31266437f0
Model: fpadovani/eng-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3369461447745269,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.958112335205078,
|
|
"epoch": 0.0005615769079575448,
|
|
"grad_norm": 13.5625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.2842,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 11659.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.9424741744995115,
|
|
"epoch": 0.0011231538159150896,
|
|
"grad_norm": 13.5625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.1707,
|
|
"mean_token_accuracy": 0.00011547344038262964,
|
|
"num_tokens": 21794.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.973624753952026,
|
|
"epoch": 0.0016847307238726343,
|
|
"grad_norm": 13.6875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.149,
|
|
"mean_token_accuracy": 6.915629492141307e-05,
|
|
"num_tokens": 33206.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.9998602867126465,
|
|
"epoch": 0.0022463076318301792,
|
|
"grad_norm": 15.6875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 14.0249,
|
|
"mean_token_accuracy": 0.00014555996167473496,
|
|
"num_tokens": 44487.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.110756301879883,
|
|
"epoch": 0.002807884539787724,
|
|
"grad_norm": 17.875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.6677,
|
|
"mean_token_accuracy": 7.246377062983811e-05,
|
|
"num_tokens": 56062.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.332080888748169,
|
|
"epoch": 0.0033694614477452686,
|
|
"grad_norm": 20.875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.1848,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 67453.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.396451139450074,
|
|
"epoch": 0.003931038355702813,
|
|
"grad_norm": 25.375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 12.2399,
|
|
"mean_token_accuracy": 6.105006323195994e-05,
|
|
"num_tokens": 78527.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 9.540253734588623,
|
|
"epoch": 0.0044926152636603585,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 11.0354,
|
|
"mean_token_accuracy": 5.87199057918042e-05,
|
|
"num_tokens": 89267.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.682201671600343,
|
|
"epoch": 0.005054192171617903,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.738,
|
|
"mean_token_accuracy": 0.007576325320405886,
|
|
"num_tokens": 102035.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.73370714187622,
|
|
"epoch": 0.005615769079575448,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.5603,
|
|
"mean_token_accuracy": 0.015592619962990283,
|
|
"num_tokens": 112734.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.730180168151856,
|
|
"epoch": 0.006177345987532993,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.3452,
|
|
"mean_token_accuracy": 0.01546380277723074,
|
|
"num_tokens": 123854.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.69598331451416,
|
|
"epoch": 0.006738922895490537,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.1223,
|
|
"mean_token_accuracy": 0.01719926903024316,
|
|
"num_tokens": 133444.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.701205444335937,
|
|
"epoch": 0.007300499803448083,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.9707,
|
|
"mean_token_accuracy": 0.01521061807870865,
|
|
"num_tokens": 144678.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.72805700302124,
|
|
"epoch": 0.007862076711405626,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8757,
|
|
"mean_token_accuracy": 0.02308740708976984,
|
|
"num_tokens": 155866.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.729030323028564,
|
|
"epoch": 0.008423653619363172,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.783,
|
|
"mean_token_accuracy": 0.04029188398271799,
|
|
"num_tokens": 166965.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.717912292480468,
|
|
"epoch": 0.008985230527320717,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.6967,
|
|
"mean_token_accuracy": 0.03837036974728107,
|
|
"num_tokens": 177423.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.714910125732422,
|
|
"epoch": 0.00954680743527826,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6005,
|
|
"mean_token_accuracy": 0.039133700914680956,
|
|
"num_tokens": 188687.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.715478420257568,
|
|
"epoch": 0.010108384343235806,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5344,
|
|
"mean_token_accuracy": 0.04223253391683102,
|
|
"num_tokens": 200173.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.7022141456604,
|
|
"epoch": 0.010669961251193351,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.4043,
|
|
"mean_token_accuracy": 0.038442989625036714,
|
|
"num_tokens": 210877.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.681341648101807,
|
|
"epoch": 0.011231538159150897,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.2957,
|
|
"mean_token_accuracy": 0.03458300586789846,
|
|
"num_tokens": 221770.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.660041809082031,
|
|
"epoch": 0.01179311506710844,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.172,
|
|
"mean_token_accuracy": 0.03827377744019032,
|
|
"num_tokens": 232140.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.632814598083495,
|
|
"epoch": 0.012354691975065986,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1093,
|
|
"mean_token_accuracy": 0.041411877423524854,
|
|
"num_tokens": 244186.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.598613166809082,
|
|
"epoch": 0.012916268883023531,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9603,
|
|
"mean_token_accuracy": 0.04186610747128725,
|
|
"num_tokens": 254805.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.550034332275391,
|
|
"epoch": 0.013477845790981074,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.7951,
|
|
"mean_token_accuracy": 0.050945664569735524,
|
|
"num_tokens": 265055.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.497636890411377,
|
|
"epoch": 0.01403942269893862,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.6784,
|
|
"mean_token_accuracy": 0.05012401342391968,
|
|
"num_tokens": 275850.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.439189529418945,
|
|
"epoch": 0.014600999606896165,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.5813,
|
|
"mean_token_accuracy": 0.04501255042850971,
|
|
"num_tokens": 286802.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.362538623809815,
|
|
"epoch": 0.015162576514853709,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5087,
|
|
"mean_token_accuracy": 0.04473419226706028,
|
|
"num_tokens": 297070.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.26766414642334,
|
|
"epoch": 0.015724153422811252,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.4016,
|
|
"mean_token_accuracy": 0.0456852950155735,
|
|
"num_tokens": 309617.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.18057041168213,
|
|
"epoch": 0.0162857303307688,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.2802,
|
|
"mean_token_accuracy": 0.04733948037028313,
|
|
"num_tokens": 321310.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.039380741119384,
|
|
"epoch": 0.016847307238726343,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1192,
|
|
"mean_token_accuracy": 0.05164117477834225,
|
|
"num_tokens": 332243.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.87264642715454,
|
|
"epoch": 0.017408884146683887,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.0322,
|
|
"mean_token_accuracy": 0.05423316806554794,
|
|
"num_tokens": 342847.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.697960758209229,
|
|
"epoch": 0.017970461054641434,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.8819,
|
|
"mean_token_accuracy": 0.054126177728176114,
|
|
"num_tokens": 353570.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.482976245880128,
|
|
"epoch": 0.018532037962598977,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.7722,
|
|
"mean_token_accuracy": 0.05961498692631721,
|
|
"num_tokens": 364330.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.207988929748534,
|
|
"epoch": 0.01909361487055652,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7247,
|
|
"mean_token_accuracy": 0.05897176414728165,
|
|
"num_tokens": 374930.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.946532917022704,
|
|
"epoch": 0.019655191778514068,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.6508,
|
|
"mean_token_accuracy": 0.05788501463830471,
|
|
"num_tokens": 384690.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.74663782119751,
|
|
"epoch": 0.020216768686471612,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.6041,
|
|
"mean_token_accuracy": 0.05669615678489208,
|
|
"num_tokens": 395753.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.500962829589843,
|
|
"epoch": 0.020778345594429155,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5318,
|
|
"mean_token_accuracy": 0.06435371935367584,
|
|
"num_tokens": 407049.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.297107601165772,
|
|
"epoch": 0.021339922502386702,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.5052,
|
|
"mean_token_accuracy": 0.07400269955396652,
|
|
"num_tokens": 417942.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.161279296875,
|
|
"epoch": 0.021901499410344246,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.5143,
|
|
"mean_token_accuracy": 0.06796157322824001,
|
|
"num_tokens": 428151.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.059497261047364,
|
|
"epoch": 0.022463076318301793,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.5599,
|
|
"mean_token_accuracy": 0.06278462670743465,
|
|
"num_tokens": 439837.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.035380172729493,
|
|
"epoch": 0.023024653226259337,
|
|
"grad_norm": 0.62109375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4149,
|
|
"mean_token_accuracy": 0.0609861858189106,
|
|
"num_tokens": 450357.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.987471294403076,
|
|
"epoch": 0.02358623013421688,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4119,
|
|
"mean_token_accuracy": 0.06853476613759994,
|
|
"num_tokens": 461174.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.993591213226319,
|
|
"epoch": 0.024147807042174427,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.4641,
|
|
"mean_token_accuracy": 0.0716362364590168,
|
|
"num_tokens": 472785.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.965004348754883,
|
|
"epoch": 0.02470938395013197,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.4134,
|
|
"mean_token_accuracy": 0.07565828561782836,
|
|
"num_tokens": 483248.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.868141603469849,
|
|
"epoch": 0.025270960858089515,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3137,
|
|
"mean_token_accuracy": 0.0714982945472002,
|
|
"num_tokens": 494690.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.927273750305176,
|
|
"epoch": 0.025832537766047062,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.4905,
|
|
"mean_token_accuracy": 0.07402925454080105,
|
|
"num_tokens": 506192.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.935389471054077,
|
|
"epoch": 0.026394114674004605,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.3528,
|
|
"mean_token_accuracy": 0.0740197867155075,
|
|
"num_tokens": 517152.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.856435060501099,
|
|
"epoch": 0.02695569158196215,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.2736,
|
|
"mean_token_accuracy": 0.08407649844884872,
|
|
"num_tokens": 527836.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.854199695587158,
|
|
"epoch": 0.027517268489919696,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.3984,
|
|
"mean_token_accuracy": 0.07311258018016815,
|
|
"num_tokens": 539491.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.888166761398315,
|
|
"epoch": 0.02807884539787724,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.3729,
|
|
"mean_token_accuracy": 0.08043631911277771,
|
|
"num_tokens": 550816.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.793630981445313,
|
|
"epoch": 0.028640422305834783,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.3921,
|
|
"mean_token_accuracy": 0.0777372658252716,
|
|
"num_tokens": 561566.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.83606104850769,
|
|
"epoch": 0.02920199921379233,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.323,
|
|
"mean_token_accuracy": 0.07814248651266098,
|
|
"num_tokens": 573032.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.867829418182373,
|
|
"epoch": 0.029763576121749874,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.2565,
|
|
"mean_token_accuracy": 0.08499897569417954,
|
|
"num_tokens": 584140.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.7688757419586185,
|
|
"epoch": 0.030325153029707418,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.3227,
|
|
"mean_token_accuracy": 0.08433490246534348,
|
|
"num_tokens": 595097.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.861677742004394,
|
|
"epoch": 0.030886729937664965,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.3152,
|
|
"mean_token_accuracy": 0.08390655070543289,
|
|
"num_tokens": 606797.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.725890064239502,
|
|
"epoch": 0.031448306845622505,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.2734,
|
|
"mean_token_accuracy": 0.08379090949892998,
|
|
"num_tokens": 618187.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.801093626022339,
|
|
"epoch": 0.032009883753580055,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.2249,
|
|
"mean_token_accuracy": 0.0867884710431099,
|
|
"num_tokens": 629829.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.699099493026734,
|
|
"epoch": 0.0325714606615376,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.2257,
|
|
"mean_token_accuracy": 0.09084633439779281,
|
|
"num_tokens": 640914.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.680918836593628,
|
|
"epoch": 0.03313303756949514,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.2187,
|
|
"mean_token_accuracy": 0.08423622846603393,
|
|
"num_tokens": 653057.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.726095199584961,
|
|
"epoch": 0.033694614477452686,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.1693,
|
|
"mean_token_accuracy": 0.08970561251044273,
|
|
"num_tokens": 663437.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.676259231567383,
|
|
"epoch": 0.03425619138541023,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.2165,
|
|
"mean_token_accuracy": 0.08746050000190735,
|
|
"num_tokens": 675416.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.61683201789856,
|
|
"epoch": 0.03481776829336777,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0378,
|
|
"mean_token_accuracy": 0.09221994504332542,
|
|
"num_tokens": 686633.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.593777084350586,
|
|
"epoch": 0.035379345201325324,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.1128,
|
|
"mean_token_accuracy": 0.09131084829568863,
|
|
"num_tokens": 698065.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.737735366821289,
|
|
"epoch": 0.03594092210928287,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.1167,
|
|
"mean_token_accuracy": 0.09759770259261132,
|
|
"num_tokens": 708652.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.677718257904052,
|
|
"epoch": 0.03650249901724041,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.2492,
|
|
"mean_token_accuracy": 0.08909616991877556,
|
|
"num_tokens": 720199.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.6231176376342775,
|
|
"epoch": 0.037064075925197955,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.2337,
|
|
"mean_token_accuracy": 0.09042609483003616,
|
|
"num_tokens": 732964.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.56429443359375,
|
|
"epoch": 0.0376256528331555,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.0063,
|
|
"mean_token_accuracy": 0.09593740776181221,
|
|
"num_tokens": 743528.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.644824886322022,
|
|
"epoch": 0.03818722974111304,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.0692,
|
|
"mean_token_accuracy": 0.09663922786712646,
|
|
"num_tokens": 754365.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.584464263916016,
|
|
"epoch": 0.03874880664907059,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9887,
|
|
"mean_token_accuracy": 0.09488176926970482,
|
|
"num_tokens": 766094.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.501060867309571,
|
|
"epoch": 0.039310383557028136,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.039,
|
|
"mean_token_accuracy": 0.09812524616718292,
|
|
"num_tokens": 777275.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.562764501571655,
|
|
"epoch": 0.03987196046498568,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.085,
|
|
"mean_token_accuracy": 0.1003342442214489,
|
|
"num_tokens": 789436.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.534398317337036,
|
|
"epoch": 0.040433537372943223,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.1145,
|
|
"mean_token_accuracy": 0.0983487956225872,
|
|
"num_tokens": 800164.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.422997093200683,
|
|
"epoch": 0.04099511428090077,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.9878,
|
|
"mean_token_accuracy": 0.09883297383785247,
|
|
"num_tokens": 811797.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.490043687820434,
|
|
"epoch": 0.04155669118885831,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.9941,
|
|
"mean_token_accuracy": 0.10256326273083687,
|
|
"num_tokens": 824158.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.519336462020874,
|
|
"epoch": 0.04211826809681586,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.9989,
|
|
"mean_token_accuracy": 0.09889804199337959,
|
|
"num_tokens": 835803.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.509277868270874,
|
|
"epoch": 0.042679845004773405,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.0624,
|
|
"mean_token_accuracy": 0.09996038749814033,
|
|
"num_tokens": 848106.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.411794948577881,
|
|
"epoch": 0.04324142191273095,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.0267,
|
|
"mean_token_accuracy": 0.09782384037971496,
|
|
"num_tokens": 859101.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.444434595108032,
|
|
"epoch": 0.04380299882068849,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.9103,
|
|
"mean_token_accuracy": 0.1043923944234848,
|
|
"num_tokens": 870309.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.441433763504028,
|
|
"epoch": 0.044364575728646036,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.9829,
|
|
"mean_token_accuracy": 0.10260054618120193,
|
|
"num_tokens": 881515.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.445163917541504,
|
|
"epoch": 0.044926152636603586,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.9395,
|
|
"mean_token_accuracy": 0.10442078933119774,
|
|
"num_tokens": 892129.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.414169979095459,
|
|
"epoch": 0.04548772954456113,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.9523,
|
|
"mean_token_accuracy": 0.10221787467598915,
|
|
"num_tokens": 903186.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.402553081512451,
|
|
"epoch": 0.046049306452518673,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.9065,
|
|
"mean_token_accuracy": 0.10986820012331008,
|
|
"num_tokens": 913471.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.422558689117432,
|
|
"epoch": 0.04661088336047622,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.9043,
|
|
"mean_token_accuracy": 0.10425306111574173,
|
|
"num_tokens": 924283.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.360500431060791,
|
|
"epoch": 0.04717246026843376,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.9377,
|
|
"mean_token_accuracy": 0.108520770072937,
|
|
"num_tokens": 934975.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.330597305297852,
|
|
"epoch": 0.047734037176391304,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8123,
|
|
"mean_token_accuracy": 0.11223476156592369,
|
|
"num_tokens": 945587.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.300155162811279,
|
|
"epoch": 0.048295614084348855,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8755,
|
|
"mean_token_accuracy": 0.10690404027700424,
|
|
"num_tokens": 955935.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.336331605911255,
|
|
"epoch": 0.0488571909923064,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8399,
|
|
"mean_token_accuracy": 0.10845198333263398,
|
|
"num_tokens": 967960.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.356525516510009,
|
|
"epoch": 0.04941876790026394,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.8741,
|
|
"mean_token_accuracy": 0.11335771456360817,
|
|
"num_tokens": 979680.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.2876073837280275,
|
|
"epoch": 0.049980344808221486,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.936,
|
|
"mean_token_accuracy": 0.10629516914486885,
|
|
"num_tokens": 990600.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.374933099746704,
|
|
"epoch": 0.05054192171617903,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.9701,
|
|
"mean_token_accuracy": 0.11168414130806922,
|
|
"num_tokens": 1002331.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.251807832717896,
|
|
"epoch": 0.05110349862413657,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.776,
|
|
"mean_token_accuracy": 0.10971713438630104,
|
|
"num_tokens": 1013473.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.274680042266846,
|
|
"epoch": 0.051665075532094124,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.8667,
|
|
"mean_token_accuracy": 0.10595520064234734,
|
|
"num_tokens": 1024434.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.303326034545899,
|
|
"epoch": 0.05222665244005167,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.8918,
|
|
"mean_token_accuracy": 0.10734717026352883,
|
|
"num_tokens": 1035452.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.202190494537353,
|
|
"epoch": 0.05278822934800921,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7608,
|
|
"mean_token_accuracy": 0.10601013004779816,
|
|
"num_tokens": 1046213.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.248915481567383,
|
|
"epoch": 0.053349806255966754,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.7926,
|
|
"mean_token_accuracy": 0.10846332460641861,
|
|
"num_tokens": 1057469.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.389639139175415,
|
|
"epoch": 0.0539113831639243,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.9242,
|
|
"mean_token_accuracy": 0.11156258061528206,
|
|
"num_tokens": 1069543.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.164505100250244,
|
|
"epoch": 0.05447296007188184,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7856,
|
|
"mean_token_accuracy": 0.1143708311021328,
|
|
"num_tokens": 1080476.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.269598531723022,
|
|
"epoch": 0.05503453697983939,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.9008,
|
|
"mean_token_accuracy": 0.11152186244726181,
|
|
"num_tokens": 1091700.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.293481063842774,
|
|
"epoch": 0.055596113887796936,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.7849,
|
|
"mean_token_accuracy": 0.1107654757797718,
|
|
"num_tokens": 1103056.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.240784788131714,
|
|
"epoch": 0.05615769079575448,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.8439,
|
|
"mean_token_accuracy": 0.11618472486734391,
|
|
"num_tokens": 1114836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.114566326141357,
|
|
"epoch": 0.05671926770371202,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7378,
|
|
"mean_token_accuracy": 0.11399558708071708,
|
|
"num_tokens": 1125993.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.239473915100097,
|
|
"epoch": 0.05728084461166957,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.8169,
|
|
"mean_token_accuracy": 0.11478226408362388,
|
|
"num_tokens": 1136719.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.177135276794433,
|
|
"epoch": 0.05784242151962711,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.6864,
|
|
"mean_token_accuracy": 0.11818328648805618,
|
|
"num_tokens": 1146947.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.201584386825561,
|
|
"epoch": 0.05840399842758466,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.8165,
|
|
"mean_token_accuracy": 0.11641246154904365,
|
|
"num_tokens": 1157974.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.081555986404419,
|
|
"epoch": 0.058965575335542204,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.7415,
|
|
"mean_token_accuracy": 0.1143609032034874,
|
|
"num_tokens": 1168573.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.127064418792725,
|
|
"epoch": 0.05952715224349975,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.656,
|
|
"mean_token_accuracy": 0.11710669472813606,
|
|
"num_tokens": 1178446.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.138171005249023,
|
|
"epoch": 0.06008872915145729,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6753,
|
|
"mean_token_accuracy": 0.11334134191274643,
|
|
"num_tokens": 1190558.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.144500207901001,
|
|
"epoch": 0.060650306059414835,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.8331,
|
|
"mean_token_accuracy": 0.11418996006250381,
|
|
"num_tokens": 1201929.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.027964735031128,
|
|
"epoch": 0.06121188296737238,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.666,
|
|
"mean_token_accuracy": 0.12040585204958916,
|
|
"num_tokens": 1213155.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.229724979400634,
|
|
"epoch": 0.06177345987532993,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7297,
|
|
"mean_token_accuracy": 0.11603076979517937,
|
|
"num_tokens": 1223961.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.008941268920898,
|
|
"epoch": 0.06233503678328747,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.6331,
|
|
"mean_token_accuracy": 0.12098302766680717,
|
|
"num_tokens": 1233888.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.994447660446167,
|
|
"epoch": 0.06289661369124501,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.7383,
|
|
"mean_token_accuracy": 0.11173689067363739,
|
|
"num_tokens": 1244405.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.166880035400391,
|
|
"epoch": 0.06345819059920256,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.682,
|
|
"mean_token_accuracy": 0.11965646147727967,
|
|
"num_tokens": 1257099.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.068090343475342,
|
|
"epoch": 0.06401976750716011,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.7839,
|
|
"mean_token_accuracy": 0.12307375743985176,
|
|
"num_tokens": 1267965.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.09981951713562,
|
|
"epoch": 0.06458134441511765,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6873,
|
|
"mean_token_accuracy": 0.11978518962860107,
|
|
"num_tokens": 1280075.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.102661514282227,
|
|
"epoch": 0.0651429213230752,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6995,
|
|
"mean_token_accuracy": 0.12262161523103714,
|
|
"num_tokens": 1290574.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.051478481292724,
|
|
"epoch": 0.06570449823103273,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6635,
|
|
"mean_token_accuracy": 0.12353429943323135,
|
|
"num_tokens": 1302680.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.008921670913696,
|
|
"epoch": 0.06626607513899029,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6518,
|
|
"mean_token_accuracy": 0.12372544482350349,
|
|
"num_tokens": 1314577.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.094518613815308,
|
|
"epoch": 0.06682765204694784,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.7729,
|
|
"mean_token_accuracy": 0.1234229065477848,
|
|
"num_tokens": 1326560.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.065892362594605,
|
|
"epoch": 0.06738922895490537,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.8373,
|
|
"mean_token_accuracy": 0.11262822896242142,
|
|
"num_tokens": 1339105.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.947021389007569,
|
|
"epoch": 0.06795080586286292,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.5099,
|
|
"mean_token_accuracy": 0.1292965017259121,
|
|
"num_tokens": 1349914.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.016496849060059,
|
|
"epoch": 0.06851238277082046,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.714,
|
|
"mean_token_accuracy": 0.12088268026709556,
|
|
"num_tokens": 1361700.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.005446863174439,
|
|
"epoch": 0.06907395967877801,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.7339,
|
|
"mean_token_accuracy": 0.12360861897468567,
|
|
"num_tokens": 1373103.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.974551010131836,
|
|
"epoch": 0.06963553658673555,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5487,
|
|
"mean_token_accuracy": 0.12374898120760917,
|
|
"num_tokens": 1383742.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.948500871658325,
|
|
"epoch": 0.0701971134946931,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6968,
|
|
"mean_token_accuracy": 0.11977056413888931,
|
|
"num_tokens": 1396656.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.922845840454102,
|
|
"epoch": 0.07075869040265065,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5605,
|
|
"mean_token_accuracy": 0.13307109400629996,
|
|
"num_tokens": 1406709.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.017679023742676,
|
|
"epoch": 0.07132026731060818,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.6002,
|
|
"mean_token_accuracy": 0.12924449220299722,
|
|
"num_tokens": 1417793.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.013447713851929,
|
|
"epoch": 0.07188184421856574,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.678,
|
|
"mean_token_accuracy": 0.12412039786577225,
|
|
"num_tokens": 1429093.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.820969581604004,
|
|
"epoch": 0.07244342112652327,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5974,
|
|
"mean_token_accuracy": 0.1283337689936161,
|
|
"num_tokens": 1440907.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.997115421295166,
|
|
"epoch": 0.07300499803448082,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6672,
|
|
"mean_token_accuracy": 0.12072568610310555,
|
|
"num_tokens": 1452089.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.984156370162964,
|
|
"epoch": 0.07356657494243837,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.674,
|
|
"mean_token_accuracy": 0.12165596857666969,
|
|
"num_tokens": 1464378.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.951331949234008,
|
|
"epoch": 0.07412815185039591,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.6099,
|
|
"mean_token_accuracy": 0.12271932810544968,
|
|
"num_tokens": 1476678.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.843834352493286,
|
|
"epoch": 0.07468972875835346,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.4578,
|
|
"mean_token_accuracy": 0.12957773357629776,
|
|
"num_tokens": 1486808.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.973170900344849,
|
|
"epoch": 0.075251305666311,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.7373,
|
|
"mean_token_accuracy": 0.12345995232462884,
|
|
"num_tokens": 1499281.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.001640558242798,
|
|
"epoch": 0.07581288257426855,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6501,
|
|
"mean_token_accuracy": 0.12579731568694114,
|
|
"num_tokens": 1510202.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.91340651512146,
|
|
"epoch": 0.07637445948222608,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5045,
|
|
"mean_token_accuracy": 0.13105906471610068,
|
|
"num_tokens": 1521492.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.800015640258789,
|
|
"epoch": 0.07693603639018363,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.5206,
|
|
"mean_token_accuracy": 0.13716215938329696,
|
|
"num_tokens": 1532856.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.814711189270019,
|
|
"epoch": 0.07749761329814119,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.5356,
|
|
"mean_token_accuracy": 0.12902490720152854,
|
|
"num_tokens": 1543408.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.86055703163147,
|
|
"epoch": 0.07805919020609872,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5525,
|
|
"mean_token_accuracy": 0.12741926535964013,
|
|
"num_tokens": 1555474.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.898800182342529,
|
|
"epoch": 0.07862076711405627,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.6414,
|
|
"mean_token_accuracy": 0.1282556474208832,
|
|
"num_tokens": 1567484.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.824853563308716,
|
|
"epoch": 0.07918234402201381,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4866,
|
|
"mean_token_accuracy": 0.1352921135723591,
|
|
"num_tokens": 1578204.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.884771060943604,
|
|
"epoch": 0.07974392092997136,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.4897,
|
|
"mean_token_accuracy": 0.1282044917345047,
|
|
"num_tokens": 1589012.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.743309259414673,
|
|
"epoch": 0.08030549783792891,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.496,
|
|
"mean_token_accuracy": 0.12868643477559089,
|
|
"num_tokens": 1601099.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.910572957992554,
|
|
"epoch": 0.08086707474588645,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.6518,
|
|
"mean_token_accuracy": 0.1232347123324871,
|
|
"num_tokens": 1612814.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.851531744003296,
|
|
"epoch": 0.081428651653844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.543,
|
|
"mean_token_accuracy": 0.12722352966666223,
|
|
"num_tokens": 1624953.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.843756008148193,
|
|
"epoch": 0.08199022856180153,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5685,
|
|
"mean_token_accuracy": 0.12934383600950242,
|
|
"num_tokens": 1635673.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.824569320678711,
|
|
"epoch": 0.08255180546975908,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.486,
|
|
"mean_token_accuracy": 0.135271368175745,
|
|
"num_tokens": 1647282.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.793824338912964,
|
|
"epoch": 0.08311338237771662,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4985,
|
|
"mean_token_accuracy": 0.13493574112653733,
|
|
"num_tokens": 1658426.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.795789480209351,
|
|
"epoch": 0.08367495928567417,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5264,
|
|
"mean_token_accuracy": 0.130235705524683,
|
|
"num_tokens": 1669958.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.745253849029541,
|
|
"epoch": 0.08423653619363172,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5678,
|
|
"mean_token_accuracy": 0.1286076597869396,
|
|
"num_tokens": 1682409.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.817635822296142,
|
|
"epoch": 0.08479811310158926,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.4985,
|
|
"mean_token_accuracy": 0.1403331384062767,
|
|
"num_tokens": 1692409.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.841214847564697,
|
|
"epoch": 0.08535969000954681,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.5853,
|
|
"mean_token_accuracy": 0.12864278703927995,
|
|
"num_tokens": 1705018.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.764056587219239,
|
|
"epoch": 0.08592126691750435,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5082,
|
|
"mean_token_accuracy": 0.12993483915925025,
|
|
"num_tokens": 1715625.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.736582279205322,
|
|
"epoch": 0.0864828438254619,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5812,
|
|
"mean_token_accuracy": 0.12060019001364708,
|
|
"num_tokens": 1727045.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.8794553756713865,
|
|
"epoch": 0.08704442073341945,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.6304,
|
|
"mean_token_accuracy": 0.12890330255031585,
|
|
"num_tokens": 1737374.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.838842105865479,
|
|
"epoch": 0.08760599764137698,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.6398,
|
|
"mean_token_accuracy": 0.13158344849944115,
|
|
"num_tokens": 1747788.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.650408744812012,
|
|
"epoch": 0.08816757454933453,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.3406,
|
|
"mean_token_accuracy": 0.14368992894887925,
|
|
"num_tokens": 1757769.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.700500535964966,
|
|
"epoch": 0.08872915145729207,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.4506,
|
|
"mean_token_accuracy": 0.12652962952852248,
|
|
"num_tokens": 1769246.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.819548749923706,
|
|
"epoch": 0.08929072836524962,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5743,
|
|
"mean_token_accuracy": 0.1305612899363041,
|
|
"num_tokens": 1781306.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.736283588409424,
|
|
"epoch": 0.08985230527320717,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.4786,
|
|
"mean_token_accuracy": 0.13247107341885567,
|
|
"num_tokens": 1792888.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.741839790344239,
|
|
"epoch": 0.09041388218116471,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4969,
|
|
"mean_token_accuracy": 0.13426485359668733,
|
|
"num_tokens": 1802938.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.803853511810303,
|
|
"epoch": 0.09097545908912226,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.5178,
|
|
"mean_token_accuracy": 0.13269057348370553,
|
|
"num_tokens": 1814738.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.784767770767212,
|
|
"epoch": 0.0915370359970798,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.5774,
|
|
"mean_token_accuracy": 0.13045511841773988,
|
|
"num_tokens": 1825100.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.586725234985352,
|
|
"epoch": 0.09209861290503735,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.4276,
|
|
"mean_token_accuracy": 0.13769749775528908,
|
|
"num_tokens": 1835879.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.844768095016479,
|
|
"epoch": 0.09266018981299488,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5658,
|
|
"mean_token_accuracy": 0.12576449438929557,
|
|
"num_tokens": 1848352.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.820197343826294,
|
|
"epoch": 0.09322176672095243,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.5146,
|
|
"mean_token_accuracy": 0.13076762184500695,
|
|
"num_tokens": 1859687.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.698688888549805,
|
|
"epoch": 0.09378334362890998,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.5072,
|
|
"mean_token_accuracy": 0.1330545090138912,
|
|
"num_tokens": 1871438.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.674928617477417,
|
|
"epoch": 0.09434492053686752,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.3932,
|
|
"mean_token_accuracy": 0.13914670795202255,
|
|
"num_tokens": 1881519.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.793725776672363,
|
|
"epoch": 0.09490649744482507,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.56,
|
|
"mean_token_accuracy": 0.13139583691954612,
|
|
"num_tokens": 1892428.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.715428733825684,
|
|
"epoch": 0.09546807435278261,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.4517,
|
|
"mean_token_accuracy": 0.13642125204205513,
|
|
"num_tokens": 1903760.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.728550386428833,
|
|
"epoch": 0.09602965126074016,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.5196,
|
|
"mean_token_accuracy": 0.1250755563378334,
|
|
"num_tokens": 1915430.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.690254163742066,
|
|
"epoch": 0.09659122816869771,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4753,
|
|
"mean_token_accuracy": 0.12775300145149232,
|
|
"num_tokens": 1925709.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.814657306671142,
|
|
"epoch": 0.09715280507665525,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.5115,
|
|
"mean_token_accuracy": 0.133428718149662,
|
|
"num_tokens": 1938148.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.454801988601685,
|
|
"epoch": 0.0977143819846128,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3948,
|
|
"mean_token_accuracy": 0.13895176202058793,
|
|
"num_tokens": 1949028.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.735638570785523,
|
|
"epoch": 0.09827595889257033,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.452,
|
|
"mean_token_accuracy": 0.1338992938399315,
|
|
"num_tokens": 1960353.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.726486015319824,
|
|
"epoch": 0.09883753580052788,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.5459,
|
|
"mean_token_accuracy": 0.12802935019135475,
|
|
"num_tokens": 1972335.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.657772254943848,
|
|
"epoch": 0.09939911270848542,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3937,
|
|
"mean_token_accuracy": 0.13370347768068314,
|
|
"num_tokens": 1982851.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.599719619750976,
|
|
"epoch": 0.09996068961644297,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.3824,
|
|
"mean_token_accuracy": 0.13738489374518395,
|
|
"num_tokens": 1993931.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.713817548751831,
|
|
"epoch": 0.10052226652440052,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.5012,
|
|
"mean_token_accuracy": 0.13419413417577744,
|
|
"num_tokens": 2004838.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.532304430007935,
|
|
"epoch": 0.10108384343235806,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3051,
|
|
"mean_token_accuracy": 0.13725042045116426,
|
|
"num_tokens": 2015620.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.6708457469940186,
|
|
"epoch": 0.10164542034031561,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4426,
|
|
"mean_token_accuracy": 0.13907212615013123,
|
|
"num_tokens": 2027489.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.573997211456299,
|
|
"epoch": 0.10220699724827315,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.3063,
|
|
"mean_token_accuracy": 0.14410469308495522,
|
|
"num_tokens": 2038475.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.5359595775604244,
|
|
"epoch": 0.1027685741562307,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3129,
|
|
"mean_token_accuracy": 0.1398226350545883,
|
|
"num_tokens": 2048938.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.542961549758911,
|
|
"epoch": 0.10333015106418825,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4021,
|
|
"mean_token_accuracy": 0.1346525728702545,
|
|
"num_tokens": 2060372.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.594799661636353,
|
|
"epoch": 0.10389172797214578,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.3928,
|
|
"mean_token_accuracy": 0.13547346442937852,
|
|
"num_tokens": 2071558.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.629229116439819,
|
|
"epoch": 0.10445330488010333,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.4373,
|
|
"mean_token_accuracy": 0.13637368977069855,
|
|
"num_tokens": 2082350.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.613821411132813,
|
|
"epoch": 0.10501488178806087,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4865,
|
|
"mean_token_accuracy": 0.13623699843883513,
|
|
"num_tokens": 2093448.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.735397148132324,
|
|
"epoch": 0.10557645869601842,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.5141,
|
|
"mean_token_accuracy": 0.13197903707623482,
|
|
"num_tokens": 2104171.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.624809694290161,
|
|
"epoch": 0.10613803560397596,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3949,
|
|
"mean_token_accuracy": 0.13641267418861389,
|
|
"num_tokens": 2114496.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.655260181427002,
|
|
"epoch": 0.10669961251193351,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.4007,
|
|
"mean_token_accuracy": 0.13775101825594901,
|
|
"num_tokens": 2125930.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.571065235137939,
|
|
"epoch": 0.10726118941989106,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.357,
|
|
"mean_token_accuracy": 0.14058973491191865,
|
|
"num_tokens": 2136452.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.6056571960449215,
|
|
"epoch": 0.1078227663278486,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.4536,
|
|
"mean_token_accuracy": 0.13291025757789612,
|
|
"num_tokens": 2148233.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.473015594482422,
|
|
"epoch": 0.10838434323580615,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.14449345842003822,
|
|
"num_tokens": 2159475.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.528903770446777,
|
|
"epoch": 0.10894592014376368,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3596,
|
|
"mean_token_accuracy": 0.13835327625274657,
|
|
"num_tokens": 2170042.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.592466688156128,
|
|
"epoch": 0.10950749705172123,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3605,
|
|
"mean_token_accuracy": 0.13567833229899406,
|
|
"num_tokens": 2182234.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.484764099121094,
|
|
"epoch": 0.11006907395967878,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3535,
|
|
"mean_token_accuracy": 0.14025619626045227,
|
|
"num_tokens": 2192477.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.500120496749878,
|
|
"epoch": 0.11063065086763632,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3405,
|
|
"mean_token_accuracy": 0.13677674606442453,
|
|
"num_tokens": 2203082.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.521809720993042,
|
|
"epoch": 0.11119222777559387,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.3143,
|
|
"mean_token_accuracy": 0.13907622545957565,
|
|
"num_tokens": 2213684.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.506216716766358,
|
|
"epoch": 0.11175380468355141,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3189,
|
|
"mean_token_accuracy": 0.13710450679063796,
|
|
"num_tokens": 2225524.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.529984045028686,
|
|
"epoch": 0.11231538159150896,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.1366613119840622,
|
|
"num_tokens": 2236004.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.607108402252197,
|
|
"epoch": 0.1128769584994665,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499999997707492,
|
|
"loss": 6.4427,
|
|
"mean_token_accuracy": 0.12697047293186187,
|
|
"num_tokens": 2247730.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.58273491859436,
|
|
"epoch": 0.11343853540742405,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999999883941787,
|
|
"loss": 6.3966,
|
|
"mean_token_accuracy": 0.14159852117300034,
|
|
"num_tokens": 2260132.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.481048250198365,
|
|
"epoch": 0.1140001123153816,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999719167785,
|
|
"loss": 6.3627,
|
|
"mean_token_accuracy": 0.13624601066112518,
|
|
"num_tokens": 2270060.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.499448776245117,
|
|
"epoch": 0.11456168922333913,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999999482752917,
|
|
"loss": 6.3727,
|
|
"mean_token_accuracy": 0.13926395475864412,
|
|
"num_tokens": 2281568.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.562040138244629,
|
|
"epoch": 0.11512326613129668,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999174697195,
|
|
"loss": 6.4069,
|
|
"mean_token_accuracy": 0.12946545705199242,
|
|
"num_tokens": 2293325.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.611707639694214,
|
|
"epoch": 0.11568484303925422,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998795000627,
|
|
"loss": 6.4062,
|
|
"mean_token_accuracy": 0.14011984914541245,
|
|
"num_tokens": 2304780.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.517575311660766,
|
|
"epoch": 0.11624641994721177,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999998343663223,
|
|
"loss": 6.3312,
|
|
"mean_token_accuracy": 0.136796210706234,
|
|
"num_tokens": 2315999.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.508590507507324,
|
|
"epoch": 0.11680799685516932,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999997820685,
|
|
"loss": 6.478,
|
|
"mean_token_accuracy": 0.13875503316521645,
|
|
"num_tokens": 2326695.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.5880430221557615,
|
|
"epoch": 0.11736957376312686,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004999997226065974,
|
|
"loss": 6.3187,
|
|
"mean_token_accuracy": 0.14242062866687774,
|
|
"num_tokens": 2336925.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.4472400665283205,
|
|
"epoch": 0.11793115067108441,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999996559806163,
|
|
"loss": 6.2145,
|
|
"mean_token_accuracy": 0.14515327513217927,
|
|
"num_tokens": 2347431.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.449374628067017,
|
|
"epoch": 0.11849272757904195,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999995821905589,
|
|
"loss": 6.3244,
|
|
"mean_token_accuracy": 0.1428348071873188,
|
|
"num_tokens": 2359894.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.484475946426391,
|
|
"epoch": 0.1190543044869995,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999995012364276,
|
|
"loss": 6.3513,
|
|
"mean_token_accuracy": 0.1399578034877777,
|
|
"num_tokens": 2371181.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.558645248413086,
|
|
"epoch": 0.11961588139495703,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999994131182248,
|
|
"loss": 6.2539,
|
|
"mean_token_accuracy": 0.14039175882935523,
|
|
"num_tokens": 2381531.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.4977819442749025,
|
|
"epoch": 0.12017745830291458,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999993178359535,
|
|
"loss": 6.3618,
|
|
"mean_token_accuracy": 0.14046622514724733,
|
|
"num_tokens": 2391573.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.531288480758667,
|
|
"epoch": 0.12073903521087213,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999992153896166,
|
|
"loss": 6.3495,
|
|
"mean_token_accuracy": 0.13780387118458748,
|
|
"num_tokens": 2402822.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.468347263336182,
|
|
"epoch": 0.12130061211882967,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999991057792175,
|
|
"loss": 6.2611,
|
|
"mean_token_accuracy": 0.13793368339538575,
|
|
"num_tokens": 2414322.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.4399701118469235,
|
|
"epoch": 0.12186218902678722,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999989890047596,
|
|
"loss": 6.4342,
|
|
"mean_token_accuracy": 0.14464614540338516,
|
|
"num_tokens": 2426560.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.6257377624511715,
|
|
"epoch": 0.12242376593474476,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999988650662467,
|
|
"loss": 6.3628,
|
|
"mean_token_accuracy": 0.1392559789121151,
|
|
"num_tokens": 2437723.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.458425664901734,
|
|
"epoch": 0.12298534284270231,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999987339636825,
|
|
"loss": 6.3052,
|
|
"mean_token_accuracy": 0.14131897166371346,
|
|
"num_tokens": 2448497.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.3388848304748535,
|
|
"epoch": 0.12354691975065986,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999985956970713,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.15202731192111968,
|
|
"num_tokens": 2459089.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.451615047454834,
|
|
"epoch": 0.1241084966586174,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999984502664178,
|
|
"loss": 6.2702,
|
|
"mean_token_accuracy": 0.14179657995700837,
|
|
"num_tokens": 2469882.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.480589246749878,
|
|
"epoch": 0.12467007356657495,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999982976717261,
|
|
"loss": 6.2999,
|
|
"mean_token_accuracy": 0.1432420939207077,
|
|
"num_tokens": 2482120.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.46314582824707,
|
|
"epoch": 0.1252316504745325,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999981379130016,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.14398316591978072,
|
|
"num_tokens": 2492626.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.512280225753784,
|
|
"epoch": 0.12579322738249002,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499997970990249,
|
|
"loss": 6.3556,
|
|
"mean_token_accuracy": 0.14139315783977507,
|
|
"num_tokens": 2506347.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.345871210098267,
|
|
"epoch": 0.12635480429044757,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999977969034737,
|
|
"loss": 6.2423,
|
|
"mean_token_accuracy": 0.14657723680138587,
|
|
"num_tokens": 2516584.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.479627084732056,
|
|
"epoch": 0.12691638119840512,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999976156526814,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.14619525671005248,
|
|
"num_tokens": 2526731.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.3882972240448,
|
|
"epoch": 0.12747795810636267,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999974272378776,
|
|
"loss": 6.1877,
|
|
"mean_token_accuracy": 0.14657506570219994,
|
|
"num_tokens": 2537180.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.418006896972656,
|
|
"epoch": 0.12803953501432022,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999972316590685,
|
|
"loss": 6.2725,
|
|
"mean_token_accuracy": 0.14524131938815116,
|
|
"num_tokens": 2547617.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.410860061645508,
|
|
"epoch": 0.12860111192227774,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999970289162604,
|
|
"loss": 6.1483,
|
|
"mean_token_accuracy": 0.1508580230176449,
|
|
"num_tokens": 2557743.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.349888610839844,
|
|
"epoch": 0.1291626888302353,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999968190094595,
|
|
"loss": 6.2487,
|
|
"mean_token_accuracy": 0.1476031497120857,
|
|
"num_tokens": 2568351.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.430012226104736,
|
|
"epoch": 0.12972426573819285,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999966019386727,
|
|
"loss": 6.3033,
|
|
"mean_token_accuracy": 0.14469023644924164,
|
|
"num_tokens": 2579703.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.4646430015563965,
|
|
"epoch": 0.1302858426461504,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999963777039067,
|
|
"loss": 6.2755,
|
|
"mean_token_accuracy": 0.1433379366993904,
|
|
"num_tokens": 2591197.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.39684362411499,
|
|
"epoch": 0.13084741955410795,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499996146305169,
|
|
"loss": 6.2434,
|
|
"mean_token_accuracy": 0.14241863116621972,
|
|
"num_tokens": 2601836.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.336419486999512,
|
|
"epoch": 0.13140899646206547,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999959077424665,
|
|
"loss": 6.1961,
|
|
"mean_token_accuracy": 0.14609644562005997,
|
|
"num_tokens": 2613513.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.367645883560181,
|
|
"epoch": 0.13197057337002302,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999956620158072,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.14458296820521355,
|
|
"num_tokens": 2625246.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.357092189788818,
|
|
"epoch": 0.13253215027798057,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999954091251987,
|
|
"loss": 6.216,
|
|
"mean_token_accuracy": 0.14300859868526458,
|
|
"num_tokens": 2636375.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.38755168914795,
|
|
"epoch": 0.13309372718593812,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999951490706491,
|
|
"loss": 6.3047,
|
|
"mean_token_accuracy": 0.13991767317056655,
|
|
"num_tokens": 2648586.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.442468166351318,
|
|
"epoch": 0.13365530409389567,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999948818521667,
|
|
"loss": 6.2964,
|
|
"mean_token_accuracy": 0.15023437291383743,
|
|
"num_tokens": 2660847.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.39590106010437,
|
|
"epoch": 0.1342168810018532,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049999460746976,
|
|
"loss": 6.2197,
|
|
"mean_token_accuracy": 0.14705628603696824,
|
|
"num_tokens": 2671160.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.4918781280517575,
|
|
"epoch": 0.13477845790981074,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999943259234377,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.14184095710515976,
|
|
"num_tokens": 2681622.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.2997137069702145,
|
|
"epoch": 0.1353400348177683,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999940372132089,
|
|
"loss": 6.1308,
|
|
"mean_token_accuracy": 0.15328069925308227,
|
|
"num_tokens": 2691503.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.358626222610473,
|
|
"epoch": 0.13590161172572585,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999937413390826,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.14330296590924263,
|
|
"num_tokens": 2702207.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.419915342330933,
|
|
"epoch": 0.1364631886336834,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999934383010683,
|
|
"loss": 6.2285,
|
|
"mean_token_accuracy": 0.14443148225545882,
|
|
"num_tokens": 2713178.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.428704166412354,
|
|
"epoch": 0.13702476554164092,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999931280991757,
|
|
"loss": 6.2391,
|
|
"mean_token_accuracy": 0.14996800050139428,
|
|
"num_tokens": 2723717.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.407614850997925,
|
|
"epoch": 0.13758634244959847,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999928107334146,
|
|
"loss": 6.3047,
|
|
"mean_token_accuracy": 0.13595292270183562,
|
|
"num_tokens": 2735669.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.339469146728516,
|
|
"epoch": 0.13814791935755602,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999924862037952,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.1468040868639946,
|
|
"num_tokens": 2746087.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.324771356582642,
|
|
"epoch": 0.13870949626551357,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999921545103278,
|
|
"loss": 6.2104,
|
|
"mean_token_accuracy": 0.14297769591212273,
|
|
"num_tokens": 2757143.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.488545560836792,
|
|
"epoch": 0.1392710731734711,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999918156530229,
|
|
"loss": 6.3189,
|
|
"mean_token_accuracy": 0.14068616107106208,
|
|
"num_tokens": 2769340.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.36818494796753,
|
|
"epoch": 0.13983265008142864,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999914696318913,
|
|
"loss": 6.2234,
|
|
"mean_token_accuracy": 0.1445622220635414,
|
|
"num_tokens": 2779514.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.3950879096984865,
|
|
"epoch": 0.1403942269893862,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999911164469441,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.15131438672542571,
|
|
"num_tokens": 2790801.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.352122497558594,
|
|
"epoch": 0.14095580389734375,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999907560981925,
|
|
"loss": 6.1722,
|
|
"mean_token_accuracy": 0.1425118625164032,
|
|
"num_tokens": 2801082.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.327898740768433,
|
|
"epoch": 0.1415173808053013,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999903885856479,
|
|
"loss": 6.1828,
|
|
"mean_token_accuracy": 0.14815054833889008,
|
|
"num_tokens": 2812719.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.260138082504272,
|
|
"epoch": 0.14207895771325882,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499990013909322,
|
|
"loss": 6.1789,
|
|
"mean_token_accuracy": 0.14185225889086722,
|
|
"num_tokens": 2823766.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.355242538452148,
|
|
"epoch": 0.14264053462121637,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499989632069227,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.14508824944496154,
|
|
"num_tokens": 2834801.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.289164733886719,
|
|
"epoch": 0.14320211152917392,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999892430653747,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.14808941408991813,
|
|
"num_tokens": 2845769.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.268469953536988,
|
|
"epoch": 0.14376368843713147,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999888468977776,
|
|
"loss": 6.1299,
|
|
"mean_token_accuracy": 0.15243081003427505,
|
|
"num_tokens": 2856001.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.349359560012817,
|
|
"epoch": 0.14432526534508902,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999884435664485,
|
|
"loss": 6.1636,
|
|
"mean_token_accuracy": 0.15014599561691283,
|
|
"num_tokens": 2867703.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.199705266952515,
|
|
"epoch": 0.14488684225304654,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999880330714,
|
|
"loss": 6.1076,
|
|
"mean_token_accuracy": 0.14883481562137604,
|
|
"num_tokens": 2878671.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.326551866531372,
|
|
"epoch": 0.1454484191610041,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999876154126453,
|
|
"loss": 6.2189,
|
|
"mean_token_accuracy": 0.14116846397519112,
|
|
"num_tokens": 2890137.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.333295202255249,
|
|
"epoch": 0.14600999606896164,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999871905901977,
|
|
"loss": 6.1345,
|
|
"mean_token_accuracy": 0.14464831352233887,
|
|
"num_tokens": 2900344.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.1990049362182615,
|
|
"epoch": 0.1465715729769192,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999867586040706,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.14359352886676788,
|
|
"num_tokens": 2912270.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.442420291900635,
|
|
"epoch": 0.14713314988487675,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999863194542779,
|
|
"loss": 6.2245,
|
|
"mean_token_accuracy": 0.13818560764193535,
|
|
"num_tokens": 2924677.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.208629751205445,
|
|
"epoch": 0.14769472679283427,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999858731408336,
|
|
"loss": 6.1435,
|
|
"mean_token_accuracy": 0.15086931586265565,
|
|
"num_tokens": 2935794.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.351964473724365,
|
|
"epoch": 0.14825630370079182,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999854196637518,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.1423012413084507,
|
|
"num_tokens": 2945958.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.388653326034546,
|
|
"epoch": 0.14881788060874937,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999849590230469,
|
|
"loss": 6.2022,
|
|
"mean_token_accuracy": 0.1418309211730957,
|
|
"num_tokens": 2957536.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.350034427642822,
|
|
"epoch": 0.14937945751670692,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999844912187336,
|
|
"loss": 6.1859,
|
|
"mean_token_accuracy": 0.14834656044840813,
|
|
"num_tokens": 2967787.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.309407663345337,
|
|
"epoch": 0.14994103442466447,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499984016250827,
|
|
"loss": 6.2062,
|
|
"mean_token_accuracy": 0.1401480630040169,
|
|
"num_tokens": 2980522.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.190045595169067,
|
|
"epoch": 0.150502611332622,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499983534119342,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.14754045605659485,
|
|
"num_tokens": 2990497.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.4408313751220705,
|
|
"epoch": 0.15106418824057954,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999830448242941,
|
|
"loss": 6.2346,
|
|
"mean_token_accuracy": 0.1441300056874752,
|
|
"num_tokens": 3002931.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.302226638793945,
|
|
"epoch": 0.1516257651485371,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999825483656986,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.15221837013959885,
|
|
"num_tokens": 3014137.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.390075826644898,
|
|
"epoch": 0.15218734205649465,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999820447435716,
|
|
"loss": 6.3144,
|
|
"mean_token_accuracy": 0.1362255647778511,
|
|
"num_tokens": 3026145.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.2819986820220945,
|
|
"epoch": 0.15274891896445217,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999815339579291,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.14926141500473022,
|
|
"num_tokens": 3037068.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.3687601566314695,
|
|
"epoch": 0.15331049587240972,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999810160087872,
|
|
"loss": 6.1057,
|
|
"mean_token_accuracy": 0.14911322370171548,
|
|
"num_tokens": 3047836.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.260298824310302,
|
|
"epoch": 0.15387207278036727,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999804908961626,
|
|
"loss": 6.228,
|
|
"mean_token_accuracy": 0.14651088342070578,
|
|
"num_tokens": 3060309.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.318568372726441,
|
|
"epoch": 0.15443364968832482,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999799586200719,
|
|
"loss": 6.1992,
|
|
"mean_token_accuracy": 0.14661515429615973,
|
|
"num_tokens": 3071789.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.3008849143981935,
|
|
"epoch": 0.15499522659628237,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499979419180532,
|
|
"loss": 6.1147,
|
|
"mean_token_accuracy": 0.1510265827178955,
|
|
"num_tokens": 3081756.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.315201616287231,
|
|
"epoch": 0.1555568035042399,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999788725775601,
|
|
"loss": 6.2108,
|
|
"mean_token_accuracy": 0.14352906197309495,
|
|
"num_tokens": 3093456.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.364352989196777,
|
|
"epoch": 0.15611838041219744,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999783188111737,
|
|
"loss": 6.1434,
|
|
"mean_token_accuracy": 0.15190799832344054,
|
|
"num_tokens": 3104565.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.244580602645874,
|
|
"epoch": 0.156679957320155,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999777578813904,
|
|
"loss": 6.1651,
|
|
"mean_token_accuracy": 0.14751930832862853,
|
|
"num_tokens": 3115577.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.268232011795044,
|
|
"epoch": 0.15724153422811254,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499977189788228,
|
|
"loss": 6.0583,
|
|
"mean_token_accuracy": 0.15186556801199913,
|
|
"num_tokens": 3126019.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.308783960342407,
|
|
"epoch": 0.1578031111360701,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999766145317046,
|
|
"loss": 6.2291,
|
|
"mean_token_accuracy": 0.13733314722776413,
|
|
"num_tokens": 3136191.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.364164161682129,
|
|
"epoch": 0.15836468804402762,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999760321118385,
|
|
"loss": 6.0879,
|
|
"mean_token_accuracy": 0.1505395717918873,
|
|
"num_tokens": 3147737.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.208480882644653,
|
|
"epoch": 0.15892626495198517,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999754425286483,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.14820881485939025,
|
|
"num_tokens": 3158494.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.3466572761535645,
|
|
"epoch": 0.15948784185994272,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999748457821529,
|
|
"loss": 6.183,
|
|
"mean_token_accuracy": 0.1488707736134529,
|
|
"num_tokens": 3170550.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.248150491714478,
|
|
"epoch": 0.16004941876790027,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499974241872371,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.15534067451953887,
|
|
"num_tokens": 3182860.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.263169813156128,
|
|
"epoch": 0.16061099567585782,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999736307993221,
|
|
"loss": 6.1687,
|
|
"mean_token_accuracy": 0.1433172792196274,
|
|
"num_tokens": 3193807.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.20141077041626,
|
|
"epoch": 0.16117257258381534,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999730125630255,
|
|
"loss": 6.0323,
|
|
"mean_token_accuracy": 0.14806009754538535,
|
|
"num_tokens": 3203959.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.278918790817261,
|
|
"epoch": 0.1617341494917729,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999723871635008,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.15965506583452224,
|
|
"num_tokens": 3215416.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.265646123886109,
|
|
"epoch": 0.16229572639973044,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999717546007681,
|
|
"loss": 6.2083,
|
|
"mean_token_accuracy": 0.14182574525475503,
|
|
"num_tokens": 3226938.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.198927593231201,
|
|
"epoch": 0.162857303307688,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999711148748476,
|
|
"loss": 6.0113,
|
|
"mean_token_accuracy": 0.15725158154964447,
|
|
"num_tokens": 3238406.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.139306259155274,
|
|
"epoch": 0.16341888021564555,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999704679857594,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.15332483649253845,
|
|
"num_tokens": 3249695.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.430513477325439,
|
|
"epoch": 0.16398045712360307,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999698139335243,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.15339794158935546,
|
|
"num_tokens": 3259656.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.138534164428711,
|
|
"epoch": 0.16454203403156062,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999691527181632,
|
|
"loss": 6.0103,
|
|
"mean_token_accuracy": 0.15821679681539536,
|
|
"num_tokens": 3269712.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.10054726600647,
|
|
"epoch": 0.16510361093951817,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999684843396968,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.1602013364434242,
|
|
"num_tokens": 3280343.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.187516689300537,
|
|
"epoch": 0.16566518784747572,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999678087981467,
|
|
"loss": 6.0398,
|
|
"mean_token_accuracy": 0.1516653686761856,
|
|
"num_tokens": 3291649.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.330076074600219,
|
|
"epoch": 0.16622676475543324,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999671260935343,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.15116648524999618,
|
|
"num_tokens": 3304190.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.137814521789551,
|
|
"epoch": 0.1667883416633908,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999664362258814,
|
|
"loss": 5.945,
|
|
"mean_token_accuracy": 0.15754275172948837,
|
|
"num_tokens": 3313966.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.239295911788941,
|
|
"epoch": 0.16734991857134834,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999657391952099,
|
|
"loss": 6.1924,
|
|
"mean_token_accuracy": 0.14727808460593222,
|
|
"num_tokens": 3326017.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.257507610321045,
|
|
"epoch": 0.1679114954793059,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499965035001542,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.14670320898294448,
|
|
"num_tokens": 3338264.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.237432384490967,
|
|
"epoch": 0.16847307238726345,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999643236449001,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.1596009373664856,
|
|
"num_tokens": 3348901.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.235905361175537,
|
|
"epoch": 0.16903464929522097,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999636051253069,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.15173731446266175,
|
|
"num_tokens": 3358441.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.294967842102051,
|
|
"epoch": 0.16959622620317852,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999628794427854,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.15502254366874696,
|
|
"num_tokens": 3369334.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.230111169815063,
|
|
"epoch": 0.17015780311113607,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999621465973583,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.1490892805159092,
|
|
"num_tokens": 3380698.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.401267576217651,
|
|
"epoch": 0.17071938001909362,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999614065890495,
|
|
"loss": 6.1586,
|
|
"mean_token_accuracy": 0.14243442714214324,
|
|
"num_tokens": 3391061.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.223486804962159,
|
|
"epoch": 0.17128095692705117,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999606594178821,
|
|
"loss": 6.2143,
|
|
"mean_token_accuracy": 0.14877415746450423,
|
|
"num_tokens": 3403983.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.3232080936431885,
|
|
"epoch": 0.1718425338350087,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049995990508388,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.1495580181479454,
|
|
"num_tokens": 3413838.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.128076457977295,
|
|
"epoch": 0.17240411074296624,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999591435870674,
|
|
"loss": 5.9598,
|
|
"mean_token_accuracy": 0.15457928329706191,
|
|
"num_tokens": 3423978.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.287269401550293,
|
|
"epoch": 0.1729656876509238,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999583749274684,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.15106903314590453,
|
|
"num_tokens": 3433416.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.143144655227661,
|
|
"epoch": 0.17352726455888134,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999575991051074,
|
|
"loss": 5.9773,
|
|
"mean_token_accuracy": 0.15837069898843764,
|
|
"num_tokens": 3444983.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.186607074737549,
|
|
"epoch": 0.1740888414668389,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999568161200093,
|
|
"loss": 5.9651,
|
|
"mean_token_accuracy": 0.15607634782791138,
|
|
"num_tokens": 3455808.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.141094207763672,
|
|
"epoch": 0.17465041837479642,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999560259721989,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.1467524640262127,
|
|
"num_tokens": 3467503.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.361791515350342,
|
|
"epoch": 0.17521199528275397,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999552286617014,
|
|
"loss": 6.3016,
|
|
"mean_token_accuracy": 0.14429757595062256,
|
|
"num_tokens": 3479941.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.129152393341064,
|
|
"epoch": 0.17577357219071152,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999544241885421,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.158864426612854,
|
|
"num_tokens": 3491069.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.282902526855469,
|
|
"epoch": 0.17633514909866907,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999536125527467,
|
|
"loss": 6.1721,
|
|
"mean_token_accuracy": 0.14678503796458245,
|
|
"num_tokens": 3502065.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.311311912536621,
|
|
"epoch": 0.17689672600662662,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499952793754341,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.1542977884411812,
|
|
"num_tokens": 3514228.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.200154161453247,
|
|
"epoch": 0.17745830291458414,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999519677933512,
|
|
"loss": 6.0557,
|
|
"mean_token_accuracy": 0.15597216486930848,
|
|
"num_tokens": 3525801.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.209293603897095,
|
|
"epoch": 0.1780198798225417,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999511346698035,
|
|
"loss": 6.0008,
|
|
"mean_token_accuracy": 0.15367855429649352,
|
|
"num_tokens": 3536431.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.126080894470215,
|
|
"epoch": 0.17858145673049924,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999502943837244,
|
|
"loss": 6.1057,
|
|
"mean_token_accuracy": 0.14980130195617675,
|
|
"num_tokens": 3549098.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.306281661987304,
|
|
"epoch": 0.1791430336384568,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999494469351406,
|
|
"loss": 6.0725,
|
|
"mean_token_accuracy": 0.1504937268793583,
|
|
"num_tokens": 3560532.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.089444303512574,
|
|
"epoch": 0.17970461054641435,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999485923240793,
|
|
"loss": 6.0566,
|
|
"mean_token_accuracy": 0.15513607040047644,
|
|
"num_tokens": 3572175.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.255811595916748,
|
|
"epoch": 0.18026618745437187,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999477305505675,
|
|
"loss": 5.9836,
|
|
"mean_token_accuracy": 0.17298887223005294,
|
|
"num_tokens": 3582862.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.210167360305786,
|
|
"epoch": 0.18082776436232942,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999468616146328,
|
|
"loss": 6.1756,
|
|
"mean_token_accuracy": 0.1523563966155052,
|
|
"num_tokens": 3594685.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.104140567779541,
|
|
"epoch": 0.18138934127028697,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999459855163026,
|
|
"loss": 5.9615,
|
|
"mean_token_accuracy": 0.16202931553125383,
|
|
"num_tokens": 3604847.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.271286487579346,
|
|
"epoch": 0.18195091817824452,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499945102255605,
|
|
"loss": 6.0582,
|
|
"mean_token_accuracy": 0.15297539979219438,
|
|
"num_tokens": 3615549.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.103758001327515,
|
|
"epoch": 0.18251249508620204,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999442118325682,
|
|
"loss": 5.9676,
|
|
"mean_token_accuracy": 0.1630454882979393,
|
|
"num_tokens": 3626300.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.127223777770996,
|
|
"epoch": 0.1830740719941596,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999433142472205,
|
|
"loss": 5.9958,
|
|
"mean_token_accuracy": 0.15685569494962692,
|
|
"num_tokens": 3637832.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.177744150161743,
|
|
"epoch": 0.18363564890211714,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999424094995902,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.14781517460942267,
|
|
"num_tokens": 3649179.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.183869218826294,
|
|
"epoch": 0.1841972258100747,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999414975897066,
|
|
"loss": 6.072,
|
|
"mean_token_accuracy": 0.14898845106363295,
|
|
"num_tokens": 3660011.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.244912004470825,
|
|
"epoch": 0.18475880271803224,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999405785175983,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.14797591269016266,
|
|
"num_tokens": 3672791.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.1082813262939455,
|
|
"epoch": 0.18532037962598977,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999396522832949,
|
|
"loss": 5.971,
|
|
"mean_token_accuracy": 0.15111488699913025,
|
|
"num_tokens": 3684709.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.10607328414917,
|
|
"epoch": 0.18588195653394732,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999387188868256,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.1563703805208206,
|
|
"num_tokens": 3694675.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.061730670928955,
|
|
"epoch": 0.18644353344190487,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999377783282203,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.15275903791189194,
|
|
"num_tokens": 3706384.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.269464302062988,
|
|
"epoch": 0.18700511034986242,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999368306075089,
|
|
"loss": 6.0202,
|
|
"mean_token_accuracy": 0.15324059426784514,
|
|
"num_tokens": 3717419.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.155914354324341,
|
|
"epoch": 0.18756668725781997,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999358757247215,
|
|
"loss": 6.0503,
|
|
"mean_token_accuracy": 0.1521863892674446,
|
|
"num_tokens": 3727306.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.2568072319030765,
|
|
"epoch": 0.1881282641657775,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999349136798886,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.14885527342557908,
|
|
"num_tokens": 3739476.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.100805997848511,
|
|
"epoch": 0.18868984107373504,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999339444730409,
|
|
"loss": 5.933,
|
|
"mean_token_accuracy": 0.15855167657136918,
|
|
"num_tokens": 3751035.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.170141315460205,
|
|
"epoch": 0.1892514179816926,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999329681042092,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.1590510666370392,
|
|
"num_tokens": 3762881.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.138400840759277,
|
|
"epoch": 0.18981299488965014,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999319845734243,
|
|
"loss": 6.044,
|
|
"mean_token_accuracy": 0.15163577049970628,
|
|
"num_tokens": 3774180.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.174570465087891,
|
|
"epoch": 0.1903745717976077,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999309938807181,
|
|
"loss": 6.0303,
|
|
"mean_token_accuracy": 0.1562027633190155,
|
|
"num_tokens": 3784864.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.1436539649963375,
|
|
"epoch": 0.19093614870556522,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999299960261216,
|
|
"loss": 6.0096,
|
|
"mean_token_accuracy": 0.15322427898645402,
|
|
"num_tokens": 3797693.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.201740980148315,
|
|
"epoch": 0.19149772561352277,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999289910096669,
|
|
"loss": 6.0241,
|
|
"mean_token_accuracy": 0.15492813885211945,
|
|
"num_tokens": 3809379.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.070269393920898,
|
|
"epoch": 0.19205930252148032,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999279788313858,
|
|
"loss": 5.8698,
|
|
"mean_token_accuracy": 0.16566905826330186,
|
|
"num_tokens": 3819473.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.977046871185303,
|
|
"epoch": 0.19262087942943787,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999269594913107,
|
|
"loss": 5.8641,
|
|
"mean_token_accuracy": 0.1651919439435005,
|
|
"num_tokens": 3831037.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.101950931549072,
|
|
"epoch": 0.19318245633739542,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999259329894739,
|
|
"loss": 6.0162,
|
|
"mean_token_accuracy": 0.1505047082901001,
|
|
"num_tokens": 3841767.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.011256885528565,
|
|
"epoch": 0.19374403324535294,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999248993259081,
|
|
"loss": 5.8642,
|
|
"mean_token_accuracy": 0.16040490120649337,
|
|
"num_tokens": 3851629.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.124179744720459,
|
|
"epoch": 0.1943056101533105,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999238585006463,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.15869803428649903,
|
|
"num_tokens": 3863247.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.08483362197876,
|
|
"epoch": 0.19486718706126804,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999228105137218,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.15641646683216096,
|
|
"num_tokens": 3873949.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.134666872024536,
|
|
"epoch": 0.1954287639692256,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999217553651676,
|
|
"loss": 6.0202,
|
|
"mean_token_accuracy": 0.1586867719888687,
|
|
"num_tokens": 3884992.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.211376428604126,
|
|
"epoch": 0.19599034087718312,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999206930550175,
|
|
"loss": 6.1354,
|
|
"mean_token_accuracy": 0.15906748920679092,
|
|
"num_tokens": 3897029.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.0789470195770265,
|
|
"epoch": 0.19655191778514067,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999196235833054,
|
|
"loss": 5.9818,
|
|
"mean_token_accuracy": 0.15585362017154694,
|
|
"num_tokens": 3909510.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.10754165649414,
|
|
"epoch": 0.19711349469309822,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999185469500651,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.1578446224331856,
|
|
"num_tokens": 3920593.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.169074296951294,
|
|
"epoch": 0.19767507160105577,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499917463155331,
|
|
"loss": 6.0256,
|
|
"mean_token_accuracy": 0.1516920581459999,
|
|
"num_tokens": 3932215.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.106430435180664,
|
|
"epoch": 0.19823664850901332,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999163721991378,
|
|
"loss": 5.9855,
|
|
"mean_token_accuracy": 0.1580495446920395,
|
|
"num_tokens": 3943876.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.031008052825928,
|
|
"epoch": 0.19879822541697084,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049991527408152,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.15963634550571443,
|
|
"num_tokens": 3954533.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.156386280059815,
|
|
"epoch": 0.1993598023249284,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999141688025127,
|
|
"loss": 6.0307,
|
|
"mean_token_accuracy": 0.16017568558454515,
|
|
"num_tokens": 3965722.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.099786853790283,
|
|
"epoch": 0.19992137923288594,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499913056362151,
|
|
"loss": 5.9427,
|
|
"mean_token_accuracy": 0.15914792269468309,
|
|
"num_tokens": 3976737.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.102410745620728,
|
|
"epoch": 0.2004829561408435,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999119367604703,
|
|
"loss": 6.0445,
|
|
"mean_token_accuracy": 0.1580652192234993,
|
|
"num_tokens": 3986102.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.172822618484497,
|
|
"epoch": 0.20104453304880104,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999108099975064,
|
|
"loss": 5.995,
|
|
"mean_token_accuracy": 0.1587173655629158,
|
|
"num_tokens": 3996534.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.050444316864014,
|
|
"epoch": 0.20160610995675857,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499909676073295,
|
|
"loss": 5.9112,
|
|
"mean_token_accuracy": 0.15411415696144104,
|
|
"num_tokens": 4006947.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.077579498291016,
|
|
"epoch": 0.20216768686471612,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999085349878723,
|
|
"loss": 5.9524,
|
|
"mean_token_accuracy": 0.16510123014450073,
|
|
"num_tokens": 4017723.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.076634263992309,
|
|
"epoch": 0.20272926377267367,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999073867412746,
|
|
"loss": 6.0289,
|
|
"mean_token_accuracy": 0.15287718251347543,
|
|
"num_tokens": 4028347.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.067677736282349,
|
|
"epoch": 0.20329084068063122,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999062313335385,
|
|
"loss": 5.8889,
|
|
"mean_token_accuracy": 0.1635470509529114,
|
|
"num_tokens": 4039648.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.1201819896698,
|
|
"epoch": 0.20385241758858877,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999050687647008,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.15459056794643403,
|
|
"num_tokens": 4050786.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.141393518447876,
|
|
"epoch": 0.2044139944965463,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999038990347984,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.16119525581598282,
|
|
"num_tokens": 4061184.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.207761764526367,
|
|
"epoch": 0.20497557140450384,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999027221438688,
|
|
"loss": 6.1171,
|
|
"mean_token_accuracy": 0.15378198772668839,
|
|
"num_tokens": 4073607.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.042503595352173,
|
|
"epoch": 0.2055371483124614,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499901538091949,
|
|
"loss": 5.9276,
|
|
"mean_token_accuracy": 0.15577400028705596,
|
|
"num_tokens": 4083924.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.11335186958313,
|
|
"epoch": 0.20609872522041894,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999003468790773,
|
|
"loss": 5.9258,
|
|
"mean_token_accuracy": 0.15859550833702088,
|
|
"num_tokens": 4094083.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.091872358322144,
|
|
"epoch": 0.2066603021283765,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998991485052911,
|
|
"loss": 5.961,
|
|
"mean_token_accuracy": 0.1666373997926712,
|
|
"num_tokens": 4105124.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.17498631477356,
|
|
"epoch": 0.20722187903633402,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499897942970629,
|
|
"loss": 6.1215,
|
|
"mean_token_accuracy": 0.1484576180577278,
|
|
"num_tokens": 4116792.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.292929363250733,
|
|
"epoch": 0.20778345594429157,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499896730275129,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.14851790070533752,
|
|
"num_tokens": 4127441.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.086349821090698,
|
|
"epoch": 0.20834503285224912,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00049989551041883,
|
|
"loss": 6.0809,
|
|
"mean_token_accuracy": 0.15333859026432037,
|
|
"num_tokens": 4138696.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.135968160629273,
|
|
"epoch": 0.20890660976020667,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998942834017707,
|
|
"loss": 5.9533,
|
|
"mean_token_accuracy": 0.15621326714754105,
|
|
"num_tokens": 4151254.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.997674369812012,
|
|
"epoch": 0.2094681866681642,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998930492239901,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.15729122012853622,
|
|
"num_tokens": 4162046.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.080434846878052,
|
|
"epoch": 0.21002976357612174,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998918078855277,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.16310780197381974,
|
|
"num_tokens": 4172409.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.069913625717163,
|
|
"epoch": 0.2105913404840793,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998905593864227,
|
|
"loss": 6.0241,
|
|
"mean_token_accuracy": 0.16471444964408874,
|
|
"num_tokens": 4182949.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.122161340713501,
|
|
"epoch": 0.21115291739203684,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998893037267153,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.15665073543787003,
|
|
"num_tokens": 4194164.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.155545330047607,
|
|
"epoch": 0.2117144942999944,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998880409064452,
|
|
"loss": 5.9416,
|
|
"mean_token_accuracy": 0.1604766234755516,
|
|
"num_tokens": 4206056.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.998275089263916,
|
|
"epoch": 0.21227607120795192,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998867709256527,
|
|
"loss": 6.0195,
|
|
"mean_token_accuracy": 0.1543448567390442,
|
|
"num_tokens": 4216660.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.106033754348755,
|
|
"epoch": 0.21283764811590947,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499885493784378,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.1672811269760132,
|
|
"num_tokens": 4228495.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.029328441619873,
|
|
"epoch": 0.21339922502386702,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998842094826621,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.15779903531074524,
|
|
"num_tokens": 4238560.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.210692977905273,
|
|
"epoch": 0.21396080193182457,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998829180205458,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.15292961820960044,
|
|
"num_tokens": 4250553.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.1289863109588625,
|
|
"epoch": 0.21452237883978212,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998816193980701,
|
|
"loss": 6.0255,
|
|
"mean_token_accuracy": 0.15285986065864562,
|
|
"num_tokens": 4262050.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.189714097976685,
|
|
"epoch": 0.21508395574773964,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998803136152764,
|
|
"loss": 5.9742,
|
|
"mean_token_accuracy": 0.15248434990644455,
|
|
"num_tokens": 4273019.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.069318389892578,
|
|
"epoch": 0.2156455326556972,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998790006722063,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.16439094692468642,
|
|
"num_tokens": 4283585.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.011609268188477,
|
|
"epoch": 0.21620710956365474,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998776805689016,
|
|
"loss": 5.9419,
|
|
"mean_token_accuracy": 0.16155797690153123,
|
|
"num_tokens": 4294905.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.21407265663147,
|
|
"epoch": 0.2167686864716123,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998763533054045,
|
|
"loss": 6.0508,
|
|
"mean_token_accuracy": 0.1579398825764656,
|
|
"num_tokens": 4305926.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.9719137191772464,
|
|
"epoch": 0.21733026337956984,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998750188817568,
|
|
"loss": 6.024,
|
|
"mean_token_accuracy": 0.1534085601568222,
|
|
"num_tokens": 4318297.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.118768739700317,
|
|
"epoch": 0.21789184028752737,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998736772980015,
|
|
"loss": 5.8435,
|
|
"mean_token_accuracy": 0.1607772260904312,
|
|
"num_tokens": 4328795.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.974378633499145,
|
|
"epoch": 0.21845341719548492,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499872328554181,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.16153356730937957,
|
|
"num_tokens": 4340279.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.151049709320068,
|
|
"epoch": 0.21901499410344247,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998709726503383,
|
|
"loss": 6.0365,
|
|
"mean_token_accuracy": 0.15092452690005304,
|
|
"num_tokens": 4352157.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.07116470336914,
|
|
"epoch": 0.21957657101140002,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998696095865168,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.16288214921951294,
|
|
"num_tokens": 4361909.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.853420877456665,
|
|
"epoch": 0.22013814791935757,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998682393627595,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.1609992802143097,
|
|
"num_tokens": 4372177.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.081985902786255,
|
|
"epoch": 0.2206997248273151,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998668619791104,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.16345320641994476,
|
|
"num_tokens": 4382872.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.015959978103638,
|
|
"epoch": 0.22126130173527264,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998654774356131,
|
|
"loss": 5.942,
|
|
"mean_token_accuracy": 0.15784113109111786,
|
|
"num_tokens": 4393623.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.030070972442627,
|
|
"epoch": 0.2218228786432302,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998640857323118,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.15540042966604234,
|
|
"num_tokens": 4404215.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.12239670753479,
|
|
"epoch": 0.22238445555118774,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998626868692509,
|
|
"loss": 6.1297,
|
|
"mean_token_accuracy": 0.15531746223568915,
|
|
"num_tokens": 4415978.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.103342962265015,
|
|
"epoch": 0.2229460324591453,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998612808464748,
|
|
"loss": 5.8857,
|
|
"mean_token_accuracy": 0.1632543236017227,
|
|
"num_tokens": 4427060.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.013435125350952,
|
|
"epoch": 0.22350760936710282,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998598676640283,
|
|
"loss": 5.9535,
|
|
"mean_token_accuracy": 0.15278794541954993,
|
|
"num_tokens": 4438145.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.176746988296509,
|
|
"epoch": 0.22406918627506037,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998584473219563,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.16004208326339722,
|
|
"num_tokens": 4449324.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.992343759536743,
|
|
"epoch": 0.22463076318301792,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998570198203043,
|
|
"loss": 5.7561,
|
|
"mean_token_accuracy": 0.1650302827358246,
|
|
"num_tokens": 4459728.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.014521694183349,
|
|
"epoch": 0.22519234009097547,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998555851591175,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.161544968187809,
|
|
"num_tokens": 4471164.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.107461452484131,
|
|
"epoch": 0.225753916998933,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998541433384416,
|
|
"loss": 6.0283,
|
|
"mean_token_accuracy": 0.16004153192043305,
|
|
"num_tokens": 4483349.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.108623361587524,
|
|
"epoch": 0.22631549390689054,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998526943583226,
|
|
"loss": 5.9901,
|
|
"mean_token_accuracy": 0.15583523511886596,
|
|
"num_tokens": 4495311.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.01443190574646,
|
|
"epoch": 0.2268770708148481,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998512382188066,
|
|
"loss": 5.9136,
|
|
"mean_token_accuracy": 0.16296836510300636,
|
|
"num_tokens": 4507017.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.0663471698760985,
|
|
"epoch": 0.22743864772280564,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998497749199401,
|
|
"loss": 5.9618,
|
|
"mean_token_accuracy": 0.15825531929731368,
|
|
"num_tokens": 4517746.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.141182708740234,
|
|
"epoch": 0.2280002246307632,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998483044617694,
|
|
"loss": 6.0486,
|
|
"mean_token_accuracy": 0.15095944553613663,
|
|
"num_tokens": 4529149.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.051037979125977,
|
|
"epoch": 0.22856180153872072,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998468268443416,
|
|
"loss": 5.9215,
|
|
"mean_token_accuracy": 0.1605049952864647,
|
|
"num_tokens": 4540630.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.922482109069824,
|
|
"epoch": 0.22912337844667827,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998453420677034,
|
|
"loss": 5.8671,
|
|
"mean_token_accuracy": 0.1568058595061302,
|
|
"num_tokens": 4552877.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.109559631347656,
|
|
"epoch": 0.22968495535463582,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998438501319025,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.16576798111200333,
|
|
"num_tokens": 4563634.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.006631994247437,
|
|
"epoch": 0.23024653226259337,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998423510369862,
|
|
"loss": 5.8817,
|
|
"mean_token_accuracy": 0.16414335668087005,
|
|
"num_tokens": 4574007.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.055240154266357,
|
|
"epoch": 0.23080810917055092,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998408447830022,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.1573481395840645,
|
|
"num_tokens": 4584146.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.047984170913696,
|
|
"epoch": 0.23136968607850844,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998393313699985,
|
|
"loss": 5.9022,
|
|
"mean_token_accuracy": 0.15559675097465514,
|
|
"num_tokens": 4594839.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.17945294380188,
|
|
"epoch": 0.231931262986466,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998378107980233,
|
|
"loss": 6.0713,
|
|
"mean_token_accuracy": 0.15039688497781753,
|
|
"num_tokens": 4608229.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.033313131332397,
|
|
"epoch": 0.23249283989442354,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998362830671249,
|
|
"loss": 5.8768,
|
|
"mean_token_accuracy": 0.1581628516316414,
|
|
"num_tokens": 4619206.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.999654817581177,
|
|
"epoch": 0.2330544168023811,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998347481773522,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.16410871893167495,
|
|
"num_tokens": 4628966.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.044484996795655,
|
|
"epoch": 0.23361599371033864,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998332061287538,
|
|
"loss": 5.7844,
|
|
"mean_token_accuracy": 0.1657311201095581,
|
|
"num_tokens": 4639935.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.110540771484375,
|
|
"epoch": 0.23417757061829617,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499831656921379,
|
|
"loss": 6.0312,
|
|
"mean_token_accuracy": 0.15397130995988845,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.098618364334106,
|
|
"epoch": 0.23473914752625372,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499830100555277,
|
|
"loss": 6.0119,
|
|
"mean_token_accuracy": 0.15659218579530715,
|
|
"num_tokens": 4664002.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.0605607509613035,
|
|
"epoch": 0.23530072443421127,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998285370304974,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.1646180883049965,
|
|
"num_tokens": 4675343.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.067137908935547,
|
|
"epoch": 0.23586230134216882,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049982696634709,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.16149791181087494,
|
|
"num_tokens": 4686410.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.0088635921478275,
|
|
"epoch": 0.23642387825012637,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998253885051048,
|
|
"loss": 5.9631,
|
|
"mean_token_accuracy": 0.15998635888099672,
|
|
"num_tokens": 4697768.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.186365938186645,
|
|
"epoch": 0.2369854551580839,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499823803504592,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.15657732859253884,
|
|
"num_tokens": 4709933.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.0428260326385494,
|
|
"epoch": 0.23754703206604144,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998222113456022,
|
|
"loss": 6.0053,
|
|
"mean_token_accuracy": 0.15467410236597062,
|
|
"num_tokens": 4721385.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.994955587387085,
|
|
"epoch": 0.238108608973999,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998206120281858,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.166511407494545,
|
|
"num_tokens": 4732562.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.013138246536255,
|
|
"epoch": 0.23867018588195654,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499819005552394,
|
|
"loss": 5.8411,
|
|
"mean_token_accuracy": 0.16182543337345123,
|
|
"num_tokens": 4742794.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.936925029754638,
|
|
"epoch": 0.23923176278991407,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998173919182779,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.166377691924572,
|
|
"num_tokens": 4754903.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.010518169403076,
|
|
"epoch": 0.23979333969787162,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499815771125889,
|
|
"loss": 5.8531,
|
|
"mean_token_accuracy": 0.1603682741522789,
|
|
"num_tokens": 4766165.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.016250658035278,
|
|
"epoch": 0.24035491660582917,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998141431752785,
|
|
"loss": 5.8637,
|
|
"mean_token_accuracy": 0.1660080596804619,
|
|
"num_tokens": 4776551.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.132618141174317,
|
|
"epoch": 0.24091649351378672,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998125080664987,
|
|
"loss": 6.0549,
|
|
"mean_token_accuracy": 0.15564174950122833,
|
|
"num_tokens": 4788344.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.058242464065552,
|
|
"epoch": 0.24147807042174427,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998108657996012,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.15423323065042496,
|
|
"num_tokens": 4799314.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.994201755523681,
|
|
"epoch": 0.2420396473297018,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998092163746387,
|
|
"loss": 5.9066,
|
|
"mean_token_accuracy": 0.16130903661251067,
|
|
"num_tokens": 4809588.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.960495901107788,
|
|
"epoch": 0.24260122423765934,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998075597916636,
|
|
"loss": 5.7183,
|
|
"mean_token_accuracy": 0.16946181207895278,
|
|
"num_tokens": 4820076.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.063351583480835,
|
|
"epoch": 0.2431628011456169,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998058960507286,
|
|
"loss": 5.9823,
|
|
"mean_token_accuracy": 0.15857519656419755,
|
|
"num_tokens": 4831504.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.972692489624023,
|
|
"epoch": 0.24372437805357444,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998042251518866,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.16298711746931077,
|
|
"num_tokens": 4842826.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.924139308929443,
|
|
"epoch": 0.244285954961532,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998025470951908,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.1663692355155945,
|
|
"num_tokens": 4853279.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.073525381088257,
|
|
"epoch": 0.24484753186948952,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998008618806949,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.16937669962644578,
|
|
"num_tokens": 4863332.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.015661668777466,
|
|
"epoch": 0.24540910877744707,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997991695084523,
|
|
"loss": 6.0104,
|
|
"mean_token_accuracy": 0.15071545988321305,
|
|
"num_tokens": 4874217.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.107934236526489,
|
|
"epoch": 0.24597068568540462,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997974699785169,
|
|
"loss": 5.8694,
|
|
"mean_token_accuracy": 0.16703585684299468,
|
|
"num_tokens": 4885322.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.851417207717896,
|
|
"epoch": 0.24653226259336217,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997957632909429,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.16415573805570602,
|
|
"num_tokens": 4895546.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.211975765228272,
|
|
"epoch": 0.24709383950131972,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997940494457846,
|
|
"loss": 6.0196,
|
|
"mean_token_accuracy": 0.1556576743721962,
|
|
"num_tokens": 4906957.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.0884904861450195,
|
|
"epoch": 0.24765541640927724,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997923284430967,
|
|
"loss": 5.9478,
|
|
"mean_token_accuracy": 0.1524835154414177,
|
|
"num_tokens": 4917965.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.958709621429444,
|
|
"epoch": 0.2482169933172348,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997906002829338,
|
|
"loss": 5.8409,
|
|
"mean_token_accuracy": 0.16658256202936172,
|
|
"num_tokens": 4928585.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.983714294433594,
|
|
"epoch": 0.24877857022519234,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499788864965351,
|
|
"loss": 5.8507,
|
|
"mean_token_accuracy": 0.15959688723087312,
|
|
"num_tokens": 4939818.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.051799154281616,
|
|
"epoch": 0.2493401471331499,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997871224904036,
|
|
"loss": 5.9405,
|
|
"mean_token_accuracy": 0.15943082571029663,
|
|
"num_tokens": 4951752.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.910864162445068,
|
|
"epoch": 0.24990172404110744,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997853728581468,
|
|
"loss": 5.7656,
|
|
"mean_token_accuracy": 0.1712748274207115,
|
|
"num_tokens": 4961846.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.999048137664795,
|
|
"epoch": 0.250463300949065,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997836160686368,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.1582569435238838,
|
|
"num_tokens": 4973693.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.025012540817261,
|
|
"epoch": 0.25102487785702254,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997818521219291,
|
|
"loss": 5.8269,
|
|
"mean_token_accuracy": 0.16620030850172043,
|
|
"num_tokens": 4986156.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.984764194488525,
|
|
"epoch": 0.25158645476498004,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997800810180803,
|
|
"loss": 5.9095,
|
|
"mean_token_accuracy": 0.16009719669818878,
|
|
"num_tokens": 4997615.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.036053133010864,
|
|
"epoch": 0.2521480316729376,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997783027571464,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.16056618392467498,
|
|
"num_tokens": 5007655.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.977190017700195,
|
|
"epoch": 0.25270960858089514,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997765173391841,
|
|
"loss": 5.9233,
|
|
"mean_token_accuracy": 0.1614665985107422,
|
|
"num_tokens": 5018933.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.129662370681762,
|
|
"epoch": 0.2532711854888527,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997747247642505,
|
|
"loss": 5.9087,
|
|
"mean_token_accuracy": 0.16192703396081926,
|
|
"num_tokens": 5030495.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.987244319915772,
|
|
"epoch": 0.25383276239681024,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997729250324023,
|
|
"loss": 5.9617,
|
|
"mean_token_accuracy": 0.15674430280923843,
|
|
"num_tokens": 5041553.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.0051435947418215,
|
|
"epoch": 0.2543943393047678,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997711181436971,
|
|
"loss": 5.9078,
|
|
"mean_token_accuracy": 0.16368893831968306,
|
|
"num_tokens": 5052312.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.128569221496582,
|
|
"epoch": 0.25495591621272534,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997693040981922,
|
|
"loss": 6.085,
|
|
"mean_token_accuracy": 0.1522883377969265,
|
|
"num_tokens": 5063445.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.1037023067474365,
|
|
"epoch": 0.2555174931206829,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997674828959456,
|
|
"loss": 5.8583,
|
|
"mean_token_accuracy": 0.1592344179749489,
|
|
"num_tokens": 5073052.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.964641094207764,
|
|
"epoch": 0.25607907002864044,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997656545370151,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.16215995848178863,
|
|
"num_tokens": 5084174.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.082666969299316,
|
|
"epoch": 0.256640646936598,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499763819021459,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.16361337155103683,
|
|
"num_tokens": 5094106.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.075915050506592,
|
|
"epoch": 0.2572022238445555,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004997619763493357,
|
|
"loss": 5.9702,
|
|
"mean_token_accuracy": 0.16184501498937606,
|
|
"num_tokens": 5106963.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.9209068775177,
|
|
"epoch": 0.25776380075251304,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499760126520704,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.16060159504413604,
|
|
"num_tokens": 5119476.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.066161727905273,
|
|
"epoch": 0.2583253776604706,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997582695356225,
|
|
"loss": 6.0127,
|
|
"mean_token_accuracy": 0.15276381820440293,
|
|
"num_tokens": 5132169.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.004144668579102,
|
|
"epoch": 0.25888695456842814,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997564053941507,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.1646599918603897,
|
|
"num_tokens": 5143354.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.958068227767944,
|
|
"epoch": 0.2594485314763857,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997545340963478,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.15578429996967316,
|
|
"num_tokens": 5154624.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.065716075897217,
|
|
"epoch": 0.26001010838434324,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997526556422733,
|
|
"loss": 5.8178,
|
|
"mean_token_accuracy": 0.1637489452958107,
|
|
"num_tokens": 5165349.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.9429624557495115,
|
|
"epoch": 0.2605716852923008,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997507700319872,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.16330261379480362,
|
|
"num_tokens": 5175874.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.980010223388672,
|
|
"epoch": 0.26113326220025834,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997488772655492,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.16592907160520554,
|
|
"num_tokens": 5186591.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.940133285522461,
|
|
"epoch": 0.2616948391082159,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997469773430199,
|
|
"loss": 5.8994,
|
|
"mean_token_accuracy": 0.16807617843151093,
|
|
"num_tokens": 5197307.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.951906204223633,
|
|
"epoch": 0.2622564160161734,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997450702644596,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.16079187989234925,
|
|
"num_tokens": 5209868.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.027046060562133,
|
|
"epoch": 0.26281799292413094,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997431560299292,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.16482030898332595,
|
|
"num_tokens": 5220365.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.010868310928345,
|
|
"epoch": 0.2633795698320885,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997412346394894,
|
|
"loss": 5.7749,
|
|
"mean_token_accuracy": 0.16639859229326248,
|
|
"num_tokens": 5231575.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.0061742782592775,
|
|
"epoch": 0.26394114674004604,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997393060932017,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.1627236321568489,
|
|
"num_tokens": 5241852.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.04571762084961,
|
|
"epoch": 0.2645027236480036,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997373703911273,
|
|
"loss": 5.8988,
|
|
"mean_token_accuracy": 0.16516432911157608,
|
|
"num_tokens": 5254536.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.020670461654663,
|
|
"epoch": 0.26506430055596114,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997354275333277,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.16114060282707215,
|
|
"num_tokens": 5264946.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.751336193084716,
|
|
"epoch": 0.2656258774639187,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499733477519865,
|
|
"loss": 5.6596,
|
|
"mean_token_accuracy": 0.1632534980773926,
|
|
"num_tokens": 5275527.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.002241468429565,
|
|
"epoch": 0.26618745437187624,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997315203508013,
|
|
"loss": 5.8389,
|
|
"mean_token_accuracy": 0.16308278292417527,
|
|
"num_tokens": 5285471.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.865285634994507,
|
|
"epoch": 0.2667490312798338,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997295560261988,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.16390506327152252,
|
|
"num_tokens": 5295743.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.007153558731079,
|
|
"epoch": 0.26731060818779134,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049972758454612,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.15694423466920854,
|
|
"num_tokens": 5307963.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.956030988693238,
|
|
"epoch": 0.26787218509574884,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997256059106279,
|
|
"loss": 5.7866,
|
|
"mean_token_accuracy": 0.16542109698057175,
|
|
"num_tokens": 5318394.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.967977046966553,
|
|
"epoch": 0.2684337620037064,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004997236201197853,
|
|
"loss": 6.0107,
|
|
"mean_token_accuracy": 0.15119242966175078,
|
|
"num_tokens": 5331728.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.002740478515625,
|
|
"epoch": 0.26899533891166394,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997216271736554,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.1701723799109459,
|
|
"num_tokens": 5342825.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.016122913360595,
|
|
"epoch": 0.2695569158196215,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997196270723018,
|
|
"loss": 5.8094,
|
|
"mean_token_accuracy": 0.16391160041093827,
|
|
"num_tokens": 5354232.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.991284513473511,
|
|
"epoch": 0.27011849272757904,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997176198157881,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.15782748833298682,
|
|
"num_tokens": 5364807.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.94521279335022,
|
|
"epoch": 0.2706800696355366,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997156054041781,
|
|
"loss": 5.8784,
|
|
"mean_token_accuracy": 0.15805881172418595,
|
|
"num_tokens": 5375593.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.9776763916015625,
|
|
"epoch": 0.27124164654349414,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997135838375362,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.16881559789180756,
|
|
"num_tokens": 5386740.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.918038845062256,
|
|
"epoch": 0.2718032234514517,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997115551159267,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.16638245284557343,
|
|
"num_tokens": 5397732.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.003497171401977,
|
|
"epoch": 0.27236480035940924,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499709519239414,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.15994038432836533,
|
|
"num_tokens": 5409392.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.84049072265625,
|
|
"epoch": 0.2729263772673668,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997074762080632,
|
|
"loss": 5.8188,
|
|
"mean_token_accuracy": 0.17128721624612808,
|
|
"num_tokens": 5420903.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.895452499389648,
|
|
"epoch": 0.2734879541753243,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499705426021939,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.16452100574970246,
|
|
"num_tokens": 5432631.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.933747625350952,
|
|
"epoch": 0.27404953108328184,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499703368681107,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.1722749501466751,
|
|
"num_tokens": 5443463.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.0137842178344725,
|
|
"epoch": 0.2746111079912394,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997013041856326,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.16273341327905655,
|
|
"num_tokens": 5455903.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.063531303405762,
|
|
"epoch": 0.27517268489919694,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996992325355815,
|
|
"loss": 5.8611,
|
|
"mean_token_accuracy": 0.1601864755153656,
|
|
"num_tokens": 5467201.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.9214695453643795,
|
|
"epoch": 0.2757342618071545,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996971537310198,
|
|
"loss": 5.7394,
|
|
"mean_token_accuracy": 0.1641487091779709,
|
|
"num_tokens": 5478109.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.962538623809815,
|
|
"epoch": 0.27629583871511204,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996950677720133,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.1609448343515396,
|
|
"num_tokens": 5489621.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.942273902893066,
|
|
"epoch": 0.2768574156230696,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499692974658629,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.1653575286269188,
|
|
"num_tokens": 5500606.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.997242736816406,
|
|
"epoch": 0.27741899253102714,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996908743909331,
|
|
"loss": 5.7714,
|
|
"mean_token_accuracy": 0.17135910093784332,
|
|
"num_tokens": 5510768.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.871461677551269,
|
|
"epoch": 0.2779805694389847,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996887669689926,
|
|
"loss": 5.7834,
|
|
"mean_token_accuracy": 0.16663116961717606,
|
|
"num_tokens": 5522210.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.993370628356933,
|
|
"epoch": 0.2785421463469422,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996866523928747,
|
|
"loss": 5.906,
|
|
"mean_token_accuracy": 0.1565551370382309,
|
|
"num_tokens": 5533055.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.032248830795288,
|
|
"epoch": 0.27910372325489974,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996845306626467,
|
|
"loss": 5.9126,
|
|
"mean_token_accuracy": 0.16118640154600145,
|
|
"num_tokens": 5544345.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.952008962631226,
|
|
"epoch": 0.2796653001628573,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996824017783759,
|
|
"loss": 5.8219,
|
|
"mean_token_accuracy": 0.16080627143383025,
|
|
"num_tokens": 5556734.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.994874143600464,
|
|
"epoch": 0.28022687707081484,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996802657401304,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.16483049243688583,
|
|
"num_tokens": 5566874.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.973210859298706,
|
|
"epoch": 0.2807884539787724,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996781225479781,
|
|
"loss": 5.8653,
|
|
"mean_token_accuracy": 0.16056755185127258,
|
|
"num_tokens": 5578812.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.982892560958862,
|
|
"epoch": 0.28135003088672994,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996759722019872,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.16154668629169464,
|
|
"num_tokens": 5590021.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.968021821975708,
|
|
"epoch": 0.2819116077946875,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996738147022262,
|
|
"loss": 5.9167,
|
|
"mean_token_accuracy": 0.15916191339492797,
|
|
"num_tokens": 5600921.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.988654041290284,
|
|
"epoch": 0.28247318470264504,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996716500487638,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.16069669425487518,
|
|
"num_tokens": 5610615.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.831103801727295,
|
|
"epoch": 0.2830347616106026,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499669478241669,
|
|
"loss": 5.7641,
|
|
"mean_token_accuracy": 0.16576093584299087,
|
|
"num_tokens": 5621596.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.091034746170044,
|
|
"epoch": 0.28359633851856014,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996672992810108,
|
|
"loss": 5.8097,
|
|
"mean_token_accuracy": 0.17065599262714387,
|
|
"num_tokens": 5633047.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.871144771575928,
|
|
"epoch": 0.28415791542651764,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996651131668587,
|
|
"loss": 5.7919,
|
|
"mean_token_accuracy": 0.16313879787921906,
|
|
"num_tokens": 5644970.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.932213592529297,
|
|
"epoch": 0.2847194923344752,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996629198992823,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.1626256823539734,
|
|
"num_tokens": 5656631.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.9674906730651855,
|
|
"epoch": 0.28528106924243274,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996607194783513,
|
|
"loss": 5.8584,
|
|
"mean_token_accuracy": 0.1576921448111534,
|
|
"num_tokens": 5668808.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.915722131729126,
|
|
"epoch": 0.2858426461503903,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996585119041359,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.16423020511865616,
|
|
"num_tokens": 5679493.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.967693042755127,
|
|
"epoch": 0.28640422305834784,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996562971767063,
|
|
"loss": 5.8304,
|
|
"mean_token_accuracy": 0.16942446082830429,
|
|
"num_tokens": 5689879.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.001515483856201,
|
|
"epoch": 0.2869657999663054,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499654075296133,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.16562376022338868,
|
|
"num_tokens": 5699934.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.961040449142456,
|
|
"epoch": 0.28752737687426294,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499651846262487,
|
|
"loss": 5.8402,
|
|
"mean_token_accuracy": 0.16511016041040422,
|
|
"num_tokens": 5710171.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.93832802772522,
|
|
"epoch": 0.2880889537822205,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996496100758389,
|
|
"loss": 5.8211,
|
|
"mean_token_accuracy": 0.15841380059719085,
|
|
"num_tokens": 5721190.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.034723091125488,
|
|
"epoch": 0.28865053069017804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996473667362604,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.16139888912439346,
|
|
"num_tokens": 5733706.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.9140746116638185,
|
|
"epoch": 0.28921210759813554,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996451162438224,
|
|
"loss": 5.8885,
|
|
"mean_token_accuracy": 0.1655304715037346,
|
|
"num_tokens": 5745712.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.83914361000061,
|
|
"epoch": 0.2897736845060931,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996428585985967,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.1763711154460907,
|
|
"num_tokens": 5757915.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.975746059417725,
|
|
"epoch": 0.29033526141405064,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996405938006553,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.16630038470029831,
|
|
"num_tokens": 5768788.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.969762325286865,
|
|
"epoch": 0.2908968383220082,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996383218500703,
|
|
"loss": 5.7839,
|
|
"mean_token_accuracy": 0.16176656484603882,
|
|
"num_tokens": 5779806.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.840362787246704,
|
|
"epoch": 0.29145841522996574,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499636042746914,
|
|
"loss": 5.754,
|
|
"mean_token_accuracy": 0.16268186420202255,
|
|
"num_tokens": 5790177.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.988736343383789,
|
|
"epoch": 0.2920199921379233,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499633756491259,
|
|
"loss": 5.7853,
|
|
"mean_token_accuracy": 0.16794030368328094,
|
|
"num_tokens": 5800251.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.903754186630249,
|
|
"epoch": 0.29258156904588084,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996314630831781,
|
|
"loss": 5.8661,
|
|
"mean_token_accuracy": 0.16568554937839508,
|
|
"num_tokens": 5812210.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.010973787307739,
|
|
"epoch": 0.2931431459538384,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996291625227443,
|
|
"loss": 5.8473,
|
|
"mean_token_accuracy": 0.1710708886384964,
|
|
"num_tokens": 5823280.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.021354675292969,
|
|
"epoch": 0.29370472286179594,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996268548100307,
|
|
"loss": 5.9222,
|
|
"mean_token_accuracy": 0.15569793581962585,
|
|
"num_tokens": 5835076.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.831182050704956,
|
|
"epoch": 0.2942662997697535,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499624539945111,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.17435432225465775,
|
|
"num_tokens": 5845376.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.840474462509155,
|
|
"epoch": 0.294827876677711,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996222179280589,
|
|
"loss": 5.7454,
|
|
"mean_token_accuracy": 0.1622859939932823,
|
|
"num_tokens": 5857124.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.0213315963745115,
|
|
"epoch": 0.29538945358566854,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996198887589481,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.1605096936225891,
|
|
"num_tokens": 5868681.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.971142911911011,
|
|
"epoch": 0.2959510304936261,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996175524378531,
|
|
"loss": 5.8464,
|
|
"mean_token_accuracy": 0.165427128970623,
|
|
"num_tokens": 5880532.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.9712464809417725,
|
|
"epoch": 0.29651260740158364,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499615208964848,
|
|
"loss": 5.7886,
|
|
"mean_token_accuracy": 0.17320181131362916,
|
|
"num_tokens": 5891582.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.880084705352783,
|
|
"epoch": 0.2970741843095412,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996128583400077,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.16468533724546433,
|
|
"num_tokens": 5903543.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.907572174072266,
|
|
"epoch": 0.29763576121749874,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996105005634066,
|
|
"loss": 5.7894,
|
|
"mean_token_accuracy": 0.1727600485086441,
|
|
"num_tokens": 5913140.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.902091121673584,
|
|
"epoch": 0.2981973381254563,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996081356351202,
|
|
"loss": 5.7472,
|
|
"mean_token_accuracy": 0.1698393240571022,
|
|
"num_tokens": 5924010.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.959113073348999,
|
|
"epoch": 0.29875891503341384,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996057635552237,
|
|
"loss": 5.9362,
|
|
"mean_token_accuracy": 0.16425639539957046,
|
|
"num_tokens": 5936246.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.979541826248169,
|
|
"epoch": 0.2993204919413714,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996033843237925,
|
|
"loss": 5.8277,
|
|
"mean_token_accuracy": 0.15435630530118943,
|
|
"num_tokens": 5947594.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.950691604614258,
|
|
"epoch": 0.29988206884932894,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996009979409025,
|
|
"loss": 5.7607,
|
|
"mean_token_accuracy": 0.1573063001036644,
|
|
"num_tokens": 5957660.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.775152015686035,
|
|
"epoch": 0.30044364575728644,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995986044066295,
|
|
"loss": 5.6079,
|
|
"mean_token_accuracy": 0.1789610669016838,
|
|
"num_tokens": 5968881.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.896370124816895,
|
|
"epoch": 0.301005222665244,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00049959620372105,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.16645503789186478,
|
|
"num_tokens": 5980032.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.799341154098511,
|
|
"epoch": 0.30156679957320154,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995937958842401,
|
|
"loss": 5.7523,
|
|
"mean_token_accuracy": 0.16536690443754196,
|
|
"num_tokens": 5991781.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.909103488922119,
|
|
"epoch": 0.3021283764811591,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995913808962767,
|
|
"loss": 5.8017,
|
|
"mean_token_accuracy": 0.16248384714126587,
|
|
"num_tokens": 6002303.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.048180866241455,
|
|
"epoch": 0.30268995338911664,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995889587572366,
|
|
"loss": 5.8939,
|
|
"mean_token_accuracy": 0.16326897740364074,
|
|
"num_tokens": 6011523.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.917131185531616,
|
|
"epoch": 0.3032515302970742,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499586529467197,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.16807254999876023,
|
|
"num_tokens": 6022169.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.779902648925781,
|
|
"epoch": 0.30381310720503174,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995840930262351,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.1646862246096134,
|
|
"num_tokens": 6033393.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.978853797912597,
|
|
"epoch": 0.3043746841129893,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004995816494344287,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.16036659330129624,
|
|
"num_tokens": 6045365.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.882379770278931,
|
|
"epoch": 0.30493626102094684,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995791986918554,
|
|
"loss": 5.8456,
|
|
"mean_token_accuracy": 0.1643943414092064,
|
|
"num_tokens": 6057482.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.924764823913574,
|
|
"epoch": 0.30549783792890434,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995767407985933,
|
|
"loss": 5.748,
|
|
"mean_token_accuracy": 0.16873836368322373,
|
|
"num_tokens": 6068194.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.872408819198609,
|
|
"epoch": 0.3060594148368619,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995742757547207,
|
|
"loss": 5.7969,
|
|
"mean_token_accuracy": 0.16693959385156631,
|
|
"num_tokens": 6080540.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.886364841461182,
|
|
"epoch": 0.30662099174481944,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499571803560316,
|
|
"loss": 5.8463,
|
|
"mean_token_accuracy": 0.16102577671408652,
|
|
"num_tokens": 6092464.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.98257966041565,
|
|
"epoch": 0.307182568652777,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995693242154581,
|
|
"loss": 5.802,
|
|
"mean_token_accuracy": 0.16416530013084413,
|
|
"num_tokens": 6103242.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.849971914291382,
|
|
"epoch": 0.30774414556073454,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995668377202258,
|
|
"loss": 5.8183,
|
|
"mean_token_accuracy": 0.1640830472111702,
|
|
"num_tokens": 6116383.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.84266676902771,
|
|
"epoch": 0.3083057224686921,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995643440746982,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.17457838654518126,
|
|
"num_tokens": 6126883.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.919090747833252,
|
|
"epoch": 0.30886729937664964,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995618432789548,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.15941525995731354,
|
|
"num_tokens": 6139613.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.950811958312988,
|
|
"epoch": 0.3094288762846072,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995593353330753,
|
|
"loss": 5.8907,
|
|
"mean_token_accuracy": 0.16074301451444625,
|
|
"num_tokens": 6151950.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.862967920303345,
|
|
"epoch": 0.30999045319256474,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995568202371393,
|
|
"loss": 5.6848,
|
|
"mean_token_accuracy": 0.17329418808221816,
|
|
"num_tokens": 6161563.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.823839712142944,
|
|
"epoch": 0.3105520301005223,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995542979912272,
|
|
"loss": 5.7043,
|
|
"mean_token_accuracy": 0.17179031819105148,
|
|
"num_tokens": 6170966.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.878972959518433,
|
|
"epoch": 0.3111136070084798,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995517685954192,
|
|
"loss": 5.7693,
|
|
"mean_token_accuracy": 0.16634240001440048,
|
|
"num_tokens": 6182563.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.939313697814941,
|
|
"epoch": 0.31167518391643734,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995492320497958,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.1600440576672554,
|
|
"num_tokens": 6194495.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.873399639129639,
|
|
"epoch": 0.3122367608243949,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995466883544376,
|
|
"loss": 5.7662,
|
|
"mean_token_accuracy": 0.1647852584719658,
|
|
"num_tokens": 6206594.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.954919242858887,
|
|
"epoch": 0.31279833773235244,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995441375094258,
|
|
"loss": 5.7954,
|
|
"mean_token_accuracy": 0.16247922629117967,
|
|
"num_tokens": 6218371.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.913018321990966,
|
|
"epoch": 0.31335991464031,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995415795148417,
|
|
"loss": 5.7292,
|
|
"mean_token_accuracy": 0.1699868232011795,
|
|
"num_tokens": 6228723.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.919421529769897,
|
|
"epoch": 0.31392149154826754,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995390143707665,
|
|
"loss": 5.9119,
|
|
"mean_token_accuracy": 0.16231555193662645,
|
|
"num_tokens": 6240535.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.8778153419494625,
|
|
"epoch": 0.3144830684562251,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995364420772821,
|
|
"loss": 5.6162,
|
|
"mean_token_accuracy": 0.17505984455347062,
|
|
"num_tokens": 6250643.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.861969089508056,
|
|
"epoch": 0.31504464536418264,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995338626344702,
|
|
"loss": 5.7474,
|
|
"mean_token_accuracy": 0.16888705044984817,
|
|
"num_tokens": 6259569.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.898400115966797,
|
|
"epoch": 0.3156062222721402,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499531276042413,
|
|
"loss": 5.8918,
|
|
"mean_token_accuracy": 0.170860131084919,
|
|
"num_tokens": 6271108.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.952102947235107,
|
|
"epoch": 0.31616779918009774,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995286823011929,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.16026092171669007,
|
|
"num_tokens": 6282352.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.886004495620727,
|
|
"epoch": 0.31672937608805524,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995260814108926,
|
|
"loss": 5.851,
|
|
"mean_token_accuracy": 0.1604265809059143,
|
|
"num_tokens": 6294946.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.816281795501709,
|
|
"epoch": 0.3172909529960128,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995234733715947,
|
|
"loss": 5.6743,
|
|
"mean_token_accuracy": 0.1721860095858574,
|
|
"num_tokens": 6305552.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.833727693557739,
|
|
"epoch": 0.31785252990397034,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995208581833824,
|
|
"loss": 5.73,
|
|
"mean_token_accuracy": 0.17419680058956147,
|
|
"num_tokens": 6315815.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.898771047592163,
|
|
"epoch": 0.3184141068119279,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995182358463388,
|
|
"loss": 5.78,
|
|
"mean_token_accuracy": 0.16381437554955483,
|
|
"num_tokens": 6327384.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.888091230392456,
|
|
"epoch": 0.31897568371988544,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995156063605475,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.162344291806221,
|
|
"num_tokens": 6338083.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.935994815826416,
|
|
"epoch": 0.319537260627843,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004995129697260922,
|
|
"loss": 5.7551,
|
|
"mean_token_accuracy": 0.16952051520347594,
|
|
"num_tokens": 6349058.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.8725059032440186,
|
|
"epoch": 0.32009883753580054,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995103259430569,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.1690447896718979,
|
|
"num_tokens": 6359655.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.961487817764282,
|
|
"epoch": 0.3206604144437581,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995076750115258,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.16322531849145888,
|
|
"num_tokens": 6372088.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.895509099960327,
|
|
"epoch": 0.32122199135171564,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995050169315832,
|
|
"loss": 5.7935,
|
|
"mean_token_accuracy": 0.16238415837287903,
|
|
"num_tokens": 6382946.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.883610486984253,
|
|
"epoch": 0.32178356825967314,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995023517033138,
|
|
"loss": 5.7896,
|
|
"mean_token_accuracy": 0.16411769539117813,
|
|
"num_tokens": 6392591.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.826980686187744,
|
|
"epoch": 0.3223451451676307,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994996793268024,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.17058148384094238,
|
|
"num_tokens": 6403159.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.929961633682251,
|
|
"epoch": 0.32290672207558824,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994969998021342,
|
|
"loss": 5.7521,
|
|
"mean_token_accuracy": 0.16720252335071564,
|
|
"num_tokens": 6414232.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.839997386932373,
|
|
"epoch": 0.3234682989835458,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994943131293944,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.1778748333454132,
|
|
"num_tokens": 6425762.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.903552103042602,
|
|
"epoch": 0.32402987589150334,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004994916193086687,
|
|
"loss": 5.7644,
|
|
"mean_token_accuracy": 0.16310417652130127,
|
|
"num_tokens": 6439077.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.938978385925293,
|
|
"epoch": 0.3245914527994609,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994889183400428,
|
|
"loss": 5.8324,
|
|
"mean_token_accuracy": 0.16593091040849686,
|
|
"num_tokens": 6450425.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.865291404724121,
|
|
"epoch": 0.32515302970741844,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994862102236025,
|
|
"loss": 5.8155,
|
|
"mean_token_accuracy": 0.16792695373296737,
|
|
"num_tokens": 6461347.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.897014474868774,
|
|
"epoch": 0.325714606615376,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994834949594342,
|
|
"loss": 5.7877,
|
|
"mean_token_accuracy": 0.1707422986626625,
|
|
"num_tokens": 6472428.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.895409822463989,
|
|
"epoch": 0.32627618352333354,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994807725476246,
|
|
"loss": 5.7553,
|
|
"mean_token_accuracy": 0.17379966527223586,
|
|
"num_tokens": 6483393.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.895529937744141,
|
|
"epoch": 0.3268377604312911,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994780429882599,
|
|
"loss": 5.7343,
|
|
"mean_token_accuracy": 0.1717408314347267,
|
|
"num_tokens": 6493520.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.796739149093628,
|
|
"epoch": 0.3273993373392486,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004994753062814274,
|
|
"loss": 5.6676,
|
|
"mean_token_accuracy": 0.1763666331768036,
|
|
"num_tokens": 6505282.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.960649013519287,
|
|
"epoch": 0.32796091424720614,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994725624272139,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.17001553177833556,
|
|
"num_tokens": 6516808.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.907238531112671,
|
|
"epoch": 0.3285224911551637,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994698114257071,
|
|
"loss": 5.7925,
|
|
"mean_token_accuracy": 0.16663295030593872,
|
|
"num_tokens": 6529184.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.828442096710205,
|
|
"epoch": 0.32908406806312124,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994670532769944,
|
|
"loss": 5.6616,
|
|
"mean_token_accuracy": 0.1743689388036728,
|
|
"num_tokens": 6539909.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.829112958908081,
|
|
"epoch": 0.3296456449710788,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994642879811637,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.17460112124681473,
|
|
"num_tokens": 6550870.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.865769577026367,
|
|
"epoch": 0.33020722187903634,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499461515538303,
|
|
"loss": 5.764,
|
|
"mean_token_accuracy": 0.1730511799454689,
|
|
"num_tokens": 6561784.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.788119268417359,
|
|
"epoch": 0.3307687987869939,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004994587359485006,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.1722067967057228,
|
|
"num_tokens": 6573422.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.982589244842529,
|
|
"epoch": 0.33133037569495144,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499455949211845,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.17219349592924119,
|
|
"num_tokens": 6584565.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.886816024780273,
|
|
"epoch": 0.331891952602909,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994531553284248,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.16870585829019547,
|
|
"num_tokens": 6594238.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.75544548034668,
|
|
"epoch": 0.3324535295108665,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004994503542983293,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.16708966344594955,
|
|
"num_tokens": 6606309.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.004780960083008,
|
|
"epoch": 0.33301510641882404,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004994475461216472,
|
|
"loss": 5.8607,
|
|
"mean_token_accuracy": 0.1612526834011078,
|
|
"num_tokens": 6617916.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.856878280639648,
|
|
"epoch": 0.3335766833267816,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994447307984684,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.16824225783348085,
|
|
"num_tokens": 6627951.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.817630767822266,
|
|
"epoch": 0.33413826023473914,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004994419083288823,
|
|
"loss": 5.7693,
|
|
"mean_token_accuracy": 0.16544559448957444,
|
|
"num_tokens": 6639285.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.849265623092651,
|
|
"epoch": 0.3346998371426967,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994390787129787,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.17561201453208924,
|
|
"num_tokens": 6649973.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.782076692581176,
|
|
"epoch": 0.33526141405065424,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994362419508478,
|
|
"loss": 5.6531,
|
|
"mean_token_accuracy": 0.17298476547002792,
|
|
"num_tokens": 6660625.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.8877051830291744,
|
|
"epoch": 0.3358229909586118,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00049943339804258,
|
|
"loss": 5.7379,
|
|
"mean_token_accuracy": 0.16518658101558686,
|
|
"num_tokens": 6673191.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.85368161201477,
|
|
"epoch": 0.33638456786656934,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994305469882657,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.17128600776195527,
|
|
"num_tokens": 6683993.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.846784543991089,
|
|
"epoch": 0.3369461447745269,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994276887879957,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.17115221917629242,
|
|
"num_tokens": 6694881.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3369461447745269,
|
|
"eval_entropy": 5.67483484951036,
|
|
"eval_loss": 5.763563632965088,
|
|
"eval_mean_token_accuracy": 0.17509971401080784,
|
|
"eval_num_tokens": 6694881.0,
|
|
"eval_runtime": 18.4605,
|
|
"eval_samples_per_second": 1679.968,
|
|
"eval_steps_per_second": 210.016,
|
|
"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": 1549103788523520.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|