f2fcd3b4ef
Model: fpadovani/tur-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.299895036737142,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 8.115966701507569,
|
|
"epoch": 0.00049982506122857,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.9779,
|
|
"mean_token_accuracy": 0.09388983175158501,
|
|
"num_tokens": 9036.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 8.105617094039918,
|
|
"epoch": 0.00099965012245714,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 8.1027,
|
|
"mean_token_accuracy": 0.08293505646288395,
|
|
"num_tokens": 19391.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 8.137477827072143,
|
|
"epoch": 0.00149947518368571,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.9326,
|
|
"mean_token_accuracy": 0.08243411704897881,
|
|
"num_tokens": 27896.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 8.191983127593994,
|
|
"epoch": 0.00199930024491428,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.9817,
|
|
"mean_token_accuracy": 0.08287211582064628,
|
|
"num_tokens": 37280.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 8.175366497039795,
|
|
"epoch": 0.00249912530614285,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.8896,
|
|
"mean_token_accuracy": 0.0876060277223587,
|
|
"num_tokens": 46010.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 8.177831649780273,
|
|
"epoch": 0.00299895036737142,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.9504,
|
|
"mean_token_accuracy": 0.08859384059906006,
|
|
"num_tokens": 55972.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 8.151965236663818,
|
|
"epoch": 0.00349877542859999,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.9227,
|
|
"mean_token_accuracy": 0.08379799723625184,
|
|
"num_tokens": 66142.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 8.180653858184815,
|
|
"epoch": 0.00399860048982856,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.8994,
|
|
"mean_token_accuracy": 0.08740837424993515,
|
|
"num_tokens": 74978.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 8.107624816894532,
|
|
"epoch": 0.00449842555105713,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.9414,
|
|
"mean_token_accuracy": 0.09354466870427132,
|
|
"num_tokens": 84153.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 8.170318412780762,
|
|
"epoch": 0.0049982506122857,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.9516,
|
|
"mean_token_accuracy": 0.08247044086456298,
|
|
"num_tokens": 94463.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 8.15045108795166,
|
|
"epoch": 0.00549807567351427,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.8657,
|
|
"mean_token_accuracy": 0.08542923405766487,
|
|
"num_tokens": 104182.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 8.115217018127442,
|
|
"epoch": 0.00599790073474284,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.8856,
|
|
"mean_token_accuracy": 0.09453774318099022,
|
|
"num_tokens": 114058.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 8.119699668884277,
|
|
"epoch": 0.00649772579597141,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.9511,
|
|
"mean_token_accuracy": 0.08501083850860595,
|
|
"num_tokens": 124154.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 8.12986068725586,
|
|
"epoch": 0.00699755085719998,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.8663,
|
|
"mean_token_accuracy": 0.09313991740345955,
|
|
"num_tokens": 132840.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 8.146929073333741,
|
|
"epoch": 0.00749737591842855,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.9197,
|
|
"mean_token_accuracy": 0.08960949406027793,
|
|
"num_tokens": 143070.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 8.190567016601562,
|
|
"epoch": 0.00799720097965712,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.9273,
|
|
"mean_token_accuracy": 0.09039379954338074,
|
|
"num_tokens": 153319.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 8.190423202514648,
|
|
"epoch": 0.00849702604088569,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.9848,
|
|
"mean_token_accuracy": 0.08413397669792175,
|
|
"num_tokens": 163152.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 8.127420330047608,
|
|
"epoch": 0.00899685110211426,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.8803,
|
|
"mean_token_accuracy": 0.09164257049560547,
|
|
"num_tokens": 173321.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 8.158605098724365,
|
|
"epoch": 0.00949667616334283,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.9,
|
|
"mean_token_accuracy": 0.0946331799030304,
|
|
"num_tokens": 182827.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 8.080010318756104,
|
|
"epoch": 0.0099965012245714,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.9007,
|
|
"mean_token_accuracy": 0.08509955257177353,
|
|
"num_tokens": 191776.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 8.090544700622559,
|
|
"epoch": 0.01049632628579997,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.8874,
|
|
"mean_token_accuracy": 0.0908079981803894,
|
|
"num_tokens": 201891.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 8.260288429260253,
|
|
"epoch": 0.01099615134702854,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.9196,
|
|
"mean_token_accuracy": 0.09156425222754479,
|
|
"num_tokens": 210385.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 8.154400157928468,
|
|
"epoch": 0.01149597640825711,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.8798,
|
|
"mean_token_accuracy": 0.09079133942723275,
|
|
"num_tokens": 220098.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 8.051148319244385,
|
|
"epoch": 0.01199580146948568,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.9117,
|
|
"mean_token_accuracy": 0.09130131006240845,
|
|
"num_tokens": 230703.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 8.107196235656739,
|
|
"epoch": 0.01249562653071425,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.8365,
|
|
"mean_token_accuracy": 0.09351907223463059,
|
|
"num_tokens": 239545.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 8.116232061386109,
|
|
"epoch": 0.01299545159194282,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.8594,
|
|
"mean_token_accuracy": 0.08991236239671707,
|
|
"num_tokens": 249726.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 8.180912399291993,
|
|
"epoch": 0.01349527665317139,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.0195,
|
|
"mean_token_accuracy": 0.08512845635414124,
|
|
"num_tokens": 259491.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 8.232371520996093,
|
|
"epoch": 0.01399510171439996,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.9204,
|
|
"mean_token_accuracy": 0.08833294585347176,
|
|
"num_tokens": 268239.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.114497804641724,
|
|
"epoch": 0.01449492677562853,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.8927,
|
|
"mean_token_accuracy": 0.08900318369269371,
|
|
"num_tokens": 276767.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.102681970596313,
|
|
"epoch": 0.0149947518368571,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.8269,
|
|
"mean_token_accuracy": 0.09594093039631843,
|
|
"num_tokens": 286072.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.218955421447754,
|
|
"epoch": 0.01549457689808567,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.8935,
|
|
"mean_token_accuracy": 0.08453865349292755,
|
|
"num_tokens": 295178.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.177178192138673,
|
|
"epoch": 0.01599440195931424,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9645,
|
|
"mean_token_accuracy": 0.08729357868432999,
|
|
"num_tokens": 305537.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.17558240890503,
|
|
"epoch": 0.01649422702054281,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8578,
|
|
"mean_token_accuracy": 0.09048740342259406,
|
|
"num_tokens": 315316.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.087751197814942,
|
|
"epoch": 0.01699405208177138,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.8939,
|
|
"mean_token_accuracy": 0.09201501980423928,
|
|
"num_tokens": 325089.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.224938583374023,
|
|
"epoch": 0.01749387714299995,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.8357,
|
|
"mean_token_accuracy": 0.09008259326219559,
|
|
"num_tokens": 334009.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.072714281082153,
|
|
"epoch": 0.01799370220422852,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.8322,
|
|
"mean_token_accuracy": 0.09141119942069054,
|
|
"num_tokens": 342535.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.01605257987976,
|
|
"epoch": 0.01849352726545709,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.8298,
|
|
"mean_token_accuracy": 0.09161713123321533,
|
|
"num_tokens": 352324.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.16107406616211,
|
|
"epoch": 0.01899335232668566,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.8893,
|
|
"mean_token_accuracy": 0.08870044574141503,
|
|
"num_tokens": 362824.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.062242889404297,
|
|
"epoch": 0.01949317738791423,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.8395,
|
|
"mean_token_accuracy": 0.08829269260168075,
|
|
"num_tokens": 373056.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.146231651306152,
|
|
"epoch": 0.0199930024491428,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.8091,
|
|
"mean_token_accuracy": 0.0935797117650509,
|
|
"num_tokens": 382448.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.083828449249268,
|
|
"epoch": 0.02049282751037137,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.894,
|
|
"mean_token_accuracy": 0.09289678484201432,
|
|
"num_tokens": 393640.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.234550094604492,
|
|
"epoch": 0.02099265257159994,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.9116,
|
|
"mean_token_accuracy": 0.08593777976930142,
|
|
"num_tokens": 403129.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.09738302230835,
|
|
"epoch": 0.02149247763282851,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.8569,
|
|
"mean_token_accuracy": 0.09456023722887039,
|
|
"num_tokens": 412673.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.173221969604493,
|
|
"epoch": 0.02199230269405708,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.8759,
|
|
"mean_token_accuracy": 0.09021985307335853,
|
|
"num_tokens": 422960.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.105310249328614,
|
|
"epoch": 0.02249212775528565,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.8843,
|
|
"mean_token_accuracy": 0.0898541733622551,
|
|
"num_tokens": 433248.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.135746097564697,
|
|
"epoch": 0.02299195281651422,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.8131,
|
|
"mean_token_accuracy": 0.09401410818099976,
|
|
"num_tokens": 441738.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.084957170486451,
|
|
"epoch": 0.02349177787774279,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.9135,
|
|
"mean_token_accuracy": 0.09210107401013375,
|
|
"num_tokens": 451894.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.101123428344726,
|
|
"epoch": 0.02399160293897136,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.8755,
|
|
"mean_token_accuracy": 0.09426127821207046,
|
|
"num_tokens": 462829.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.216189861297607,
|
|
"epoch": 0.02449142800019993,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.8754,
|
|
"mean_token_accuracy": 0.08819158300757408,
|
|
"num_tokens": 472034.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.028231763839722,
|
|
"epoch": 0.0249912530614285,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.9268,
|
|
"mean_token_accuracy": 0.08805325403809547,
|
|
"num_tokens": 481963.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.267205619812012,
|
|
"epoch": 0.02549107812265707,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.8241,
|
|
"mean_token_accuracy": 0.09464174434542656,
|
|
"num_tokens": 491562.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.98403491973877,
|
|
"epoch": 0.02599090318388564,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.7673,
|
|
"mean_token_accuracy": 0.10128638967871666,
|
|
"num_tokens": 500884.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.152617645263671,
|
|
"epoch": 0.026490728245114212,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.8325,
|
|
"mean_token_accuracy": 0.08933599889278412,
|
|
"num_tokens": 510287.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.9761005401611325,
|
|
"epoch": 0.02699055330634278,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.7612,
|
|
"mean_token_accuracy": 0.09821977689862252,
|
|
"num_tokens": 519633.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.178555679321288,
|
|
"epoch": 0.02749037836757135,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.8645,
|
|
"mean_token_accuracy": 0.08926928378641605,
|
|
"num_tokens": 528999.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.06614933013916,
|
|
"epoch": 0.02799020342879992,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.8455,
|
|
"mean_token_accuracy": 0.09183734282851219,
|
|
"num_tokens": 538403.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.094897556304932,
|
|
"epoch": 0.02849002849002849,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.8199,
|
|
"mean_token_accuracy": 0.09269031435251236,
|
|
"num_tokens": 547716.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.069192457199097,
|
|
"epoch": 0.02898985355125706,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.8119,
|
|
"mean_token_accuracy": 0.09283587783575058,
|
|
"num_tokens": 557714.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.185009765625,
|
|
"epoch": 0.02948967861248563,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.8673,
|
|
"mean_token_accuracy": 0.09096960946917534,
|
|
"num_tokens": 568591.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.038140535354614,
|
|
"epoch": 0.0299895036737142,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.7626,
|
|
"mean_token_accuracy": 0.09647799134254456,
|
|
"num_tokens": 578435.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.096207904815675,
|
|
"epoch": 0.03048932873494277,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.8044,
|
|
"mean_token_accuracy": 0.09069146290421486,
|
|
"num_tokens": 587461.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.098102331161499,
|
|
"epoch": 0.03098915379617134,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.8719,
|
|
"mean_token_accuracy": 0.08908754512667656,
|
|
"num_tokens": 597004.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.09911379814148,
|
|
"epoch": 0.03148897885739991,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.8298,
|
|
"mean_token_accuracy": 0.09009509831666947,
|
|
"num_tokens": 607831.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.104575824737548,
|
|
"epoch": 0.03198880391862848,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.8515,
|
|
"mean_token_accuracy": 0.09431877583265305,
|
|
"num_tokens": 618008.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.003451538085937,
|
|
"epoch": 0.03248862897985705,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.7285,
|
|
"mean_token_accuracy": 0.09802025258541107,
|
|
"num_tokens": 627970.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.075142240524292,
|
|
"epoch": 0.03298845404108562,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.8052,
|
|
"mean_token_accuracy": 0.09450135603547097,
|
|
"num_tokens": 638059.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.108322143554688,
|
|
"epoch": 0.03348827910231419,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.8892,
|
|
"mean_token_accuracy": 0.08549424782395362,
|
|
"num_tokens": 648169.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.106694269180299,
|
|
"epoch": 0.03398810416354276,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.8806,
|
|
"mean_token_accuracy": 0.08569936826825142,
|
|
"num_tokens": 659351.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.085410118103027,
|
|
"epoch": 0.03448792922477133,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.7017,
|
|
"mean_token_accuracy": 0.09293192699551582,
|
|
"num_tokens": 669602.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.03732442855835,
|
|
"epoch": 0.0349877542859999,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.8203,
|
|
"mean_token_accuracy": 0.09097881987690926,
|
|
"num_tokens": 679497.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.093275213241578,
|
|
"epoch": 0.03548757934722847,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.7341,
|
|
"mean_token_accuracy": 0.09658810496330261,
|
|
"num_tokens": 689020.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.989745807647705,
|
|
"epoch": 0.03598740440845704,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.735,
|
|
"mean_token_accuracy": 0.09265206158161163,
|
|
"num_tokens": 697505.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.095442819595338,
|
|
"epoch": 0.03648722946968561,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.7433,
|
|
"mean_token_accuracy": 0.0910780519247055,
|
|
"num_tokens": 707646.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.930270195007324,
|
|
"epoch": 0.03698705453091418,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.671,
|
|
"mean_token_accuracy": 0.09586982429027557,
|
|
"num_tokens": 717345.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.013105392456055,
|
|
"epoch": 0.03748687959214275,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.7725,
|
|
"mean_token_accuracy": 0.09069561287760734,
|
|
"num_tokens": 727785.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.108489894866944,
|
|
"epoch": 0.03798670465337132,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.7723,
|
|
"mean_token_accuracy": 0.09322713911533356,
|
|
"num_tokens": 737740.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.981899881362915,
|
|
"epoch": 0.03848652971459989,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.7423,
|
|
"mean_token_accuracy": 0.09115721732378006,
|
|
"num_tokens": 747026.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.915007829666138,
|
|
"epoch": 0.03898635477582846,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.7139,
|
|
"mean_token_accuracy": 0.09398729205131531,
|
|
"num_tokens": 756798.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.194568920135499,
|
|
"epoch": 0.03948617983705703,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.7745,
|
|
"mean_token_accuracy": 0.08935758769512177,
|
|
"num_tokens": 765730.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.9383749008178714,
|
|
"epoch": 0.0399860048982856,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.7555,
|
|
"mean_token_accuracy": 0.0994470827281475,
|
|
"num_tokens": 776330.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.0953604221344,
|
|
"epoch": 0.04048582995951417,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.8216,
|
|
"mean_token_accuracy": 0.08922872990369797,
|
|
"num_tokens": 785840.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.943257141113281,
|
|
"epoch": 0.04098565502074274,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.6662,
|
|
"mean_token_accuracy": 0.0952746793627739,
|
|
"num_tokens": 795126.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.076482248306274,
|
|
"epoch": 0.04148548008197131,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.8195,
|
|
"mean_token_accuracy": 0.08982234001159668,
|
|
"num_tokens": 805766.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.9645508289337155,
|
|
"epoch": 0.04198530514319988,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.7635,
|
|
"mean_token_accuracy": 0.09018896147608757,
|
|
"num_tokens": 815202.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.063913249969483,
|
|
"epoch": 0.04248513020442845,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.7291,
|
|
"mean_token_accuracy": 0.0924349457025528,
|
|
"num_tokens": 825065.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.959709167480469,
|
|
"epoch": 0.04298495526565702,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.7472,
|
|
"mean_token_accuracy": 0.09275062531232833,
|
|
"num_tokens": 834088.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.983949851989746,
|
|
"epoch": 0.04348478032688559,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.7716,
|
|
"mean_token_accuracy": 0.09366122782230377,
|
|
"num_tokens": 843653.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.977571678161621,
|
|
"epoch": 0.04398460538811416,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.6356,
|
|
"mean_token_accuracy": 0.09651589393615723,
|
|
"num_tokens": 853248.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.041356611251832,
|
|
"epoch": 0.04448443044934273,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.8109,
|
|
"mean_token_accuracy": 0.0912716869264841,
|
|
"num_tokens": 863814.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.979821443557739,
|
|
"epoch": 0.0449842555105713,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.7105,
|
|
"mean_token_accuracy": 0.09547068625688553,
|
|
"num_tokens": 874030.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.984935569763183,
|
|
"epoch": 0.04548408057179987,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.6921,
|
|
"mean_token_accuracy": 0.09831217005848884,
|
|
"num_tokens": 883006.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.867571020126343,
|
|
"epoch": 0.04598390563302844,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.6585,
|
|
"mean_token_accuracy": 0.10229817032814026,
|
|
"num_tokens": 892953.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.069862604141235,
|
|
"epoch": 0.04648373069425701,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.7835,
|
|
"mean_token_accuracy": 0.08745714724063873,
|
|
"num_tokens": 904228.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.877147006988525,
|
|
"epoch": 0.04698355575548558,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.6468,
|
|
"mean_token_accuracy": 0.0926812507212162,
|
|
"num_tokens": 915161.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.05656394958496,
|
|
"epoch": 0.04748338081671415,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.7928,
|
|
"mean_token_accuracy": 0.08807904869318009,
|
|
"num_tokens": 925167.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.888152980804444,
|
|
"epoch": 0.04798320587794272,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.666,
|
|
"mean_token_accuracy": 0.09307035207748413,
|
|
"num_tokens": 934742.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.976586484909058,
|
|
"epoch": 0.04848303093917129,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.7478,
|
|
"mean_token_accuracy": 0.0892964169383049,
|
|
"num_tokens": 944549.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.876341152191162,
|
|
"epoch": 0.04898285600039986,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.629,
|
|
"mean_token_accuracy": 0.0999104768037796,
|
|
"num_tokens": 954668.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.100045585632325,
|
|
"epoch": 0.04948268106162843,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.7424,
|
|
"mean_token_accuracy": 0.08877054788172245,
|
|
"num_tokens": 964953.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.773602247238159,
|
|
"epoch": 0.049982506122857,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.6328,
|
|
"mean_token_accuracy": 0.09981884956359863,
|
|
"num_tokens": 974820.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.927160835266113,
|
|
"epoch": 0.05048233118408557,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.6404,
|
|
"mean_token_accuracy": 0.09584514498710632,
|
|
"num_tokens": 984888.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.802907085418701,
|
|
"epoch": 0.05098215624531414,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.6596,
|
|
"mean_token_accuracy": 0.0964170329272747,
|
|
"num_tokens": 993731.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.990255212783813,
|
|
"epoch": 0.05148198130654271,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.5766,
|
|
"mean_token_accuracy": 0.09960651695728302,
|
|
"num_tokens": 1003138.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.7881842136383055,
|
|
"epoch": 0.05198180636777128,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.5953,
|
|
"mean_token_accuracy": 0.09512121453881264,
|
|
"num_tokens": 1012058.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.89219651222229,
|
|
"epoch": 0.05248163142899985,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.614,
|
|
"mean_token_accuracy": 0.10023076310753823,
|
|
"num_tokens": 1020804.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.951163721084595,
|
|
"epoch": 0.052981456490228424,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.6299,
|
|
"mean_token_accuracy": 0.09837900400161743,
|
|
"num_tokens": 1030432.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.835769939422607,
|
|
"epoch": 0.05348128155145699,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.5993,
|
|
"mean_token_accuracy": 0.09920521229505538,
|
|
"num_tokens": 1039336.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.788568496704102,
|
|
"epoch": 0.05398110661268556,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.5576,
|
|
"mean_token_accuracy": 0.10085468515753745,
|
|
"num_tokens": 1049314.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.914288330078125,
|
|
"epoch": 0.05448093167391413,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.6261,
|
|
"mean_token_accuracy": 0.09385359957814217,
|
|
"num_tokens": 1059248.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.7171854972839355,
|
|
"epoch": 0.0549807567351427,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.5969,
|
|
"mean_token_accuracy": 0.09892648234963416,
|
|
"num_tokens": 1069307.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.915244913101196,
|
|
"epoch": 0.05548058179637127,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.5987,
|
|
"mean_token_accuracy": 0.10670549720525742,
|
|
"num_tokens": 1079603.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.749522876739502,
|
|
"epoch": 0.05598040685759984,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.5703,
|
|
"mean_token_accuracy": 0.09797492027282714,
|
|
"num_tokens": 1089386.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.899583625793457,
|
|
"epoch": 0.05648023191882841,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.6497,
|
|
"mean_token_accuracy": 0.10379090011119843,
|
|
"num_tokens": 1099501.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.773384618759155,
|
|
"epoch": 0.05698005698005698,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.5484,
|
|
"mean_token_accuracy": 0.09730408489704132,
|
|
"num_tokens": 1108942.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.850360488891601,
|
|
"epoch": 0.05747988204128555,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.6693,
|
|
"mean_token_accuracy": 0.08937681168317795,
|
|
"num_tokens": 1119484.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.852486276626587,
|
|
"epoch": 0.05797970710251412,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.6211,
|
|
"mean_token_accuracy": 0.0964928537607193,
|
|
"num_tokens": 1130426.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.850640439987183,
|
|
"epoch": 0.05847953216374269,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.5938,
|
|
"mean_token_accuracy": 0.09419768303632736,
|
|
"num_tokens": 1140917.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.806917428970337,
|
|
"epoch": 0.05897935722497126,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.5431,
|
|
"mean_token_accuracy": 0.09883978441357613,
|
|
"num_tokens": 1149863.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.7598425388336185,
|
|
"epoch": 0.05947918228619983,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.5827,
|
|
"mean_token_accuracy": 0.09910288006067276,
|
|
"num_tokens": 1158915.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.7976579666137695,
|
|
"epoch": 0.0599790073474284,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.5754,
|
|
"mean_token_accuracy": 0.09979746043682099,
|
|
"num_tokens": 1167886.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.82974419593811,
|
|
"epoch": 0.06047883240865697,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.6081,
|
|
"mean_token_accuracy": 0.09990579262375832,
|
|
"num_tokens": 1177878.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.870800113677978,
|
|
"epoch": 0.06097865746988554,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.6324,
|
|
"mean_token_accuracy": 0.0978995405137539,
|
|
"num_tokens": 1189511.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.803325939178467,
|
|
"epoch": 0.06147848253111411,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.6302,
|
|
"mean_token_accuracy": 0.09554598703980446,
|
|
"num_tokens": 1199350.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.773017311096192,
|
|
"epoch": 0.06197830759234268,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.5891,
|
|
"mean_token_accuracy": 0.09778468236327172,
|
|
"num_tokens": 1209036.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.699917221069336,
|
|
"epoch": 0.06247813265357125,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.5951,
|
|
"mean_token_accuracy": 0.09537834152579308,
|
|
"num_tokens": 1218841.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.926633691787719,
|
|
"epoch": 0.06297795771479982,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.6178,
|
|
"mean_token_accuracy": 0.09458025097846985,
|
|
"num_tokens": 1229700.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.723057842254638,
|
|
"epoch": 0.06347778277602839,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.5944,
|
|
"mean_token_accuracy": 0.09242647364735604,
|
|
"num_tokens": 1239604.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.595082759857178,
|
|
"epoch": 0.06397760783725696,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.4804,
|
|
"mean_token_accuracy": 0.10766572058200836,
|
|
"num_tokens": 1249305.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.834075403213501,
|
|
"epoch": 0.06447743289848552,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.6121,
|
|
"mean_token_accuracy": 0.09711179062724114,
|
|
"num_tokens": 1261289.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.696876096725464,
|
|
"epoch": 0.0649772579597141,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.564,
|
|
"mean_token_accuracy": 0.0964186169207096,
|
|
"num_tokens": 1271062.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.794726324081421,
|
|
"epoch": 0.06547708302094267,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.5588,
|
|
"mean_token_accuracy": 0.09274660423398018,
|
|
"num_tokens": 1280259.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.854710912704467,
|
|
"epoch": 0.06597690808217124,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.5464,
|
|
"mean_token_accuracy": 0.10048911944031716,
|
|
"num_tokens": 1289184.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.689560794830323,
|
|
"epoch": 0.06647673314339982,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.5339,
|
|
"mean_token_accuracy": 0.10461926683783532,
|
|
"num_tokens": 1297916.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.747795343399048,
|
|
"epoch": 0.06697655820462838,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.5534,
|
|
"mean_token_accuracy": 0.10210059732198715,
|
|
"num_tokens": 1307786.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.681216049194336,
|
|
"epoch": 0.06747638326585695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.4656,
|
|
"mean_token_accuracy": 0.09771529659628868,
|
|
"num_tokens": 1317528.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.736382722854614,
|
|
"epoch": 0.06797620832708552,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.5177,
|
|
"mean_token_accuracy": 0.09926827922463417,
|
|
"num_tokens": 1326170.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.642406272888183,
|
|
"epoch": 0.0684760333883141,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.5243,
|
|
"mean_token_accuracy": 0.09604377187788486,
|
|
"num_tokens": 1336469.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.716367149353028,
|
|
"epoch": 0.06897585844954265,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.517,
|
|
"mean_token_accuracy": 0.09137366265058518,
|
|
"num_tokens": 1347449.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.62940821647644,
|
|
"epoch": 0.06947568351077123,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.5357,
|
|
"mean_token_accuracy": 0.10426082238554954,
|
|
"num_tokens": 1357849.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.692328882217407,
|
|
"epoch": 0.0699755085719998,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.471,
|
|
"mean_token_accuracy": 0.09552951604127884,
|
|
"num_tokens": 1366784.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.6839916706085205,
|
|
"epoch": 0.07047533363322837,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.4466,
|
|
"mean_token_accuracy": 0.09935205802321434,
|
|
"num_tokens": 1376059.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.5484521865844725,
|
|
"epoch": 0.07097515869445695,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.4194,
|
|
"mean_token_accuracy": 0.10240289196372032,
|
|
"num_tokens": 1385505.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.7426775932312015,
|
|
"epoch": 0.0714749837556855,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.4931,
|
|
"mean_token_accuracy": 0.10483329370617867,
|
|
"num_tokens": 1395200.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.512200260162354,
|
|
"epoch": 0.07197480881691408,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.4294,
|
|
"mean_token_accuracy": 0.10536539554595947,
|
|
"num_tokens": 1404599.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.642330694198608,
|
|
"epoch": 0.07247463387814265,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.5033,
|
|
"mean_token_accuracy": 0.10006041154265403,
|
|
"num_tokens": 1414761.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.612363624572754,
|
|
"epoch": 0.07297445893937123,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.4319,
|
|
"mean_token_accuracy": 0.10430303364992141,
|
|
"num_tokens": 1424296.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.659904146194458,
|
|
"epoch": 0.07347428400059978,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.4992,
|
|
"mean_token_accuracy": 0.10049317553639411,
|
|
"num_tokens": 1433729.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.663594388961792,
|
|
"epoch": 0.07397410906182836,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.57,
|
|
"mean_token_accuracy": 0.09031622260808944,
|
|
"num_tokens": 1444214.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.683882474899292,
|
|
"epoch": 0.07447393412305693,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.5678,
|
|
"mean_token_accuracy": 0.09561188071966172,
|
|
"num_tokens": 1454364.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.629066228866577,
|
|
"epoch": 0.0749737591842855,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.4202,
|
|
"mean_token_accuracy": 0.10247516110539437,
|
|
"num_tokens": 1465018.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.573776149749756,
|
|
"epoch": 0.07547358424551406,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.4268,
|
|
"mean_token_accuracy": 0.10416854470968247,
|
|
"num_tokens": 1474316.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.603347063064575,
|
|
"epoch": 0.07597340930674264,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.4846,
|
|
"mean_token_accuracy": 0.09634485989809036,
|
|
"num_tokens": 1483867.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.588646364212036,
|
|
"epoch": 0.07647323436797121,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.5488,
|
|
"mean_token_accuracy": 0.09254544489085674,
|
|
"num_tokens": 1493760.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.642456197738648,
|
|
"epoch": 0.07697305942919978,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.4797,
|
|
"mean_token_accuracy": 0.10259066373109818,
|
|
"num_tokens": 1503984.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.631467628479004,
|
|
"epoch": 0.07747288449042836,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.5315,
|
|
"mean_token_accuracy": 0.09757167249917983,
|
|
"num_tokens": 1513550.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.658507061004639,
|
|
"epoch": 0.07797270955165692,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.4792,
|
|
"mean_token_accuracy": 0.09825642928481101,
|
|
"num_tokens": 1523543.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.600262832641602,
|
|
"epoch": 0.07847253461288549,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.4436,
|
|
"mean_token_accuracy": 0.09491991028189659,
|
|
"num_tokens": 1533775.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.519190692901612,
|
|
"epoch": 0.07897235967411406,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.4623,
|
|
"mean_token_accuracy": 0.10000543147325516,
|
|
"num_tokens": 1545008.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.6924022197723385,
|
|
"epoch": 0.07947218473534264,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.4861,
|
|
"mean_token_accuracy": 0.09440402016043663,
|
|
"num_tokens": 1554458.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.538026142120361,
|
|
"epoch": 0.0799720097965712,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.465,
|
|
"mean_token_accuracy": 0.09284278675913811,
|
|
"num_tokens": 1565827.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.685927486419677,
|
|
"epoch": 0.08047183485779977,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.5537,
|
|
"mean_token_accuracy": 0.0930624283850193,
|
|
"num_tokens": 1577477.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.504521799087525,
|
|
"epoch": 0.08097165991902834,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.3868,
|
|
"mean_token_accuracy": 0.10175873637199402,
|
|
"num_tokens": 1586622.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.513061571121216,
|
|
"epoch": 0.08147148498025691,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.4031,
|
|
"mean_token_accuracy": 0.10046703219413758,
|
|
"num_tokens": 1596038.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.6118467330932615,
|
|
"epoch": 0.08197131004148547,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.5118,
|
|
"mean_token_accuracy": 0.09201489984989167,
|
|
"num_tokens": 1606419.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.520540618896485,
|
|
"epoch": 0.08247113510271405,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.457,
|
|
"mean_token_accuracy": 0.09784280806779862,
|
|
"num_tokens": 1617178.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.604987335205078,
|
|
"epoch": 0.08297096016394262,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.4982,
|
|
"mean_token_accuracy": 0.09498569741845131,
|
|
"num_tokens": 1628066.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.5044020652771,
|
|
"epoch": 0.08347078522517119,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.4454,
|
|
"mean_token_accuracy": 0.09581194594502448,
|
|
"num_tokens": 1637956.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.500812101364136,
|
|
"epoch": 0.08397061028639977,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.4666,
|
|
"mean_token_accuracy": 0.09536369666457176,
|
|
"num_tokens": 1647388.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.6309302806854244,
|
|
"epoch": 0.08447043534762833,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.4971,
|
|
"mean_token_accuracy": 0.09469880238175392,
|
|
"num_tokens": 1656983.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.519527626037598,
|
|
"epoch": 0.0849702604088569,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.4669,
|
|
"mean_token_accuracy": 0.09942631423473358,
|
|
"num_tokens": 1666956.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.404068660736084,
|
|
"epoch": 0.08547008547008547,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.3124,
|
|
"mean_token_accuracy": 0.10641250684857369,
|
|
"num_tokens": 1675249.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.5542021751403805,
|
|
"epoch": 0.08596991053131404,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.4107,
|
|
"mean_token_accuracy": 0.09953751862049103,
|
|
"num_tokens": 1684142.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.51811375617981,
|
|
"epoch": 0.0864697355925426,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.4541,
|
|
"mean_token_accuracy": 0.09805193170905113,
|
|
"num_tokens": 1693512.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.540082168579102,
|
|
"epoch": 0.08696956065377118,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.4372,
|
|
"mean_token_accuracy": 0.09531431272625923,
|
|
"num_tokens": 1703509.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.518545818328858,
|
|
"epoch": 0.08746938571499975,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.3685,
|
|
"mean_token_accuracy": 0.10407287031412124,
|
|
"num_tokens": 1712158.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.444411420822144,
|
|
"epoch": 0.08796921077622832,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.4137,
|
|
"mean_token_accuracy": 0.10234727710485458,
|
|
"num_tokens": 1721797.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.505835008621216,
|
|
"epoch": 0.0884690358374569,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.4375,
|
|
"mean_token_accuracy": 0.09196901768445968,
|
|
"num_tokens": 1732139.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.492173051834106,
|
|
"epoch": 0.08896886089868546,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.4836,
|
|
"mean_token_accuracy": 0.09574326947331428,
|
|
"num_tokens": 1742419.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.495395612716675,
|
|
"epoch": 0.08946868595991403,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.4579,
|
|
"mean_token_accuracy": 0.09730211272835732,
|
|
"num_tokens": 1752339.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.465468120574951,
|
|
"epoch": 0.0899685110211426,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.3246,
|
|
"mean_token_accuracy": 0.10337135419249535,
|
|
"num_tokens": 1763014.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.376938724517823,
|
|
"epoch": 0.09046833608237118,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.3169,
|
|
"mean_token_accuracy": 0.10913435965776444,
|
|
"num_tokens": 1772977.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.61873426437378,
|
|
"epoch": 0.09096816114359974,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.4175,
|
|
"mean_token_accuracy": 0.10118973776698112,
|
|
"num_tokens": 1782085.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.334328937530517,
|
|
"epoch": 0.09146798620482831,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.4619,
|
|
"mean_token_accuracy": 0.10010594651103019,
|
|
"num_tokens": 1791856.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.482182407379151,
|
|
"epoch": 0.09196781126605688,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.2896,
|
|
"mean_token_accuracy": 0.10650820061564445,
|
|
"num_tokens": 1800670.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.426328849792481,
|
|
"epoch": 0.09246763632728545,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.4508,
|
|
"mean_token_accuracy": 0.10260506570339203,
|
|
"num_tokens": 1811138.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.442462730407715,
|
|
"epoch": 0.09296746138851401,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.3307,
|
|
"mean_token_accuracy": 0.09987644553184509,
|
|
"num_tokens": 1819771.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.374147653579712,
|
|
"epoch": 0.09346728644974259,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.3942,
|
|
"mean_token_accuracy": 0.09991481155157089,
|
|
"num_tokens": 1829075.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.41774353981018,
|
|
"epoch": 0.09396711151097116,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.3552,
|
|
"mean_token_accuracy": 0.10564769506454467,
|
|
"num_tokens": 1837892.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.433983230590821,
|
|
"epoch": 0.09446693657219973,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.4104,
|
|
"mean_token_accuracy": 0.10003899708390236,
|
|
"num_tokens": 1848359.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.449016141891479,
|
|
"epoch": 0.0949667616334283,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.3765,
|
|
"mean_token_accuracy": 0.09999907165765762,
|
|
"num_tokens": 1857665.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.458324146270752,
|
|
"epoch": 0.09546658669465687,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.35,
|
|
"mean_token_accuracy": 0.10186451897025109,
|
|
"num_tokens": 1867313.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.404160976409912,
|
|
"epoch": 0.09596641175588544,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.4371,
|
|
"mean_token_accuracy": 0.0957965947687626,
|
|
"num_tokens": 1877904.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.462620973587036,
|
|
"epoch": 0.09646623681711401,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.3508,
|
|
"mean_token_accuracy": 0.10784625113010407,
|
|
"num_tokens": 1887173.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.463750505447388,
|
|
"epoch": 0.09696606187834259,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.4364,
|
|
"mean_token_accuracy": 0.09779566004872323,
|
|
"num_tokens": 1896326.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.386555910110474,
|
|
"epoch": 0.09746588693957114,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.3174,
|
|
"mean_token_accuracy": 0.09860834032297135,
|
|
"num_tokens": 1905403.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.493797731399536,
|
|
"epoch": 0.09796571200079972,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.4104,
|
|
"mean_token_accuracy": 0.09834235757589341,
|
|
"num_tokens": 1915910.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.351792240142823,
|
|
"epoch": 0.09846553706202829,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.3515,
|
|
"mean_token_accuracy": 0.10310368835926056,
|
|
"num_tokens": 1926538.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.331353616714478,
|
|
"epoch": 0.09896536212325686,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.4155,
|
|
"mean_token_accuracy": 0.09870894104242325,
|
|
"num_tokens": 1936604.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.351730632781982,
|
|
"epoch": 0.09946518718448542,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.2687,
|
|
"mean_token_accuracy": 0.10868923962116242,
|
|
"num_tokens": 1946509.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.449704694747925,
|
|
"epoch": 0.099965012245714,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.4381,
|
|
"mean_token_accuracy": 0.09592320919036865,
|
|
"num_tokens": 1955562.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.3522120952606205,
|
|
"epoch": 0.10046483730694257,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999981884985,
|
|
"loss": 7.2931,
|
|
"mean_token_accuracy": 0.10394947901368141,
|
|
"num_tokens": 1964805.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.453734540939331,
|
|
"epoch": 0.10096466236817114,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999999908292739,
|
|
"loss": 7.3876,
|
|
"mean_token_accuracy": 0.10147590786218644,
|
|
"num_tokens": 1973735.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.296640205383301,
|
|
"epoch": 0.10146448742939972,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999778091072,
|
|
"loss": 7.2858,
|
|
"mean_token_accuracy": 0.09892769753932953,
|
|
"num_tokens": 1983657.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.4748045921325685,
|
|
"epoch": 0.10196431249062828,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999999591279991,
|
|
"loss": 7.3675,
|
|
"mean_token_accuracy": 0.10389427542686462,
|
|
"num_tokens": 1994767.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.266379356384277,
|
|
"epoch": 0.10246413755185685,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049999993478595,
|
|
"loss": 7.3899,
|
|
"mean_token_accuracy": 0.10590666383504868,
|
|
"num_tokens": 2004634.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.3518266677856445,
|
|
"epoch": 0.10296396261308542,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999047829604,
|
|
"loss": 7.2877,
|
|
"mean_token_accuracy": 0.10322983711957931,
|
|
"num_tokens": 2014346.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.398997354507446,
|
|
"epoch": 0.103463787674314,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499999869119031,
|
|
"loss": 7.3821,
|
|
"mean_token_accuracy": 0.10241326168179513,
|
|
"num_tokens": 2024132.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.32396936416626,
|
|
"epoch": 0.10396361273554255,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998277941629,
|
|
"loss": 7.3135,
|
|
"mean_token_accuracy": 0.09869552403688431,
|
|
"num_tokens": 2034230.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.388594722747802,
|
|
"epoch": 0.10446343779677113,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999997808083569,
|
|
"loss": 7.3698,
|
|
"mean_token_accuracy": 0.10165157392621041,
|
|
"num_tokens": 2043936.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.276969957351684,
|
|
"epoch": 0.1049632628579997,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999997281616144,
|
|
"loss": 7.3319,
|
|
"mean_token_accuracy": 0.09708460494875908,
|
|
"num_tokens": 2053386.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.300722360610962,
|
|
"epoch": 0.10546308791922827,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999996698539366,
|
|
"loss": 7.2492,
|
|
"mean_token_accuracy": 0.1117588073015213,
|
|
"num_tokens": 2063604.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.340676641464233,
|
|
"epoch": 0.10596291298045685,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499999605885325,
|
|
"loss": 7.3128,
|
|
"mean_token_accuracy": 0.10286297127604485,
|
|
"num_tokens": 2072795.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.354478883743286,
|
|
"epoch": 0.1064627380416854,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004999995362557813,
|
|
"loss": 7.2888,
|
|
"mean_token_accuracy": 0.1015630230307579,
|
|
"num_tokens": 2082113.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.253059196472168,
|
|
"epoch": 0.10696256310291398,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499999460965307,
|
|
"loss": 7.1843,
|
|
"mean_token_accuracy": 0.11151959002017975,
|
|
"num_tokens": 2090484.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.203897428512573,
|
|
"epoch": 0.10746238816414255,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999993800139043,
|
|
"loss": 7.2397,
|
|
"mean_token_accuracy": 0.10655209198594093,
|
|
"num_tokens": 2100703.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.286228370666504,
|
|
"epoch": 0.10796221322537113,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999992934015752,
|
|
"loss": 7.3485,
|
|
"mean_token_accuracy": 0.09915086925029755,
|
|
"num_tokens": 2110861.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.353559732437134,
|
|
"epoch": 0.10846203828659969,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999992011283215,
|
|
"loss": 7.2853,
|
|
"mean_token_accuracy": 0.10259805619716644,
|
|
"num_tokens": 2121414.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.3230507373809814,
|
|
"epoch": 0.10896186334782826,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999991031941459,
|
|
"loss": 7.2654,
|
|
"mean_token_accuracy": 0.10948954746127129,
|
|
"num_tokens": 2131201.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.256815958023071,
|
|
"epoch": 0.10946168840905683,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999989995990509,
|
|
"loss": 7.2584,
|
|
"mean_token_accuracy": 0.10254568606615067,
|
|
"num_tokens": 2142071.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.249517440795898,
|
|
"epoch": 0.1099615134702854,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999988903430389,
|
|
"loss": 7.3155,
|
|
"mean_token_accuracy": 0.10242817401885987,
|
|
"num_tokens": 2151514.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.30422077178955,
|
|
"epoch": 0.11046133853151396,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999987754261126,
|
|
"loss": 7.2977,
|
|
"mean_token_accuracy": 0.10412856489419937,
|
|
"num_tokens": 2160828.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.329158115386963,
|
|
"epoch": 0.11096116359274254,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999986548482751,
|
|
"loss": 7.3347,
|
|
"mean_token_accuracy": 0.10781540647149086,
|
|
"num_tokens": 2169968.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.330237340927124,
|
|
"epoch": 0.11146098865397111,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999985286095293,
|
|
"loss": 7.2593,
|
|
"mean_token_accuracy": 0.10637600645422936,
|
|
"num_tokens": 2180434.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.239208841323853,
|
|
"epoch": 0.11196081371519968,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999983967098785,
|
|
"loss": 7.1956,
|
|
"mean_token_accuracy": 0.10522906109690666,
|
|
"num_tokens": 2190024.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.288405704498291,
|
|
"epoch": 0.11246063877642826,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999982591493258,
|
|
"loss": 7.2271,
|
|
"mean_token_accuracy": 0.1099842593073845,
|
|
"num_tokens": 2199897.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.168730354309082,
|
|
"epoch": 0.11296046383765682,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999981159278749,
|
|
"loss": 7.2887,
|
|
"mean_token_accuracy": 0.10584141686558723,
|
|
"num_tokens": 2209865.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.373020601272583,
|
|
"epoch": 0.11346028889888539,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004999979670455292,
|
|
"loss": 7.2426,
|
|
"mean_token_accuracy": 0.1077901616692543,
|
|
"num_tokens": 2219960.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.236533546447754,
|
|
"epoch": 0.11396011396011396,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999978125022926,
|
|
"loss": 7.2442,
|
|
"mean_token_accuracy": 0.10784188359975815,
|
|
"num_tokens": 2230699.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.2002357006072994,
|
|
"epoch": 0.11445993902134254,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499997652298169,
|
|
"loss": 7.2507,
|
|
"mean_token_accuracy": 0.10368520766496658,
|
|
"num_tokens": 2239694.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.327735424041748,
|
|
"epoch": 0.1149597640825711,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999974864331624,
|
|
"loss": 7.2772,
|
|
"mean_token_accuracy": 0.10986744239926338,
|
|
"num_tokens": 2250624.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.30306601524353,
|
|
"epoch": 0.11545958914379967,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999973149072768,
|
|
"loss": 7.2842,
|
|
"mean_token_accuracy": 0.10279571041464805,
|
|
"num_tokens": 2260759.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.238110876083374,
|
|
"epoch": 0.11595941420502824,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999971377205167,
|
|
"loss": 7.3117,
|
|
"mean_token_accuracy": 0.10007711425423622,
|
|
"num_tokens": 2271151.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.237846374511719,
|
|
"epoch": 0.11645923926625681,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999969548728864,
|
|
"loss": 7.1965,
|
|
"mean_token_accuracy": 0.11174095422029495,
|
|
"num_tokens": 2280014.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.2414806365966795,
|
|
"epoch": 0.11695906432748537,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999967663643908,
|
|
"loss": 7.1659,
|
|
"mean_token_accuracy": 0.11187820881605148,
|
|
"num_tokens": 2288550.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.226145553588867,
|
|
"epoch": 0.11745888938871395,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999965721950345,
|
|
"loss": 7.2567,
|
|
"mean_token_accuracy": 0.10522151663899422,
|
|
"num_tokens": 2297899.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.251861715316773,
|
|
"epoch": 0.11795871444994252,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999963723648222,
|
|
"loss": 7.2035,
|
|
"mean_token_accuracy": 0.1062523826956749,
|
|
"num_tokens": 2308021.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.288262224197387,
|
|
"epoch": 0.1184585395111711,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000499996166873759,
|
|
"loss": 7.2486,
|
|
"mean_token_accuracy": 0.10318779572844505,
|
|
"num_tokens": 2319607.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.178311777114868,
|
|
"epoch": 0.11895836457239967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999959557218502,
|
|
"loss": 7.2494,
|
|
"mean_token_accuracy": 0.10606426224112511,
|
|
"num_tokens": 2329293.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.335767650604248,
|
|
"epoch": 0.11945818963362823,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999957389091012,
|
|
"loss": 7.2712,
|
|
"mean_token_accuracy": 0.10525668188929557,
|
|
"num_tokens": 2339812.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.135515928268433,
|
|
"epoch": 0.1199580146948568,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999955164355171,
|
|
"loss": 7.2314,
|
|
"mean_token_accuracy": 0.10235729217529296,
|
|
"num_tokens": 2349770.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.282419157028198,
|
|
"epoch": 0.12045783975608537,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004999952883011038,
|
|
"loss": 7.1282,
|
|
"mean_token_accuracy": 0.11181103363633156,
|
|
"num_tokens": 2360355.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.135486125946045,
|
|
"epoch": 0.12095766481731395,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499995054505867,
|
|
"loss": 7.3192,
|
|
"mean_token_accuracy": 0.10360833257436752,
|
|
"num_tokens": 2369444.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.23374752998352,
|
|
"epoch": 0.1214574898785425,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999948150498124,
|
|
"loss": 7.1863,
|
|
"mean_token_accuracy": 0.10711781978607178,
|
|
"num_tokens": 2380172.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.309315729141235,
|
|
"epoch": 0.12195731493977108,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999945699329462,
|
|
"loss": 7.3493,
|
|
"mean_token_accuracy": 0.1012509100139141,
|
|
"num_tokens": 2391520.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.295082521438599,
|
|
"epoch": 0.12245714000099965,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999943191552745,
|
|
"loss": 7.2548,
|
|
"mean_token_accuracy": 0.1027175396680832,
|
|
"num_tokens": 2400977.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.329327964782715,
|
|
"epoch": 0.12295696506222822,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999940627168037,
|
|
"loss": 7.2506,
|
|
"mean_token_accuracy": 0.10020245537161827,
|
|
"num_tokens": 2410220.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.180943441390991,
|
|
"epoch": 0.12345679012345678,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00049999380061754,
|
|
"loss": 7.2642,
|
|
"mean_token_accuracy": 0.10909186080098152,
|
|
"num_tokens": 2420000.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.274267911911011,
|
|
"epoch": 0.12395661518468536,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999935328574903,
|
|
"loss": 7.2054,
|
|
"mean_token_accuracy": 0.10308079868555069,
|
|
"num_tokens": 2429236.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.123314380645752,
|
|
"epoch": 0.12445644024591393,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999932594366613,
|
|
"loss": 7.1065,
|
|
"mean_token_accuracy": 0.1079021766781807,
|
|
"num_tokens": 2438830.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.20734977722168,
|
|
"epoch": 0.1249562653071425,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999929803550597,
|
|
"loss": 7.1211,
|
|
"mean_token_accuracy": 0.11151803135871888,
|
|
"num_tokens": 2448218.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.212431287765503,
|
|
"epoch": 0.12545609036837108,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999926956126927,
|
|
"loss": 7.1895,
|
|
"mean_token_accuracy": 0.1051447942852974,
|
|
"num_tokens": 2458016.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.124825382232666,
|
|
"epoch": 0.12595591542959964,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999924052095672,
|
|
"loss": 7.095,
|
|
"mean_token_accuracy": 0.10699434652924537,
|
|
"num_tokens": 2467973.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.153971910476685,
|
|
"epoch": 0.12645574049082822,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999921091456907,
|
|
"loss": 7.2014,
|
|
"mean_token_accuracy": 0.10560873597860336,
|
|
"num_tokens": 2477811.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.186617374420166,
|
|
"epoch": 0.12695556555205678,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999918074210707,
|
|
"loss": 7.1761,
|
|
"mean_token_accuracy": 0.10755071565508842,
|
|
"num_tokens": 2487477.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.109448385238648,
|
|
"epoch": 0.12745539061328534,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999915000357147,
|
|
"loss": 7.0675,
|
|
"mean_token_accuracy": 0.11184290945529937,
|
|
"num_tokens": 2497127.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.090885353088379,
|
|
"epoch": 0.12795521567451393,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999911869896305,
|
|
"loss": 7.1605,
|
|
"mean_token_accuracy": 0.10718183293938637,
|
|
"num_tokens": 2506340.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.297980165481567,
|
|
"epoch": 0.1284550407357425,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999908682828258,
|
|
"loss": 7.1951,
|
|
"mean_token_accuracy": 0.10084473490715026,
|
|
"num_tokens": 2515210.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.0772905349731445,
|
|
"epoch": 0.12895486579697105,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999905439153089,
|
|
"loss": 7.0952,
|
|
"mean_token_accuracy": 0.1110685035586357,
|
|
"num_tokens": 2524653.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.150044536590576,
|
|
"epoch": 0.12945469085819963,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999902138870878,
|
|
"loss": 7.1397,
|
|
"mean_token_accuracy": 0.10771988704800606,
|
|
"num_tokens": 2534243.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.236660671234131,
|
|
"epoch": 0.1299545159194282,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999898781981707,
|
|
"loss": 7.1998,
|
|
"mean_token_accuracy": 0.10407418459653854,
|
|
"num_tokens": 2543758.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.205931663513184,
|
|
"epoch": 0.13045434098065678,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999895368485662,
|
|
"loss": 7.2281,
|
|
"mean_token_accuracy": 0.1009873628616333,
|
|
"num_tokens": 2553537.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.116842460632324,
|
|
"epoch": 0.13095416604188534,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499989189838283,
|
|
"loss": 7.145,
|
|
"mean_token_accuracy": 0.10926665514707565,
|
|
"num_tokens": 2562812.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.184953212738037,
|
|
"epoch": 0.1314539911031139,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999888371673295,
|
|
"loss": 7.1309,
|
|
"mean_token_accuracy": 0.11213063448667526,
|
|
"num_tokens": 2571728.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.177727079391479,
|
|
"epoch": 0.13195381616434249,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999884788357147,
|
|
"loss": 7.2195,
|
|
"mean_token_accuracy": 0.10633473843336105,
|
|
"num_tokens": 2582309.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.1854188442230225,
|
|
"epoch": 0.13245364122557104,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999881148434478,
|
|
"loss": 7.128,
|
|
"mean_token_accuracy": 0.11164407134056091,
|
|
"num_tokens": 2591810.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.0932341575622555,
|
|
"epoch": 0.13295346628679963,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999877451905378,
|
|
"loss": 7.1083,
|
|
"mean_token_accuracy": 0.11393467858433723,
|
|
"num_tokens": 2602028.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.095207071304321,
|
|
"epoch": 0.1334532913480282,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999873698769941,
|
|
"loss": 7.108,
|
|
"mean_token_accuracy": 0.11159966364502907,
|
|
"num_tokens": 2610900.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.107607173919678,
|
|
"epoch": 0.13395311640925675,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499986988902826,
|
|
"loss": 7.1132,
|
|
"mean_token_accuracy": 0.11127648279070854,
|
|
"num_tokens": 2620918.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.139119338989258,
|
|
"epoch": 0.13445294147048534,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999866022680431,
|
|
"loss": 7.1284,
|
|
"mean_token_accuracy": 0.11192728728055953,
|
|
"num_tokens": 2631383.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.102079010009765,
|
|
"epoch": 0.1349527665317139,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999862099726552,
|
|
"loss": 7.0999,
|
|
"mean_token_accuracy": 0.11033402979373932,
|
|
"num_tokens": 2640824.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.178639459609985,
|
|
"epoch": 0.13545259159294248,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999858120166721,
|
|
"loss": 7.0784,
|
|
"mean_token_accuracy": 0.1097441516816616,
|
|
"num_tokens": 2649884.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.068162250518799,
|
|
"epoch": 0.13595241665417104,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999854084001039,
|
|
"loss": 7.1528,
|
|
"mean_token_accuracy": 0.11337249279022217,
|
|
"num_tokens": 2659464.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.113283252716064,
|
|
"epoch": 0.1364522417153996,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999849991229608,
|
|
"loss": 7.1487,
|
|
"mean_token_accuracy": 0.10855353698134422,
|
|
"num_tokens": 2668271.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.187230062484741,
|
|
"epoch": 0.1369520667766282,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499984584185253,
|
|
"loss": 7.2098,
|
|
"mean_token_accuracy": 0.10614682957530022,
|
|
"num_tokens": 2678353.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.149409389495849,
|
|
"epoch": 0.13745189183785675,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999841635869909,
|
|
"loss": 7.1448,
|
|
"mean_token_accuracy": 0.10726541206240654,
|
|
"num_tokens": 2688082.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.158280563354492,
|
|
"epoch": 0.1379517168990853,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999837373281852,
|
|
"loss": 7.1357,
|
|
"mean_token_accuracy": 0.1082352265715599,
|
|
"num_tokens": 2697780.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.153148174285889,
|
|
"epoch": 0.1384515419603139,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999833054088465,
|
|
"loss": 7.1464,
|
|
"mean_token_accuracy": 0.11163995936512947,
|
|
"num_tokens": 2707851.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.146587085723877,
|
|
"epoch": 0.13895136702154245,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999828678289858,
|
|
"loss": 7.2008,
|
|
"mean_token_accuracy": 0.10463528037071228,
|
|
"num_tokens": 2718041.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.154413461685181,
|
|
"epoch": 0.13945119208277104,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499982424588614,
|
|
"loss": 7.0933,
|
|
"mean_token_accuracy": 0.1157912366092205,
|
|
"num_tokens": 2726663.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.1343855381011965,
|
|
"epoch": 0.1399510171439996,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999819756877422,
|
|
"loss": 7.0596,
|
|
"mean_token_accuracy": 0.11434894353151322,
|
|
"num_tokens": 2734926.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.131910037994385,
|
|
"epoch": 0.14045084220522816,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999815211263819,
|
|
"loss": 7.1364,
|
|
"mean_token_accuracy": 0.10998270213603974,
|
|
"num_tokens": 2744984.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.1278736114501955,
|
|
"epoch": 0.14095066726645675,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999810609045444,
|
|
"loss": 7.0561,
|
|
"mean_token_accuracy": 0.11019435450434685,
|
|
"num_tokens": 2754293.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.038761758804322,
|
|
"epoch": 0.1414504923276853,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999805950222412,
|
|
"loss": 7.1112,
|
|
"mean_token_accuracy": 0.11249493733048439,
|
|
"num_tokens": 2764602.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.136958646774292,
|
|
"epoch": 0.1419503173889139,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999801234794843,
|
|
"loss": 7.1579,
|
|
"mean_token_accuracy": 0.10929414480924607,
|
|
"num_tokens": 2775171.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.107983350753784,
|
|
"epoch": 0.14245014245014245,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999796462762853,
|
|
"loss": 7.052,
|
|
"mean_token_accuracy": 0.1148157998919487,
|
|
"num_tokens": 2784739.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.160243511199951,
|
|
"epoch": 0.142949967511371,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004999791634126562,
|
|
"loss": 7.1657,
|
|
"mean_token_accuracy": 0.11298665180802345,
|
|
"num_tokens": 2794549.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.166717195510865,
|
|
"epoch": 0.1434497925725996,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999786748886094,
|
|
"loss": 7.1116,
|
|
"mean_token_accuracy": 0.11435734257102012,
|
|
"num_tokens": 2803235.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.079634094238282,
|
|
"epoch": 0.14394961763382816,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999781807041569,
|
|
"loss": 7.0513,
|
|
"mean_token_accuracy": 0.10983316227793694,
|
|
"num_tokens": 2812367.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.01149172782898,
|
|
"epoch": 0.14444944269505672,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999776808593113,
|
|
"loss": 7.0788,
|
|
"mean_token_accuracy": 0.115450157225132,
|
|
"num_tokens": 2822173.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.19095778465271,
|
|
"epoch": 0.1449492677562853,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999771753540852,
|
|
"loss": 7.1296,
|
|
"mean_token_accuracy": 0.10804187655448913,
|
|
"num_tokens": 2831498.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.151987075805664,
|
|
"epoch": 0.14544909281751386,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999766641884912,
|
|
"loss": 7.2708,
|
|
"mean_token_accuracy": 0.10761458948254585,
|
|
"num_tokens": 2840883.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.108257818222046,
|
|
"epoch": 0.14594891787874245,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999761473625422,
|
|
"loss": 7.0424,
|
|
"mean_token_accuracy": 0.11248427405953407,
|
|
"num_tokens": 2850694.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.983803033828735,
|
|
"epoch": 0.146448742939971,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999756248762513,
|
|
"loss": 7.0643,
|
|
"mean_token_accuracy": 0.11776667833328247,
|
|
"num_tokens": 2861100.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.087214612960816,
|
|
"epoch": 0.14694856800119957,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999750967296315,
|
|
"loss": 7.0179,
|
|
"mean_token_accuracy": 0.11294868513941765,
|
|
"num_tokens": 2871054.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.02065601348877,
|
|
"epoch": 0.14744839306242816,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999745629226962,
|
|
"loss": 6.9776,
|
|
"mean_token_accuracy": 0.11572617068886756,
|
|
"num_tokens": 2880244.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.022220134735107,
|
|
"epoch": 0.14794821812365672,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999740234554589,
|
|
"loss": 7.0832,
|
|
"mean_token_accuracy": 0.10742958262562752,
|
|
"num_tokens": 2891441.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.101360940933228,
|
|
"epoch": 0.1484480431848853,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999734783279327,
|
|
"loss": 7.0758,
|
|
"mean_token_accuracy": 0.10424959361553192,
|
|
"num_tokens": 2901784.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.106187534332276,
|
|
"epoch": 0.14894786824611386,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499972927540132,
|
|
"loss": 7.0934,
|
|
"mean_token_accuracy": 0.11211119145154953,
|
|
"num_tokens": 2912294.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.037475490570069,
|
|
"epoch": 0.14944769330734242,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999723710920703,
|
|
"loss": 7.0035,
|
|
"mean_token_accuracy": 0.10910386443138123,
|
|
"num_tokens": 2921558.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.123606777191162,
|
|
"epoch": 0.149947518368571,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999718089837616,
|
|
"loss": 7.0266,
|
|
"mean_token_accuracy": 0.10954056233167649,
|
|
"num_tokens": 2930997.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.054976892471314,
|
|
"epoch": 0.15044734342979957,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00049997124121522,
|
|
"loss": 7.0144,
|
|
"mean_token_accuracy": 0.11238231882452965,
|
|
"num_tokens": 2939199.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.039057970046997,
|
|
"epoch": 0.15094716849102813,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999706677864599,
|
|
"loss": 7.0878,
|
|
"mean_token_accuracy": 0.11365630775690079,
|
|
"num_tokens": 2949466.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.079186916351318,
|
|
"epoch": 0.15144699355225671,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999700886974958,
|
|
"loss": 7.0284,
|
|
"mean_token_accuracy": 0.11694424152374268,
|
|
"num_tokens": 2959653.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.05449070930481,
|
|
"epoch": 0.15194681861348527,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499969503948342,
|
|
"loss": 7.0295,
|
|
"mean_token_accuracy": 0.11299590468406677,
|
|
"num_tokens": 2970331.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.995374393463135,
|
|
"epoch": 0.15244664367471386,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999689135390134,
|
|
"loss": 6.9897,
|
|
"mean_token_accuracy": 0.11340121328830718,
|
|
"num_tokens": 2980375.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.982559442520142,
|
|
"epoch": 0.15294646873594242,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999683174695249,
|
|
"loss": 7.0662,
|
|
"mean_token_accuracy": 0.10985481515526771,
|
|
"num_tokens": 2990562.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.104888010025024,
|
|
"epoch": 0.15344629379717098,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999677157398914,
|
|
"loss": 6.9735,
|
|
"mean_token_accuracy": 0.12070909142494202,
|
|
"num_tokens": 3000797.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.979942655563354,
|
|
"epoch": 0.15394611885839957,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999671083501281,
|
|
"loss": 7.0347,
|
|
"mean_token_accuracy": 0.11492840200662613,
|
|
"num_tokens": 3010520.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.0611762523651125,
|
|
"epoch": 0.15444594391962813,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999664953002502,
|
|
"loss": 6.9505,
|
|
"mean_token_accuracy": 0.11264497265219689,
|
|
"num_tokens": 3020249.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.055840873718262,
|
|
"epoch": 0.1549457689808567,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499965876590273,
|
|
"loss": 7.1282,
|
|
"mean_token_accuracy": 0.11212135925889015,
|
|
"num_tokens": 3031721.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.055178308486939,
|
|
"epoch": 0.15544559404208527,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999652522202125,
|
|
"loss": 7.0479,
|
|
"mean_token_accuracy": 0.11103066131472587,
|
|
"num_tokens": 3041236.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.10380334854126,
|
|
"epoch": 0.15594541910331383,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999646221900839,
|
|
"loss": 7.0251,
|
|
"mean_token_accuracy": 0.11302450522780419,
|
|
"num_tokens": 3051749.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.081645584106445,
|
|
"epoch": 0.15644524416454242,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999639864999034,
|
|
"loss": 7.1237,
|
|
"mean_token_accuracy": 0.10856601297855377,
|
|
"num_tokens": 3061928.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.9718320846557615,
|
|
"epoch": 0.15694506922577098,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499963345149687,
|
|
"loss": 6.9493,
|
|
"mean_token_accuracy": 0.11934173181653022,
|
|
"num_tokens": 3071598.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.99726939201355,
|
|
"epoch": 0.15744489428699954,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999626981394506,
|
|
"loss": 6.9957,
|
|
"mean_token_accuracy": 0.11047958061099053,
|
|
"num_tokens": 3081952.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.108104562759399,
|
|
"epoch": 0.15794471934822812,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999620454692106,
|
|
"loss": 7.0704,
|
|
"mean_token_accuracy": 0.11186990886926651,
|
|
"num_tokens": 3092047.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.076290416717529,
|
|
"epoch": 0.15844454440945668,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999613871389836,
|
|
"loss": 7.0374,
|
|
"mean_token_accuracy": 0.10968389436602592,
|
|
"num_tokens": 3101454.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.990331602096558,
|
|
"epoch": 0.15894436947068527,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999607231487858,
|
|
"loss": 6.997,
|
|
"mean_token_accuracy": 0.11208927035331726,
|
|
"num_tokens": 3111447.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.939959478378296,
|
|
"epoch": 0.15944419453191383,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499960053498634,
|
|
"loss": 6.9089,
|
|
"mean_token_accuracy": 0.11952870041131973,
|
|
"num_tokens": 3121085.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.9829981327056885,
|
|
"epoch": 0.1599440195931424,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999593781885454,
|
|
"loss": 6.9608,
|
|
"mean_token_accuracy": 0.11509754583239555,
|
|
"num_tokens": 3131233.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.03386549949646,
|
|
"epoch": 0.16044384465437098,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999586972185366,
|
|
"loss": 7.0519,
|
|
"mean_token_accuracy": 0.11012849733233451,
|
|
"num_tokens": 3140541.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.025159740447998,
|
|
"epoch": 0.16094366971559954,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999580105886248,
|
|
"loss": 7.0377,
|
|
"mean_token_accuracy": 0.10797161757946014,
|
|
"num_tokens": 3150166.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.028019046783447,
|
|
"epoch": 0.16144349477682812,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999573182988275,
|
|
"loss": 7.0528,
|
|
"mean_token_accuracy": 0.11481094807386398,
|
|
"num_tokens": 3160259.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.063313341140747,
|
|
"epoch": 0.16194331983805668,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999566203491619,
|
|
"loss": 6.9958,
|
|
"mean_token_accuracy": 0.11163723319768906,
|
|
"num_tokens": 3168801.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.082771110534668,
|
|
"epoch": 0.16244314489928524,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999559167396455,
|
|
"loss": 7.1206,
|
|
"mean_token_accuracy": 0.10632694289088249,
|
|
"num_tokens": 3181029.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.970886611938477,
|
|
"epoch": 0.16294296996051383,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999552074702963,
|
|
"loss": 6.9377,
|
|
"mean_token_accuracy": 0.12233891040086746,
|
|
"num_tokens": 3190963.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.8871989250183105,
|
|
"epoch": 0.1634427950217424,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999544925411318,
|
|
"loss": 6.9319,
|
|
"mean_token_accuracy": 0.11681057810783387,
|
|
"num_tokens": 3200714.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.0543567657470705,
|
|
"epoch": 0.16394262008297095,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999537719521703,
|
|
"loss": 6.9678,
|
|
"mean_token_accuracy": 0.11916712298989296,
|
|
"num_tokens": 3209965.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.976824760437012,
|
|
"epoch": 0.16444244514419953,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999530457034297,
|
|
"loss": 7.0004,
|
|
"mean_token_accuracy": 0.10843002274632454,
|
|
"num_tokens": 3218849.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.04572696685791,
|
|
"epoch": 0.1649422702054281,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999523137949283,
|
|
"loss": 7.0266,
|
|
"mean_token_accuracy": 0.11135978549718857,
|
|
"num_tokens": 3229483.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.008546638488769,
|
|
"epoch": 0.16544209526665668,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999515762266846,
|
|
"loss": 7.0348,
|
|
"mean_token_accuracy": 0.11097366139292716,
|
|
"num_tokens": 3239818.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.0645958423614506,
|
|
"epoch": 0.16594192032788524,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999508329987173,
|
|
"loss": 7.0354,
|
|
"mean_token_accuracy": 0.1088833674788475,
|
|
"num_tokens": 3249136.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.004113721847534,
|
|
"epoch": 0.1664417453891138,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999500841110447,
|
|
"loss": 6.9393,
|
|
"mean_token_accuracy": 0.11334899812936783,
|
|
"num_tokens": 3258624.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.035124921798706,
|
|
"epoch": 0.16694157045034239,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499949329563686,
|
|
"loss": 7.0458,
|
|
"mean_token_accuracy": 0.1125538133084774,
|
|
"num_tokens": 3269079.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.938257694244385,
|
|
"epoch": 0.16744139551157095,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049994856935666,
|
|
"loss": 6.9704,
|
|
"mean_token_accuracy": 0.11796347573399543,
|
|
"num_tokens": 3280069.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.02333631515503,
|
|
"epoch": 0.16794122057279953,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499947803489986,
|
|
"loss": 6.9613,
|
|
"mean_token_accuracy": 0.11881004869937897,
|
|
"num_tokens": 3289520.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.031835699081421,
|
|
"epoch": 0.1684410456340281,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999470319636829,
|
|
"loss": 6.9666,
|
|
"mean_token_accuracy": 0.11380762606859207,
|
|
"num_tokens": 3299162.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.830581951141357,
|
|
"epoch": 0.16894087069525665,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999462547777705,
|
|
"loss": 6.9635,
|
|
"mean_token_accuracy": 0.1131022647023201,
|
|
"num_tokens": 3308184.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.141867733001709,
|
|
"epoch": 0.16944069575648524,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999454719322682,
|
|
"loss": 6.9862,
|
|
"mean_token_accuracy": 0.1092725582420826,
|
|
"num_tokens": 3317647.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.935384607315063,
|
|
"epoch": 0.1699405208177138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999446834271958,
|
|
"loss": 7.0218,
|
|
"mean_token_accuracy": 0.11219843700528145,
|
|
"num_tokens": 3329437.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.0339641094207765,
|
|
"epoch": 0.17044034587894236,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999438892625728,
|
|
"loss": 6.9907,
|
|
"mean_token_accuracy": 0.11866170018911362,
|
|
"num_tokens": 3340011.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.95525631904602,
|
|
"epoch": 0.17094017094017094,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999430894384198,
|
|
"loss": 6.9671,
|
|
"mean_token_accuracy": 0.11526316031813622,
|
|
"num_tokens": 3348979.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.004418611526489,
|
|
"epoch": 0.1714399960013995,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999422839547564,
|
|
"loss": 7.0279,
|
|
"mean_token_accuracy": 0.1140359953045845,
|
|
"num_tokens": 3359055.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.011244440078736,
|
|
"epoch": 0.1719398210626281,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999414728116029,
|
|
"loss": 6.9398,
|
|
"mean_token_accuracy": 0.11288423910737037,
|
|
"num_tokens": 3368206.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.919700384140015,
|
|
"epoch": 0.17243964612385665,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999406560089798,
|
|
"loss": 6.9835,
|
|
"mean_token_accuracy": 0.11329871043562889,
|
|
"num_tokens": 3378522.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.055575942993164,
|
|
"epoch": 0.1729394711850852,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999398335469078,
|
|
"loss": 6.9712,
|
|
"mean_token_accuracy": 0.117507603764534,
|
|
"num_tokens": 3389052.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.872907257080078,
|
|
"epoch": 0.1734392962463138,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999390054254074,
|
|
"loss": 6.8651,
|
|
"mean_token_accuracy": 0.12086718901991844,
|
|
"num_tokens": 3398269.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.002393960952759,
|
|
"epoch": 0.17393912130754235,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999381716444996,
|
|
"loss": 6.9319,
|
|
"mean_token_accuracy": 0.11592117547988892,
|
|
"num_tokens": 3408063.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.98644380569458,
|
|
"epoch": 0.17443894636877094,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999373322042052,
|
|
"loss": 6.9981,
|
|
"mean_token_accuracy": 0.11340354084968567,
|
|
"num_tokens": 3418903.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.914481353759766,
|
|
"epoch": 0.1749387714299995,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999364871045455,
|
|
"loss": 6.9073,
|
|
"mean_token_accuracy": 0.11716172620654106,
|
|
"num_tokens": 3428831.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.91617751121521,
|
|
"epoch": 0.17543859649122806,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999356363455415,
|
|
"loss": 6.9844,
|
|
"mean_token_accuracy": 0.11535566821694374,
|
|
"num_tokens": 3438314.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.010489749908447,
|
|
"epoch": 0.17593842155245665,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499934779927215,
|
|
"loss": 6.9705,
|
|
"mean_token_accuracy": 0.11254550069570542,
|
|
"num_tokens": 3449248.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.90408673286438,
|
|
"epoch": 0.1764382466136852,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999339178495872,
|
|
"loss": 6.9531,
|
|
"mean_token_accuracy": 0.11303596422076226,
|
|
"num_tokens": 3460119.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.994387435913086,
|
|
"epoch": 0.1769380716749138,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999330501126798,
|
|
"loss": 6.884,
|
|
"mean_token_accuracy": 0.11875045150518418,
|
|
"num_tokens": 3469610.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.824668645858765,
|
|
"epoch": 0.17743789673614235,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999321767165148,
|
|
"loss": 6.9264,
|
|
"mean_token_accuracy": 0.11300530284643173,
|
|
"num_tokens": 3480219.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.031301259994507,
|
|
"epoch": 0.1779377217973709,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999312976611142,
|
|
"loss": 6.8611,
|
|
"mean_token_accuracy": 0.11751789450645447,
|
|
"num_tokens": 3489445.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.933603763580322,
|
|
"epoch": 0.1784375468585995,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999304129465,
|
|
"loss": 6.894,
|
|
"mean_token_accuracy": 0.11873501911759377,
|
|
"num_tokens": 3499164.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.993748378753662,
|
|
"epoch": 0.17893737191982806,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999295225726945,
|
|
"loss": 7.0016,
|
|
"mean_token_accuracy": 0.10571552962064742,
|
|
"num_tokens": 3510242.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.956596851348877,
|
|
"epoch": 0.17943719698105662,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049992862653972,
|
|
"loss": 6.9074,
|
|
"mean_token_accuracy": 0.11266488656401634,
|
|
"num_tokens": 3519481.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.899724102020263,
|
|
"epoch": 0.1799370220422852,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999277248475992,
|
|
"loss": 6.9373,
|
|
"mean_token_accuracy": 0.11640474870800972,
|
|
"num_tokens": 3529706.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.865712833404541,
|
|
"epoch": 0.18043684710351376,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999268174963547,
|
|
"loss": 6.8878,
|
|
"mean_token_accuracy": 0.11141645014286042,
|
|
"num_tokens": 3539239.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.976277828216553,
|
|
"epoch": 0.18093667216474235,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999259044860093,
|
|
"loss": 6.8532,
|
|
"mean_token_accuracy": 0.12506242021918296,
|
|
"num_tokens": 3548177.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.886385822296143,
|
|
"epoch": 0.1814364972259709,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999249858165861,
|
|
"loss": 6.927,
|
|
"mean_token_accuracy": 0.11031646355986595,
|
|
"num_tokens": 3557957.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.96489896774292,
|
|
"epoch": 0.18193632228719947,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999240614881082,
|
|
"loss": 6.9478,
|
|
"mean_token_accuracy": 0.11222271621227264,
|
|
"num_tokens": 3567701.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.956703519821167,
|
|
"epoch": 0.18243614734842806,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999231315005987,
|
|
"loss": 6.887,
|
|
"mean_token_accuracy": 0.11699776723980904,
|
|
"num_tokens": 3575830.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.923069858551026,
|
|
"epoch": 0.18293597240965662,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999221958540811,
|
|
"loss": 6.872,
|
|
"mean_token_accuracy": 0.12267111539840699,
|
|
"num_tokens": 3585453.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.869595146179199,
|
|
"epoch": 0.1834357974708852,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999212545485789,
|
|
"loss": 6.8817,
|
|
"mean_token_accuracy": 0.11956133246421814,
|
|
"num_tokens": 3595340.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.947260522842408,
|
|
"epoch": 0.18393562253211376,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999203075841159,
|
|
"loss": 6.9164,
|
|
"mean_token_accuracy": 0.11490913555026054,
|
|
"num_tokens": 3605083.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.913357925415039,
|
|
"epoch": 0.18443544759334232,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999193549607157,
|
|
"loss": 6.8603,
|
|
"mean_token_accuracy": 0.115931436419487,
|
|
"num_tokens": 3614852.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.967413473129272,
|
|
"epoch": 0.1849352726545709,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999183966784026,
|
|
"loss": 6.869,
|
|
"mean_token_accuracy": 0.11511830314993858,
|
|
"num_tokens": 3624267.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.8707140445709225,
|
|
"epoch": 0.18543509771579947,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999174327372004,
|
|
"loss": 6.8022,
|
|
"mean_token_accuracy": 0.1178055003285408,
|
|
"num_tokens": 3633826.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.904180192947388,
|
|
"epoch": 0.18593492277702803,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999164631371335,
|
|
"loss": 6.9176,
|
|
"mean_token_accuracy": 0.11305896788835526,
|
|
"num_tokens": 3643236.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.843501710891724,
|
|
"epoch": 0.18643474783825661,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999154878782262,
|
|
"loss": 6.7872,
|
|
"mean_token_accuracy": 0.11652820855379105,
|
|
"num_tokens": 3652859.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.843868541717529,
|
|
"epoch": 0.18693457289948517,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499914506960503,
|
|
"loss": 6.9538,
|
|
"mean_token_accuracy": 0.11344718858599663,
|
|
"num_tokens": 3663145.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.950706338882446,
|
|
"epoch": 0.18743439796071376,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999135203839889,
|
|
"loss": 6.9009,
|
|
"mean_token_accuracy": 0.11639713943004608,
|
|
"num_tokens": 3673492.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.898825740814209,
|
|
"epoch": 0.18793422302194232,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999125281487084,
|
|
"loss": 6.912,
|
|
"mean_token_accuracy": 0.11780212670564652,
|
|
"num_tokens": 3683582.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.920530509948731,
|
|
"epoch": 0.18843404808317088,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999115302546866,
|
|
"loss": 6.8498,
|
|
"mean_token_accuracy": 0.11961384862661362,
|
|
"num_tokens": 3693075.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.830911254882812,
|
|
"epoch": 0.18893387314439947,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999105267019486,
|
|
"loss": 6.8987,
|
|
"mean_token_accuracy": 0.11175734475255013,
|
|
"num_tokens": 3702290.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.879076433181763,
|
|
"epoch": 0.18943369820562803,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999095174905195,
|
|
"loss": 6.873,
|
|
"mean_token_accuracy": 0.11547678783535957,
|
|
"num_tokens": 3711811.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.915720272064209,
|
|
"epoch": 0.1899335232668566,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999085026204249,
|
|
"loss": 6.8422,
|
|
"mean_token_accuracy": 0.1173863522708416,
|
|
"num_tokens": 3720863.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.956280708312988,
|
|
"epoch": 0.19043334832808517,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999074820916903,
|
|
"loss": 7.0935,
|
|
"mean_token_accuracy": 0.10641425475478172,
|
|
"num_tokens": 3731797.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.9982743740081785,
|
|
"epoch": 0.19093317338931373,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999064559043412,
|
|
"loss": 6.7111,
|
|
"mean_token_accuracy": 0.12687933146953584,
|
|
"num_tokens": 3741083.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.688722705841064,
|
|
"epoch": 0.19143299845054232,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999054240584037,
|
|
"loss": 6.838,
|
|
"mean_token_accuracy": 0.11955974251031876,
|
|
"num_tokens": 3750438.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.99309196472168,
|
|
"epoch": 0.19193282351177088,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004999043865539035,
|
|
"loss": 6.8709,
|
|
"mean_token_accuracy": 0.11821675300598145,
|
|
"num_tokens": 3759763.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.875771236419678,
|
|
"epoch": 0.19243264857299944,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999033433908667,
|
|
"loss": 6.7974,
|
|
"mean_token_accuracy": 0.12742093130946158,
|
|
"num_tokens": 3769523.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.739752101898193,
|
|
"epoch": 0.19293247363422802,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999022945693198,
|
|
"loss": 6.8347,
|
|
"mean_token_accuracy": 0.1254890479147434,
|
|
"num_tokens": 3779290.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.964044713973999,
|
|
"epoch": 0.19343229869545658,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499901240089289,
|
|
"loss": 6.8592,
|
|
"mean_token_accuracy": 0.12065653949975967,
|
|
"num_tokens": 3788582.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.872059679031372,
|
|
"epoch": 0.19393212375668517,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999001799508009,
|
|
"loss": 6.85,
|
|
"mean_token_accuracy": 0.11490488201379775,
|
|
"num_tokens": 3798281.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.848344993591309,
|
|
"epoch": 0.19443194881791373,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998991141538821,
|
|
"loss": 6.823,
|
|
"mean_token_accuracy": 0.11408965140581132,
|
|
"num_tokens": 3807775.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.9306305885314945,
|
|
"epoch": 0.1949317738791423,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998980426985596,
|
|
"loss": 6.9891,
|
|
"mean_token_accuracy": 0.11584151759743691,
|
|
"num_tokens": 3818852.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.973212671279907,
|
|
"epoch": 0.19543159894037088,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049989696558486,
|
|
"loss": 6.8774,
|
|
"mean_token_accuracy": 0.11234008148312569,
|
|
"num_tokens": 3826924.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.759911155700683,
|
|
"epoch": 0.19593142400159944,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998958828128108,
|
|
"loss": 6.7857,
|
|
"mean_token_accuracy": 0.12838144823908806,
|
|
"num_tokens": 3835098.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.982933855056762,
|
|
"epoch": 0.19643124906282802,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998947943824389,
|
|
"loss": 6.9578,
|
|
"mean_token_accuracy": 0.11286306157708167,
|
|
"num_tokens": 3845914.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.852990055084229,
|
|
"epoch": 0.19693107412405658,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998937002937719,
|
|
"loss": 6.8304,
|
|
"mean_token_accuracy": 0.12221820950508118,
|
|
"num_tokens": 3855791.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.869904279708862,
|
|
"epoch": 0.19743089918528514,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998926005468373,
|
|
"loss": 6.8011,
|
|
"mean_token_accuracy": 0.1274337239563465,
|
|
"num_tokens": 3865970.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.778682661056519,
|
|
"epoch": 0.19793072424651373,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998914951416627,
|
|
"loss": 6.8579,
|
|
"mean_token_accuracy": 0.12313915342092514,
|
|
"num_tokens": 3875139.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.860070657730103,
|
|
"epoch": 0.1984305493077423,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499890384078276,
|
|
"loss": 6.8678,
|
|
"mean_token_accuracy": 0.12257373183965684,
|
|
"num_tokens": 3884075.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.945457220077515,
|
|
"epoch": 0.19893037436897085,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998892673567051,
|
|
"loss": 6.7782,
|
|
"mean_token_accuracy": 0.11979793757200241,
|
|
"num_tokens": 3894273.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.792132806777954,
|
|
"epoch": 0.19943019943019943,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998881449769781,
|
|
"loss": 6.8492,
|
|
"mean_token_accuracy": 0.11639444679021835,
|
|
"num_tokens": 3904940.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.058999633789062,
|
|
"epoch": 0.199930024491428,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004998870169391232,
|
|
"loss": 6.9935,
|
|
"mean_token_accuracy": 0.10505019277334213,
|
|
"num_tokens": 3916273.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.793080759048462,
|
|
"epoch": 0.20042984955265658,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499885883243169,
|
|
"loss": 6.7725,
|
|
"mean_token_accuracy": 0.1189383864402771,
|
|
"num_tokens": 3926495.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.804683971405029,
|
|
"epoch": 0.20092967461388514,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998847438891437,
|
|
"loss": 6.855,
|
|
"mean_token_accuracy": 0.11757523566484451,
|
|
"num_tokens": 3936286.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.880439329147339,
|
|
"epoch": 0.2014294996751137,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998835988770761,
|
|
"loss": 6.8972,
|
|
"mean_token_accuracy": 0.11336359679698944,
|
|
"num_tokens": 3946924.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.921899366378784,
|
|
"epoch": 0.20192932473634229,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499882448206995,
|
|
"loss": 6.8214,
|
|
"mean_token_accuracy": 0.11907981783151626,
|
|
"num_tokens": 3956815.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.759397315979004,
|
|
"epoch": 0.20242914979757085,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998812918789293,
|
|
"loss": 6.7921,
|
|
"mean_token_accuracy": 0.12498126104474068,
|
|
"num_tokens": 3967034.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.884777498245239,
|
|
"epoch": 0.20292897485879943,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998801298929084,
|
|
"loss": 6.8584,
|
|
"mean_token_accuracy": 0.11634212955832482,
|
|
"num_tokens": 3976800.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.952639722824097,
|
|
"epoch": 0.203428799920028,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998789622489611,
|
|
"loss": 6.9162,
|
|
"mean_token_accuracy": 0.11593235284090042,
|
|
"num_tokens": 3987279.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.809817600250244,
|
|
"epoch": 0.20392862498125655,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998777889471171,
|
|
"loss": 6.8146,
|
|
"mean_token_accuracy": 0.11954162642359734,
|
|
"num_tokens": 3998414.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.752009677886963,
|
|
"epoch": 0.20442845004248514,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998766099874056,
|
|
"loss": 6.7814,
|
|
"mean_token_accuracy": 0.12704155817627907,
|
|
"num_tokens": 4007994.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.8828105449676515,
|
|
"epoch": 0.2049282751037137,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998754253698566,
|
|
"loss": 6.8057,
|
|
"mean_token_accuracy": 0.11565538421273232,
|
|
"num_tokens": 4018285.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.942424201965332,
|
|
"epoch": 0.20542810016494226,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998742350944998,
|
|
"loss": 6.8811,
|
|
"mean_token_accuracy": 0.11090886443853379,
|
|
"num_tokens": 4028689.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.7840094566345215,
|
|
"epoch": 0.20592792522617084,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998730391613651,
|
|
"loss": 6.7998,
|
|
"mean_token_accuracy": 0.12368144318461419,
|
|
"num_tokens": 4038944.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.943382596969604,
|
|
"epoch": 0.2064277502873994,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998718375704825,
|
|
"loss": 6.9236,
|
|
"mean_token_accuracy": 0.11197515055537224,
|
|
"num_tokens": 4049048.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.869805145263672,
|
|
"epoch": 0.206927575348628,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998706303218825,
|
|
"loss": 6.7558,
|
|
"mean_token_accuracy": 0.12332033663988114,
|
|
"num_tokens": 4058710.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.802251243591309,
|
|
"epoch": 0.20742740040985655,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998694174155952,
|
|
"loss": 6.7397,
|
|
"mean_token_accuracy": 0.1152039721608162,
|
|
"num_tokens": 4069517.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.766680097579956,
|
|
"epoch": 0.2079272254710851,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998681988516512,
|
|
"loss": 6.8445,
|
|
"mean_token_accuracy": 0.1188851423561573,
|
|
"num_tokens": 4080730.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.908146905899048,
|
|
"epoch": 0.2084270505323137,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998669746300811,
|
|
"loss": 6.7327,
|
|
"mean_token_accuracy": 0.12420074567198754,
|
|
"num_tokens": 4090505.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.732927560806274,
|
|
"epoch": 0.20892687559354226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998657447509159,
|
|
"loss": 6.7299,
|
|
"mean_token_accuracy": 0.12293928116559982,
|
|
"num_tokens": 4099963.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.810068845748901,
|
|
"epoch": 0.20942670065477084,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998645092141864,
|
|
"loss": 6.8291,
|
|
"mean_token_accuracy": 0.12254174649715424,
|
|
"num_tokens": 4109340.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 7.008067846298218,
|
|
"epoch": 0.2099265257159994,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998632680199238,
|
|
"loss": 6.8521,
|
|
"mean_token_accuracy": 0.11651415005326271,
|
|
"num_tokens": 4118476.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.791560316085816,
|
|
"epoch": 0.21042635077722796,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998620211681591,
|
|
"loss": 6.7869,
|
|
"mean_token_accuracy": 0.12428712770342827,
|
|
"num_tokens": 4127922.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.768087768554688,
|
|
"epoch": 0.21092617583845655,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998607686589239,
|
|
"loss": 6.7947,
|
|
"mean_token_accuracy": 0.11915560439229012,
|
|
"num_tokens": 4137202.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.775341320037842,
|
|
"epoch": 0.2114260008996851,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998595104922496,
|
|
"loss": 6.7885,
|
|
"mean_token_accuracy": 0.1231108471751213,
|
|
"num_tokens": 4146789.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.813695859909058,
|
|
"epoch": 0.2119258259609137,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998582466681678,
|
|
"loss": 6.8566,
|
|
"mean_token_accuracy": 0.11805249378085136,
|
|
"num_tokens": 4157628.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.864239072799682,
|
|
"epoch": 0.21242565102214225,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998569771867105,
|
|
"loss": 6.8133,
|
|
"mean_token_accuracy": 0.11805640012025834,
|
|
"num_tokens": 4168522.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.8641472339630125,
|
|
"epoch": 0.2129254760833708,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998557020479095,
|
|
"loss": 6.883,
|
|
"mean_token_accuracy": 0.12175262719392776,
|
|
"num_tokens": 4178590.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.829242372512818,
|
|
"epoch": 0.2134253011445994,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998544212517968,
|
|
"loss": 6.6766,
|
|
"mean_token_accuracy": 0.13151731938123704,
|
|
"num_tokens": 4188004.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.81755428314209,
|
|
"epoch": 0.21392512620582796,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998531347984047,
|
|
"loss": 6.7795,
|
|
"mean_token_accuracy": 0.11880608722567558,
|
|
"num_tokens": 4197481.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.842449045181274,
|
|
"epoch": 0.21442495126705652,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998518426877656,
|
|
"loss": 6.8284,
|
|
"mean_token_accuracy": 0.12467390969395638,
|
|
"num_tokens": 4207187.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.799112701416016,
|
|
"epoch": 0.2149247763282851,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998505449199122,
|
|
"loss": 6.8034,
|
|
"mean_token_accuracy": 0.12435225024819374,
|
|
"num_tokens": 4216485.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.803231239318848,
|
|
"epoch": 0.21542460138951366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998492414948768,
|
|
"loss": 6.88,
|
|
"mean_token_accuracy": 0.11924681589007377,
|
|
"num_tokens": 4228268.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.819182586669922,
|
|
"epoch": 0.21592442645074225,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998479324126924,
|
|
"loss": 6.7148,
|
|
"mean_token_accuracy": 0.12601147666573526,
|
|
"num_tokens": 4237755.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.888819837570191,
|
|
"epoch": 0.2164242515119708,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998466176733918,
|
|
"loss": 6.8649,
|
|
"mean_token_accuracy": 0.11659305468201638,
|
|
"num_tokens": 4247571.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.720103931427002,
|
|
"epoch": 0.21692407657319937,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998452972770082,
|
|
"loss": 6.8112,
|
|
"mean_token_accuracy": 0.12066830769181251,
|
|
"num_tokens": 4257003.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.877090406417847,
|
|
"epoch": 0.21742390163442796,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998439712235747,
|
|
"loss": 6.8425,
|
|
"mean_token_accuracy": 0.11793331429362297,
|
|
"num_tokens": 4266412.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.851199150085449,
|
|
"epoch": 0.21792372669565652,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998426395131248,
|
|
"loss": 6.7926,
|
|
"mean_token_accuracy": 0.11362633481621742,
|
|
"num_tokens": 4276361.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.8144981384277346,
|
|
"epoch": 0.2184235517568851,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998413021456919,
|
|
"loss": 6.777,
|
|
"mean_token_accuracy": 0.12194588780403137,
|
|
"num_tokens": 4285815.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.815514469146729,
|
|
"epoch": 0.21892337681811366,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998399591213098,
|
|
"loss": 6.7683,
|
|
"mean_token_accuracy": 0.12466176748275756,
|
|
"num_tokens": 4296071.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.768910217285156,
|
|
"epoch": 0.21942320187934222,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998386104400122,
|
|
"loss": 6.7675,
|
|
"mean_token_accuracy": 0.12030394151806831,
|
|
"num_tokens": 4306476.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.856772565841675,
|
|
"epoch": 0.2199230269405708,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998372561018329,
|
|
"loss": 6.8139,
|
|
"mean_token_accuracy": 0.12123706415295601,
|
|
"num_tokens": 4316312.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.765644359588623,
|
|
"epoch": 0.22042285200179937,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998358961068062,
|
|
"loss": 6.7023,
|
|
"mean_token_accuracy": 0.13033238649368287,
|
|
"num_tokens": 4325443.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.814023971557617,
|
|
"epoch": 0.22092267706302793,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998345304549661,
|
|
"loss": 6.7587,
|
|
"mean_token_accuracy": 0.11952677890658378,
|
|
"num_tokens": 4334354.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.719250440597534,
|
|
"epoch": 0.22142250212425652,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998331591463471,
|
|
"loss": 6.665,
|
|
"mean_token_accuracy": 0.12632832303643227,
|
|
"num_tokens": 4344714.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.773249101638794,
|
|
"epoch": 0.22192232718548507,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998317821809837,
|
|
"loss": 6.7179,
|
|
"mean_token_accuracy": 0.12060520201921462,
|
|
"num_tokens": 4354216.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.795089530944824,
|
|
"epoch": 0.22242215224671366,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998303995589104,
|
|
"loss": 6.7614,
|
|
"mean_token_accuracy": 0.1252301424741745,
|
|
"num_tokens": 4364764.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.863585424423218,
|
|
"epoch": 0.22292197730794222,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998290112801623,
|
|
"loss": 6.8389,
|
|
"mean_token_accuracy": 0.11243418082594872,
|
|
"num_tokens": 4375289.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.749932384490966,
|
|
"epoch": 0.22342180236917078,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499827617344774,
|
|
"loss": 6.7263,
|
|
"mean_token_accuracy": 0.12714286744594575,
|
|
"num_tokens": 4384984.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.787637710571289,
|
|
"epoch": 0.22392162743039937,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998262177527807,
|
|
"loss": 6.7057,
|
|
"mean_token_accuracy": 0.12606788277626038,
|
|
"num_tokens": 4393321.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.711228847503662,
|
|
"epoch": 0.22442145249162793,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998248125042177,
|
|
"loss": 6.7929,
|
|
"mean_token_accuracy": 0.1157205656170845,
|
|
"num_tokens": 4404908.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.944765281677246,
|
|
"epoch": 0.2249212775528565,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998234015991202,
|
|
"loss": 6.8806,
|
|
"mean_token_accuracy": 0.11683219075202941,
|
|
"num_tokens": 4415530.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.803278064727783,
|
|
"epoch": 0.22542110261408507,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998219850375238,
|
|
"loss": 6.7849,
|
|
"mean_token_accuracy": 0.11715331003069877,
|
|
"num_tokens": 4425678.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.70594801902771,
|
|
"epoch": 0.22592092767531363,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998205628194641,
|
|
"loss": 6.7662,
|
|
"mean_token_accuracy": 0.12059013247489929,
|
|
"num_tokens": 4436890.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.824479770660401,
|
|
"epoch": 0.22642075273654222,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004998191349449768,
|
|
"loss": 6.5938,
|
|
"mean_token_accuracy": 0.12804949507117272,
|
|
"num_tokens": 4446947.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.856104373931885,
|
|
"epoch": 0.22692057779777078,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998177014140981,
|
|
"loss": 6.7874,
|
|
"mean_token_accuracy": 0.12311343476176262,
|
|
"num_tokens": 4457052.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.644788122177124,
|
|
"epoch": 0.22742040285899934,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998162622268637,
|
|
"loss": 6.6125,
|
|
"mean_token_accuracy": 0.13069870918989182,
|
|
"num_tokens": 4466171.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.739696311950683,
|
|
"epoch": 0.22792022792022792,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998148173833101,
|
|
"loss": 6.8447,
|
|
"mean_token_accuracy": 0.11991135403513908,
|
|
"num_tokens": 4476147.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.839726161956787,
|
|
"epoch": 0.22842005298145648,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998133668834735,
|
|
"loss": 6.7495,
|
|
"mean_token_accuracy": 0.12500213459134102,
|
|
"num_tokens": 4485786.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.724114465713501,
|
|
"epoch": 0.22891987804268507,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998119107273905,
|
|
"loss": 6.8116,
|
|
"mean_token_accuracy": 0.12492655441164971,
|
|
"num_tokens": 4495376.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.879471206665039,
|
|
"epoch": 0.22941970310391363,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998104489150975,
|
|
"loss": 6.7649,
|
|
"mean_token_accuracy": 0.1197766162455082,
|
|
"num_tokens": 4504500.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.749096775054932,
|
|
"epoch": 0.2299195281651422,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998089814466318,
|
|
"loss": 6.8406,
|
|
"mean_token_accuracy": 0.11749223545193672,
|
|
"num_tokens": 4514842.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.818306827545166,
|
|
"epoch": 0.23041935322637078,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998075083220295,
|
|
"loss": 6.7133,
|
|
"mean_token_accuracy": 0.12731910049915313,
|
|
"num_tokens": 4523794.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.823913145065307,
|
|
"epoch": 0.23091917828759934,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998060295413286,
|
|
"loss": 6.7766,
|
|
"mean_token_accuracy": 0.11975430250167847,
|
|
"num_tokens": 4533315.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.660467863082886,
|
|
"epoch": 0.23141900334882792,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998045451045656,
|
|
"loss": 6.6327,
|
|
"mean_token_accuracy": 0.1325990788638592,
|
|
"num_tokens": 4542996.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.791189050674438,
|
|
"epoch": 0.23191882841005648,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998030550117782,
|
|
"loss": 6.7008,
|
|
"mean_token_accuracy": 0.12028939574956894,
|
|
"num_tokens": 4552719.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.704330396652222,
|
|
"epoch": 0.23241865347128504,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998015592630037,
|
|
"loss": 6.648,
|
|
"mean_token_accuracy": 0.12924702242016792,
|
|
"num_tokens": 4562040.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.669022941589356,
|
|
"epoch": 0.23291847853251363,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998000578582798,
|
|
"loss": 6.6894,
|
|
"mean_token_accuracy": 0.12677412778139113,
|
|
"num_tokens": 4570855.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.832343626022339,
|
|
"epoch": 0.2334183035937422,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997985507976443,
|
|
"loss": 6.8056,
|
|
"mean_token_accuracy": 0.11848708391189575,
|
|
"num_tokens": 4581814.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.751095962524414,
|
|
"epoch": 0.23391812865497075,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997970380811351,
|
|
"loss": 6.7034,
|
|
"mean_token_accuracy": 0.12684452831745147,
|
|
"num_tokens": 4590731.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.754598665237427,
|
|
"epoch": 0.23441795371619933,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997955197087904,
|
|
"loss": 6.6995,
|
|
"mean_token_accuracy": 0.11840205565094948,
|
|
"num_tokens": 4600440.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.735138940811157,
|
|
"epoch": 0.2349177787774279,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997939956806481,
|
|
"loss": 6.6952,
|
|
"mean_token_accuracy": 0.12488049641251564,
|
|
"num_tokens": 4609510.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.743107795715332,
|
|
"epoch": 0.23541760383865648,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997924659967467,
|
|
"loss": 6.7829,
|
|
"mean_token_accuracy": 0.12009901478886605,
|
|
"num_tokens": 4620481.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.784450817108154,
|
|
"epoch": 0.23591742889988504,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997909306571248,
|
|
"loss": 6.6512,
|
|
"mean_token_accuracy": 0.1273428089916706,
|
|
"num_tokens": 4629388.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.603338050842285,
|
|
"epoch": 0.2364172539611136,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997893896618209,
|
|
"loss": 6.6389,
|
|
"mean_token_accuracy": 0.1293751984834671,
|
|
"num_tokens": 4638429.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.7959905624389645,
|
|
"epoch": 0.2369170790223422,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997878430108738,
|
|
"loss": 6.7779,
|
|
"mean_token_accuracy": 0.12506488636136054,
|
|
"num_tokens": 4648995.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.788811445236206,
|
|
"epoch": 0.23741690408357075,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997862907043224,
|
|
"loss": 6.6646,
|
|
"mean_token_accuracy": 0.1183782771229744,
|
|
"num_tokens": 4658584.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.686025953292846,
|
|
"epoch": 0.23791672914479933,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997847327422059,
|
|
"loss": 6.7057,
|
|
"mean_token_accuracy": 0.12550745904445648,
|
|
"num_tokens": 4668859.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.788628959655762,
|
|
"epoch": 0.2384165542060279,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997831691245632,
|
|
"loss": 6.7445,
|
|
"mean_token_accuracy": 0.1137440986931324,
|
|
"num_tokens": 4678389.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.700611639022827,
|
|
"epoch": 0.23891637926725645,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997815998514337,
|
|
"loss": 6.7501,
|
|
"mean_token_accuracy": 0.12377952635288239,
|
|
"num_tokens": 4688763.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.7670745849609375,
|
|
"epoch": 0.23941620432848504,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997800249228572,
|
|
"loss": 6.628,
|
|
"mean_token_accuracy": 0.1264137051999569,
|
|
"num_tokens": 4698180.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.683659410476684,
|
|
"epoch": 0.2399160293897136,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997784443388732,
|
|
"loss": 6.6073,
|
|
"mean_token_accuracy": 0.12491724789142608,
|
|
"num_tokens": 4708111.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.736080121994019,
|
|
"epoch": 0.24041585445094216,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997768580995212,
|
|
"loss": 6.7446,
|
|
"mean_token_accuracy": 0.12171546146273612,
|
|
"num_tokens": 4717247.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.755503082275391,
|
|
"epoch": 0.24091567951217074,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997752662048413,
|
|
"loss": 6.6726,
|
|
"mean_token_accuracy": 0.12635646536946296,
|
|
"num_tokens": 4727062.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.629852771759033,
|
|
"epoch": 0.2414155045733993,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997736686548736,
|
|
"loss": 6.6241,
|
|
"mean_token_accuracy": 0.13165736421942711,
|
|
"num_tokens": 4735806.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.795121574401856,
|
|
"epoch": 0.2419153296346279,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997720654496582,
|
|
"loss": 6.7557,
|
|
"mean_token_accuracy": 0.12245218381285668,
|
|
"num_tokens": 4745246.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.797226619720459,
|
|
"epoch": 0.24241515469585645,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997704565892355,
|
|
"loss": 6.6616,
|
|
"mean_token_accuracy": 0.12756211906671525,
|
|
"num_tokens": 4754867.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.677945375442505,
|
|
"epoch": 0.242914979757085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997688420736459,
|
|
"loss": 6.7266,
|
|
"mean_token_accuracy": 0.12988825812935828,
|
|
"num_tokens": 4764418.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.6626581192016605,
|
|
"epoch": 0.2434148048183136,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997672219029301,
|
|
"loss": 6.6897,
|
|
"mean_token_accuracy": 0.12267833352088928,
|
|
"num_tokens": 4774137.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.657618188858033,
|
|
"epoch": 0.24391462987954216,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997655960771288,
|
|
"loss": 6.7239,
|
|
"mean_token_accuracy": 0.12646948918700218,
|
|
"num_tokens": 4784503.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.762366390228271,
|
|
"epoch": 0.24441445494077074,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499763964596283,
|
|
"loss": 6.7776,
|
|
"mean_token_accuracy": 0.118136465549469,
|
|
"num_tokens": 4795847.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.702267074584961,
|
|
"epoch": 0.2449142800019993,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997623274604336,
|
|
"loss": 6.62,
|
|
"mean_token_accuracy": 0.1314212679862976,
|
|
"num_tokens": 4805230.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.675754165649414,
|
|
"epoch": 0.24541410506322786,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499760684669622,
|
|
"loss": 6.5836,
|
|
"mean_token_accuracy": 0.12938425019383432,
|
|
"num_tokens": 4815345.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.669795942306519,
|
|
"epoch": 0.24591393012445645,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997590362238894,
|
|
"loss": 6.6613,
|
|
"mean_token_accuracy": 0.12406706139445305,
|
|
"num_tokens": 4824819.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.726718330383301,
|
|
"epoch": 0.246413755185685,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997573821232772,
|
|
"loss": 6.6956,
|
|
"mean_token_accuracy": 0.12626968026161195,
|
|
"num_tokens": 4834339.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.672310066223145,
|
|
"epoch": 0.24691358024691357,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997557223678272,
|
|
"loss": 6.6875,
|
|
"mean_token_accuracy": 0.1265610449016094,
|
|
"num_tokens": 4844440.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.752259016036987,
|
|
"epoch": 0.24741340530814215,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997540569575809,
|
|
"loss": 6.6733,
|
|
"mean_token_accuracy": 0.12238761708140374,
|
|
"num_tokens": 4854688.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.686040306091309,
|
|
"epoch": 0.2479132303693707,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997523858925805,
|
|
"loss": 6.6788,
|
|
"mean_token_accuracy": 0.12459717616438866,
|
|
"num_tokens": 4864629.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.6606574058532715,
|
|
"epoch": 0.2484130554305993,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997507091728678,
|
|
"loss": 6.6391,
|
|
"mean_token_accuracy": 0.12691431269049644,
|
|
"num_tokens": 4873693.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.66929292678833,
|
|
"epoch": 0.24891288049182786,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997490267984853,
|
|
"loss": 6.6117,
|
|
"mean_token_accuracy": 0.1293844424188137,
|
|
"num_tokens": 4882640.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.712693500518799,
|
|
"epoch": 0.24941270555305642,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997473387694749,
|
|
"loss": 6.7247,
|
|
"mean_token_accuracy": 0.12217676192522049,
|
|
"num_tokens": 4893452.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.7423759460449215,
|
|
"epoch": 0.249912530614285,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997456450858793,
|
|
"loss": 6.744,
|
|
"mean_token_accuracy": 0.11771068722009659,
|
|
"num_tokens": 4902949.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.795651006698608,
|
|
"epoch": 0.25041235567551356,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997439457477412,
|
|
"loss": 6.7037,
|
|
"mean_token_accuracy": 0.12298239767551422,
|
|
"num_tokens": 4912748.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.6983723640441895,
|
|
"epoch": 0.25091218073674215,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997422407551032,
|
|
"loss": 6.6458,
|
|
"mean_token_accuracy": 0.12610778957605362,
|
|
"num_tokens": 4922405.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.636437129974365,
|
|
"epoch": 0.2514120057979707,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997405301080082,
|
|
"loss": 6.6314,
|
|
"mean_token_accuracy": 0.12737202569842337,
|
|
"num_tokens": 4931826.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.669645738601685,
|
|
"epoch": 0.25191183085919927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997388138064994,
|
|
"loss": 6.6993,
|
|
"mean_token_accuracy": 0.12631320729851722,
|
|
"num_tokens": 4942165.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.79401969909668,
|
|
"epoch": 0.25241165592042786,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997370918506198,
|
|
"loss": 6.653,
|
|
"mean_token_accuracy": 0.12517872527241708,
|
|
"num_tokens": 4951287.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.670285224914551,
|
|
"epoch": 0.25291148098165644,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997353642404129,
|
|
"loss": 6.6299,
|
|
"mean_token_accuracy": 0.12621796652674674,
|
|
"num_tokens": 4960452.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.645723724365235,
|
|
"epoch": 0.253411306042885,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997336309759219,
|
|
"loss": 6.6873,
|
|
"mean_token_accuracy": 0.12333321720361709,
|
|
"num_tokens": 4971310.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.833752012252807,
|
|
"epoch": 0.25391113110411356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997318920571907,
|
|
"loss": 6.6327,
|
|
"mean_token_accuracy": 0.1271618574857712,
|
|
"num_tokens": 4980609.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.708815956115723,
|
|
"epoch": 0.25441095616534215,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499730147484263,
|
|
"loss": 6.6814,
|
|
"mean_token_accuracy": 0.12484947890043259,
|
|
"num_tokens": 4989991.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.629834270477295,
|
|
"epoch": 0.2549107812265707,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997283972571824,
|
|
"loss": 6.6538,
|
|
"mean_token_accuracy": 0.12454636245965958,
|
|
"num_tokens": 5000493.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.724473524093628,
|
|
"epoch": 0.25541060628779927,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997266413759934,
|
|
"loss": 6.7358,
|
|
"mean_token_accuracy": 0.1258261241018772,
|
|
"num_tokens": 5010496.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.846870994567871,
|
|
"epoch": 0.25591043134902786,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997248798407397,
|
|
"loss": 6.7987,
|
|
"mean_token_accuracy": 0.11873462423682213,
|
|
"num_tokens": 5020783.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.65616626739502,
|
|
"epoch": 0.2564102564102564,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997231126514659,
|
|
"loss": 6.7041,
|
|
"mean_token_accuracy": 0.12581986486911773,
|
|
"num_tokens": 5029939.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.805445528030395,
|
|
"epoch": 0.256910081471485,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997213398082165,
|
|
"loss": 6.6965,
|
|
"mean_token_accuracy": 0.12117815464735031,
|
|
"num_tokens": 5039491.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.728080701828003,
|
|
"epoch": 0.25740990653271356,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499719561311036,
|
|
"loss": 6.703,
|
|
"mean_token_accuracy": 0.12322363704442978,
|
|
"num_tokens": 5049780.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.738219356536865,
|
|
"epoch": 0.2579097315939421,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997177771599691,
|
|
"loss": 6.6478,
|
|
"mean_token_accuracy": 0.13262535333633424,
|
|
"num_tokens": 5058986.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.644556093215942,
|
|
"epoch": 0.2584095566551707,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997159873550607,
|
|
"loss": 6.6067,
|
|
"mean_token_accuracy": 0.1257613942027092,
|
|
"num_tokens": 5068269.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.6656200885772705,
|
|
"epoch": 0.25890938171639927,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997141918963561,
|
|
"loss": 6.7376,
|
|
"mean_token_accuracy": 0.12358493357896805,
|
|
"num_tokens": 5078674.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.735020542144776,
|
|
"epoch": 0.25940920677762785,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997123907839001,
|
|
"loss": 6.6596,
|
|
"mean_token_accuracy": 0.13049351200461387,
|
|
"num_tokens": 5087599.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.6297863006591795,
|
|
"epoch": 0.2599090318388564,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997105840177381,
|
|
"loss": 6.573,
|
|
"mean_token_accuracy": 0.13603698685765267,
|
|
"num_tokens": 5097418.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.63222975730896,
|
|
"epoch": 0.260408856900085,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997087715979157,
|
|
"loss": 6.6406,
|
|
"mean_token_accuracy": 0.12458560839295388,
|
|
"num_tokens": 5108248.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.792977571487427,
|
|
"epoch": 0.26090868196131356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997069535244785,
|
|
"loss": 6.5949,
|
|
"mean_token_accuracy": 0.13078215345740318,
|
|
"num_tokens": 5118284.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.670963287353516,
|
|
"epoch": 0.2614085070225421,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997051297974722,
|
|
"loss": 6.7458,
|
|
"mean_token_accuracy": 0.12364816442131996,
|
|
"num_tokens": 5128485.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.724144172668457,
|
|
"epoch": 0.2619083320837707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997033004169425,
|
|
"loss": 6.6801,
|
|
"mean_token_accuracy": 0.12441147118806839,
|
|
"num_tokens": 5138058.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.594963788986206,
|
|
"epoch": 0.26240815714499927,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997014653829357,
|
|
"loss": 6.5718,
|
|
"mean_token_accuracy": 0.12949975505471228,
|
|
"num_tokens": 5148555.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.686042213439942,
|
|
"epoch": 0.2629079822062278,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996996246954977,
|
|
"loss": 6.7521,
|
|
"mean_token_accuracy": 0.12199698463082313,
|
|
"num_tokens": 5158729.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.8165223598480225,
|
|
"epoch": 0.2634078072674564,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996977783546752,
|
|
"loss": 6.7889,
|
|
"mean_token_accuracy": 0.12042256221175193,
|
|
"num_tokens": 5168900.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.663141918182373,
|
|
"epoch": 0.26390763232868497,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996959263605143,
|
|
"loss": 6.6848,
|
|
"mean_token_accuracy": 0.12062885612249374,
|
|
"num_tokens": 5179742.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.765869045257569,
|
|
"epoch": 0.2644074573899135,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996940687130617,
|
|
"loss": 6.7068,
|
|
"mean_token_accuracy": 0.12952368706464767,
|
|
"num_tokens": 5190221.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.686702489852905,
|
|
"epoch": 0.2649072824511421,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996922054123641,
|
|
"loss": 6.6781,
|
|
"mean_token_accuracy": 0.1280037760734558,
|
|
"num_tokens": 5200252.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.598478031158447,
|
|
"epoch": 0.2654071075123707,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996903364584685,
|
|
"loss": 6.615,
|
|
"mean_token_accuracy": 0.13113286942243577,
|
|
"num_tokens": 5209388.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.72690258026123,
|
|
"epoch": 0.26590693257359926,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996884618514219,
|
|
"loss": 6.6068,
|
|
"mean_token_accuracy": 0.12769930958747863,
|
|
"num_tokens": 5219806.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.614221572875977,
|
|
"epoch": 0.2664067576348278,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996865815912713,
|
|
"loss": 6.6466,
|
|
"mean_token_accuracy": 0.13306735530495645,
|
|
"num_tokens": 5229485.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.752274036407471,
|
|
"epoch": 0.2669065826960564,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996846956780642,
|
|
"loss": 6.5997,
|
|
"mean_token_accuracy": 0.12850728780031204,
|
|
"num_tokens": 5238922.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.690626525878907,
|
|
"epoch": 0.26740640775728497,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499682804111848,
|
|
"loss": 6.6119,
|
|
"mean_token_accuracy": 0.12641794681549073,
|
|
"num_tokens": 5248391.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.60139684677124,
|
|
"epoch": 0.2679062328185135,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996809068926702,
|
|
"loss": 6.6419,
|
|
"mean_token_accuracy": 0.123379535228014,
|
|
"num_tokens": 5257605.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.855893611907959,
|
|
"epoch": 0.2684060578797421,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996790040205786,
|
|
"loss": 6.733,
|
|
"mean_token_accuracy": 0.12259264960885048,
|
|
"num_tokens": 5266808.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.6668785572052,
|
|
"epoch": 0.2689058829409707,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996770954956211,
|
|
"loss": 6.588,
|
|
"mean_token_accuracy": 0.12270834892988206,
|
|
"num_tokens": 5276471.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.526516389846802,
|
|
"epoch": 0.2694057080021992,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996751813178456,
|
|
"loss": 6.5825,
|
|
"mean_token_accuracy": 0.1287649765610695,
|
|
"num_tokens": 5285312.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.743730878829956,
|
|
"epoch": 0.2699055330634278,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996732614873005,
|
|
"loss": 6.7142,
|
|
"mean_token_accuracy": 0.1179872803390026,
|
|
"num_tokens": 5295608.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.770171070098877,
|
|
"epoch": 0.2704053581246564,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996713360040339,
|
|
"loss": 6.6397,
|
|
"mean_token_accuracy": 0.11945433616638183,
|
|
"num_tokens": 5305181.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.633085536956787,
|
|
"epoch": 0.27090518318588497,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996694048680942,
|
|
"loss": 6.6363,
|
|
"mean_token_accuracy": 0.1233569286763668,
|
|
"num_tokens": 5314706.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.692262840270996,
|
|
"epoch": 0.2714050082471135,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996674680795302,
|
|
"loss": 6.5719,
|
|
"mean_token_accuracy": 0.12792405486106873,
|
|
"num_tokens": 5324207.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.684712648391724,
|
|
"epoch": 0.2719048333083421,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996655256383905,
|
|
"loss": 6.6373,
|
|
"mean_token_accuracy": 0.13132793381810187,
|
|
"num_tokens": 5333554.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.712253999710083,
|
|
"epoch": 0.2724046583695707,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499663577544724,
|
|
"loss": 6.7384,
|
|
"mean_token_accuracy": 0.12213098257780075,
|
|
"num_tokens": 5343811.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.668386173248291,
|
|
"epoch": 0.2729044834307992,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996616237985796,
|
|
"loss": 6.6756,
|
|
"mean_token_accuracy": 0.12649924755096437,
|
|
"num_tokens": 5353980.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.679471397399903,
|
|
"epoch": 0.2734043084920278,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996596644000066,
|
|
"loss": 6.6248,
|
|
"mean_token_accuracy": 0.12806927114725114,
|
|
"num_tokens": 5363681.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.6617810249328615,
|
|
"epoch": 0.2739041335532564,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996576993490543,
|
|
"loss": 6.5761,
|
|
"mean_token_accuracy": 0.131463872641325,
|
|
"num_tokens": 5373855.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.67656135559082,
|
|
"epoch": 0.2744039586144849,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996557286457721,
|
|
"loss": 6.6356,
|
|
"mean_token_accuracy": 0.13073286339640616,
|
|
"num_tokens": 5383831.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.643531417846679,
|
|
"epoch": 0.2749037836757135,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996537522902096,
|
|
"loss": 6.6556,
|
|
"mean_token_accuracy": 0.12728592455387117,
|
|
"num_tokens": 5392247.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.7533129215240475,
|
|
"epoch": 0.2754036087369421,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996517702824163,
|
|
"loss": 6.5965,
|
|
"mean_token_accuracy": 0.12399986758828163,
|
|
"num_tokens": 5401091.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.579279232025146,
|
|
"epoch": 0.2759034337981706,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996497826224425,
|
|
"loss": 6.5962,
|
|
"mean_token_accuracy": 0.12309449911117554,
|
|
"num_tokens": 5409809.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.620116662979126,
|
|
"epoch": 0.2764032588593992,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996477893103379,
|
|
"loss": 6.5615,
|
|
"mean_token_accuracy": 0.12355576753616333,
|
|
"num_tokens": 5420104.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.729361152648925,
|
|
"epoch": 0.2769030839206278,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996457903461527,
|
|
"loss": 6.6167,
|
|
"mean_token_accuracy": 0.1286129795014858,
|
|
"num_tokens": 5427905.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.547765827178955,
|
|
"epoch": 0.2774029089818564,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996437857299373,
|
|
"loss": 6.6143,
|
|
"mean_token_accuracy": 0.12569204494357109,
|
|
"num_tokens": 5438537.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.656113147735596,
|
|
"epoch": 0.2779027340430849,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499641775461742,
|
|
"loss": 6.6938,
|
|
"mean_token_accuracy": 0.11961924210190773,
|
|
"num_tokens": 5447622.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.70698127746582,
|
|
"epoch": 0.2784025591043135,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996397595416173,
|
|
"loss": 6.5777,
|
|
"mean_token_accuracy": 0.13341286554932594,
|
|
"num_tokens": 5457407.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.622921562194824,
|
|
"epoch": 0.2789023841655421,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996377379696143,
|
|
"loss": 6.5933,
|
|
"mean_token_accuracy": 0.13096230253577232,
|
|
"num_tokens": 5467187.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.642458534240722,
|
|
"epoch": 0.2794022092267706,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996357107457834,
|
|
"loss": 6.6399,
|
|
"mean_token_accuracy": 0.1232068620622158,
|
|
"num_tokens": 5477188.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.670599174499512,
|
|
"epoch": 0.2799020342879992,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499633677870176,
|
|
"loss": 6.6117,
|
|
"mean_token_accuracy": 0.12734065651893617,
|
|
"num_tokens": 5485851.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.606281375885009,
|
|
"epoch": 0.2804018593492278,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996316393428429,
|
|
"loss": 6.6693,
|
|
"mean_token_accuracy": 0.12643833607435226,
|
|
"num_tokens": 5496415.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.692524671554565,
|
|
"epoch": 0.2809016844104563,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996295951638357,
|
|
"loss": 6.5686,
|
|
"mean_token_accuracy": 0.12833034321665765,
|
|
"num_tokens": 5505538.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.568633985519409,
|
|
"epoch": 0.2814015094716849,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996275453332057,
|
|
"loss": 6.6514,
|
|
"mean_token_accuracy": 0.12869037836790084,
|
|
"num_tokens": 5514608.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.656951904296875,
|
|
"epoch": 0.2819013345329135,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996254898510043,
|
|
"loss": 6.6142,
|
|
"mean_token_accuracy": 0.12892503589391707,
|
|
"num_tokens": 5523935.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.599626064300537,
|
|
"epoch": 0.282401159594142,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996234287172835,
|
|
"loss": 6.5469,
|
|
"mean_token_accuracy": 0.13197477608919145,
|
|
"num_tokens": 5534393.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.674867105484009,
|
|
"epoch": 0.2829009846553706,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499621361932095,
|
|
"loss": 6.554,
|
|
"mean_token_accuracy": 0.13297315090894699,
|
|
"num_tokens": 5543414.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.550549697875977,
|
|
"epoch": 0.2834008097165992,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996192894954909,
|
|
"loss": 6.5881,
|
|
"mean_token_accuracy": 0.12630681097507476,
|
|
"num_tokens": 5553742.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.552373313903809,
|
|
"epoch": 0.2839006347778278,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996172114075232,
|
|
"loss": 6.4778,
|
|
"mean_token_accuracy": 0.14240361452102662,
|
|
"num_tokens": 5562092.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.673096942901611,
|
|
"epoch": 0.2844004598390563,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996151276682443,
|
|
"loss": 6.7083,
|
|
"mean_token_accuracy": 0.120253437012434,
|
|
"num_tokens": 5571130.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.812530374526977,
|
|
"epoch": 0.2849002849002849,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996130382777065,
|
|
"loss": 6.8625,
|
|
"mean_token_accuracy": 0.11538219377398491,
|
|
"num_tokens": 5581237.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.786452722549439,
|
|
"epoch": 0.2854001099615135,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996109432359625,
|
|
"loss": 6.7088,
|
|
"mean_token_accuracy": 0.11961062774062156,
|
|
"num_tokens": 5592488.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.614932441711426,
|
|
"epoch": 0.285899935022742,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996088425430651,
|
|
"loss": 6.6408,
|
|
"mean_token_accuracy": 0.12676824256777763,
|
|
"num_tokens": 5602958.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.676570177078247,
|
|
"epoch": 0.2863997600839706,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996067361990669,
|
|
"loss": 6.5944,
|
|
"mean_token_accuracy": 0.12091765776276589,
|
|
"num_tokens": 5613247.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.595865106582641,
|
|
"epoch": 0.2868995851451992,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996046242040209,
|
|
"loss": 6.6159,
|
|
"mean_token_accuracy": 0.12946290895342827,
|
|
"num_tokens": 5624102.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.722023248672485,
|
|
"epoch": 0.28739941020642773,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996025065579805,
|
|
"loss": 6.5746,
|
|
"mean_token_accuracy": 0.1296988345682621,
|
|
"num_tokens": 5633147.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.571990823745727,
|
|
"epoch": 0.2878992352676563,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996003832609988,
|
|
"loss": 6.52,
|
|
"mean_token_accuracy": 0.12874272242188453,
|
|
"num_tokens": 5643399.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.636166620254516,
|
|
"epoch": 0.2883990603288849,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995982543131292,
|
|
"loss": 6.6537,
|
|
"mean_token_accuracy": 0.12803954407572746,
|
|
"num_tokens": 5653129.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.659896039962769,
|
|
"epoch": 0.28889888539011344,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995961197144254,
|
|
"loss": 6.574,
|
|
"mean_token_accuracy": 0.12690625563263894,
|
|
"num_tokens": 5662834.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.62721266746521,
|
|
"epoch": 0.289398710451342,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499593979464941,
|
|
"loss": 6.5245,
|
|
"mean_token_accuracy": 0.1367620535194874,
|
|
"num_tokens": 5672393.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.575651407241821,
|
|
"epoch": 0.2898985355125706,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995918335647298,
|
|
"loss": 6.641,
|
|
"mean_token_accuracy": 0.12922657430171966,
|
|
"num_tokens": 5683189.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.698366451263428,
|
|
"epoch": 0.2903983605737992,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995896820138459,
|
|
"loss": 6.6047,
|
|
"mean_token_accuracy": 0.12848019748926162,
|
|
"num_tokens": 5692999.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.607630872726441,
|
|
"epoch": 0.29089818563502773,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995875248123434,
|
|
"loss": 6.5603,
|
|
"mean_token_accuracy": 0.13163489624857902,
|
|
"num_tokens": 5701707.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.550287914276123,
|
|
"epoch": 0.2913980106962563,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995853619602766,
|
|
"loss": 6.5145,
|
|
"mean_token_accuracy": 0.13139068633317946,
|
|
"num_tokens": 5711824.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.6153514862060545,
|
|
"epoch": 0.2918978357574849,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995831934576998,
|
|
"loss": 6.6159,
|
|
"mean_token_accuracy": 0.1276139497756958,
|
|
"num_tokens": 5722681.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.689180564880371,
|
|
"epoch": 0.29239766081871343,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995810193046677,
|
|
"loss": 6.6413,
|
|
"mean_token_accuracy": 0.12465909719467164,
|
|
"num_tokens": 5731806.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.621496391296387,
|
|
"epoch": 0.292897485879942,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499578839501235,
|
|
"loss": 6.5787,
|
|
"mean_token_accuracy": 0.13288640938699245,
|
|
"num_tokens": 5742144.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.629134702682495,
|
|
"epoch": 0.2933973109411706,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004995766540474564,
|
|
"loss": 6.5861,
|
|
"mean_token_accuracy": 0.12582591250538827,
|
|
"num_tokens": 5752752.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.645046520233154,
|
|
"epoch": 0.29389713600239914,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499574462943387,
|
|
"loss": 6.5592,
|
|
"mean_token_accuracy": 0.12969356775283813,
|
|
"num_tokens": 5762031.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.555618953704834,
|
|
"epoch": 0.2943969610636277,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499572266189082,
|
|
"loss": 6.4955,
|
|
"mean_token_accuracy": 0.13256025910377503,
|
|
"num_tokens": 5772160.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.672516822814941,
|
|
"epoch": 0.2948967861248563,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995700637845964,
|
|
"loss": 6.5956,
|
|
"mean_token_accuracy": 0.1309208579361439,
|
|
"num_tokens": 5782145.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.504296970367432,
|
|
"epoch": 0.29539661118608485,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995678557299859,
|
|
"loss": 6.4564,
|
|
"mean_token_accuracy": 0.13597625270485877,
|
|
"num_tokens": 5790889.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.603075456619263,
|
|
"epoch": 0.29589643624731343,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995656420253058,
|
|
"loss": 6.5988,
|
|
"mean_token_accuracy": 0.12828355878591538,
|
|
"num_tokens": 5801239.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.740132427215576,
|
|
"epoch": 0.296396261308542,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499563422670612,
|
|
"loss": 6.7086,
|
|
"mean_token_accuracy": 0.12531245574355127,
|
|
"num_tokens": 5811390.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.689449691772461,
|
|
"epoch": 0.2968960863697706,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995611976659604,
|
|
"loss": 6.66,
|
|
"mean_token_accuracy": 0.11997519657015801,
|
|
"num_tokens": 5821529.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.641141653060913,
|
|
"epoch": 0.29739591143099914,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995589670114067,
|
|
"loss": 6.5939,
|
|
"mean_token_accuracy": 0.12763414531946182,
|
|
"num_tokens": 5830551.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.6380698680877686,
|
|
"epoch": 0.2978957364922277,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995567307070072,
|
|
"loss": 6.6318,
|
|
"mean_token_accuracy": 0.1293273761868477,
|
|
"num_tokens": 5840768.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.71539797782898,
|
|
"epoch": 0.2983955615534563,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995544887528182,
|
|
"loss": 6.6436,
|
|
"mean_token_accuracy": 0.12486452683806419,
|
|
"num_tokens": 5850515.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.6234863758087155,
|
|
"epoch": 0.29889538661468484,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995522411488959,
|
|
"loss": 6.5344,
|
|
"mean_token_accuracy": 0.1385308474302292,
|
|
"num_tokens": 5859480.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.690147447586059,
|
|
"epoch": 0.29939521167591343,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995499878952971,
|
|
"loss": 6.606,
|
|
"mean_token_accuracy": 0.12124009132385254,
|
|
"num_tokens": 5871255.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.553613376617432,
|
|
"epoch": 0.299895036737142,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995477289920784,
|
|
"loss": 6.5068,
|
|
"mean_token_accuracy": 0.1348038263618946,
|
|
"num_tokens": 5881306.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.299895036737142,
|
|
"eval_entropy": 6.4320071945790005,
|
|
"eval_loss": 6.631665229797363,
|
|
"eval_mean_token_accuracy": 0.13145681092632214,
|
|
"eval_num_tokens": 5881306.0,
|
|
"eval_runtime": 23.9243,
|
|
"eval_samples_per_second": 1297.635,
|
|
"eval_steps_per_second": 162.22,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 100030,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 9369189218304000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|