250d9f219f
Model: fpadovani/eng-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 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": 0.3369461447745269,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.838842916488647,
|
|
"epoch": 0.0005615769079575448,
|
|
"grad_norm": 17.625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.3444,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 10897.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.85677433013916,
|
|
"epoch": 0.0011231538159150896,
|
|
"grad_norm": 27.375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.2546,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 23084.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.91091685295105,
|
|
"epoch": 0.0016847307238726343,
|
|
"grad_norm": 22.375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.0991,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 35810.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.158815002441406,
|
|
"epoch": 0.0022463076318301792,
|
|
"grad_norm": 30.625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.5174,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 46019.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.645208549499512,
|
|
"epoch": 0.002807884539787724,
|
|
"grad_norm": 26.75,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 12.2545,
|
|
"mean_token_accuracy": 7.246377062983811e-05,
|
|
"num_tokens": 57272.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 9.382804870605469,
|
|
"epoch": 0.0033694614477452686,
|
|
"grad_norm": 5.15625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 11.1662,
|
|
"mean_token_accuracy": 0.00013372841058298946,
|
|
"num_tokens": 68686.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.640052032470702,
|
|
"epoch": 0.003931038355702813,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.7365,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 79187.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.704295444488526,
|
|
"epoch": 0.0044926152636603585,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.4885,
|
|
"mean_token_accuracy": 0.02202295488677919,
|
|
"num_tokens": 90293.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.693971633911133,
|
|
"epoch": 0.005054192171617903,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.1222,
|
|
"mean_token_accuracy": 0.038746101595461366,
|
|
"num_tokens": 100420.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.644959449768066,
|
|
"epoch": 0.005615769079575448,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.8614,
|
|
"mean_token_accuracy": 0.03684623762965202,
|
|
"num_tokens": 111198.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.567186164855958,
|
|
"epoch": 0.006177345987532993,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.6438,
|
|
"mean_token_accuracy": 0.03930287417024374,
|
|
"num_tokens": 124723.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.53961763381958,
|
|
"epoch": 0.006738922895490537,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.4635,
|
|
"mean_token_accuracy": 0.03558007832616568,
|
|
"num_tokens": 136366.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.547893810272218,
|
|
"epoch": 0.007300499803448083,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.3861,
|
|
"mean_token_accuracy": 0.03799900617450476,
|
|
"num_tokens": 146536.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.548893260955811,
|
|
"epoch": 0.007862076711405626,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.3036,
|
|
"mean_token_accuracy": 0.04170756805688143,
|
|
"num_tokens": 157005.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.522705841064454,
|
|
"epoch": 0.008423653619363172,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.248,
|
|
"mean_token_accuracy": 0.035757702216506,
|
|
"num_tokens": 167864.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.487411975860596,
|
|
"epoch": 0.008985230527320717,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.1701,
|
|
"mean_token_accuracy": 0.0344331294298172,
|
|
"num_tokens": 179635.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.44954423904419,
|
|
"epoch": 0.00954680743527826,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.0736,
|
|
"mean_token_accuracy": 0.0393454410135746,
|
|
"num_tokens": 190614.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.411544609069825,
|
|
"epoch": 0.010108384343235806,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.9515,
|
|
"mean_token_accuracy": 0.03861959706991911,
|
|
"num_tokens": 201496.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.388364028930663,
|
|
"epoch": 0.010669961251193351,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.8206,
|
|
"mean_token_accuracy": 0.041578310914337634,
|
|
"num_tokens": 211606.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.31544532775879,
|
|
"epoch": 0.011231538159150897,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.6811,
|
|
"mean_token_accuracy": 0.03809907417744398,
|
|
"num_tokens": 223503.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.235967540740967,
|
|
"epoch": 0.01179311506710844,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.602,
|
|
"mean_token_accuracy": 0.03533066865056753,
|
|
"num_tokens": 234744.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.127453708648682,
|
|
"epoch": 0.012354691975065986,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.5013,
|
|
"mean_token_accuracy": 0.04971061982214451,
|
|
"num_tokens": 247663.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.991131114959718,
|
|
"epoch": 0.012916268883023531,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.3462,
|
|
"mean_token_accuracy": 0.051536497101187705,
|
|
"num_tokens": 260326.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.806007671356202,
|
|
"epoch": 0.013477845790981074,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.186,
|
|
"mean_token_accuracy": 0.04841248132288456,
|
|
"num_tokens": 271568.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.62636604309082,
|
|
"epoch": 0.01403942269893862,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.0076,
|
|
"mean_token_accuracy": 0.057324649021029475,
|
|
"num_tokens": 282651.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.388986778259277,
|
|
"epoch": 0.014600999606896165,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.8519,
|
|
"mean_token_accuracy": 0.0591864850372076,
|
|
"num_tokens": 292753.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.186084842681884,
|
|
"epoch": 0.015162576514853709,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8262,
|
|
"mean_token_accuracy": 0.05541557185351849,
|
|
"num_tokens": 302981.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 8.970846366882324,
|
|
"epoch": 0.015724153422811252,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.7879,
|
|
"mean_token_accuracy": 0.05500966273248196,
|
|
"num_tokens": 314461.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.709946346282958,
|
|
"epoch": 0.0162857303307688,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.7088,
|
|
"mean_token_accuracy": 0.0600316010415554,
|
|
"num_tokens": 326877.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.442815399169922,
|
|
"epoch": 0.016847307238726343,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.5355,
|
|
"mean_token_accuracy": 0.0628300279378891,
|
|
"num_tokens": 337831.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.346270942687989,
|
|
"epoch": 0.017408884146683887,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.4941,
|
|
"mean_token_accuracy": 0.061401508003473285,
|
|
"num_tokens": 348233.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.139367294311523,
|
|
"epoch": 0.017970461054641434,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.394,
|
|
"mean_token_accuracy": 0.06936323903501034,
|
|
"num_tokens": 359113.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.002007293701173,
|
|
"epoch": 0.018532037962598977,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.4953,
|
|
"mean_token_accuracy": 0.06876972652971744,
|
|
"num_tokens": 370284.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.985783815383911,
|
|
"epoch": 0.01909361487055652,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.5029,
|
|
"mean_token_accuracy": 0.06690707504749298,
|
|
"num_tokens": 381415.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.8451512336730955,
|
|
"epoch": 0.019655191778514068,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.4341,
|
|
"mean_token_accuracy": 0.07936849370598793,
|
|
"num_tokens": 392080.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.888399457931518,
|
|
"epoch": 0.020216768686471612,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.4261,
|
|
"mean_token_accuracy": 0.07295190393924714,
|
|
"num_tokens": 402551.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.864237499237061,
|
|
"epoch": 0.020778345594429155,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.4271,
|
|
"mean_token_accuracy": 0.07404583394527435,
|
|
"num_tokens": 414670.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.856368970870972,
|
|
"epoch": 0.021339922502386702,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.3977,
|
|
"mean_token_accuracy": 0.08026547133922576,
|
|
"num_tokens": 427162.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.7947780132293705,
|
|
"epoch": 0.021901499410344246,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.2803,
|
|
"mean_token_accuracy": 0.08303194791078568,
|
|
"num_tokens": 438628.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.755880117416382,
|
|
"epoch": 0.022463076318301793,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.2159,
|
|
"mean_token_accuracy": 0.0891957201063633,
|
|
"num_tokens": 449248.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.714970827102661,
|
|
"epoch": 0.023024653226259337,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.1809,
|
|
"mean_token_accuracy": 0.08612844422459602,
|
|
"num_tokens": 460815.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.662018966674805,
|
|
"epoch": 0.02358623013421688,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.3416,
|
|
"mean_token_accuracy": 0.0834441527724266,
|
|
"num_tokens": 471972.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.711150503158569,
|
|
"epoch": 0.024147807042174427,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.3092,
|
|
"mean_token_accuracy": 0.0846812091767788,
|
|
"num_tokens": 482775.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.647646760940551,
|
|
"epoch": 0.02470938395013197,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.2401,
|
|
"mean_token_accuracy": 0.08639068603515625,
|
|
"num_tokens": 495151.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.704783630371094,
|
|
"epoch": 0.025270960858089515,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.2108,
|
|
"mean_token_accuracy": 0.085585917532444,
|
|
"num_tokens": 506947.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.684891605377198,
|
|
"epoch": 0.025832537766047062,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.2449,
|
|
"mean_token_accuracy": 0.08590937703847885,
|
|
"num_tokens": 519153.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.573825359344482,
|
|
"epoch": 0.026394114674004605,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2067,
|
|
"mean_token_accuracy": 0.08794588595628738,
|
|
"num_tokens": 531050.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.663270759582519,
|
|
"epoch": 0.02695569158196215,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.1534,
|
|
"mean_token_accuracy": 0.09201830625534058,
|
|
"num_tokens": 542744.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.600920248031616,
|
|
"epoch": 0.027517268489919696,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.228,
|
|
"mean_token_accuracy": 0.08778905719518662,
|
|
"num_tokens": 554748.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.532622385025024,
|
|
"epoch": 0.02807884539787724,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.1585,
|
|
"mean_token_accuracy": 0.09387479797005653,
|
|
"num_tokens": 564868.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.697250652313232,
|
|
"epoch": 0.028640422305834783,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.1689,
|
|
"mean_token_accuracy": 0.09540257602930069,
|
|
"num_tokens": 575668.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.548843145370483,
|
|
"epoch": 0.02920199921379233,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.2777,
|
|
"mean_token_accuracy": 0.08451436385512352,
|
|
"num_tokens": 587956.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.618549108505249,
|
|
"epoch": 0.029763576121749874,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1221,
|
|
"mean_token_accuracy": 0.09290947988629342,
|
|
"num_tokens": 598246.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.489711093902588,
|
|
"epoch": 0.030325153029707418,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.2436,
|
|
"mean_token_accuracy": 0.09298828765749931,
|
|
"num_tokens": 610628.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.488981866836548,
|
|
"epoch": 0.030886729937664965,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.0009,
|
|
"mean_token_accuracy": 0.09813047423958779,
|
|
"num_tokens": 621214.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.4872016429901125,
|
|
"epoch": 0.031448306845622505,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1012,
|
|
"mean_token_accuracy": 0.10055555552244186,
|
|
"num_tokens": 631123.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.584370040893555,
|
|
"epoch": 0.032009883753580055,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.085,
|
|
"mean_token_accuracy": 0.09335025921463966,
|
|
"num_tokens": 643434.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.4562742710113525,
|
|
"epoch": 0.0325714606615376,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.0706,
|
|
"mean_token_accuracy": 0.09464491978287697,
|
|
"num_tokens": 655336.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.467017602920532,
|
|
"epoch": 0.03313303756949514,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.0599,
|
|
"mean_token_accuracy": 0.09872465133666992,
|
|
"num_tokens": 666591.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.420497798919678,
|
|
"epoch": 0.033694614477452686,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0739,
|
|
"mean_token_accuracy": 0.09496475607156754,
|
|
"num_tokens": 678288.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.421144628524781,
|
|
"epoch": 0.03425619138541023,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.0016,
|
|
"mean_token_accuracy": 0.10096974968910218,
|
|
"num_tokens": 688526.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.3301185131072994,
|
|
"epoch": 0.03481776829336777,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.9177,
|
|
"mean_token_accuracy": 0.110024693608284,
|
|
"num_tokens": 698727.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.411620664596557,
|
|
"epoch": 0.035379345201325324,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.9695,
|
|
"mean_token_accuracy": 0.10299110189080238,
|
|
"num_tokens": 710042.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.385035133361816,
|
|
"epoch": 0.03594092210928287,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.9146,
|
|
"mean_token_accuracy": 0.10558308735489845,
|
|
"num_tokens": 721390.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.296188449859619,
|
|
"epoch": 0.03650249901724041,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.0823,
|
|
"mean_token_accuracy": 0.09788208454847336,
|
|
"num_tokens": 732949.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.4511847496032715,
|
|
"epoch": 0.037064075925197955,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.0935,
|
|
"mean_token_accuracy": 0.09952903613448143,
|
|
"num_tokens": 744943.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.254492616653442,
|
|
"epoch": 0.0376256528331555,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8781,
|
|
"mean_token_accuracy": 0.10532095208764077,
|
|
"num_tokens": 756579.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.256378412246704,
|
|
"epoch": 0.03818722974111304,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8154,
|
|
"mean_token_accuracy": 0.11190035417675973,
|
|
"num_tokens": 767260.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.247639799118042,
|
|
"epoch": 0.03874880664907059,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9169,
|
|
"mean_token_accuracy": 0.10428953543305397,
|
|
"num_tokens": 778163.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.356704139709473,
|
|
"epoch": 0.039310383557028136,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9501,
|
|
"mean_token_accuracy": 0.10315855517983437,
|
|
"num_tokens": 788912.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.303907775878907,
|
|
"epoch": 0.03987196046498568,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.0559,
|
|
"mean_token_accuracy": 0.10429143980145454,
|
|
"num_tokens": 801405.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.173692321777343,
|
|
"epoch": 0.040433537372943223,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8638,
|
|
"mean_token_accuracy": 0.10999086052179337,
|
|
"num_tokens": 813023.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.268525695800781,
|
|
"epoch": 0.04099511428090077,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8755,
|
|
"mean_token_accuracy": 0.1096720390021801,
|
|
"num_tokens": 823993.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.310594749450684,
|
|
"epoch": 0.04155669118885831,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.9426,
|
|
"mean_token_accuracy": 0.10535624772310256,
|
|
"num_tokens": 836642.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.09607253074646,
|
|
"epoch": 0.04211826809681586,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.7626,
|
|
"mean_token_accuracy": 0.10821205154061317,
|
|
"num_tokens": 847475.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.293263673782349,
|
|
"epoch": 0.042679845004773405,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8202,
|
|
"mean_token_accuracy": 0.1073866032063961,
|
|
"num_tokens": 857949.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.130275249481201,
|
|
"epoch": 0.04324142191273095,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8675,
|
|
"mean_token_accuracy": 0.10518962070345879,
|
|
"num_tokens": 868661.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.215259170532226,
|
|
"epoch": 0.04380299882068849,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.8914,
|
|
"mean_token_accuracy": 0.10828885361552239,
|
|
"num_tokens": 879651.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.22428069114685,
|
|
"epoch": 0.044364575728646036,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.8748,
|
|
"mean_token_accuracy": 0.10419828295707703,
|
|
"num_tokens": 891189.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.181816673278808,
|
|
"epoch": 0.044926152636603586,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7881,
|
|
"mean_token_accuracy": 0.10996332466602325,
|
|
"num_tokens": 902915.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.18764443397522,
|
|
"epoch": 0.04548772954456113,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8843,
|
|
"mean_token_accuracy": 0.10474307015538216,
|
|
"num_tokens": 914108.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.189007234573364,
|
|
"epoch": 0.046049306452518673,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.8786,
|
|
"mean_token_accuracy": 0.10835319235920907,
|
|
"num_tokens": 925729.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.182924604415893,
|
|
"epoch": 0.04661088336047622,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.8842,
|
|
"mean_token_accuracy": 0.11298655942082406,
|
|
"num_tokens": 936912.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.123146343231201,
|
|
"epoch": 0.04717246026843376,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.8558,
|
|
"mean_token_accuracy": 0.11014456525444985,
|
|
"num_tokens": 948576.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.098531770706177,
|
|
"epoch": 0.047734037176391304,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7199,
|
|
"mean_token_accuracy": 0.11547508239746093,
|
|
"num_tokens": 959346.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.038528633117676,
|
|
"epoch": 0.048295614084348855,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.7322,
|
|
"mean_token_accuracy": 0.11771169304847717,
|
|
"num_tokens": 970124.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.150494194030761,
|
|
"epoch": 0.0488571909923064,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8081,
|
|
"mean_token_accuracy": 0.11283196061849594,
|
|
"num_tokens": 981628.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.029330587387085,
|
|
"epoch": 0.04941876790026394,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7668,
|
|
"mean_token_accuracy": 0.12012017667293548,
|
|
"num_tokens": 992423.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.096112585067749,
|
|
"epoch": 0.049980344808221486,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7728,
|
|
"mean_token_accuracy": 0.1109731949865818,
|
|
"num_tokens": 1002954.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.020883989334107,
|
|
"epoch": 0.05054192171617903,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.6564,
|
|
"mean_token_accuracy": 0.11653559058904647,
|
|
"num_tokens": 1013351.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.039500284194946,
|
|
"epoch": 0.05110349862413657,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.7656,
|
|
"mean_token_accuracy": 0.11227584257721901,
|
|
"num_tokens": 1023781.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.15218596458435,
|
|
"epoch": 0.051665075532094124,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.8282,
|
|
"mean_token_accuracy": 0.11297958865761756,
|
|
"num_tokens": 1034565.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.995783090591431,
|
|
"epoch": 0.05222665244005167,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.6247,
|
|
"mean_token_accuracy": 0.11796534955501556,
|
|
"num_tokens": 1045595.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.886814785003662,
|
|
"epoch": 0.05278822934800921,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.6337,
|
|
"mean_token_accuracy": 0.11582124829292298,
|
|
"num_tokens": 1056084.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.037261819839477,
|
|
"epoch": 0.053349806255966754,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.682,
|
|
"mean_token_accuracy": 0.11749066337943077,
|
|
"num_tokens": 1067014.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.891424036026001,
|
|
"epoch": 0.0539113831639243,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6497,
|
|
"mean_token_accuracy": 0.12076789811253548,
|
|
"num_tokens": 1078557.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.8824389457702635,
|
|
"epoch": 0.05447296007188184,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7126,
|
|
"mean_token_accuracy": 0.12164518311619758,
|
|
"num_tokens": 1090541.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.996250343322754,
|
|
"epoch": 0.05503453697983939,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7637,
|
|
"mean_token_accuracy": 0.11996383219957352,
|
|
"num_tokens": 1101851.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.960945463180542,
|
|
"epoch": 0.055596113887796936,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.675,
|
|
"mean_token_accuracy": 0.11683426722884178,
|
|
"num_tokens": 1112728.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.036937141418457,
|
|
"epoch": 0.05615769079575448,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7971,
|
|
"mean_token_accuracy": 0.1172296643257141,
|
|
"num_tokens": 1124537.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.785452508926392,
|
|
"epoch": 0.05671926770371202,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6958,
|
|
"mean_token_accuracy": 0.11893488615751266,
|
|
"num_tokens": 1135749.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.959902667999268,
|
|
"epoch": 0.05728084461166957,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6181,
|
|
"mean_token_accuracy": 0.11765907853841781,
|
|
"num_tokens": 1147597.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.922120237350464,
|
|
"epoch": 0.05784242151962711,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.5849,
|
|
"mean_token_accuracy": 0.1235293172299862,
|
|
"num_tokens": 1158975.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.856467056274414,
|
|
"epoch": 0.05840399842758466,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6972,
|
|
"mean_token_accuracy": 0.12084685266017914,
|
|
"num_tokens": 1170556.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.8622949600219725,
|
|
"epoch": 0.058965575335542204,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.5607,
|
|
"mean_token_accuracy": 0.12300923243165016,
|
|
"num_tokens": 1180757.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.924650192260742,
|
|
"epoch": 0.05952715224349975,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.596,
|
|
"mean_token_accuracy": 0.12116657346487045,
|
|
"num_tokens": 1192428.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.890792942047119,
|
|
"epoch": 0.06008872915145729,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6508,
|
|
"mean_token_accuracy": 0.11567564010620117,
|
|
"num_tokens": 1203867.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.883419179916382,
|
|
"epoch": 0.060650306059414835,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6555,
|
|
"mean_token_accuracy": 0.12775546982884406,
|
|
"num_tokens": 1214059.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.8652650833129885,
|
|
"epoch": 0.06121188296737238,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.7077,
|
|
"mean_token_accuracy": 0.12304283306002617,
|
|
"num_tokens": 1224750.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.938561868667603,
|
|
"epoch": 0.06177345987532993,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7628,
|
|
"mean_token_accuracy": 0.11775858029723167,
|
|
"num_tokens": 1235936.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.777755689620972,
|
|
"epoch": 0.06233503678328747,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5937,
|
|
"mean_token_accuracy": 0.12519247382879256,
|
|
"num_tokens": 1247619.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.887727403640747,
|
|
"epoch": 0.06289661369124501,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.659,
|
|
"mean_token_accuracy": 0.12322699278593063,
|
|
"num_tokens": 1258089.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.906085586547851,
|
|
"epoch": 0.06345819059920256,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.7312,
|
|
"mean_token_accuracy": 0.12112714126706123,
|
|
"num_tokens": 1270727.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.755902671813965,
|
|
"epoch": 0.06401976750716011,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.6007,
|
|
"mean_token_accuracy": 0.12350654378533363,
|
|
"num_tokens": 1280886.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.883510446548462,
|
|
"epoch": 0.06458134441511765,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6176,
|
|
"mean_token_accuracy": 0.12934386506676673,
|
|
"num_tokens": 1292205.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.82674560546875,
|
|
"epoch": 0.0651429213230752,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6112,
|
|
"mean_token_accuracy": 0.11811202019453049,
|
|
"num_tokens": 1304621.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.911860084533691,
|
|
"epoch": 0.06570449823103273,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.687,
|
|
"mean_token_accuracy": 0.12401566356420517,
|
|
"num_tokens": 1315481.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.72884316444397,
|
|
"epoch": 0.06626607513899029,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.672,
|
|
"mean_token_accuracy": 0.1262218400835991,
|
|
"num_tokens": 1328726.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.845497131347656,
|
|
"epoch": 0.06682765204694784,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.7212,
|
|
"mean_token_accuracy": 0.11815008223056793,
|
|
"num_tokens": 1340151.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.719886589050293,
|
|
"epoch": 0.06738922895490537,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.4967,
|
|
"mean_token_accuracy": 0.12117979228496552,
|
|
"num_tokens": 1350833.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.805467367172241,
|
|
"epoch": 0.06795080586286292,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6645,
|
|
"mean_token_accuracy": 0.12367547824978828,
|
|
"num_tokens": 1362332.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.769433450698853,
|
|
"epoch": 0.06851238277082046,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5527,
|
|
"mean_token_accuracy": 0.12536538690328597,
|
|
"num_tokens": 1373696.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.676548099517822,
|
|
"epoch": 0.06907395967877801,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.4719,
|
|
"mean_token_accuracy": 0.13480750992894172,
|
|
"num_tokens": 1383553.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.740024566650391,
|
|
"epoch": 0.06963553658673555,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5834,
|
|
"mean_token_accuracy": 0.12851510047912598,
|
|
"num_tokens": 1394487.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.825436305999756,
|
|
"epoch": 0.0701971134946931,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6125,
|
|
"mean_token_accuracy": 0.12515986561775208,
|
|
"num_tokens": 1404928.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.644348859786987,
|
|
"epoch": 0.07075869040265065,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.4801,
|
|
"mean_token_accuracy": 0.13337204083800316,
|
|
"num_tokens": 1415854.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.6855494499206545,
|
|
"epoch": 0.07132026731060818,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5309,
|
|
"mean_token_accuracy": 0.12912384271621705,
|
|
"num_tokens": 1427153.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.709783935546875,
|
|
"epoch": 0.07188184421856574,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.6399,
|
|
"mean_token_accuracy": 0.1278666652739048,
|
|
"num_tokens": 1438907.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.7197265625,
|
|
"epoch": 0.07244342112652327,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5184,
|
|
"mean_token_accuracy": 0.12605315521359445,
|
|
"num_tokens": 1449975.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.712170648574829,
|
|
"epoch": 0.07300499803448082,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4948,
|
|
"mean_token_accuracy": 0.12966418787837028,
|
|
"num_tokens": 1460815.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.6579677104949955,
|
|
"epoch": 0.07356657494243837,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5567,
|
|
"mean_token_accuracy": 0.12379679009318352,
|
|
"num_tokens": 1472403.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.710644960403442,
|
|
"epoch": 0.07412815185039591,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5702,
|
|
"mean_token_accuracy": 0.12100749611854553,
|
|
"num_tokens": 1484015.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.797943162918091,
|
|
"epoch": 0.07468972875835346,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5901,
|
|
"mean_token_accuracy": 0.12561839520931245,
|
|
"num_tokens": 1495383.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.693433809280395,
|
|
"epoch": 0.075251305666311,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.5047,
|
|
"mean_token_accuracy": 0.12705199867486955,
|
|
"num_tokens": 1505893.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.6826924800872805,
|
|
"epoch": 0.07581288257426855,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6436,
|
|
"mean_token_accuracy": 0.12257061004638672,
|
|
"num_tokens": 1518933.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.760889625549316,
|
|
"epoch": 0.07637445948222608,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6673,
|
|
"mean_token_accuracy": 0.12451218515634536,
|
|
"num_tokens": 1530603.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.696544408798218,
|
|
"epoch": 0.07693603639018363,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.5067,
|
|
"mean_token_accuracy": 0.13363826498389245,
|
|
"num_tokens": 1540977.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.735008668899536,
|
|
"epoch": 0.07749761329814119,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.5981,
|
|
"mean_token_accuracy": 0.12193178161978721,
|
|
"num_tokens": 1553004.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.677850008010864,
|
|
"epoch": 0.07805919020609872,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5178,
|
|
"mean_token_accuracy": 0.13057287335395812,
|
|
"num_tokens": 1563446.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.671777582168579,
|
|
"epoch": 0.07862076711405627,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5655,
|
|
"mean_token_accuracy": 0.12624817118048667,
|
|
"num_tokens": 1573884.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.61401858329773,
|
|
"epoch": 0.07918234402201381,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4291,
|
|
"mean_token_accuracy": 0.13389793410897255,
|
|
"num_tokens": 1585396.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.501125383377075,
|
|
"epoch": 0.07974392092997136,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.4109,
|
|
"mean_token_accuracy": 0.13774080127477645,
|
|
"num_tokens": 1596934.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.609948444366455,
|
|
"epoch": 0.08030549783792891,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.4683,
|
|
"mean_token_accuracy": 0.1344927228987217,
|
|
"num_tokens": 1608069.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.599338579177856,
|
|
"epoch": 0.08086707474588645,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.3866,
|
|
"mean_token_accuracy": 0.13470392003655435,
|
|
"num_tokens": 1619532.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.591270208358765,
|
|
"epoch": 0.081428651653844,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5525,
|
|
"mean_token_accuracy": 0.12656062543392183,
|
|
"num_tokens": 1630697.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.659748363494873,
|
|
"epoch": 0.08199022856180153,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5249,
|
|
"mean_token_accuracy": 0.1280876874923706,
|
|
"num_tokens": 1641854.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.703177356719971,
|
|
"epoch": 0.08255180546975908,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.6371,
|
|
"mean_token_accuracy": 0.1277525916695595,
|
|
"num_tokens": 1653036.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.552266073226929,
|
|
"epoch": 0.08311338237771662,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4117,
|
|
"mean_token_accuracy": 0.12795400097966195,
|
|
"num_tokens": 1664096.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.613392782211304,
|
|
"epoch": 0.08367495928567417,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5774,
|
|
"mean_token_accuracy": 0.12923691421747208,
|
|
"num_tokens": 1677890.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.594800758361816,
|
|
"epoch": 0.08423653619363172,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4451,
|
|
"mean_token_accuracy": 0.12722701579332352,
|
|
"num_tokens": 1687627.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.683115100860595,
|
|
"epoch": 0.08479811310158926,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.6706,
|
|
"mean_token_accuracy": 0.12636393308639526,
|
|
"num_tokens": 1700843.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.58741455078125,
|
|
"epoch": 0.08535969000954681,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4928,
|
|
"mean_token_accuracy": 0.12452271282672882,
|
|
"num_tokens": 1712356.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.643987846374512,
|
|
"epoch": 0.08592126691750435,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4807,
|
|
"mean_token_accuracy": 0.13168904408812523,
|
|
"num_tokens": 1722041.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.53457236289978,
|
|
"epoch": 0.0864828438254619,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.57,
|
|
"mean_token_accuracy": 0.12712905704975128,
|
|
"num_tokens": 1733628.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.591041088104248,
|
|
"epoch": 0.08704442073341945,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.4336,
|
|
"mean_token_accuracy": 0.13341111317276955,
|
|
"num_tokens": 1745174.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.515659618377685,
|
|
"epoch": 0.08760599764137698,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.38,
|
|
"mean_token_accuracy": 0.13189554139971732,
|
|
"num_tokens": 1757117.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.525059461593628,
|
|
"epoch": 0.08816757454933453,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.3682,
|
|
"mean_token_accuracy": 0.1381472647190094,
|
|
"num_tokens": 1767343.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.593395042419433,
|
|
"epoch": 0.08872915145729207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.462,
|
|
"mean_token_accuracy": 0.12963056042790413,
|
|
"num_tokens": 1778500.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.50290265083313,
|
|
"epoch": 0.08929072836524962,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4653,
|
|
"mean_token_accuracy": 0.13221071287989616,
|
|
"num_tokens": 1788474.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.755932855606079,
|
|
"epoch": 0.08985230527320717,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.6218,
|
|
"mean_token_accuracy": 0.12680470421910287,
|
|
"num_tokens": 1800756.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.268558931350708,
|
|
"epoch": 0.09041388218116471,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.1349015899002552,
|
|
"num_tokens": 1812172.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.630968856811523,
|
|
"epoch": 0.09097545908912226,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4633,
|
|
"mean_token_accuracy": 0.1382911778986454,
|
|
"num_tokens": 1822057.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.488110589981079,
|
|
"epoch": 0.0915370359970798,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.4049,
|
|
"mean_token_accuracy": 0.13655738160014153,
|
|
"num_tokens": 1833074.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.4761574268341064,
|
|
"epoch": 0.09209861290503735,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3869,
|
|
"mean_token_accuracy": 0.14094622135162355,
|
|
"num_tokens": 1844932.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.494161558151245,
|
|
"epoch": 0.09266018981299488,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4131,
|
|
"mean_token_accuracy": 0.1332133084535599,
|
|
"num_tokens": 1855591.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.388966846466064,
|
|
"epoch": 0.09322176672095243,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3704,
|
|
"mean_token_accuracy": 0.13496313914656638,
|
|
"num_tokens": 1866726.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.572238254547119,
|
|
"epoch": 0.09378334362890998,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.4138,
|
|
"mean_token_accuracy": 0.1391880229115486,
|
|
"num_tokens": 1877385.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.4263691902160645,
|
|
"epoch": 0.09434492053686752,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.3199,
|
|
"mean_token_accuracy": 0.1338621348142624,
|
|
"num_tokens": 1887905.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.395117902755738,
|
|
"epoch": 0.09490649744482507,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3642,
|
|
"mean_token_accuracy": 0.13623479902744293,
|
|
"num_tokens": 1898649.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.444835424423218,
|
|
"epoch": 0.09546807435278261,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.13008482083678247,
|
|
"num_tokens": 1908808.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.572300815582276,
|
|
"epoch": 0.09602965126074016,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4928,
|
|
"mean_token_accuracy": 0.1304762378334999,
|
|
"num_tokens": 1920360.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.422976160049439,
|
|
"epoch": 0.09659122816869771,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3844,
|
|
"mean_token_accuracy": 0.13653280809521676,
|
|
"num_tokens": 1931082.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.534259939193726,
|
|
"epoch": 0.09715280507665525,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.5493,
|
|
"mean_token_accuracy": 0.12917705476284028,
|
|
"num_tokens": 1942712.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.3769426345825195,
|
|
"epoch": 0.0977143819846128,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2825,
|
|
"mean_token_accuracy": 0.13908328264951705,
|
|
"num_tokens": 1953316.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.47237458229065,
|
|
"epoch": 0.09827595889257033,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.3548,
|
|
"mean_token_accuracy": 0.1339756242930889,
|
|
"num_tokens": 1963936.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.405522155761719,
|
|
"epoch": 0.09883753580052788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.3967,
|
|
"mean_token_accuracy": 0.14097022041678428,
|
|
"num_tokens": 1974502.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.409914779663086,
|
|
"epoch": 0.09939911270848542,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.1387803927063942,
|
|
"num_tokens": 1985746.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.426558923721314,
|
|
"epoch": 0.09996068961644297,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4244,
|
|
"mean_token_accuracy": 0.13661134615540504,
|
|
"num_tokens": 1997696.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.5053589820861815,
|
|
"epoch": 0.10052226652440052,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3979,
|
|
"mean_token_accuracy": 0.1326365053653717,
|
|
"num_tokens": 2009462.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.395185899734497,
|
|
"epoch": 0.10108384343235806,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3199,
|
|
"mean_token_accuracy": 0.13828641325235366,
|
|
"num_tokens": 2019547.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.321804475784302,
|
|
"epoch": 0.10164542034031561,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3305,
|
|
"mean_token_accuracy": 0.13299717009067535,
|
|
"num_tokens": 2030990.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.37341685295105,
|
|
"epoch": 0.10220699724827315,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4025,
|
|
"mean_token_accuracy": 0.13234635218977928,
|
|
"num_tokens": 2042488.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.573526334762573,
|
|
"epoch": 0.1027685741562307,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4312,
|
|
"mean_token_accuracy": 0.1312362991273403,
|
|
"num_tokens": 2052822.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.418108129501343,
|
|
"epoch": 0.10333015106418825,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3949,
|
|
"mean_token_accuracy": 0.13608081564307212,
|
|
"num_tokens": 2063274.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.522128009796143,
|
|
"epoch": 0.10389172797214578,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.4406,
|
|
"mean_token_accuracy": 0.1320824518799782,
|
|
"num_tokens": 2074424.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.382816791534424,
|
|
"epoch": 0.10445330488010333,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.4306,
|
|
"mean_token_accuracy": 0.13350846022367477,
|
|
"num_tokens": 2085776.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.57677001953125,
|
|
"epoch": 0.10501488178806087,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4913,
|
|
"mean_token_accuracy": 0.13423626497387886,
|
|
"num_tokens": 2096789.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.406237030029297,
|
|
"epoch": 0.10557645869601842,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4001,
|
|
"mean_token_accuracy": 0.1370982863008976,
|
|
"num_tokens": 2108335.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.491322803497314,
|
|
"epoch": 0.10613803560397596,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4755,
|
|
"mean_token_accuracy": 0.13377573490142822,
|
|
"num_tokens": 2121063.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.351012897491455,
|
|
"epoch": 0.10669961251193351,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.3532,
|
|
"mean_token_accuracy": 0.14160069227218627,
|
|
"num_tokens": 2132442.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.3580584049224855,
|
|
"epoch": 0.10726118941989106,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2661,
|
|
"mean_token_accuracy": 0.14054919332265853,
|
|
"num_tokens": 2142155.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.399745845794678,
|
|
"epoch": 0.1078227663278486,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.14111177176237105,
|
|
"num_tokens": 2152923.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.359347009658814,
|
|
"epoch": 0.10838434323580615,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3205,
|
|
"mean_token_accuracy": 0.13966229930520058,
|
|
"num_tokens": 2164640.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.258652973175049,
|
|
"epoch": 0.10894592014376368,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2377,
|
|
"mean_token_accuracy": 0.1407262295484543,
|
|
"num_tokens": 2175403.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.3965113162994385,
|
|
"epoch": 0.10950749705172123,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3472,
|
|
"mean_token_accuracy": 0.13764843419194223,
|
|
"num_tokens": 2186031.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.3890174388885494,
|
|
"epoch": 0.11006907395967878,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3411,
|
|
"mean_token_accuracy": 0.13227884098887444,
|
|
"num_tokens": 2198152.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.318311357498169,
|
|
"epoch": 0.11063065086763632,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3484,
|
|
"mean_token_accuracy": 0.13873713985085487,
|
|
"num_tokens": 2209435.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.323774909973144,
|
|
"epoch": 0.11119222777559387,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.3035,
|
|
"mean_token_accuracy": 0.1427369087934494,
|
|
"num_tokens": 2219476.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.493531656265259,
|
|
"epoch": 0.11175380468355141,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3993,
|
|
"mean_token_accuracy": 0.1396132729947567,
|
|
"num_tokens": 2231131.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.319530439376831,
|
|
"epoch": 0.11231538159150896,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.3023,
|
|
"mean_token_accuracy": 0.14031659737229346,
|
|
"num_tokens": 2242309.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.262487936019897,
|
|
"epoch": 0.1128769584994665,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499999997707492,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.1367334969341755,
|
|
"num_tokens": 2252236.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.368433952331543,
|
|
"epoch": 0.11343853540742405,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999883941787,
|
|
"loss": 6.4644,
|
|
"mean_token_accuracy": 0.12982962355017663,
|
|
"num_tokens": 2263529.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.292843532562256,
|
|
"epoch": 0.1140001123153816,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999719167785,
|
|
"loss": 6.3108,
|
|
"mean_token_accuracy": 0.13819449320435523,
|
|
"num_tokens": 2275318.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.369863128662109,
|
|
"epoch": 0.11456168922333913,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999482752917,
|
|
"loss": 6.3412,
|
|
"mean_token_accuracy": 0.136563753336668,
|
|
"num_tokens": 2287434.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.253592109680175,
|
|
"epoch": 0.11512326613129668,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999999174697195,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.13917232006788255,
|
|
"num_tokens": 2299145.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.300353574752807,
|
|
"epoch": 0.11568484303925422,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999998795000627,
|
|
"loss": 6.3371,
|
|
"mean_token_accuracy": 0.1372515380382538,
|
|
"num_tokens": 2309841.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.349047756195068,
|
|
"epoch": 0.11624641994721177,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999998343663223,
|
|
"loss": 6.3261,
|
|
"mean_token_accuracy": 0.1395231880247593,
|
|
"num_tokens": 2322143.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.3239373683929445,
|
|
"epoch": 0.11680799685516932,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999997820685,
|
|
"loss": 6.2641,
|
|
"mean_token_accuracy": 0.13360065817832947,
|
|
"num_tokens": 2333207.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.235982275009155,
|
|
"epoch": 0.11736957376312686,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999997226065974,
|
|
"loss": 6.3289,
|
|
"mean_token_accuracy": 0.13780270218849183,
|
|
"num_tokens": 2345542.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.4007457256317135,
|
|
"epoch": 0.11793115067108441,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999996559806163,
|
|
"loss": 6.314,
|
|
"mean_token_accuracy": 0.14232611060142517,
|
|
"num_tokens": 2356612.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.266652011871338,
|
|
"epoch": 0.11849272757904195,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999995821905589,
|
|
"loss": 6.2434,
|
|
"mean_token_accuracy": 0.13702767938375474,
|
|
"num_tokens": 2368204.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.304989004135132,
|
|
"epoch": 0.1190543044869995,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999995012364276,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.14323293939232826,
|
|
"num_tokens": 2379114.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.26793475151062,
|
|
"epoch": 0.11961588139495703,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999994131182248,
|
|
"loss": 6.3179,
|
|
"mean_token_accuracy": 0.1384415589272976,
|
|
"num_tokens": 2390562.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.350690174102783,
|
|
"epoch": 0.12017745830291458,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999993178359535,
|
|
"loss": 6.3826,
|
|
"mean_token_accuracy": 0.13662955462932586,
|
|
"num_tokens": 2402352.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.4283607006073,
|
|
"epoch": 0.12073903521087213,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999992153896166,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.14080253392457961,
|
|
"num_tokens": 2415140.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.249602460861206,
|
|
"epoch": 0.12130061211882967,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999991057792175,
|
|
"loss": 6.2969,
|
|
"mean_token_accuracy": 0.13987230136990547,
|
|
"num_tokens": 2426679.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.337273216247558,
|
|
"epoch": 0.12186218902678722,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999989890047596,
|
|
"loss": 6.3586,
|
|
"mean_token_accuracy": 0.14236537516117095,
|
|
"num_tokens": 2437735.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.343389844894409,
|
|
"epoch": 0.12242376593474476,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999988650662467,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.14142627790570259,
|
|
"num_tokens": 2448611.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.220987558364868,
|
|
"epoch": 0.12298534284270231,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999987339636825,
|
|
"loss": 6.1792,
|
|
"mean_token_accuracy": 0.14699204117059708,
|
|
"num_tokens": 2461101.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.273333358764648,
|
|
"epoch": 0.12354691975065986,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999985956970713,
|
|
"loss": 6.3255,
|
|
"mean_token_accuracy": 0.1386694774031639,
|
|
"num_tokens": 2473569.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.208774709701538,
|
|
"epoch": 0.1241084966586174,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999984502664178,
|
|
"loss": 6.2466,
|
|
"mean_token_accuracy": 0.1429204486310482,
|
|
"num_tokens": 2483970.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.335579538345337,
|
|
"epoch": 0.12467007356657495,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999982976717261,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.14402595162391663,
|
|
"num_tokens": 2494184.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.263895559310913,
|
|
"epoch": 0.1252316504745325,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999981379130016,
|
|
"loss": 6.3083,
|
|
"mean_token_accuracy": 0.14719027727842332,
|
|
"num_tokens": 2505715.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.438121223449707,
|
|
"epoch": 0.12579322738249002,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499997970990249,
|
|
"loss": 6.3564,
|
|
"mean_token_accuracy": 0.1362408310174942,
|
|
"num_tokens": 2517168.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.369924163818359,
|
|
"epoch": 0.12635480429044757,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999977969034737,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.13768665492534637,
|
|
"num_tokens": 2528296.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.212030839920044,
|
|
"epoch": 0.12691638119840512,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999976156526814,
|
|
"loss": 6.3186,
|
|
"mean_token_accuracy": 0.14621145129203797,
|
|
"num_tokens": 2540648.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.224785709381104,
|
|
"epoch": 0.12747795810636267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999974272378776,
|
|
"loss": 6.196,
|
|
"mean_token_accuracy": 0.14358407855033875,
|
|
"num_tokens": 2551840.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.380413961410523,
|
|
"epoch": 0.12803953501432022,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999972316590685,
|
|
"loss": 6.263,
|
|
"mean_token_accuracy": 0.14095489978790282,
|
|
"num_tokens": 2561362.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.275799179077149,
|
|
"epoch": 0.12860111192227774,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999970289162604,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.14759473651647567,
|
|
"num_tokens": 2573584.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.472133827209473,
|
|
"epoch": 0.1291626888302353,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999968190094595,
|
|
"loss": 6.4268,
|
|
"mean_token_accuracy": 0.13627540394663812,
|
|
"num_tokens": 2585255.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.098404502868652,
|
|
"epoch": 0.12972426573819285,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999966019386727,
|
|
"loss": 6.2311,
|
|
"mean_token_accuracy": 0.14041587859392166,
|
|
"num_tokens": 2596849.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.301661539077759,
|
|
"epoch": 0.1302858426461504,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999963777039067,
|
|
"loss": 6.2686,
|
|
"mean_token_accuracy": 0.1406569629907608,
|
|
"num_tokens": 2606918.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.24212965965271,
|
|
"epoch": 0.13084741955410795,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499996146305169,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.1421182483434677,
|
|
"num_tokens": 2617779.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.263619422912598,
|
|
"epoch": 0.13140899646206547,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999959077424665,
|
|
"loss": 6.2691,
|
|
"mean_token_accuracy": 0.14162113517522812,
|
|
"num_tokens": 2630294.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.185452175140381,
|
|
"epoch": 0.13197057337002302,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999956620158072,
|
|
"loss": 6.1681,
|
|
"mean_token_accuracy": 0.1465056374669075,
|
|
"num_tokens": 2641002.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.21528000831604,
|
|
"epoch": 0.13253215027798057,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999954091251987,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.14625044465065,
|
|
"num_tokens": 2652188.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.194118452072144,
|
|
"epoch": 0.13309372718593812,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999951490706491,
|
|
"loss": 6.2151,
|
|
"mean_token_accuracy": 0.14109446853399277,
|
|
"num_tokens": 2662542.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.315721750259399,
|
|
"epoch": 0.13365530409389567,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999948818521667,
|
|
"loss": 6.2176,
|
|
"mean_token_accuracy": 0.14606809467077256,
|
|
"num_tokens": 2673292.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.192793464660644,
|
|
"epoch": 0.1342168810018532,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049999460746976,
|
|
"loss": 6.2188,
|
|
"mean_token_accuracy": 0.14586541950702667,
|
|
"num_tokens": 2684042.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.236338186264038,
|
|
"epoch": 0.13477845790981074,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999943259234377,
|
|
"loss": 6.1383,
|
|
"mean_token_accuracy": 0.14659893661737441,
|
|
"num_tokens": 2694716.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.314930438995361,
|
|
"epoch": 0.1353400348177683,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999940372132089,
|
|
"loss": 6.2874,
|
|
"mean_token_accuracy": 0.14430573657155038,
|
|
"num_tokens": 2706200.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.087372541427612,
|
|
"epoch": 0.13590161172572585,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999937413390826,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.1477084070444107,
|
|
"num_tokens": 2716814.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.265769004821777,
|
|
"epoch": 0.1364631886336834,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999934383010683,
|
|
"loss": 6.2639,
|
|
"mean_token_accuracy": 0.1386260524392128,
|
|
"num_tokens": 2728042.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.220071077346802,
|
|
"epoch": 0.13702476554164092,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999931280991757,
|
|
"loss": 6.2398,
|
|
"mean_token_accuracy": 0.13685657903552056,
|
|
"num_tokens": 2739093.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.315275382995606,
|
|
"epoch": 0.13758634244959847,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999928107334146,
|
|
"loss": 6.273,
|
|
"mean_token_accuracy": 0.13907489106059073,
|
|
"num_tokens": 2750307.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.200074577331543,
|
|
"epoch": 0.13814791935755602,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999924862037952,
|
|
"loss": 6.1898,
|
|
"mean_token_accuracy": 0.14381182566285133,
|
|
"num_tokens": 2760534.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.189889335632325,
|
|
"epoch": 0.13870949626551357,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999921545103278,
|
|
"loss": 6.217,
|
|
"mean_token_accuracy": 0.1399001397192478,
|
|
"num_tokens": 2772459.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.180458927154541,
|
|
"epoch": 0.1392710731734711,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999918156530229,
|
|
"loss": 6.1231,
|
|
"mean_token_accuracy": 0.1533089265227318,
|
|
"num_tokens": 2784038.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.275652027130127,
|
|
"epoch": 0.13983265008142864,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999914696318913,
|
|
"loss": 6.2431,
|
|
"mean_token_accuracy": 0.15094640329480172,
|
|
"num_tokens": 2795756.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.123087310791016,
|
|
"epoch": 0.1403942269893862,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999911164469441,
|
|
"loss": 6.1844,
|
|
"mean_token_accuracy": 0.14661128968000411,
|
|
"num_tokens": 2806242.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.29753270149231,
|
|
"epoch": 0.14095580389734375,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999907560981925,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.14754103049635886,
|
|
"num_tokens": 2817017.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.216703319549561,
|
|
"epoch": 0.1415173808053013,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999903885856479,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.15246719866991043,
|
|
"num_tokens": 2827415.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.185984897613525,
|
|
"epoch": 0.14207895771325882,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499990013909322,
|
|
"loss": 6.1905,
|
|
"mean_token_accuracy": 0.1513909749686718,
|
|
"num_tokens": 2837595.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.154061126708984,
|
|
"epoch": 0.14264053462121637,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499989632069227,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.14768583253026007,
|
|
"num_tokens": 2847906.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.224718379974365,
|
|
"epoch": 0.14320211152917392,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999892430653747,
|
|
"loss": 6.2518,
|
|
"mean_token_accuracy": 0.13458375483751298,
|
|
"num_tokens": 2859145.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.155771541595459,
|
|
"epoch": 0.14376368843713147,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999888468977776,
|
|
"loss": 6.165,
|
|
"mean_token_accuracy": 0.14523654133081437,
|
|
"num_tokens": 2870704.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.266523933410644,
|
|
"epoch": 0.14432526534508902,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999884435664485,
|
|
"loss": 6.2767,
|
|
"mean_token_accuracy": 0.1407052122056484,
|
|
"num_tokens": 2881861.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.25180025100708,
|
|
"epoch": 0.14488684225304654,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004999880330714,
|
|
"loss": 6.2025,
|
|
"mean_token_accuracy": 0.1466933399438858,
|
|
"num_tokens": 2893247.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.105476760864258,
|
|
"epoch": 0.1454484191610041,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999876154126453,
|
|
"loss": 6.0418,
|
|
"mean_token_accuracy": 0.14936177730560302,
|
|
"num_tokens": 2905351.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.1718381404876705,
|
|
"epoch": 0.14600999606896164,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999871905901977,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.1479304015636444,
|
|
"num_tokens": 2915153.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.215558004379273,
|
|
"epoch": 0.1465715729769192,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999867586040706,
|
|
"loss": 6.158,
|
|
"mean_token_accuracy": 0.13994157537817956,
|
|
"num_tokens": 2926234.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.141939926147461,
|
|
"epoch": 0.14713314988487675,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999863194542779,
|
|
"loss": 6.1102,
|
|
"mean_token_accuracy": 0.14791369438171387,
|
|
"num_tokens": 2937033.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.09499454498291,
|
|
"epoch": 0.14769472679283427,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999858731408336,
|
|
"loss": 6.0657,
|
|
"mean_token_accuracy": 0.1484006866812706,
|
|
"num_tokens": 2945904.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.192239475250244,
|
|
"epoch": 0.14825630370079182,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999854196637518,
|
|
"loss": 6.2645,
|
|
"mean_token_accuracy": 0.13989078402519226,
|
|
"num_tokens": 2956298.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.196642541885376,
|
|
"epoch": 0.14881788060874937,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999849590230469,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.14732514470815658,
|
|
"num_tokens": 2967660.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.234364652633667,
|
|
"epoch": 0.14937945751670692,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999844912187336,
|
|
"loss": 6.2437,
|
|
"mean_token_accuracy": 0.14329968988895417,
|
|
"num_tokens": 2978616.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.08893051147461,
|
|
"epoch": 0.14994103442466447,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499984016250827,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.14890712201595308,
|
|
"num_tokens": 2989731.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.246871900558472,
|
|
"epoch": 0.150502611332622,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499983534119342,
|
|
"loss": 6.1816,
|
|
"mean_token_accuracy": 0.14426462948322297,
|
|
"num_tokens": 3002110.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.933366966247559,
|
|
"epoch": 0.15106418824057954,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999830448242941,
|
|
"loss": 6.0031,
|
|
"mean_token_accuracy": 0.1531351014971733,
|
|
"num_tokens": 3012709.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.321645641326905,
|
|
"epoch": 0.1516257651485371,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999825483656986,
|
|
"loss": 6.3087,
|
|
"mean_token_accuracy": 0.13611152917146682,
|
|
"num_tokens": 3025738.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.149252319335938,
|
|
"epoch": 0.15218734205649465,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999820447435716,
|
|
"loss": 6.1525,
|
|
"mean_token_accuracy": 0.14370962455868722,
|
|
"num_tokens": 3037711.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.265703773498535,
|
|
"epoch": 0.15274891896445217,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999815339579291,
|
|
"loss": 6.3363,
|
|
"mean_token_accuracy": 0.1384710282087326,
|
|
"num_tokens": 3048929.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.190625715255737,
|
|
"epoch": 0.15331049587240972,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999810160087872,
|
|
"loss": 6.0812,
|
|
"mean_token_accuracy": 0.1597306936979294,
|
|
"num_tokens": 3059717.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.122515726089477,
|
|
"epoch": 0.15387207278036727,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999804908961626,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.14993196427822114,
|
|
"num_tokens": 3069530.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.177134799957275,
|
|
"epoch": 0.15443364968832482,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999799586200719,
|
|
"loss": 6.2762,
|
|
"mean_token_accuracy": 0.14048854932188987,
|
|
"num_tokens": 3080705.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.211107969284058,
|
|
"epoch": 0.15499522659628237,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499979419180532,
|
|
"loss": 6.1237,
|
|
"mean_token_accuracy": 0.1432718813419342,
|
|
"num_tokens": 3092553.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.260249090194702,
|
|
"epoch": 0.1555568035042399,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999788725775601,
|
|
"loss": 6.2522,
|
|
"mean_token_accuracy": 0.14531850293278695,
|
|
"num_tokens": 3102947.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.119967412948609,
|
|
"epoch": 0.15611838041219744,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999783188111737,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.14920552223920822,
|
|
"num_tokens": 3114157.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.029822540283203,
|
|
"epoch": 0.156679957320155,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999777578813904,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.1501602292060852,
|
|
"num_tokens": 3125739.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.111610746383667,
|
|
"epoch": 0.15724153422811254,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499977189788228,
|
|
"loss": 6.1285,
|
|
"mean_token_accuracy": 0.1495620235800743,
|
|
"num_tokens": 3136970.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.170126581192017,
|
|
"epoch": 0.1578031111360701,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999766145317046,
|
|
"loss": 6.0804,
|
|
"mean_token_accuracy": 0.15332209914922715,
|
|
"num_tokens": 3148512.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.112670230865478,
|
|
"epoch": 0.15836468804402762,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999760321118385,
|
|
"loss": 6.1281,
|
|
"mean_token_accuracy": 0.15459683984518052,
|
|
"num_tokens": 3159477.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.104544401168823,
|
|
"epoch": 0.15892626495198517,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999754425286483,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.14965095221996308,
|
|
"num_tokens": 3171361.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.267684602737427,
|
|
"epoch": 0.15948784185994272,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999748457821529,
|
|
"loss": 6.2915,
|
|
"mean_token_accuracy": 0.1418513722717762,
|
|
"num_tokens": 3184652.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.195340013504028,
|
|
"epoch": 0.16004941876790027,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499974241872371,
|
|
"loss": 6.1786,
|
|
"mean_token_accuracy": 0.14732735827565194,
|
|
"num_tokens": 3195557.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.219116926193237,
|
|
"epoch": 0.16061099567585782,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999736307993221,
|
|
"loss": 6.2129,
|
|
"mean_token_accuracy": 0.1357981599867344,
|
|
"num_tokens": 3207139.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.232678031921386,
|
|
"epoch": 0.16117257258381534,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999730125630255,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.14023263975977898,
|
|
"num_tokens": 3218967.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.271196174621582,
|
|
"epoch": 0.1617341494917729,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999723871635008,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.14901139065623284,
|
|
"num_tokens": 3230168.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.015722990036011,
|
|
"epoch": 0.16229572639973044,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999717546007681,
|
|
"loss": 6.1545,
|
|
"mean_token_accuracy": 0.14376315474510193,
|
|
"num_tokens": 3241829.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.264339351654053,
|
|
"epoch": 0.162857303307688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999711148748476,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.1445568896830082,
|
|
"num_tokens": 3253195.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.123285531997681,
|
|
"epoch": 0.16341888021564555,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999704679857594,
|
|
"loss": 6.2042,
|
|
"mean_token_accuracy": 0.13930154219269753,
|
|
"num_tokens": 3264951.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.061741495132447,
|
|
"epoch": 0.16398045712360307,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999698139335243,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.15055785626173018,
|
|
"num_tokens": 3276054.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.117865514755249,
|
|
"epoch": 0.16454203403156062,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999691527181632,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.15988054275512695,
|
|
"num_tokens": 3285540.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.181283855438233,
|
|
"epoch": 0.16510361093951817,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999684843396968,
|
|
"loss": 6.1457,
|
|
"mean_token_accuracy": 0.15024212151765823,
|
|
"num_tokens": 3296869.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.154390048980713,
|
|
"epoch": 0.16566518784747572,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999678087981467,
|
|
"loss": 6.0919,
|
|
"mean_token_accuracy": 0.15537651777267455,
|
|
"num_tokens": 3307554.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.024777555465699,
|
|
"epoch": 0.16622676475543324,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999671260935343,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.1448281340301037,
|
|
"num_tokens": 3319685.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.090826416015625,
|
|
"epoch": 0.1667883416633908,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999664362258814,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.1465357907116413,
|
|
"num_tokens": 3330742.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.111087989807129,
|
|
"epoch": 0.16734991857134834,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999657391952099,
|
|
"loss": 6.169,
|
|
"mean_token_accuracy": 0.1444841891527176,
|
|
"num_tokens": 3343613.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.308396863937378,
|
|
"epoch": 0.1679114954793059,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499965035001542,
|
|
"loss": 6.2148,
|
|
"mean_token_accuracy": 0.15076154470443726,
|
|
"num_tokens": 3355162.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.160010528564453,
|
|
"epoch": 0.16847307238726345,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999643236449001,
|
|
"loss": 6.1347,
|
|
"mean_token_accuracy": 0.15359269082546234,
|
|
"num_tokens": 3366324.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.283501052856446,
|
|
"epoch": 0.16903464929522097,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999636051253069,
|
|
"loss": 6.2882,
|
|
"mean_token_accuracy": 0.14009708762168885,
|
|
"num_tokens": 3378571.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.109706830978394,
|
|
"epoch": 0.16959622620317852,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999628794427854,
|
|
"loss": 6.168,
|
|
"mean_token_accuracy": 0.14259269535541536,
|
|
"num_tokens": 3390605.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.130779981613159,
|
|
"epoch": 0.17015780311113607,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999621465973583,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.15212171971797944,
|
|
"num_tokens": 3402735.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.165618658065796,
|
|
"epoch": 0.17071938001909362,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999614065890495,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.15175931602716447,
|
|
"num_tokens": 3413079.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.059429597854614,
|
|
"epoch": 0.17128095692705117,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999606594178821,
|
|
"loss": 6.037,
|
|
"mean_token_accuracy": 0.15060681253671646,
|
|
"num_tokens": 3423098.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.137203025817871,
|
|
"epoch": 0.1718425338350087,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00049995990508388,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.14952545762062072,
|
|
"num_tokens": 3435794.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.122977447509766,
|
|
"epoch": 0.17240411074296624,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999591435870674,
|
|
"loss": 6.2098,
|
|
"mean_token_accuracy": 0.14280164167284964,
|
|
"num_tokens": 3448125.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.121371603012085,
|
|
"epoch": 0.1729656876509238,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999583749274684,
|
|
"loss": 6.0418,
|
|
"mean_token_accuracy": 0.151399427652359,
|
|
"num_tokens": 3458217.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.071384716033935,
|
|
"epoch": 0.17352726455888134,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999575991051074,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.15133253037929534,
|
|
"num_tokens": 3469553.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.166380977630615,
|
|
"epoch": 0.1740888414668389,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999568161200093,
|
|
"loss": 6.0439,
|
|
"mean_token_accuracy": 0.1554693400859833,
|
|
"num_tokens": 3480928.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.097128963470459,
|
|
"epoch": 0.17465041837479642,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999560259721989,
|
|
"loss": 6.1325,
|
|
"mean_token_accuracy": 0.1535270929336548,
|
|
"num_tokens": 3492074.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.1337090015411375,
|
|
"epoch": 0.17521199528275397,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999552286617014,
|
|
"loss": 6.1384,
|
|
"mean_token_accuracy": 0.14494589790701867,
|
|
"num_tokens": 3503320.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.057374572753906,
|
|
"epoch": 0.17577357219071152,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004999544241885421,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.15341189801692962,
|
|
"num_tokens": 3515466.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.160209703445434,
|
|
"epoch": 0.17633514909866907,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999536125527467,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.1521401584148407,
|
|
"num_tokens": 3525584.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.019997692108154,
|
|
"epoch": 0.17689672600662662,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499952793754341,
|
|
"loss": 6.1022,
|
|
"mean_token_accuracy": 0.14772207736968995,
|
|
"num_tokens": 3536973.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.149301910400391,
|
|
"epoch": 0.17745830291458414,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999519677933512,
|
|
"loss": 6.1208,
|
|
"mean_token_accuracy": 0.14433789029717445,
|
|
"num_tokens": 3547799.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.182972002029419,
|
|
"epoch": 0.1780198798225417,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999511346698035,
|
|
"loss": 6.1857,
|
|
"mean_token_accuracy": 0.14982210397720336,
|
|
"num_tokens": 3558436.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.146703910827637,
|
|
"epoch": 0.17858145673049924,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999502943837244,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.14957652762532234,
|
|
"num_tokens": 3569851.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.185033321380615,
|
|
"epoch": 0.1791430336384568,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999494469351406,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.15206927061080933,
|
|
"num_tokens": 3580797.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.020595216751099,
|
|
"epoch": 0.17970461054641435,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999485923240793,
|
|
"loss": 6.0549,
|
|
"mean_token_accuracy": 0.15080841779708862,
|
|
"num_tokens": 3592552.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.074697542190552,
|
|
"epoch": 0.18026618745437187,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999477305505675,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.15332526564598084,
|
|
"num_tokens": 3603932.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.0842041015625,
|
|
"epoch": 0.18082776436232942,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999468616146328,
|
|
"loss": 6.0442,
|
|
"mean_token_accuracy": 0.16077973172068596,
|
|
"num_tokens": 3614865.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.924830675125122,
|
|
"epoch": 0.18138934127028697,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999459855163026,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.15816942751407623,
|
|
"num_tokens": 3626275.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.170416784286499,
|
|
"epoch": 0.18195091817824452,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499945102255605,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.14498920738697052,
|
|
"num_tokens": 3638416.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.96520586013794,
|
|
"epoch": 0.18251249508620204,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999442118325682,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.1536343052983284,
|
|
"num_tokens": 3649651.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.211764001846314,
|
|
"epoch": 0.1830740719941596,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999433142472205,
|
|
"loss": 6.1963,
|
|
"mean_token_accuracy": 0.15030549317598343,
|
|
"num_tokens": 3661172.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.097804975509644,
|
|
"epoch": 0.18363564890211714,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999424094995902,
|
|
"loss": 6.0371,
|
|
"mean_token_accuracy": 0.15204803496599198,
|
|
"num_tokens": 3672086.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.043741655349732,
|
|
"epoch": 0.1841972258100747,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999414975897066,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.1487807512283325,
|
|
"num_tokens": 3682579.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.1238837242126465,
|
|
"epoch": 0.18475880271803224,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999405785175983,
|
|
"loss": 6.1187,
|
|
"mean_token_accuracy": 0.1473942831158638,
|
|
"num_tokens": 3694616.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.982372426986695,
|
|
"epoch": 0.18532037962598977,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999396522832949,
|
|
"loss": 5.919,
|
|
"mean_token_accuracy": 0.15665805488824844,
|
|
"num_tokens": 3706821.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.029320240020752,
|
|
"epoch": 0.18588195653394732,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999387188868256,
|
|
"loss": 5.9732,
|
|
"mean_token_accuracy": 0.1571487694978714,
|
|
"num_tokens": 3717552.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.036300897598267,
|
|
"epoch": 0.18644353344190487,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999377783282203,
|
|
"loss": 6.0474,
|
|
"mean_token_accuracy": 0.14972800016403198,
|
|
"num_tokens": 3728300.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.082576656341553,
|
|
"epoch": 0.18700511034986242,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999368306075089,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.16109108030796052,
|
|
"num_tokens": 3738545.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.077401065826416,
|
|
"epoch": 0.18756668725781997,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999358757247215,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.15040296018123628,
|
|
"num_tokens": 3749190.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.0228570938110355,
|
|
"epoch": 0.1881282641657775,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999349136798886,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.15334153771400452,
|
|
"num_tokens": 3760978.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.990633153915406,
|
|
"epoch": 0.18868984107373504,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999339444730409,
|
|
"loss": 5.9467,
|
|
"mean_token_accuracy": 0.1572801098227501,
|
|
"num_tokens": 3771339.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.005237627029419,
|
|
"epoch": 0.1892514179816926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999329681042092,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.15659749656915664,
|
|
"num_tokens": 3781550.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.061115407943726,
|
|
"epoch": 0.18981299488965014,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999319845734243,
|
|
"loss": 6.1359,
|
|
"mean_token_accuracy": 0.14560328647494317,
|
|
"num_tokens": 3793700.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.180884456634521,
|
|
"epoch": 0.1903745717976077,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999309938807181,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.14918680638074874,
|
|
"num_tokens": 3806114.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.095144414901734,
|
|
"epoch": 0.19093614870556522,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999299960261216,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.1524960294365883,
|
|
"num_tokens": 3817251.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.046061992645264,
|
|
"epoch": 0.19149772561352277,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999289910096669,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.15111273676156997,
|
|
"num_tokens": 3828544.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.141667985916138,
|
|
"epoch": 0.19205930252148032,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999279788313858,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.14861491471529006,
|
|
"num_tokens": 3840423.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.044348049163818,
|
|
"epoch": 0.19262087942943787,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999269594913107,
|
|
"loss": 6.0097,
|
|
"mean_token_accuracy": 0.15253075659275056,
|
|
"num_tokens": 3852751.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.987351751327514,
|
|
"epoch": 0.19318245633739542,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999259329894739,
|
|
"loss": 6.0073,
|
|
"mean_token_accuracy": 0.15642097666859628,
|
|
"num_tokens": 3863382.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.021144962310791,
|
|
"epoch": 0.19374403324535294,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999248993259081,
|
|
"loss": 6.0064,
|
|
"mean_token_accuracy": 0.15451697632670403,
|
|
"num_tokens": 3874294.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.07633786201477,
|
|
"epoch": 0.1943056101533105,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999238585006463,
|
|
"loss": 6.0426,
|
|
"mean_token_accuracy": 0.14845188707113266,
|
|
"num_tokens": 3886693.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.009305143356324,
|
|
"epoch": 0.19486718706126804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999228105137218,
|
|
"loss": 5.9498,
|
|
"mean_token_accuracy": 0.15883688777685165,
|
|
"num_tokens": 3897755.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.021089506149292,
|
|
"epoch": 0.1954287639692256,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999217553651676,
|
|
"loss": 5.9524,
|
|
"mean_token_accuracy": 0.15532039254903793,
|
|
"num_tokens": 3909418.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.1032227039337155,
|
|
"epoch": 0.19599034087718312,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999206930550175,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.1495990239083767,
|
|
"num_tokens": 3919992.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.063982629776001,
|
|
"epoch": 0.19655191778514067,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999196235833054,
|
|
"loss": 5.9716,
|
|
"mean_token_accuracy": 0.1587469384074211,
|
|
"num_tokens": 3930648.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.948443031311035,
|
|
"epoch": 0.19711349469309822,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999185469500651,
|
|
"loss": 5.9572,
|
|
"mean_token_accuracy": 0.1576173797249794,
|
|
"num_tokens": 3941883.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.984550046920776,
|
|
"epoch": 0.19767507160105577,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499917463155331,
|
|
"loss": 6.004,
|
|
"mean_token_accuracy": 0.15634143352508545,
|
|
"num_tokens": 3952005.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.034853076934814,
|
|
"epoch": 0.19823664850901332,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999163721991378,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.15769157111644744,
|
|
"num_tokens": 3963720.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.936740970611572,
|
|
"epoch": 0.19879822541697084,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049991527408152,
|
|
"loss": 6.0118,
|
|
"mean_token_accuracy": 0.15719937086105346,
|
|
"num_tokens": 3974998.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.06788649559021,
|
|
"epoch": 0.1993598023249284,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999141688025127,
|
|
"loss": 6.0574,
|
|
"mean_token_accuracy": 0.14897572845220566,
|
|
"num_tokens": 3986469.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.033199405670166,
|
|
"epoch": 0.19992137923288594,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499913056362151,
|
|
"loss": 5.876,
|
|
"mean_token_accuracy": 0.15733214020729064,
|
|
"num_tokens": 3997553.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.917162466049194,
|
|
"epoch": 0.2004829561408435,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999119367604703,
|
|
"loss": 5.9558,
|
|
"mean_token_accuracy": 0.15673445910215378,
|
|
"num_tokens": 4008613.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.153360414505005,
|
|
"epoch": 0.20104453304880104,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999108099975064,
|
|
"loss": 6.1283,
|
|
"mean_token_accuracy": 0.1536238044500351,
|
|
"num_tokens": 4019860.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.023882675170898,
|
|
"epoch": 0.20160610995675857,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499909676073295,
|
|
"loss": 6.017,
|
|
"mean_token_accuracy": 0.15675632730126382,
|
|
"num_tokens": 4030602.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.985197401046753,
|
|
"epoch": 0.20216768686471612,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999085349878723,
|
|
"loss": 5.8936,
|
|
"mean_token_accuracy": 0.15248199701309204,
|
|
"num_tokens": 4041878.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.950754308700562,
|
|
"epoch": 0.20272926377267367,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999073867412746,
|
|
"loss": 5.9882,
|
|
"mean_token_accuracy": 0.1526031345129013,
|
|
"num_tokens": 4052799.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.037546443939209,
|
|
"epoch": 0.20329084068063122,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999062313335385,
|
|
"loss": 5.9902,
|
|
"mean_token_accuracy": 0.1529676452279091,
|
|
"num_tokens": 4064339.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.8854522705078125,
|
|
"epoch": 0.20385241758858877,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999050687647008,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.15455373972654343,
|
|
"num_tokens": 4076246.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.971135139465332,
|
|
"epoch": 0.2044139944965463,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999038990347984,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.1492105543613434,
|
|
"num_tokens": 4088006.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.113638019561767,
|
|
"epoch": 0.20497557140450384,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999027221438688,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.1529981389641762,
|
|
"num_tokens": 4098122.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.144082927703858,
|
|
"epoch": 0.2055371483124614,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499901538091949,
|
|
"loss": 6.2063,
|
|
"mean_token_accuracy": 0.1428961783647537,
|
|
"num_tokens": 4109958.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.17197060585022,
|
|
"epoch": 0.20609872522041894,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999003468790773,
|
|
"loss": 6.0981,
|
|
"mean_token_accuracy": 0.14817476719617845,
|
|
"num_tokens": 4121262.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.936773729324341,
|
|
"epoch": 0.2066603021283765,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998991485052911,
|
|
"loss": 5.8681,
|
|
"mean_token_accuracy": 0.16058467477560043,
|
|
"num_tokens": 4130958.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.0173663139343265,
|
|
"epoch": 0.20722187903633402,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499897942970629,
|
|
"loss": 6.0781,
|
|
"mean_token_accuracy": 0.14642804861068726,
|
|
"num_tokens": 4143779.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.1406467914581295,
|
|
"epoch": 0.20778345594429157,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499896730275129,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.14446378648281097,
|
|
"num_tokens": 4155367.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.987906074523925,
|
|
"epoch": 0.20834503285224912,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049989551041883,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.15731868371367455,
|
|
"num_tokens": 4166657.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.03128080368042,
|
|
"epoch": 0.20890660976020667,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998942834017707,
|
|
"loss": 6.0393,
|
|
"mean_token_accuracy": 0.14800393357872962,
|
|
"num_tokens": 4177517.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.982046890258789,
|
|
"epoch": 0.2094681866681642,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998930492239901,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.15527052879333497,
|
|
"num_tokens": 4188182.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.043006801605225,
|
|
"epoch": 0.21002976357612174,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998918078855277,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.15780879855155944,
|
|
"num_tokens": 4199415.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.954761743545532,
|
|
"epoch": 0.2105913404840793,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998905593864227,
|
|
"loss": 5.9667,
|
|
"mean_token_accuracy": 0.15191469490528106,
|
|
"num_tokens": 4210025.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.013121223449707,
|
|
"epoch": 0.21115291739203684,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998893037267153,
|
|
"loss": 5.8829,
|
|
"mean_token_accuracy": 0.15989519357681276,
|
|
"num_tokens": 4219920.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.9762413024902346,
|
|
"epoch": 0.2117144942999944,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998880409064452,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.15269239693880082,
|
|
"num_tokens": 4232647.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.130297899246216,
|
|
"epoch": 0.21227607120795192,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998867709256527,
|
|
"loss": 5.9489,
|
|
"mean_token_accuracy": 0.1568835824728012,
|
|
"num_tokens": 4242637.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.8553040504455565,
|
|
"epoch": 0.21283764811590947,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499885493784378,
|
|
"loss": 5.9229,
|
|
"mean_token_accuracy": 0.15738577097654344,
|
|
"num_tokens": 4253633.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.022933912277222,
|
|
"epoch": 0.21339922502386702,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998842094826621,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.15891942679882048,
|
|
"num_tokens": 4264472.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.982009840011597,
|
|
"epoch": 0.21396080193182457,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998829180205458,
|
|
"loss": 6.0074,
|
|
"mean_token_accuracy": 0.15923700332641602,
|
|
"num_tokens": 4275233.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.03095121383667,
|
|
"epoch": 0.21452237883978212,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998816193980701,
|
|
"loss": 5.9611,
|
|
"mean_token_accuracy": 0.15337118357419968,
|
|
"num_tokens": 4287063.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.989390468597412,
|
|
"epoch": 0.21508395574773964,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998803136152764,
|
|
"loss": 5.9785,
|
|
"mean_token_accuracy": 0.14854297190904617,
|
|
"num_tokens": 4298761.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.828275489807129,
|
|
"epoch": 0.2156455326556972,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998790006722063,
|
|
"loss": 5.8355,
|
|
"mean_token_accuracy": 0.16531981974840165,
|
|
"num_tokens": 4309650.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.0078376770019535,
|
|
"epoch": 0.21620710956365474,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998776805689016,
|
|
"loss": 5.9047,
|
|
"mean_token_accuracy": 0.16718189269304276,
|
|
"num_tokens": 4320403.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.839940357208252,
|
|
"epoch": 0.2167686864716123,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998763533054045,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.1600561797618866,
|
|
"num_tokens": 4332049.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.9344322681427,
|
|
"epoch": 0.21733026337956984,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998750188817568,
|
|
"loss": 5.8379,
|
|
"mean_token_accuracy": 0.1621323823928833,
|
|
"num_tokens": 4342551.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.97367901802063,
|
|
"epoch": 0.21789184028752737,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998736772980015,
|
|
"loss": 5.9608,
|
|
"mean_token_accuracy": 0.16004323810338975,
|
|
"num_tokens": 4355156.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.941838502883911,
|
|
"epoch": 0.21845341719548492,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499872328554181,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.15124871134757994,
|
|
"num_tokens": 4367402.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.041738891601563,
|
|
"epoch": 0.21901499410344247,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998709726503383,
|
|
"loss": 5.9018,
|
|
"mean_token_accuracy": 0.16085198670625686,
|
|
"num_tokens": 4378687.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.0037284851074215,
|
|
"epoch": 0.21957657101140002,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998696095865168,
|
|
"loss": 6.0324,
|
|
"mean_token_accuracy": 0.16538831740617752,
|
|
"num_tokens": 4388871.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.935435390472412,
|
|
"epoch": 0.22013814791935757,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998682393627595,
|
|
"loss": 5.861,
|
|
"mean_token_accuracy": 0.1636255994439125,
|
|
"num_tokens": 4399440.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.838962459564209,
|
|
"epoch": 0.2206997248273151,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998668619791104,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.16348468512296677,
|
|
"num_tokens": 4409989.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.090083599090576,
|
|
"epoch": 0.22126130173527264,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998654774356131,
|
|
"loss": 6.0124,
|
|
"mean_token_accuracy": 0.1552437886595726,
|
|
"num_tokens": 4422149.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.077429008483887,
|
|
"epoch": 0.2218228786432302,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998640857323118,
|
|
"loss": 6.0456,
|
|
"mean_token_accuracy": 0.15136015340685843,
|
|
"num_tokens": 4433157.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.002451324462891,
|
|
"epoch": 0.22238445555118774,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998626868692509,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.15625503659248352,
|
|
"num_tokens": 4444595.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.024257373809815,
|
|
"epoch": 0.2229460324591453,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998612808464748,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.15059059411287307,
|
|
"num_tokens": 4456592.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.03296799659729,
|
|
"epoch": 0.22350760936710282,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998598676640283,
|
|
"loss": 5.867,
|
|
"mean_token_accuracy": 0.17013804167509078,
|
|
"num_tokens": 4467624.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.895969343185425,
|
|
"epoch": 0.22406918627506037,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998584473219563,
|
|
"loss": 6.052,
|
|
"mean_token_accuracy": 0.15197935700416565,
|
|
"num_tokens": 4479766.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.083270072937012,
|
|
"epoch": 0.22463076318301792,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998570198203043,
|
|
"loss": 5.9056,
|
|
"mean_token_accuracy": 0.1571629002690315,
|
|
"num_tokens": 4490023.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.897563028335571,
|
|
"epoch": 0.22519234009097547,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998555851591175,
|
|
"loss": 5.9511,
|
|
"mean_token_accuracy": 0.15516175776720048,
|
|
"num_tokens": 4500651.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.082723474502563,
|
|
"epoch": 0.225753916998933,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998541433384416,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.15102613866329193,
|
|
"num_tokens": 4512934.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.9272867202758786,
|
|
"epoch": 0.22631549390689054,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998526943583226,
|
|
"loss": 5.9453,
|
|
"mean_token_accuracy": 0.15935770124197007,
|
|
"num_tokens": 4524251.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.003200340270996,
|
|
"epoch": 0.2268770708148481,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998512382188066,
|
|
"loss": 6.0203,
|
|
"mean_token_accuracy": 0.1512477733194828,
|
|
"num_tokens": 4536025.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.054232501983643,
|
|
"epoch": 0.22743864772280564,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998497749199401,
|
|
"loss": 5.9695,
|
|
"mean_token_accuracy": 0.15859290361404418,
|
|
"num_tokens": 4546717.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.903731346130371,
|
|
"epoch": 0.2280002246307632,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998483044617694,
|
|
"loss": 5.8621,
|
|
"mean_token_accuracy": 0.16061438173055648,
|
|
"num_tokens": 4557206.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.900349473953247,
|
|
"epoch": 0.22856180153872072,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998468268443416,
|
|
"loss": 5.8563,
|
|
"mean_token_accuracy": 0.16150960475206375,
|
|
"num_tokens": 4568123.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.986484718322754,
|
|
"epoch": 0.22912337844667827,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998453420677034,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.15943958312273027,
|
|
"num_tokens": 4579385.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.026423215866089,
|
|
"epoch": 0.22968495535463582,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998438501319025,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.15108214914798737,
|
|
"num_tokens": 4590514.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.957902145385742,
|
|
"epoch": 0.23024653226259337,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998423510369862,
|
|
"loss": 5.9695,
|
|
"mean_token_accuracy": 0.1499602884054184,
|
|
"num_tokens": 4601624.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.06238203048706,
|
|
"epoch": 0.23080810917055092,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998408447830022,
|
|
"loss": 5.9435,
|
|
"mean_token_accuracy": 0.1589498057961464,
|
|
"num_tokens": 4612822.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.938096332550049,
|
|
"epoch": 0.23136968607850844,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998393313699985,
|
|
"loss": 5.9516,
|
|
"mean_token_accuracy": 0.16269320100545884,
|
|
"num_tokens": 4623443.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.958241176605225,
|
|
"epoch": 0.231931262986466,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998378107980233,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.16247376054525375,
|
|
"num_tokens": 4633600.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.959673881530762,
|
|
"epoch": 0.23249283989442354,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998362830671249,
|
|
"loss": 6.0057,
|
|
"mean_token_accuracy": 0.15157989487051965,
|
|
"num_tokens": 4644217.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.015304946899414,
|
|
"epoch": 0.2330544168023811,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998347481773522,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.15409978926181794,
|
|
"num_tokens": 4654671.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.001746320724488,
|
|
"epoch": 0.23361599371033864,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998332061287538,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.15379573553800582,
|
|
"num_tokens": 4665920.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.931762742996216,
|
|
"epoch": 0.23417757061829617,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499831656921379,
|
|
"loss": 5.9091,
|
|
"mean_token_accuracy": 0.15680453628301622,
|
|
"num_tokens": 4675406.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.051575613021851,
|
|
"epoch": 0.23473914752625372,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499830100555277,
|
|
"loss": 5.9274,
|
|
"mean_token_accuracy": 0.16170108020305635,
|
|
"num_tokens": 4686870.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.986575174331665,
|
|
"epoch": 0.23530072443421127,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998285370304974,
|
|
"loss": 6.0236,
|
|
"mean_token_accuracy": 0.15555590838193895,
|
|
"num_tokens": 4698926.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.053481721878052,
|
|
"epoch": 0.23586230134216882,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049982696634709,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.1449894279241562,
|
|
"num_tokens": 4709318.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.874515628814697,
|
|
"epoch": 0.23642387825012637,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998253885051048,
|
|
"loss": 5.7865,
|
|
"mean_token_accuracy": 0.17088475227355956,
|
|
"num_tokens": 4718819.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.872879409790039,
|
|
"epoch": 0.2369854551580839,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499823803504592,
|
|
"loss": 5.8319,
|
|
"mean_token_accuracy": 0.165112866461277,
|
|
"num_tokens": 4729513.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.943530511856079,
|
|
"epoch": 0.23754703206604144,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998222113456022,
|
|
"loss": 5.935,
|
|
"mean_token_accuracy": 0.15231743901968003,
|
|
"num_tokens": 4739875.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.088411569595337,
|
|
"epoch": 0.238108608973999,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998206120281858,
|
|
"loss": 6.0438,
|
|
"mean_token_accuracy": 0.15248556584119796,
|
|
"num_tokens": 4752933.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.917099142074585,
|
|
"epoch": 0.23867018588195654,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499819005552394,
|
|
"loss": 5.84,
|
|
"mean_token_accuracy": 0.16093057990074158,
|
|
"num_tokens": 4762969.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.932834434509277,
|
|
"epoch": 0.23923176278991407,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998173919182779,
|
|
"loss": 5.9482,
|
|
"mean_token_accuracy": 0.15672307163476945,
|
|
"num_tokens": 4773495.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.969760227203369,
|
|
"epoch": 0.23979333969787162,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499815771125889,
|
|
"loss": 5.9697,
|
|
"mean_token_accuracy": 0.1630027860403061,
|
|
"num_tokens": 4785335.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.086810684204101,
|
|
"epoch": 0.24035491660582917,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998141431752785,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.15253835916519165,
|
|
"num_tokens": 4798068.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.0190082550048825,
|
|
"epoch": 0.24091649351378672,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998125080664987,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.16539788246154785,
|
|
"num_tokens": 4809338.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.937499141693115,
|
|
"epoch": 0.24147807042174427,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998108657996012,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.15961964651942254,
|
|
"num_tokens": 4819636.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.9000465869903564,
|
|
"epoch": 0.2420396473297018,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998092163746387,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.15810615718364715,
|
|
"num_tokens": 4830975.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.922979879379272,
|
|
"epoch": 0.24260122423765934,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998075597916636,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.15569430440664292,
|
|
"num_tokens": 4841951.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.041098976135254,
|
|
"epoch": 0.2431628011456169,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998058960507286,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.16229601576924324,
|
|
"num_tokens": 4852919.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.922900772094726,
|
|
"epoch": 0.24372437805357444,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998042251518866,
|
|
"loss": 5.9418,
|
|
"mean_token_accuracy": 0.15963752567768097,
|
|
"num_tokens": 4863433.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.997221231460571,
|
|
"epoch": 0.244285954961532,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998025470951908,
|
|
"loss": 6.0079,
|
|
"mean_token_accuracy": 0.15224221497774124,
|
|
"num_tokens": 4875685.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.946529865264893,
|
|
"epoch": 0.24484753186948952,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998008618806949,
|
|
"loss": 5.9148,
|
|
"mean_token_accuracy": 0.1580193430185318,
|
|
"num_tokens": 4886347.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.936647653579712,
|
|
"epoch": 0.24540910877744707,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997991695084523,
|
|
"loss": 5.9116,
|
|
"mean_token_accuracy": 0.16283671855926513,
|
|
"num_tokens": 4896898.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.9814536571502686,
|
|
"epoch": 0.24597068568540462,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997974699785169,
|
|
"loss": 5.9969,
|
|
"mean_token_accuracy": 0.1565718963742256,
|
|
"num_tokens": 4908892.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.995170927047729,
|
|
"epoch": 0.24653226259336217,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997957632909429,
|
|
"loss": 5.953,
|
|
"mean_token_accuracy": 0.15219104290008545,
|
|
"num_tokens": 4920855.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.939112997055053,
|
|
"epoch": 0.24709383950131972,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997940494457846,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.1611930876970291,
|
|
"num_tokens": 4932857.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.920130109786987,
|
|
"epoch": 0.24765541640927724,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997923284430967,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.157567498087883,
|
|
"num_tokens": 4944063.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.916885423660278,
|
|
"epoch": 0.2482169933172348,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997906002829338,
|
|
"loss": 5.8422,
|
|
"mean_token_accuracy": 0.16268620938062667,
|
|
"num_tokens": 4955126.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.011972093582154,
|
|
"epoch": 0.24877857022519234,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499788864965351,
|
|
"loss": 6.0297,
|
|
"mean_token_accuracy": 0.1572894498705864,
|
|
"num_tokens": 4965738.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.104279661178589,
|
|
"epoch": 0.2493401471331499,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997871224904036,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.1530898168683052,
|
|
"num_tokens": 4976963.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.95416898727417,
|
|
"epoch": 0.24990172404110744,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997853728581468,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.15562186539173126,
|
|
"num_tokens": 4987577.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.972849702835083,
|
|
"epoch": 0.250463300949065,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997836160686368,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.15612355023622512,
|
|
"num_tokens": 5000234.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.0028489112854,
|
|
"epoch": 0.25102487785702254,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997818521219291,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.1534307286143303,
|
|
"num_tokens": 5011652.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.960933828353882,
|
|
"epoch": 0.25158645476498004,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997800810180803,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.15806746035814284,
|
|
"num_tokens": 5023603.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.890470409393311,
|
|
"epoch": 0.2521480316729376,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997783027571464,
|
|
"loss": 5.9027,
|
|
"mean_token_accuracy": 0.16501567810773848,
|
|
"num_tokens": 5034427.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.9391638278961185,
|
|
"epoch": 0.25270960858089514,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997765173391841,
|
|
"loss": 5.8942,
|
|
"mean_token_accuracy": 0.16304780095815657,
|
|
"num_tokens": 5045738.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.828226089477539,
|
|
"epoch": 0.2532711854888527,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997747247642505,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.15862570255994796,
|
|
"num_tokens": 5057021.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.92571177482605,
|
|
"epoch": 0.25383276239681024,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997729250324023,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.1542244702577591,
|
|
"num_tokens": 5067676.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.909444570541382,
|
|
"epoch": 0.2543943393047678,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997711181436971,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.16087970584630967,
|
|
"num_tokens": 5079422.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.894988298416138,
|
|
"epoch": 0.25495591621272534,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997693040981922,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.160662043094635,
|
|
"num_tokens": 5091242.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.955714464187622,
|
|
"epoch": 0.2555174931206829,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997674828959456,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.15537350177764891,
|
|
"num_tokens": 5102251.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.890719270706176,
|
|
"epoch": 0.25607907002864044,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004997656545370151,
|
|
"loss": 5.9183,
|
|
"mean_token_accuracy": 0.16142252534627916,
|
|
"num_tokens": 5113276.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.97783522605896,
|
|
"epoch": 0.256640646936598,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499763819021459,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.15958033353090287,
|
|
"num_tokens": 5124472.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.908177518844605,
|
|
"epoch": 0.2572022238445555,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997619763493357,
|
|
"loss": 5.86,
|
|
"mean_token_accuracy": 0.1621762201189995,
|
|
"num_tokens": 5134896.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.960345888137818,
|
|
"epoch": 0.25776380075251304,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499760126520704,
|
|
"loss": 5.9422,
|
|
"mean_token_accuracy": 0.16326863765716554,
|
|
"num_tokens": 5145115.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.935664415359497,
|
|
"epoch": 0.2583253776604706,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997582695356225,
|
|
"loss": 5.8934,
|
|
"mean_token_accuracy": 0.16419054567813873,
|
|
"num_tokens": 5155620.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.026849174499512,
|
|
"epoch": 0.25888695456842814,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997564053941507,
|
|
"loss": 5.9954,
|
|
"mean_token_accuracy": 0.15510585457086562,
|
|
"num_tokens": 5166260.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.943055200576782,
|
|
"epoch": 0.2594485314763857,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997545340963478,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.15928099900484086,
|
|
"num_tokens": 5177143.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.971165609359741,
|
|
"epoch": 0.26001010838434324,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997526556422733,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.15262550860643387,
|
|
"num_tokens": 5187795.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.947878408432007,
|
|
"epoch": 0.2605716852923008,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997507700319872,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.16017002314329148,
|
|
"num_tokens": 5199365.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.992268705368042,
|
|
"epoch": 0.26113326220025834,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997488772655492,
|
|
"loss": 6.097,
|
|
"mean_token_accuracy": 0.1522466480731964,
|
|
"num_tokens": 5212264.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.11021203994751,
|
|
"epoch": 0.2616948391082159,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997469773430199,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.1561689630150795,
|
|
"num_tokens": 5223544.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.8078991889953615,
|
|
"epoch": 0.2622564160161734,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997450702644596,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.16755220293998718,
|
|
"num_tokens": 5234713.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.004143762588501,
|
|
"epoch": 0.26281799292413094,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997431560299292,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.15500690788030624,
|
|
"num_tokens": 5246103.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.804888391494751,
|
|
"epoch": 0.2633795698320885,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997412346394894,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.16899138689041138,
|
|
"num_tokens": 5257372.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.825739240646362,
|
|
"epoch": 0.26394114674004604,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997393060932017,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.16804155260324477,
|
|
"num_tokens": 5268677.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.981194734573364,
|
|
"epoch": 0.2645027236480036,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997373703911273,
|
|
"loss": 5.9211,
|
|
"mean_token_accuracy": 0.16036693155765533,
|
|
"num_tokens": 5279056.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.791534566879273,
|
|
"epoch": 0.26506430055596114,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997354275333277,
|
|
"loss": 5.8086,
|
|
"mean_token_accuracy": 0.16567573547363282,
|
|
"num_tokens": 5289310.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.013248252868652,
|
|
"epoch": 0.2656258774639187,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499733477519865,
|
|
"loss": 5.8963,
|
|
"mean_token_accuracy": 0.16800552755594253,
|
|
"num_tokens": 5300619.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.035416316986084,
|
|
"epoch": 0.26618745437187624,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997315203508013,
|
|
"loss": 6.0486,
|
|
"mean_token_accuracy": 0.15519964396953584,
|
|
"num_tokens": 5311554.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.981985998153687,
|
|
"epoch": 0.2667490312798338,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997295560261988,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.16367268562316895,
|
|
"num_tokens": 5323592.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.978114938735962,
|
|
"epoch": 0.26731060818779134,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049972758454612,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.15567181259393692,
|
|
"num_tokens": 5334978.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.869251680374146,
|
|
"epoch": 0.26787218509574884,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997256059106279,
|
|
"loss": 5.8687,
|
|
"mean_token_accuracy": 0.15930577069520951,
|
|
"num_tokens": 5345724.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.983371686935425,
|
|
"epoch": 0.2684337620037064,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997236201197853,
|
|
"loss": 5.9829,
|
|
"mean_token_accuracy": 0.15415222197771072,
|
|
"num_tokens": 5357141.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.8907865524292,
|
|
"epoch": 0.26899533891166394,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997216271736554,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.1598132699728012,
|
|
"num_tokens": 5367889.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.8703772068023685,
|
|
"epoch": 0.2695569158196215,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997196270723018,
|
|
"loss": 5.7156,
|
|
"mean_token_accuracy": 0.16515835821628572,
|
|
"num_tokens": 5379329.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.878870630264283,
|
|
"epoch": 0.27011849272757904,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997176198157881,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.16479273587465287,
|
|
"num_tokens": 5389525.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.872372484207153,
|
|
"epoch": 0.2706800696355366,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997156054041781,
|
|
"loss": 5.791,
|
|
"mean_token_accuracy": 0.16410698741674423,
|
|
"num_tokens": 5401061.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.8996857643127445,
|
|
"epoch": 0.27124164654349414,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997135838375362,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.16323280036449433,
|
|
"num_tokens": 5411791.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.924712800979615,
|
|
"epoch": 0.2718032234514517,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997115551159267,
|
|
"loss": 5.8386,
|
|
"mean_token_accuracy": 0.16478586345911025,
|
|
"num_tokens": 5422790.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.759177160263062,
|
|
"epoch": 0.27236480035940924,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499709519239414,
|
|
"loss": 5.7834,
|
|
"mean_token_accuracy": 0.16483882069587708,
|
|
"num_tokens": 5434170.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.053406143188477,
|
|
"epoch": 0.2729263772673668,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004997074762080632,
|
|
"loss": 5.9184,
|
|
"mean_token_accuracy": 0.1545036256313324,
|
|
"num_tokens": 5445948.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.891904878616333,
|
|
"epoch": 0.2734879541753243,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499705426021939,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.15728461295366286,
|
|
"num_tokens": 5457786.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.781130790710449,
|
|
"epoch": 0.27404953108328184,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499703368681107,
|
|
"loss": 5.8408,
|
|
"mean_token_accuracy": 0.1613198235630989,
|
|
"num_tokens": 5469434.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.9204620838165285,
|
|
"epoch": 0.2746111079912394,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997013041856326,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.1561868131160736,
|
|
"num_tokens": 5480393.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.874335432052613,
|
|
"epoch": 0.27517268489919694,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996992325355815,
|
|
"loss": 5.8282,
|
|
"mean_token_accuracy": 0.16535558551549911,
|
|
"num_tokens": 5490452.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.791786336898804,
|
|
"epoch": 0.2757342618071545,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996971537310198,
|
|
"loss": 5.7938,
|
|
"mean_token_accuracy": 0.1647621661424637,
|
|
"num_tokens": 5501404.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.994299411773682,
|
|
"epoch": 0.27629583871511204,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996950677720133,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.15404624938964845,
|
|
"num_tokens": 5512938.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.8537561893463135,
|
|
"epoch": 0.2768574156230696,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499692974658629,
|
|
"loss": 5.8529,
|
|
"mean_token_accuracy": 0.1536116473376751,
|
|
"num_tokens": 5524009.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.983808088302612,
|
|
"epoch": 0.27741899253102714,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996908743909331,
|
|
"loss": 5.9422,
|
|
"mean_token_accuracy": 0.15818442404270172,
|
|
"num_tokens": 5535930.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.950139951705933,
|
|
"epoch": 0.2779805694389847,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996887669689926,
|
|
"loss": 5.9345,
|
|
"mean_token_accuracy": 0.15633012354373932,
|
|
"num_tokens": 5547295.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.969197559356689,
|
|
"epoch": 0.2785421463469422,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996866523928747,
|
|
"loss": 5.8346,
|
|
"mean_token_accuracy": 0.16864263713359834,
|
|
"num_tokens": 5558447.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.92009596824646,
|
|
"epoch": 0.27910372325489974,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996845306626467,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.1618420287966728,
|
|
"num_tokens": 5569822.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.958059930801392,
|
|
"epoch": 0.2796653001628573,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996824017783759,
|
|
"loss": 5.9856,
|
|
"mean_token_accuracy": 0.15708132237195968,
|
|
"num_tokens": 5582284.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.984194135665893,
|
|
"epoch": 0.28022687707081484,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996802657401304,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.163690784573555,
|
|
"num_tokens": 5593765.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.780626010894776,
|
|
"epoch": 0.2807884539787724,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996781225479781,
|
|
"loss": 5.8481,
|
|
"mean_token_accuracy": 0.1617444708943367,
|
|
"num_tokens": 5605080.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.99798469543457,
|
|
"epoch": 0.28135003088672994,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996759722019872,
|
|
"loss": 6.0017,
|
|
"mean_token_accuracy": 0.15487387031316757,
|
|
"num_tokens": 5616739.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.904121208190918,
|
|
"epoch": 0.2819116077946875,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996738147022262,
|
|
"loss": 5.8621,
|
|
"mean_token_accuracy": 0.15306745395064353,
|
|
"num_tokens": 5628779.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.885381984710693,
|
|
"epoch": 0.28247318470264504,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996716500487638,
|
|
"loss": 5.8984,
|
|
"mean_token_accuracy": 0.1586427852511406,
|
|
"num_tokens": 5639168.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.909733247756958,
|
|
"epoch": 0.2830347616106026,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499669478241669,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.15645023584365844,
|
|
"num_tokens": 5650739.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.885955667495727,
|
|
"epoch": 0.28359633851856014,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996672992810108,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.15876920521259308,
|
|
"num_tokens": 5662630.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.927337265014648,
|
|
"epoch": 0.28415791542651764,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996651131668587,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.16869498640298844,
|
|
"num_tokens": 5673473.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.940307760238648,
|
|
"epoch": 0.2847194923344752,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996629198992823,
|
|
"loss": 6.0388,
|
|
"mean_token_accuracy": 0.150181782245636,
|
|
"num_tokens": 5686577.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.947848510742188,
|
|
"epoch": 0.28528106924243274,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996607194783513,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.16303919181227683,
|
|
"num_tokens": 5697570.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.871793365478515,
|
|
"epoch": 0.2858426461503903,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996585119041359,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.15702579021453858,
|
|
"num_tokens": 5708601.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.792822456359863,
|
|
"epoch": 0.28640422305834784,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996562971767063,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.16065748929977416,
|
|
"num_tokens": 5719619.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.899547290802002,
|
|
"epoch": 0.2869657999663054,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499654075296133,
|
|
"loss": 5.8429,
|
|
"mean_token_accuracy": 0.16420732587575912,
|
|
"num_tokens": 5730061.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.912689304351806,
|
|
"epoch": 0.28752737687426294,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499651846262487,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.1673080876469612,
|
|
"num_tokens": 5741579.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.8733302593231205,
|
|
"epoch": 0.2880889537822205,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996496100758389,
|
|
"loss": 5.8671,
|
|
"mean_token_accuracy": 0.16228052973747253,
|
|
"num_tokens": 5754001.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.9434535026550295,
|
|
"epoch": 0.28865053069017804,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996473667362604,
|
|
"loss": 5.9618,
|
|
"mean_token_accuracy": 0.1558829851448536,
|
|
"num_tokens": 5766224.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.918426132202148,
|
|
"epoch": 0.28921210759813554,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996451162438224,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.15533761382102967,
|
|
"num_tokens": 5777475.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.021241569519043,
|
|
"epoch": 0.2897736845060931,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996428585985967,
|
|
"loss": 5.9082,
|
|
"mean_token_accuracy": 0.15379685014486313,
|
|
"num_tokens": 5788359.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.839427900314331,
|
|
"epoch": 0.29033526141405064,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996405938006553,
|
|
"loss": 5.8604,
|
|
"mean_token_accuracy": 0.16365527361631393,
|
|
"num_tokens": 5799116.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.8858864307403564,
|
|
"epoch": 0.2908968383220082,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996383218500703,
|
|
"loss": 5.8009,
|
|
"mean_token_accuracy": 0.16506671160459518,
|
|
"num_tokens": 5811221.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.835213947296142,
|
|
"epoch": 0.29145841522996574,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499636042746914,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.16208941340446473,
|
|
"num_tokens": 5822099.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.913222026824951,
|
|
"epoch": 0.2920199921379233,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499633756491259,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.15887113511562348,
|
|
"num_tokens": 5832836.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.820470571517944,
|
|
"epoch": 0.29258156904588084,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996314630831781,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.15489693582057953,
|
|
"num_tokens": 5842892.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.879719972610474,
|
|
"epoch": 0.2931431459538384,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996291625227443,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.17257018089294435,
|
|
"num_tokens": 5852909.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.919102716445923,
|
|
"epoch": 0.29370472286179594,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996268548100307,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.15507653206586838,
|
|
"num_tokens": 5864676.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.755217504501343,
|
|
"epoch": 0.2942662997697535,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499624539945111,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.17032847702503204,
|
|
"num_tokens": 5875258.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.909181356430054,
|
|
"epoch": 0.294827876677711,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996222179280589,
|
|
"loss": 5.8435,
|
|
"mean_token_accuracy": 0.16484241038560868,
|
|
"num_tokens": 5885611.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.845112323760986,
|
|
"epoch": 0.29538945358566854,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996198887589481,
|
|
"loss": 5.804,
|
|
"mean_token_accuracy": 0.16185440346598626,
|
|
"num_tokens": 5896726.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.90363187789917,
|
|
"epoch": 0.2959510304936261,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996175524378531,
|
|
"loss": 5.836,
|
|
"mean_token_accuracy": 0.1556556850671768,
|
|
"num_tokens": 5907860.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.824535226821899,
|
|
"epoch": 0.29651260740158364,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499615208964848,
|
|
"loss": 5.7633,
|
|
"mean_token_accuracy": 0.16664294600486756,
|
|
"num_tokens": 5918676.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.854987764358521,
|
|
"epoch": 0.2970741843095412,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996128583400077,
|
|
"loss": 5.8401,
|
|
"mean_token_accuracy": 0.1673136442899704,
|
|
"num_tokens": 5928646.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.853833866119385,
|
|
"epoch": 0.29763576121749874,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996105005634066,
|
|
"loss": 5.8502,
|
|
"mean_token_accuracy": 0.16196250915527344,
|
|
"num_tokens": 5938990.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.856926727294922,
|
|
"epoch": 0.2981973381254563,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996081356351202,
|
|
"loss": 5.7999,
|
|
"mean_token_accuracy": 0.16858235150575637,
|
|
"num_tokens": 5948811.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.798100328445434,
|
|
"epoch": 0.29875891503341384,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996057635552237,
|
|
"loss": 5.8268,
|
|
"mean_token_accuracy": 0.16800669431686402,
|
|
"num_tokens": 5959227.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.866962957382202,
|
|
"epoch": 0.2993204919413714,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996033843237925,
|
|
"loss": 5.748,
|
|
"mean_token_accuracy": 0.1633942097425461,
|
|
"num_tokens": 5970546.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.948568105697632,
|
|
"epoch": 0.29988206884932894,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996009979409025,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.15058949068188668,
|
|
"num_tokens": 5983936.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.829497051239014,
|
|
"epoch": 0.30044364575728644,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995986044066295,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.15705229640007018,
|
|
"num_tokens": 5994963.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.724363040924072,
|
|
"epoch": 0.301005222665244,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00049959620372105,
|
|
"loss": 5.7848,
|
|
"mean_token_accuracy": 0.1620802253484726,
|
|
"num_tokens": 6005836.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.882124423980713,
|
|
"epoch": 0.30156679957320154,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995937958842401,
|
|
"loss": 5.7842,
|
|
"mean_token_accuracy": 0.16714142858982087,
|
|
"num_tokens": 6017408.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.831092786788941,
|
|
"epoch": 0.3021283764811591,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995913808962767,
|
|
"loss": 5.7877,
|
|
"mean_token_accuracy": 0.162654872238636,
|
|
"num_tokens": 6029281.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.836739444732666,
|
|
"epoch": 0.30268995338911664,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995889587572366,
|
|
"loss": 5.7974,
|
|
"mean_token_accuracy": 0.171444633603096,
|
|
"num_tokens": 6039354.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.8621213912963865,
|
|
"epoch": 0.3032515302970742,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499586529467197,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.16184911429882048,
|
|
"num_tokens": 6050053.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.8485065460205075,
|
|
"epoch": 0.30381310720503174,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995840930262351,
|
|
"loss": 5.8236,
|
|
"mean_token_accuracy": 0.1607857584953308,
|
|
"num_tokens": 6060221.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.851527500152588,
|
|
"epoch": 0.3043746841129893,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995816494344287,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.16010224372148513,
|
|
"num_tokens": 6070963.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.9478880882263185,
|
|
"epoch": 0.30493626102094684,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995791986918554,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.1615760624408722,
|
|
"num_tokens": 6082028.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.897542142868042,
|
|
"epoch": 0.30549783792890434,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995767407985933,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.16264641284942627,
|
|
"num_tokens": 6092778.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.689213371276855,
|
|
"epoch": 0.3060594148368619,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995742757547207,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.17164971232414244,
|
|
"num_tokens": 6103093.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.817043876647949,
|
|
"epoch": 0.30662099174481944,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499571803560316,
|
|
"loss": 5.7244,
|
|
"mean_token_accuracy": 0.16921960562467575,
|
|
"num_tokens": 6113516.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.806196832656861,
|
|
"epoch": 0.307182568652777,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995693242154581,
|
|
"loss": 5.7965,
|
|
"mean_token_accuracy": 0.16070803254842758,
|
|
"num_tokens": 6125723.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.849681663513183,
|
|
"epoch": 0.30774414556073454,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995668377202258,
|
|
"loss": 5.7988,
|
|
"mean_token_accuracy": 0.16376324146986007,
|
|
"num_tokens": 6137091.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.76956524848938,
|
|
"epoch": 0.3083057224686921,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995643440746982,
|
|
"loss": 5.7289,
|
|
"mean_token_accuracy": 0.17301594614982604,
|
|
"num_tokens": 6147941.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.743298673629761,
|
|
"epoch": 0.30886729937664964,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995618432789548,
|
|
"loss": 5.7378,
|
|
"mean_token_accuracy": 0.1669941335916519,
|
|
"num_tokens": 6158493.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.804452991485595,
|
|
"epoch": 0.3094288762846072,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995593353330753,
|
|
"loss": 5.8589,
|
|
"mean_token_accuracy": 0.16288769990205765,
|
|
"num_tokens": 6170759.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.855029296875,
|
|
"epoch": 0.30999045319256474,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995568202371393,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.16882307976484298,
|
|
"num_tokens": 6182488.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.854329395294189,
|
|
"epoch": 0.3105520301005223,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995542979912272,
|
|
"loss": 5.891,
|
|
"mean_token_accuracy": 0.15524321794509888,
|
|
"num_tokens": 6193849.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.789872646331787,
|
|
"epoch": 0.3111136070084798,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995517685954192,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.16951252967119218,
|
|
"num_tokens": 6204132.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.9421745300292965,
|
|
"epoch": 0.31167518391643734,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995492320497958,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.1572794422507286,
|
|
"num_tokens": 6215547.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.9671179294586185,
|
|
"epoch": 0.3122367608243949,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995466883544376,
|
|
"loss": 5.9168,
|
|
"mean_token_accuracy": 0.15148334205150604,
|
|
"num_tokens": 6227150.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.834510707855225,
|
|
"epoch": 0.31279833773235244,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995441375094258,
|
|
"loss": 5.911,
|
|
"mean_token_accuracy": 0.16446434408426286,
|
|
"num_tokens": 6237387.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.939399671554566,
|
|
"epoch": 0.31335991464031,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995415795148417,
|
|
"loss": 5.8125,
|
|
"mean_token_accuracy": 0.16512976735830306,
|
|
"num_tokens": 6248623.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.766932392120362,
|
|
"epoch": 0.31392149154826754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995390143707665,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.1762712210416794,
|
|
"num_tokens": 6258596.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.81198902130127,
|
|
"epoch": 0.3144830684562251,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995364420772821,
|
|
"loss": 5.935,
|
|
"mean_token_accuracy": 0.15414962992072107,
|
|
"num_tokens": 6270529.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.066451454162598,
|
|
"epoch": 0.31504464536418264,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995338626344702,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.16282169967889787,
|
|
"num_tokens": 6280891.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.736438417434693,
|
|
"epoch": 0.3156062222721402,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499531276042413,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.15952381491661072,
|
|
"num_tokens": 6292247.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.746332216262817,
|
|
"epoch": 0.31616779918009774,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995286823011929,
|
|
"loss": 5.7661,
|
|
"mean_token_accuracy": 0.16169815212488176,
|
|
"num_tokens": 6302403.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.739615869522095,
|
|
"epoch": 0.31672937608805524,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995260814108926,
|
|
"loss": 5.6451,
|
|
"mean_token_accuracy": 0.17269758135080338,
|
|
"num_tokens": 6313901.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.937485456466675,
|
|
"epoch": 0.3172909529960128,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995234733715947,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.16334352642297745,
|
|
"num_tokens": 6323711.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.813136100769043,
|
|
"epoch": 0.31785252990397034,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995208581833824,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.16345760077238083,
|
|
"num_tokens": 6334937.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.919223499298096,
|
|
"epoch": 0.3184141068119279,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995182358463388,
|
|
"loss": 5.8575,
|
|
"mean_token_accuracy": 0.16153930276632308,
|
|
"num_tokens": 6345723.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.8121337890625,
|
|
"epoch": 0.31897568371988544,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995156063605475,
|
|
"loss": 5.8015,
|
|
"mean_token_accuracy": 0.1603420630097389,
|
|
"num_tokens": 6357573.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.871078062057495,
|
|
"epoch": 0.319537260627843,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995129697260922,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.16848725825548172,
|
|
"num_tokens": 6367417.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.8781421184539795,
|
|
"epoch": 0.32009883753580054,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995103259430569,
|
|
"loss": 5.8276,
|
|
"mean_token_accuracy": 0.16959178149700166,
|
|
"num_tokens": 6377753.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.828861999511719,
|
|
"epoch": 0.3206604144437581,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995076750115258,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.16387695223093032,
|
|
"num_tokens": 6388613.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.8316224098205565,
|
|
"epoch": 0.32122199135171564,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995050169315832,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.1644709199666977,
|
|
"num_tokens": 6399415.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.866077947616577,
|
|
"epoch": 0.32178356825967314,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995023517033138,
|
|
"loss": 5.8072,
|
|
"mean_token_accuracy": 0.16304630041122437,
|
|
"num_tokens": 6411435.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.856478118896485,
|
|
"epoch": 0.3223451451676307,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994996793268024,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.16070206016302108,
|
|
"num_tokens": 6423030.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.8936666488647464,
|
|
"epoch": 0.32290672207558824,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994969998021342,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.1634832188487053,
|
|
"num_tokens": 6434330.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.910007047653198,
|
|
"epoch": 0.3234682989835458,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994943131293944,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.1616750717163086,
|
|
"num_tokens": 6446452.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.813801622390747,
|
|
"epoch": 0.32402987589150334,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994916193086687,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.16977857053279877,
|
|
"num_tokens": 6456723.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.856975555419922,
|
|
"epoch": 0.3245914527994609,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994889183400428,
|
|
"loss": 5.9158,
|
|
"mean_token_accuracy": 0.15541210025548935,
|
|
"num_tokens": 6468117.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.875374364852905,
|
|
"epoch": 0.32515302970741844,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994862102236025,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.16900594830513,
|
|
"num_tokens": 6479465.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.878074026107788,
|
|
"epoch": 0.325714606615376,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994834949594342,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.16639080941677092,
|
|
"num_tokens": 6490868.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.9626843452453615,
|
|
"epoch": 0.32627618352333354,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994807725476246,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.16306480169296264,
|
|
"num_tokens": 6502126.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.729597043991089,
|
|
"epoch": 0.3268377604312911,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994780429882599,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.15703100711107254,
|
|
"num_tokens": 6514382.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.896344518661499,
|
|
"epoch": 0.3273993373392486,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994753062814274,
|
|
"loss": 5.7714,
|
|
"mean_token_accuracy": 0.16577536463737488,
|
|
"num_tokens": 6526272.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.8439172267913815,
|
|
"epoch": 0.32796091424720614,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994725624272139,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.1664314329624176,
|
|
"num_tokens": 6537511.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.755551195144653,
|
|
"epoch": 0.3285224911551637,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994698114257071,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.16514882296323777,
|
|
"num_tokens": 6549737.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.780179738998413,
|
|
"epoch": 0.32908406806312124,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994670532769944,
|
|
"loss": 5.8268,
|
|
"mean_token_accuracy": 0.1637934371829033,
|
|
"num_tokens": 6560318.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.810793733596801,
|
|
"epoch": 0.3296456449710788,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994642879811637,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.16960348188877106,
|
|
"num_tokens": 6570575.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.7971124172210695,
|
|
"epoch": 0.33020722187903634,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499461515538303,
|
|
"loss": 5.7894,
|
|
"mean_token_accuracy": 0.15714770257472993,
|
|
"num_tokens": 6582083.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.988094854354858,
|
|
"epoch": 0.3307687987869939,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994587359485006,
|
|
"loss": 5.9175,
|
|
"mean_token_accuracy": 0.16404277086257935,
|
|
"num_tokens": 6592240.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.789616870880127,
|
|
"epoch": 0.33133037569495144,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499455949211845,
|
|
"loss": 5.7105,
|
|
"mean_token_accuracy": 0.16835165172815322,
|
|
"num_tokens": 6602680.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.819018793106079,
|
|
"epoch": 0.331891952602909,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994531553284248,
|
|
"loss": 5.8154,
|
|
"mean_token_accuracy": 0.1665824145078659,
|
|
"num_tokens": 6613399.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.913612318038941,
|
|
"epoch": 0.3324535295108665,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994503542983293,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.160952527821064,
|
|
"num_tokens": 6624410.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.85199613571167,
|
|
"epoch": 0.33301510641882404,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994475461216472,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.16876164823770523,
|
|
"num_tokens": 6635523.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.898876953125,
|
|
"epoch": 0.3335766833267816,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994447307984684,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.1576322928071022,
|
|
"num_tokens": 6648416.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.7013694763183596,
|
|
"epoch": 0.33413826023473914,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994419083288823,
|
|
"loss": 5.7018,
|
|
"mean_token_accuracy": 0.16272213459014892,
|
|
"num_tokens": 6658907.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.858709526062012,
|
|
"epoch": 0.3346998371426967,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994390787129787,
|
|
"loss": 5.8528,
|
|
"mean_token_accuracy": 0.16023978292942048,
|
|
"num_tokens": 6669682.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.921603679656982,
|
|
"epoch": 0.33526141405065424,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994362419508478,
|
|
"loss": 5.9159,
|
|
"mean_token_accuracy": 0.15644512325525284,
|
|
"num_tokens": 6681919.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.877898931503296,
|
|
"epoch": 0.3358229909586118,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00049943339804258,
|
|
"loss": 5.8463,
|
|
"mean_token_accuracy": 0.164728282392025,
|
|
"num_tokens": 6693988.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.7946343421936035,
|
|
"epoch": 0.33638456786656934,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994305469882657,
|
|
"loss": 5.7797,
|
|
"mean_token_accuracy": 0.16247627437114714,
|
|
"num_tokens": 6705413.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.833203840255737,
|
|
"epoch": 0.3369461447745269,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994276887879957,
|
|
"loss": 5.7304,
|
|
"mean_token_accuracy": 0.1643373355269432,
|
|
"num_tokens": 6716217.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3369461447745269,
|
|
"eval_entropy": 5.671144631587263,
|
|
"eval_loss": 5.824180603027344,
|
|
"eval_mean_token_accuracy": 0.1703288601276599,
|
|
"eval_num_tokens": 6716217.0,
|
|
"eval_runtime": 24.7059,
|
|
"eval_samples_per_second": 1255.289,
|
|
"eval_steps_per_second": 156.926,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 89030,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.0538862999552e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|