7544 lines
204 KiB
JSON
7544 lines
204 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 3.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 750,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 0.563934326171875,
|
||
|
|
"epoch": 0.004,
|
||
|
|
"grad_norm": 5.719812068765233,
|
||
|
|
"learning_rate": 0.0,
|
||
|
|
"loss": 1.4166,
|
||
|
|
"mean_token_accuracy": 0.6491004461422563,
|
||
|
|
"num_tokens": 452051.0,
|
||
|
|
"step": 1
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.563568115234375,
|
||
|
|
"epoch": 0.008,
|
||
|
|
"grad_norm": 5.846193833605467,
|
||
|
|
"learning_rate": 5.263157894736843e-07,
|
||
|
|
"loss": 1.4069,
|
||
|
|
"mean_token_accuracy": 0.652142221108079,
|
||
|
|
"num_tokens": 895890.0,
|
||
|
|
"step": 2
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.574981689453125,
|
||
|
|
"epoch": 0.012,
|
||
|
|
"grad_norm": 5.920834503228064,
|
||
|
|
"learning_rate": 1.0526315789473685e-06,
|
||
|
|
"loss": 1.416,
|
||
|
|
"mean_token_accuracy": 0.6499378671869636,
|
||
|
|
"num_tokens": 1322220.0,
|
||
|
|
"step": 3
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5565185546875,
|
||
|
|
"epoch": 0.016,
|
||
|
|
"grad_norm": 5.770409716942624,
|
||
|
|
"learning_rate": 1.5789473684210526e-06,
|
||
|
|
"loss": 1.3881,
|
||
|
|
"mean_token_accuracy": 0.6594483349472284,
|
||
|
|
"num_tokens": 1770398.0,
|
||
|
|
"step": 4
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.577789306640625,
|
||
|
|
"epoch": 0.02,
|
||
|
|
"grad_norm": 5.617254110348697,
|
||
|
|
"learning_rate": 2.105263157894737e-06,
|
||
|
|
"loss": 1.38,
|
||
|
|
"mean_token_accuracy": 0.6590819656848907,
|
||
|
|
"num_tokens": 2187694.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.577392578125,
|
||
|
|
"epoch": 0.024,
|
||
|
|
"grad_norm": 5.458965290510816,
|
||
|
|
"learning_rate": 2.631578947368421e-06,
|
||
|
|
"loss": 1.3518,
|
||
|
|
"mean_token_accuracy": 0.6633852664381266,
|
||
|
|
"num_tokens": 2603855.0,
|
||
|
|
"step": 6
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.57147216796875,
|
||
|
|
"epoch": 0.028,
|
||
|
|
"grad_norm": 4.666244157179746,
|
||
|
|
"learning_rate": 3.157894736842105e-06,
|
||
|
|
"loss": 1.3251,
|
||
|
|
"mean_token_accuracy": 0.665694653056562,
|
||
|
|
"num_tokens": 3038521.0,
|
||
|
|
"step": 7
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.577362060546875,
|
||
|
|
"epoch": 0.032,
|
||
|
|
"grad_norm": 4.613154791901382,
|
||
|
|
"learning_rate": 3.6842105263157896e-06,
|
||
|
|
"loss": 1.3181,
|
||
|
|
"mean_token_accuracy": 0.666081240400672,
|
||
|
|
"num_tokens": 3467089.0,
|
||
|
|
"step": 8
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.567413330078125,
|
||
|
|
"epoch": 0.036,
|
||
|
|
"grad_norm": 4.430273311169495,
|
||
|
|
"learning_rate": 4.210526315789474e-06,
|
||
|
|
"loss": 1.2853,
|
||
|
|
"mean_token_accuracy": 0.6712537305429578,
|
||
|
|
"num_tokens": 3893210.0,
|
||
|
|
"step": 9
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5662841796875,
|
||
|
|
"epoch": 0.04,
|
||
|
|
"grad_norm": 3.872601118964935,
|
||
|
|
"learning_rate": 4.736842105263158e-06,
|
||
|
|
"loss": 1.1894,
|
||
|
|
"mean_token_accuracy": 0.6869636094197631,
|
||
|
|
"num_tokens": 4319594.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.576080322265625,
|
||
|
|
"epoch": 0.044,
|
||
|
|
"grad_norm": 3.357334154753164,
|
||
|
|
"learning_rate": 5.263157894736842e-06,
|
||
|
|
"loss": 1.1403,
|
||
|
|
"mean_token_accuracy": 0.6961174448952079,
|
||
|
|
"num_tokens": 4731512.0,
|
||
|
|
"step": 11
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5509033203125,
|
||
|
|
"epoch": 0.048,
|
||
|
|
"grad_norm": 3.180160983681141,
|
||
|
|
"learning_rate": 5.789473684210527e-06,
|
||
|
|
"loss": 1.1269,
|
||
|
|
"mean_token_accuracy": 0.6986328465864062,
|
||
|
|
"num_tokens": 5178419.0,
|
||
|
|
"step": 12
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.533203125,
|
||
|
|
"epoch": 0.052,
|
||
|
|
"grad_norm": 4.762032359993077,
|
||
|
|
"learning_rate": 6.31578947368421e-06,
|
||
|
|
"loss": 1.0576,
|
||
|
|
"mean_token_accuracy": 0.7113204095512629,
|
||
|
|
"num_tokens": 5618248.0,
|
||
|
|
"step": 13
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5516357421875,
|
||
|
|
"epoch": 0.056,
|
||
|
|
"grad_norm": 4.959757383982294,
|
||
|
|
"learning_rate": 6.842105263157896e-06,
|
||
|
|
"loss": 1.0229,
|
||
|
|
"mean_token_accuracy": 0.7213256992399693,
|
||
|
|
"num_tokens": 6022021.0,
|
||
|
|
"step": 14
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.53997802734375,
|
||
|
|
"epoch": 0.06,
|
||
|
|
"grad_norm": 4.013751051267831,
|
||
|
|
"learning_rate": 7.368421052631579e-06,
|
||
|
|
"loss": 1.0147,
|
||
|
|
"mean_token_accuracy": 0.7179919620975852,
|
||
|
|
"num_tokens": 6473004.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.535430908203125,
|
||
|
|
"epoch": 0.064,
|
||
|
|
"grad_norm": 3.437853792915007,
|
||
|
|
"learning_rate": 7.894736842105265e-06,
|
||
|
|
"loss": 0.9694,
|
||
|
|
"mean_token_accuracy": 0.7278459081426263,
|
||
|
|
"num_tokens": 6919063.0,
|
||
|
|
"step": 16
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.54180908203125,
|
||
|
|
"epoch": 0.068,
|
||
|
|
"grad_norm": 3.075292947583913,
|
||
|
|
"learning_rate": 8.421052631578948e-06,
|
||
|
|
"loss": 0.9171,
|
||
|
|
"mean_token_accuracy": 0.7417749995365739,
|
||
|
|
"num_tokens": 7368671.0,
|
||
|
|
"step": 17
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5355224609375,
|
||
|
|
"epoch": 0.072,
|
||
|
|
"grad_norm": 4.220217212783532,
|
||
|
|
"learning_rate": 8.947368421052632e-06,
|
||
|
|
"loss": 0.93,
|
||
|
|
"mean_token_accuracy": 0.7356898840516806,
|
||
|
|
"num_tokens": 7814021.0,
|
||
|
|
"step": 18
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.546661376953125,
|
||
|
|
"epoch": 0.076,
|
||
|
|
"grad_norm": 3.681586236229438,
|
||
|
|
"learning_rate": 9.473684210526315e-06,
|
||
|
|
"loss": 0.9198,
|
||
|
|
"mean_token_accuracy": 0.7357039181515574,
|
||
|
|
"num_tokens": 8261483.0,
|
||
|
|
"step": 19
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5501708984375,
|
||
|
|
"epoch": 0.08,
|
||
|
|
"grad_norm": 2.8706880539249773,
|
||
|
|
"learning_rate": 1e-05,
|
||
|
|
"loss": 0.8896,
|
||
|
|
"mean_token_accuracy": 0.7432091468945146,
|
||
|
|
"num_tokens": 8679549.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.541046142578125,
|
||
|
|
"epoch": 0.084,
|
||
|
|
"grad_norm": 2.703917360443058,
|
||
|
|
"learning_rate": 1.0526315789473684e-05,
|
||
|
|
"loss": 0.8654,
|
||
|
|
"mean_token_accuracy": 0.7487076604738832,
|
||
|
|
"num_tokens": 9120646.0,
|
||
|
|
"step": 21
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.539031982421875,
|
||
|
|
"epoch": 0.088,
|
||
|
|
"grad_norm": 2.819653296931558,
|
||
|
|
"learning_rate": 1.105263157894737e-05,
|
||
|
|
"loss": 0.8317,
|
||
|
|
"mean_token_accuracy": 0.7593385186046362,
|
||
|
|
"num_tokens": 9549355.0,
|
||
|
|
"step": 22
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5355224609375,
|
||
|
|
"epoch": 0.092,
|
||
|
|
"grad_norm": 2.6077443805364173,
|
||
|
|
"learning_rate": 1.1578947368421053e-05,
|
||
|
|
"loss": 0.8435,
|
||
|
|
"mean_token_accuracy": 0.7541799638420343,
|
||
|
|
"num_tokens": 9986936.0,
|
||
|
|
"step": 23
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.521728515625,
|
||
|
|
"epoch": 0.096,
|
||
|
|
"grad_norm": 2.1546071370731186,
|
||
|
|
"learning_rate": 1.2105263157894737e-05,
|
||
|
|
"loss": 0.8023,
|
||
|
|
"mean_token_accuracy": 0.7640062151476741,
|
||
|
|
"num_tokens": 10429772.0,
|
||
|
|
"step": 24
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5389404296875,
|
||
|
|
"epoch": 0.1,
|
||
|
|
"grad_norm": 2.2112379790866497,
|
||
|
|
"learning_rate": 1.263157894736842e-05,
|
||
|
|
"loss": 0.791,
|
||
|
|
"mean_token_accuracy": 0.7672639861702919,
|
||
|
|
"num_tokens": 10857794.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.52618408203125,
|
||
|
|
"epoch": 0.104,
|
||
|
|
"grad_norm": 2.266197057923945,
|
||
|
|
"learning_rate": 1.3157894736842108e-05,
|
||
|
|
"loss": 0.7737,
|
||
|
|
"mean_token_accuracy": 0.76796246599406,
|
||
|
|
"num_tokens": 11287814.0,
|
||
|
|
"step": 26
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.51788330078125,
|
||
|
|
"epoch": 0.108,
|
||
|
|
"grad_norm": 2.150200842677149,
|
||
|
|
"learning_rate": 1.3684210526315791e-05,
|
||
|
|
"loss": 0.7555,
|
||
|
|
"mean_token_accuracy": 0.7700982708483934,
|
||
|
|
"num_tokens": 11703374.0,
|
||
|
|
"step": 27
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.51025390625,
|
||
|
|
"epoch": 0.112,
|
||
|
|
"grad_norm": 1.6980406851322742,
|
||
|
|
"learning_rate": 1.4210526315789475e-05,
|
||
|
|
"loss": 0.7464,
|
||
|
|
"mean_token_accuracy": 0.7748355558142066,
|
||
|
|
"num_tokens": 12138427.0,
|
||
|
|
"step": 28
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.51580810546875,
|
||
|
|
"epoch": 0.116,
|
||
|
|
"grad_norm": 1.6457348788372888,
|
||
|
|
"learning_rate": 1.4736842105263159e-05,
|
||
|
|
"loss": 0.7367,
|
||
|
|
"mean_token_accuracy": 0.7755188457667828,
|
||
|
|
"num_tokens": 12556209.0,
|
||
|
|
"step": 29
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.513885498046875,
|
||
|
|
"epoch": 0.12,
|
||
|
|
"grad_norm": 1.7862062243377317,
|
||
|
|
"learning_rate": 1.5263157894736846e-05,
|
||
|
|
"loss": 0.7232,
|
||
|
|
"mean_token_accuracy": 0.7800800753757358,
|
||
|
|
"num_tokens": 12991506.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.506622314453125,
|
||
|
|
"epoch": 0.124,
|
||
|
|
"grad_norm": 2.143966995691478,
|
||
|
|
"learning_rate": 1.578947368421053e-05,
|
||
|
|
"loss": 0.7307,
|
||
|
|
"mean_token_accuracy": 0.778203465975821,
|
||
|
|
"num_tokens": 13449907.0,
|
||
|
|
"step": 31
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.51611328125,
|
||
|
|
"epoch": 0.128,
|
||
|
|
"grad_norm": 1.8506857448497256,
|
||
|
|
"learning_rate": 1.6315789473684213e-05,
|
||
|
|
"loss": 0.7072,
|
||
|
|
"mean_token_accuracy": 0.7812101496383548,
|
||
|
|
"num_tokens": 13870914.0,
|
||
|
|
"step": 32
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4964599609375,
|
||
|
|
"epoch": 0.132,
|
||
|
|
"grad_norm": 1.790034164053607,
|
||
|
|
"learning_rate": 1.6842105263157896e-05,
|
||
|
|
"loss": 0.7021,
|
||
|
|
"mean_token_accuracy": 0.7827972108498216,
|
||
|
|
"num_tokens": 14315654.0,
|
||
|
|
"step": 33
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.507720947265625,
|
||
|
|
"epoch": 0.136,
|
||
|
|
"grad_norm": 1.6626325871093515,
|
||
|
|
"learning_rate": 1.736842105263158e-05,
|
||
|
|
"loss": 0.6913,
|
||
|
|
"mean_token_accuracy": 0.7875423710793257,
|
||
|
|
"num_tokens": 14755772.0,
|
||
|
|
"step": 34
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.49713134765625,
|
||
|
|
"epoch": 0.14,
|
||
|
|
"grad_norm": 1.7524548177487227,
|
||
|
|
"learning_rate": 1.7894736842105264e-05,
|
||
|
|
"loss": 0.6719,
|
||
|
|
"mean_token_accuracy": 0.7920364886522293,
|
||
|
|
"num_tokens": 15186450.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.502410888671875,
|
||
|
|
"epoch": 0.144,
|
||
|
|
"grad_norm": 1.6136196416688096,
|
||
|
|
"learning_rate": 1.8421052631578947e-05,
|
||
|
|
"loss": 0.6929,
|
||
|
|
"mean_token_accuracy": 0.7869782624766231,
|
||
|
|
"num_tokens": 15625710.0,
|
||
|
|
"step": 36
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.503570556640625,
|
||
|
|
"epoch": 0.148,
|
||
|
|
"grad_norm": 1.5074507504888874,
|
||
|
|
"learning_rate": 1.894736842105263e-05,
|
||
|
|
"loss": 0.6652,
|
||
|
|
"mean_token_accuracy": 0.7915960419923067,
|
||
|
|
"num_tokens": 16045181.0,
|
||
|
|
"step": 37
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.492889404296875,
|
||
|
|
"epoch": 0.152,
|
||
|
|
"grad_norm": 1.5649053357685532,
|
||
|
|
"learning_rate": 1.9473684210526318e-05,
|
||
|
|
"loss": 0.6781,
|
||
|
|
"mean_token_accuracy": 0.7892287913709879,
|
||
|
|
"num_tokens": 16495178.0,
|
||
|
|
"step": 38
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.504425048828125,
|
||
|
|
"epoch": 0.156,
|
||
|
|
"grad_norm": 1.596203156077193,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.6535,
|
||
|
|
"mean_token_accuracy": 0.79360440839082,
|
||
|
|
"num_tokens": 16927012.0,
|
||
|
|
"step": 39
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.484375,
|
||
|
|
"epoch": 0.16,
|
||
|
|
"grad_norm": 1.5939241668806758,
|
||
|
|
"learning_rate": 1.9999902656029183e-05,
|
||
|
|
"loss": 0.6447,
|
||
|
|
"mean_token_accuracy": 0.7983620716258883,
|
||
|
|
"num_tokens": 17374173.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4970703125,
|
||
|
|
"epoch": 0.164,
|
||
|
|
"grad_norm": 1.593649812276319,
|
||
|
|
"learning_rate": 1.999961062601189e-05,
|
||
|
|
"loss": 0.6559,
|
||
|
|
"mean_token_accuracy": 0.7953264936804771,
|
||
|
|
"num_tokens": 17796443.0,
|
||
|
|
"step": 41
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.505279541015625,
|
||
|
|
"epoch": 0.168,
|
||
|
|
"grad_norm": 1.7551586936569723,
|
||
|
|
"learning_rate": 1.9999123915633606e-05,
|
||
|
|
"loss": 0.6549,
|
||
|
|
"mean_token_accuracy": 0.7932727839797735,
|
||
|
|
"num_tokens": 18217985.0,
|
||
|
|
"step": 42
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.48822021484375,
|
||
|
|
"epoch": 0.172,
|
||
|
|
"grad_norm": 1.5878932028353792,
|
||
|
|
"learning_rate": 1.9998442534369986e-05,
|
||
|
|
"loss": 0.6316,
|
||
|
|
"mean_token_accuracy": 0.7986164651811123,
|
||
|
|
"num_tokens": 18664374.0,
|
||
|
|
"step": 43
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5067138671875,
|
||
|
|
"epoch": 0.176,
|
||
|
|
"grad_norm": 1.5103599378711612,
|
||
|
|
"learning_rate": 1.9997566495486705e-05,
|
||
|
|
"loss": 0.6303,
|
||
|
|
"mean_token_accuracy": 0.7999572716653347,
|
||
|
|
"num_tokens": 19082152.0,
|
||
|
|
"step": 44
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.48748779296875,
|
||
|
|
"epoch": 0.18,
|
||
|
|
"grad_norm": 1.7929398525282843,
|
||
|
|
"learning_rate": 1.999649581603919e-05,
|
||
|
|
"loss": 0.6342,
|
||
|
|
"mean_token_accuracy": 0.803133218549192,
|
||
|
|
"num_tokens": 19510589.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.499176025390625,
|
||
|
|
"epoch": 0.184,
|
||
|
|
"grad_norm": 1.8028740897912008,
|
||
|
|
"learning_rate": 1.999523051687226e-05,
|
||
|
|
"loss": 0.626,
|
||
|
|
"mean_token_accuracy": 0.8030202044174075,
|
||
|
|
"num_tokens": 19936054.0,
|
||
|
|
"step": 46
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.485748291015625,
|
||
|
|
"epoch": 0.188,
|
||
|
|
"grad_norm": 1.670191271839292,
|
||
|
|
"learning_rate": 1.9993770622619784e-05,
|
||
|
|
"loss": 0.6327,
|
||
|
|
"mean_token_accuracy": 0.7978525487706065,
|
||
|
|
"num_tokens": 20381264.0,
|
||
|
|
"step": 47
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.49468994140625,
|
||
|
|
"epoch": 0.192,
|
||
|
|
"grad_norm": 1.6466166924433663,
|
||
|
|
"learning_rate": 1.9992116161704134e-05,
|
||
|
|
"loss": 0.6125,
|
||
|
|
"mean_token_accuracy": 0.8037526048719883,
|
||
|
|
"num_tokens": 20806445.0,
|
||
|
|
"step": 48
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.485321044921875,
|
||
|
|
"epoch": 0.196,
|
||
|
|
"grad_norm": 1.5586257107615933,
|
||
|
|
"learning_rate": 1.9990267166335665e-05,
|
||
|
|
"loss": 0.6166,
|
||
|
|
"mean_token_accuracy": 0.8023359170183539,
|
||
|
|
"num_tokens": 21260045.0,
|
||
|
|
"step": 49
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.49078369140625,
|
||
|
|
"epoch": 0.2,
|
||
|
|
"grad_norm": 1.6029319673713698,
|
||
|
|
"learning_rate": 1.9988223672512097e-05,
|
||
|
|
"loss": 0.6011,
|
||
|
|
"mean_token_accuracy": 0.8067194325849414,
|
||
|
|
"num_tokens": 21697763.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.48974609375,
|
||
|
|
"epoch": 0.204,
|
||
|
|
"grad_norm": 1.3690422379433078,
|
||
|
|
"learning_rate": 1.9985985720017786e-05,
|
||
|
|
"loss": 0.6052,
|
||
|
|
"mean_token_accuracy": 0.8041236568242311,
|
||
|
|
"num_tokens": 22119216.0,
|
||
|
|
"step": 51
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.472076416015625,
|
||
|
|
"epoch": 0.208,
|
||
|
|
"grad_norm": 1.4922129221931275,
|
||
|
|
"learning_rate": 1.9983553352422966e-05,
|
||
|
|
"loss": 0.6031,
|
||
|
|
"mean_token_accuracy": 0.8054024120792747,
|
||
|
|
"num_tokens": 22563927.0,
|
||
|
|
"step": 52
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.486785888671875,
|
||
|
|
"epoch": 0.212,
|
||
|
|
"grad_norm": 1.5653387141706678,
|
||
|
|
"learning_rate": 1.9980926617082904e-05,
|
||
|
|
"loss": 0.6073,
|
||
|
|
"mean_token_accuracy": 0.8049731086939573,
|
||
|
|
"num_tokens": 22986329.0,
|
||
|
|
"step": 53
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.490081787109375,
|
||
|
|
"epoch": 0.216,
|
||
|
|
"grad_norm": 1.552590904624544,
|
||
|
|
"learning_rate": 1.997810556513697e-05,
|
||
|
|
"loss": 0.6082,
|
||
|
|
"mean_token_accuracy": 0.8048472162336111,
|
||
|
|
"num_tokens": 23408332.0,
|
||
|
|
"step": 54
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.484527587890625,
|
||
|
|
"epoch": 0.22,
|
||
|
|
"grad_norm": 1.4870393630435006,
|
||
|
|
"learning_rate": 1.9975090251507637e-05,
|
||
|
|
"loss": 0.6056,
|
||
|
|
"mean_token_accuracy": 0.8051685085520148,
|
||
|
|
"num_tokens": 23849559.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.482025146484375,
|
||
|
|
"epoch": 0.224,
|
||
|
|
"grad_norm": 1.435453082817674,
|
||
|
|
"learning_rate": 1.997188073489944e-05,
|
||
|
|
"loss": 0.5905,
|
||
|
|
"mean_token_accuracy": 0.8096179841086268,
|
||
|
|
"num_tokens": 24273319.0,
|
||
|
|
"step": 56
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.469451904296875,
|
||
|
|
"epoch": 0.228,
|
||
|
|
"grad_norm": 1.4698706486665516,
|
||
|
|
"learning_rate": 1.996847707779778e-05,
|
||
|
|
"loss": 0.6043,
|
||
|
|
"mean_token_accuracy": 0.8078873148187995,
|
||
|
|
"num_tokens": 24720831.0,
|
||
|
|
"step": 57
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.47918701171875,
|
||
|
|
"epoch": 0.232,
|
||
|
|
"grad_norm": 1.5513993433856552,
|
||
|
|
"learning_rate": 1.996487934646777e-05,
|
||
|
|
"loss": 0.5837,
|
||
|
|
"mean_token_accuracy": 0.8120508277788758,
|
||
|
|
"num_tokens": 25138664.0,
|
||
|
|
"step": 58
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.477783203125,
|
||
|
|
"epoch": 0.236,
|
||
|
|
"grad_norm": 1.4361244238681858,
|
||
|
|
"learning_rate": 1.9961087610952893e-05,
|
||
|
|
"loss": 0.5906,
|
||
|
|
"mean_token_accuracy": 0.8100186409428716,
|
||
|
|
"num_tokens": 25584697.0,
|
||
|
|
"step": 59
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.488372802734375,
|
||
|
|
"epoch": 0.24,
|
||
|
|
"grad_norm": 1.6828511602647536,
|
||
|
|
"learning_rate": 1.995710194507367e-05,
|
||
|
|
"loss": 0.5773,
|
||
|
|
"mean_token_accuracy": 0.8114486206322908,
|
||
|
|
"num_tokens": 25995526.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.478759765625,
|
||
|
|
"epoch": 0.244,
|
||
|
|
"grad_norm": 1.6293297322851392,
|
||
|
|
"learning_rate": 1.9952922426426208e-05,
|
||
|
|
"loss": 0.5815,
|
||
|
|
"mean_token_accuracy": 0.8117062347009778,
|
||
|
|
"num_tokens": 26436029.0,
|
||
|
|
"step": 61
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.497344970703125,
|
||
|
|
"epoch": 0.248,
|
||
|
|
"grad_norm": 1.7039421480122217,
|
||
|
|
"learning_rate": 1.9948549136380698e-05,
|
||
|
|
"loss": 0.5769,
|
||
|
|
"mean_token_accuracy": 0.8106265868991613,
|
||
|
|
"num_tokens": 26853573.0,
|
||
|
|
"step": 62
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.479888916015625,
|
||
|
|
"epoch": 0.252,
|
||
|
|
"grad_norm": 1.2788852830756723,
|
||
|
|
"learning_rate": 1.9943982160079823e-05,
|
||
|
|
"loss": 0.5841,
|
||
|
|
"mean_token_accuracy": 0.8100276347249746,
|
||
|
|
"num_tokens": 27302940.0,
|
||
|
|
"step": 63
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.475433349609375,
|
||
|
|
"epoch": 0.256,
|
||
|
|
"grad_norm": 1.4935703775206974,
|
||
|
|
"learning_rate": 1.99392215864371e-05,
|
||
|
|
"loss": 0.5891,
|
||
|
|
"mean_token_accuracy": 0.809790151193738,
|
||
|
|
"num_tokens": 27758121.0,
|
||
|
|
"step": 64
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.483612060546875,
|
||
|
|
"epoch": 0.26,
|
||
|
|
"grad_norm": 1.320605391382422,
|
||
|
|
"learning_rate": 1.9934267508135163e-05,
|
||
|
|
"loss": 0.5618,
|
||
|
|
"mean_token_accuracy": 0.8154447739943862,
|
||
|
|
"num_tokens": 28167303.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4771728515625,
|
||
|
|
"epoch": 0.264,
|
||
|
|
"grad_norm": 1.352642694825481,
|
||
|
|
"learning_rate": 1.9929120021623945e-05,
|
||
|
|
"loss": 0.5432,
|
||
|
|
"mean_token_accuracy": 0.8210669262334704,
|
||
|
|
"num_tokens": 28580032.0,
|
||
|
|
"step": 66
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.477630615234375,
|
||
|
|
"epoch": 0.268,
|
||
|
|
"grad_norm": 1.3542769876185135,
|
||
|
|
"learning_rate": 1.9923779227118793e-05,
|
||
|
|
"loss": 0.5555,
|
||
|
|
"mean_token_accuracy": 0.8154290318489075,
|
||
|
|
"num_tokens": 29001759.0,
|
||
|
|
"step": 67
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.48333740234375,
|
||
|
|
"epoch": 0.272,
|
||
|
|
"grad_norm": 1.226814453219975,
|
||
|
|
"learning_rate": 1.991824522859854e-05,
|
||
|
|
"loss": 0.5566,
|
||
|
|
"mean_token_accuracy": 0.8191100442782044,
|
||
|
|
"num_tokens": 29420681.0,
|
||
|
|
"step": 68
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.48980712890625,
|
||
|
|
"epoch": 0.276,
|
||
|
|
"grad_norm": 1.7222393360747934,
|
||
|
|
"learning_rate": 1.9912518133803466e-05,
|
||
|
|
"loss": 0.578,
|
||
|
|
"mean_token_accuracy": 0.8095786944031715,
|
||
|
|
"num_tokens": 29842792.0,
|
||
|
|
"step": 69
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.48162841796875,
|
||
|
|
"epoch": 0.28,
|
||
|
|
"grad_norm": 1.2956461664877132,
|
||
|
|
"learning_rate": 1.9906598054233197e-05,
|
||
|
|
"loss": 0.564,
|
||
|
|
"mean_token_accuracy": 0.814757970161736,
|
||
|
|
"num_tokens": 30251877.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.480072021484375,
|
||
|
|
"epoch": 0.284,
|
||
|
|
"grad_norm": 1.178124769611262,
|
||
|
|
"learning_rate": 1.9900485105144544e-05,
|
||
|
|
"loss": 0.5748,
|
||
|
|
"mean_token_accuracy": 0.8113822266459465,
|
||
|
|
"num_tokens": 30692814.0,
|
||
|
|
"step": 71
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.477935791015625,
|
||
|
|
"epoch": 0.288,
|
||
|
|
"grad_norm": 1.2781824113249132,
|
||
|
|
"learning_rate": 1.989417940554926e-05,
|
||
|
|
"loss": 0.5642,
|
||
|
|
"mean_token_accuracy": 0.8156066592782736,
|
||
|
|
"num_tokens": 31141419.0,
|
||
|
|
"step": 72
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4847412109375,
|
||
|
|
"epoch": 0.292,
|
||
|
|
"grad_norm": 1.5450596158916734,
|
||
|
|
"learning_rate": 1.9887681078211706e-05,
|
||
|
|
"loss": 0.58,
|
||
|
|
"mean_token_accuracy": 0.8094583582133055,
|
||
|
|
"num_tokens": 31567997.0,
|
||
|
|
"step": 73
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.48394775390625,
|
||
|
|
"epoch": 0.296,
|
||
|
|
"grad_norm": 1.1038048333539334,
|
||
|
|
"learning_rate": 1.9880990249646482e-05,
|
||
|
|
"loss": 0.5785,
|
||
|
|
"mean_token_accuracy": 0.8123246096074581,
|
||
|
|
"num_tokens": 32003793.0,
|
||
|
|
"step": 74
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.476348876953125,
|
||
|
|
"epoch": 0.3,
|
||
|
|
"grad_norm": 1.4489866691023914,
|
||
|
|
"learning_rate": 1.9874107050115954e-05,
|
||
|
|
"loss": 0.5624,
|
||
|
|
"mean_token_accuracy": 0.814401812851429,
|
||
|
|
"num_tokens": 32428075.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.48455810546875,
|
||
|
|
"epoch": 0.304,
|
||
|
|
"grad_norm": 1.3987253769987265,
|
||
|
|
"learning_rate": 1.9867031613627712e-05,
|
||
|
|
"loss": 0.5537,
|
||
|
|
"mean_token_accuracy": 0.8153460891917348,
|
||
|
|
"num_tokens": 32839359.0,
|
||
|
|
"step": 76
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4666748046875,
|
||
|
|
"epoch": 0.308,
|
||
|
|
"grad_norm": 1.314619438229883,
|
||
|
|
"learning_rate": 1.985976407793198e-05,
|
||
|
|
"loss": 0.5603,
|
||
|
|
"mean_token_accuracy": 0.8185823541134596,
|
||
|
|
"num_tokens": 33273317.0,
|
||
|
|
"step": 77
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.473663330078125,
|
||
|
|
"epoch": 0.312,
|
||
|
|
"grad_norm": 1.8426884636296479,
|
||
|
|
"learning_rate": 1.9852304584518904e-05,
|
||
|
|
"loss": 0.5523,
|
||
|
|
"mean_token_accuracy": 0.8174495724961162,
|
||
|
|
"num_tokens": 33681563.0,
|
||
|
|
"step": 78
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46795654296875,
|
||
|
|
"epoch": 0.316,
|
||
|
|
"grad_norm": 1.3442854640551003,
|
||
|
|
"learning_rate": 1.9844653278615836e-05,
|
||
|
|
"loss": 0.5706,
|
||
|
|
"mean_token_accuracy": 0.8139378279447556,
|
||
|
|
"num_tokens": 34112434.0,
|
||
|
|
"step": 79
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.465911865234375,
|
||
|
|
"epoch": 0.32,
|
||
|
|
"grad_norm": 1.2842573212277777,
|
||
|
|
"learning_rate": 1.9836810309184468e-05,
|
||
|
|
"loss": 0.5537,
|
||
|
|
"mean_token_accuracy": 0.8158122533932328,
|
||
|
|
"num_tokens": 34542498.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.47161865234375,
|
||
|
|
"epoch": 0.324,
|
||
|
|
"grad_norm": 1.2749265611296718,
|
||
|
|
"learning_rate": 1.9828775828917966e-05,
|
||
|
|
"loss": 0.5728,
|
||
|
|
"mean_token_accuracy": 0.8130983002483845,
|
||
|
|
"num_tokens": 34975109.0,
|
||
|
|
"step": 81
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.467437744140625,
|
||
|
|
"epoch": 0.328,
|
||
|
|
"grad_norm": 1.3030140136994661,
|
||
|
|
"learning_rate": 1.9820549994237965e-05,
|
||
|
|
"loss": 0.534,
|
||
|
|
"mean_token_accuracy": 0.8220111019909382,
|
||
|
|
"num_tokens": 35402123.0,
|
||
|
|
"step": 82
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.48553466796875,
|
||
|
|
"epoch": 0.332,
|
||
|
|
"grad_norm": 1.1847106962537846,
|
||
|
|
"learning_rate": 1.9812132965291548e-05,
|
||
|
|
"loss": 0.5657,
|
||
|
|
"mean_token_accuracy": 0.815069598145783,
|
||
|
|
"num_tokens": 35809058.0,
|
||
|
|
"step": 83
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.47467041015625,
|
||
|
|
"epoch": 0.336,
|
||
|
|
"grad_norm": 1.4683448312215357,
|
||
|
|
"learning_rate": 1.980352490594812e-05,
|
||
|
|
"loss": 0.57,
|
||
|
|
"mean_token_accuracy": 0.8136926973238587,
|
||
|
|
"num_tokens": 36235222.0,
|
||
|
|
"step": 84
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.474456787109375,
|
||
|
|
"epoch": 0.34,
|
||
|
|
"grad_norm": 1.4812782065474495,
|
||
|
|
"learning_rate": 1.979472598379622e-05,
|
||
|
|
"loss": 0.5621,
|
||
|
|
"mean_token_accuracy": 0.815330064855516,
|
||
|
|
"num_tokens": 36666833.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.470184326171875,
|
||
|
|
"epoch": 0.344,
|
||
|
|
"grad_norm": 1.1710183846896318,
|
||
|
|
"learning_rate": 1.978573637014025e-05,
|
||
|
|
"loss": 0.5552,
|
||
|
|
"mean_token_accuracy": 0.8170776553452015,
|
||
|
|
"num_tokens": 37108949.0,
|
||
|
|
"step": 86
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.453369140625,
|
||
|
|
"epoch": 0.348,
|
||
|
|
"grad_norm": 1.2124898801856632,
|
||
|
|
"learning_rate": 1.9776556239997146e-05,
|
||
|
|
"loss": 0.5433,
|
||
|
|
"mean_token_accuracy": 0.8192396052181721,
|
||
|
|
"num_tokens": 37523564.0,
|
||
|
|
"step": 87
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4451904296875,
|
||
|
|
"epoch": 0.352,
|
||
|
|
"grad_norm": 1.1668973505032287,
|
||
|
|
"learning_rate": 1.9767185772092973e-05,
|
||
|
|
"loss": 0.5488,
|
||
|
|
"mean_token_accuracy": 0.8205649498850107,
|
||
|
|
"num_tokens": 37960115.0,
|
||
|
|
"step": 88
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.450469970703125,
|
||
|
|
"epoch": 0.356,
|
||
|
|
"grad_norm": 1.2989760167358035,
|
||
|
|
"learning_rate": 1.9757625148859444e-05,
|
||
|
|
"loss": 0.5625,
|
||
|
|
"mean_token_accuracy": 0.8144238376989961,
|
||
|
|
"num_tokens": 38397911.0,
|
||
|
|
"step": 89
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.453887939453125,
|
||
|
|
"epoch": 0.36,
|
||
|
|
"grad_norm": 1.3061696531580331,
|
||
|
|
"learning_rate": 1.9747874556430363e-05,
|
||
|
|
"loss": 0.559,
|
||
|
|
"mean_token_accuracy": 0.8167312312871218,
|
||
|
|
"num_tokens": 38841950.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.463531494140625,
|
||
|
|
"epoch": 0.364,
|
||
|
|
"grad_norm": 1.2276905960702014,
|
||
|
|
"learning_rate": 1.9737934184638006e-05,
|
||
|
|
"loss": 0.5535,
|
||
|
|
"mean_token_accuracy": 0.817347701638937,
|
||
|
|
"num_tokens": 39272992.0,
|
||
|
|
"step": 91
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.458648681640625,
|
||
|
|
"epoch": 0.368,
|
||
|
|
"grad_norm": 1.2136735426148433,
|
||
|
|
"learning_rate": 1.9727804227009426e-05,
|
||
|
|
"loss": 0.5418,
|
||
|
|
"mean_token_accuracy": 0.8182446910068393,
|
||
|
|
"num_tokens": 39697176.0,
|
||
|
|
"step": 92
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.463958740234375,
|
||
|
|
"epoch": 0.372,
|
||
|
|
"grad_norm": 1.286386291575192,
|
||
|
|
"learning_rate": 1.9717484880762685e-05,
|
||
|
|
"loss": 0.5528,
|
||
|
|
"mean_token_accuracy": 0.8148206798359752,
|
||
|
|
"num_tokens": 40130130.0,
|
||
|
|
"step": 93
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.462646484375,
|
||
|
|
"epoch": 0.376,
|
||
|
|
"grad_norm": 1.1855717940150183,
|
||
|
|
"learning_rate": 1.9706976346803007e-05,
|
||
|
|
"loss": 0.5434,
|
||
|
|
"mean_token_accuracy": 0.8216626970097423,
|
||
|
|
"num_tokens": 40545367.0,
|
||
|
|
"step": 94
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.457733154296875,
|
||
|
|
"epoch": 0.38,
|
||
|
|
"grad_norm": 1.3760749134989956,
|
||
|
|
"learning_rate": 1.9696278829718882e-05,
|
||
|
|
"loss": 0.5331,
|
||
|
|
"mean_token_accuracy": 0.8223517127335072,
|
||
|
|
"num_tokens": 40964521.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4666748046875,
|
||
|
|
"epoch": 0.384,
|
||
|
|
"grad_norm": 1.1571483673841827,
|
||
|
|
"learning_rate": 1.9685392537778065e-05,
|
||
|
|
"loss": 0.5251,
|
||
|
|
"mean_token_accuracy": 0.8252335842698812,
|
||
|
|
"num_tokens": 41366901.0,
|
||
|
|
"step": 96
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.461944580078125,
|
||
|
|
"epoch": 0.388,
|
||
|
|
"grad_norm": 2.0469761772765405,
|
||
|
|
"learning_rate": 1.9674317682923535e-05,
|
||
|
|
"loss": 0.5263,
|
||
|
|
"mean_token_accuracy": 0.8254131898283958,
|
||
|
|
"num_tokens": 41793174.0,
|
||
|
|
"step": 97
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.463348388671875,
|
||
|
|
"epoch": 0.392,
|
||
|
|
"grad_norm": 1.3375127045518034,
|
||
|
|
"learning_rate": 1.9663054480769354e-05,
|
||
|
|
"loss": 0.5519,
|
||
|
|
"mean_token_accuracy": 0.8164043603464961,
|
||
|
|
"num_tokens": 42227685.0,
|
||
|
|
"step": 98
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46734619140625,
|
||
|
|
"epoch": 0.396,
|
||
|
|
"grad_norm": 1.2387807350199211,
|
||
|
|
"learning_rate": 1.9651603150596497e-05,
|
||
|
|
"loss": 0.5358,
|
||
|
|
"mean_token_accuracy": 0.822145925834775,
|
||
|
|
"num_tokens": 42642757.0,
|
||
|
|
"step": 99
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.463531494140625,
|
||
|
|
"epoch": 0.4,
|
||
|
|
"grad_norm": 1.3700084142763935,
|
||
|
|
"learning_rate": 1.9639963915348547e-05,
|
||
|
|
"loss": 0.5696,
|
||
|
|
"mean_token_accuracy": 0.8138548666611314,
|
||
|
|
"num_tokens": 43096829.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.467071533203125,
|
||
|
|
"epoch": 0.404,
|
||
|
|
"grad_norm": 1.0885875044592115,
|
||
|
|
"learning_rate": 1.9628137001627385e-05,
|
||
|
|
"loss": 0.5621,
|
||
|
|
"mean_token_accuracy": 0.813389697112143,
|
||
|
|
"num_tokens": 43545727.0,
|
||
|
|
"step": 101
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.472381591796875,
|
||
|
|
"epoch": 0.408,
|
||
|
|
"grad_norm": 1.1886417761568062,
|
||
|
|
"learning_rate": 1.9616122639688752e-05,
|
||
|
|
"loss": 0.5453,
|
||
|
|
"mean_token_accuracy": 0.8214895911514759,
|
||
|
|
"num_tokens": 43977418.0,
|
||
|
|
"step": 102
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.472015380859375,
|
||
|
|
"epoch": 0.412,
|
||
|
|
"grad_norm": 1.0696989841570876,
|
||
|
|
"learning_rate": 1.9603921063437795e-05,
|
||
|
|
"loss": 0.5265,
|
||
|
|
"mean_token_accuracy": 0.8257799986749887,
|
||
|
|
"num_tokens": 44413391.0,
|
||
|
|
"step": 103
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.465576171875,
|
||
|
|
"epoch": 0.416,
|
||
|
|
"grad_norm": 1.154202448514392,
|
||
|
|
"learning_rate": 1.9591532510424485e-05,
|
||
|
|
"loss": 0.5408,
|
||
|
|
"mean_token_accuracy": 0.8214380610734224,
|
||
|
|
"num_tokens": 44858426.0,
|
||
|
|
"step": 104
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4622802734375,
|
||
|
|
"epoch": 0.42,
|
||
|
|
"grad_norm": 1.0651389108901288,
|
||
|
|
"learning_rate": 1.9578957221839016e-05,
|
||
|
|
"loss": 0.5469,
|
||
|
|
"mean_token_accuracy": 0.8193699764087796,
|
||
|
|
"num_tokens": 45315027.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46575927734375,
|
||
|
|
"epoch": 0.424,
|
||
|
|
"grad_norm": 1.0358158864990028,
|
||
|
|
"learning_rate": 1.9566195442507087e-05,
|
||
|
|
"loss": 0.5244,
|
||
|
|
"mean_token_accuracy": 0.8261851761490107,
|
||
|
|
"num_tokens": 45736680.0,
|
||
|
|
"step": 106
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46759033203125,
|
||
|
|
"epoch": 0.428,
|
||
|
|
"grad_norm": 1.1452299020768106,
|
||
|
|
"learning_rate": 1.955324742088516e-05,
|
||
|
|
"loss": 0.5462,
|
||
|
|
"mean_token_accuracy": 0.8194631757214665,
|
||
|
|
"num_tokens": 46171524.0,
|
||
|
|
"step": 107
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.47723388671875,
|
||
|
|
"epoch": 0.432,
|
||
|
|
"grad_norm": 1.0627473286915439,
|
||
|
|
"learning_rate": 1.9540113409055593e-05,
|
||
|
|
"loss": 0.5285,
|
||
|
|
"mean_token_accuracy": 0.8242058157920837,
|
||
|
|
"num_tokens": 46595722.0,
|
||
|
|
"step": 108
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.47039794921875,
|
||
|
|
"epoch": 0.436,
|
||
|
|
"grad_norm": 1.1381389505969772,
|
||
|
|
"learning_rate": 1.9526793662721768e-05,
|
||
|
|
"loss": 0.5311,
|
||
|
|
"mean_token_accuracy": 0.8229827443137765,
|
||
|
|
"num_tokens": 47006343.0,
|
||
|
|
"step": 109
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.479217529296875,
|
||
|
|
"epoch": 0.44,
|
||
|
|
"grad_norm": 1.131794811381897,
|
||
|
|
"learning_rate": 1.9513288441203083e-05,
|
||
|
|
"loss": 0.5426,
|
||
|
|
"mean_token_accuracy": 0.8203764734789729,
|
||
|
|
"num_tokens": 47417426.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.475341796875,
|
||
|
|
"epoch": 0.444,
|
||
|
|
"grad_norm": 1.154605479621705,
|
||
|
|
"learning_rate": 1.949959800742991e-05,
|
||
|
|
"loss": 0.5283,
|
||
|
|
"mean_token_accuracy": 0.8233116855844855,
|
||
|
|
"num_tokens": 47831739.0,
|
||
|
|
"step": 111
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46331787109375,
|
||
|
|
"epoch": 0.448,
|
||
|
|
"grad_norm": 1.240731540812167,
|
||
|
|
"learning_rate": 1.9485722627938493e-05,
|
||
|
|
"loss": 0.541,
|
||
|
|
"mean_token_accuracy": 0.819410003721714,
|
||
|
|
"num_tokens": 48254350.0,
|
||
|
|
"step": 112
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4715576171875,
|
||
|
|
"epoch": 0.452,
|
||
|
|
"grad_norm": 1.0447503497349395,
|
||
|
|
"learning_rate": 1.9471662572865738e-05,
|
||
|
|
"loss": 0.524,
|
||
|
|
"mean_token_accuracy": 0.82669781986624,
|
||
|
|
"num_tokens": 48666431.0,
|
||
|
|
"step": 113
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.467315673828125,
|
||
|
|
"epoch": 0.456,
|
||
|
|
"grad_norm": 1.088088376842833,
|
||
|
|
"learning_rate": 1.9457418115943957e-05,
|
||
|
|
"loss": 0.5137,
|
||
|
|
"mean_token_accuracy": 0.8272674307227135,
|
||
|
|
"num_tokens": 49089655.0,
|
||
|
|
"step": 114
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46832275390625,
|
||
|
|
"epoch": 0.46,
|
||
|
|
"grad_norm": 1.3085810462854417,
|
||
|
|
"learning_rate": 1.9442989534495557e-05,
|
||
|
|
"loss": 0.5538,
|
||
|
|
"mean_token_accuracy": 0.8190359249711037,
|
||
|
|
"num_tokens": 49540650.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46942138671875,
|
||
|
|
"epoch": 0.464,
|
||
|
|
"grad_norm": 1.1429134033862727,
|
||
|
|
"learning_rate": 1.942837710942762e-05,
|
||
|
|
"loss": 0.5204,
|
||
|
|
"mean_token_accuracy": 0.8236291669309139,
|
||
|
|
"num_tokens": 49956904.0,
|
||
|
|
"step": 116
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45904541015625,
|
||
|
|
"epoch": 0.468,
|
||
|
|
"grad_norm": 1.0895293625758646,
|
||
|
|
"learning_rate": 1.941358112522644e-05,
|
||
|
|
"loss": 0.5256,
|
||
|
|
"mean_token_accuracy": 0.8249471010640264,
|
||
|
|
"num_tokens": 50381109.0,
|
||
|
|
"step": 117
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.457275390625,
|
||
|
|
"epoch": 0.472,
|
||
|
|
"grad_norm": 1.1971462909554917,
|
||
|
|
"learning_rate": 1.9398601869951985e-05,
|
||
|
|
"loss": 0.5259,
|
||
|
|
"mean_token_accuracy": 0.8235180974006653,
|
||
|
|
"num_tokens": 50817582.0,
|
||
|
|
"step": 118
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46270751953125,
|
||
|
|
"epoch": 0.476,
|
||
|
|
"grad_norm": 1.2494838558053953,
|
||
|
|
"learning_rate": 1.9383439635232296e-05,
|
||
|
|
"loss": 0.5416,
|
||
|
|
"mean_token_accuracy": 0.8187661021947861,
|
||
|
|
"num_tokens": 51257498.0,
|
||
|
|
"step": 119
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.462615966796875,
|
||
|
|
"epoch": 0.48,
|
||
|
|
"grad_norm": 1.0673462440765011,
|
||
|
|
"learning_rate": 1.93680947162578e-05,
|
||
|
|
"loss": 0.5306,
|
||
|
|
"mean_token_accuracy": 0.8209635242819786,
|
||
|
|
"num_tokens": 51692021.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.461761474609375,
|
||
|
|
"epoch": 0.484,
|
||
|
|
"grad_norm": 1.0243446543615218,
|
||
|
|
"learning_rate": 1.9352567411775565e-05,
|
||
|
|
"loss": 0.5189,
|
||
|
|
"mean_token_accuracy": 0.8259513303637505,
|
||
|
|
"num_tokens": 52119343.0,
|
||
|
|
"step": 121
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46307373046875,
|
||
|
|
"epoch": 0.488,
|
||
|
|
"grad_norm": 0.9777966321154316,
|
||
|
|
"learning_rate": 1.9336858024083484e-05,
|
||
|
|
"loss": 0.5294,
|
||
|
|
"mean_token_accuracy": 0.8230921700596809,
|
||
|
|
"num_tokens": 52547186.0,
|
||
|
|
"step": 122
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4693603515625,
|
||
|
|
"epoch": 0.492,
|
||
|
|
"grad_norm": 1.0267616529150283,
|
||
|
|
"learning_rate": 1.9320966859024397e-05,
|
||
|
|
"loss": 0.5157,
|
||
|
|
"mean_token_accuracy": 0.8272608360275626,
|
||
|
|
"num_tokens": 52971088.0,
|
||
|
|
"step": 123
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.460784912109375,
|
||
|
|
"epoch": 0.496,
|
||
|
|
"grad_norm": 1.0515600670205572,
|
||
|
|
"learning_rate": 1.9304894225980126e-05,
|
||
|
|
"loss": 0.5108,
|
||
|
|
"mean_token_accuracy": 0.830218655988574,
|
||
|
|
"num_tokens": 53388466.0,
|
||
|
|
"step": 124
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4619140625,
|
||
|
|
"epoch": 0.5,
|
||
|
|
"grad_norm": 1.1022818467340172,
|
||
|
|
"learning_rate": 1.9288640437865445e-05,
|
||
|
|
"loss": 0.5285,
|
||
|
|
"mean_token_accuracy": 0.8264590501785278,
|
||
|
|
"num_tokens": 53808058.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46441650390625,
|
||
|
|
"epoch": 0.504,
|
||
|
|
"grad_norm": 0.9986322253479598,
|
||
|
|
"learning_rate": 1.927220581112202e-05,
|
||
|
|
"loss": 0.5159,
|
||
|
|
"mean_token_accuracy": 0.8257627114653587,
|
||
|
|
"num_tokens": 54227928.0,
|
||
|
|
"step": 126
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46063232421875,
|
||
|
|
"epoch": 0.508,
|
||
|
|
"grad_norm": 1.0013750951559839,
|
||
|
|
"learning_rate": 1.9255590665712214e-05,
|
||
|
|
"loss": 0.5349,
|
||
|
|
"mean_token_accuracy": 0.8253623321652412,
|
||
|
|
"num_tokens": 54677129.0,
|
||
|
|
"step": 127
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4595947265625,
|
||
|
|
"epoch": 0.512,
|
||
|
|
"grad_norm": 1.1054521898293674,
|
||
|
|
"learning_rate": 1.9238795325112867e-05,
|
||
|
|
"loss": 0.506,
|
||
|
|
"mean_token_accuracy": 0.8297894420102239,
|
||
|
|
"num_tokens": 55104735.0,
|
||
|
|
"step": 128
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.462371826171875,
|
||
|
|
"epoch": 0.516,
|
||
|
|
"grad_norm": 0.9728993389610864,
|
||
|
|
"learning_rate": 1.922182011630902e-05,
|
||
|
|
"loss": 0.5156,
|
||
|
|
"mean_token_accuracy": 0.8265899391844869,
|
||
|
|
"num_tokens": 55529534.0,
|
||
|
|
"step": 129
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.462982177734375,
|
||
|
|
"epoch": 0.52,
|
||
|
|
"grad_norm": 0.9983295925734529,
|
||
|
|
"learning_rate": 1.9204665369787507e-05,
|
||
|
|
"loss": 0.5191,
|
||
|
|
"mean_token_accuracy": 0.8279944825917482,
|
||
|
|
"num_tokens": 55954518.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.454498291015625,
|
||
|
|
"epoch": 0.524,
|
||
|
|
"grad_norm": 0.98905839747544,
|
||
|
|
"learning_rate": 1.918733141953056e-05,
|
||
|
|
"loss": 0.5145,
|
||
|
|
"mean_token_accuracy": 0.8263998003676534,
|
||
|
|
"num_tokens": 56392643.0,
|
||
|
|
"step": 131
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45501708984375,
|
||
|
|
"epoch": 0.528,
|
||
|
|
"grad_norm": 1.0806603199375153,
|
||
|
|
"learning_rate": 1.9169818603009298e-05,
|
||
|
|
"loss": 0.5103,
|
||
|
|
"mean_token_accuracy": 0.8272571098059416,
|
||
|
|
"num_tokens": 56819406.0,
|
||
|
|
"step": 132
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45574951171875,
|
||
|
|
"epoch": 0.532,
|
||
|
|
"grad_norm": 1.1547682466608173,
|
||
|
|
"learning_rate": 1.9152127261177127e-05,
|
||
|
|
"loss": 0.5129,
|
||
|
|
"mean_token_accuracy": 0.828819821588695,
|
||
|
|
"num_tokens": 57232802.0,
|
||
|
|
"step": 133
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45135498046875,
|
||
|
|
"epoch": 0.536,
|
||
|
|
"grad_norm": 1.193707240750841,
|
||
|
|
"learning_rate": 1.913425773846315e-05,
|
||
|
|
"loss": 0.5221,
|
||
|
|
"mean_token_accuracy": 0.8264128090813756,
|
||
|
|
"num_tokens": 57657590.0,
|
||
|
|
"step": 134
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45794677734375,
|
||
|
|
"epoch": 0.54,
|
||
|
|
"grad_norm": 1.1088081742478038,
|
||
|
|
"learning_rate": 1.911621038276542e-05,
|
||
|
|
"loss": 0.5189,
|
||
|
|
"mean_token_accuracy": 0.827189352363348,
|
||
|
|
"num_tokens": 58089514.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.449432373046875,
|
||
|
|
"epoch": 0.544,
|
||
|
|
"grad_norm": 1.0376980359839427,
|
||
|
|
"learning_rate": 1.9097985545444195e-05,
|
||
|
|
"loss": 0.5172,
|
||
|
|
"mean_token_accuracy": 0.8250835612416267,
|
||
|
|
"num_tokens": 58522713.0,
|
||
|
|
"step": 136
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.444915771484375,
|
||
|
|
"epoch": 0.548,
|
||
|
|
"grad_norm": 0.9984573217495579,
|
||
|
|
"learning_rate": 1.907958358131508e-05,
|
||
|
|
"loss": 0.5027,
|
||
|
|
"mean_token_accuracy": 0.8301894329488277,
|
||
|
|
"num_tokens": 58939116.0,
|
||
|
|
"step": 137
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44378662109375,
|
||
|
|
"epoch": 0.552,
|
||
|
|
"grad_norm": 0.9648385417833156,
|
||
|
|
"learning_rate": 1.9061004848642124e-05,
|
||
|
|
"loss": 0.5122,
|
||
|
|
"mean_token_accuracy": 0.8280163994058967,
|
||
|
|
"num_tokens": 59383329.0,
|
||
|
|
"step": 138
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45013427734375,
|
||
|
|
"epoch": 0.556,
|
||
|
|
"grad_norm": 0.9294605162569634,
|
||
|
|
"learning_rate": 1.904224970913085e-05,
|
||
|
|
"loss": 0.5201,
|
||
|
|
"mean_token_accuracy": 0.8262923201546073,
|
||
|
|
"num_tokens": 59822669.0,
|
||
|
|
"step": 139
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.443084716796875,
|
||
|
|
"epoch": 0.56,
|
||
|
|
"grad_norm": 0.910275363799664,
|
||
|
|
"learning_rate": 1.9023318527921213e-05,
|
||
|
|
"loss": 0.51,
|
||
|
|
"mean_token_accuracy": 0.8312698202207685,
|
||
|
|
"num_tokens": 60266406.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.446075439453125,
|
||
|
|
"epoch": 0.564,
|
||
|
|
"grad_norm": 0.9401078127838067,
|
||
|
|
"learning_rate": 1.900421167358048e-05,
|
||
|
|
"loss": 0.5204,
|
||
|
|
"mean_token_accuracy": 0.8288511419668794,
|
||
|
|
"num_tokens": 60707059.0,
|
||
|
|
"step": 141
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.442108154296875,
|
||
|
|
"epoch": 0.568,
|
||
|
|
"grad_norm": 1.0007098188117969,
|
||
|
|
"learning_rate": 1.8984929518096065e-05,
|
||
|
|
"loss": 0.5044,
|
||
|
|
"mean_token_accuracy": 0.8303408762440085,
|
||
|
|
"num_tokens": 61135545.0,
|
||
|
|
"step": 142
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.452850341796875,
|
||
|
|
"epoch": 0.572,
|
||
|
|
"grad_norm": 1.0058213928774558,
|
||
|
|
"learning_rate": 1.8965472436868288e-05,
|
||
|
|
"loss": 0.5322,
|
||
|
|
"mean_token_accuracy": 0.82315091509372,
|
||
|
|
"num_tokens": 61561899.0,
|
||
|
|
"step": 143
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4517822265625,
|
||
|
|
"epoch": 0.576,
|
||
|
|
"grad_norm": 0.9874601836198499,
|
||
|
|
"learning_rate": 1.8945840808703053e-05,
|
||
|
|
"loss": 0.5134,
|
||
|
|
"mean_token_accuracy": 0.8281162921339273,
|
||
|
|
"num_tokens": 61984971.0,
|
||
|
|
"step": 144
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.46240234375,
|
||
|
|
"epoch": 0.58,
|
||
|
|
"grad_norm": 0.9726922402395054,
|
||
|
|
"learning_rate": 1.892603501580449e-05,
|
||
|
|
"loss": 0.5106,
|
||
|
|
"mean_token_accuracy": 0.8296762034296989,
|
||
|
|
"num_tokens": 62403600.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44866943359375,
|
||
|
|
"epoch": 0.584,
|
||
|
|
"grad_norm": 0.9926174853332148,
|
||
|
|
"learning_rate": 1.8906055443767502e-05,
|
||
|
|
"loss": 0.5142,
|
||
|
|
"mean_token_accuracy": 0.8281713770702481,
|
||
|
|
"num_tokens": 62831938.0,
|
||
|
|
"step": 146
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45654296875,
|
||
|
|
"epoch": 0.588,
|
||
|
|
"grad_norm": 0.9931525276196623,
|
||
|
|
"learning_rate": 1.888590248157027e-05,
|
||
|
|
"loss": 0.5072,
|
||
|
|
"mean_token_accuracy": 0.8285547904670238,
|
||
|
|
"num_tokens": 63250592.0,
|
||
|
|
"step": 147
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45831298828125,
|
||
|
|
"epoch": 0.592,
|
||
|
|
"grad_norm": 1.0795179316406467,
|
||
|
|
"learning_rate": 1.8865576521566665e-05,
|
||
|
|
"loss": 0.4984,
|
||
|
|
"mean_token_accuracy": 0.8306977925822139,
|
||
|
|
"num_tokens": 63663509.0,
|
||
|
|
"step": 148
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.448211669921875,
|
||
|
|
"epoch": 0.596,
|
||
|
|
"grad_norm": 0.9203935868704187,
|
||
|
|
"learning_rate": 1.8845077959478615e-05,
|
||
|
|
"loss": 0.5117,
|
||
|
|
"mean_token_accuracy": 0.8279412044212222,
|
||
|
|
"num_tokens": 64086993.0,
|
||
|
|
"step": 149
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44720458984375,
|
||
|
|
"epoch": 0.6,
|
||
|
|
"grad_norm": 0.9915746078456793,
|
||
|
|
"learning_rate": 1.8824407194388408e-05,
|
||
|
|
"loss": 0.5134,
|
||
|
|
"mean_token_accuracy": 0.8278513699769974,
|
||
|
|
"num_tokens": 64532482.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.456817626953125,
|
||
|
|
"epoch": 0.604,
|
||
|
|
"grad_norm": 0.9358233962017566,
|
||
|
|
"learning_rate": 1.8803564628730916e-05,
|
||
|
|
"loss": 0.5344,
|
||
|
|
"mean_token_accuracy": 0.8210849752649665,
|
||
|
|
"num_tokens": 64967411.0,
|
||
|
|
"step": 151
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.449676513671875,
|
||
|
|
"epoch": 0.608,
|
||
|
|
"grad_norm": 1.0684965960163662,
|
||
|
|
"learning_rate": 1.8782550668285758e-05,
|
||
|
|
"loss": 0.5088,
|
||
|
|
"mean_token_accuracy": 0.8318922128528357,
|
||
|
|
"num_tokens": 65402584.0,
|
||
|
|
"step": 152
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.451873779296875,
|
||
|
|
"epoch": 0.612,
|
||
|
|
"grad_norm": 1.0827788127356732,
|
||
|
|
"learning_rate": 1.8761365722169405e-05,
|
||
|
|
"loss": 0.5085,
|
||
|
|
"mean_token_accuracy": 0.8294419320300221,
|
||
|
|
"num_tokens": 65837669.0,
|
||
|
|
"step": 153
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.457611083984375,
|
||
|
|
"epoch": 0.616,
|
||
|
|
"grad_norm": 1.1097392028922026,
|
||
|
|
"learning_rate": 1.874001020282721e-05,
|
||
|
|
"loss": 0.522,
|
||
|
|
"mean_token_accuracy": 0.8242032425478101,
|
||
|
|
"num_tokens": 66270001.0,
|
||
|
|
"step": 154
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.453216552734375,
|
||
|
|
"epoch": 0.62,
|
||
|
|
"grad_norm": 0.8972211136652368,
|
||
|
|
"learning_rate": 1.8718484526025387e-05,
|
||
|
|
"loss": 0.5154,
|
||
|
|
"mean_token_accuracy": 0.8258903725072742,
|
||
|
|
"num_tokens": 66711490.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4593505859375,
|
||
|
|
"epoch": 0.624,
|
||
|
|
"grad_norm": 1.1305489594365614,
|
||
|
|
"learning_rate": 1.8696789110842908e-05,
|
||
|
|
"loss": 0.4938,
|
||
|
|
"mean_token_accuracy": 0.8332448862493038,
|
||
|
|
"num_tokens": 67122918.0,
|
||
|
|
"step": 156
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.451385498046875,
|
||
|
|
"epoch": 0.628,
|
||
|
|
"grad_norm": 1.157249109023668,
|
||
|
|
"learning_rate": 1.867492437966334e-05,
|
||
|
|
"loss": 0.5017,
|
||
|
|
"mean_token_accuracy": 0.83094790764153,
|
||
|
|
"num_tokens": 67540775.0,
|
||
|
|
"step": 157
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.451080322265625,
|
||
|
|
"epoch": 0.632,
|
||
|
|
"grad_norm": 1.1979070454541574,
|
||
|
|
"learning_rate": 1.865289075816664e-05,
|
||
|
|
"loss": 0.5171,
|
||
|
|
"mean_token_accuracy": 0.8249188186600804,
|
||
|
|
"num_tokens": 67967705.0,
|
||
|
|
"step": 158
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45458984375,
|
||
|
|
"epoch": 0.636,
|
||
|
|
"grad_norm": 0.9598158123373788,
|
||
|
|
"learning_rate": 1.8630688675320844e-05,
|
||
|
|
"loss": 0.5175,
|
||
|
|
"mean_token_accuracy": 0.8283455595374107,
|
||
|
|
"num_tokens": 68404234.0,
|
||
|
|
"step": 159
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.455322265625,
|
||
|
|
"epoch": 0.64,
|
||
|
|
"grad_norm": 0.9020034608540674,
|
||
|
|
"learning_rate": 1.8608318563373735e-05,
|
||
|
|
"loss": 0.517,
|
||
|
|
"mean_token_accuracy": 0.8263333952054381,
|
||
|
|
"num_tokens": 68847969.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.462371826171875,
|
||
|
|
"epoch": 0.644,
|
||
|
|
"grad_norm": 0.9003936673437223,
|
||
|
|
"learning_rate": 1.858578085784442e-05,
|
||
|
|
"loss": 0.4976,
|
||
|
|
"mean_token_accuracy": 0.830751427449286,
|
||
|
|
"num_tokens": 69263603.0,
|
||
|
|
"step": 161
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4498291015625,
|
||
|
|
"epoch": 0.648,
|
||
|
|
"grad_norm": 0.9202962608554202,
|
||
|
|
"learning_rate": 1.8563075997514842e-05,
|
||
|
|
"loss": 0.4914,
|
||
|
|
"mean_token_accuracy": 0.8341594729572535,
|
||
|
|
"num_tokens": 69689171.0,
|
||
|
|
"step": 162
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45648193359375,
|
||
|
|
"epoch": 0.652,
|
||
|
|
"grad_norm": 0.9252817402969755,
|
||
|
|
"learning_rate": 1.8540204424421264e-05,
|
||
|
|
"loss": 0.5105,
|
||
|
|
"mean_token_accuracy": 0.8272971650585532,
|
||
|
|
"num_tokens": 70129694.0,
|
||
|
|
"step": 163
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45355224609375,
|
||
|
|
"epoch": 0.656,
|
||
|
|
"grad_norm": 0.9331796089689303,
|
||
|
|
"learning_rate": 1.8517166583845628e-05,
|
||
|
|
"loss": 0.5013,
|
||
|
|
"mean_token_accuracy": 0.8324267938733101,
|
||
|
|
"num_tokens": 70557497.0,
|
||
|
|
"step": 164
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.455718994140625,
|
||
|
|
"epoch": 0.66,
|
||
|
|
"grad_norm": 1.0349760499514833,
|
||
|
|
"learning_rate": 1.849396292430691e-05,
|
||
|
|
"loss": 0.5157,
|
||
|
|
"mean_token_accuracy": 0.8284419225528836,
|
||
|
|
"num_tokens": 70973887.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4530029296875,
|
||
|
|
"epoch": 0.664,
|
||
|
|
"grad_norm": 0.870000526901812,
|
||
|
|
"learning_rate": 1.8470593897552387e-05,
|
||
|
|
"loss": 0.5024,
|
||
|
|
"mean_token_accuracy": 0.830081689171493,
|
||
|
|
"num_tokens": 71385684.0,
|
||
|
|
"step": 166
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4520263671875,
|
||
|
|
"epoch": 0.668,
|
||
|
|
"grad_norm": 1.0345782777048673,
|
||
|
|
"learning_rate": 1.8447059958548822e-05,
|
||
|
|
"loss": 0.5004,
|
||
|
|
"mean_token_accuracy": 0.8322744397446513,
|
||
|
|
"num_tokens": 71816941.0,
|
||
|
|
"step": 167
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.459564208984375,
|
||
|
|
"epoch": 0.672,
|
||
|
|
"grad_norm": 0.9825288639785867,
|
||
|
|
"learning_rate": 1.8423361565473636e-05,
|
||
|
|
"loss": 0.5033,
|
||
|
|
"mean_token_accuracy": 0.8282082267105579,
|
||
|
|
"num_tokens": 72251260.0,
|
||
|
|
"step": 168
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4512939453125,
|
||
|
|
"epoch": 0.676,
|
||
|
|
"grad_norm": 0.9193823933980492,
|
||
|
|
"learning_rate": 1.839949917970596e-05,
|
||
|
|
"loss": 0.5041,
|
||
|
|
"mean_token_accuracy": 0.8298061117529869,
|
||
|
|
"num_tokens": 72689743.0,
|
||
|
|
"step": 169
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.444915771484375,
|
||
|
|
"epoch": 0.68,
|
||
|
|
"grad_norm": 0.9566359142849042,
|
||
|
|
"learning_rate": 1.837547326581768e-05,
|
||
|
|
"loss": 0.4907,
|
||
|
|
"mean_token_accuracy": 0.8339335415512323,
|
||
|
|
"num_tokens": 73115859.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45452880859375,
|
||
|
|
"epoch": 0.684,
|
||
|
|
"grad_norm": 0.9211487615324878,
|
||
|
|
"learning_rate": 1.8351284291564358e-05,
|
||
|
|
"loss": 0.503,
|
||
|
|
"mean_token_accuracy": 0.8309380281716585,
|
||
|
|
"num_tokens": 73542927.0,
|
||
|
|
"step": 171
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.442657470703125,
|
||
|
|
"epoch": 0.688,
|
||
|
|
"grad_norm": 0.8677368460230288,
|
||
|
|
"learning_rate": 1.832693272787616e-05,
|
||
|
|
"loss": 0.5042,
|
||
|
|
"mean_token_accuracy": 0.8317311052232981,
|
||
|
|
"num_tokens": 73986918.0,
|
||
|
|
"step": 172
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44183349609375,
|
||
|
|
"epoch": 0.692,
|
||
|
|
"grad_norm": 0.786274457857099,
|
||
|
|
"learning_rate": 1.8302419048848666e-05,
|
||
|
|
"loss": 0.488,
|
||
|
|
"mean_token_accuracy": 0.834156553260982,
|
||
|
|
"num_tokens": 74410258.0,
|
||
|
|
"step": 173
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.443115234375,
|
||
|
|
"epoch": 0.696,
|
||
|
|
"grad_norm": 0.9385712558351066,
|
||
|
|
"learning_rate": 1.8277743731733647e-05,
|
||
|
|
"loss": 0.5132,
|
||
|
|
"mean_token_accuracy": 0.8276038644835353,
|
||
|
|
"num_tokens": 74857870.0,
|
||
|
|
"step": 174
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.442230224609375,
|
||
|
|
"epoch": 0.7,
|
||
|
|
"grad_norm": 0.9283106639008171,
|
||
|
|
"learning_rate": 1.8252907256929777e-05,
|
||
|
|
"loss": 0.4918,
|
||
|
|
"mean_token_accuracy": 0.832920434884727,
|
||
|
|
"num_tokens": 75293641.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.447967529296875,
|
||
|
|
"epoch": 0.704,
|
||
|
|
"grad_norm": 0.8046650042623317,
|
||
|
|
"learning_rate": 1.8227910107973264e-05,
|
||
|
|
"loss": 0.5209,
|
||
|
|
"mean_token_accuracy": 0.8249119343236089,
|
||
|
|
"num_tokens": 75742874.0,
|
||
|
|
"step": 176
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.449005126953125,
|
||
|
|
"epoch": 0.708,
|
||
|
|
"grad_norm": 0.9350725783417487,
|
||
|
|
"learning_rate": 1.820275277152846e-05,
|
||
|
|
"loss": 0.4947,
|
||
|
|
"mean_token_accuracy": 0.8325502732768655,
|
||
|
|
"num_tokens": 76166281.0,
|
||
|
|
"step": 177
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.446197509765625,
|
||
|
|
"epoch": 0.712,
|
||
|
|
"grad_norm": 0.9279881919895089,
|
||
|
|
"learning_rate": 1.817743573737837e-05,
|
||
|
|
"loss": 0.5062,
|
||
|
|
"mean_token_accuracy": 0.8302598362788558,
|
||
|
|
"num_tokens": 76586590.0,
|
||
|
|
"step": 178
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.445831298828125,
|
||
|
|
"epoch": 0.716,
|
||
|
|
"grad_norm": 0.9195710368939999,
|
||
|
|
"learning_rate": 1.815195949841512e-05,
|
||
|
|
"loss": 0.4914,
|
||
|
|
"mean_token_accuracy": 0.8362073982134461,
|
||
|
|
"num_tokens": 77002622.0,
|
||
|
|
"step": 179
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44403076171875,
|
||
|
|
"epoch": 0.72,
|
||
|
|
"grad_norm": 0.9244782955466698,
|
||
|
|
"learning_rate": 1.8126324550630364e-05,
|
||
|
|
"loss": 0.4999,
|
||
|
|
"mean_token_accuracy": 0.8324580751359463,
|
||
|
|
"num_tokens": 77441354.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.43975830078125,
|
||
|
|
"epoch": 0.724,
|
||
|
|
"grad_norm": 0.8717941163611566,
|
||
|
|
"learning_rate": 1.810053139310562e-05,
|
||
|
|
"loss": 0.4828,
|
||
|
|
"mean_token_accuracy": 0.8344852039590478,
|
||
|
|
"num_tokens": 77864521.0,
|
||
|
|
"step": 181
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44024658203125,
|
||
|
|
"epoch": 0.728,
|
||
|
|
"grad_norm": 0.9886028991872213,
|
||
|
|
"learning_rate": 1.8074580528002572e-05,
|
||
|
|
"loss": 0.4842,
|
||
|
|
"mean_token_accuracy": 0.8351197401061654,
|
||
|
|
"num_tokens": 78292952.0,
|
||
|
|
"step": 182
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.440338134765625,
|
||
|
|
"epoch": 0.732,
|
||
|
|
"grad_norm": 0.8934536981501154,
|
||
|
|
"learning_rate": 1.804847246055326e-05,
|
||
|
|
"loss": 0.482,
|
||
|
|
"mean_token_accuracy": 0.8356953859329224,
|
||
|
|
"num_tokens": 78708621.0,
|
||
|
|
"step": 183
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.43902587890625,
|
||
|
|
"epoch": 0.736,
|
||
|
|
"grad_norm": 1.0653823466937893,
|
||
|
|
"learning_rate": 1.8022207699050278e-05,
|
||
|
|
"loss": 0.5088,
|
||
|
|
"mean_token_accuracy": 0.8291170001029968,
|
||
|
|
"num_tokens": 79142108.0,
|
||
|
|
"step": 184
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.444671630859375,
|
||
|
|
"epoch": 0.74,
|
||
|
|
"grad_norm": 1.0140468220944059,
|
||
|
|
"learning_rate": 1.7995786754836863e-05,
|
||
|
|
"loss": 0.4969,
|
||
|
|
"mean_token_accuracy": 0.8308103987947106,
|
||
|
|
"num_tokens": 79572933.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4453125,
|
||
|
|
"epoch": 0.744,
|
||
|
|
"grad_norm": 1.32281698643728,
|
||
|
|
"learning_rate": 1.7969210142296942e-05,
|
||
|
|
"loss": 0.4911,
|
||
|
|
"mean_token_accuracy": 0.8336349315941334,
|
||
|
|
"num_tokens": 80000987.0,
|
||
|
|
"step": 186
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44708251953125,
|
||
|
|
"epoch": 0.748,
|
||
|
|
"grad_norm": 0.8846492464872316,
|
||
|
|
"learning_rate": 1.794247837884511e-05,
|
||
|
|
"loss": 0.496,
|
||
|
|
"mean_token_accuracy": 0.8321015769615769,
|
||
|
|
"num_tokens": 80460455.0,
|
||
|
|
"step": 187
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.448211669921875,
|
||
|
|
"epoch": 0.752,
|
||
|
|
"grad_norm": 0.9600055350465384,
|
||
|
|
"learning_rate": 1.791559198491657e-05,
|
||
|
|
"loss": 0.4976,
|
||
|
|
"mean_token_accuracy": 0.8331601927056909,
|
||
|
|
"num_tokens": 80913949.0,
|
||
|
|
"step": 188
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4464111328125,
|
||
|
|
"epoch": 0.756,
|
||
|
|
"grad_norm": 0.8637362813606588,
|
||
|
|
"learning_rate": 1.788855148395699e-05,
|
||
|
|
"loss": 0.5014,
|
||
|
|
"mean_token_accuracy": 0.8302784692496061,
|
||
|
|
"num_tokens": 81344830.0,
|
||
|
|
"step": 189
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.441009521484375,
|
||
|
|
"epoch": 0.76,
|
||
|
|
"grad_norm": 0.8985382142107833,
|
||
|
|
"learning_rate": 1.786135740241232e-05,
|
||
|
|
"loss": 0.4898,
|
||
|
|
"mean_token_accuracy": 0.8343158382922411,
|
||
|
|
"num_tokens": 81791815.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.444793701171875,
|
||
|
|
"epoch": 0.764,
|
||
|
|
"grad_norm": 0.8839433830952508,
|
||
|
|
"learning_rate": 1.7834010269718526e-05,
|
||
|
|
"loss": 0.4809,
|
||
|
|
"mean_token_accuracy": 0.8366794409230351,
|
||
|
|
"num_tokens": 82216228.0,
|
||
|
|
"step": 191
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.442626953125,
|
||
|
|
"epoch": 0.768,
|
||
|
|
"grad_norm": 0.8595931240450239,
|
||
|
|
"learning_rate": 1.780651061829132e-05,
|
||
|
|
"loss": 0.488,
|
||
|
|
"mean_token_accuracy": 0.8337099198251963,
|
||
|
|
"num_tokens": 82651253.0,
|
||
|
|
"step": 192
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4453125,
|
||
|
|
"epoch": 0.772,
|
||
|
|
"grad_norm": 0.8724722218663216,
|
||
|
|
"learning_rate": 1.7778858983515744e-05,
|
||
|
|
"loss": 0.4983,
|
||
|
|
"mean_token_accuracy": 0.8326056655496359,
|
||
|
|
"num_tokens": 83077652.0,
|
||
|
|
"step": 193
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45111083984375,
|
||
|
|
"epoch": 0.776,
|
||
|
|
"grad_norm": 0.9409924255944003,
|
||
|
|
"learning_rate": 1.775105590373579e-05,
|
||
|
|
"loss": 0.4907,
|
||
|
|
"mean_token_accuracy": 0.8332920717075467,
|
||
|
|
"num_tokens": 83504119.0,
|
||
|
|
"step": 194
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44378662109375,
|
||
|
|
"epoch": 0.78,
|
||
|
|
"grad_norm": 0.9627952185645313,
|
||
|
|
"learning_rate": 1.772310192024389e-05,
|
||
|
|
"loss": 0.4937,
|
||
|
|
"mean_token_accuracy": 0.8324889503419399,
|
||
|
|
"num_tokens": 83932445.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.438507080078125,
|
||
|
|
"epoch": 0.784,
|
||
|
|
"grad_norm": 0.8213070899857671,
|
||
|
|
"learning_rate": 1.76949975772704e-05,
|
||
|
|
"loss": 0.4888,
|
||
|
|
"mean_token_accuracy": 0.8341877050697803,
|
||
|
|
"num_tokens": 84381174.0,
|
||
|
|
"step": 196
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44390869140625,
|
||
|
|
"epoch": 0.788,
|
||
|
|
"grad_norm": 0.8443499324801843,
|
||
|
|
"learning_rate": 1.7666743421972986e-05,
|
||
|
|
"loss": 0.4914,
|
||
|
|
"mean_token_accuracy": 0.8327549444511533,
|
||
|
|
"num_tokens": 84818289.0,
|
||
|
|
"step": 197
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.447723388671875,
|
||
|
|
"epoch": 0.792,
|
||
|
|
"grad_norm": 0.8367256837299023,
|
||
|
|
"learning_rate": 1.7638340004425984e-05,
|
||
|
|
"loss": 0.4854,
|
||
|
|
"mean_token_accuracy": 0.8357967529445887,
|
||
|
|
"num_tokens": 85243958.0,
|
||
|
|
"step": 198
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.438720703125,
|
||
|
|
"epoch": 0.796,
|
||
|
|
"grad_norm": 0.8719381684552924,
|
||
|
|
"learning_rate": 1.7609787877609678e-05,
|
||
|
|
"loss": 0.4825,
|
||
|
|
"mean_token_accuracy": 0.8368498403578997,
|
||
|
|
"num_tokens": 85667666.0,
|
||
|
|
"step": 199
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.440338134765625,
|
||
|
|
"epoch": 0.8,
|
||
|
|
"grad_norm": 0.9554461755760871,
|
||
|
|
"learning_rate": 1.7581087597399556e-05,
|
||
|
|
"loss": 0.487,
|
||
|
|
"mean_token_accuracy": 0.8363207206130028,
|
||
|
|
"num_tokens": 86111567.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44659423828125,
|
||
|
|
"epoch": 0.804,
|
||
|
|
"grad_norm": 0.8203515153767914,
|
||
|
|
"learning_rate": 1.755223972255546e-05,
|
||
|
|
"loss": 0.4879,
|
||
|
|
"mean_token_accuracy": 0.8348002340644598,
|
||
|
|
"num_tokens": 86533732.0,
|
||
|
|
"step": 201
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44342041015625,
|
||
|
|
"epoch": 0.808,
|
||
|
|
"grad_norm": 0.9066800432002657,
|
||
|
|
"learning_rate": 1.7523244814710728e-05,
|
||
|
|
"loss": 0.4795,
|
||
|
|
"mean_token_accuracy": 0.8359106043353677,
|
||
|
|
"num_tokens": 86978859.0,
|
||
|
|
"step": 202
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4464111328125,
|
||
|
|
"epoch": 0.812,
|
||
|
|
"grad_norm": 0.9673356712859635,
|
||
|
|
"learning_rate": 1.7494103438361252e-05,
|
||
|
|
"loss": 0.4869,
|
||
|
|
"mean_token_accuracy": 0.8333167713135481,
|
||
|
|
"num_tokens": 87420045.0,
|
||
|
|
"step": 203
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.445465087890625,
|
||
|
|
"epoch": 0.816,
|
||
|
|
"grad_norm": 0.8789458903527486,
|
||
|
|
"learning_rate": 1.7464816160854494e-05,
|
||
|
|
"loss": 0.5063,
|
||
|
|
"mean_token_accuracy": 0.8298322511836886,
|
||
|
|
"num_tokens": 87863126.0,
|
||
|
|
"step": 204
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.445892333984375,
|
||
|
|
"epoch": 0.82,
|
||
|
|
"grad_norm": 0.9564318518804198,
|
||
|
|
"learning_rate": 1.7435383552378428e-05,
|
||
|
|
"loss": 0.4993,
|
||
|
|
"mean_token_accuracy": 0.8326402669772506,
|
||
|
|
"num_tokens": 88280109.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4427490234375,
|
||
|
|
"epoch": 0.824,
|
||
|
|
"grad_norm": 0.8874034702827066,
|
||
|
|
"learning_rate": 1.7405806185950452e-05,
|
||
|
|
"loss": 0.4912,
|
||
|
|
"mean_token_accuracy": 0.8338399855419993,
|
||
|
|
"num_tokens": 88720431.0,
|
||
|
|
"step": 206
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.443450927734375,
|
||
|
|
"epoch": 0.828,
|
||
|
|
"grad_norm": 0.8386661522377065,
|
||
|
|
"learning_rate": 1.7376084637406222e-05,
|
||
|
|
"loss": 0.4854,
|
||
|
|
"mean_token_accuracy": 0.8347595361992717,
|
||
|
|
"num_tokens": 89158797.0,
|
||
|
|
"step": 207
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44439697265625,
|
||
|
|
"epoch": 0.832,
|
||
|
|
"grad_norm": 0.8836343144841785,
|
||
|
|
"learning_rate": 1.7346219485388455e-05,
|
||
|
|
"loss": 0.4972,
|
||
|
|
"mean_token_accuracy": 0.831147588789463,
|
||
|
|
"num_tokens": 89601912.0,
|
||
|
|
"step": 208
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.446075439453125,
|
||
|
|
"epoch": 0.836,
|
||
|
|
"grad_norm": 0.857083565075856,
|
||
|
|
"learning_rate": 1.731621131133564e-05,
|
||
|
|
"loss": 0.4768,
|
||
|
|
"mean_token_accuracy": 0.8356449427083135,
|
||
|
|
"num_tokens": 90018865.0,
|
||
|
|
"step": 209
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44830322265625,
|
||
|
|
"epoch": 0.84,
|
||
|
|
"grad_norm": 0.9211691506385639,
|
||
|
|
"learning_rate": 1.7286060699470746e-05,
|
||
|
|
"loss": 0.4888,
|
||
|
|
"mean_token_accuracy": 0.834488301537931,
|
||
|
|
"num_tokens": 90440076.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.443389892578125,
|
||
|
|
"epoch": 0.844,
|
||
|
|
"grad_norm": 0.8164186466823801,
|
||
|
|
"learning_rate": 1.7255768236789826e-05,
|
||
|
|
"loss": 0.4896,
|
||
|
|
"mean_token_accuracy": 0.832357844337821,
|
||
|
|
"num_tokens": 90889364.0,
|
||
|
|
"step": 211
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4508056640625,
|
||
|
|
"epoch": 0.848,
|
||
|
|
"grad_norm": 0.8167961105035216,
|
||
|
|
"learning_rate": 1.722533451305061e-05,
|
||
|
|
"loss": 0.4854,
|
||
|
|
"mean_token_accuracy": 0.8348451629281044,
|
||
|
|
"num_tokens": 91322040.0,
|
||
|
|
"step": 212
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.438385009765625,
|
||
|
|
"epoch": 0.852,
|
||
|
|
"grad_norm": 0.7995835613550173,
|
||
|
|
"learning_rate": 1.7194760120760987e-05,
|
||
|
|
"loss": 0.4761,
|
||
|
|
"mean_token_accuracy": 0.8368159225210547,
|
||
|
|
"num_tokens": 91772392.0,
|
||
|
|
"step": 213
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.439422607421875,
|
||
|
|
"epoch": 0.856,
|
||
|
|
"grad_norm": 0.8645379648608623,
|
||
|
|
"learning_rate": 1.7164045655167516e-05,
|
||
|
|
"loss": 0.4697,
|
||
|
|
"mean_token_accuracy": 0.837960172444582,
|
||
|
|
"num_tokens": 92202548.0,
|
||
|
|
"step": 214
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.439300537109375,
|
||
|
|
"epoch": 0.86,
|
||
|
|
"grad_norm": 0.8801586177000972,
|
||
|
|
"learning_rate": 1.7133191714243805e-05,
|
||
|
|
"loss": 0.4663,
|
||
|
|
"mean_token_accuracy": 0.8421149319037795,
|
||
|
|
"num_tokens": 92610190.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44036865234375,
|
||
|
|
"epoch": 0.864,
|
||
|
|
"grad_norm": 1.0174207080724988,
|
||
|
|
"learning_rate": 1.7102198898678875e-05,
|
||
|
|
"loss": 0.4787,
|
||
|
|
"mean_token_accuracy": 0.8360245265066624,
|
||
|
|
"num_tokens": 93036445.0,
|
||
|
|
"step": 216
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.446502685546875,
|
||
|
|
"epoch": 0.868,
|
||
|
|
"grad_norm": 0.8186905174875171,
|
||
|
|
"learning_rate": 1.7071067811865477e-05,
|
||
|
|
"loss": 0.479,
|
||
|
|
"mean_token_accuracy": 0.8356093447655439,
|
||
|
|
"num_tokens": 93465707.0,
|
||
|
|
"step": 217
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44769287109375,
|
||
|
|
"epoch": 0.872,
|
||
|
|
"grad_norm": 0.8570919121991946,
|
||
|
|
"learning_rate": 1.7039799059888333e-05,
|
||
|
|
"loss": 0.4785,
|
||
|
|
"mean_token_accuracy": 0.8383363289758563,
|
||
|
|
"num_tokens": 93889274.0,
|
||
|
|
"step": 218
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.445159912109375,
|
||
|
|
"epoch": 0.876,
|
||
|
|
"grad_norm": 0.8306433124203642,
|
||
|
|
"learning_rate": 1.700839325151233e-05,
|
||
|
|
"loss": 0.4702,
|
||
|
|
"mean_token_accuracy": 0.8406954538077116,
|
||
|
|
"num_tokens": 94317628.0,
|
||
|
|
"step": 219
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.448516845703125,
|
||
|
|
"epoch": 0.88,
|
||
|
|
"grad_norm": 0.8685341759661007,
|
||
|
|
"learning_rate": 1.69768509981707e-05,
|
||
|
|
"loss": 0.4927,
|
||
|
|
"mean_token_accuracy": 0.8356264876201749,
|
||
|
|
"num_tokens": 94755278.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.43853759765625,
|
||
|
|
"epoch": 0.884,
|
||
|
|
"grad_norm": 0.8116375274404566,
|
||
|
|
"learning_rate": 1.6945172913953068e-05,
|
||
|
|
"loss": 0.4643,
|
||
|
|
"mean_token_accuracy": 0.8408653726801276,
|
||
|
|
"num_tokens": 95179309.0,
|
||
|
|
"step": 221
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4395751953125,
|
||
|
|
"epoch": 0.888,
|
||
|
|
"grad_norm": 0.7450791263757587,
|
||
|
|
"learning_rate": 1.691335961559355e-05,
|
||
|
|
"loss": 0.4851,
|
||
|
|
"mean_token_accuracy": 0.8348496314138174,
|
||
|
|
"num_tokens": 95626000.0,
|
||
|
|
"step": 222
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.440277099609375,
|
||
|
|
"epoch": 0.892,
|
||
|
|
"grad_norm": 0.8638048167834911,
|
||
|
|
"learning_rate": 1.6881411722458688e-05,
|
||
|
|
"loss": 0.4843,
|
||
|
|
"mean_token_accuracy": 0.8344123205170035,
|
||
|
|
"num_tokens": 96076167.0,
|
||
|
|
"step": 223
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.455535888671875,
|
||
|
|
"epoch": 0.896,
|
||
|
|
"grad_norm": 0.8608797138472072,
|
||
|
|
"learning_rate": 1.6849329856535448e-05,
|
||
|
|
"loss": 0.4823,
|
||
|
|
"mean_token_accuracy": 0.8360185427591205,
|
||
|
|
"num_tokens": 96484783.0,
|
||
|
|
"step": 224
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.443939208984375,
|
||
|
|
"epoch": 0.9,
|
||
|
|
"grad_norm": 0.7913735384558466,
|
||
|
|
"learning_rate": 1.6817114642419068e-05,
|
||
|
|
"loss": 0.4838,
|
||
|
|
"mean_token_accuracy": 0.8360353093594313,
|
||
|
|
"num_tokens": 96910022.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4434814453125,
|
||
|
|
"epoch": 0.904,
|
||
|
|
"grad_norm": 0.8069741806700161,
|
||
|
|
"learning_rate": 1.6784766707300926e-05,
|
||
|
|
"loss": 0.4793,
|
||
|
|
"mean_token_accuracy": 0.8368015950545669,
|
||
|
|
"num_tokens": 97330681.0,
|
||
|
|
"step": 226
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4378662109375,
|
||
|
|
"epoch": 0.908,
|
||
|
|
"grad_norm": 0.7996771243733364,
|
||
|
|
"learning_rate": 1.6752286680956306e-05,
|
||
|
|
"loss": 0.4747,
|
||
|
|
"mean_token_accuracy": 0.8375375494360924,
|
||
|
|
"num_tokens": 97754087.0,
|
||
|
|
"step": 227
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44500732421875,
|
||
|
|
"epoch": 0.912,
|
||
|
|
"grad_norm": 0.8058886055611645,
|
||
|
|
"learning_rate": 1.671967519573216e-05,
|
||
|
|
"loss": 0.485,
|
||
|
|
"mean_token_accuracy": 0.8344050459563732,
|
||
|
|
"num_tokens": 98175653.0,
|
||
|
|
"step": 228
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.435760498046875,
|
||
|
|
"epoch": 0.916,
|
||
|
|
"grad_norm": 0.8214447292617232,
|
||
|
|
"learning_rate": 1.668693288653478e-05,
|
||
|
|
"loss": 0.485,
|
||
|
|
"mean_token_accuracy": 0.8356199618428946,
|
||
|
|
"num_tokens": 98628571.0,
|
||
|
|
"step": 229
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.437957763671875,
|
||
|
|
"epoch": 0.92,
|
||
|
|
"grad_norm": 0.9188580317306568,
|
||
|
|
"learning_rate": 1.6654060390817445e-05,
|
||
|
|
"loss": 0.476,
|
||
|
|
"mean_token_accuracy": 0.8368279924616218,
|
||
|
|
"num_tokens": 99068942.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4400634765625,
|
||
|
|
"epoch": 0.924,
|
||
|
|
"grad_norm": 0.8100958840205814,
|
||
|
|
"learning_rate": 1.6621058348568008e-05,
|
||
|
|
"loss": 0.4716,
|
||
|
|
"mean_token_accuracy": 0.8402912747114897,
|
||
|
|
"num_tokens": 99489068.0,
|
||
|
|
"step": 231
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4366455078125,
|
||
|
|
"epoch": 0.928,
|
||
|
|
"grad_norm": 0.8235008035739063,
|
||
|
|
"learning_rate": 1.658792740229643e-05,
|
||
|
|
"loss": 0.4699,
|
||
|
|
"mean_token_accuracy": 0.837085940875113,
|
||
|
|
"num_tokens": 99907814.0,
|
||
|
|
"step": 232
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4423828125,
|
||
|
|
"epoch": 0.932,
|
||
|
|
"grad_norm": 0.9289735042859542,
|
||
|
|
"learning_rate": 1.6554668197022295e-05,
|
||
|
|
"loss": 0.4776,
|
||
|
|
"mean_token_accuracy": 0.8375649051740766,
|
||
|
|
"num_tokens": 100338810.0,
|
||
|
|
"step": 233
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.438995361328125,
|
||
|
|
"epoch": 0.936,
|
||
|
|
"grad_norm": 0.8004063202017938,
|
||
|
|
"learning_rate": 1.6521281380262216e-05,
|
||
|
|
"loss": 0.473,
|
||
|
|
"mean_token_accuracy": 0.8390795504674315,
|
||
|
|
"num_tokens": 100770751.0,
|
||
|
|
"step": 234
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44610595703125,
|
||
|
|
"epoch": 0.94,
|
||
|
|
"grad_norm": 0.819788697069678,
|
||
|
|
"learning_rate": 1.6487767602017264e-05,
|
||
|
|
"loss": 0.4691,
|
||
|
|
"mean_token_accuracy": 0.8398507405072451,
|
||
|
|
"num_tokens": 101188202.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.441802978515625,
|
||
|
|
"epoch": 0.944,
|
||
|
|
"grad_norm": 0.755037201137922,
|
||
|
|
"learning_rate": 1.6454127514760282e-05,
|
||
|
|
"loss": 0.4775,
|
||
|
|
"mean_token_accuracy": 0.836041983217001,
|
||
|
|
"num_tokens": 101620214.0,
|
||
|
|
"step": 236
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.446502685546875,
|
||
|
|
"epoch": 0.948,
|
||
|
|
"grad_norm": 0.7888771862885081,
|
||
|
|
"learning_rate": 1.6420361773423205e-05,
|
||
|
|
"loss": 0.4828,
|
||
|
|
"mean_token_accuracy": 0.8356077531352639,
|
||
|
|
"num_tokens": 102050717.0,
|
||
|
|
"step": 237
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4493408203125,
|
||
|
|
"epoch": 0.952,
|
||
|
|
"grad_norm": 0.8428575148853099,
|
||
|
|
"learning_rate": 1.6386471035384307e-05,
|
||
|
|
"loss": 0.4781,
|
||
|
|
"mean_token_accuracy": 0.836411502212286,
|
||
|
|
"num_tokens": 102470788.0,
|
||
|
|
"step": 238
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.45257568359375,
|
||
|
|
"epoch": 0.956,
|
||
|
|
"grad_norm": 0.8425284674948922,
|
||
|
|
"learning_rate": 1.6352455960455385e-05,
|
||
|
|
"loss": 0.4798,
|
||
|
|
"mean_token_accuracy": 0.8356124544516206,
|
||
|
|
"num_tokens": 102882366.0,
|
||
|
|
"step": 239
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.441192626953125,
|
||
|
|
"epoch": 0.96,
|
||
|
|
"grad_norm": 0.8625521956786869,
|
||
|
|
"learning_rate": 1.6318317210868936e-05,
|
||
|
|
"loss": 0.4701,
|
||
|
|
"mean_token_accuracy": 0.8408640632405877,
|
||
|
|
"num_tokens": 103335768.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.435089111328125,
|
||
|
|
"epoch": 0.964,
|
||
|
|
"grad_norm": 0.9059896368931234,
|
||
|
|
"learning_rate": 1.6284055451265245e-05,
|
||
|
|
"loss": 0.4627,
|
||
|
|
"mean_token_accuracy": 0.8408188289031386,
|
||
|
|
"num_tokens": 103782147.0,
|
||
|
|
"step": 241
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4449462890625,
|
||
|
|
"epoch": 0.968,
|
||
|
|
"grad_norm": 0.7860174339495051,
|
||
|
|
"learning_rate": 1.624967134867946e-05,
|
||
|
|
"loss": 0.4743,
|
||
|
|
"mean_token_accuracy": 0.8390708761289716,
|
||
|
|
"num_tokens": 104216288.0,
|
||
|
|
"step": 242
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44677734375,
|
||
|
|
"epoch": 0.972,
|
||
|
|
"grad_norm": 0.7432383528681069,
|
||
|
|
"learning_rate": 1.6215165572528598e-05,
|
||
|
|
"loss": 0.4691,
|
||
|
|
"mean_token_accuracy": 0.8398871822282672,
|
||
|
|
"num_tokens": 104632611.0,
|
||
|
|
"step": 243
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.442169189453125,
|
||
|
|
"epoch": 0.976,
|
||
|
|
"grad_norm": 0.7690158727235689,
|
||
|
|
"learning_rate": 1.61805387945985e-05,
|
||
|
|
"loss": 0.4701,
|
||
|
|
"mean_token_accuracy": 0.8372912667691708,
|
||
|
|
"num_tokens": 105046600.0,
|
||
|
|
"step": 244
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.436492919921875,
|
||
|
|
"epoch": 0.98,
|
||
|
|
"grad_norm": 0.7783910183308835,
|
||
|
|
"learning_rate": 1.6145791689030795e-05,
|
||
|
|
"loss": 0.4709,
|
||
|
|
"mean_token_accuracy": 0.8394292127341032,
|
||
|
|
"num_tokens": 105491506.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.433624267578125,
|
||
|
|
"epoch": 0.984,
|
||
|
|
"grad_norm": 0.7473335219744389,
|
||
|
|
"learning_rate": 1.6110924932309725e-05,
|
||
|
|
"loss": 0.4681,
|
||
|
|
"mean_token_accuracy": 0.840594264678657,
|
||
|
|
"num_tokens": 105938102.0,
|
||
|
|
"step": 246
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.441497802734375,
|
||
|
|
"epoch": 0.988,
|
||
|
|
"grad_norm": 0.7524883799556067,
|
||
|
|
"learning_rate": 1.607593920324899e-05,
|
||
|
|
"loss": 0.4787,
|
||
|
|
"mean_token_accuracy": 0.8356803832575679,
|
||
|
|
"num_tokens": 106392341.0,
|
||
|
|
"step": 247
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4404296875,
|
||
|
|
"epoch": 0.992,
|
||
|
|
"grad_norm": 0.6945374760161314,
|
||
|
|
"learning_rate": 1.6040835182978557e-05,
|
||
|
|
"loss": 0.4837,
|
||
|
|
"mean_token_accuracy": 0.8346766140311956,
|
||
|
|
"num_tokens": 106836464.0,
|
||
|
|
"step": 248
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4447021484375,
|
||
|
|
"epoch": 0.996,
|
||
|
|
"grad_norm": 0.7313204414564726,
|
||
|
|
"learning_rate": 1.600561355493137e-05,
|
||
|
|
"loss": 0.473,
|
||
|
|
"mean_token_accuracy": 0.8379186801612377,
|
||
|
|
"num_tokens": 107273885.0,
|
||
|
|
"step": 249
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.437225341796875,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 0.7884335786639071,
|
||
|
|
"learning_rate": 1.5970275004830053e-05,
|
||
|
|
"loss": 0.4731,
|
||
|
|
"mean_token_accuracy": 0.838553256355226,
|
||
|
|
"num_tokens": 107716190.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.449432373046875,
|
||
|
|
"epoch": 1.004,
|
||
|
|
"grad_norm": 0.754742195118407,
|
||
|
|
"learning_rate": 1.5934820220673564e-05,
|
||
|
|
"loss": 0.4277,
|
||
|
|
"mean_token_accuracy": 0.8529959749430418,
|
||
|
|
"num_tokens": 108110329.0,
|
||
|
|
"step": 251
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.43255615234375,
|
||
|
|
"epoch": 1.008,
|
||
|
|
"grad_norm": 0.7759821001286626,
|
||
|
|
"learning_rate": 1.58992498927238e-05,
|
||
|
|
"loss": 0.4445,
|
||
|
|
"mean_token_accuracy": 0.846840132959187,
|
||
|
|
"num_tokens": 108536473.0,
|
||
|
|
"step": 252
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.42926025390625,
|
||
|
|
"epoch": 1.012,
|
||
|
|
"grad_norm": 0.7226143092786326,
|
||
|
|
"learning_rate": 1.5863564713492152e-05,
|
||
|
|
"loss": 0.4461,
|
||
|
|
"mean_token_accuracy": 0.8457893040031195,
|
||
|
|
"num_tokens": 108979948.0,
|
||
|
|
"step": 253
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.430755615234375,
|
||
|
|
"epoch": 1.016,
|
||
|
|
"grad_norm": 0.7085816958286468,
|
||
|
|
"learning_rate": 1.582776537772603e-05,
|
||
|
|
"loss": 0.4304,
|
||
|
|
"mean_token_accuracy": 0.850044415332377,
|
||
|
|
"num_tokens": 109409689.0,
|
||
|
|
"step": 254
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.436248779296875,
|
||
|
|
"epoch": 1.02,
|
||
|
|
"grad_norm": 0.7558632854393661,
|
||
|
|
"learning_rate": 1.5791852582395334e-05,
|
||
|
|
"loss": 0.4484,
|
||
|
|
"mean_token_accuracy": 0.8475431306287646,
|
||
|
|
"num_tokens": 109824009.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.427001953125,
|
||
|
|
"epoch": 1.024,
|
||
|
|
"grad_norm": 0.725801245107027,
|
||
|
|
"learning_rate": 1.5755827026678888e-05,
|
||
|
|
"loss": 0.4287,
|
||
|
|
"mean_token_accuracy": 0.8506967611610889,
|
||
|
|
"num_tokens": 110251290.0,
|
||
|
|
"step": 256
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.429656982421875,
|
||
|
|
"epoch": 1.028,
|
||
|
|
"grad_norm": 0.8015787635643825,
|
||
|
|
"learning_rate": 1.571968941195081e-05,
|
||
|
|
"loss": 0.443,
|
||
|
|
"mean_token_accuracy": 0.8482880908995867,
|
||
|
|
"num_tokens": 110687923.0,
|
||
|
|
"step": 257
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.425628662109375,
|
||
|
|
"epoch": 1.032,
|
||
|
|
"grad_norm": 0.7223789975220349,
|
||
|
|
"learning_rate": 1.5683440441766892e-05,
|
||
|
|
"loss": 0.442,
|
||
|
|
"mean_token_accuracy": 0.8467493932694197,
|
||
|
|
"num_tokens": 111116805.0,
|
||
|
|
"step": 258
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4228515625,
|
||
|
|
"epoch": 1.036,
|
||
|
|
"grad_norm": 0.8059860186796021,
|
||
|
|
"learning_rate": 1.5647080821850868e-05,
|
||
|
|
"loss": 0.4381,
|
||
|
|
"mean_token_accuracy": 0.8475091988220811,
|
||
|
|
"num_tokens": 111550694.0,
|
||
|
|
"step": 259
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.421875,
|
||
|
|
"epoch": 1.04,
|
||
|
|
"grad_norm": 0.7941613733719948,
|
||
|
|
"learning_rate": 1.56106112600807e-05,
|
||
|
|
"loss": 0.4454,
|
||
|
|
"mean_token_accuracy": 0.846760431304574,
|
||
|
|
"num_tokens": 111986669.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.424346923828125,
|
||
|
|
"epoch": 1.044,
|
||
|
|
"grad_norm": 0.7311520474032861,
|
||
|
|
"learning_rate": 1.5574032466474774e-05,
|
||
|
|
"loss": 0.4263,
|
||
|
|
"mean_token_accuracy": 0.8513347879052162,
|
||
|
|
"num_tokens": 112420714.0,
|
||
|
|
"step": 261
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.43096923828125,
|
||
|
|
"epoch": 1.048,
|
||
|
|
"grad_norm": 0.7370202245015283,
|
||
|
|
"learning_rate": 1.5537345153178093e-05,
|
||
|
|
"loss": 0.433,
|
||
|
|
"mean_token_accuracy": 0.8504221336916089,
|
||
|
|
"num_tokens": 112861685.0,
|
||
|
|
"step": 262
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.42218017578125,
|
||
|
|
"epoch": 1.052,
|
||
|
|
"grad_norm": 0.7619459023831388,
|
||
|
|
"learning_rate": 1.5500550034448415e-05,
|
||
|
|
"loss": 0.4321,
|
||
|
|
"mean_token_accuracy": 0.8495560837909579,
|
||
|
|
"num_tokens": 113294965.0,
|
||
|
|
"step": 263
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.418304443359375,
|
||
|
|
"epoch": 1.056,
|
||
|
|
"grad_norm": 0.7462871390183937,
|
||
|
|
"learning_rate": 1.5463647826642324e-05,
|
||
|
|
"loss": 0.4439,
|
||
|
|
"mean_token_accuracy": 0.8437428651377559,
|
||
|
|
"num_tokens": 113736214.0,
|
||
|
|
"step": 264
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.42913818359375,
|
||
|
|
"epoch": 1.06,
|
||
|
|
"grad_norm": 0.7006453946875808,
|
||
|
|
"learning_rate": 1.5426639248201313e-05,
|
||
|
|
"loss": 0.4195,
|
||
|
|
"mean_token_accuracy": 0.8547126511111856,
|
||
|
|
"num_tokens": 114142641.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.413330078125,
|
||
|
|
"epoch": 1.064,
|
||
|
|
"grad_norm": 0.7532504993590574,
|
||
|
|
"learning_rate": 1.538952501963778e-05,
|
||
|
|
"loss": 0.435,
|
||
|
|
"mean_token_accuracy": 0.8491028100252151,
|
||
|
|
"num_tokens": 114593540.0,
|
||
|
|
"step": 266
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41851806640625,
|
||
|
|
"epoch": 1.068,
|
||
|
|
"grad_norm": 0.8163734182435384,
|
||
|
|
"learning_rate": 1.535230586352099e-05,
|
||
|
|
"loss": 0.4179,
|
||
|
|
"mean_token_accuracy": 0.8545977836474776,
|
||
|
|
"num_tokens": 115025921.0,
|
||
|
|
"step": 267
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.421966552734375,
|
||
|
|
"epoch": 1.072,
|
||
|
|
"grad_norm": 0.7162939639785946,
|
||
|
|
"learning_rate": 1.531498250446305e-05,
|
||
|
|
"loss": 0.4387,
|
||
|
|
"mean_token_accuracy": 0.8486642893403769,
|
||
|
|
"num_tokens": 115468784.0,
|
||
|
|
"step": 268
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4249267578125,
|
||
|
|
"epoch": 1.076,
|
||
|
|
"grad_norm": 0.785594909046763,
|
||
|
|
"learning_rate": 1.5277555669104743e-05,
|
||
|
|
"loss": 0.4366,
|
||
|
|
"mean_token_accuracy": 0.8476139353588223,
|
||
|
|
"num_tokens": 115908990.0,
|
||
|
|
"step": 269
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.427642822265625,
|
||
|
|
"epoch": 1.08,
|
||
|
|
"grad_norm": 0.7664902906674754,
|
||
|
|
"learning_rate": 1.5240026086101425e-05,
|
||
|
|
"loss": 0.4268,
|
||
|
|
"mean_token_accuracy": 0.8521448345854878,
|
||
|
|
"num_tokens": 116343811.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.416961669921875,
|
||
|
|
"epoch": 1.084,
|
||
|
|
"grad_norm": 0.7922953636021284,
|
||
|
|
"learning_rate": 1.5202394486108823e-05,
|
||
|
|
"loss": 0.4309,
|
||
|
|
"mean_token_accuracy": 0.8476423183456063,
|
||
|
|
"num_tokens": 116784438.0,
|
||
|
|
"step": 271
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.415924072265625,
|
||
|
|
"epoch": 1.088,
|
||
|
|
"grad_norm": 0.710114511107566,
|
||
|
|
"learning_rate": 1.516466160176881e-05,
|
||
|
|
"loss": 0.4347,
|
||
|
|
"mean_token_accuracy": 0.8488046675920486,
|
||
|
|
"num_tokens": 117221245.0,
|
||
|
|
"step": 272
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.424163818359375,
|
||
|
|
"epoch": 1.092,
|
||
|
|
"grad_norm": 0.9155490792207649,
|
||
|
|
"learning_rate": 1.5126828167695146e-05,
|
||
|
|
"loss": 0.4302,
|
||
|
|
"mean_token_accuracy": 0.8478541998192668,
|
||
|
|
"num_tokens": 117643749.0,
|
||
|
|
"step": 273
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412994384765625,
|
||
|
|
"epoch": 1.096,
|
||
|
|
"grad_norm": 0.7643827412666216,
|
||
|
|
"learning_rate": 1.5088894920459175e-05,
|
||
|
|
"loss": 0.427,
|
||
|
|
"mean_token_accuracy": 0.851541593670845,
|
||
|
|
"num_tokens": 118070664.0,
|
||
|
|
"step": 274
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.416015625,
|
||
|
|
"epoch": 1.1,
|
||
|
|
"grad_norm": 0.7682806867164477,
|
||
|
|
"learning_rate": 1.5050862598575474e-05,
|
||
|
|
"loss": 0.4267,
|
||
|
|
"mean_token_accuracy": 0.8510230127722025,
|
||
|
|
"num_tokens": 118485926.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4150390625,
|
||
|
|
"epoch": 1.104,
|
||
|
|
"grad_norm": 0.7837962133832181,
|
||
|
|
"learning_rate": 1.5012731942487491e-05,
|
||
|
|
"loss": 0.4273,
|
||
|
|
"mean_token_accuracy": 0.8506404822692275,
|
||
|
|
"num_tokens": 118901920.0,
|
||
|
|
"step": 276
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.418975830078125,
|
||
|
|
"epoch": 1.108,
|
||
|
|
"grad_norm": 0.7676000283526232,
|
||
|
|
"learning_rate": 1.4974503694553119e-05,
|
||
|
|
"loss": 0.4277,
|
||
|
|
"mean_token_accuracy": 0.8520775474607944,
|
||
|
|
"num_tokens": 119319898.0,
|
||
|
|
"step": 277
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4183349609375,
|
||
|
|
"epoch": 1.112,
|
||
|
|
"grad_norm": 0.7618435078747199,
|
||
|
|
"learning_rate": 1.4936178599030253e-05,
|
||
|
|
"loss": 0.4334,
|
||
|
|
"mean_token_accuracy": 0.848803554661572,
|
||
|
|
"num_tokens": 119748174.0,
|
||
|
|
"step": 278
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4217529296875,
|
||
|
|
"epoch": 1.116,
|
||
|
|
"grad_norm": 0.760216840464579,
|
||
|
|
"learning_rate": 1.4897757402062285e-05,
|
||
|
|
"loss": 0.4297,
|
||
|
|
"mean_token_accuracy": 0.8503622030839324,
|
||
|
|
"num_tokens": 120189611.0,
|
||
|
|
"step": 279
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.42083740234375,
|
||
|
|
"epoch": 1.12,
|
||
|
|
"grad_norm": 0.8252464400276497,
|
||
|
|
"learning_rate": 1.485924085166359e-05,
|
||
|
|
"loss": 0.4373,
|
||
|
|
"mean_token_accuracy": 0.8503516279160976,
|
||
|
|
"num_tokens": 120625832.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4234619140625,
|
||
|
|
"epoch": 1.124,
|
||
|
|
"grad_norm": 0.7924307965957313,
|
||
|
|
"learning_rate": 1.4820629697704965e-05,
|
||
|
|
"loss": 0.4357,
|
||
|
|
"mean_token_accuracy": 0.848094753921032,
|
||
|
|
"num_tokens": 121034556.0,
|
||
|
|
"step": 281
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41748046875,
|
||
|
|
"epoch": 1.1280000000000001,
|
||
|
|
"grad_norm": 0.8424707489393521,
|
||
|
|
"learning_rate": 1.4781924691899013e-05,
|
||
|
|
"loss": 0.4281,
|
||
|
|
"mean_token_accuracy": 0.8495879424735904,
|
||
|
|
"num_tokens": 121463227.0,
|
||
|
|
"step": 282
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412994384765625,
|
||
|
|
"epoch": 1.1320000000000001,
|
||
|
|
"grad_norm": 0.740284746073995,
|
||
|
|
"learning_rate": 1.4743126587785523e-05,
|
||
|
|
"loss": 0.4252,
|
||
|
|
"mean_token_accuracy": 0.8524118987843394,
|
||
|
|
"num_tokens": 121894963.0,
|
||
|
|
"step": 283
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.424072265625,
|
||
|
|
"epoch": 1.1360000000000001,
|
||
|
|
"grad_norm": 0.7973186891876394,
|
||
|
|
"learning_rate": 1.4704236140716805e-05,
|
||
|
|
"loss": 0.4233,
|
||
|
|
"mean_token_accuracy": 0.8519144328311086,
|
||
|
|
"num_tokens": 122317175.0,
|
||
|
|
"step": 284
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.430908203125,
|
||
|
|
"epoch": 1.1400000000000001,
|
||
|
|
"grad_norm": 0.7192730193942931,
|
||
|
|
"learning_rate": 1.4665254107842965e-05,
|
||
|
|
"loss": 0.4226,
|
||
|
|
"mean_token_accuracy": 0.8517552921548486,
|
||
|
|
"num_tokens": 122714376.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.424774169921875,
|
||
|
|
"epoch": 1.144,
|
||
|
|
"grad_norm": 0.7602530945244642,
|
||
|
|
"learning_rate": 1.4626181248097177e-05,
|
||
|
|
"loss": 0.4259,
|
||
|
|
"mean_token_accuracy": 0.8512626467272639,
|
||
|
|
"num_tokens": 123136047.0,
|
||
|
|
"step": 286
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4298095703125,
|
||
|
|
"epoch": 1.148,
|
||
|
|
"grad_norm": 0.8036233238278768,
|
||
|
|
"learning_rate": 1.4587018322180906e-05,
|
||
|
|
"loss": 0.4327,
|
||
|
|
"mean_token_accuracy": 0.8496435089036822,
|
||
|
|
"num_tokens": 123566182.0,
|
||
|
|
"step": 287
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4158935546875,
|
||
|
|
"epoch": 1.152,
|
||
|
|
"grad_norm": 0.7834701014273616,
|
||
|
|
"learning_rate": 1.4547766092549093e-05,
|
||
|
|
"loss": 0.4372,
|
||
|
|
"mean_token_accuracy": 0.8449214575812221,
|
||
|
|
"num_tokens": 124008901.0,
|
||
|
|
"step": 288
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.423004150390625,
|
||
|
|
"epoch": 1.156,
|
||
|
|
"grad_norm": 0.6971633874960722,
|
||
|
|
"learning_rate": 1.4508425323395319e-05,
|
||
|
|
"loss": 0.4185,
|
||
|
|
"mean_token_accuracy": 0.8519801776856184,
|
||
|
|
"num_tokens": 124425971.0,
|
||
|
|
"step": 289
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41650390625,
|
||
|
|
"epoch": 1.16,
|
||
|
|
"grad_norm": 0.7974135295232867,
|
||
|
|
"learning_rate": 1.4468996780636922e-05,
|
||
|
|
"loss": 0.4345,
|
||
|
|
"mean_token_accuracy": 0.8475042302161455,
|
||
|
|
"num_tokens": 124860194.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.420684814453125,
|
||
|
|
"epoch": 1.164,
|
||
|
|
"grad_norm": 0.7169623212651368,
|
||
|
|
"learning_rate": 1.4429481231900082e-05,
|
||
|
|
"loss": 0.4379,
|
||
|
|
"mean_token_accuracy": 0.8508820924907923,
|
||
|
|
"num_tokens": 125294535.0,
|
||
|
|
"step": 291
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41961669921875,
|
||
|
|
"epoch": 1.168,
|
||
|
|
"grad_norm": 0.7475936880979188,
|
||
|
|
"learning_rate": 1.4389879446504884e-05,
|
||
|
|
"loss": 0.4403,
|
||
|
|
"mean_token_accuracy": 0.8482796754688025,
|
||
|
|
"num_tokens": 125745287.0,
|
||
|
|
"step": 292
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4234619140625,
|
||
|
|
"epoch": 1.172,
|
||
|
|
"grad_norm": 0.7732119440629578,
|
||
|
|
"learning_rate": 1.4350192195450339e-05,
|
||
|
|
"loss": 0.4377,
|
||
|
|
"mean_token_accuracy": 0.8473051218315959,
|
||
|
|
"num_tokens": 126199772.0,
|
||
|
|
"step": 293
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.421722412109375,
|
||
|
|
"epoch": 1.176,
|
||
|
|
"grad_norm": 0.7440857584911619,
|
||
|
|
"learning_rate": 1.4310420251399366e-05,
|
||
|
|
"loss": 0.4353,
|
||
|
|
"mean_token_accuracy": 0.848833603784442,
|
||
|
|
"num_tokens": 126637960.0,
|
||
|
|
"step": 294
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4197998046875,
|
||
|
|
"epoch": 1.18,
|
||
|
|
"grad_norm": 0.7399667547958811,
|
||
|
|
"learning_rate": 1.4270564388663761e-05,
|
||
|
|
"loss": 0.4402,
|
||
|
|
"mean_token_accuracy": 0.8460560040548444,
|
||
|
|
"num_tokens": 127071787.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.42413330078125,
|
||
|
|
"epoch": 1.184,
|
||
|
|
"grad_norm": 0.7059251150089407,
|
||
|
|
"learning_rate": 1.4230625383189107e-05,
|
||
|
|
"loss": 0.4514,
|
||
|
|
"mean_token_accuracy": 0.8442188752815127,
|
||
|
|
"num_tokens": 127491434.0,
|
||
|
|
"step": 296
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.418487548828125,
|
||
|
|
"epoch": 1.188,
|
||
|
|
"grad_norm": 0.7554546148656285,
|
||
|
|
"learning_rate": 1.4190604012539684e-05,
|
||
|
|
"loss": 0.4234,
|
||
|
|
"mean_token_accuracy": 0.8512083925306797,
|
||
|
|
"num_tokens": 127913023.0,
|
||
|
|
"step": 297
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.422576904296875,
|
||
|
|
"epoch": 1.192,
|
||
|
|
"grad_norm": 0.7324492293153907,
|
||
|
|
"learning_rate": 1.415050105588332e-05,
|
||
|
|
"loss": 0.4286,
|
||
|
|
"mean_token_accuracy": 0.8506187023594975,
|
||
|
|
"num_tokens": 128341789.0,
|
||
|
|
"step": 298
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41864013671875,
|
||
|
|
"epoch": 1.196,
|
||
|
|
"grad_norm": 0.7250589650165655,
|
||
|
|
"learning_rate": 1.411031729397622e-05,
|
||
|
|
"loss": 0.4245,
|
||
|
|
"mean_token_accuracy": 0.8525028061121702,
|
||
|
|
"num_tokens": 128774458.0,
|
||
|
|
"step": 299
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41943359375,
|
||
|
|
"epoch": 1.2,
|
||
|
|
"grad_norm": 0.6667092392283802,
|
||
|
|
"learning_rate": 1.4070053509147777e-05,
|
||
|
|
"loss": 0.4209,
|
||
|
|
"mean_token_accuracy": 0.8496069815009832,
|
||
|
|
"num_tokens": 129191458.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41461181640625,
|
||
|
|
"epoch": 1.204,
|
||
|
|
"grad_norm": 1.0720090172879642,
|
||
|
|
"learning_rate": 1.4029710485285324e-05,
|
||
|
|
"loss": 0.4186,
|
||
|
|
"mean_token_accuracy": 0.8521048631519079,
|
||
|
|
"num_tokens": 129628820.0,
|
||
|
|
"step": 301
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.414794921875,
|
||
|
|
"epoch": 1.208,
|
||
|
|
"grad_norm": 0.7120866685891664,
|
||
|
|
"learning_rate": 1.3989289007818898e-05,
|
||
|
|
"loss": 0.4251,
|
||
|
|
"mean_token_accuracy": 0.8497876860201359,
|
||
|
|
"num_tokens": 130057403.0,
|
||
|
|
"step": 302
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4217529296875,
|
||
|
|
"epoch": 1.212,
|
||
|
|
"grad_norm": 0.7247300576353728,
|
||
|
|
"learning_rate": 1.3948789863705914e-05,
|
||
|
|
"loss": 0.427,
|
||
|
|
"mean_token_accuracy": 0.8510121935978532,
|
||
|
|
"num_tokens": 130470556.0,
|
||
|
|
"step": 303
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4149169921875,
|
||
|
|
"epoch": 1.216,
|
||
|
|
"grad_norm": 0.6748116451015059,
|
||
|
|
"learning_rate": 1.3908213841415878e-05,
|
||
|
|
"loss": 0.4254,
|
||
|
|
"mean_token_accuracy": 0.8510571764782071,
|
||
|
|
"num_tokens": 130894995.0,
|
||
|
|
"step": 304
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.42388916015625,
|
||
|
|
"epoch": 1.22,
|
||
|
|
"grad_norm": 1.4959872698176582,
|
||
|
|
"learning_rate": 1.3867561730915016e-05,
|
||
|
|
"loss": 0.4265,
|
||
|
|
"mean_token_accuracy": 0.851023062132299,
|
||
|
|
"num_tokens": 131311074.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4263916015625,
|
||
|
|
"epoch": 1.224,
|
||
|
|
"grad_norm": 0.7202236831258392,
|
||
|
|
"learning_rate": 1.3826834323650899e-05,
|
||
|
|
"loss": 0.423,
|
||
|
|
"mean_token_accuracy": 0.8530107829719782,
|
||
|
|
"num_tokens": 131728255.0,
|
||
|
|
"step": 306
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41998291015625,
|
||
|
|
"epoch": 1.228,
|
||
|
|
"grad_norm": 0.6901114596376479,
|
||
|
|
"learning_rate": 1.3786032412537037e-05,
|
||
|
|
"loss": 0.4259,
|
||
|
|
"mean_token_accuracy": 0.8518217569217086,
|
||
|
|
"num_tokens": 132151390.0,
|
||
|
|
"step": 307
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.419921875,
|
||
|
|
"epoch": 1.232,
|
||
|
|
"grad_norm": 0.7134485132840357,
|
||
|
|
"learning_rate": 1.3745156791937433e-05,
|
||
|
|
"loss": 0.4216,
|
||
|
|
"mean_token_accuracy": 0.8524185344576836,
|
||
|
|
"num_tokens": 132583881.0,
|
||
|
|
"step": 308
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.419158935546875,
|
||
|
|
"epoch": 1.236,
|
||
|
|
"grad_norm": 0.7723060500219715,
|
||
|
|
"learning_rate": 1.370420825765114e-05,
|
||
|
|
"loss": 0.4276,
|
||
|
|
"mean_token_accuracy": 0.8506783451884985,
|
||
|
|
"num_tokens": 133012775.0,
|
||
|
|
"step": 309
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.415191650390625,
|
||
|
|
"epoch": 1.24,
|
||
|
|
"grad_norm": 0.719570520068601,
|
||
|
|
"learning_rate": 1.3663187606896733e-05,
|
||
|
|
"loss": 0.4193,
|
||
|
|
"mean_token_accuracy": 0.8533845813944936,
|
||
|
|
"num_tokens": 133445980.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412811279296875,
|
||
|
|
"epoch": 1.244,
|
||
|
|
"grad_norm": 0.7968539654742268,
|
||
|
|
"learning_rate": 1.3622095638296827e-05,
|
||
|
|
"loss": 0.4274,
|
||
|
|
"mean_token_accuracy": 0.8506917888298631,
|
||
|
|
"num_tokens": 133880798.0,
|
||
|
|
"step": 311
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412811279296875,
|
||
|
|
"epoch": 1.248,
|
||
|
|
"grad_norm": 1.2020444525143104,
|
||
|
|
"learning_rate": 1.3580933151862495e-05,
|
||
|
|
"loss": 0.4272,
|
||
|
|
"mean_token_accuracy": 0.8524878853932023,
|
||
|
|
"num_tokens": 134330425.0,
|
||
|
|
"step": 312
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.421600341796875,
|
||
|
|
"epoch": 1.252,
|
||
|
|
"grad_norm": 0.7513714636205986,
|
||
|
|
"learning_rate": 1.3539700948977718e-05,
|
||
|
|
"loss": 0.4281,
|
||
|
|
"mean_token_accuracy": 0.851118192076683,
|
||
|
|
"num_tokens": 134753628.0,
|
||
|
|
"step": 313
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.430633544921875,
|
||
|
|
"epoch": 1.256,
|
||
|
|
"grad_norm": 0.7379697542458173,
|
||
|
|
"learning_rate": 1.349839983238376e-05,
|
||
|
|
"loss": 0.4173,
|
||
|
|
"mean_token_accuracy": 0.853589472360909,
|
||
|
|
"num_tokens": 135158015.0,
|
||
|
|
"step": 314
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.42706298828125,
|
||
|
|
"epoch": 1.26,
|
||
|
|
"grad_norm": 0.7512399517621322,
|
||
|
|
"learning_rate": 1.3457030606163564e-05,
|
||
|
|
"loss": 0.4359,
|
||
|
|
"mean_token_accuracy": 0.8488859990611672,
|
||
|
|
"num_tokens": 135581273.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.424468994140625,
|
||
|
|
"epoch": 1.264,
|
||
|
|
"grad_norm": 0.7572120063483,
|
||
|
|
"learning_rate": 1.341559407572608e-05,
|
||
|
|
"loss": 0.426,
|
||
|
|
"mean_token_accuracy": 0.8512191195040941,
|
||
|
|
"num_tokens": 136035594.0,
|
||
|
|
"step": 316
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.424468994140625,
|
||
|
|
"epoch": 1.268,
|
||
|
|
"grad_norm": 0.702495833986174,
|
||
|
|
"learning_rate": 1.3374091047790585e-05,
|
||
|
|
"loss": 0.4383,
|
||
|
|
"mean_token_accuracy": 0.8475337652489543,
|
||
|
|
"num_tokens": 136456574.0,
|
||
|
|
"step": 317
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4202880859375,
|
||
|
|
"epoch": 1.272,
|
||
|
|
"grad_norm": 0.7530534625950329,
|
||
|
|
"learning_rate": 1.3332522330370991e-05,
|
||
|
|
"loss": 0.438,
|
||
|
|
"mean_token_accuracy": 0.8453158177435398,
|
||
|
|
"num_tokens": 136915099.0,
|
||
|
|
"step": 318
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4293212890625,
|
||
|
|
"epoch": 1.276,
|
||
|
|
"grad_norm": 0.7133580987259571,
|
||
|
|
"learning_rate": 1.32908887327601e-05,
|
||
|
|
"loss": 0.4198,
|
||
|
|
"mean_token_accuracy": 0.8535940377041698,
|
||
|
|
"num_tokens": 137329041.0,
|
||
|
|
"step": 319
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4287109375,
|
||
|
|
"epoch": 1.28,
|
||
|
|
"grad_norm": 0.7716543431926535,
|
||
|
|
"learning_rate": 1.3249191065513857e-05,
|
||
|
|
"loss": 0.4364,
|
||
|
|
"mean_token_accuracy": 0.8495151000097394,
|
||
|
|
"num_tokens": 137733745.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41912841796875,
|
||
|
|
"epoch": 1.284,
|
||
|
|
"grad_norm": 0.7482800970820215,
|
||
|
|
"learning_rate": 1.3207430140435557e-05,
|
||
|
|
"loss": 0.4147,
|
||
|
|
"mean_token_accuracy": 0.8556731203570962,
|
||
|
|
"num_tokens": 138194389.0,
|
||
|
|
"step": 321
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.420257568359375,
|
||
|
|
"epoch": 1.288,
|
||
|
|
"grad_norm": 0.7322424259031981,
|
||
|
|
"learning_rate": 1.316560677056006e-05,
|
||
|
|
"loss": 0.4273,
|
||
|
|
"mean_token_accuracy": 0.8498243819922209,
|
||
|
|
"num_tokens": 138625019.0,
|
||
|
|
"step": 322
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.42205810546875,
|
||
|
|
"epoch": 1.292,
|
||
|
|
"grad_norm": 0.7586819861154115,
|
||
|
|
"learning_rate": 1.3123721770137945e-05,
|
||
|
|
"loss": 0.421,
|
||
|
|
"mean_token_accuracy": 0.8542669964954257,
|
||
|
|
"num_tokens": 139069471.0,
|
||
|
|
"step": 323
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.425384521484375,
|
||
|
|
"epoch": 1.296,
|
||
|
|
"grad_norm": 0.7382298644890732,
|
||
|
|
"learning_rate": 1.3081775954619658e-05,
|
||
|
|
"loss": 0.4258,
|
||
|
|
"mean_token_accuracy": 0.8529874803498387,
|
||
|
|
"num_tokens": 139499294.0,
|
||
|
|
"step": 324
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.425506591796875,
|
||
|
|
"epoch": 1.3,
|
||
|
|
"grad_norm": 0.7549864771011471,
|
||
|
|
"learning_rate": 1.3039770140639654e-05,
|
||
|
|
"loss": 0.4143,
|
||
|
|
"mean_token_accuracy": 0.8556197742000222,
|
||
|
|
"num_tokens": 139901756.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.420074462890625,
|
||
|
|
"epoch": 1.304,
|
||
|
|
"grad_norm": 0.7358581503464654,
|
||
|
|
"learning_rate": 1.2997705146000472e-05,
|
||
|
|
"loss": 0.4115,
|
||
|
|
"mean_token_accuracy": 0.8551269033923745,
|
||
|
|
"num_tokens": 140348225.0,
|
||
|
|
"step": 326
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.413726806640625,
|
||
|
|
"epoch": 1.308,
|
||
|
|
"grad_norm": 0.7236753643260282,
|
||
|
|
"learning_rate": 1.2955581789656844e-05,
|
||
|
|
"loss": 0.422,
|
||
|
|
"mean_token_accuracy": 0.8521746266633272,
|
||
|
|
"num_tokens": 140795117.0,
|
||
|
|
"step": 327
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.414886474609375,
|
||
|
|
"epoch": 1.312,
|
||
|
|
"grad_norm": 0.7232212062127383,
|
||
|
|
"learning_rate": 1.2913400891699714e-05,
|
||
|
|
"loss": 0.419,
|
||
|
|
"mean_token_accuracy": 0.8528529489412904,
|
||
|
|
"num_tokens": 141245270.0,
|
||
|
|
"step": 328
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4117431640625,
|
||
|
|
"epoch": 1.316,
|
||
|
|
"grad_norm": 0.7379388409532525,
|
||
|
|
"learning_rate": 1.2871163273340309e-05,
|
||
|
|
"loss": 0.4279,
|
||
|
|
"mean_token_accuracy": 0.8515938762575388,
|
||
|
|
"num_tokens": 141698417.0,
|
||
|
|
"step": 329
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.421539306640625,
|
||
|
|
"epoch": 1.32,
|
||
|
|
"grad_norm": 0.7153426383003381,
|
||
|
|
"learning_rate": 1.2828869756894122e-05,
|
||
|
|
"loss": 0.4067,
|
||
|
|
"mean_token_accuracy": 0.8577967891469598,
|
||
|
|
"num_tokens": 142122221.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41448974609375,
|
||
|
|
"epoch": 1.324,
|
||
|
|
"grad_norm": 0.7260890688092612,
|
||
|
|
"learning_rate": 1.2786521165764923e-05,
|
||
|
|
"loss": 0.4191,
|
||
|
|
"mean_token_accuracy": 0.8531659161671996,
|
||
|
|
"num_tokens": 142551506.0,
|
||
|
|
"step": 331
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41180419921875,
|
||
|
|
"epoch": 1.328,
|
||
|
|
"grad_norm": 0.6842179406194782,
|
||
|
|
"learning_rate": 1.2744118324428716e-05,
|
||
|
|
"loss": 0.4156,
|
||
|
|
"mean_token_accuracy": 0.8547742431983352,
|
||
|
|
"num_tokens": 142975689.0,
|
||
|
|
"step": 332
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.414154052734375,
|
||
|
|
"epoch": 1.332,
|
||
|
|
"grad_norm": 0.914221019274642,
|
||
|
|
"learning_rate": 1.2701662058417687e-05,
|
||
|
|
"loss": 0.4278,
|
||
|
|
"mean_token_accuracy": 0.851158537901938,
|
||
|
|
"num_tokens": 143394496.0,
|
||
|
|
"step": 333
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412353515625,
|
||
|
|
"epoch": 1.336,
|
||
|
|
"grad_norm": 0.6561939926153415,
|
||
|
|
"learning_rate": 1.2659153194304144e-05,
|
||
|
|
"loss": 0.4046,
|
||
|
|
"mean_token_accuracy": 0.8565410729497671,
|
||
|
|
"num_tokens": 143824087.0,
|
||
|
|
"step": 334
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.409637451171875,
|
||
|
|
"epoch": 1.34,
|
||
|
|
"grad_norm": 0.73886055368417,
|
||
|
|
"learning_rate": 1.2616592559684408e-05,
|
||
|
|
"loss": 0.4209,
|
||
|
|
"mean_token_accuracy": 0.8535389620810747,
|
||
|
|
"num_tokens": 144261140.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.419464111328125,
|
||
|
|
"epoch": 1.3439999999999999,
|
||
|
|
"grad_norm": 0.6933179239547224,
|
||
|
|
"learning_rate": 1.257398098316272e-05,
|
||
|
|
"loss": 0.4247,
|
||
|
|
"mean_token_accuracy": 0.8519382746890187,
|
||
|
|
"num_tokens": 144678622.0,
|
||
|
|
"step": 336
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.421630859375,
|
||
|
|
"epoch": 1.3479999999999999,
|
||
|
|
"grad_norm": 0.6713699178175702,
|
||
|
|
"learning_rate": 1.2531319294335084e-05,
|
||
|
|
"loss": 0.4128,
|
||
|
|
"mean_token_accuracy": 0.8543006032705307,
|
||
|
|
"num_tokens": 145100676.0,
|
||
|
|
"step": 337
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.413543701171875,
|
||
|
|
"epoch": 1.3519999999999999,
|
||
|
|
"grad_norm": 0.6525192309473724,
|
||
|
|
"learning_rate": 1.2488608323773148e-05,
|
||
|
|
"loss": 0.4175,
|
||
|
|
"mean_token_accuracy": 0.8539420170709491,
|
||
|
|
"num_tokens": 145540336.0,
|
||
|
|
"step": 338
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41851806640625,
|
||
|
|
"epoch": 1.3559999999999999,
|
||
|
|
"grad_norm": 0.6846281269083487,
|
||
|
|
"learning_rate": 1.2445848903008001e-05,
|
||
|
|
"loss": 0.4153,
|
||
|
|
"mean_token_accuracy": 0.856916569173336,
|
||
|
|
"num_tokens": 145962134.0,
|
||
|
|
"step": 339
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.413726806640625,
|
||
|
|
"epoch": 1.3599999999999999,
|
||
|
|
"grad_norm": 0.7375225517442358,
|
||
|
|
"learning_rate": 1.2403041864514005e-05,
|
||
|
|
"loss": 0.4176,
|
||
|
|
"mean_token_accuracy": 0.8525944352149963,
|
||
|
|
"num_tokens": 146388328.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.420562744140625,
|
||
|
|
"epoch": 1.3639999999999999,
|
||
|
|
"grad_norm": 0.6746771657147853,
|
||
|
|
"learning_rate": 1.2360188041692582e-05,
|
||
|
|
"loss": 0.4168,
|
||
|
|
"mean_token_accuracy": 0.8548533888533711,
|
||
|
|
"num_tokens": 146815071.0,
|
||
|
|
"step": 341
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41461181640625,
|
||
|
|
"epoch": 1.3679999999999999,
|
||
|
|
"grad_norm": 0.6882112206386428,
|
||
|
|
"learning_rate": 1.2317288268855988e-05,
|
||
|
|
"loss": 0.4154,
|
||
|
|
"mean_token_accuracy": 0.8558593699708581,
|
||
|
|
"num_tokens": 147255681.0,
|
||
|
|
"step": 342
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41448974609375,
|
||
|
|
"epoch": 1.3719999999999999,
|
||
|
|
"grad_norm": 0.682300023985118,
|
||
|
|
"learning_rate": 1.2274343381211067e-05,
|
||
|
|
"loss": 0.4103,
|
||
|
|
"mean_token_accuracy": 0.8562826663255692,
|
||
|
|
"num_tokens": 147692081.0,
|
||
|
|
"step": 343
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.410400390625,
|
||
|
|
"epoch": 1.376,
|
||
|
|
"grad_norm": 0.7228748460103065,
|
||
|
|
"learning_rate": 1.2231354214842999e-05,
|
||
|
|
"loss": 0.4122,
|
||
|
|
"mean_token_accuracy": 0.8531584572046995,
|
||
|
|
"num_tokens": 148113667.0,
|
||
|
|
"step": 344
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412384033203125,
|
||
|
|
"epoch": 1.38,
|
||
|
|
"grad_norm": 0.7102490034223478,
|
||
|
|
"learning_rate": 1.2188321606699016e-05,
|
||
|
|
"loss": 0.43,
|
||
|
|
"mean_token_accuracy": 0.8523981813341379,
|
||
|
|
"num_tokens": 148560765.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.411895751953125,
|
||
|
|
"epoch": 1.384,
|
||
|
|
"grad_norm": 0.6859621285140972,
|
||
|
|
"learning_rate": 1.2145246394572107e-05,
|
||
|
|
"loss": 0.427,
|
||
|
|
"mean_token_accuracy": 0.8505155732855201,
|
||
|
|
"num_tokens": 149006467.0,
|
||
|
|
"step": 346
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41748046875,
|
||
|
|
"epoch": 1.388,
|
||
|
|
"grad_norm": 0.7041765825063732,
|
||
|
|
"learning_rate": 1.2102129417084713e-05,
|
||
|
|
"loss": 0.4233,
|
||
|
|
"mean_token_accuracy": 0.8504170291125774,
|
||
|
|
"num_tokens": 149441379.0,
|
||
|
|
"step": 347
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.418243408203125,
|
||
|
|
"epoch": 1.392,
|
||
|
|
"grad_norm": 0.7126851691187697,
|
||
|
|
"learning_rate": 1.205897151367239e-05,
|
||
|
|
"loss": 0.4149,
|
||
|
|
"mean_token_accuracy": 0.8563994932919741,
|
||
|
|
"num_tokens": 149875837.0,
|
||
|
|
"step": 348
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41705322265625,
|
||
|
|
"epoch": 1.396,
|
||
|
|
"grad_norm": 0.7061404630466647,
|
||
|
|
"learning_rate": 1.201577352456748e-05,
|
||
|
|
"loss": 0.4202,
|
||
|
|
"mean_token_accuracy": 0.8534773541614413,
|
||
|
|
"num_tokens": 150319725.0,
|
||
|
|
"step": 349
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41558837890625,
|
||
|
|
"epoch": 1.4,
|
||
|
|
"grad_norm": 0.7049990162693296,
|
||
|
|
"learning_rate": 1.1972536290782738e-05,
|
||
|
|
"loss": 0.413,
|
||
|
|
"mean_token_accuracy": 0.85490408167243,
|
||
|
|
"num_tokens": 150757199.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.410308837890625,
|
||
|
|
"epoch": 1.404,
|
||
|
|
"grad_norm": 0.698070692673497,
|
||
|
|
"learning_rate": 1.192926065409497e-05,
|
||
|
|
"loss": 0.413,
|
||
|
|
"mean_token_accuracy": 0.8535341378301382,
|
||
|
|
"num_tokens": 151206497.0,
|
||
|
|
"step": 351
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40826416015625,
|
||
|
|
"epoch": 1.408,
|
||
|
|
"grad_norm": 0.7342465296030858,
|
||
|
|
"learning_rate": 1.1885947457028637e-05,
|
||
|
|
"loss": 0.4191,
|
||
|
|
"mean_token_accuracy": 0.8515512710437179,
|
||
|
|
"num_tokens": 151636335.0,
|
||
|
|
"step": 352
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407623291015625,
|
||
|
|
"epoch": 1.412,
|
||
|
|
"grad_norm": 0.7193569965057444,
|
||
|
|
"learning_rate": 1.1842597542839463e-05,
|
||
|
|
"loss": 0.4108,
|
||
|
|
"mean_token_accuracy": 0.8569664945825934,
|
||
|
|
"num_tokens": 152070244.0,
|
||
|
|
"step": 353
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41033935546875,
|
||
|
|
"epoch": 1.416,
|
||
|
|
"grad_norm": 0.7140123108306045,
|
||
|
|
"learning_rate": 1.1799211755497997e-05,
|
||
|
|
"loss": 0.4149,
|
||
|
|
"mean_token_accuracy": 0.8563533332198858,
|
||
|
|
"num_tokens": 152496447.0,
|
||
|
|
"step": 354
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4169921875,
|
||
|
|
"epoch": 1.42,
|
||
|
|
"grad_norm": 0.6982363640960147,
|
||
|
|
"learning_rate": 1.1755790939673208e-05,
|
||
|
|
"loss": 0.4084,
|
||
|
|
"mean_token_accuracy": 0.8563586985692382,
|
||
|
|
"num_tokens": 152903744.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.415740966796875,
|
||
|
|
"epoch": 1.424,
|
||
|
|
"grad_norm": 0.6975765355838127,
|
||
|
|
"learning_rate": 1.171233594071602e-05,
|
||
|
|
"loss": 0.4129,
|
||
|
|
"mean_token_accuracy": 0.856822595000267,
|
||
|
|
"num_tokens": 153335756.0,
|
||
|
|
"step": 356
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4200439453125,
|
||
|
|
"epoch": 1.428,
|
||
|
|
"grad_norm": 0.7181027926510303,
|
||
|
|
"learning_rate": 1.1668847604642861e-05,
|
||
|
|
"loss": 0.3995,
|
||
|
|
"mean_token_accuracy": 0.8599634571000934,
|
||
|
|
"num_tokens": 153755052.0,
|
||
|
|
"step": 357
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41363525390625,
|
||
|
|
"epoch": 1.432,
|
||
|
|
"grad_norm": 0.6699596756433271,
|
||
|
|
"learning_rate": 1.1625326778119197e-05,
|
||
|
|
"loss": 0.4023,
|
||
|
|
"mean_token_accuracy": 0.8575366428121924,
|
||
|
|
"num_tokens": 154198817.0,
|
||
|
|
"step": 358
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41229248046875,
|
||
|
|
"epoch": 1.436,
|
||
|
|
"grad_norm": 0.6895274286700186,
|
||
|
|
"learning_rate": 1.1581774308443042e-05,
|
||
|
|
"loss": 0.4093,
|
||
|
|
"mean_token_accuracy": 0.855594202876091,
|
||
|
|
"num_tokens": 154642259.0,
|
||
|
|
"step": 359
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407135009765625,
|
||
|
|
"epoch": 1.44,
|
||
|
|
"grad_norm": 0.7637445241754676,
|
||
|
|
"learning_rate": 1.153819104352846e-05,
|
||
|
|
"loss": 0.4172,
|
||
|
|
"mean_token_accuracy": 0.8560828929767013,
|
||
|
|
"num_tokens": 155073383.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.408203125,
|
||
|
|
"epoch": 1.444,
|
||
|
|
"grad_norm": 0.6986903239763986,
|
||
|
|
"learning_rate": 1.1494577831889066e-05,
|
||
|
|
"loss": 0.4234,
|
||
|
|
"mean_token_accuracy": 0.8529677856713533,
|
||
|
|
"num_tokens": 155509328.0,
|
||
|
|
"step": 361
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40765380859375,
|
||
|
|
"epoch": 1.448,
|
||
|
|
"grad_norm": 0.6807334508058177,
|
||
|
|
"learning_rate": 1.1450935522621502e-05,
|
||
|
|
"loss": 0.4156,
|
||
|
|
"mean_token_accuracy": 0.8541600769385695,
|
||
|
|
"num_tokens": 155952128.0,
|
||
|
|
"step": 362
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.414947509765625,
|
||
|
|
"epoch": 1.452,
|
||
|
|
"grad_norm": 0.7146218464194601,
|
||
|
|
"learning_rate": 1.1407264965388907e-05,
|
||
|
|
"loss": 0.4197,
|
||
|
|
"mean_token_accuracy": 0.8527621440589428,
|
||
|
|
"num_tokens": 156381836.0,
|
||
|
|
"step": 363
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41705322265625,
|
||
|
|
"epoch": 1.456,
|
||
|
|
"grad_norm": 0.6907629508669298,
|
||
|
|
"learning_rate": 1.1363567010404364e-05,
|
||
|
|
"loss": 0.4082,
|
||
|
|
"mean_token_accuracy": 0.8582943920046091,
|
||
|
|
"num_tokens": 156818448.0,
|
||
|
|
"step": 364
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412445068359375,
|
||
|
|
"epoch": 1.46,
|
||
|
|
"grad_norm": 0.7112236492265632,
|
||
|
|
"learning_rate": 1.1319842508414365e-05,
|
||
|
|
"loss": 0.4127,
|
||
|
|
"mean_token_accuracy": 0.8547119218856096,
|
||
|
|
"num_tokens": 157257517.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41461181640625,
|
||
|
|
"epoch": 1.464,
|
||
|
|
"grad_norm": 0.6792365630415643,
|
||
|
|
"learning_rate": 1.1276092310682242e-05,
|
||
|
|
"loss": 0.4181,
|
||
|
|
"mean_token_accuracy": 0.854391559958458,
|
||
|
|
"num_tokens": 157696293.0,
|
||
|
|
"step": 366
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.414276123046875,
|
||
|
|
"epoch": 1.468,
|
||
|
|
"grad_norm": 0.7272012442546584,
|
||
|
|
"learning_rate": 1.1232317268971586e-05,
|
||
|
|
"loss": 0.4045,
|
||
|
|
"mean_token_accuracy": 0.8570738714188337,
|
||
|
|
"num_tokens": 158124347.0,
|
||
|
|
"step": 367
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4097900390625,
|
||
|
|
"epoch": 1.472,
|
||
|
|
"grad_norm": 0.7650247202111974,
|
||
|
|
"learning_rate": 1.118851823552968e-05,
|
||
|
|
"loss": 0.414,
|
||
|
|
"mean_token_accuracy": 0.8557765521109104,
|
||
|
|
"num_tokens": 158544583.0,
|
||
|
|
"step": 368
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407806396484375,
|
||
|
|
"epoch": 1.476,
|
||
|
|
"grad_norm": 0.7466614197665594,
|
||
|
|
"learning_rate": 1.1144696063070884e-05,
|
||
|
|
"loss": 0.4115,
|
||
|
|
"mean_token_accuracy": 0.8575149001553655,
|
||
|
|
"num_tokens": 158982048.0,
|
||
|
|
"step": 369
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.404632568359375,
|
||
|
|
"epoch": 1.48,
|
||
|
|
"grad_norm": 0.7133350056171555,
|
||
|
|
"learning_rate": 1.1100851604760057e-05,
|
||
|
|
"loss": 0.4122,
|
||
|
|
"mean_token_accuracy": 0.8557309806346893,
|
||
|
|
"num_tokens": 159419154.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40716552734375,
|
||
|
|
"epoch": 1.484,
|
||
|
|
"grad_norm": 0.7085938932945478,
|
||
|
|
"learning_rate": 1.1056985714195931e-05,
|
||
|
|
"loss": 0.4077,
|
||
|
|
"mean_token_accuracy": 0.8581976741552353,
|
||
|
|
"num_tokens": 159844254.0,
|
||
|
|
"step": 371
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.413116455078125,
|
||
|
|
"epoch": 1.488,
|
||
|
|
"grad_norm": 0.7122679402004573,
|
||
|
|
"learning_rate": 1.1013099245394502e-05,
|
||
|
|
"loss": 0.4228,
|
||
|
|
"mean_token_accuracy": 0.8539408091455698,
|
||
|
|
"num_tokens": 160274508.0,
|
||
|
|
"step": 372
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412628173828125,
|
||
|
|
"epoch": 1.492,
|
||
|
|
"grad_norm": 0.7014272852357373,
|
||
|
|
"learning_rate": 1.0969193052772396e-05,
|
||
|
|
"loss": 0.4035,
|
||
|
|
"mean_token_accuracy": 0.8589663235470653,
|
||
|
|
"num_tokens": 160699134.0,
|
||
|
|
"step": 373
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.408447265625,
|
||
|
|
"epoch": 1.496,
|
||
|
|
"grad_norm": 0.720115682623306,
|
||
|
|
"learning_rate": 1.092526799113024e-05,
|
||
|
|
"loss": 0.4053,
|
||
|
|
"mean_token_accuracy": 0.8574986280873418,
|
||
|
|
"num_tokens": 161170970.0,
|
||
|
|
"step": 374
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41668701171875,
|
||
|
|
"epoch": 1.5,
|
||
|
|
"grad_norm": 0.7503724888233894,
|
||
|
|
"learning_rate": 1.088132491563602e-05,
|
||
|
|
"loss": 0.4111,
|
||
|
|
"mean_token_accuracy": 0.854155614040792,
|
||
|
|
"num_tokens": 161605197.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.410247802734375,
|
||
|
|
"epoch": 1.504,
|
||
|
|
"grad_norm": 0.6623018660280868,
|
||
|
|
"learning_rate": 1.0837364681808423e-05,
|
||
|
|
"loss": 0.4003,
|
||
|
|
"mean_token_accuracy": 0.8586085420101881,
|
||
|
|
"num_tokens": 162032207.0,
|
||
|
|
"step": 376
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.410400390625,
|
||
|
|
"epoch": 1.508,
|
||
|
|
"grad_norm": 0.7136835157927635,
|
||
|
|
"learning_rate": 1.0793388145500199e-05,
|
||
|
|
"loss": 0.4024,
|
||
|
|
"mean_token_accuracy": 0.8600826943293214,
|
||
|
|
"num_tokens": 162463665.0,
|
||
|
|
"step": 377
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40423583984375,
|
||
|
|
"epoch": 1.512,
|
||
|
|
"grad_norm": 0.7603498575844098,
|
||
|
|
"learning_rate": 1.0749396162881474e-05,
|
||
|
|
"loss": 0.4315,
|
||
|
|
"mean_token_accuracy": 0.8493955200538039,
|
||
|
|
"num_tokens": 162905453.0,
|
||
|
|
"step": 378
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.411834716796875,
|
||
|
|
"epoch": 1.516,
|
||
|
|
"grad_norm": 0.6600998313853261,
|
||
|
|
"learning_rate": 1.070538959042311e-05,
|
||
|
|
"loss": 0.4086,
|
||
|
|
"mean_token_accuracy": 0.8573091719299555,
|
||
|
|
"num_tokens": 163346488.0,
|
||
|
|
"step": 379
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.417205810546875,
|
||
|
|
"epoch": 1.52,
|
||
|
|
"grad_norm": 0.7293829613677237,
|
||
|
|
"learning_rate": 1.0661369284880005e-05,
|
||
|
|
"loss": 0.4247,
|
||
|
|
"mean_token_accuracy": 0.8541067717596889,
|
||
|
|
"num_tokens": 163778736.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.415802001953125,
|
||
|
|
"epoch": 1.524,
|
||
|
|
"grad_norm": 0.7515340530308919,
|
||
|
|
"learning_rate": 1.0617336103274425e-05,
|
||
|
|
"loss": 0.4049,
|
||
|
|
"mean_token_accuracy": 0.8578369095921516,
|
||
|
|
"num_tokens": 164222876.0,
|
||
|
|
"step": 381
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.415863037109375,
|
||
|
|
"epoch": 1.528,
|
||
|
|
"grad_norm": 0.6745327663355307,
|
||
|
|
"learning_rate": 1.057329090287932e-05,
|
||
|
|
"loss": 0.4067,
|
||
|
|
"mean_token_accuracy": 0.8564223228022456,
|
||
|
|
"num_tokens": 164640372.0,
|
||
|
|
"step": 382
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.411102294921875,
|
||
|
|
"epoch": 1.532,
|
||
|
|
"grad_norm": 0.739782284340543,
|
||
|
|
"learning_rate": 1.0529234541201631e-05,
|
||
|
|
"loss": 0.4214,
|
||
|
|
"mean_token_accuracy": 0.8527001310139894,
|
||
|
|
"num_tokens": 165076369.0,
|
||
|
|
"step": 383
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41455078125,
|
||
|
|
"epoch": 1.536,
|
||
|
|
"grad_norm": 0.6747505023141314,
|
||
|
|
"learning_rate": 1.0485167875965596e-05,
|
||
|
|
"loss": 0.4048,
|
||
|
|
"mean_token_accuracy": 0.856804140843451,
|
||
|
|
"num_tokens": 165523879.0,
|
||
|
|
"step": 384
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.415557861328125,
|
||
|
|
"epoch": 1.54,
|
||
|
|
"grad_norm": 0.6819606464666561,
|
||
|
|
"learning_rate": 1.0441091765096048e-05,
|
||
|
|
"loss": 0.4122,
|
||
|
|
"mean_token_accuracy": 0.8560525663197041,
|
||
|
|
"num_tokens": 165950483.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.414764404296875,
|
||
|
|
"epoch": 1.544,
|
||
|
|
"grad_norm": 0.6869284806680699,
|
||
|
|
"learning_rate": 1.0397007066701718e-05,
|
||
|
|
"loss": 0.4045,
|
||
|
|
"mean_token_accuracy": 0.8588801184669137,
|
||
|
|
"num_tokens": 166358598.0,
|
||
|
|
"step": 386
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4166259765625,
|
||
|
|
"epoch": 1.548,
|
||
|
|
"grad_norm": 0.6475456226685314,
|
||
|
|
"learning_rate": 1.0352914639058527e-05,
|
||
|
|
"loss": 0.4149,
|
||
|
|
"mean_token_accuracy": 0.8560916474089026,
|
||
|
|
"num_tokens": 166792909.0,
|
||
|
|
"step": 387
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.417724609375,
|
||
|
|
"epoch": 1.552,
|
||
|
|
"grad_norm": 0.653930246354718,
|
||
|
|
"learning_rate": 1.0308815340592868e-05,
|
||
|
|
"loss": 0.3971,
|
||
|
|
"mean_token_accuracy": 0.8593933470547199,
|
||
|
|
"num_tokens": 167209719.0,
|
||
|
|
"step": 388
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.420196533203125,
|
||
|
|
"epoch": 1.556,
|
||
|
|
"grad_norm": 0.6450978802469657,
|
||
|
|
"learning_rate": 1.026471002986491e-05,
|
||
|
|
"loss": 0.3998,
|
||
|
|
"mean_token_accuracy": 0.8592543043196201,
|
||
|
|
"num_tokens": 167621593.0,
|
||
|
|
"step": 389
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40521240234375,
|
||
|
|
"epoch": 1.56,
|
||
|
|
"grad_norm": 0.6243471289609605,
|
||
|
|
"learning_rate": 1.0220599565551865e-05,
|
||
|
|
"loss": 0.4122,
|
||
|
|
"mean_token_accuracy": 0.8562554866075516,
|
||
|
|
"num_tokens": 168070543.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412078857421875,
|
||
|
|
"epoch": 1.564,
|
||
|
|
"grad_norm": 0.6614310562058813,
|
||
|
|
"learning_rate": 1.0176484806431288e-05,
|
||
|
|
"loss": 0.3944,
|
||
|
|
"mean_token_accuracy": 0.8619842659682035,
|
||
|
|
"num_tokens": 168491130.0,
|
||
|
|
"step": 391
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.406036376953125,
|
||
|
|
"epoch": 1.568,
|
||
|
|
"grad_norm": 0.6654742450589866,
|
||
|
|
"learning_rate": 1.013236661136434e-05,
|
||
|
|
"loss": 0.3936,
|
||
|
|
"mean_token_accuracy": 0.8601486897096038,
|
||
|
|
"num_tokens": 168925312.0,
|
||
|
|
"step": 392
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.410400390625,
|
||
|
|
"epoch": 1.572,
|
||
|
|
"grad_norm": 0.6635152736247658,
|
||
|
|
"learning_rate": 1.0088245839279083e-05,
|
||
|
|
"loss": 0.3959,
|
||
|
|
"mean_token_accuracy": 0.8574687512591481,
|
||
|
|
"num_tokens": 169336956.0,
|
||
|
|
"step": 393
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40142822265625,
|
||
|
|
"epoch": 1.576,
|
||
|
|
"grad_norm": 0.7006370812823328,
|
||
|
|
"learning_rate": 1.0044123349153742e-05,
|
||
|
|
"loss": 0.4196,
|
||
|
|
"mean_token_accuracy": 0.8530107187107205,
|
||
|
|
"num_tokens": 169800103.0,
|
||
|
|
"step": 394
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.409393310546875,
|
||
|
|
"epoch": 1.58,
|
||
|
|
"grad_norm": 0.6852039198373086,
|
||
|
|
"learning_rate": 1e-05,
|
||
|
|
"loss": 0.4029,
|
||
|
|
"mean_token_accuracy": 0.8560533076524734,
|
||
|
|
"num_tokens": 170218031.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407958984375,
|
||
|
|
"epoch": 1.584,
|
||
|
|
"grad_norm": 0.6161996118860441,
|
||
|
|
"learning_rate": 9.95587665084626e-06,
|
||
|
|
"loss": 0.394,
|
||
|
|
"mean_token_accuracy": 0.8614465706050396,
|
||
|
|
"num_tokens": 170654363.0,
|
||
|
|
"step": 396
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.408294677734375,
|
||
|
|
"epoch": 1.588,
|
||
|
|
"grad_norm": 0.6804240912799484,
|
||
|
|
"learning_rate": 9.911754160720924e-06,
|
||
|
|
"loss": 0.403,
|
||
|
|
"mean_token_accuracy": 0.8582493038848042,
|
||
|
|
"num_tokens": 171085481.0,
|
||
|
|
"step": 397
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.402679443359375,
|
||
|
|
"epoch": 1.592,
|
||
|
|
"grad_norm": 0.7091648016717254,
|
||
|
|
"learning_rate": 9.867633388635664e-06,
|
||
|
|
"loss": 0.4004,
|
||
|
|
"mean_token_accuracy": 0.8588832160457969,
|
||
|
|
"num_tokens": 171523065.0,
|
||
|
|
"step": 398
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41009521484375,
|
||
|
|
"epoch": 1.596,
|
||
|
|
"grad_norm": 0.7009086919595189,
|
||
|
|
"learning_rate": 9.823515193568715e-06,
|
||
|
|
"loss": 0.4004,
|
||
|
|
"mean_token_accuracy": 0.8595101200044155,
|
||
|
|
"num_tokens": 171961541.0,
|
||
|
|
"step": 399
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.417572021484375,
|
||
|
|
"epoch": 1.6,
|
||
|
|
"grad_norm": 0.6854567759235809,
|
||
|
|
"learning_rate": 9.779400434448137e-06,
|
||
|
|
"loss": 0.4079,
|
||
|
|
"mean_token_accuracy": 0.8558001965284348,
|
||
|
|
"num_tokens": 172359854.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.415557861328125,
|
||
|
|
"epoch": 1.604,
|
||
|
|
"grad_norm": 0.6811426029825497,
|
||
|
|
"learning_rate": 9.735289970135096e-06,
|
||
|
|
"loss": 0.3948,
|
||
|
|
"mean_token_accuracy": 0.8603504663333297,
|
||
|
|
"num_tokens": 172763931.0,
|
||
|
|
"step": 401
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41143798828125,
|
||
|
|
"epoch": 1.608,
|
||
|
|
"grad_norm": 0.7760006655804381,
|
||
|
|
"learning_rate": 9.691184659407136e-06,
|
||
|
|
"loss": 0.4043,
|
||
|
|
"mean_token_accuracy": 0.8575050104409456,
|
||
|
|
"num_tokens": 173182270.0,
|
||
|
|
"step": 402
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40850830078125,
|
||
|
|
"epoch": 1.612,
|
||
|
|
"grad_norm": 0.7022901545448671,
|
||
|
|
"learning_rate": 9.647085360941476e-06,
|
||
|
|
"loss": 0.4019,
|
||
|
|
"mean_token_accuracy": 0.860319490544498,
|
||
|
|
"num_tokens": 173607412.0,
|
||
|
|
"step": 403
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.416534423828125,
|
||
|
|
"epoch": 1.616,
|
||
|
|
"grad_norm": 0.6461683299271066,
|
||
|
|
"learning_rate": 9.602992933298287e-06,
|
||
|
|
"loss": 0.4073,
|
||
|
|
"mean_token_accuracy": 0.8571165865287185,
|
||
|
|
"num_tokens": 174022563.0,
|
||
|
|
"step": 404
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412933349609375,
|
||
|
|
"epoch": 1.62,
|
||
|
|
"grad_norm": 0.6988747266727962,
|
||
|
|
"learning_rate": 9.558908234903955e-06,
|
||
|
|
"loss": 0.4086,
|
||
|
|
"mean_token_accuracy": 0.8568466678261757,
|
||
|
|
"num_tokens": 174472777.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.408050537109375,
|
||
|
|
"epoch": 1.624,
|
||
|
|
"grad_norm": 0.6161989235392599,
|
||
|
|
"learning_rate": 9.514832124034406e-06,
|
||
|
|
"loss": 0.4074,
|
||
|
|
"mean_token_accuracy": 0.8572264648973942,
|
||
|
|
"num_tokens": 174918864.0,
|
||
|
|
"step": 406
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.414276123046875,
|
||
|
|
"epoch": 1.6280000000000001,
|
||
|
|
"grad_norm": 0.6539952481991733,
|
||
|
|
"learning_rate": 9.470765458798369e-06,
|
||
|
|
"loss": 0.4089,
|
||
|
|
"mean_token_accuracy": 0.8567299004644156,
|
||
|
|
"num_tokens": 175350288.0,
|
||
|
|
"step": 407
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.417388916015625,
|
||
|
|
"epoch": 1.6320000000000001,
|
||
|
|
"grad_norm": 0.6569980542426004,
|
||
|
|
"learning_rate": 9.426709097120685e-06,
|
||
|
|
"loss": 0.4029,
|
||
|
|
"mean_token_accuracy": 0.8590945731848478,
|
||
|
|
"num_tokens": 175782136.0,
|
||
|
|
"step": 408
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.410430908203125,
|
||
|
|
"epoch": 1.6360000000000001,
|
||
|
|
"grad_norm": 0.6449695898880148,
|
||
|
|
"learning_rate": 9.382663896725578e-06,
|
||
|
|
"loss": 0.4024,
|
||
|
|
"mean_token_accuracy": 0.8592733666300774,
|
||
|
|
"num_tokens": 176213818.0,
|
||
|
|
"step": 409
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.408843994140625,
|
||
|
|
"epoch": 1.6400000000000001,
|
||
|
|
"grad_norm": 0.6654491142010023,
|
||
|
|
"learning_rate": 9.338630715119998e-06,
|
||
|
|
"loss": 0.4033,
|
||
|
|
"mean_token_accuracy": 0.8572635091841221,
|
||
|
|
"num_tokens": 176640898.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412384033203125,
|
||
|
|
"epoch": 1.6440000000000001,
|
||
|
|
"grad_norm": 0.6861351752503534,
|
||
|
|
"learning_rate": 9.29461040957689e-06,
|
||
|
|
"loss": 0.3898,
|
||
|
|
"mean_token_accuracy": 0.8619167460128665,
|
||
|
|
"num_tokens": 177050752.0,
|
||
|
|
"step": 411
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407958984375,
|
||
|
|
"epoch": 1.6480000000000001,
|
||
|
|
"grad_norm": 0.6736445997784616,
|
||
|
|
"learning_rate": 9.250603837118527e-06,
|
||
|
|
"loss": 0.4056,
|
||
|
|
"mean_token_accuracy": 0.8594129281118512,
|
||
|
|
"num_tokens": 177498349.0,
|
||
|
|
"step": 412
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412322998046875,
|
||
|
|
"epoch": 1.6520000000000001,
|
||
|
|
"grad_norm": 0.6424325697160609,
|
||
|
|
"learning_rate": 9.206611854499805e-06,
|
||
|
|
"loss": 0.4058,
|
||
|
|
"mean_token_accuracy": 0.8558228416368365,
|
||
|
|
"num_tokens": 177939885.0,
|
||
|
|
"step": 413
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40826416015625,
|
||
|
|
"epoch": 1.6560000000000001,
|
||
|
|
"grad_norm": 0.6614231419047583,
|
||
|
|
"learning_rate": 9.162635318191579e-06,
|
||
|
|
"loss": 0.4064,
|
||
|
|
"mean_token_accuracy": 0.8577278964221478,
|
||
|
|
"num_tokens": 178392755.0,
|
||
|
|
"step": 414
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.416961669921875,
|
||
|
|
"epoch": 1.6600000000000001,
|
||
|
|
"grad_norm": 0.6295162176614454,
|
||
|
|
"learning_rate": 9.118675084363986e-06,
|
||
|
|
"loss": 0.4008,
|
||
|
|
"mean_token_accuracy": 0.8593049440532923,
|
||
|
|
"num_tokens": 178825389.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4178466796875,
|
||
|
|
"epoch": 1.6640000000000001,
|
||
|
|
"grad_norm": 0.6934629278063407,
|
||
|
|
"learning_rate": 9.074732008869764e-06,
|
||
|
|
"loss": 0.3999,
|
||
|
|
"mean_token_accuracy": 0.8584995586425066,
|
||
|
|
"num_tokens": 179259066.0,
|
||
|
|
"step": 416
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.419158935546875,
|
||
|
|
"epoch": 1.6680000000000001,
|
||
|
|
"grad_norm": 0.6620695482577096,
|
||
|
|
"learning_rate": 9.030806947227607e-06,
|
||
|
|
"loss": 0.4035,
|
||
|
|
"mean_token_accuracy": 0.8569263610988855,
|
||
|
|
"num_tokens": 179681585.0,
|
||
|
|
"step": 417
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412200927734375,
|
||
|
|
"epoch": 1.6720000000000002,
|
||
|
|
"grad_norm": 0.6330647818374247,
|
||
|
|
"learning_rate": 8.9869007546055e-06,
|
||
|
|
"loss": 0.3993,
|
||
|
|
"mean_token_accuracy": 0.8594193672761321,
|
||
|
|
"num_tokens": 180108668.0,
|
||
|
|
"step": 418
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.411285400390625,
|
||
|
|
"epoch": 1.6760000000000002,
|
||
|
|
"grad_norm": 0.6672167906983725,
|
||
|
|
"learning_rate": 8.943014285804072e-06,
|
||
|
|
"loss": 0.3966,
|
||
|
|
"mean_token_accuracy": 0.8588360520079732,
|
||
|
|
"num_tokens": 180547083.0,
|
||
|
|
"step": 419
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41839599609375,
|
||
|
|
"epoch": 1.6800000000000002,
|
||
|
|
"grad_norm": 0.6671340074033112,
|
||
|
|
"learning_rate": 8.899148395239946e-06,
|
||
|
|
"loss": 0.3958,
|
||
|
|
"mean_token_accuracy": 0.8608447695150971,
|
||
|
|
"num_tokens": 180973634.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4102783203125,
|
||
|
|
"epoch": 1.6840000000000002,
|
||
|
|
"grad_norm": 0.6517389338564636,
|
||
|
|
"learning_rate": 8.855303936929118e-06,
|
||
|
|
"loss": 0.4066,
|
||
|
|
"mean_token_accuracy": 0.8587689083069563,
|
||
|
|
"num_tokens": 181422148.0,
|
||
|
|
"step": 421
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41656494140625,
|
||
|
|
"epoch": 1.688,
|
||
|
|
"grad_norm": 0.6394134749830557,
|
||
|
|
"learning_rate": 8.811481764470325e-06,
|
||
|
|
"loss": 0.3995,
|
||
|
|
"mean_token_accuracy": 0.8590722978115082,
|
||
|
|
"num_tokens": 181849404.0,
|
||
|
|
"step": 422
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41278076171875,
|
||
|
|
"epoch": 1.692,
|
||
|
|
"grad_norm": 0.6647393448223814,
|
||
|
|
"learning_rate": 8.767682731028415e-06,
|
||
|
|
"loss": 0.4077,
|
||
|
|
"mean_token_accuracy": 0.8569863801822066,
|
||
|
|
"num_tokens": 182287273.0,
|
||
|
|
"step": 423
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.420196533203125,
|
||
|
|
"epoch": 1.696,
|
||
|
|
"grad_norm": 0.6396953890085154,
|
||
|
|
"learning_rate": 8.723907689317761e-06,
|
||
|
|
"loss": 0.4004,
|
||
|
|
"mean_token_accuracy": 0.8573690420016646,
|
||
|
|
"num_tokens": 182707504.0,
|
||
|
|
"step": 424
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4095458984375,
|
||
|
|
"epoch": 1.7,
|
||
|
|
"grad_norm": 0.7082102512973018,
|
||
|
|
"learning_rate": 8.680157491585636e-06,
|
||
|
|
"loss": 0.3887,
|
||
|
|
"mean_token_accuracy": 0.8624168410897255,
|
||
|
|
"num_tokens": 183141265.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.417327880859375,
|
||
|
|
"epoch": 1.704,
|
||
|
|
"grad_norm": 0.7367141195801427,
|
||
|
|
"learning_rate": 8.636432989595643e-06,
|
||
|
|
"loss": 0.4076,
|
||
|
|
"mean_token_accuracy": 0.856782041490078,
|
||
|
|
"num_tokens": 183565563.0,
|
||
|
|
"step": 426
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.413055419921875,
|
||
|
|
"epoch": 1.708,
|
||
|
|
"grad_norm": 0.647004967784992,
|
||
|
|
"learning_rate": 8.592735034611097e-06,
|
||
|
|
"loss": 0.391,
|
||
|
|
"mean_token_accuracy": 0.8623571246862411,
|
||
|
|
"num_tokens": 183990365.0,
|
||
|
|
"step": 427
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407958984375,
|
||
|
|
"epoch": 1.712,
|
||
|
|
"grad_norm": 0.6487220927366086,
|
||
|
|
"learning_rate": 8.549064477378496e-06,
|
||
|
|
"loss": 0.3908,
|
||
|
|
"mean_token_accuracy": 0.8625257322564721,
|
||
|
|
"num_tokens": 184422740.0,
|
||
|
|
"step": 428
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.402130126953125,
|
||
|
|
"epoch": 1.716,
|
||
|
|
"grad_norm": 0.7017783250157711,
|
||
|
|
"learning_rate": 8.505422168110936e-06,
|
||
|
|
"loss": 0.392,
|
||
|
|
"mean_token_accuracy": 0.8597327955067158,
|
||
|
|
"num_tokens": 184859844.0,
|
||
|
|
"step": 429
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40313720703125,
|
||
|
|
"epoch": 1.72,
|
||
|
|
"grad_norm": 0.6524551843893845,
|
||
|
|
"learning_rate": 8.461808956471545e-06,
|
||
|
|
"loss": 0.3948,
|
||
|
|
"mean_token_accuracy": 0.8616371499374509,
|
||
|
|
"num_tokens": 185298002.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407867431640625,
|
||
|
|
"epoch": 1.724,
|
||
|
|
"grad_norm": 0.6463189136577974,
|
||
|
|
"learning_rate": 8.418225691556962e-06,
|
||
|
|
"loss": 0.3924,
|
||
|
|
"mean_token_accuracy": 0.8606541519984603,
|
||
|
|
"num_tokens": 185724753.0,
|
||
|
|
"step": 431
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40948486328125,
|
||
|
|
"epoch": 1.728,
|
||
|
|
"grad_norm": 0.6692488797876049,
|
||
|
|
"learning_rate": 8.374673221880805e-06,
|
||
|
|
"loss": 0.3989,
|
||
|
|
"mean_token_accuracy": 0.8587784441187978,
|
||
|
|
"num_tokens": 186164691.0,
|
||
|
|
"step": 432
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.403717041015625,
|
||
|
|
"epoch": 1.732,
|
||
|
|
"grad_norm": 0.6414007215294726,
|
||
|
|
"learning_rate": 8.331152395357142e-06,
|
||
|
|
"loss": 0.3885,
|
||
|
|
"mean_token_accuracy": 0.8626800943166018,
|
||
|
|
"num_tokens": 186606787.0,
|
||
|
|
"step": 433
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.403167724609375,
|
||
|
|
"epoch": 1.736,
|
||
|
|
"grad_norm": 0.6095340071646608,
|
||
|
|
"learning_rate": 8.287664059283984e-06,
|
||
|
|
"loss": 0.3948,
|
||
|
|
"mean_token_accuracy": 0.860966794192791,
|
||
|
|
"num_tokens": 187041084.0,
|
||
|
|
"step": 434
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.403717041015625,
|
||
|
|
"epoch": 1.74,
|
||
|
|
"grad_norm": 0.6748909864821571,
|
||
|
|
"learning_rate": 8.244209060326794e-06,
|
||
|
|
"loss": 0.3991,
|
||
|
|
"mean_token_accuracy": 0.8598612304776907,
|
||
|
|
"num_tokens": 187484754.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4073486328125,
|
||
|
|
"epoch": 1.744,
|
||
|
|
"grad_norm": 0.68207189270992,
|
||
|
|
"learning_rate": 8.200788244502005e-06,
|
||
|
|
"loss": 0.4001,
|
||
|
|
"mean_token_accuracy": 0.8590181078761816,
|
||
|
|
"num_tokens": 187905457.0,
|
||
|
|
"step": 436
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.411895751953125,
|
||
|
|
"epoch": 1.748,
|
||
|
|
"grad_norm": 0.6537236992004675,
|
||
|
|
"learning_rate": 8.157402457160539e-06,
|
||
|
|
"loss": 0.3977,
|
||
|
|
"mean_token_accuracy": 0.8613210869953036,
|
||
|
|
"num_tokens": 188331148.0,
|
||
|
|
"step": 437
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4061279296875,
|
||
|
|
"epoch": 1.752,
|
||
|
|
"grad_norm": 0.6904539320630789,
|
||
|
|
"learning_rate": 8.114052542971365e-06,
|
||
|
|
"loss": 0.399,
|
||
|
|
"mean_token_accuracy": 0.8597118034958839,
|
||
|
|
"num_tokens": 188787528.0,
|
||
|
|
"step": 438
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.408599853515625,
|
||
|
|
"epoch": 1.756,
|
||
|
|
"grad_norm": 0.6271754922666051,
|
||
|
|
"learning_rate": 8.070739345905032e-06,
|
||
|
|
"loss": 0.3868,
|
||
|
|
"mean_token_accuracy": 0.8614202663302422,
|
||
|
|
"num_tokens": 189219464.0,
|
||
|
|
"step": 439
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.409881591796875,
|
||
|
|
"epoch": 1.76,
|
||
|
|
"grad_norm": 0.6914690608520508,
|
||
|
|
"learning_rate": 8.027463709217266e-06,
|
||
|
|
"loss": 0.3871,
|
||
|
|
"mean_token_accuracy": 0.8628098396584392,
|
||
|
|
"num_tokens": 189637422.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41357421875,
|
||
|
|
"epoch": 1.764,
|
||
|
|
"grad_norm": 0.6369202186196429,
|
||
|
|
"learning_rate": 7.984226475432522e-06,
|
||
|
|
"loss": 0.3928,
|
||
|
|
"mean_token_accuracy": 0.8593615358695388,
|
||
|
|
"num_tokens": 190086453.0,
|
||
|
|
"step": 441
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.404815673828125,
|
||
|
|
"epoch": 1.768,
|
||
|
|
"grad_norm": 0.6421366969205309,
|
||
|
|
"learning_rate": 7.941028486327613e-06,
|
||
|
|
"loss": 0.3862,
|
||
|
|
"mean_token_accuracy": 0.8644828842952847,
|
||
|
|
"num_tokens": 190516380.0,
|
||
|
|
"step": 442
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40570068359375,
|
||
|
|
"epoch": 1.772,
|
||
|
|
"grad_norm": 0.6373512654019737,
|
||
|
|
"learning_rate": 7.89787058291529e-06,
|
||
|
|
"loss": 0.4021,
|
||
|
|
"mean_token_accuracy": 0.8560875318944454,
|
||
|
|
"num_tokens": 190953674.0,
|
||
|
|
"step": 443
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.413848876953125,
|
||
|
|
"epoch": 1.776,
|
||
|
|
"grad_norm": 0.6739734110872234,
|
||
|
|
"learning_rate": 7.854753605427896e-06,
|
||
|
|
"loss": 0.3893,
|
||
|
|
"mean_token_accuracy": 0.863305039703846,
|
||
|
|
"num_tokens": 191369112.0,
|
||
|
|
"step": 444
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40325927734375,
|
||
|
|
"epoch": 1.78,
|
||
|
|
"grad_norm": 0.6948784324035026,
|
||
|
|
"learning_rate": 7.811678393300987e-06,
|
||
|
|
"loss": 0.3879,
|
||
|
|
"mean_token_accuracy": 0.8615602031350136,
|
||
|
|
"num_tokens": 191789071.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.410919189453125,
|
||
|
|
"epoch": 1.784,
|
||
|
|
"grad_norm": 0.6884152996091764,
|
||
|
|
"learning_rate": 7.768645785157006e-06,
|
||
|
|
"loss": 0.3918,
|
||
|
|
"mean_token_accuracy": 0.8601081343367696,
|
||
|
|
"num_tokens": 192220840.0,
|
||
|
|
"step": 446
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.413818359375,
|
||
|
|
"epoch": 1.788,
|
||
|
|
"grad_norm": 0.6748051767712123,
|
||
|
|
"learning_rate": 7.725656618788938e-06,
|
||
|
|
"loss": 0.3978,
|
||
|
|
"mean_token_accuracy": 0.8583832308650017,
|
||
|
|
"num_tokens": 192652654.0,
|
||
|
|
"step": 447
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40618896484375,
|
||
|
|
"epoch": 1.792,
|
||
|
|
"grad_norm": 0.6722495276861636,
|
||
|
|
"learning_rate": 7.682711731144017e-06,
|
||
|
|
"loss": 0.3945,
|
||
|
|
"mean_token_accuracy": 0.861555578187108,
|
||
|
|
"num_tokens": 193106168.0,
|
||
|
|
"step": 448
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412872314453125,
|
||
|
|
"epoch": 1.796,
|
||
|
|
"grad_norm": 0.6866250410563648,
|
||
|
|
"learning_rate": 7.639811958307421e-06,
|
||
|
|
"loss": 0.3869,
|
||
|
|
"mean_token_accuracy": 0.8625627057626843,
|
||
|
|
"num_tokens": 193528197.0,
|
||
|
|
"step": 449
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40765380859375,
|
||
|
|
"epoch": 1.8,
|
||
|
|
"grad_norm": 0.686111932085338,
|
||
|
|
"learning_rate": 7.5969581354859976e-06,
|
||
|
|
"loss": 0.3814,
|
||
|
|
"mean_token_accuracy": 0.8628572663292289,
|
||
|
|
"num_tokens": 193951394.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4068603515625,
|
||
|
|
"epoch": 1.804,
|
||
|
|
"grad_norm": 0.6158364870461676,
|
||
|
|
"learning_rate": 7.554151096992002e-06,
|
||
|
|
"loss": 0.3971,
|
||
|
|
"mean_token_accuracy": 0.8595391642302275,
|
||
|
|
"num_tokens": 194396278.0,
|
||
|
|
"step": 451
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.413055419921875,
|
||
|
|
"epoch": 1.808,
|
||
|
|
"grad_norm": 0.6910519600076203,
|
||
|
|
"learning_rate": 7.511391676226854e-06,
|
||
|
|
"loss": 0.3938,
|
||
|
|
"mean_token_accuracy": 0.8589740972965956,
|
||
|
|
"num_tokens": 194820737.0,
|
||
|
|
"step": 452
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40740966796875,
|
||
|
|
"epoch": 1.812,
|
||
|
|
"grad_norm": 0.6413817052499748,
|
||
|
|
"learning_rate": 7.468680705664915e-06,
|
||
|
|
"loss": 0.3836,
|
||
|
|
"mean_token_accuracy": 0.8646212602034211,
|
||
|
|
"num_tokens": 195235958.0,
|
||
|
|
"step": 453
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.405853271484375,
|
||
|
|
"epoch": 1.8159999999999998,
|
||
|
|
"grad_norm": 0.6556986757581252,
|
||
|
|
"learning_rate": 7.426019016837286e-06,
|
||
|
|
"loss": 0.3734,
|
||
|
|
"mean_token_accuracy": 0.8668158845975995,
|
||
|
|
"num_tokens": 195656181.0,
|
||
|
|
"step": 454
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.404541015625,
|
||
|
|
"epoch": 1.8199999999999998,
|
||
|
|
"grad_norm": 0.7046860959373552,
|
||
|
|
"learning_rate": 7.383407440315595e-06,
|
||
|
|
"loss": 0.3948,
|
||
|
|
"mean_token_accuracy": 0.8619125122204423,
|
||
|
|
"num_tokens": 196092544.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40667724609375,
|
||
|
|
"epoch": 1.8239999999999998,
|
||
|
|
"grad_norm": 0.6264092306744613,
|
||
|
|
"learning_rate": 7.340846805695859e-06,
|
||
|
|
"loss": 0.3893,
|
||
|
|
"mean_token_accuracy": 0.8629148006439209,
|
||
|
|
"num_tokens": 196518833.0,
|
||
|
|
"step": 456
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.411224365234375,
|
||
|
|
"epoch": 1.8279999999999998,
|
||
|
|
"grad_norm": 0.6692127205845958,
|
||
|
|
"learning_rate": 7.298337941582314e-06,
|
||
|
|
"loss": 0.3958,
|
||
|
|
"mean_token_accuracy": 0.8608935186639428,
|
||
|
|
"num_tokens": 196948002.0,
|
||
|
|
"step": 457
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.403045654296875,
|
||
|
|
"epoch": 1.8319999999999999,
|
||
|
|
"grad_norm": 0.6397665337784525,
|
||
|
|
"learning_rate": 7.255881675571289e-06,
|
||
|
|
"loss": 0.3756,
|
||
|
|
"mean_token_accuracy": 0.8672095471993089,
|
||
|
|
"num_tokens": 197383675.0,
|
||
|
|
"step": 458
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407867431640625,
|
||
|
|
"epoch": 1.8359999999999999,
|
||
|
|
"grad_norm": 0.6618863286668225,
|
||
|
|
"learning_rate": 7.213478834235079e-06,
|
||
|
|
"loss": 0.3794,
|
||
|
|
"mean_token_accuracy": 0.8648229213431478,
|
||
|
|
"num_tokens": 197813317.0,
|
||
|
|
"step": 459
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40484619140625,
|
||
|
|
"epoch": 1.8399999999999999,
|
||
|
|
"grad_norm": 0.6874164573811824,
|
||
|
|
"learning_rate": 7.1711302431058795e-06,
|
||
|
|
"loss": 0.3918,
|
||
|
|
"mean_token_accuracy": 0.8624518197029829,
|
||
|
|
"num_tokens": 198229146.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407989501953125,
|
||
|
|
"epoch": 1.8439999999999999,
|
||
|
|
"grad_norm": 0.669713392864529,
|
||
|
|
"learning_rate": 7.128836726659696e-06,
|
||
|
|
"loss": 0.3882,
|
||
|
|
"mean_token_accuracy": 0.8641708763316274,
|
||
|
|
"num_tokens": 198667252.0,
|
||
|
|
"step": 461
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412933349609375,
|
||
|
|
"epoch": 1.8479999999999999,
|
||
|
|
"grad_norm": 0.6560514511796613,
|
||
|
|
"learning_rate": 7.086599108300289e-06,
|
||
|
|
"loss": 0.403,
|
||
|
|
"mean_token_accuracy": 0.8595296870917082,
|
||
|
|
"num_tokens": 199106530.0,
|
||
|
|
"step": 462
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.406402587890625,
|
||
|
|
"epoch": 1.8519999999999999,
|
||
|
|
"grad_norm": 0.6500403374848039,
|
||
|
|
"learning_rate": 7.044418210343161e-06,
|
||
|
|
"loss": 0.4007,
|
||
|
|
"mean_token_accuracy": 0.860261969268322,
|
||
|
|
"num_tokens": 199534315.0,
|
||
|
|
"step": 463
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4046630859375,
|
||
|
|
"epoch": 1.8559999999999999,
|
||
|
|
"grad_norm": 0.6542661306267925,
|
||
|
|
"learning_rate": 7.002294853999528e-06,
|
||
|
|
"loss": 0.3917,
|
||
|
|
"mean_token_accuracy": 0.8613046947866678,
|
||
|
|
"num_tokens": 199979382.0,
|
||
|
|
"step": 464
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407562255859375,
|
||
|
|
"epoch": 1.8599999999999999,
|
||
|
|
"grad_norm": 0.6585049396575183,
|
||
|
|
"learning_rate": 6.960229859360352e-06,
|
||
|
|
"loss": 0.3724,
|
||
|
|
"mean_token_accuracy": 0.8677730653434992,
|
||
|
|
"num_tokens": 200386177.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4029541015625,
|
||
|
|
"epoch": 1.8639999999999999,
|
||
|
|
"grad_norm": 0.6827988004668867,
|
||
|
|
"learning_rate": 6.918224045380345e-06,
|
||
|
|
"loss": 0.3884,
|
||
|
|
"mean_token_accuracy": 0.8635709015652537,
|
||
|
|
"num_tokens": 200821706.0,
|
||
|
|
"step": 466
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41094970703125,
|
||
|
|
"epoch": 1.8679999999999999,
|
||
|
|
"grad_norm": 0.6574103962762489,
|
||
|
|
"learning_rate": 6.876278229862059e-06,
|
||
|
|
"loss": 0.394,
|
||
|
|
"mean_token_accuracy": 0.8631828241050243,
|
||
|
|
"num_tokens": 201268538.0,
|
||
|
|
"step": 467
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40545654296875,
|
||
|
|
"epoch": 1.8719999999999999,
|
||
|
|
"grad_norm": 0.7326535287694641,
|
||
|
|
"learning_rate": 6.834393229439944e-06,
|
||
|
|
"loss": 0.3985,
|
||
|
|
"mean_token_accuracy": 0.8607317674905062,
|
||
|
|
"num_tokens": 201688954.0,
|
||
|
|
"step": 468
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40301513671875,
|
||
|
|
"epoch": 1.876,
|
||
|
|
"grad_norm": 0.6841048987843088,
|
||
|
|
"learning_rate": 6.792569859564445e-06,
|
||
|
|
"loss": 0.3799,
|
||
|
|
"mean_token_accuracy": 0.86605981644243,
|
||
|
|
"num_tokens": 202111890.0,
|
||
|
|
"step": 469
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.409576416015625,
|
||
|
|
"epoch": 1.88,
|
||
|
|
"grad_norm": 0.648423513707528,
|
||
|
|
"learning_rate": 6.750808934486146e-06,
|
||
|
|
"loss": 0.3803,
|
||
|
|
"mean_token_accuracy": 0.8641104605048895,
|
||
|
|
"num_tokens": 202538957.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.399658203125,
|
||
|
|
"epoch": 1.884,
|
||
|
|
"grad_norm": 0.6145919027022069,
|
||
|
|
"learning_rate": 6.7091112672399e-06,
|
||
|
|
"loss": 0.3833,
|
||
|
|
"mean_token_accuracy": 0.8640132574364543,
|
||
|
|
"num_tokens": 202981046.0,
|
||
|
|
"step": 471
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.406768798828125,
|
||
|
|
"epoch": 1.888,
|
||
|
|
"grad_norm": 0.6317866884075767,
|
||
|
|
"learning_rate": 6.667477669629012e-06,
|
||
|
|
"loss": 0.3909,
|
||
|
|
"mean_token_accuracy": 0.8626346606761217,
|
||
|
|
"num_tokens": 203429737.0,
|
||
|
|
"step": 472
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.406707763671875,
|
||
|
|
"epoch": 1.892,
|
||
|
|
"grad_norm": 0.6526460287220226,
|
||
|
|
"learning_rate": 6.6259089522094185e-06,
|
||
|
|
"loss": 0.3993,
|
||
|
|
"mean_token_accuracy": 0.8592673875391483,
|
||
|
|
"num_tokens": 203862306.0,
|
||
|
|
"step": 473
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4073486328125,
|
||
|
|
"epoch": 1.896,
|
||
|
|
"grad_norm": 0.6334517609242964,
|
||
|
|
"learning_rate": 6.584405924273924e-06,
|
||
|
|
"loss": 0.3848,
|
||
|
|
"mean_token_accuracy": 0.8638465590775013,
|
||
|
|
"num_tokens": 204290039.0,
|
||
|
|
"step": 474
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4085693359375,
|
||
|
|
"epoch": 1.9,
|
||
|
|
"grad_norm": 0.6505158131893306,
|
||
|
|
"learning_rate": 6.542969393836436e-06,
|
||
|
|
"loss": 0.3894,
|
||
|
|
"mean_token_accuracy": 0.8615700863301754,
|
||
|
|
"num_tokens": 204703452.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.409637451171875,
|
||
|
|
"epoch": 1.904,
|
||
|
|
"grad_norm": 0.6048642972346052,
|
||
|
|
"learning_rate": 6.501600167616242e-06,
|
||
|
|
"loss": 0.3844,
|
||
|
|
"mean_token_accuracy": 0.8640108555555344,
|
||
|
|
"num_tokens": 205131119.0,
|
||
|
|
"step": 476
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.422943115234375,
|
||
|
|
"epoch": 1.908,
|
||
|
|
"grad_norm": 0.6402963756115108,
|
||
|
|
"learning_rate": 6.460299051022285e-06,
|
||
|
|
"loss": 0.3895,
|
||
|
|
"mean_token_accuracy": 0.8651626836508512,
|
||
|
|
"num_tokens": 205526794.0,
|
||
|
|
"step": 477
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4049072265625,
|
||
|
|
"epoch": 1.912,
|
||
|
|
"grad_norm": 0.6346420886039273,
|
||
|
|
"learning_rate": 6.419066848137505e-06,
|
||
|
|
"loss": 0.3848,
|
||
|
|
"mean_token_accuracy": 0.8632886866107583,
|
||
|
|
"num_tokens": 205946503.0,
|
||
|
|
"step": 478
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.406982421875,
|
||
|
|
"epoch": 1.916,
|
||
|
|
"grad_norm": 0.6779099992580604,
|
||
|
|
"learning_rate": 6.3779043617031775e-06,
|
||
|
|
"loss": 0.3783,
|
||
|
|
"mean_token_accuracy": 0.8644304508343339,
|
||
|
|
"num_tokens": 206370640.0,
|
||
|
|
"step": 479
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.41162109375,
|
||
|
|
"epoch": 1.92,
|
||
|
|
"grad_norm": 0.623189579776375,
|
||
|
|
"learning_rate": 6.33681239310327e-06,
|
||
|
|
"loss": 0.3956,
|
||
|
|
"mean_token_accuracy": 0.8629116946831346,
|
||
|
|
"num_tokens": 206813267.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.405426025390625,
|
||
|
|
"epoch": 1.924,
|
||
|
|
"grad_norm": 0.6743868275741082,
|
||
|
|
"learning_rate": 6.295791742348865e-06,
|
||
|
|
"loss": 0.3896,
|
||
|
|
"mean_token_accuracy": 0.8618472386151552,
|
||
|
|
"num_tokens": 207242362.0,
|
||
|
|
"step": 481
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407257080078125,
|
||
|
|
"epoch": 1.928,
|
||
|
|
"grad_norm": 0.6527353407309008,
|
||
|
|
"learning_rate": 6.254843208062568e-06,
|
||
|
|
"loss": 0.3862,
|
||
|
|
"mean_token_accuracy": 0.8633310841396451,
|
||
|
|
"num_tokens": 207664803.0,
|
||
|
|
"step": 482
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.399871826171875,
|
||
|
|
"epoch": 1.932,
|
||
|
|
"grad_norm": 0.6630986629469768,
|
||
|
|
"learning_rate": 6.213967587462969e-06,
|
||
|
|
"loss": 0.3885,
|
||
|
|
"mean_token_accuracy": 0.86393450666219,
|
||
|
|
"num_tokens": 208123795.0,
|
||
|
|
"step": 483
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40985107421875,
|
||
|
|
"epoch": 1.936,
|
||
|
|
"grad_norm": 0.6318603752553104,
|
||
|
|
"learning_rate": 6.173165676349103e-06,
|
||
|
|
"loss": 0.3855,
|
||
|
|
"mean_token_accuracy": 0.8643161999061704,
|
||
|
|
"num_tokens": 208544314.0,
|
||
|
|
"step": 484
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.420623779296875,
|
||
|
|
"epoch": 1.94,
|
||
|
|
"grad_norm": 0.6686203329470276,
|
||
|
|
"learning_rate": 6.132438269084985e-06,
|
||
|
|
"loss": 0.3922,
|
||
|
|
"mean_token_accuracy": 0.8621006421744823,
|
||
|
|
"num_tokens": 208958796.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407196044921875,
|
||
|
|
"epoch": 1.944,
|
||
|
|
"grad_norm": 0.6277983499697525,
|
||
|
|
"learning_rate": 6.091786158584126e-06,
|
||
|
|
"loss": 0.3847,
|
||
|
|
"mean_token_accuracy": 0.8640569858253002,
|
||
|
|
"num_tokens": 209404731.0,
|
||
|
|
"step": 486
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.406097412109375,
|
||
|
|
"epoch": 1.948,
|
||
|
|
"grad_norm": 0.6291721902302041,
|
||
|
|
"learning_rate": 6.051210136294089e-06,
|
||
|
|
"loss": 0.3728,
|
||
|
|
"mean_token_accuracy": 0.8678881358355284,
|
||
|
|
"num_tokens": 209843671.0,
|
||
|
|
"step": 487
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40826416015625,
|
||
|
|
"epoch": 1.952,
|
||
|
|
"grad_norm": 0.62043746355451,
|
||
|
|
"learning_rate": 6.010710992181106e-06,
|
||
|
|
"loss": 0.3878,
|
||
|
|
"mean_token_accuracy": 0.8643698301166296,
|
||
|
|
"num_tokens": 210290934.0,
|
||
|
|
"step": 488
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.422821044921875,
|
||
|
|
"epoch": 1.956,
|
||
|
|
"grad_norm": 0.6632953634117479,
|
||
|
|
"learning_rate": 5.9702895147146765e-06,
|
||
|
|
"loss": 0.3903,
|
||
|
|
"mean_token_accuracy": 0.8627456789836287,
|
||
|
|
"num_tokens": 210704121.0,
|
||
|
|
"step": 489
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.420166015625,
|
||
|
|
"epoch": 1.96,
|
||
|
|
"grad_norm": 0.602459643663508,
|
||
|
|
"learning_rate": 5.92994649085223e-06,
|
||
|
|
"loss": 0.3732,
|
||
|
|
"mean_token_accuracy": 0.8684184439480305,
|
||
|
|
"num_tokens": 211094521.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.407379150390625,
|
||
|
|
"epoch": 1.964,
|
||
|
|
"grad_norm": 0.6538674115774668,
|
||
|
|
"learning_rate": 5.8896827060237824e-06,
|
||
|
|
"loss": 0.3881,
|
||
|
|
"mean_token_accuracy": 0.8617850253358483,
|
||
|
|
"num_tokens": 211529622.0,
|
||
|
|
"step": 491
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.401947021484375,
|
||
|
|
"epoch": 1.968,
|
||
|
|
"grad_norm": 0.6010641269239138,
|
||
|
|
"learning_rate": 5.849498944116683e-06,
|
||
|
|
"loss": 0.3753,
|
||
|
|
"mean_token_accuracy": 0.8674526829272509,
|
||
|
|
"num_tokens": 211972998.0,
|
||
|
|
"step": 492
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.403045654296875,
|
||
|
|
"epoch": 1.972,
|
||
|
|
"grad_norm": 0.6369840337161883,
|
||
|
|
"learning_rate": 5.809395987460318e-06,
|
||
|
|
"loss": 0.3728,
|
||
|
|
"mean_token_accuracy": 0.8687785798683763,
|
||
|
|
"num_tokens": 212386956.0,
|
||
|
|
"step": 493
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.405975341796875,
|
||
|
|
"epoch": 1.976,
|
||
|
|
"grad_norm": 0.720272596409066,
|
||
|
|
"learning_rate": 5.7693746168108956e-06,
|
||
|
|
"loss": 0.3873,
|
||
|
|
"mean_token_accuracy": 0.8629772569984198,
|
||
|
|
"num_tokens": 212804881.0,
|
||
|
|
"step": 494
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.406707763671875,
|
||
|
|
"epoch": 1.98,
|
||
|
|
"grad_norm": 0.6954529294837389,
|
||
|
|
"learning_rate": 5.729435611336239e-06,
|
||
|
|
"loss": 0.3907,
|
||
|
|
"mean_token_accuracy": 0.863201935775578,
|
||
|
|
"num_tokens": 213217231.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.411773681640625,
|
||
|
|
"epoch": 1.984,
|
||
|
|
"grad_norm": 0.6362476416465715,
|
||
|
|
"learning_rate": 5.689579748600633e-06,
|
||
|
|
"loss": 0.388,
|
||
|
|
"mean_token_accuracy": 0.862574577331543,
|
||
|
|
"num_tokens": 213641028.0,
|
||
|
|
"step": 496
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40753173828125,
|
||
|
|
"epoch": 1.988,
|
||
|
|
"grad_norm": 0.6401600918135668,
|
||
|
|
"learning_rate": 5.649807804549663e-06,
|
||
|
|
"loss": 0.3788,
|
||
|
|
"mean_token_accuracy": 0.8672118578106165,
|
||
|
|
"num_tokens": 214088319.0,
|
||
|
|
"step": 497
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.409698486328125,
|
||
|
|
"epoch": 1.992,
|
||
|
|
"grad_norm": 0.6300943384654363,
|
||
|
|
"learning_rate": 5.610120553495119e-06,
|
||
|
|
"loss": 0.3831,
|
||
|
|
"mean_token_accuracy": 0.8632525196298957,
|
||
|
|
"num_tokens": 214513994.0,
|
||
|
|
"step": 498
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.405426025390625,
|
||
|
|
"epoch": 1.996,
|
||
|
|
"grad_norm": 0.5988531890730382,
|
||
|
|
"learning_rate": 5.570518768099918e-06,
|
||
|
|
"loss": 0.3723,
|
||
|
|
"mean_token_accuracy": 0.8672952260822058,
|
||
|
|
"num_tokens": 214956342.0,
|
||
|
|
"step": 499
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.412384033203125,
|
||
|
|
"epoch": 2.0,
|
||
|
|
"grad_norm": 0.6428247979460421,
|
||
|
|
"learning_rate": 5.531003219363079e-06,
|
||
|
|
"loss": 0.3739,
|
||
|
|
"mean_token_accuracy": 0.8669361406937242,
|
||
|
|
"num_tokens": 215379613.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4066162109375,
|
||
|
|
"epoch": 2.004,
|
||
|
|
"grad_norm": 0.6604848968916728,
|
||
|
|
"learning_rate": 5.491574676604682e-06,
|
||
|
|
"loss": 0.3358,
|
||
|
|
"mean_token_accuracy": 0.8794156834483147,
|
||
|
|
"num_tokens": 215791272.0,
|
||
|
|
"step": 501
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.394683837890625,
|
||
|
|
"epoch": 2.008,
|
||
|
|
"grad_norm": 0.6575787082709688,
|
||
|
|
"learning_rate": 5.452233907450908e-06,
|
||
|
|
"loss": 0.3351,
|
||
|
|
"mean_token_accuracy": 0.8805775856599212,
|
||
|
|
"num_tokens": 216234315.0,
|
||
|
|
"step": 502
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392059326171875,
|
||
|
|
"epoch": 2.012,
|
||
|
|
"grad_norm": 0.6093132809717208,
|
||
|
|
"learning_rate": 5.412981677819094e-06,
|
||
|
|
"loss": 0.3441,
|
||
|
|
"mean_token_accuracy": 0.8756103273481131,
|
||
|
|
"num_tokens": 216675706.0,
|
||
|
|
"step": 503
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3887939453125,
|
||
|
|
"epoch": 2.016,
|
||
|
|
"grad_norm": 0.7712186850152813,
|
||
|
|
"learning_rate": 5.373818751902826e-06,
|
||
|
|
"loss": 0.3345,
|
||
|
|
"mean_token_accuracy": 0.8791009830310941,
|
||
|
|
"num_tokens": 217117819.0,
|
||
|
|
"step": 504
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38433837890625,
|
||
|
|
"epoch": 2.02,
|
||
|
|
"grad_norm": 0.8618910933695957,
|
||
|
|
"learning_rate": 5.334745892157035e-06,
|
||
|
|
"loss": 0.3301,
|
||
|
|
"mean_token_accuracy": 0.8820771733298898,
|
||
|
|
"num_tokens": 217549696.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392486572265625,
|
||
|
|
"epoch": 2.024,
|
||
|
|
"grad_norm": 0.6852632299008219,
|
||
|
|
"learning_rate": 5.295763859283196e-06,
|
||
|
|
"loss": 0.3343,
|
||
|
|
"mean_token_accuracy": 0.8784472970291972,
|
||
|
|
"num_tokens": 217979209.0,
|
||
|
|
"step": 506
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.394287109375,
|
||
|
|
"epoch": 2.028,
|
||
|
|
"grad_norm": 0.6142231507092684,
|
||
|
|
"learning_rate": 5.256873412214476e-06,
|
||
|
|
"loss": 0.3467,
|
||
|
|
"mean_token_accuracy": 0.8770469687879086,
|
||
|
|
"num_tokens": 218408252.0,
|
||
|
|
"step": 507
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39581298828125,
|
||
|
|
"epoch": 2.032,
|
||
|
|
"grad_norm": 0.7176547496602971,
|
||
|
|
"learning_rate": 5.218075308100994e-06,
|
||
|
|
"loss": 0.3308,
|
||
|
|
"mean_token_accuracy": 0.8822501227259636,
|
||
|
|
"num_tokens": 218845196.0,
|
||
|
|
"step": 508
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.395782470703125,
|
||
|
|
"epoch": 2.036,
|
||
|
|
"grad_norm": 0.7273762193691284,
|
||
|
|
"learning_rate": 5.179370302295037e-06,
|
||
|
|
"loss": 0.3466,
|
||
|
|
"mean_token_accuracy": 0.8772828225046396,
|
||
|
|
"num_tokens": 219293570.0,
|
||
|
|
"step": 509
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39501953125,
|
||
|
|
"epoch": 2.04,
|
||
|
|
"grad_norm": 0.6784176157846691,
|
||
|
|
"learning_rate": 5.140759148336411e-06,
|
||
|
|
"loss": 0.3402,
|
||
|
|
"mean_token_accuracy": 0.8777928734198213,
|
||
|
|
"num_tokens": 219732309.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.391448974609375,
|
||
|
|
"epoch": 2.044,
|
||
|
|
"grad_norm": 0.7257940361479285,
|
||
|
|
"learning_rate": 5.1022425979377174e-06,
|
||
|
|
"loss": 0.3503,
|
||
|
|
"mean_token_accuracy": 0.8748949179425836,
|
||
|
|
"num_tokens": 220156696.0,
|
||
|
|
"step": 511
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390960693359375,
|
||
|
|
"epoch": 2.048,
|
||
|
|
"grad_norm": 0.6631914463040799,
|
||
|
|
"learning_rate": 5.0638214009697505e-06,
|
||
|
|
"loss": 0.3335,
|
||
|
|
"mean_token_accuracy": 0.8786340272054076,
|
||
|
|
"num_tokens": 220579987.0,
|
||
|
|
"step": 512
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38861083984375,
|
||
|
|
"epoch": 2.052,
|
||
|
|
"grad_norm": 0.7265907358934853,
|
||
|
|
"learning_rate": 5.025496305446879e-06,
|
||
|
|
"loss": 0.3329,
|
||
|
|
"mean_token_accuracy": 0.8817512942478061,
|
||
|
|
"num_tokens": 221002504.0,
|
||
|
|
"step": 513
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.394744873046875,
|
||
|
|
"epoch": 2.056,
|
||
|
|
"grad_norm": 0.7249342131312608,
|
||
|
|
"learning_rate": 4.98726805751251e-06,
|
||
|
|
"loss": 0.3367,
|
||
|
|
"mean_token_accuracy": 0.8770640818402171,
|
||
|
|
"num_tokens": 221435042.0,
|
||
|
|
"step": 514
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.391937255859375,
|
||
|
|
"epoch": 2.06,
|
||
|
|
"grad_norm": 0.6516384545759323,
|
||
|
|
"learning_rate": 4.949137401424527e-06,
|
||
|
|
"loss": 0.3322,
|
||
|
|
"mean_token_accuracy": 0.8820293378084898,
|
||
|
|
"num_tokens": 221864997.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39141845703125,
|
||
|
|
"epoch": 2.064,
|
||
|
|
"grad_norm": 0.6849914697314624,
|
||
|
|
"learning_rate": 4.911105079540828e-06,
|
||
|
|
"loss": 0.3268,
|
||
|
|
"mean_token_accuracy": 0.882698523811996,
|
||
|
|
"num_tokens": 222303042.0,
|
||
|
|
"step": 516
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.395050048828125,
|
||
|
|
"epoch": 2.068,
|
||
|
|
"grad_norm": 0.6525469664422942,
|
||
|
|
"learning_rate": 4.873171832304852e-06,
|
||
|
|
"loss": 0.3314,
|
||
|
|
"mean_token_accuracy": 0.8791795996949077,
|
||
|
|
"num_tokens": 222722214.0,
|
||
|
|
"step": 517
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.385345458984375,
|
||
|
|
"epoch": 2.072,
|
||
|
|
"grad_norm": 0.7024725918333409,
|
||
|
|
"learning_rate": 4.835338398231193e-06,
|
||
|
|
"loss": 0.3348,
|
||
|
|
"mean_token_accuracy": 0.8792968168854713,
|
||
|
|
"num_tokens": 223166096.0,
|
||
|
|
"step": 518
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39056396484375,
|
||
|
|
"epoch": 2.076,
|
||
|
|
"grad_norm": 0.6910080875870691,
|
||
|
|
"learning_rate": 4.797605513891179e-06,
|
||
|
|
"loss": 0.3364,
|
||
|
|
"mean_token_accuracy": 0.8807164039462805,
|
||
|
|
"num_tokens": 223602339.0,
|
||
|
|
"step": 519
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.391937255859375,
|
||
|
|
"epoch": 2.08,
|
||
|
|
"grad_norm": 0.6609216573820202,
|
||
|
|
"learning_rate": 4.759973913898578e-06,
|
||
|
|
"loss": 0.3412,
|
||
|
|
"mean_token_accuracy": 0.8781759701669216,
|
||
|
|
"num_tokens": 224026317.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38885498046875,
|
||
|
|
"epoch": 2.084,
|
||
|
|
"grad_norm": 0.7030100366729122,
|
||
|
|
"learning_rate": 4.722444330895256e-06,
|
||
|
|
"loss": 0.3343,
|
||
|
|
"mean_token_accuracy": 0.8794793700799346,
|
||
|
|
"num_tokens": 224440053.0,
|
||
|
|
"step": 521
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38818359375,
|
||
|
|
"epoch": 2.088,
|
||
|
|
"grad_norm": 0.7426250147038123,
|
||
|
|
"learning_rate": 4.685017495536953e-06,
|
||
|
|
"loss": 0.3383,
|
||
|
|
"mean_token_accuracy": 0.8780775973573327,
|
||
|
|
"num_tokens": 224875380.0,
|
||
|
|
"step": 522
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3900146484375,
|
||
|
|
"epoch": 2.092,
|
||
|
|
"grad_norm": 0.647494221050209,
|
||
|
|
"learning_rate": 4.647694136479008e-06,
|
||
|
|
"loss": 0.3241,
|
||
|
|
"mean_token_accuracy": 0.8822417063638568,
|
||
|
|
"num_tokens": 225328131.0,
|
||
|
|
"step": 523
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.396697998046875,
|
||
|
|
"epoch": 2.096,
|
||
|
|
"grad_norm": 0.6454136007237774,
|
||
|
|
"learning_rate": 4.610474980362224e-06,
|
||
|
|
"loss": 0.3332,
|
||
|
|
"mean_token_accuracy": 0.8803549045696855,
|
||
|
|
"num_tokens": 225756745.0,
|
||
|
|
"step": 524
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38629150390625,
|
||
|
|
"epoch": 2.1,
|
||
|
|
"grad_norm": 0.7060633355006614,
|
||
|
|
"learning_rate": 4.573360751798689e-06,
|
||
|
|
"loss": 0.347,
|
||
|
|
"mean_token_accuracy": 0.8762347372248769,
|
||
|
|
"num_tokens": 226195684.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38519287109375,
|
||
|
|
"epoch": 2.104,
|
||
|
|
"grad_norm": 0.6341950197289519,
|
||
|
|
"learning_rate": 4.5363521733576795e-06,
|
||
|
|
"loss": 0.325,
|
||
|
|
"mean_token_accuracy": 0.8815079219639301,
|
||
|
|
"num_tokens": 226630766.0,
|
||
|
|
"step": 526
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.394195556640625,
|
||
|
|
"epoch": 2.108,
|
||
|
|
"grad_norm": 0.6455723940644649,
|
||
|
|
"learning_rate": 4.4994499655515865e-06,
|
||
|
|
"loss": 0.3536,
|
||
|
|
"mean_token_accuracy": 0.8749488908797503,
|
||
|
|
"num_tokens": 227045904.0,
|
||
|
|
"step": 527
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39349365234375,
|
||
|
|
"epoch": 2.112,
|
||
|
|
"grad_norm": 0.6552362494822913,
|
||
|
|
"learning_rate": 4.462654846821908e-06,
|
||
|
|
"loss": 0.3362,
|
||
|
|
"mean_token_accuracy": 0.8788075894117355,
|
||
|
|
"num_tokens": 227483363.0,
|
||
|
|
"step": 528
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392242431640625,
|
||
|
|
"epoch": 2.116,
|
||
|
|
"grad_norm": 0.6944224407208079,
|
||
|
|
"learning_rate": 4.425967533525229e-06,
|
||
|
|
"loss": 0.3248,
|
||
|
|
"mean_token_accuracy": 0.8820354640483856,
|
||
|
|
"num_tokens": 227911937.0,
|
||
|
|
"step": 529
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38897705078125,
|
||
|
|
"epoch": 2.12,
|
||
|
|
"grad_norm": 0.6812957254364187,
|
||
|
|
"learning_rate": 4.389388739919303e-06,
|
||
|
|
"loss": 0.3388,
|
||
|
|
"mean_token_accuracy": 0.876352796331048,
|
||
|
|
"num_tokens": 228354542.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38800048828125,
|
||
|
|
"epoch": 2.124,
|
||
|
|
"grad_norm": 0.6875721381056159,
|
||
|
|
"learning_rate": 4.352919178149132e-06,
|
||
|
|
"loss": 0.3442,
|
||
|
|
"mean_token_accuracy": 0.8763610608875751,
|
||
|
|
"num_tokens": 228808090.0,
|
||
|
|
"step": 531
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.391754150390625,
|
||
|
|
"epoch": 2.128,
|
||
|
|
"grad_norm": 0.6916941504128791,
|
||
|
|
"learning_rate": 4.31655955823311e-06,
|
||
|
|
"loss": 0.3112,
|
||
|
|
"mean_token_accuracy": 0.8876630086451769,
|
||
|
|
"num_tokens": 229226062.0,
|
||
|
|
"step": 532
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384918212890625,
|
||
|
|
"epoch": 2.132,
|
||
|
|
"grad_norm": 0.6554227326589483,
|
||
|
|
"learning_rate": 4.2803105880491925e-06,
|
||
|
|
"loss": 0.3359,
|
||
|
|
"mean_token_accuracy": 0.8804919496178627,
|
||
|
|
"num_tokens": 229653368.0,
|
||
|
|
"step": 533
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38665771484375,
|
||
|
|
"epoch": 2.136,
|
||
|
|
"grad_norm": 0.7730900001140166,
|
||
|
|
"learning_rate": 4.244172973321118e-06,
|
||
|
|
"loss": 0.3492,
|
||
|
|
"mean_token_accuracy": 0.8732189508154988,
|
||
|
|
"num_tokens": 230085585.0,
|
||
|
|
"step": 534
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39288330078125,
|
||
|
|
"epoch": 2.14,
|
||
|
|
"grad_norm": 0.645639272269303,
|
||
|
|
"learning_rate": 4.208147417604665e-06,
|
||
|
|
"loss": 0.3233,
|
||
|
|
"mean_token_accuracy": 0.8826432377099991,
|
||
|
|
"num_tokens": 230510360.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3857421875,
|
||
|
|
"epoch": 2.144,
|
||
|
|
"grad_norm": 0.6298710197715661,
|
||
|
|
"learning_rate": 4.172234622273974e-06,
|
||
|
|
"loss": 0.3246,
|
||
|
|
"mean_token_accuracy": 0.8809650391340256,
|
||
|
|
"num_tokens": 230938426.0,
|
||
|
|
"step": 536
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39105224609375,
|
||
|
|
"epoch": 2.148,
|
||
|
|
"grad_norm": 0.6337004400064974,
|
||
|
|
"learning_rate": 4.13643528650785e-06,
|
||
|
|
"loss": 0.3391,
|
||
|
|
"mean_token_accuracy": 0.8806687965989113,
|
||
|
|
"num_tokens": 231382671.0,
|
||
|
|
"step": 537
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.389007568359375,
|
||
|
|
"epoch": 2.152,
|
||
|
|
"grad_norm": 0.6610037057251965,
|
||
|
|
"learning_rate": 4.100750107276203e-06,
|
||
|
|
"loss": 0.341,
|
||
|
|
"mean_token_accuracy": 0.8784824516624212,
|
||
|
|
"num_tokens": 231828320.0,
|
||
|
|
"step": 538
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3936767578125,
|
||
|
|
"epoch": 2.156,
|
||
|
|
"grad_norm": 0.6486409864335421,
|
||
|
|
"learning_rate": 4.0651797793264356e-06,
|
||
|
|
"loss": 0.3275,
|
||
|
|
"mean_token_accuracy": 0.8811681428924203,
|
||
|
|
"num_tokens": 232261339.0,
|
||
|
|
"step": 539
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.385833740234375,
|
||
|
|
"epoch": 2.16,
|
||
|
|
"grad_norm": 0.6478843896251482,
|
||
|
|
"learning_rate": 4.029724995169951e-06,
|
||
|
|
"loss": 0.3216,
|
||
|
|
"mean_token_accuracy": 0.8853343818336725,
|
||
|
|
"num_tokens": 232693719.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38482666015625,
|
||
|
|
"epoch": 2.164,
|
||
|
|
"grad_norm": 0.6129511183984708,
|
||
|
|
"learning_rate": 3.994386445068632e-06,
|
||
|
|
"loss": 0.3224,
|
||
|
|
"mean_token_accuracy": 0.8818883365020156,
|
||
|
|
"num_tokens": 233134375.0,
|
||
|
|
"step": 541
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3931884765625,
|
||
|
|
"epoch": 2.168,
|
||
|
|
"grad_norm": 0.6671110105971623,
|
||
|
|
"learning_rate": 3.959164817021443e-06,
|
||
|
|
"loss": 0.3341,
|
||
|
|
"mean_token_accuracy": 0.8805986801162362,
|
||
|
|
"num_tokens": 233556342.0,
|
||
|
|
"step": 542
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38983154296875,
|
||
|
|
"epoch": 2.172,
|
||
|
|
"grad_norm": 0.7060173021661289,
|
||
|
|
"learning_rate": 3.924060796751012e-06,
|
||
|
|
"loss": 0.3285,
|
||
|
|
"mean_token_accuracy": 0.8839866500347853,
|
||
|
|
"num_tokens": 233985592.0,
|
||
|
|
"step": 543
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3883056640625,
|
||
|
|
"epoch": 2.176,
|
||
|
|
"grad_norm": 0.6382960307925457,
|
||
|
|
"learning_rate": 3.889075067690281e-06,
|
||
|
|
"loss": 0.3296,
|
||
|
|
"mean_token_accuracy": 0.8844837825745344,
|
||
|
|
"num_tokens": 234398271.0,
|
||
|
|
"step": 544
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.389190673828125,
|
||
|
|
"epoch": 2.18,
|
||
|
|
"grad_norm": 0.6476094327438024,
|
||
|
|
"learning_rate": 3.854208310969204e-06,
|
||
|
|
"loss": 0.335,
|
||
|
|
"mean_token_accuracy": 0.8793821493163705,
|
||
|
|
"num_tokens": 234839941.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3873291015625,
|
||
|
|
"epoch": 2.184,
|
||
|
|
"grad_norm": 0.6243757438091312,
|
||
|
|
"learning_rate": 3.819461205401499e-06,
|
||
|
|
"loss": 0.3285,
|
||
|
|
"mean_token_accuracy": 0.883407536894083,
|
||
|
|
"num_tokens": 235256577.0,
|
||
|
|
"step": 546
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39129638671875,
|
||
|
|
"epoch": 2.188,
|
||
|
|
"grad_norm": 0.6538246194762162,
|
||
|
|
"learning_rate": 3.7848344274714075e-06,
|
||
|
|
"loss": 0.3314,
|
||
|
|
"mean_token_accuracy": 0.8798129223287106,
|
||
|
|
"num_tokens": 235673524.0,
|
||
|
|
"step": 547
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3931884765625,
|
||
|
|
"epoch": 2.192,
|
||
|
|
"grad_norm": 0.6366137034587003,
|
||
|
|
"learning_rate": 3.750328651320543e-06,
|
||
|
|
"loss": 0.3474,
|
||
|
|
"mean_token_accuracy": 0.8761398484930396,
|
||
|
|
"num_tokens": 236126394.0,
|
||
|
|
"step": 548
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4012451171875,
|
||
|
|
"epoch": 2.196,
|
||
|
|
"grad_norm": 0.6587509673889667,
|
||
|
|
"learning_rate": 3.7159445487347546e-06,
|
||
|
|
"loss": 0.3346,
|
||
|
|
"mean_token_accuracy": 0.8827248122543097,
|
||
|
|
"num_tokens": 236555440.0,
|
||
|
|
"step": 549
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.394378662109375,
|
||
|
|
"epoch": 2.2,
|
||
|
|
"grad_norm": 0.625797151637782,
|
||
|
|
"learning_rate": 3.681682789131068e-06,
|
||
|
|
"loss": 0.3416,
|
||
|
|
"mean_token_accuracy": 0.8779640728607774,
|
||
|
|
"num_tokens": 236979585.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390777587890625,
|
||
|
|
"epoch": 2.204,
|
||
|
|
"grad_norm": 0.626869373949747,
|
||
|
|
"learning_rate": 3.647544039544615e-06,
|
||
|
|
"loss": 0.3389,
|
||
|
|
"mean_token_accuracy": 0.8798139095306396,
|
||
|
|
"num_tokens": 237418109.0,
|
||
|
|
"step": 551
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390472412109375,
|
||
|
|
"epoch": 2.208,
|
||
|
|
"grad_norm": 0.6349988280837471,
|
||
|
|
"learning_rate": 3.613528964615696e-06,
|
||
|
|
"loss": 0.3349,
|
||
|
|
"mean_token_accuracy": 0.880202136002481,
|
||
|
|
"num_tokens": 237849699.0,
|
||
|
|
"step": 552
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392059326171875,
|
||
|
|
"epoch": 2.212,
|
||
|
|
"grad_norm": 0.6013025115324859,
|
||
|
|
"learning_rate": 3.579638226576794e-06,
|
||
|
|
"loss": 0.3335,
|
||
|
|
"mean_token_accuracy": 0.8818651661276817,
|
||
|
|
"num_tokens": 238277677.0,
|
||
|
|
"step": 553
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390960693359375,
|
||
|
|
"epoch": 2.216,
|
||
|
|
"grad_norm": 0.6700959082164812,
|
||
|
|
"learning_rate": 3.545872485239724e-06,
|
||
|
|
"loss": 0.3377,
|
||
|
|
"mean_token_accuracy": 0.8801340516656637,
|
||
|
|
"num_tokens": 238699752.0,
|
||
|
|
"step": 554
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390228271484375,
|
||
|
|
"epoch": 2.22,
|
||
|
|
"grad_norm": 0.6387896404726974,
|
||
|
|
"learning_rate": 3.51223239798274e-06,
|
||
|
|
"loss": 0.3235,
|
||
|
|
"mean_token_accuracy": 0.8812453290447593,
|
||
|
|
"num_tokens": 239118565.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38897705078125,
|
||
|
|
"epoch": 2.224,
|
||
|
|
"grad_norm": 0.6354436120277321,
|
||
|
|
"learning_rate": 3.4787186197377866e-06,
|
||
|
|
"loss": 0.3237,
|
||
|
|
"mean_token_accuracy": 0.8839503647759557,
|
||
|
|
"num_tokens": 239541175.0,
|
||
|
|
"step": 556
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.396331787109375,
|
||
|
|
"epoch": 2.228,
|
||
|
|
"grad_norm": 0.6487258661220877,
|
||
|
|
"learning_rate": 3.4453318029777096e-06,
|
||
|
|
"loss": 0.3321,
|
||
|
|
"mean_token_accuracy": 0.8787043550983071,
|
||
|
|
"num_tokens": 239945453.0,
|
||
|
|
"step": 557
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39166259765625,
|
||
|
|
"epoch": 2.232,
|
||
|
|
"grad_norm": 0.6383761179915859,
|
||
|
|
"learning_rate": 3.412072597703574e-06,
|
||
|
|
"loss": 0.3283,
|
||
|
|
"mean_token_accuracy": 0.8817808367311954,
|
||
|
|
"num_tokens": 240389344.0,
|
||
|
|
"step": 558
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390045166015625,
|
||
|
|
"epoch": 2.2359999999999998,
|
||
|
|
"grad_norm": 0.6628339239465953,
|
||
|
|
"learning_rate": 3.378941651431996e-06,
|
||
|
|
"loss": 0.3243,
|
||
|
|
"mean_token_accuracy": 0.8849960509687662,
|
||
|
|
"num_tokens": 240823764.0,
|
||
|
|
"step": 559
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392303466796875,
|
||
|
|
"epoch": 2.24,
|
||
|
|
"grad_norm": 0.645129680952455,
|
||
|
|
"learning_rate": 3.345939609182558e-06,
|
||
|
|
"loss": 0.3326,
|
||
|
|
"mean_token_accuracy": 0.8838113946840167,
|
||
|
|
"num_tokens": 241254037.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3927001953125,
|
||
|
|
"epoch": 2.2439999999999998,
|
||
|
|
"grad_norm": 0.6337087973681855,
|
||
|
|
"learning_rate": 3.3130671134652224e-06,
|
||
|
|
"loss": 0.3226,
|
||
|
|
"mean_token_accuracy": 0.8822179799899459,
|
||
|
|
"num_tokens": 241657534.0,
|
||
|
|
"step": 561
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39349365234375,
|
||
|
|
"epoch": 2.248,
|
||
|
|
"grad_norm": 0.6242327745279578,
|
||
|
|
"learning_rate": 3.2803248042678436e-06,
|
||
|
|
"loss": 0.327,
|
||
|
|
"mean_token_accuracy": 0.8822993338108063,
|
||
|
|
"num_tokens": 242083384.0,
|
||
|
|
"step": 562
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39105224609375,
|
||
|
|
"epoch": 2.252,
|
||
|
|
"grad_norm": 0.6228842742683107,
|
||
|
|
"learning_rate": 3.247713319043695e-06,
|
||
|
|
"loss": 0.322,
|
||
|
|
"mean_token_accuracy": 0.8833278147503734,
|
||
|
|
"num_tokens": 242527271.0,
|
||
|
|
"step": 563
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39520263671875,
|
||
|
|
"epoch": 2.2560000000000002,
|
||
|
|
"grad_norm": 0.6175839238970445,
|
||
|
|
"learning_rate": 3.215233292699077e-06,
|
||
|
|
"loss": 0.3138,
|
||
|
|
"mean_token_accuracy": 0.8878155276179314,
|
||
|
|
"num_tokens": 242927970.0,
|
||
|
|
"step": 564
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387847900390625,
|
||
|
|
"epoch": 2.26,
|
||
|
|
"grad_norm": 0.6618951768061766,
|
||
|
|
"learning_rate": 3.182885357580934e-06,
|
||
|
|
"loss": 0.3231,
|
||
|
|
"mean_token_accuracy": 0.883756154216826,
|
||
|
|
"num_tokens": 243365174.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387542724609375,
|
||
|
|
"epoch": 2.2640000000000002,
|
||
|
|
"grad_norm": 0.711044578215042,
|
||
|
|
"learning_rate": 3.150670143464556e-06,
|
||
|
|
"loss": 0.3373,
|
||
|
|
"mean_token_accuracy": 0.8777942629531026,
|
||
|
|
"num_tokens": 243808925.0,
|
||
|
|
"step": 566
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387939453125,
|
||
|
|
"epoch": 2.268,
|
||
|
|
"grad_norm": 0.6327657842786318,
|
||
|
|
"learning_rate": 3.1185882775413123e-06,
|
||
|
|
"loss": 0.3225,
|
||
|
|
"mean_token_accuracy": 0.8818872682750225,
|
||
|
|
"num_tokens": 244263384.0,
|
||
|
|
"step": 567
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38818359375,
|
||
|
|
"epoch": 2.2720000000000002,
|
||
|
|
"grad_norm": 0.6068197817358456,
|
||
|
|
"learning_rate": 3.086640384406453e-06,
|
||
|
|
"loss": 0.3251,
|
||
|
|
"mean_token_accuracy": 0.882589784450829,
|
||
|
|
"num_tokens": 244697703.0,
|
||
|
|
"step": 568
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388702392578125,
|
||
|
|
"epoch": 2.276,
|
||
|
|
"grad_norm": 0.6474221412103411,
|
||
|
|
"learning_rate": 3.054827086046931e-06,
|
||
|
|
"loss": 0.3282,
|
||
|
|
"mean_token_accuracy": 0.8800750700756907,
|
||
|
|
"num_tokens": 245122089.0,
|
||
|
|
"step": 569
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392669677734375,
|
||
|
|
"epoch": 2.2800000000000002,
|
||
|
|
"grad_norm": 0.645637591011538,
|
||
|
|
"learning_rate": 3.0231490018293042e-06,
|
||
|
|
"loss": 0.3364,
|
||
|
|
"mean_token_accuracy": 0.8780366098508239,
|
||
|
|
"num_tokens": 245555429.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388885498046875,
|
||
|
|
"epoch": 2.284,
|
||
|
|
"grad_norm": 0.6613789361180501,
|
||
|
|
"learning_rate": 2.9916067484876697e-06,
|
||
|
|
"loss": 0.324,
|
||
|
|
"mean_token_accuracy": 0.8827451905235648,
|
||
|
|
"num_tokens": 246006725.0,
|
||
|
|
"step": 571
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392730712890625,
|
||
|
|
"epoch": 2.288,
|
||
|
|
"grad_norm": 0.6394101971652224,
|
||
|
|
"learning_rate": 2.9602009401116716e-06,
|
||
|
|
"loss": 0.3335,
|
||
|
|
"mean_token_accuracy": 0.8798945927992463,
|
||
|
|
"num_tokens": 246425875.0,
|
||
|
|
"step": 572
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387542724609375,
|
||
|
|
"epoch": 2.292,
|
||
|
|
"grad_norm": 0.6332054862884792,
|
||
|
|
"learning_rate": 2.9289321881345257e-06,
|
||
|
|
"loss": 0.3228,
|
||
|
|
"mean_token_accuracy": 0.8839686112478375,
|
||
|
|
"num_tokens": 246874899.0,
|
||
|
|
"step": 573
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388916015625,
|
||
|
|
"epoch": 2.296,
|
||
|
|
"grad_norm": 0.6697198539666123,
|
||
|
|
"learning_rate": 2.897801101321128e-06,
|
||
|
|
"loss": 0.3401,
|
||
|
|
"mean_token_accuracy": 0.8789337836205959,
|
||
|
|
"num_tokens": 247334918.0,
|
||
|
|
"step": 574
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390533447265625,
|
||
|
|
"epoch": 2.3,
|
||
|
|
"grad_norm": 0.6735081154437351,
|
||
|
|
"learning_rate": 2.8668082857562006e-06,
|
||
|
|
"loss": 0.3365,
|
||
|
|
"mean_token_accuracy": 0.8790748296305537,
|
||
|
|
"num_tokens": 247746103.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387786865234375,
|
||
|
|
"epoch": 2.304,
|
||
|
|
"grad_norm": 0.6337350993484439,
|
||
|
|
"learning_rate": 2.8359543448324856e-06,
|
||
|
|
"loss": 0.3441,
|
||
|
|
"mean_token_accuracy": 0.878231386654079,
|
||
|
|
"num_tokens": 248203529.0,
|
||
|
|
"step": 576
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38861083984375,
|
||
|
|
"epoch": 2.308,
|
||
|
|
"grad_norm": 0.6547592368588677,
|
||
|
|
"learning_rate": 2.8052398792390155e-06,
|
||
|
|
"loss": 0.3138,
|
||
|
|
"mean_token_accuracy": 0.8875163504853845,
|
||
|
|
"num_tokens": 248634764.0,
|
||
|
|
"step": 577
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3924560546875,
|
||
|
|
"epoch": 2.312,
|
||
|
|
"grad_norm": 0.6548215177581781,
|
||
|
|
"learning_rate": 2.774665486949395e-06,
|
||
|
|
"loss": 0.3152,
|
||
|
|
"mean_token_accuracy": 0.8839077344164252,
|
||
|
|
"num_tokens": 249076618.0,
|
||
|
|
"step": 578
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.389434814453125,
|
||
|
|
"epoch": 2.316,
|
||
|
|
"grad_norm": 0.6324955811508368,
|
||
|
|
"learning_rate": 2.7442317632101743e-06,
|
||
|
|
"loss": 0.3176,
|
||
|
|
"mean_token_accuracy": 0.8851284068077803,
|
||
|
|
"num_tokens": 249520848.0,
|
||
|
|
"step": 579
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3900146484375,
|
||
|
|
"epoch": 2.32,
|
||
|
|
"grad_norm": 0.6601317687553189,
|
||
|
|
"learning_rate": 2.713939300529255e-06,
|
||
|
|
"loss": 0.3477,
|
||
|
|
"mean_token_accuracy": 0.8765273755416274,
|
||
|
|
"num_tokens": 249947522.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.389434814453125,
|
||
|
|
"epoch": 2.324,
|
||
|
|
"grad_norm": 1.123871344236666,
|
||
|
|
"learning_rate": 2.6837886886643615e-06,
|
||
|
|
"loss": 0.3271,
|
||
|
|
"mean_token_accuracy": 0.8832463938742876,
|
||
|
|
"num_tokens": 250347598.0,
|
||
|
|
"step": 581
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.386077880859375,
|
||
|
|
"epoch": 2.328,
|
||
|
|
"grad_norm": 0.6276498253602809,
|
||
|
|
"learning_rate": 2.653780514611548e-06,
|
||
|
|
"loss": 0.324,
|
||
|
|
"mean_token_accuracy": 0.8840926708653569,
|
||
|
|
"num_tokens": 250784153.0,
|
||
|
|
"step": 582
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.386962890625,
|
||
|
|
"epoch": 2.332,
|
||
|
|
"grad_norm": 0.6962339738316794,
|
||
|
|
"learning_rate": 2.6239153625937786e-06,
|
||
|
|
"loss": 0.3268,
|
||
|
|
"mean_token_accuracy": 0.8837611731141806,
|
||
|
|
"num_tokens": 251209170.0,
|
||
|
|
"step": 583
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3941650390625,
|
||
|
|
"epoch": 2.336,
|
||
|
|
"grad_norm": 0.6757314222176184,
|
||
|
|
"learning_rate": 2.5941938140495483e-06,
|
||
|
|
"loss": 0.3574,
|
||
|
|
"mean_token_accuracy": 0.8737319763749838,
|
||
|
|
"num_tokens": 251647277.0,
|
||
|
|
"step": 584
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38385009765625,
|
||
|
|
"epoch": 2.34,
|
||
|
|
"grad_norm": 0.6198824260288804,
|
||
|
|
"learning_rate": 2.564616447621572e-06,
|
||
|
|
"loss": 0.3181,
|
||
|
|
"mean_token_accuracy": 0.8853395711630583,
|
||
|
|
"num_tokens": 252102080.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392822265625,
|
||
|
|
"epoch": 2.344,
|
||
|
|
"grad_norm": 0.6374885364307245,
|
||
|
|
"learning_rate": 2.5351838391455074e-06,
|
||
|
|
"loss": 0.3252,
|
||
|
|
"mean_token_accuracy": 0.8820815095677972,
|
||
|
|
"num_tokens": 252531975.0,
|
||
|
|
"step": 586
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392608642578125,
|
||
|
|
"epoch": 2.348,
|
||
|
|
"grad_norm": 0.6275966565447,
|
||
|
|
"learning_rate": 2.50589656163875e-06,
|
||
|
|
"loss": 0.3394,
|
||
|
|
"mean_token_accuracy": 0.8797515127807856,
|
||
|
|
"num_tokens": 252959602.0,
|
||
|
|
"step": 587
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392242431640625,
|
||
|
|
"epoch": 2.352,
|
||
|
|
"grad_norm": 0.6436737149432719,
|
||
|
|
"learning_rate": 2.4767551852892733e-06,
|
||
|
|
"loss": 0.3382,
|
||
|
|
"mean_token_accuracy": 0.8808635594323277,
|
||
|
|
"num_tokens": 253389744.0,
|
||
|
|
"step": 588
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.391082763671875,
|
||
|
|
"epoch": 2.356,
|
||
|
|
"grad_norm": 0.6306636990526113,
|
||
|
|
"learning_rate": 2.447760277444543e-06,
|
||
|
|
"loss": 0.3263,
|
||
|
|
"mean_token_accuracy": 0.8844602555036545,
|
||
|
|
"num_tokens": 253813401.0,
|
||
|
|
"step": 589
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387359619140625,
|
||
|
|
"epoch": 2.36,
|
||
|
|
"grad_norm": 0.6495756121007508,
|
||
|
|
"learning_rate": 2.4189124026004474e-06,
|
||
|
|
"loss": 0.3168,
|
||
|
|
"mean_token_accuracy": 0.8866690248250961,
|
||
|
|
"num_tokens": 254247124.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388702392578125,
|
||
|
|
"epoch": 2.364,
|
||
|
|
"grad_norm": 0.6380073400902024,
|
||
|
|
"learning_rate": 2.390212122390323e-06,
|
||
|
|
"loss": 0.327,
|
||
|
|
"mean_token_accuracy": 0.8814845606684685,
|
||
|
|
"num_tokens": 254693087.0,
|
||
|
|
"step": 591
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388519287109375,
|
||
|
|
"epoch": 2.368,
|
||
|
|
"grad_norm": 0.608302964861183,
|
||
|
|
"learning_rate": 2.3616599955740173e-06,
|
||
|
|
"loss": 0.3226,
|
||
|
|
"mean_token_accuracy": 0.8831873508170247,
|
||
|
|
"num_tokens": 255119031.0,
|
||
|
|
"step": 592
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3900146484375,
|
||
|
|
"epoch": 2.372,
|
||
|
|
"grad_norm": 0.6567960161045082,
|
||
|
|
"learning_rate": 2.3332565780270165e-06,
|
||
|
|
"loss": 0.3218,
|
||
|
|
"mean_token_accuracy": 0.8844241676852107,
|
||
|
|
"num_tokens": 255550476.0,
|
||
|
|
"step": 593
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3846435546875,
|
||
|
|
"epoch": 2.376,
|
||
|
|
"grad_norm": 0.6148271230852593,
|
||
|
|
"learning_rate": 2.3050024227296008e-06,
|
||
|
|
"loss": 0.3206,
|
||
|
|
"mean_token_accuracy": 0.8835389213636518,
|
||
|
|
"num_tokens": 255980424.0,
|
||
|
|
"step": 594
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384552001953125,
|
||
|
|
"epoch": 2.38,
|
||
|
|
"grad_norm": 0.6378973723179633,
|
||
|
|
"learning_rate": 2.2768980797561125e-06,
|
||
|
|
"loss": 0.3146,
|
||
|
|
"mean_token_accuracy": 0.8855107128620148,
|
||
|
|
"num_tokens": 256433326.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392486572265625,
|
||
|
|
"epoch": 2.384,
|
||
|
|
"grad_norm": 0.6884114369249636,
|
||
|
|
"learning_rate": 2.2489440962642117e-06,
|
||
|
|
"loss": 0.3359,
|
||
|
|
"mean_token_accuracy": 0.878860772587359,
|
||
|
|
"num_tokens": 256848167.0,
|
||
|
|
"step": 596
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387451171875,
|
||
|
|
"epoch": 2.388,
|
||
|
|
"grad_norm": 0.6433974611831177,
|
||
|
|
"learning_rate": 2.2211410164842605e-06,
|
||
|
|
"loss": 0.3163,
|
||
|
|
"mean_token_accuracy": 0.8846540944650769,
|
||
|
|
"num_tokens": 257278891.0,
|
||
|
|
"step": 597
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3868408203125,
|
||
|
|
"epoch": 2.392,
|
||
|
|
"grad_norm": 0.6267183505146826,
|
||
|
|
"learning_rate": 2.1934893817086834e-06,
|
||
|
|
"loss": 0.3224,
|
||
|
|
"mean_token_accuracy": 0.8838652614504099,
|
||
|
|
"num_tokens": 257711245.0,
|
||
|
|
"step": 598
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38153076171875,
|
||
|
|
"epoch": 2.396,
|
||
|
|
"grad_norm": 0.6127663801107301,
|
||
|
|
"learning_rate": 2.165989730281475e-06,
|
||
|
|
"loss": 0.3206,
|
||
|
|
"mean_token_accuracy": 0.8841096553951502,
|
||
|
|
"num_tokens": 258164428.0,
|
||
|
|
"step": 599
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383392333984375,
|
||
|
|
"epoch": 2.4,
|
||
|
|
"grad_norm": 0.6283959147250862,
|
||
|
|
"learning_rate": 2.138642597587686e-06,
|
||
|
|
"loss": 0.3136,
|
||
|
|
"mean_token_accuracy": 0.8862687824293971,
|
||
|
|
"num_tokens": 258606236.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3843994140625,
|
||
|
|
"epoch": 2.404,
|
||
|
|
"grad_norm": 0.6106429627595987,
|
||
|
|
"learning_rate": 2.1114485160430132e-06,
|
||
|
|
"loss": 0.3233,
|
||
|
|
"mean_token_accuracy": 0.8821805631741881,
|
||
|
|
"num_tokens": 259038774.0,
|
||
|
|
"step": 601
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390838623046875,
|
||
|
|
"epoch": 2.408,
|
||
|
|
"grad_norm": 0.6507214028155965,
|
||
|
|
"learning_rate": 2.0844080150834313e-06,
|
||
|
|
"loss": 0.3183,
|
||
|
|
"mean_token_accuracy": 0.8830812107771635,
|
||
|
|
"num_tokens": 259443698.0,
|
||
|
|
"step": 602
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383636474609375,
|
||
|
|
"epoch": 2.412,
|
||
|
|
"grad_norm": 0.6333429162525563,
|
||
|
|
"learning_rate": 2.057521621154891e-06,
|
||
|
|
"loss": 0.3156,
|
||
|
|
"mean_token_accuracy": 0.8859158186241984,
|
||
|
|
"num_tokens": 259854707.0,
|
||
|
|
"step": 603
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.382232666015625,
|
||
|
|
"epoch": 2.416,
|
||
|
|
"grad_norm": 0.61434335074145,
|
||
|
|
"learning_rate": 2.0307898577030603e-06,
|
||
|
|
"loss": 0.3098,
|
||
|
|
"mean_token_accuracy": 0.8855212489143014,
|
||
|
|
"num_tokens": 260284264.0,
|
||
|
|
"step": 604
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38177490234375,
|
||
|
|
"epoch": 2.42,
|
||
|
|
"grad_norm": 0.6335342159071906,
|
||
|
|
"learning_rate": 2.004213245163138e-06,
|
||
|
|
"loss": 0.3101,
|
||
|
|
"mean_token_accuracy": 0.8882576022297144,
|
||
|
|
"num_tokens": 260715156.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.382110595703125,
|
||
|
|
"epoch": 2.424,
|
||
|
|
"grad_norm": 0.6452980907092565,
|
||
|
|
"learning_rate": 1.9777923009497225e-06,
|
||
|
|
"loss": 0.3144,
|
||
|
|
"mean_token_accuracy": 0.8865978652611375,
|
||
|
|
"num_tokens": 261179476.0,
|
||
|
|
"step": 606
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387054443359375,
|
||
|
|
"epoch": 2.428,
|
||
|
|
"grad_norm": 0.6315489999728183,
|
||
|
|
"learning_rate": 1.9515275394467446e-06,
|
||
|
|
"loss": 0.3212,
|
||
|
|
"mean_token_accuracy": 0.8823178960010409,
|
||
|
|
"num_tokens": 261615332.0,
|
||
|
|
"step": 607
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3856201171875,
|
||
|
|
"epoch": 2.432,
|
||
|
|
"grad_norm": 0.6298103563075008,
|
||
|
|
"learning_rate": 1.9254194719974307e-06,
|
||
|
|
"loss": 0.3255,
|
||
|
|
"mean_token_accuracy": 0.8806961001828313,
|
||
|
|
"num_tokens": 262043771.0,
|
||
|
|
"step": 608
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388885498046875,
|
||
|
|
"epoch": 2.436,
|
||
|
|
"grad_norm": 0.6137765496922394,
|
||
|
|
"learning_rate": 1.8994686068943792e-06,
|
||
|
|
"loss": 0.3208,
|
||
|
|
"mean_token_accuracy": 0.8832854721695185,
|
||
|
|
"num_tokens": 262463499.0,
|
||
|
|
"step": 609
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384552001953125,
|
||
|
|
"epoch": 2.44,
|
||
|
|
"grad_norm": 0.6490274904718708,
|
||
|
|
"learning_rate": 1.8736754493696352e-06,
|
||
|
|
"loss": 0.3219,
|
||
|
|
"mean_token_accuracy": 0.882375804707408,
|
||
|
|
"num_tokens": 262889574.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387542724609375,
|
||
|
|
"epoch": 2.444,
|
||
|
|
"grad_norm": 0.6131004457282236,
|
||
|
|
"learning_rate": 1.8480405015848824e-06,
|
||
|
|
"loss": 0.3316,
|
||
|
|
"mean_token_accuracy": 0.8824941245839,
|
||
|
|
"num_tokens": 263325997.0,
|
||
|
|
"step": 611
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38128662109375,
|
||
|
|
"epoch": 2.448,
|
||
|
|
"grad_norm": 0.6392594100395339,
|
||
|
|
"learning_rate": 1.822564262621631e-06,
|
||
|
|
"loss": 0.3222,
|
||
|
|
"mean_token_accuracy": 0.8853313140571117,
|
||
|
|
"num_tokens": 263780910.0,
|
||
|
|
"step": 612
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38787841796875,
|
||
|
|
"epoch": 2.452,
|
||
|
|
"grad_norm": 0.6299188739102849,
|
||
|
|
"learning_rate": 1.7972472284715415e-06,
|
||
|
|
"loss": 0.3263,
|
||
|
|
"mean_token_accuracy": 0.8821143126115203,
|
||
|
|
"num_tokens": 264211563.0,
|
||
|
|
"step": 613
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.389007568359375,
|
||
|
|
"epoch": 2.456,
|
||
|
|
"grad_norm": 0.6323306930432039,
|
||
|
|
"learning_rate": 1.7720898920267393e-06,
|
||
|
|
"loss": 0.3236,
|
||
|
|
"mean_token_accuracy": 0.8841777127236128,
|
||
|
|
"num_tokens": 264631508.0,
|
||
|
|
"step": 614
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38787841796875,
|
||
|
|
"epoch": 2.46,
|
||
|
|
"grad_norm": 0.6850999065086314,
|
||
|
|
"learning_rate": 1.7470927430702277e-06,
|
||
|
|
"loss": 0.3302,
|
||
|
|
"mean_token_accuracy": 0.8811214789748192,
|
||
|
|
"num_tokens": 265056615.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3837890625,
|
||
|
|
"epoch": 2.464,
|
||
|
|
"grad_norm": 0.6568250685775315,
|
||
|
|
"learning_rate": 1.7222562682663535e-06,
|
||
|
|
"loss": 0.3225,
|
||
|
|
"mean_token_accuracy": 0.8852691203355789,
|
||
|
|
"num_tokens": 265492863.0,
|
||
|
|
"step": 616
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384002685546875,
|
||
|
|
"epoch": 2.468,
|
||
|
|
"grad_norm": 0.6302041888433078,
|
||
|
|
"learning_rate": 1.6975809511513352e-06,
|
||
|
|
"loss": 0.3014,
|
||
|
|
"mean_token_accuracy": 0.889856580644846,
|
||
|
|
"num_tokens": 265905859.0,
|
||
|
|
"step": 617
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3795166015625,
|
||
|
|
"epoch": 2.472,
|
||
|
|
"grad_norm": 0.622286365279042,
|
||
|
|
"learning_rate": 1.6730672721238428e-06,
|
||
|
|
"loss": 0.3227,
|
||
|
|
"mean_token_accuracy": 0.8816931359469891,
|
||
|
|
"num_tokens": 266368407.0,
|
||
|
|
"step": 618
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.385467529296875,
|
||
|
|
"epoch": 2.476,
|
||
|
|
"grad_norm": 0.6160647888551942,
|
||
|
|
"learning_rate": 1.6487157084356454e-06,
|
||
|
|
"loss": 0.3187,
|
||
|
|
"mean_token_accuracy": 0.8854724783450365,
|
||
|
|
"num_tokens": 266805440.0,
|
||
|
|
"step": 619
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.382568359375,
|
||
|
|
"epoch": 2.48,
|
||
|
|
"grad_norm": 0.609905668201121,
|
||
|
|
"learning_rate": 1.6245267341823235e-06,
|
||
|
|
"loss": 0.3121,
|
||
|
|
"mean_token_accuracy": 0.8862016862258315,
|
||
|
|
"num_tokens": 267245007.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.392486572265625,
|
||
|
|
"epoch": 2.484,
|
||
|
|
"grad_norm": 0.6873221968582729,
|
||
|
|
"learning_rate": 1.600500820294041e-06,
|
||
|
|
"loss": 0.3273,
|
||
|
|
"mean_token_accuracy": 0.8827656377106905,
|
||
|
|
"num_tokens": 267670366.0,
|
||
|
|
"step": 621
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3856201171875,
|
||
|
|
"epoch": 2.488,
|
||
|
|
"grad_norm": 0.640082763234737,
|
||
|
|
"learning_rate": 1.5766384345263674e-06,
|
||
|
|
"loss": 0.3316,
|
||
|
|
"mean_token_accuracy": 0.8826957670971751,
|
||
|
|
"num_tokens": 268104370.0,
|
||
|
|
"step": 622
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383331298828125,
|
||
|
|
"epoch": 2.492,
|
||
|
|
"grad_norm": 0.6170248378378831,
|
||
|
|
"learning_rate": 1.5529400414511809e-06,
|
||
|
|
"loss": 0.3204,
|
||
|
|
"mean_token_accuracy": 0.8837010702118278,
|
||
|
|
"num_tokens": 268544793.0,
|
||
|
|
"step": 623
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.385040283203125,
|
||
|
|
"epoch": 2.496,
|
||
|
|
"grad_norm": 0.6044914949460987,
|
||
|
|
"learning_rate": 1.5294061024476148e-06,
|
||
|
|
"loss": 0.3326,
|
||
|
|
"mean_token_accuracy": 0.8818602953106165,
|
||
|
|
"num_tokens": 268982108.0,
|
||
|
|
"step": 624
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38775634765625,
|
||
|
|
"epoch": 2.5,
|
||
|
|
"grad_norm": 0.6226964380482034,
|
||
|
|
"learning_rate": 1.5060370756930919e-06,
|
||
|
|
"loss": 0.3095,
|
||
|
|
"mean_token_accuracy": 0.8886573808267713,
|
||
|
|
"num_tokens": 269407602.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38623046875,
|
||
|
|
"epoch": 2.504,
|
||
|
|
"grad_norm": 0.631582099145346,
|
||
|
|
"learning_rate": 1.4828334161543733e-06,
|
||
|
|
"loss": 0.3277,
|
||
|
|
"mean_token_accuracy": 0.8824242260307074,
|
||
|
|
"num_tokens": 269843206.0,
|
||
|
|
"step": 626
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384063720703125,
|
||
|
|
"epoch": 2.508,
|
||
|
|
"grad_norm": 0.6299802710503133,
|
||
|
|
"learning_rate": 1.4597955755787375e-06,
|
||
|
|
"loss": 0.3166,
|
||
|
|
"mean_token_accuracy": 0.8863658849149942,
|
||
|
|
"num_tokens": 270262338.0,
|
||
|
|
"step": 627
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38116455078125,
|
||
|
|
"epoch": 2.512,
|
||
|
|
"grad_norm": 0.6204862622321253,
|
||
|
|
"learning_rate": 1.4369240024851561e-06,
|
||
|
|
"loss": 0.3181,
|
||
|
|
"mean_token_accuracy": 0.8856295952573419,
|
||
|
|
"num_tokens": 270699850.0,
|
||
|
|
"step": 628
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3870849609375,
|
||
|
|
"epoch": 2.516,
|
||
|
|
"grad_norm": 0.6047572599469239,
|
||
|
|
"learning_rate": 1.414219142155585e-06,
|
||
|
|
"loss": 0.3284,
|
||
|
|
"mean_token_accuracy": 0.882879882119596,
|
||
|
|
"num_tokens": 271120339.0,
|
||
|
|
"step": 629
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38427734375,
|
||
|
|
"epoch": 2.52,
|
||
|
|
"grad_norm": 0.7178325031634158,
|
||
|
|
"learning_rate": 1.3916814366262677e-06,
|
||
|
|
"loss": 0.3131,
|
||
|
|
"mean_token_accuracy": 0.8854036265984178,
|
||
|
|
"num_tokens": 271570979.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3802490234375,
|
||
|
|
"epoch": 2.524,
|
||
|
|
"grad_norm": 0.622497603823067,
|
||
|
|
"learning_rate": 1.369311324679159e-06,
|
||
|
|
"loss": 0.3181,
|
||
|
|
"mean_token_accuracy": 0.885633397847414,
|
||
|
|
"num_tokens": 272017460.0,
|
||
|
|
"step": 631
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.393096923828125,
|
||
|
|
"epoch": 2.528,
|
||
|
|
"grad_norm": 0.6408649657268423,
|
||
|
|
"learning_rate": 1.3471092418333643e-06,
|
||
|
|
"loss": 0.3293,
|
||
|
|
"mean_token_accuracy": 0.8825702192261815,
|
||
|
|
"num_tokens": 272407355.0,
|
||
|
|
"step": 632
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38525390625,
|
||
|
|
"epoch": 2.532,
|
||
|
|
"grad_norm": 0.6468488430784601,
|
||
|
|
"learning_rate": 1.3250756203366633e-06,
|
||
|
|
"loss": 0.3146,
|
||
|
|
"mean_token_accuracy": 0.886208432726562,
|
||
|
|
"num_tokens": 272829943.0,
|
||
|
|
"step": 633
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388153076171875,
|
||
|
|
"epoch": 2.536,
|
||
|
|
"grad_norm": 0.6313231098892841,
|
||
|
|
"learning_rate": 1.3032108891570938e-06,
|
||
|
|
"loss": 0.3168,
|
||
|
|
"mean_token_accuracy": 0.8858510609716177,
|
||
|
|
"num_tokens": 273246671.0,
|
||
|
|
"step": 634
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38604736328125,
|
||
|
|
"epoch": 2.54,
|
||
|
|
"grad_norm": 0.6376957725476771,
|
||
|
|
"learning_rate": 1.281515473974614e-06,
|
||
|
|
"loss": 0.3271,
|
||
|
|
"mean_token_accuracy": 0.8837200487032533,
|
||
|
|
"num_tokens": 273669206.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.381927490234375,
|
||
|
|
"epoch": 2.544,
|
||
|
|
"grad_norm": 0.6375566484383391,
|
||
|
|
"learning_rate": 1.2599897971727926e-06,
|
||
|
|
"loss": 0.3056,
|
||
|
|
"mean_token_accuracy": 0.8876464394852519,
|
||
|
|
"num_tokens": 274097354.0,
|
||
|
|
"step": 636
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38153076171875,
|
||
|
|
"epoch": 2.548,
|
||
|
|
"grad_norm": 0.629169536287612,
|
||
|
|
"learning_rate": 1.2386342778305993e-06,
|
||
|
|
"loss": 0.324,
|
||
|
|
"mean_token_accuracy": 0.8828590949997306,
|
||
|
|
"num_tokens": 274526359.0,
|
||
|
|
"step": 637
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384735107421875,
|
||
|
|
"epoch": 2.552,
|
||
|
|
"grad_norm": 0.6553494485101379,
|
||
|
|
"learning_rate": 1.2174493317142443e-06,
|
||
|
|
"loss": 0.3333,
|
||
|
|
"mean_token_accuracy": 0.8820989085361362,
|
||
|
|
"num_tokens": 274962479.0,
|
||
|
|
"step": 638
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3787841796875,
|
||
|
|
"epoch": 2.556,
|
||
|
|
"grad_norm": 1.0141467200628742,
|
||
|
|
"learning_rate": 1.196435371269089e-06,
|
||
|
|
"loss": 0.3091,
|
||
|
|
"mean_token_accuracy": 0.8869879674166441,
|
||
|
|
"num_tokens": 275400063.0,
|
||
|
|
"step": 639
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3887939453125,
|
||
|
|
"epoch": 2.56,
|
||
|
|
"grad_norm": 0.6463002822705318,
|
||
|
|
"learning_rate": 1.1755928056115951e-06,
|
||
|
|
"loss": 0.3211,
|
||
|
|
"mean_token_accuracy": 0.8871809123083949,
|
||
|
|
"num_tokens": 275829826.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3941650390625,
|
||
|
|
"epoch": 2.564,
|
||
|
|
"grad_norm": 0.65440234611849,
|
||
|
|
"learning_rate": 1.1549220405213878e-06,
|
||
|
|
"loss": 0.3121,
|
||
|
|
"mean_token_accuracy": 0.8876083409413695,
|
||
|
|
"num_tokens": 276232549.0,
|
||
|
|
"step": 641
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3824462890625,
|
||
|
|
"epoch": 2.568,
|
||
|
|
"grad_norm": 0.6281659939831451,
|
||
|
|
"learning_rate": 1.1344234784333375e-06,
|
||
|
|
"loss": 0.3163,
|
||
|
|
"mean_token_accuracy": 0.8846692852675915,
|
||
|
|
"num_tokens": 276685306.0,
|
||
|
|
"step": 642
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.381866455078125,
|
||
|
|
"epoch": 2.572,
|
||
|
|
"grad_norm": 0.6698509729221452,
|
||
|
|
"learning_rate": 1.1140975184297332e-06,
|
||
|
|
"loss": 0.3182,
|
||
|
|
"mean_token_accuracy": 0.887131629511714,
|
||
|
|
"num_tokens": 277108759.0,
|
||
|
|
"step": 643
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3912353515625,
|
||
|
|
"epoch": 2.576,
|
||
|
|
"grad_norm": 0.5994384440975246,
|
||
|
|
"learning_rate": 1.093944556232499e-06,
|
||
|
|
"loss": 0.3121,
|
||
|
|
"mean_token_accuracy": 0.887452301569283,
|
||
|
|
"num_tokens": 277521010.0,
|
||
|
|
"step": 644
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3873291015625,
|
||
|
|
"epoch": 2.58,
|
||
|
|
"grad_norm": 0.6491625905834876,
|
||
|
|
"learning_rate": 1.0739649841955135e-06,
|
||
|
|
"loss": 0.3222,
|
||
|
|
"mean_token_accuracy": 0.882330465130508,
|
||
|
|
"num_tokens": 277959598.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38616943359375,
|
||
|
|
"epoch": 2.584,
|
||
|
|
"grad_norm": 0.6526530597009726,
|
||
|
|
"learning_rate": 1.0541591912969506e-06,
|
||
|
|
"loss": 0.3062,
|
||
|
|
"mean_token_accuracy": 0.8896217923611403,
|
||
|
|
"num_tokens": 278399073.0,
|
||
|
|
"step": 646
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.389678955078125,
|
||
|
|
"epoch": 2.588,
|
||
|
|
"grad_norm": 0.6207638905441022,
|
||
|
|
"learning_rate": 1.0345275631317165e-06,
|
||
|
|
"loss": 0.326,
|
||
|
|
"mean_token_accuracy": 0.8824352445080876,
|
||
|
|
"num_tokens": 278834878.0,
|
||
|
|
"step": 647
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.382598876953125,
|
||
|
|
"epoch": 2.592,
|
||
|
|
"grad_norm": 0.6381908822179618,
|
||
|
|
"learning_rate": 1.0150704819039358e-06,
|
||
|
|
"loss": 0.3301,
|
||
|
|
"mean_token_accuracy": 0.881490919739008,
|
||
|
|
"num_tokens": 279278852.0,
|
||
|
|
"step": 648
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3868408203125,
|
||
|
|
"epoch": 2.596,
|
||
|
|
"grad_norm": 0.6237265012394507,
|
||
|
|
"learning_rate": 9.957883264195224e-07,
|
||
|
|
"loss": 0.3175,
|
||
|
|
"mean_token_accuracy": 0.886386756785214,
|
||
|
|
"num_tokens": 279690146.0,
|
||
|
|
"step": 649
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.380615234375,
|
||
|
|
"epoch": 2.6,
|
||
|
|
"grad_norm": 0.6062661636933474,
|
||
|
|
"learning_rate": 9.766814720787887e-07,
|
||
|
|
"loss": 0.3097,
|
||
|
|
"mean_token_accuracy": 0.8863510163500905,
|
||
|
|
"num_tokens": 280135880.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387115478515625,
|
||
|
|
"epoch": 2.604,
|
||
|
|
"grad_norm": 0.6323450088238554,
|
||
|
|
"learning_rate": 9.577502908691526e-07,
|
||
|
|
"loss": 0.3301,
|
||
|
|
"mean_token_accuracy": 0.8812247337773442,
|
||
|
|
"num_tokens": 280583221.0,
|
||
|
|
"step": 651
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.389923095703125,
|
||
|
|
"epoch": 2.608,
|
||
|
|
"grad_norm": 0.6097510084885248,
|
||
|
|
"learning_rate": 9.389951513578787e-07,
|
||
|
|
"loss": 0.3216,
|
||
|
|
"mean_token_accuracy": 0.882429831661284,
|
||
|
|
"num_tokens": 281010180.0,
|
||
|
|
"step": 652
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.379608154296875,
|
||
|
|
"epoch": 2.612,
|
||
|
|
"grad_norm": 0.7020996410176391,
|
||
|
|
"learning_rate": 9.20416418684924e-07,
|
||
|
|
"loss": 0.3172,
|
||
|
|
"mean_token_accuracy": 0.8843332845717669,
|
||
|
|
"num_tokens": 281464029.0,
|
||
|
|
"step": 653
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3807373046875,
|
||
|
|
"epoch": 2.616,
|
||
|
|
"grad_norm": 0.6502742463088902,
|
||
|
|
"learning_rate": 9.020144545558085e-07,
|
||
|
|
"loss": 0.325,
|
||
|
|
"mean_token_accuracy": 0.8821850307285786,
|
||
|
|
"num_tokens": 281908447.0,
|
||
|
|
"step": 654
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38623046875,
|
||
|
|
"epoch": 2.62,
|
||
|
|
"grad_norm": 0.6438312036581462,
|
||
|
|
"learning_rate": 8.837896172345827e-07,
|
||
|
|
"loss": 0.3242,
|
||
|
|
"mean_token_accuracy": 0.884060300886631,
|
||
|
|
"num_tokens": 282342628.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39678955078125,
|
||
|
|
"epoch": 2.624,
|
||
|
|
"grad_norm": 0.6464132265166465,
|
||
|
|
"learning_rate": 8.657422615368527e-07,
|
||
|
|
"loss": 0.303,
|
||
|
|
"mean_token_accuracy": 0.8899175068363547,
|
||
|
|
"num_tokens": 282735527.0,
|
||
|
|
"step": 656
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38726806640625,
|
||
|
|
"epoch": 2.628,
|
||
|
|
"grad_norm": 0.6337229749994866,
|
||
|
|
"learning_rate": 8.478727388228736e-07,
|
||
|
|
"loss": 0.3125,
|
||
|
|
"mean_token_accuracy": 0.8865322135388851,
|
||
|
|
"num_tokens": 283163056.0,
|
||
|
|
"step": 657
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383941650390625,
|
||
|
|
"epoch": 2.632,
|
||
|
|
"grad_norm": 0.6962579596749039,
|
||
|
|
"learning_rate": 8.301813969907058e-07,
|
||
|
|
"loss": 0.3068,
|
||
|
|
"mean_token_accuracy": 0.8878968292847276,
|
||
|
|
"num_tokens": 283592438.0,
|
||
|
|
"step": 658
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.380615234375,
|
||
|
|
"epoch": 2.636,
|
||
|
|
"grad_norm": 0.6015060363626404,
|
||
|
|
"learning_rate": 8.126685804694401e-07,
|
||
|
|
"loss": 0.309,
|
||
|
|
"mean_token_accuracy": 0.8880268186330795,
|
||
|
|
"num_tokens": 284039209.0,
|
||
|
|
"step": 659
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.378082275390625,
|
||
|
|
"epoch": 2.64,
|
||
|
|
"grad_norm": 0.6215904157488176,
|
||
|
|
"learning_rate": 7.953346302124943e-07,
|
||
|
|
"loss": 0.3187,
|
||
|
|
"mean_token_accuracy": 0.8871674025431275,
|
||
|
|
"num_tokens": 284484347.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384857177734375,
|
||
|
|
"epoch": 2.644,
|
||
|
|
"grad_norm": 0.6253531383438732,
|
||
|
|
"learning_rate": 7.781798836909826e-07,
|
||
|
|
"loss": 0.3209,
|
||
|
|
"mean_token_accuracy": 0.8840792588889599,
|
||
|
|
"num_tokens": 284913077.0,
|
||
|
|
"step": 661
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.389129638671875,
|
||
|
|
"epoch": 2.648,
|
||
|
|
"grad_norm": 0.6179886639806718,
|
||
|
|
"learning_rate": 7.612046748871327e-07,
|
||
|
|
"loss": 0.3131,
|
||
|
|
"mean_token_accuracy": 0.8876432795077562,
|
||
|
|
"num_tokens": 285340201.0,
|
||
|
|
"step": 662
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.381866455078125,
|
||
|
|
"epoch": 2.652,
|
||
|
|
"grad_norm": 0.5975030461311783,
|
||
|
|
"learning_rate": 7.4440933428779e-07,
|
||
|
|
"loss": 0.3037,
|
||
|
|
"mean_token_accuracy": 0.8897746112197638,
|
||
|
|
"num_tokens": 285766878.0,
|
||
|
|
"step": 663
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3858642578125,
|
||
|
|
"epoch": 2.656,
|
||
|
|
"grad_norm": 0.6306613553928485,
|
||
|
|
"learning_rate": 7.277941888779827e-07,
|
||
|
|
"loss": 0.3179,
|
||
|
|
"mean_token_accuracy": 0.8850843440741301,
|
||
|
|
"num_tokens": 286200320.0,
|
||
|
|
"step": 664
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.380401611328125,
|
||
|
|
"epoch": 2.66,
|
||
|
|
"grad_norm": 0.6153866678252313,
|
||
|
|
"learning_rate": 7.11359562134557e-07,
|
||
|
|
"loss": 0.3222,
|
||
|
|
"mean_token_accuracy": 0.8843325190246105,
|
||
|
|
"num_tokens": 286662516.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38818359375,
|
||
|
|
"epoch": 2.664,
|
||
|
|
"grad_norm": 0.608725091223259,
|
||
|
|
"learning_rate": 6.951057740198797e-07,
|
||
|
|
"loss": 0.3125,
|
||
|
|
"mean_token_accuracy": 0.8864667201414704,
|
||
|
|
"num_tokens": 287084045.0,
|
||
|
|
"step": 666
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3846435546875,
|
||
|
|
"epoch": 2.668,
|
||
|
|
"grad_norm": 0.5933810502312873,
|
||
|
|
"learning_rate": 6.790331409756046e-07,
|
||
|
|
"loss": 0.3071,
|
||
|
|
"mean_token_accuracy": 0.8896127883344889,
|
||
|
|
"num_tokens": 287507695.0,
|
||
|
|
"step": 667
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38629150390625,
|
||
|
|
"epoch": 2.672,
|
||
|
|
"grad_norm": 0.6259349243058988,
|
||
|
|
"learning_rate": 6.631419759165169e-07,
|
||
|
|
"loss": 0.3149,
|
||
|
|
"mean_token_accuracy": 0.8856349429115653,
|
||
|
|
"num_tokens": 287932473.0,
|
||
|
|
"step": 668
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38177490234375,
|
||
|
|
"epoch": 2.676,
|
||
|
|
"grad_norm": 0.6240946828393763,
|
||
|
|
"learning_rate": 6.47432588224437e-07,
|
||
|
|
"loss": 0.3112,
|
||
|
|
"mean_token_accuracy": 0.8893291493877769,
|
||
|
|
"num_tokens": 288384176.0,
|
||
|
|
"step": 669
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.386932373046875,
|
||
|
|
"epoch": 2.68,
|
||
|
|
"grad_norm": 0.6270623796470234,
|
||
|
|
"learning_rate": 6.319052837422013e-07,
|
||
|
|
"loss": 0.3339,
|
||
|
|
"mean_token_accuracy": 0.880031406879425,
|
||
|
|
"num_tokens": 288803503.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3880615234375,
|
||
|
|
"epoch": 2.684,
|
||
|
|
"grad_norm": 0.6262798398692215,
|
||
|
|
"learning_rate": 6.165603647677054e-07,
|
||
|
|
"loss": 0.3331,
|
||
|
|
"mean_token_accuracy": 0.8801755160093307,
|
||
|
|
"num_tokens": 289225928.0,
|
||
|
|
"step": 671
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38922119140625,
|
||
|
|
"epoch": 2.6879999999999997,
|
||
|
|
"grad_norm": 0.6013328076204115,
|
||
|
|
"learning_rate": 6.013981300480176e-07,
|
||
|
|
"loss": 0.3083,
|
||
|
|
"mean_token_accuracy": 0.8870955817401409,
|
||
|
|
"num_tokens": 289639024.0,
|
||
|
|
"step": 672
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38922119140625,
|
||
|
|
"epoch": 2.692,
|
||
|
|
"grad_norm": 0.6086230362592738,
|
||
|
|
"learning_rate": 5.864188747735622e-07,
|
||
|
|
"loss": 0.3218,
|
||
|
|
"mean_token_accuracy": 0.8845323557034135,
|
||
|
|
"num_tokens": 290073682.0,
|
||
|
|
"step": 673
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38616943359375,
|
||
|
|
"epoch": 2.6959999999999997,
|
||
|
|
"grad_norm": 0.6287079530697675,
|
||
|
|
"learning_rate": 5.716228905723808e-07,
|
||
|
|
"loss": 0.3092,
|
||
|
|
"mean_token_accuracy": 0.8880302328616381,
|
||
|
|
"num_tokens": 290500887.0,
|
||
|
|
"step": 674
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384124755859375,
|
||
|
|
"epoch": 2.7,
|
||
|
|
"grad_norm": 0.6235864544497625,
|
||
|
|
"learning_rate": 5.570104655044428e-07,
|
||
|
|
"loss": 0.3269,
|
||
|
|
"mean_token_accuracy": 0.8841457972303033,
|
||
|
|
"num_tokens": 290929686.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38739013671875,
|
||
|
|
"epoch": 2.7039999999999997,
|
||
|
|
"grad_norm": 0.6279926286810523,
|
||
|
|
"learning_rate": 5.425818840560438e-07,
|
||
|
|
"loss": 0.3193,
|
||
|
|
"mean_token_accuracy": 0.8858560882508755,
|
||
|
|
"num_tokens": 291348534.0,
|
||
|
|
"step": 676
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.391021728515625,
|
||
|
|
"epoch": 2.708,
|
||
|
|
"grad_norm": 0.6512251547504384,
|
||
|
|
"learning_rate": 5.283374271342645e-07,
|
||
|
|
"loss": 0.3054,
|
||
|
|
"mean_token_accuracy": 0.8885214906185865,
|
||
|
|
"num_tokens": 291751928.0,
|
||
|
|
"step": 677
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.391937255859375,
|
||
|
|
"epoch": 2.7119999999999997,
|
||
|
|
"grad_norm": 0.6384396120018543,
|
||
|
|
"learning_rate": 5.142773720615091e-07,
|
||
|
|
"loss": 0.3207,
|
||
|
|
"mean_token_accuracy": 0.8856092458590865,
|
||
|
|
"num_tokens": 292172114.0,
|
||
|
|
"step": 678
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.385223388671875,
|
||
|
|
"epoch": 2.716,
|
||
|
|
"grad_norm": 0.6176462738912027,
|
||
|
|
"learning_rate": 5.004019925700921e-07,
|
||
|
|
"loss": 0.3125,
|
||
|
|
"mean_token_accuracy": 0.8883070889860392,
|
||
|
|
"num_tokens": 292585966.0,
|
||
|
|
"step": 679
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390533447265625,
|
||
|
|
"epoch": 2.7199999999999998,
|
||
|
|
"grad_norm": 0.7242794770293791,
|
||
|
|
"learning_rate": 4.867115587969218e-07,
|
||
|
|
"loss": 0.3249,
|
||
|
|
"mean_token_accuracy": 0.8838935270905495,
|
||
|
|
"num_tokens": 293020362.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.385467529296875,
|
||
|
|
"epoch": 2.724,
|
||
|
|
"grad_norm": 0.6027631487913132,
|
||
|
|
"learning_rate": 4.7320633727823363e-07,
|
||
|
|
"loss": 0.3204,
|
||
|
|
"mean_token_accuracy": 0.8854356305673718,
|
||
|
|
"num_tokens": 293449430.0,
|
||
|
|
"step": 681
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387603759765625,
|
||
|
|
"epoch": 2.7279999999999998,
|
||
|
|
"grad_norm": 0.6138927394672524,
|
||
|
|
"learning_rate": 4.598865909444095e-07,
|
||
|
|
"loss": 0.3164,
|
||
|
|
"mean_token_accuracy": 0.8867169562727213,
|
||
|
|
"num_tokens": 293888995.0,
|
||
|
|
"step": 682
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390228271484375,
|
||
|
|
"epoch": 2.732,
|
||
|
|
"grad_norm": 0.6088189203014976,
|
||
|
|
"learning_rate": 4.4675257911484526e-07,
|
||
|
|
"loss": 0.3108,
|
||
|
|
"mean_token_accuracy": 0.8861931953579187,
|
||
|
|
"num_tokens": 294305216.0,
|
||
|
|
"step": 683
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.379852294921875,
|
||
|
|
"epoch": 2.7359999999999998,
|
||
|
|
"grad_norm": 0.6112168480778134,
|
||
|
|
"learning_rate": 4.3380455749291504e-07,
|
||
|
|
"loss": 0.3204,
|
||
|
|
"mean_token_accuracy": 0.8850634396076202,
|
||
|
|
"num_tokens": 294766131.0,
|
||
|
|
"step": 684
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3836669921875,
|
||
|
|
"epoch": 2.74,
|
||
|
|
"grad_norm": 0.6243355700686475,
|
||
|
|
"learning_rate": 4.2104277816098606e-07,
|
||
|
|
"loss": 0.307,
|
||
|
|
"mean_token_accuracy": 0.8891284754499793,
|
||
|
|
"num_tokens": 295194543.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383575439453125,
|
||
|
|
"epoch": 2.7439999999999998,
|
||
|
|
"grad_norm": 0.5903195115366202,
|
||
|
|
"learning_rate": 4.0846748957551696e-07,
|
||
|
|
"loss": 0.3047,
|
||
|
|
"mean_token_accuracy": 0.8886916963383555,
|
||
|
|
"num_tokens": 295625199.0,
|
||
|
|
"step": 686
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38555908203125,
|
||
|
|
"epoch": 2.748,
|
||
|
|
"grad_norm": 0.6154974646569,
|
||
|
|
"learning_rate": 3.960789365622075e-07,
|
||
|
|
"loss": 0.3197,
|
||
|
|
"mean_token_accuracy": 0.8853367818519473,
|
||
|
|
"num_tokens": 296060525.0,
|
||
|
|
"step": 687
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.389404296875,
|
||
|
|
"epoch": 2.752,
|
||
|
|
"grad_norm": 0.631420373748385,
|
||
|
|
"learning_rate": 3.838773603112489e-07,
|
||
|
|
"loss": 0.3248,
|
||
|
|
"mean_token_accuracy": 0.8861450525000691,
|
||
|
|
"num_tokens": 296488512.0,
|
||
|
|
"step": 688
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3856201171875,
|
||
|
|
"epoch": 2.7560000000000002,
|
||
|
|
"grad_norm": 0.6176493094867966,
|
||
|
|
"learning_rate": 3.7186299837261855e-07,
|
||
|
|
"loss": 0.3126,
|
||
|
|
"mean_token_accuracy": 0.8872075108811259,
|
||
|
|
"num_tokens": 296924404.0,
|
||
|
|
"step": 689
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.386932373046875,
|
||
|
|
"epoch": 2.76,
|
||
|
|
"grad_norm": 0.6070436851236336,
|
||
|
|
"learning_rate": 3.600360846514539e-07,
|
||
|
|
"loss": 0.315,
|
||
|
|
"mean_token_accuracy": 0.8865385623648763,
|
||
|
|
"num_tokens": 297345770.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38067626953125,
|
||
|
|
"epoch": 2.7640000000000002,
|
||
|
|
"grad_norm": 0.6250143569161336,
|
||
|
|
"learning_rate": 3.483968494035039e-07,
|
||
|
|
"loss": 0.3155,
|
||
|
|
"mean_token_accuracy": 0.8858968764543533,
|
||
|
|
"num_tokens": 297776100.0,
|
||
|
|
"step": 691
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388946533203125,
|
||
|
|
"epoch": 2.768,
|
||
|
|
"grad_norm": 0.6174656632542973,
|
||
|
|
"learning_rate": 3.369455192306459e-07,
|
||
|
|
"loss": 0.3189,
|
||
|
|
"mean_token_accuracy": 0.8857243089005351,
|
||
|
|
"num_tokens": 298190692.0,
|
||
|
|
"step": 692
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383819580078125,
|
||
|
|
"epoch": 2.7720000000000002,
|
||
|
|
"grad_norm": 0.6833172910337608,
|
||
|
|
"learning_rate": 3.256823170764689e-07,
|
||
|
|
"loss": 0.3164,
|
||
|
|
"mean_token_accuracy": 0.8862426020205021,
|
||
|
|
"num_tokens": 298623881.0,
|
||
|
|
"step": 693
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38421630859375,
|
||
|
|
"epoch": 2.776,
|
||
|
|
"grad_norm": 0.6192038351142729,
|
||
|
|
"learning_rate": 3.146074622219364e-07,
|
||
|
|
"loss": 0.3124,
|
||
|
|
"mean_token_accuracy": 0.8866107268258929,
|
||
|
|
"num_tokens": 299072200.0,
|
||
|
|
"step": 694
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387908935546875,
|
||
|
|
"epoch": 2.7800000000000002,
|
||
|
|
"grad_norm": 0.5932005134533544,
|
||
|
|
"learning_rate": 3.0372117028111825e-07,
|
||
|
|
"loss": 0.3141,
|
||
|
|
"mean_token_accuracy": 0.8876512804999948,
|
||
|
|
"num_tokens": 299494616.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383514404296875,
|
||
|
|
"epoch": 2.784,
|
||
|
|
"grad_norm": 0.5857122840381176,
|
||
|
|
"learning_rate": 2.930236531969932e-07,
|
||
|
|
"loss": 0.3131,
|
||
|
|
"mean_token_accuracy": 0.8877815566956997,
|
||
|
|
"num_tokens": 299929131.0,
|
||
|
|
"step": 696
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38189697265625,
|
||
|
|
"epoch": 2.7880000000000003,
|
||
|
|
"grad_norm": 0.6240324665386945,
|
||
|
|
"learning_rate": 2.8251511923731655e-07,
|
||
|
|
"loss": 0.3191,
|
||
|
|
"mean_token_accuracy": 0.8852393655106425,
|
||
|
|
"num_tokens": 300375188.0,
|
||
|
|
"step": 697
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.390380859375,
|
||
|
|
"epoch": 2.792,
|
||
|
|
"grad_norm": 0.6268380888087441,
|
||
|
|
"learning_rate": 2.721957729905755e-07,
|
||
|
|
"loss": 0.3222,
|
||
|
|
"mean_token_accuracy": 0.8849149039015174,
|
||
|
|
"num_tokens": 300791782.0,
|
||
|
|
"step": 698
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.376922607421875,
|
||
|
|
"epoch": 2.7960000000000003,
|
||
|
|
"grad_norm": 0.6198915310383893,
|
||
|
|
"learning_rate": 2.620658153619959e-07,
|
||
|
|
"loss": 0.3184,
|
||
|
|
"mean_token_accuracy": 0.8855067268013954,
|
||
|
|
"num_tokens": 301260557.0,
|
||
|
|
"step": 699
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388214111328125,
|
||
|
|
"epoch": 2.8,
|
||
|
|
"grad_norm": 0.5784219774060501,
|
||
|
|
"learning_rate": 2.5212544356964073e-07,
|
||
|
|
"loss": 0.3067,
|
||
|
|
"mean_token_accuracy": 0.8888456197455525,
|
||
|
|
"num_tokens": 301670065.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.386627197265625,
|
||
|
|
"epoch": 2.8040000000000003,
|
||
|
|
"grad_norm": 0.610478159060291,
|
||
|
|
"learning_rate": 2.423748511405577e-07,
|
||
|
|
"loss": 0.3195,
|
||
|
|
"mean_token_accuracy": 0.8867878997698426,
|
||
|
|
"num_tokens": 302114825.0,
|
||
|
|
"step": 701
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388397216796875,
|
||
|
|
"epoch": 2.808,
|
||
|
|
"grad_norm": 0.6024007272307298,
|
||
|
|
"learning_rate": 2.328142279070289e-07,
|
||
|
|
"loss": 0.3074,
|
||
|
|
"mean_token_accuracy": 0.8878991520032287,
|
||
|
|
"num_tokens": 302557866.0,
|
||
|
|
"step": 702
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384857177734375,
|
||
|
|
"epoch": 2.8120000000000003,
|
||
|
|
"grad_norm": 0.5973212459647047,
|
||
|
|
"learning_rate": 2.2344376000285606e-07,
|
||
|
|
"loss": 0.3233,
|
||
|
|
"mean_token_accuracy": 0.8850280288606882,
|
||
|
|
"num_tokens": 303002226.0,
|
||
|
|
"step": 703
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.391448974609375,
|
||
|
|
"epoch": 2.816,
|
||
|
|
"grad_norm": 0.6148099846549463,
|
||
|
|
"learning_rate": 2.1426362985975334e-07,
|
||
|
|
"loss": 0.2998,
|
||
|
|
"mean_token_accuracy": 0.8905485738068819,
|
||
|
|
"num_tokens": 303406909.0,
|
||
|
|
"step": 704
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39190673828125,
|
||
|
|
"epoch": 2.82,
|
||
|
|
"grad_norm": 0.6098232708309501,
|
||
|
|
"learning_rate": 2.052740162037814e-07,
|
||
|
|
"loss": 0.3246,
|
||
|
|
"mean_token_accuracy": 0.8855294845998287,
|
||
|
|
"num_tokens": 303833709.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.382598876953125,
|
||
|
|
"epoch": 2.824,
|
||
|
|
"grad_norm": 0.6160318716547906,
|
||
|
|
"learning_rate": 1.9647509405188115e-07,
|
||
|
|
"loss": 0.3147,
|
||
|
|
"mean_token_accuracy": 0.8862805562093854,
|
||
|
|
"num_tokens": 304263846.0,
|
||
|
|
"step": 706
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.386932373046875,
|
||
|
|
"epoch": 2.828,
|
||
|
|
"grad_norm": 0.6178367278331753,
|
||
|
|
"learning_rate": 1.8786703470845546e-07,
|
||
|
|
"loss": 0.3077,
|
||
|
|
"mean_token_accuracy": 0.8874261844903231,
|
||
|
|
"num_tokens": 304684545.0,
|
||
|
|
"step": 707
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.380615234375,
|
||
|
|
"epoch": 2.832,
|
||
|
|
"grad_norm": 0.6046390818527115,
|
||
|
|
"learning_rate": 1.7945000576203962e-07,
|
||
|
|
"loss": 0.3088,
|
||
|
|
"mean_token_accuracy": 0.888632545247674,
|
||
|
|
"num_tokens": 305140949.0,
|
||
|
|
"step": 708
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384246826171875,
|
||
|
|
"epoch": 2.836,
|
||
|
|
"grad_norm": 0.5965081996545096,
|
||
|
|
"learning_rate": 1.7122417108203727e-07,
|
||
|
|
"loss": 0.3063,
|
||
|
|
"mean_token_accuracy": 0.8875861754640937,
|
||
|
|
"num_tokens": 305576247.0,
|
||
|
|
"step": 709
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.385498046875,
|
||
|
|
"epoch": 2.84,
|
||
|
|
"grad_norm": 0.6352373103381211,
|
||
|
|
"learning_rate": 1.6318969081553283e-07,
|
||
|
|
"loss": 0.3225,
|
||
|
|
"mean_token_accuracy": 0.886294306255877,
|
||
|
|
"num_tokens": 306015310.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383544921875,
|
||
|
|
"epoch": 2.844,
|
||
|
|
"grad_norm": 0.5951846558370995,
|
||
|
|
"learning_rate": 1.553467213841664e-07,
|
||
|
|
"loss": 0.3258,
|
||
|
|
"mean_token_accuracy": 0.8848567642271519,
|
||
|
|
"num_tokens": 306449953.0,
|
||
|
|
"step": 711
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.385345458984375,
|
||
|
|
"epoch": 2.848,
|
||
|
|
"grad_norm": 0.6624211548269271,
|
||
|
|
"learning_rate": 1.4769541548109721e-07,
|
||
|
|
"loss": 0.3189,
|
||
|
|
"mean_token_accuracy": 0.8862940901890397,
|
||
|
|
"num_tokens": 306869158.0,
|
||
|
|
"step": 712
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39044189453125,
|
||
|
|
"epoch": 2.852,
|
||
|
|
"grad_norm": 0.6378222960734339,
|
||
|
|
"learning_rate": 1.4023592206802383e-07,
|
||
|
|
"loss": 0.3377,
|
||
|
|
"mean_token_accuracy": 0.8787785656750202,
|
||
|
|
"num_tokens": 307291781.0,
|
||
|
|
"step": 713
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3890380859375,
|
||
|
|
"epoch": 2.856,
|
||
|
|
"grad_norm": 0.6198151930784155,
|
||
|
|
"learning_rate": 1.329683863722897e-07,
|
||
|
|
"loss": 0.3061,
|
||
|
|
"mean_token_accuracy": 0.8910735612735152,
|
||
|
|
"num_tokens": 307698850.0,
|
||
|
|
"step": 714
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38128662109375,
|
||
|
|
"epoch": 2.86,
|
||
|
|
"grad_norm": 0.6056214401028286,
|
||
|
|
"learning_rate": 1.2589294988404887e-07,
|
||
|
|
"loss": 0.3061,
|
||
|
|
"mean_token_accuracy": 0.8911067135632038,
|
||
|
|
"num_tokens": 308129170.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38128662109375,
|
||
|
|
"epoch": 2.864,
|
||
|
|
"grad_norm": 0.6110606811080237,
|
||
|
|
"learning_rate": 1.1900975035351924e-07,
|
||
|
|
"loss": 0.3195,
|
||
|
|
"mean_token_accuracy": 0.8843246959149837,
|
||
|
|
"num_tokens": 308559010.0,
|
||
|
|
"step": 716
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.386199951171875,
|
||
|
|
"epoch": 2.868,
|
||
|
|
"grad_norm": 0.6146762298107256,
|
||
|
|
"learning_rate": 1.1231892178829474e-07,
|
||
|
|
"loss": 0.3232,
|
||
|
|
"mean_token_accuracy": 0.8830932695418596,
|
||
|
|
"num_tokens": 308975843.0,
|
||
|
|
"step": 717
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.378814697265625,
|
||
|
|
"epoch": 2.872,
|
||
|
|
"grad_norm": 0.586811860540753,
|
||
|
|
"learning_rate": 1.0582059445074288e-07,
|
||
|
|
"loss": 0.3056,
|
||
|
|
"mean_token_accuracy": 0.8887392682954669,
|
||
|
|
"num_tokens": 309422383.0,
|
||
|
|
"step": 718
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388702392578125,
|
||
|
|
"epoch": 2.876,
|
||
|
|
"grad_norm": 0.6127971970880335,
|
||
|
|
"learning_rate": 9.951489485545696e-08,
|
||
|
|
"loss": 0.3128,
|
||
|
|
"mean_token_accuracy": 0.8878753315657377,
|
||
|
|
"num_tokens": 309830483.0,
|
||
|
|
"step": 719
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.381072998046875,
|
||
|
|
"epoch": 2.88,
|
||
|
|
"grad_norm": 0.6070027100195104,
|
||
|
|
"learning_rate": 9.340194576680562e-08,
|
||
|
|
"loss": 0.3079,
|
||
|
|
"mean_token_accuracy": 0.8888015942648053,
|
||
|
|
"num_tokens": 310247175.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38031005859375,
|
||
|
|
"epoch": 2.884,
|
||
|
|
"grad_norm": 0.6233577173139083,
|
||
|
|
"learning_rate": 8.74818661965382e-08,
|
||
|
|
"loss": 0.2979,
|
||
|
|
"mean_token_accuracy": 0.8913767877966166,
|
||
|
|
"num_tokens": 310674697.0,
|
||
|
|
"step": 721
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384063720703125,
|
||
|
|
"epoch": 2.888,
|
||
|
|
"grad_norm": 0.6395722152570308,
|
||
|
|
"learning_rate": 8.175477140146327e-08,
|
||
|
|
"loss": 0.3249,
|
||
|
|
"mean_token_accuracy": 0.884283890016377,
|
||
|
|
"num_tokens": 311113672.0,
|
||
|
|
"step": 722
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.382049560546875,
|
||
|
|
"epoch": 2.892,
|
||
|
|
"grad_norm": 0.6046711033937197,
|
||
|
|
"learning_rate": 7.622077288121033e-08,
|
||
|
|
"loss": 0.3126,
|
||
|
|
"mean_token_accuracy": 0.8866025386378169,
|
||
|
|
"num_tokens": 311545478.0,
|
||
|
|
"step": 723
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38739013671875,
|
||
|
|
"epoch": 2.896,
|
||
|
|
"grad_norm": 0.638449551275483,
|
||
|
|
"learning_rate": 7.087997837605831e-08,
|
||
|
|
"loss": 0.3144,
|
||
|
|
"mean_token_accuracy": 0.8893121806904674,
|
||
|
|
"num_tokens": 311951388.0,
|
||
|
|
"step": 724
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.382049560546875,
|
||
|
|
"epoch": 2.9,
|
||
|
|
"grad_norm": 0.6191630789624003,
|
||
|
|
"learning_rate": 6.573249186483721e-08,
|
||
|
|
"loss": 0.3088,
|
||
|
|
"mean_token_accuracy": 0.8877979721873999,
|
||
|
|
"num_tokens": 312375648.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383453369140625,
|
||
|
|
"epoch": 2.904,
|
||
|
|
"grad_norm": 0.5921620043095492,
|
||
|
|
"learning_rate": 6.077841356290082e-08,
|
||
|
|
"loss": 0.3188,
|
||
|
|
"mean_token_accuracy": 0.8858416993170977,
|
||
|
|
"num_tokens": 312802165.0,
|
||
|
|
"step": 726
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.381805419921875,
|
||
|
|
"epoch": 2.908,
|
||
|
|
"grad_norm": 0.6201699219273529,
|
||
|
|
"learning_rate": 5.6017839920180506e-08,
|
||
|
|
"loss": 0.3126,
|
||
|
|
"mean_token_accuracy": 0.8880118168890476,
|
||
|
|
"num_tokens": 313232518.0,
|
||
|
|
"step": 727
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38726806640625,
|
||
|
|
"epoch": 2.912,
|
||
|
|
"grad_norm": 0.6011217173183366,
|
||
|
|
"learning_rate": 5.1450863619304514e-08,
|
||
|
|
"loss": 0.3164,
|
||
|
|
"mean_token_accuracy": 0.8850157065317035,
|
||
|
|
"num_tokens": 313641264.0,
|
||
|
|
"step": 728
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3804931640625,
|
||
|
|
"epoch": 2.916,
|
||
|
|
"grad_norm": 0.5874482091504839,
|
||
|
|
"learning_rate": 4.7077573573793836e-08,
|
||
|
|
"loss": 0.3016,
|
||
|
|
"mean_token_accuracy": 0.8907887460663915,
|
||
|
|
"num_tokens": 314075771.0,
|
||
|
|
"step": 729
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38983154296875,
|
||
|
|
"epoch": 2.92,
|
||
|
|
"grad_norm": 0.5998645712409401,
|
||
|
|
"learning_rate": 4.289805492633248e-08,
|
||
|
|
"loss": 0.3139,
|
||
|
|
"mean_token_accuracy": 0.8873224621638656,
|
||
|
|
"num_tokens": 314501483.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3863525390625,
|
||
|
|
"epoch": 2.924,
|
||
|
|
"grad_norm": 0.6253471573876503,
|
||
|
|
"learning_rate": 3.891238904710881e-08,
|
||
|
|
"loss": 0.3257,
|
||
|
|
"mean_token_accuracy": 0.8830218855291605,
|
||
|
|
"num_tokens": 314920510.0,
|
||
|
|
"step": 731
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.39190673828125,
|
||
|
|
"epoch": 2.928,
|
||
|
|
"grad_norm": 0.6178207837869576,
|
||
|
|
"learning_rate": 3.512065353223348e-08,
|
||
|
|
"loss": 0.3289,
|
||
|
|
"mean_token_accuracy": 0.8820950528606772,
|
||
|
|
"num_tokens": 315346617.0,
|
||
|
|
"step": 732
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3878173828125,
|
||
|
|
"epoch": 2.932,
|
||
|
|
"grad_norm": 0.6444865946057428,
|
||
|
|
"learning_rate": 3.152292220222064e-08,
|
||
|
|
"loss": 0.2875,
|
||
|
|
"mean_token_accuracy": 0.8951279120519757,
|
||
|
|
"num_tokens": 315745477.0,
|
||
|
|
"step": 733
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38458251953125,
|
||
|
|
"epoch": 2.936,
|
||
|
|
"grad_norm": 0.6167602617076726,
|
||
|
|
"learning_rate": 2.8119265100563507e-08,
|
||
|
|
"loss": 0.3181,
|
||
|
|
"mean_token_accuracy": 0.8845036048442125,
|
||
|
|
"num_tokens": 316191594.0,
|
||
|
|
"step": 734
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.385040283203125,
|
||
|
|
"epoch": 2.94,
|
||
|
|
"grad_norm": 0.6361905890035172,
|
||
|
|
"learning_rate": 2.4909748492362162e-08,
|
||
|
|
"loss": 0.3164,
|
||
|
|
"mean_token_accuracy": 0.8861745931208134,
|
||
|
|
"num_tokens": 316614697.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.380035400390625,
|
||
|
|
"epoch": 2.944,
|
||
|
|
"grad_norm": 0.6149023257396274,
|
||
|
|
"learning_rate": 2.1894434863033443e-08,
|
||
|
|
"loss": 0.315,
|
||
|
|
"mean_token_accuracy": 0.8862256295979023,
|
||
|
|
"num_tokens": 317038972.0,
|
||
|
|
"step": 736
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.387481689453125,
|
||
|
|
"epoch": 2.948,
|
||
|
|
"grad_norm": 0.5999447748620422,
|
||
|
|
"learning_rate": 1.9073382917097482e-08,
|
||
|
|
"loss": 0.3137,
|
||
|
|
"mean_token_accuracy": 0.8869608389213681,
|
||
|
|
"num_tokens": 317474451.0,
|
||
|
|
"step": 737
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.384002685546875,
|
||
|
|
"epoch": 2.952,
|
||
|
|
"grad_norm": 0.593785270936263,
|
||
|
|
"learning_rate": 1.644664757703529e-08,
|
||
|
|
"loss": 0.3112,
|
||
|
|
"mean_token_accuracy": 0.8884929670020938,
|
||
|
|
"num_tokens": 317905851.0,
|
||
|
|
"step": 738
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.376739501953125,
|
||
|
|
"epoch": 2.956,
|
||
|
|
"grad_norm": 0.6116455145662006,
|
||
|
|
"learning_rate": 1.4014279982216272e-08,
|
||
|
|
"loss": 0.3038,
|
||
|
|
"mean_token_accuracy": 0.8896695990115404,
|
||
|
|
"num_tokens": 318346948.0,
|
||
|
|
"step": 739
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383392333984375,
|
||
|
|
"epoch": 2.96,
|
||
|
|
"grad_norm": 0.5751583308574376,
|
||
|
|
"learning_rate": 1.1776327487903472e-08,
|
||
|
|
"loss": 0.3211,
|
||
|
|
"mean_token_accuracy": 0.8841962143778801,
|
||
|
|
"num_tokens": 318789623.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38177490234375,
|
||
|
|
"epoch": 2.964,
|
||
|
|
"grad_norm": 0.6123503036221056,
|
||
|
|
"learning_rate": 9.732833664334306e-09,
|
||
|
|
"loss": 0.3266,
|
||
|
|
"mean_token_accuracy": 0.8838892253115773,
|
||
|
|
"num_tokens": 319218312.0,
|
||
|
|
"step": 741
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3828125,
|
||
|
|
"epoch": 2.968,
|
||
|
|
"grad_norm": 0.6011614060211472,
|
||
|
|
"learning_rate": 7.883838295869028e-09,
|
||
|
|
"loss": 0.319,
|
||
|
|
"mean_token_accuracy": 0.8867388982325792,
|
||
|
|
"num_tokens": 319649976.0,
|
||
|
|
"step": 742
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383880615234375,
|
||
|
|
"epoch": 2.972,
|
||
|
|
"grad_norm": 0.6377154388987775,
|
||
|
|
"learning_rate": 6.229377380218005e-09,
|
||
|
|
"loss": 0.2998,
|
||
|
|
"mean_token_accuracy": 0.8929746048524976,
|
||
|
|
"num_tokens": 320066123.0,
|
||
|
|
"step": 743
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.3846435546875,
|
||
|
|
"epoch": 2.976,
|
||
|
|
"grad_norm": 0.621118116680167,
|
||
|
|
"learning_rate": 4.76948312774006e-09,
|
||
|
|
"loss": 0.3057,
|
||
|
|
"mean_token_accuracy": 0.8881496572867036,
|
||
|
|
"num_tokens": 320479540.0,
|
||
|
|
"step": 744
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.385955810546875,
|
||
|
|
"epoch": 2.98,
|
||
|
|
"grad_norm": 0.5927217632130223,
|
||
|
|
"learning_rate": 3.5041839608151994e-09,
|
||
|
|
"loss": 0.3019,
|
||
|
|
"mean_token_accuracy": 0.8917762441560626,
|
||
|
|
"num_tokens": 320914512.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383087158203125,
|
||
|
|
"epoch": 2.984,
|
||
|
|
"grad_norm": 0.5969902301926779,
|
||
|
|
"learning_rate": 2.433504513293938e-09,
|
||
|
|
"loss": 0.3241,
|
||
|
|
"mean_token_accuracy": 0.8819628749042749,
|
||
|
|
"num_tokens": 321352759.0,
|
||
|
|
"step": 746
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.389923095703125,
|
||
|
|
"epoch": 2.988,
|
||
|
|
"grad_norm": 0.6389886378385963,
|
||
|
|
"learning_rate": 1.5574656300143542e-09,
|
||
|
|
"loss": 0.3138,
|
||
|
|
"mean_token_accuracy": 0.8871579300612211,
|
||
|
|
"num_tokens": 321766982.0,
|
||
|
|
"step": 747
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.383209228515625,
|
||
|
|
"epoch": 2.992,
|
||
|
|
"grad_norm": 0.6208962699449172,
|
||
|
|
"learning_rate": 8.760843663946361e-10,
|
||
|
|
"loss": 0.3013,
|
||
|
|
"mean_token_accuracy": 0.8893428910523653,
|
||
|
|
"num_tokens": 322194732.0,
|
||
|
|
"step": 748
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.38568115234375,
|
||
|
|
"epoch": 2.996,
|
||
|
|
"grad_norm": 0.6730895773286322,
|
||
|
|
"learning_rate": 3.893739881088987e-10,
|
||
|
|
"loss": 0.3185,
|
||
|
|
"mean_token_accuracy": 0.8868034956976771,
|
||
|
|
"num_tokens": 322612384.0,
|
||
|
|
"step": 749
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.388336181640625,
|
||
|
|
"epoch": 3.0,
|
||
|
|
"grad_norm": 0.6215856546026891,
|
||
|
|
"learning_rate": 9.734397081961888e-11,
|
||
|
|
"loss": 0.3056,
|
||
|
|
"mean_token_accuracy": 0.8899814244359732,
|
||
|
|
"num_tokens": 323026997.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.0,
|
||
|
|
"step": 750,
|
||
|
|
"total_flos": 597372590817280.0,
|
||
|
|
"train_loss": 0.4411480824549993,
|
||
|
|
"train_runtime": 57703.0115,
|
||
|
|
"train_samples_per_second": 1.275,
|
||
|
|
"train_steps_per_second": 0.013
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 1,
|
||
|
|
"max_steps": 750,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 3,
|
||
|
|
"save_steps": 63,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 597372590817280.0,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|