracy": 0.10120946541428566,
|
||
|
|
"num_tokens": 6761908.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.923025035858155,
|
||
|
|
"epoch": 0.25430411354974375,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.00040068814771294134,
|
||
|
|
"loss": 6.8935,
|
||
|
|
"mean_token_accuracy": 0.11003192588686943,
|
||
|
|
"num_tokens": 6779792.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.963992881774902,
|
||
|
|
"epoch": 0.25496123012222366,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0003997092827157562,
|
||
|
|
"loss": 6.9779,
|
||
|
|
"mean_token_accuracy": 0.10324695706367493,
|
||
|
|
"num_tokens": 6798833.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.997112083435058,
|
||
|
|
"epoch": 0.2556183466947036,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.000398726998750589,
|
||
|
|
"loss": 6.9269,
|
||
|
|
"mean_token_accuracy": 0.10882530882954597,
|
||
|
|
"num_tokens": 6815895.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.933638191223144,
|
||
|
|
"epoch": 0.2562754632671836,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00039774132274725076,
|
||
|
|
"loss": 6.8987,
|
||
|
|
"mean_token_accuracy": 0.10688839256763458,
|
||
|
|
"num_tokens": 6834053.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.894039964675903,
|
||
|
|
"epoch": 0.25693257983966356,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00039675228172854707,
|
||
|
|
"loss": 6.8821,
|
||
|
|
"mean_token_accuracy": 0.11116306111216545,
|
||
|
|
"num_tokens": 6850970.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.819674253463745,
|
||
|
|
"epoch": 0.2575896964121435,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0003957599028095371,
|
||
|
|
"loss": 6.7196,
|
||
|
|
"mean_token_accuracy": 0.12090378776192665,
|
||
|
|
"num_tokens": 6869063.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.878556632995606,
|
||
|
|
"epoch": 0.2582468129846235,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00039476421319679017,
|
||
|
|
"loss": 6.7706,
|
||
|
|
"mean_token_accuracy": 0.1244881734251976,
|
||
|
|
"num_tokens": 6886581.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8946946144104,
|
||
|
|
"epoch": 0.25890392955710345,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00039376524018764,
|
||
|
|
"loss": 6.9022,
|
||
|
|
"mean_token_accuracy": 0.10421441718935967,
|
||
|
|
"num_tokens": 6903421.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.937630653381348,
|
||
|
|
"epoch": 0.25956104612958336,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00039276301116943616,
|
||
|
|
"loss": 6.8318,
|
||
|
|
"mean_token_accuracy": 0.11262184754014015,
|
||
|
|
"num_tokens": 6920576.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.912281799316406,
|
||
|
|
"epoch": 0.2602181627020633,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0003917575536187936,
|
||
|
|
"loss": 6.8867,
|
||
|
|
"mean_token_accuracy": 0.1057386837899685,
|
||
|
|
"num_tokens": 6937115.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9639496326446535,
|
||
|
|
"epoch": 0.2608752792745433,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00039074889510083894,
|
||
|
|
"loss": 6.8888,
|
||
|
|
"mean_token_accuracy": 0.10327341929078102,
|
||
|
|
"num_tokens": 6955253.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.880260324478149,
|
||
|
|
"epoch": 0.26153239584702326,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.00038973706326845495,
|
||
|
|
"loss": 6.8042,
|
||
|
|
"mean_token_accuracy": 0.11103835329413414,
|
||
|
|
"num_tokens": 6972101.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.908779525756836,
|
||
|
|
"epoch": 0.2621895124195032,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.0003887220858615225,
|
||
|
|
"loss": 6.872,
|
||
|
|
"mean_token_accuracy": 0.1067228451371193,
|
||
|
|
"num_tokens": 6989909.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.959236907958984,
|
||
|
|
"epoch": 0.2628466289919832,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0003877039907061597,
|
||
|
|
"loss": 6.9357,
|
||
|
|
"mean_token_accuracy": 0.10451695770025253,
|
||
|
|
"num_tokens": 7007328.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.90189380645752,
|
||
|
|
"epoch": 0.26350374556446315,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0003866828057139598,
|
||
|
|
"loss": 6.8454,
|
||
|
|
"mean_token_accuracy": 0.11510350406169892,
|
||
|
|
"num_tokens": 7026676.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.915361166000366,
|
||
|
|
"epoch": 0.2641608621369431,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.00038565855888122503,
|
||
|
|
"loss": 6.8318,
|
||
|
|
"mean_token_accuracy": 0.10741369724273682,
|
||
|
|
"num_tokens": 7042400.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8233069896698,
|
||
|
|
"epoch": 0.26481797870942303,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00038463127828819975,
|
||
|
|
"loss": 6.7536,
|
||
|
|
"mean_token_accuracy": 0.11599642261862755,
|
||
|
|
"num_tokens": 7059479.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.888656234741211,
|
||
|
|
"epoch": 0.265475095281903,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.00038360099209830043,
|
||
|
|
"loss": 6.8972,
|
||
|
|
"mean_token_accuracy": 0.10539637207984924,
|
||
|
|
"num_tokens": 7077689.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.779890632629394,
|
||
|
|
"epoch": 0.26613221185438296,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003825677285573433,
|
||
|
|
"loss": 6.6859,
|
||
|
|
"mean_token_accuracy": 0.1261440023779869,
|
||
|
|
"num_tokens": 7095145.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.915167379379272,
|
||
|
|
"epoch": 0.2667893284268629,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.00038153151599277027,
|
||
|
|
"loss": 6.835,
|
||
|
|
"mean_token_accuracy": 0.11041357144713401,
|
||
|
|
"num_tokens": 7111567.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.795621395111084,
|
||
|
|
"epoch": 0.2674464449993429,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0003804923828128723,
|
||
|
|
"loss": 6.717,
|
||
|
|
"mean_token_accuracy": 0.1174989253282547,
|
||
|
|
"num_tokens": 7129128.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.866275501251221,
|
||
|
|
"epoch": 0.26810356157182286,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0003794503575060104,
|
||
|
|
"loss": 6.7432,
|
||
|
|
"mean_token_accuracy": 0.11609803289175033,
|
||
|
|
"num_tokens": 7146662.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.936456632614136,
|
||
|
|
"epoch": 0.2687606781443028,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00037840546863983484,
|
||
|
|
"loss": 6.871,
|
||
|
|
"mean_token_accuracy": 0.10677279382944108,
|
||
|
|
"num_tokens": 7164535.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.867893362045288,
|
||
|
|
"epoch": 0.26941779471678273,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0003773577448605015,
|
||
|
|
"loss": 6.8406,
|
||
|
|
"mean_token_accuracy": 0.11388155296444893,
|
||
|
|
"num_tokens": 7182044.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.875605869293213,
|
||
|
|
"epoch": 0.2700749112892627,
|
||
|
|
"grad_norm": 0.76953125,
|
||
|
|
"learning_rate": 0.0003763072148918872,
|
||
|
|
"loss": 6.82,
|
||
|
|
"mean_token_accuracy": 0.11503146290779113,
|
||
|
|
"num_tokens": 7201042.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8541844367980955,
|
||
|
|
"epoch": 0.27073202786174266,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0003752539075348017,
|
||
|
|
"loss": 6.8188,
|
||
|
|
"mean_token_accuracy": 0.11022190079092979,
|
||
|
|
"num_tokens": 7219363.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.909026479721069,
|
||
|
|
"epoch": 0.27138914443422263,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.00037419785166619817,
|
||
|
|
"loss": 6.8042,
|
||
|
|
"mean_token_accuracy": 0.1083768866956234,
|
||
|
|
"num_tokens": 7235919.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.822417497634888,
|
||
|
|
"epoch": 0.2720462610067026,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0003731390762383818,
|
||
|
|
"loss": 6.7678,
|
||
|
|
"mean_token_accuracy": 0.1129553645849228,
|
||
|
|
"num_tokens": 7253395.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.970107460021973,
|
||
|
|
"epoch": 0.27270337757918256,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0003720776102782158,
|
||
|
|
"loss": 6.8582,
|
||
|
|
"mean_token_accuracy": 0.10589501410722732,
|
||
|
|
"num_tokens": 7271164.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.861213493347168,
|
||
|
|
"epoch": 0.2733604941516625,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00037101348288632555,
|
||
|
|
"loss": 6.7831,
|
||
|
|
"mean_token_accuracy": 0.11100676655769348,
|
||
|
|
"num_tokens": 7287272.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.807501983642578,
|
||
|
|
"epoch": 0.27401761072414244,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0003699467232363012,
|
||
|
|
"loss": 6.7367,
|
||
|
|
"mean_token_accuracy": 0.11350043416023255,
|
||
|
|
"num_tokens": 7305984.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.797293663024902,
|
||
|
|
"epoch": 0.2746747272966224,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0003688773605738973,
|
||
|
|
"loss": 6.7114,
|
||
|
|
"mean_token_accuracy": 0.1228457234799862,
|
||
|
|
"num_tokens": 7323832.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.955334091186524,
|
||
|
|
"epoch": 0.27533184386910237,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.00036780542421623134,
|
||
|
|
"loss": 6.8812,
|
||
|
|
"mean_token_accuracy": 0.10829322934150695,
|
||
|
|
"num_tokens": 7341630.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9222198009490965,
|
||
|
|
"epoch": 0.27598896044158233,
|
||
|
|
"grad_norm": 0.7421875,
|
||
|
|
"learning_rate": 0.0003667309435509802,
|
||
|
|
"loss": 6.8951,
|
||
|
|
"mean_token_accuracy": 0.10414667651057244,
|
||
|
|
"num_tokens": 7360615.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9413331031799315,
|
||
|
|
"epoch": 0.2766460770140623,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0003656539480355741,
|
||
|
|
"loss": 6.8474,
|
||
|
|
"mean_token_accuracy": 0.1066794827580452,
|
||
|
|
"num_tokens": 7378342.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.851767730712891,
|
||
|
|
"epoch": 0.27730319358654226,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0003645744671963891,
|
||
|
|
"loss": 6.8081,
|
||
|
|
"mean_token_accuracy": 0.11258630454540253,
|
||
|
|
"num_tokens": 7397305.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.868390798568726,
|
||
|
|
"epoch": 0.27796031015902223,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0003634925306279376,
|
||
|
|
"loss": 6.7908,
|
||
|
|
"mean_token_accuracy": 0.10977037325501442,
|
||
|
|
"num_tokens": 7414682.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.845829057693481,
|
||
|
|
"epoch": 0.2786174267315022,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0003624081679920574,
|
||
|
|
"loss": 6.7559,
|
||
|
|
"mean_token_accuracy": 0.11788599193096161,
|
||
|
|
"num_tokens": 7432867.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.915082263946533,
|
||
|
|
"epoch": 0.2792745433039821,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0003613214090170977,
|
||
|
|
"loss": 6.844,
|
||
|
|
"mean_token_accuracy": 0.10410375520586967,
|
||
|
|
"num_tokens": 7450407.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839028978347779,
|
||
|
|
"epoch": 0.27993165987646207,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0003602322834971048,
|
||
|
|
"loss": 6.7555,
|
||
|
|
"mean_token_accuracy": 0.10915418267250061,
|
||
|
|
"num_tokens": 7468244.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.976844549179077,
|
||
|
|
"epoch": 0.28058877644894203,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0003591408212910051,
|
||
|
|
"loss": 6.9269,
|
||
|
|
"mean_token_accuracy": 0.10237115323543548,
|
||
|
|
"num_tokens": 7485772.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.824065542221069,
|
||
|
|
"epoch": 0.281245893021422,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0003580470523217863,
|
||
|
|
"loss": 6.7713,
|
||
|
|
"mean_token_accuracy": 0.11021952107548713,
|
||
|
|
"num_tokens": 7502518.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.868778562545776,
|
||
|
|
"epoch": 0.28190300959390197,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003569510065756771,
|
||
|
|
"loss": 6.78,
|
||
|
|
"mean_token_accuracy": 0.11237410828471184,
|
||
|
|
"num_tokens": 7518511.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.777426910400391,
|
||
|
|
"epoch": 0.28256012616638193,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0003558527141013254,
|
||
|
|
"loss": 6.7045,
|
||
|
|
"mean_token_accuracy": 0.1184836395084858,
|
||
|
|
"num_tokens": 7536408.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.90195665359497,
|
||
|
|
"epoch": 0.2832172427388619,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0003547522050089742,
|
||
|
|
"loss": 6.8293,
|
||
|
|
"mean_token_accuracy": 0.1089038796722889,
|
||
|
|
"num_tokens": 7552987.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.892579460144043,
|
||
|
|
"epoch": 0.2838743593113418,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00035364950946963606,
|
||
|
|
"loss": 6.7787,
|
||
|
|
"mean_token_accuracy": 0.11169492080807686,
|
||
|
|
"num_tokens": 7569392.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.849013471603394,
|
||
|
|
"epoch": 0.28453147588382177,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0003525446577142663,
|
||
|
|
"loss": 6.8012,
|
||
|
|
"mean_token_accuracy": 0.1053639903664589,
|
||
|
|
"num_tokens": 7588380.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9202512264251705,
|
||
|
|
"epoch": 0.28518859245630174,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.00035143768003293395,
|
||
|
|
"loss": 6.808,
|
||
|
|
"mean_token_accuracy": 0.10984457135200501,
|
||
|
|
"num_tokens": 7605590.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.799256896972656,
|
||
|
|
"epoch": 0.2858457090287817,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0003503286067739913,
|
||
|
|
"loss": 6.7677,
|
||
|
|
"mean_token_accuracy": 0.11929863542318345,
|
||
|
|
"num_tokens": 7624502.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.854879760742188,
|
||
|
|
"epoch": 0.28650282560126167,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.00034921746834324193,
|
||
|
|
"loss": 6.7421,
|
||
|
|
"mean_token_accuracy": 0.11639903634786605,
|
||
|
|
"num_tokens": 7641687.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839727830886841,
|
||
|
|
"epoch": 0.28715994217374163,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0003481042952031072,
|
||
|
|
"loss": 6.8022,
|
||
|
|
"mean_token_accuracy": 0.11233005970716477,
|
||
|
|
"num_tokens": 7660253.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.857293272018433,
|
||
|
|
"epoch": 0.2878170587462216,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0003469891178717911,
|
||
|
|
"loss": 6.8281,
|
||
|
|
"mean_token_accuracy": 0.10818165466189385,
|
||
|
|
"num_tokens": 7677258.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.961129522323608,
|
||
|
|
"epoch": 0.28847417531870156,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0003458719669224436,
|
||
|
|
"loss": 6.8761,
|
||
|
|
"mean_token_accuracy": 0.1069383479654789,
|
||
|
|
"num_tokens": 7694550.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.746155691146851,
|
||
|
|
"epoch": 0.2891312918911815,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003447528729823221,
|
||
|
|
"loss": 6.695,
|
||
|
|
"mean_token_accuracy": 0.11654992252588273,
|
||
|
|
"num_tokens": 7711998.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.891735601425171,
|
||
|
|
"epoch": 0.28978840846366144,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0003436318667319525,
|
||
|
|
"loss": 6.7998,
|
||
|
|
"mean_token_accuracy": 0.11585988402366638,
|
||
|
|
"num_tokens": 7730183.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.910313749313355,
|
||
|
|
"epoch": 0.2904455250361414,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00034250897890428716,
|
||
|
|
"loss": 6.7547,
|
||
|
|
"mean_token_accuracy": 0.10601133480668068,
|
||
|
|
"num_tokens": 7746481.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.779348468780517,
|
||
|
|
"epoch": 0.29110264160862137,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0003413842402838633,
|
||
|
|
"loss": 6.8005,
|
||
|
|
"mean_token_accuracy": 0.11217569559812546,
|
||
|
|
"num_tokens": 7764277.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.897648811340332,
|
||
|
|
"epoch": 0.29175975818110134,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.00034025768170595834,
|
||
|
|
"loss": 6.7809,
|
||
|
|
"mean_token_accuracy": 0.10989216491580009,
|
||
|
|
"num_tokens": 7780695.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8095055103302,
|
||
|
|
"epoch": 0.2924168747535813,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0003391293340557446,
|
||
|
|
"loss": 6.7077,
|
||
|
|
"mean_token_accuracy": 0.1234839379787445,
|
||
|
|
"num_tokens": 7799229.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8860759258270265,
|
||
|
|
"epoch": 0.29307399132606127,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0003379992282674431,
|
||
|
|
"loss": 6.8044,
|
||
|
|
"mean_token_accuracy": 0.1079778216779232,
|
||
|
|
"num_tokens": 7815238.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.904814863204956,
|
||
|
|
"epoch": 0.2937311078985412,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0003368673953234749,
|
||
|
|
"loss": 6.7044,
|
||
|
|
"mean_token_accuracy": 0.11529508754611015,
|
||
|
|
"num_tokens": 7832751.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839742040634155,
|
||
|
|
"epoch": 0.29438822447102114,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.00033573386625361176,
|
||
|
|
"loss": 6.8549,
|
||
|
|
"mean_token_accuracy": 0.1069272667169571,
|
||
|
|
"num_tokens": 7850649.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8689690113067625,
|
||
|
|
"epoch": 0.2950453410435011,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00033459867213412567,
|
||
|
|
"loss": 6.7217,
|
||
|
|
"mean_token_accuracy": 0.12011009529232979,
|
||
|
|
"num_tokens": 7868895.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.83195481300354,
|
||
|
|
"epoch": 0.2957024576159811,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.000333461844086937,
|
||
|
|
"loss": 6.7856,
|
||
|
|
"mean_token_accuracy": 0.1111657202243805,
|
||
|
|
"num_tokens": 7884839.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.874276781082154,
|
||
|
|
"epoch": 0.29635957418846104,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00033232341327876097,
|
||
|
|
"loss": 6.7613,
|
||
|
|
"mean_token_accuracy": 0.11410071104764938,
|
||
|
|
"num_tokens": 7901140.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.87677149772644,
|
||
|
|
"epoch": 0.297016690760941,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0003311834109202531,
|
||
|
|
"loss": 6.806,
|
||
|
|
"mean_token_accuracy": 0.10669303387403488,
|
||
|
|
"num_tokens": 7918779.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.878875017166138,
|
||
|
|
"epoch": 0.29767380733342097,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00033004186826515416,
|
||
|
|
"loss": 6.8042,
|
||
|
|
"mean_token_accuracy": 0.10461228787899017,
|
||
|
|
"num_tokens": 7937120.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.865233087539673,
|
||
|
|
"epoch": 0.2983309239059009,
|
||
|
|
"grad_norm": 0.71875,
|
||
|
|
"learning_rate": 0.0003288988166094324,
|
||
|
|
"loss": 6.7515,
|
||
|
|
"mean_token_accuracy": 0.11575486734509469,
|
||
|
|
"num_tokens": 7955522.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.84414439201355,
|
||
|
|
"epoch": 0.29898804047838085,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00032775428729042656,
|
||
|
|
"loss": 6.7167,
|
||
|
|
"mean_token_accuracy": 0.11176927238702775,
|
||
|
|
"num_tokens": 7972372.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.738534259796142,
|
||
|
|
"epoch": 0.2996451570508608,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000326608311685986,
|
||
|
|
"loss": 6.6501,
|
||
|
|
"mean_token_accuracy": 0.12354057505726815,
|
||
|
|
"num_tokens": 7990592.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.843465662002563,
|
||
|
|
"epoch": 0.3003022736233408,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0003254609212136108,
|
||
|
|
"loss": 6.7138,
|
||
|
|
"mean_token_accuracy": 0.11330792680382729,
|
||
|
|
"num_tokens": 8008590.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.812521743774414,
|
||
|
|
"epoch": 0.30095939019582074,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.00032431214732959036,
|
||
|
|
"loss": 6.7315,
|
||
|
|
"mean_token_accuracy": 0.11075285524129867,
|
||
|
|
"num_tokens": 8027640.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.85067458152771,
|
||
|
|
"epoch": 0.3016165067683007,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.000323162021528141,
|
||
|
|
"loss": 6.8353,
|
||
|
|
"mean_token_accuracy": 0.10363074988126755,
|
||
|
|
"num_tokens": 8044762.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.939677333831787,
|
||
|
|
"epoch": 0.3022736233407807,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.00032201057534054264,
|
||
|
|
"loss": 6.719,
|
||
|
|
"mean_token_accuracy": 0.1254444032907486,
|
||
|
|
"num_tokens": 8063935.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.688869142532349,
|
||
|
|
"epoch": 0.30293073991326064,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.00032085784033427414,
|
||
|
|
"loss": 6.566,
|
||
|
|
"mean_token_accuracy": 0.12919426411390306,
|
||
|
|
"num_tokens": 8081047.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.646978044509888,
|
||
|
|
"epoch": 0.30358785648574055,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0003197038481121478,
|
||
|
|
"loss": 6.5638,
|
||
|
|
"mean_token_accuracy": 0.12495062351226807,
|
||
|
|
"num_tokens": 8099990.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.856139612197876,
|
||
|
|
"epoch": 0.3042449730582205,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0003185486303114436,
|
||
|
|
"loss": 6.6644,
|
||
|
|
"mean_token_accuracy": 0.1174974113702774,
|
||
|
|
"num_tokens": 8117358.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7390540599822994,
|
||
|
|
"epoch": 0.3049020896307005,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0003173922186030409,
|
||
|
|
"loss": 6.7347,
|
||
|
|
"mean_token_accuracy": 0.11599681973457336,
|
||
|
|
"num_tokens": 8135581.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839409732818604,
|
||
|
|
"epoch": 0.30555920620318044,
|
||
|
|
"grad_norm": 0.74609375,
|
||
|
|
"learning_rate": 0.000316234644690551,
|
||
|
|
"loss": 6.7229,
|
||
|
|
"mean_token_accuracy": 0.11520425081253052,
|
||
|
|
"num_tokens": 8155161.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.78435959815979,
|
||
|
|
"epoch": 0.3062163227756604,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003150759403094473,
|
||
|
|
"loss": 6.6864,
|
||
|
|
"mean_token_accuracy": 0.1165648266673088,
|
||
|
|
"num_tokens": 8173049.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.853875970840454,
|
||
|
|
"epoch": 0.3068734393481404,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.00031391613722619587,
|
||
|
|
"loss": 6.7144,
|
||
|
|
"mean_token_accuracy": 0.11264509186148644,
|
||
|
|
"num_tokens": 8188849.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.877394914627075,
|
||
|
|
"epoch": 0.30753055592062034,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000312755267237384,
|
||
|
|
"loss": 6.7371,
|
||
|
|
"mean_token_accuracy": 0.11314060315489768,
|
||
|
|
"num_tokens": 8206459.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.726744651794434,
|
||
|
|
"epoch": 0.30818767249310025,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003115933621688488,
|
||
|
|
"loss": 6.6196,
|
||
|
|
"mean_token_accuracy": 0.1252942256629467,
|
||
|
|
"num_tokens": 8224292.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8630290031433105,
|
||
|
|
"epoch": 0.3088447890655802,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.00031043045387480487,
|
||
|
|
"loss": 6.8085,
|
||
|
|
"mean_token_accuracy": 0.10712570622563362,
|
||
|
|
"num_tokens": 8241841.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.878791570663452,
|
||
|
|
"epoch": 0.3095019056380602,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0003092665742369703,
|
||
|
|
"loss": 6.8201,
|
||
|
|
"mean_token_accuracy": 0.11099817901849747,
|
||
|
|
"num_tokens": 8260122.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.885977125167846,
|
||
|
|
"epoch": 0.31015902221054015,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00030810175516369343,
|
||
|
|
"loss": 6.7359,
|
||
|
|
"mean_token_accuracy": 0.11548222526907921,
|
||
|
|
"num_tokens": 8277329.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.746277523040772,
|
||
|
|
"epoch": 0.3108161387830201,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0003069360285890775,
|
||
|
|
"loss": 6.5573,
|
||
|
|
"mean_token_accuracy": 0.1205863781273365,
|
||
|
|
"num_tokens": 8293324.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.834659051895142,
|
||
|
|
"epoch": 0.3114732553555001,
|
||
|
|
"grad_norm": 0.765625,
|
||
|
|
"learning_rate": 0.00030576942647210547,
|
||
|
|
"loss": 6.774,
|
||
|
|
"mean_token_accuracy": 0.10828504115343093,
|
||
|
|
"num_tokens": 8309507.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.885479402542114,
|
||
|
|
"epoch": 0.31213037192798004,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00030460198079576355,
|
||
|
|
"loss": 6.7867,
|
||
|
|
"mean_token_accuracy": 0.11647109314799309,
|
||
|
|
"num_tokens": 8326391.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.90219407081604,
|
||
|
|
"epoch": 0.31278748850046,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0003034337235661648,
|
||
|
|
"loss": 6.7805,
|
||
|
|
"mean_token_accuracy": 0.11166351884603501,
|
||
|
|
"num_tokens": 8344394.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.840408897399902,
|
||
|
|
"epoch": 0.3134446050729399,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0003022646868116714,
|
||
|
|
"loss": 6.823,
|
||
|
|
"mean_token_accuracy": 0.10478725954890251,
|
||
|
|
"num_tokens": 8362301.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.859322547912598,
|
||
|
|
"epoch": 0.3141017216454199,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0003010949025820163,
|
||
|
|
"loss": 6.7303,
|
||
|
|
"mean_token_accuracy": 0.11084634363651276,
|
||
|
|
"num_tokens": 8379017.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.794443559646607,
|
||
|
|
"epoch": 0.31475883821789985,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0002999244029474252,
|
||
|
|
"loss": 6.7179,
|
||
|
|
"mean_token_accuracy": 0.11309120506048202,
|
||
|
|
"num_tokens": 8397662.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.885931444168091,
|
||
|
|
"epoch": 0.3154159547903798,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.00029875321999773684,
|
||
|
|
"loss": 6.7747,
|
||
|
|
"mean_token_accuracy": 0.10787786841392517,
|
||
|
|
"num_tokens": 8414236.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.875982427597046,
|
||
|
|
"epoch": 0.3160730713628598,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.00029758138584152333,
|
||
|
|
"loss": 6.8008,
|
||
|
|
"mean_token_accuracy": 0.109447081387043,
|
||
|
|
"num_tokens": 8431510.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8201006889343265,
|
||
|
|
"epoch": 0.31673018793533975,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.0002964089326052102,
|
||
|
|
"loss": 6.6699,
|
||
|
|
"mean_token_accuracy": 0.1127239592373371,
|
||
|
|
"num_tokens": 8449978.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8044671535491945,
|
||
|
|
"epoch": 0.3173873045078197,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0002952358924321949,
|
||
|
|
"loss": 6.706,
|
||
|
|
"mean_token_accuracy": 0.11496890485286712,
|
||
|
|
"num_tokens": 8467433.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.788022661209107,
|
||
|
|
"epoch": 0.3180444210802996,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.00029406229748196657,
|
||
|
|
"loss": 6.6336,
|
||
|
|
"mean_token_accuracy": 0.11725025177001953,
|
||
|
|
"num_tokens": 8486864.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.86285514831543,
|
||
|
|
"epoch": 0.3187015376527796,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0002928881799292235,
|
||
|
|
"loss": 6.7715,
|
||
|
|
"mean_token_accuracy": 0.10842417627573013,
|
||
|
|
"num_tokens": 8504592.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.636095762252808,
|
||
|
|
"epoch": 0.31935865422525955,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.00029171357196299154,
|
||
|
|
"loss": 6.5449,
|
||
|
|
"mean_token_accuracy": 0.13502381294965743,
|
||
|
|
"num_tokens": 8523834.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7693451881408695,
|
||
|
|
"epoch": 0.3200157707977395,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0002905385057857414,
|
||
|
|
"loss": 6.7218,
|
||
|
|
"mean_token_accuracy": 0.11330327913165092,
|
||
|
|
"num_tokens": 8540288.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.852287292480469,
|
||
|
|
"epoch": 0.3206728873702195,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0002893630136125058,
|
||
|
|
"loss": 6.7332,
|
||
|
|
"mean_token_accuracy": 0.10845599770545959,
|
||
|
|
"num_tokens": 8557637.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.884438943862915,
|
||
|
|
"epoch": 0.32133000394269945,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0002881871276699967,
|
||
|
|
"loss": 6.797,
|
||
|
|
"mean_token_accuracy": 0.1135961540043354,
|
||
|
|
"num_tokens": 8575607.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.902685022354126,
|
||
|
|
"epoch": 0.3219871205151794,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00028701088019572114,
|
||
|
|
"loss": 6.7422,
|
||
|
|
"mean_token_accuracy": 0.11158652007579803,
|
||
|
|
"num_tokens": 8593381.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.774290275573731,
|
||
|
|
"epoch": 0.3226442370876593,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0002858343034370977,
|
||
|
|
"loss": 6.7206,
|
||
|
|
"mean_token_accuracy": 0.11927049532532692,
|
||
|
|
"num_tokens": 8612854.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.648822450637818,
|
||
|
|
"epoch": 0.3233013536601393,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00028465742965057267,
|
||
|
|
"loss": 6.5308,
|
||
|
|
"mean_token_accuracy": 0.1225376196205616,
|
||
|
|
"num_tokens": 8630645.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.876934146881103,
|
||
|
|
"epoch": 0.32395847023261926,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.00028348029110073533,
|
||
|
|
"loss": 6.7655,
|
||
|
|
"mean_token_accuracy": 0.10845103561878204,
|
||
|
|
"num_tokens": 8647662.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.863807678222656,
|
||
|
|
"epoch": 0.3246155868050992,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00028230292005943365,
|
||
|
|
"loss": 6.7649,
|
||
|
|
"mean_token_accuracy": 0.11021208688616753,
|
||
|
|
"num_tokens": 8664997.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.882658576965332,
|
||
|
|
"epoch": 0.3252727033775792,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.00028112534880488945,
|
||
|
|
"loss": 6.713,
|
||
|
|
"mean_token_accuracy": 0.11658079773187638,
|
||
|
|
"num_tokens": 8682401.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.796290063858033,
|
||
|
|
"epoch": 0.32592981995005915,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0002799476096208137,
|
||
|
|
"loss": 6.6337,
|
||
|
|
"mean_token_accuracy": 0.11471380814909934,
|
||
|
|
"num_tokens": 8699646.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.732109832763672,
|
||
|
|
"epoch": 0.3265869365225391,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.00027876973479552087,
|
||
|
|
"loss": 6.5878,
|
||
|
|
"mean_token_accuracy": 0.1167381078004837,
|
||
|
|
"num_tokens": 8717635.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.786510372161866,
|
||
|
|
"epoch": 0.3272440530950191,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.00027759175662104424,
|
||
|
|
"loss": 6.591,
|
||
|
|
"mean_token_accuracy": 0.12484889850020409,
|
||
|
|
"num_tokens": 8734282.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.771283578872681,
|
||
|
|
"epoch": 0.327901169667499,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0002764137073922508,
|
||
|
|
"loss": 6.7219,
|
||
|
|
"mean_token_accuracy": 0.10792348310351371,
|
||
|
|
"num_tokens": 8751449.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.859547281265259,
|
||
|
|
"epoch": 0.32855828623997896,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00027523561940595505,
|
||
|
|
"loss": 6.7471,
|
||
|
|
"mean_token_accuracy": 0.10983080118894577,
|
||
|
|
"num_tokens": 8768093.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.818148374557495,
|
||
|
|
"epoch": 0.3292154028124589,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0002740575249600342,
|
||
|
|
"loss": 6.738,
|
||
|
|
"mean_token_accuracy": 0.1129427745938301,
|
||
|
|
"num_tokens": 8785203.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.756053876876831,
|
||
|
|
"epoch": 0.3298725193849389,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00027287945635254263,
|
||
|
|
"loss": 6.6302,
|
||
|
|
"mean_token_accuracy": 0.11689828261733055,
|
||
|
|
"num_tokens": 8802171.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8046938419342045,
|
||
|
|
"epoch": 0.33052963595741885,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00027170144588082635,
|
||
|
|
"loss": 6.6357,
|
||
|
|
"mean_token_accuracy": 0.12506143972277642,
|
||
|
|
"num_tokens": 8819237.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8445367336273195,
|
||
|
|
"epoch": 0.3311867525298988,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.00027052352584063763,
|
||
|
|
"loss": 6.7583,
|
||
|
|
"mean_token_accuracy": 0.10731849521398544,
|
||
|
|
"num_tokens": 8836563.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.837574434280396,
|
||
|
|
"epoch": 0.3318438691023788,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.00026934572852524907,
|
||
|
|
"loss": 6.7255,
|
||
|
|
"mean_token_accuracy": 0.11873878687620162,
|
||
|
|
"num_tokens": 8854578.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.831789112091064,
|
||
|
|
"epoch": 0.3325009856748587,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.00026816808622456937,
|
||
|
|
"loss": 6.6696,
|
||
|
|
"mean_token_accuracy": 0.11565513908863068,
|
||
|
|
"num_tokens": 8871610.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839486408233642,
|
||
|
|
"epoch": 0.33315810224733866,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0002669906312242569,
|
||
|
|
"loss": 6.6653,
|
||
|
|
"mean_token_accuracy": 0.11815011352300644,
|
||
|
|
"num_tokens": 8889162.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7442834854125975,
|
||
|
|
"epoch": 0.3338152188198186,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.00026581339580483525,
|
||
|
|
"loss": 6.689,
|
||
|
|
"mean_token_accuracy": 0.11806058511137962,
|
||
|
|
"num_tokens": 8905746.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.813786792755127,
|
||
|
|
"epoch": 0.3344723353922986,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0002646364122408082,
|
||
|
|
"loss": 6.6807,
|
||
|
|
"mean_token_accuracy": 0.1123983956873417,
|
||
|
|
"num_tokens": 8924088.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.798582553863525,
|
||
|
|
"epoch": 0.33512945196477856,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0002634597127997749,
|
||
|
|
"loss": 6.6409,
|
||
|
|
"mean_token_accuracy": 0.11660403534770011,
|
||
|
|
"num_tokens": 8941292.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.744631004333496,
|
||
|
|
"epoch": 0.3357865685372585,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0002622833297415445,
|
||
|
|
"loss": 6.6262,
|
||
|
|
"mean_token_accuracy": 0.11935020238161087,
|
||
|
|
"num_tokens": 8958168.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8401611328125,
|
||
|
|
"epoch": 0.3364436851097385,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0002611072953172531,
|
||
|
|
"loss": 6.5847,
|
||
|
|
"mean_token_accuracy": 0.11788244172930717,
|
||
|
|
"num_tokens": 8976203.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.812955760955811,
|
||
|
|
"epoch": 0.3371008016822184,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.00025993164176847845,
|
||
|
|
"loss": 6.6841,
|
||
|
|
"mean_token_accuracy": 0.11328838914632797,
|
||
|
|
"num_tokens": 8992524.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.728555679321289,
|
||
|
|
"epoch": 0.33775791825469836,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0002587564013263564,
|
||
|
|
"loss": 6.6319,
|
||
|
|
"mean_token_accuracy": 0.11895213574171067,
|
||
|
|
"num_tokens": 9009234.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.838398075103759,
|
||
|
|
"epoch": 0.33841503482717833,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0002575816062106974,
|
||
|
|
"loss": 6.7419,
|
||
|
|
"mean_token_accuracy": 0.103299842774868,
|
||
|
|
"num_tokens": 9026878.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.760490846633911,
|
||
|
|
"epoch": 0.3390721513996583,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00025640728862910293,
|
||
|
|
"loss": 6.5479,
|
||
|
|
"mean_token_accuracy": 0.12153853997588157,
|
||
|
|
"num_tokens": 9045591.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.754572629928589,
|
||
|
|
"epoch": 0.33972926797213826,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.00025523348077608285,
|
||
|
|
"loss": 6.6538,
|
||
|
|
"mean_token_accuracy": 0.11465492621064186,
|
||
|
|
"num_tokens": 9062431.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.831317949295044,
|
||
|
|
"epoch": 0.3403863845446182,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.00025406021483217225,
|
||
|
|
"loss": 6.6985,
|
||
|
|
"mean_token_accuracy": 0.11585047021508217,
|
||
|
|
"num_tokens": 9079415.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.700525283813477,
|
||
|
|
"epoch": 0.3410435011170982,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00025288752296304963,
|
||
|
|
"loss": 6.5503,
|
||
|
|
"mean_token_accuracy": 0.1295196756720543,
|
||
|
|
"num_tokens": 9096325.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.801946067810059,
|
||
|
|
"epoch": 0.34170061768957816,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000251715437318655,
|
||
|
|
"loss": 6.6774,
|
||
|
|
"mean_token_accuracy": 0.11396888867020608,
|
||
|
|
"num_tokens": 9114392.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.780405759811401,
|
||
|
|
"epoch": 0.34235773426205807,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0002505439900323084,
|
||
|
|
"loss": 6.6416,
|
||
|
|
"mean_token_accuracy": 0.12040675356984139,
|
||
|
|
"num_tokens": 9130103.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.783097267150879,
|
||
|
|
"epoch": 0.34301485083453803,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.00024937321321982894,
|
||
|
|
"loss": 6.6874,
|
||
|
|
"mean_token_accuracy": 0.11125573813915253,
|
||
|
|
"num_tokens": 9147570.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.777477979660034,
|
||
|
|
"epoch": 0.343671967407018,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.00024820313897865433,
|
||
|
|
"loss": 6.6092,
|
||
|
|
"mean_token_accuracy": 0.11934626251459121,
|
||
|
|
"num_tokens": 9164925.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.82387752532959,
|
||
|
|
"epoch": 0.34432908397949796,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.00024703379938696105,
|
||
|
|
"loss": 6.7002,
|
||
|
|
"mean_token_accuracy": 0.11279828399419785,
|
||
|
|
"num_tokens": 9181983.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.807449293136597,
|
||
|
|
"epoch": 0.34498620055197793,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00024586522650278447,
|
||
|
|
"loss": 6.6721,
|
||
|
|
"mean_token_accuracy": 0.11800289377570153,
|
||
|
|
"num_tokens": 9199726.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.730328989028931,
|
||
|
|
"epoch": 0.3456433171244579,
|
||
|
|
"grad_norm": 0.75390625,
|
||
|
|
"learning_rate": 0.00024469745236314064,
|
||
|
|
"loss": 6.5889,
|
||
|
|
"mean_token_accuracy": 0.12466638460755348,
|
||
|
|
"num_tokens": 9215749.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.784063720703125,
|
||
|
|
"epoch": 0.34630043369693786,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00024353050898314767,
|
||
|
|
"loss": 6.6286,
|
||
|
|
"mean_token_accuracy": 0.11424450799822808,
|
||
|
|
"num_tokens": 9231931.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.802047777175903,
|
||
|
|
"epoch": 0.34695755026941777,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00024236442835514743,
|
||
|
|
"loss": 6.7604,
|
||
|
|
"mean_token_accuracy": 0.107723218947649,
|
||
|
|
"num_tokens": 9249674.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.89581332206726,
|
||
|
|
"epoch": 0.34761466684189773,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00024119924244782965,
|
||
|
|
"loss": 6.705,
|
||
|
|
"mean_token_accuracy": 0.1095836617052555,
|
||
|
|
"num_tokens": 9266246.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.730526304244995,
|
||
|
|
"epoch": 0.3482717834143777,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00024003498320535462,
|
||
|
|
"loss": 6.6696,
|
||
|
|
"mean_token_accuracy": 0.11263803839683532,
|
||
|
|
"num_tokens": 9282923.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.712793588638306,
|
||
|
|
"epoch": 0.34892889998685767,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.00023887168254647727,
|
||
|
|
"loss": 6.5476,
|
||
|
|
"mean_token_accuracy": 0.13104497268795967,
|
||
|
|
"num_tokens": 9300801.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.875895404815674,
|
||
|
|
"epoch": 0.34958601655933763,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.00023770937236367308,
|
||
|
|
"loss": 6.6814,
|
||
|
|
"mean_token_accuracy": 0.11430239379405975,
|
||
|
|
"num_tokens": 9316956.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.761322450637818,
|
||
|
|
"epoch": 0.3502431331318176,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.00023654808452226278,
|
||
|
|
"loss": 6.736,
|
||
|
|
"mean_token_accuracy": 0.11177758798003197,
|
||
|
|
"num_tokens": 9336300.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.721040344238281,
|
||
|
|
"epoch": 0.35090024970429756,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00023538785085953912,
|
||
|
|
"loss": 6.5212,
|
||
|
|
"mean_token_accuracy": 0.1253015398979187,
|
||
|
|
"num_tokens": 9352609.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.847442293167115,
|
||
|
|
"epoch": 0.3515573662767775,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00023422870318389404,
|
||
|
|
"loss": 6.621,
|
||
|
|
"mean_token_accuracy": 0.11668119505047798,
|
||
|
|
"num_tokens": 9368881.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.68349175453186,
|
||
|
|
"epoch": 0.35221448284925744,
|
||
|
|
"grad_norm": 0.75,
|
||
|
|
"learning_rate": 0.0002330706732739468,
|
||
|
|
"loss": 6.5689,
|
||
|
|
"mean_token_accuracy": 0.12725232690572738,
|
||
|
|
"num_tokens": 9386610.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.837378120422363,
|
||
|
|
"epoch": 0.3528715994217374,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.00023191379287767211,
|
||
|
|
"loss": 6.5943,
|
||
|
|
"mean_token_accuracy": 0.12152000293135642,
|
||
|
|
"num_tokens": 9403768.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.622219085693359,
|
||
|
|
"epoch": 0.35352871599421737,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0002307580937115305,
|
||
|
|
"loss": 6.4451,
|
||
|
|
"mean_token_accuracy": 0.13854755833745003,
|
||
|
|
"num_tokens": 9421092.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.77311487197876,
|
||
|
|
"epoch": 0.35418583256669733,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.00022960360745959846,
|
||
|
|
"loss": 6.5985,
|
||
|
|
"mean_token_accuracy": 0.11288280859589576,
|
||
|
|
"num_tokens": 9438594.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.802717065811157,
|
||
|
|
"epoch": 0.3548429491391773,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.00022845036577269972,
|
||
|
|
"loss": 6.7021,
|
||
|
|
"mean_token_accuracy": 0.11373834609985352,
|
||
|
|
"num_tokens": 9456501.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7988534450531,
|
||
|
|
"epoch": 0.35550006571165726,
|
||
|
|
"grad_norm": 0.7578125,
|
||
|
|
"learning_rate": 0.00022729840026753777,
|
||
|
|
"loss": 6.7032,
|
||
|
|
"mean_token_accuracy": 0.11476492956280708,
|
||
|
|
"num_tokens": 9472702.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.846177291870117,
|
||
|
|
"epoch": 0.35615718228413723,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.0002261477425258287,
|
||
|
|
"loss": 6.645,
|
||
|
|
"mean_token_accuracy": 0.11662858948111535,
|
||
|
|
"num_tokens": 9489010.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.730893468856811,
|
||
|
|
"epoch": 0.35681429885661714,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.0002249984240934358,
|
||
|
|
"loss": 6.5595,
|
||
|
|
"mean_token_accuracy": 0.12515562772750854,
|
||
|
|
"num_tokens": 9507375.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8566466808319095,
|
||
|
|
"epoch": 0.3574714154290971,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.00022385047647950464,
|
||
|
|
"loss": 6.7846,
|
||
|
|
"mean_token_accuracy": 0.11169525384902954,
|
||
|
|
"num_tokens": 9524261.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.859349489212036,
|
||
|
|
"epoch": 0.35812853200157707,
|
||
|
|
"grad_norm": 0.765625,
|
||
|
|
"learning_rate": 0.0002227039311555986,
|
||
|
|
"loss": 6.7189,
|
||
|
|
"mean_token_accuracy": 0.11351526007056237,
|
||
|
|
"num_tokens": 9543497.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.836163759231567,
|
||
|
|
"epoch": 0.35878564857405704,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0002215588195548372,
|
||
|
|
"loss": 6.6789,
|
||
|
|
"mean_token_accuracy": 0.1161867581307888,
|
||
|
|
"num_tokens": 9560815.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.646726608276367,
|
||
|
|
"epoch": 0.359442765146537,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.00022041517307103337,
|
||
|
|
"loss": 6.4971,
|
||
|
|
"mean_token_accuracy": 0.1258929803967476,
|
||
|
|
"num_tokens": 9578221.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.827611017227173,
|
||
|
|
"epoch": 0.36009988171901697,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0002192730230578331,
|
||
|
|
"loss": 6.6624,
|
||
|
|
"mean_token_accuracy": 0.11771810874342918,
|
||
|
|
"num_tokens": 9593791.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.834709596633911,
|
||
|
|
"epoch": 0.36075699829149693,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0002181324008278559,
|
||
|
|
"loss": 6.6921,
|
||
|
|
"mean_token_accuracy": 0.10897867456078529,
|
||
|
|
"num_tokens": 9611103.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.815229701995849,
|
||
|
|
"epoch": 0.36141411486397684,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.00021699333765183655,
|
||
|
|
"loss": 6.6796,
|
||
|
|
"mean_token_accuracy": 0.11590011939406394,
|
||
|
|
"num_tokens": 9628280.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.712098836898804,
|
||
|
|
"epoch": 0.3620712314364568,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.0002158558647577673,
|
||
|
|
"loss": 6.5381,
|
||
|
|
"mean_token_accuracy": 0.13391041234135628,
|
||
|
|
"num_tokens": 9646875.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.744359159469605,
|
||
|
|
"epoch": 0.3627283480089368,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00021472001333004215,
|
||
|
|
"loss": 6.5188,
|
||
|
|
"mean_token_accuracy": 0.1265867233276367,
|
||
|
|
"num_tokens": 9663351.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.838795375823975,
|
||
|
|
"epoch": 0.36338546458141674,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.00021358581450860186,
|
||
|
|
"loss": 6.6666,
|
||
|
|
"mean_token_accuracy": 0.11247403845191002,
|
||
|
|
"num_tokens": 9680384.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.762395191192627,
|
||
|
|
"epoch": 0.3640425811538967,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.0002124532993880799,
|
||
|
|
"loss": 6.5887,
|
||
|
|
"mean_token_accuracy": 0.12084712386131287,
|
||
|
|
"num_tokens": 9697944.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8892895698547365,
|
||
|
|
"epoch": 0.36469969772637667,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.00021132249901695044,
|
||
|
|
"loss": 6.6753,
|
||
|
|
"mean_token_accuracy": 0.11380163207650185,
|
||
|
|
"num_tokens": 9715049.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6804876804351805,
|
||
|
|
"epoch": 0.36535681429885664,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.00021019344439667705,
|
||
|
|
"loss": 6.5914,
|
||
|
|
"mean_token_accuracy": 0.12288473173975945,
|
||
|
|
"num_tokens": 9732341.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.775627279281617,
|
||
|
|
"epoch": 0.3660139308713366,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.00020906616648086213,
|
||
|
|
"loss": 6.5984,
|
||
|
|
"mean_token_accuracy": 0.11893511936068535,
|
||
|
|
"num_tokens": 9749431.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.764123487472534,
|
||
|
|
"epoch": 0.3666710474438165,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00020794069617439942,
|
||
|
|
"loss": 6.6287,
|
||
|
|
"mean_token_accuracy": 0.1128695048391819,
|
||
|
|
"num_tokens": 9766286.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.751502943038941,
|
||
|
|
"epoch": 0.3673281640162965,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.00020681706433262593,
|
||
|
|
"loss": 6.5993,
|
||
|
|
"mean_token_accuracy": 0.12138979732990265,
|
||
|
|
"num_tokens": 9784616.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.842967414855957,
|
||
|
|
"epoch": 0.36798528058877644,
|
||
|
|
"grad_norm": 0.78515625,
|
||
|
|
"learning_rate": 0.00020569530176047602,
|
||
|
|
"loss": 6.6818,
|
||
|
|
"mean_token_accuracy": 0.11678276285529136,
|
||
|
|
"num_tokens": 9803251.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.768125247955322,
|
||
|
|
"epoch": 0.3686423971612564,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0002045754392116374,
|
||
|
|
"loss": 6.6389,
|
||
|
|
"mean_token_accuracy": 0.11537939831614494,
|
||
|
|
"num_tokens": 9821294.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.842143964767456,
|
||
|
|
"epoch": 0.3692995137337364,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.00020345750738770757,
|
||
|
|
"loss": 6.6232,
|
||
|
|
"mean_token_accuracy": 0.116897002607584,
|
||
|
|
"num_tokens": 9838131.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8127593994140625,
|
||
|
|
"epoch": 0.36995663030621634,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00020234153693735214,
|
||
|
|
"loss": 6.6362,
|
||
|
|
"mean_token_accuracy": 0.11208590492606163,
|
||
|
|
"num_tokens": 9855266.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.777508020401001,
|
||
|
|
"epoch": 0.3706137468786963,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0002012275584554647,
|
||
|
|
"loss": 6.6568,
|
||
|
|
"mean_token_accuracy": 0.11643510907888413,
|
||
|
|
"num_tokens": 9873547.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.744866609573364,
|
||
|
|
"epoch": 0.3712708634511762,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.00020011560248232803,
|
||
|
|
"loss": 6.6556,
|
||
|
|
"mean_token_accuracy": 0.12075368911027909,
|
||
|
|
"num_tokens": 9891349.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.823014545440674,
|
||
|
|
"epoch": 0.3719279800236562,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.00019900569950277692,
|
||
|
|
"loss": 6.6053,
|
||
|
|
"mean_token_accuracy": 0.11942033097147942,
|
||
|
|
"num_tokens": 9909085.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.848727655410767,
|
||
|
|
"epoch": 0.37258509659613614,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.00019789787994536228,
|
||
|
|
"loss": 6.6447,
|
||
|
|
"mean_token_accuracy": 0.11113560050725937,
|
||
|
|
"num_tokens": 9926627.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6871490478515625,
|
||
|
|
"epoch": 0.3732422131686161,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00019679217418151667,
|
||
|
|
"loss": 6.5137,
|
||
|
|
"mean_token_accuracy": 0.1287542037665844,
|
||
|
|
"num_tokens": 9946648.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.846956014633179,
|
||
|
|
"epoch": 0.3738993297410961,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.00019568861252472236,
|
||
|
|
"loss": 6.6956,
|
||
|
|
"mean_token_accuracy": 0.11283852085471154,
|
||
|
|
"num_tokens": 9963532.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.796116352081299,
|
||
|
|
"epoch": 0.37455644631357604,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.00019458722522967952,
|
||
|
|
"loss": 6.6605,
|
||
|
|
"mean_token_accuracy": 0.11486830562353134,
|
||
|
|
"num_tokens": 9981645.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8110510349273685,
|
||
|
|
"epoch": 0.375213562886056,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.00019348804249147723,
|
||
|
|
"loss": 6.5671,
|
||
|
|
"mean_token_accuracy": 0.11914361119270325,
|
||
|
|
"num_tokens": 9998924.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.819836282730103,
|
||
|
|
"epoch": 0.3758706794585359,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0001923910944447655,
|
||
|
|
"loss": 6.6831,
|
||
|
|
"mean_token_accuracy": 0.11173157840967178,
|
||
|
|
"num_tokens": 10015896.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.629815244674683,
|
||
|
|
"epoch": 0.3765277960310159,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.00019129641116292928,
|
||
|
|
"loss": 6.4094,
|
||
|
|
"mean_token_accuracy": 0.1376834250986576,
|
||
|
|
"num_tokens": 10033217.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.727242040634155,
|
||
|
|
"epoch": 0.37718491260349585,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.00019020402265726343,
|
||
|
|
"loss": 6.6071,
|
||
|
|
"mean_token_accuracy": 0.1284671403467655,
|
||
|
|
"num_tokens": 10051470.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.811199569702149,
|
||
|
|
"epoch": 0.3778420291759758,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0001891139588761509,
|
||
|
|
"loss": 6.6637,
|
||
|
|
"mean_token_accuracy": 0.1108133040368557,
|
||
|
|
"num_tokens": 10069127.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.748363065719604,
|
||
|
|
"epoch": 0.3784991457484558,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.00018802624970424076,
|
||
|
|
"loss": 6.5026,
|
||
|
|
"mean_token_accuracy": 0.12364941984415054,
|
||
|
|
"num_tokens": 10085993.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.784980726242066,
|
||
|
|
"epoch": 0.37915626232093574,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.00018694092496162945,
|
||
|
|
"loss": 6.6012,
|
||
|
|
"mean_token_accuracy": 0.11848501414060593,
|
||
|
|
"num_tokens": 10103552.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.76716194152832,
|
||
|
|
"epoch": 0.3798133788934157,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00018585801440304306,
|
||
|
|
"loss": 6.5897,
|
||
|
|
"mean_token_accuracy": 0.11782421693205833,
|
||
|
|
"num_tokens": 10119856.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.822872734069824,
|
||
|
|
"epoch": 0.3804704954658957,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.00018477754771702165,
|
||
|
|
"loss": 6.6377,
|
||
|
|
"mean_token_accuracy": 0.11552480310201645,
|
||
|
|
"num_tokens": 10136080.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.684869432449341,
|
||
|
|
"epoch": 0.3811276120383756,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.00018369955452510506,
|
||
|
|
"loss": 6.5716,
|
||
|
|
"mean_token_accuracy": 0.12180276587605476,
|
||
|
|
"num_tokens": 10152477.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.699605894088745,
|
||
|
|
"epoch": 0.38178472861085555,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0001826240643810212,
|
||
|
|
"loss": 6.4927,
|
||
|
|
"mean_token_accuracy": 0.1281001850962639,
|
||
|
|
"num_tokens": 10170118.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.86851167678833,
|
||
|
|
"epoch": 0.3824418451833355,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0001815511067698758,
|
||
|
|
"loss": 6.6662,
|
||
|
|
"mean_token_accuracy": 0.11514169052243232,
|
||
|
|
"num_tokens": 10186496.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.752274036407471,
|
||
|
|
"epoch": 0.3830989617558155,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0001804807111073436,
|
||
|
|
"loss": 6.5652,
|
||
|
|
"mean_token_accuracy": 0.11551203802227974,
|
||
|
|
"num_tokens": 10204174.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.71249418258667,
|
||
|
|
"epoch": 0.38375607832829545,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0001794129067388625,
|
||
|
|
"loss": 6.5345,
|
||
|
|
"mean_token_accuracy": 0.12417124882340431,
|
||
|
|
"num_tokens": 10222264.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.844579696655273,
|
||
|
|
"epoch": 0.3844131949007754,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.00017834772293882868,
|
||
|
|
"loss": 6.6768,
|
||
|
|
"mean_token_accuracy": 0.11600073277950287,
|
||
|
|
"num_tokens": 10239287.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.809977388381958,
|
||
|
|
"epoch": 0.3850703114732554,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.000177285188909794,
|
||
|
|
"loss": 6.6095,
|
||
|
|
"mean_token_accuracy": 0.11677622869610786,
|
||
|
|
"num_tokens": 10257324.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.794890117645264,
|
||
|
|
"epoch": 0.3857274280457353,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0001762253337816656,
|
||
|
|
"loss": 6.6432,
|
||
|
|
"mean_token_accuracy": 0.1195074126124382,
|
||
|
|
"num_tokens": 10273928.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.842269468307495,
|
||
|
|
"epoch": 0.38638454461821525,
|
||
|
|
"grad_norm": 0.78515625,
|
||
|
|
"learning_rate": 0.00017516818661090738,
|
||
|
|
"loss": 6.6056,
|
||
|
|
"mean_token_accuracy": 0.11565284952521324,
|
||
|
|
"num_tokens": 10292454.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.804778242111206,
|
||
|
|
"epoch": 0.3870416611906952,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0001741137763797428,
|
||
|
|
"loss": 6.7062,
|
||
|
|
"mean_token_accuracy": 0.1166993223130703,
|
||
|
|
"num_tokens": 10311454.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.789822196960449,
|
||
|
|
"epoch": 0.3876987777631752,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.00017306213199536115,
|
||
|
|
"loss": 6.6341,
|
||
|
|
"mean_token_accuracy": 0.11207709833979607,
|
||
|
|
"num_tokens": 10328163.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.75770411491394,
|
||
|
|
"epoch": 0.38835589433565515,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0001720132822891243,
|
||
|
|
"loss": 6.5186,
|
||
|
|
"mean_token_accuracy": 0.12132606357336044,
|
||
|
|
"num_tokens": 10345688.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.768074989318848,
|
||
|
|
"epoch": 0.3890130109081351,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0001709672560157769,
|
||
|
|
"loss": 6.6018,
|
||
|
|
"mean_token_accuracy": 0.11889762952923774,
|
||
|
|
"num_tokens": 10361924.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.758661699295044,
|
||
|
|
"epoch": 0.3896701274806151,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.00016992408185265758,
|
||
|
|
"loss": 6.5562,
|
||
|
|
"mean_token_accuracy": 0.12002668157219887,
|
||
|
|
"num_tokens": 10379031.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7115621089935305,
|
||
|
|
"epoch": 0.39032724405309505,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00016888378839891298,
|
||
|
|
"loss": 6.501,
|
||
|
|
"mean_token_accuracy": 0.1222024329006672,
|
||
|
|
"num_tokens": 10396575.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.673724842071533,
|
||
|
|
"epoch": 0.39098436062557496,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0001678464041747137,
|
||
|
|
"loss": 6.5362,
|
||
|
|
"mean_token_accuracy": 0.12940696999430656,
|
||
|
|
"num_tokens": 10414338.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6905763149261475,
|
||
|
|
"epoch": 0.3916414771980549,
|
||
|
|
"grad_norm": 0.75390625,
|
||
|
|
"learning_rate": 0.00016681195762047223,
|
||
|
|
"loss": 6.495,
|
||
|
|
"mean_token_accuracy": 0.1305336534976959,
|
||
|
|
"num_tokens": 10431704.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6907586574554445,
|
||
|
|
"epoch": 0.3922985937705349,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.00016578047709606337,
|
||
|
|
"loss": 6.456,
|
||
|
|
"mean_token_accuracy": 0.13183174803853034,
|
||
|
|
"num_tokens": 10449346.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.621657133102417,
|
||
|
|
"epoch": 0.39295571034301485,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.00016475199088004678,
|
||
|
|
"loss": 6.3424,
|
||
|
|
"mean_token_accuracy": 0.14128923416137695,
|
||
|
|
"num_tokens": 10468234.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.790988969802856,
|
||
|
|
"epoch": 0.3936128269154948,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.00016372652716889163,
|
||
|
|
"loss": 6.5694,
|
||
|
|
"mean_token_accuracy": 0.11570587977766991,
|
||
|
|
"num_tokens": 10485341.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.622765159606933,
|
||
|
|
"epoch": 0.3942699434879748,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0001627041140762035,
|
||
|
|
"loss": 6.3785,
|
||
|
|
"mean_token_accuracy": 0.13365377709269524,
|
||
|
|
"num_tokens": 10502412.0,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 4000,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1.4114521976832e+16,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|