6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.3210444646583552,
|
||
|
|
"eval_steps": 3000,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.742589855194092,
|
||
|
|
"epoch": 0.0005350741077639254,
|
||
|
|
"grad_norm": 4.28125,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.7541,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 10038.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742583560943604,
|
||
|
|
"epoch": 0.0010701482155278507,
|
||
|
|
"grad_norm": 4.5625,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7779,
|
||
|
|
"mean_token_accuracy": 0.0001301236217841506,
|
||
|
|
"num_tokens": 21916.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.74256067276001,
|
||
|
|
"epoch": 0.0016052223232917758,
|
||
|
|
"grad_norm": 4.53125,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.7579,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 33434.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742603588104249,
|
||
|
|
"epoch": 0.0021402964310557014,
|
||
|
|
"grad_norm": 4.4375,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.7083,
|
||
|
|
"mean_token_accuracy": 0.0009079659474082291,
|
||
|
|
"num_tokens": 44216.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742497825622559,
|
||
|
|
"epoch": 0.0026753705388196263,
|
||
|
|
"grad_norm": 4.1875,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 10.6241,
|
||
|
|
"mean_token_accuracy": 0.011269020987674594,
|
||
|
|
"num_tokens": 54874.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742123413085938,
|
||
|
|
"epoch": 0.0032104446465835517,
|
||
|
|
"grad_norm": 3.578125,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 10.5235,
|
||
|
|
"mean_token_accuracy": 0.036691234819591044,
|
||
|
|
"num_tokens": 65085.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.740595722198487,
|
||
|
|
"epoch": 0.003745518754347477,
|
||
|
|
"grad_norm": 3.296875,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 10.4,
|
||
|
|
"mean_token_accuracy": 0.03980725221335888,
|
||
|
|
"num_tokens": 75601.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.73592758178711,
|
||
|
|
"epoch": 0.004280592862111403,
|
||
|
|
"grad_norm": 2.59375,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.305,
|
||
|
|
"mean_token_accuracy": 0.04284566193819046,
|
||
|
|
"num_tokens": 86193.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.72725419998169,
|
||
|
|
"epoch": 0.004815666969875327,
|
||
|
|
"grad_norm": 2.1875,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.2038,
|
||
|
|
"mean_token_accuracy": 0.04451024234294891,
|
||
|
|
"num_tokens": 96957.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.716819572448731,
|
||
|
|
"epoch": 0.005350741077639253,
|
||
|
|
"grad_norm": 1.9921875,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 10.1336,
|
||
|
|
"mean_token_accuracy": 0.046419617533683774,
|
||
|
|
"num_tokens": 108408.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.70680923461914,
|
||
|
|
"epoch": 0.005885815185403178,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 10.0839,
|
||
|
|
"mean_token_accuracy": 0.04571915306150913,
|
||
|
|
"num_tokens": 119273.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.699491024017334,
|
||
|
|
"epoch": 0.006420889293167103,
|
||
|
|
"grad_norm": 1.765625,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 10.0328,
|
||
|
|
"mean_token_accuracy": 0.045481448620557786,
|
||
|
|
"num_tokens": 130817.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.691621112823487,
|
||
|
|
"epoch": 0.006955963400931029,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.9967,
|
||
|
|
"mean_token_accuracy": 0.04715100526809692,
|
||
|
|
"num_tokens": 142599.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.683260250091553,
|
||
|
|
"epoch": 0.007491037508694954,
|
||
|
|
"grad_norm": 1.734375,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.9367,
|
||
|
|
"mean_token_accuracy": 0.04639097899198532,
|
||
|
|
"num_tokens": 153617.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.678304195404053,
|
||
|
|
"epoch": 0.00802611161645888,
|
||
|
|
"grad_norm": 1.546875,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.9037,
|
||
|
|
"mean_token_accuracy": 0.046589919924736024,
|
||
|
|
"num_tokens": 165280.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.674316120147704,
|
||
|
|
"epoch": 0.008561185724222806,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.8497,
|
||
|
|
"mean_token_accuracy": 0.045006733387708664,
|
||
|
|
"num_tokens": 176896.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.66965456008911,
|
||
|
|
"epoch": 0.00909625983198673,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.7994,
|
||
|
|
"mean_token_accuracy": 0.04748752862215042,
|
||
|
|
"num_tokens": 188000.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.65854778289795,
|
||
|
|
"epoch": 0.009631333939750655,
|
||
|
|
"grad_norm": 1.6640625,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.7526,
|
||
|
|
"mean_token_accuracy": 0.04719592090696097,
|
||
|
|
"num_tokens": 199360.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.643428230285645,
|
||
|
|
"epoch": 0.01016640804751458,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.719,
|
||
|
|
"mean_token_accuracy": 0.04324237890541553,
|
||
|
|
"num_tokens": 210214.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.625392246246339,
|
||
|
|
"epoch": 0.010701482155278505,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.5936,
|
||
|
|
"mean_token_accuracy": 0.04677215106785297,
|
||
|
|
"num_tokens": 220567.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.598260879516602,
|
||
|
|
"epoch": 0.011236556263042432,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.501,
|
||
|
|
"mean_token_accuracy": 0.05159270279109478,
|
||
|
|
"num_tokens": 230585.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.57242784500122,
|
||
|
|
"epoch": 0.011771630370806356,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 9.4414,
|
||
|
|
"mean_token_accuracy": 0.06068843938410282,
|
||
|
|
"num_tokens": 241996.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.52662353515625,
|
||
|
|
"epoch": 0.012306704478570282,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 9.4061,
|
||
|
|
"mean_token_accuracy": 0.0571962833404541,
|
||
|
|
"num_tokens": 253348.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.50029878616333,
|
||
|
|
"epoch": 0.012841778586334207,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 9.3061,
|
||
|
|
"mean_token_accuracy": 0.05508606694638729,
|
||
|
|
"num_tokens": 264239.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.464248943328858,
|
||
|
|
"epoch": 0.013376852694098133,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 9.2082,
|
||
|
|
"mean_token_accuracy": 0.05605855137109757,
|
||
|
|
"num_tokens": 274522.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.388753318786621,
|
||
|
|
"epoch": 0.013911926801862057,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 9.0975,
|
||
|
|
"mean_token_accuracy": 0.05725604817271233,
|
||
|
|
"num_tokens": 284492.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.300678062438966,
|
||
|
|
"epoch": 0.014447000909625984,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 9.0275,
|
||
|
|
"mean_token_accuracy": 0.05757311806082725,
|
||
|
|
"num_tokens": 294796.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.245001888275146,
|
||
|
|
"epoch": 0.014982075017389908,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.9879,
|
||
|
|
"mean_token_accuracy": 0.054746798053383824,
|
||
|
|
"num_tokens": 305252.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.183552169799805,
|
||
|
|
"epoch": 0.015517149125153834,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.863,
|
||
|
|
"mean_token_accuracy": 0.0523694459348917,
|
||
|
|
"num_tokens": 315505.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.06383113861084,
|
||
|
|
"epoch": 0.01605222323291776,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.8077,
|
||
|
|
"mean_token_accuracy": 0.05920022949576378,
|
||
|
|
"num_tokens": 326997.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.937602138519287,
|
||
|
|
"epoch": 0.016587297340681685,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.7117,
|
||
|
|
"mean_token_accuracy": 0.05458217263221741,
|
||
|
|
"num_tokens": 338089.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.84811716079712,
|
||
|
|
"epoch": 0.01712237144844561,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 8.6529,
|
||
|
|
"mean_token_accuracy": 0.054475641995668414,
|
||
|
|
"num_tokens": 348536.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.70736255645752,
|
||
|
|
"epoch": 0.017657445556209534,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 8.6324,
|
||
|
|
"mean_token_accuracy": 0.056421706452965736,
|
||
|
|
"num_tokens": 359776.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.479524993896485,
|
||
|
|
"epoch": 0.01819251966397346,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 8.526,
|
||
|
|
"mean_token_accuracy": 0.05786490514874458,
|
||
|
|
"num_tokens": 370810.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.431317043304443,
|
||
|
|
"epoch": 0.018727593771737387,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 8.4965,
|
||
|
|
"mean_token_accuracy": 0.05679596289992332,
|
||
|
|
"num_tokens": 381788.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.251888465881347,
|
||
|
|
"epoch": 0.01926266787950131,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 8.4589,
|
||
|
|
"mean_token_accuracy": 0.05575237199664116,
|
||
|
|
"num_tokens": 391984.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.08928623199463,
|
||
|
|
"epoch": 0.019797741987265235,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 8.4473,
|
||
|
|
"mean_token_accuracy": 0.055337863974273205,
|
||
|
|
"num_tokens": 403430.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.020852279663085,
|
||
|
|
"epoch": 0.02033281609502916,
|
||
|
|
"grad_norm": 0.703125,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 8.4221,
|
||
|
|
"mean_token_accuracy": 0.05334745533764362,
|
||
|
|
"num_tokens": 414467.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.932736873626709,
|
||
|
|
"epoch": 0.020867890202793088,
|
||
|
|
"grad_norm": 0.671875,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 8.3858,
|
||
|
|
"mean_token_accuracy": 0.05892428457736969,
|
||
|
|
"num_tokens": 425752.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.8809063911438,
|
||
|
|
"epoch": 0.02140296431055701,
|
||
|
|
"grad_norm": 0.66796875,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 8.3505,
|
||
|
|
"mean_token_accuracy": 0.06053958684206009,
|
||
|
|
"num_tokens": 435908.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.834921646118165,
|
||
|
|
"epoch": 0.021938038418320937,
|
||
|
|
"grad_norm": 0.7421875,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 8.3934,
|
||
|
|
"mean_token_accuracy": 0.05831273719668388,
|
||
|
|
"num_tokens": 446424.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.796385478973388,
|
||
|
|
"epoch": 0.022473112526084863,
|
||
|
|
"grad_norm": 0.73046875,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 8.3548,
|
||
|
|
"mean_token_accuracy": 0.06081846654415131,
|
||
|
|
"num_tokens": 456854.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.77077407836914,
|
||
|
|
"epoch": 0.02300818663384879,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 8.3721,
|
||
|
|
"mean_token_accuracy": 0.06371170245110988,
|
||
|
|
"num_tokens": 467899.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.727867889404298,
|
||
|
|
"epoch": 0.023543260741612712,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 8.3147,
|
||
|
|
"mean_token_accuracy": 0.05818791352212429,
|
||
|
|
"num_tokens": 478683.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.737598705291749,
|
||
|
|
"epoch": 0.02407833484937664,
|
||
|
|
"grad_norm": 0.7265625,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 8.3471,
|
||
|
|
"mean_token_accuracy": 0.05725232698023319,
|
||
|
|
"num_tokens": 488745.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.692263221740722,
|
||
|
|
"epoch": 0.024613408957140565,
|
||
|
|
"grad_norm": 0.69140625,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 8.4263,
|
||
|
|
"mean_token_accuracy": 0.05620986633002758,
|
||
|
|
"num_tokens": 499448.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.758592700958252,
|
||
|
|
"epoch": 0.02514848306490449,
|
||
|
|
"grad_norm": 0.70703125,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 8.3538,
|
||
|
|
"mean_token_accuracy": 0.06146201193332672,
|
||
|
|
"num_tokens": 510148.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.709297561645508,
|
||
|
|
"epoch": 0.025683557172668414,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 8.2859,
|
||
|
|
"mean_token_accuracy": 0.054982627555727956,
|
||
|
|
"num_tokens": 522093.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.692859649658203,
|
||
|
|
"epoch": 0.02621863128043234,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 8.3126,
|
||
|
|
"mean_token_accuracy": 0.061951137706637384,
|
||
|
|
"num_tokens": 532598.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.706014442443848,
|
||
|
|
"epoch": 0.026753705388196266,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 8.2807,
|
||
|
|
"mean_token_accuracy": 0.05960803255438805,
|
||
|
|
"num_tokens": 542652.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.617518043518066,
|
||
|
|
"epoch": 0.027288779495960192,
|
||
|
|
"grad_norm": 0.6875,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 8.3078,
|
||
|
|
"mean_token_accuracy": 0.06188668571412563,
|
||
|
|
"num_tokens": 552526.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.682402229309082,
|
||
|
|
"epoch": 0.027823853603724115,
|
||
|
|
"grad_norm": 0.73828125,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 8.3288,
|
||
|
|
"mean_token_accuracy": 0.06049223951995373,
|
||
|
|
"num_tokens": 563143.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.659179401397704,
|
||
|
|
"epoch": 0.02835892771148804,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 8.2969,
|
||
|
|
"mean_token_accuracy": 0.060585920512676236,
|
||
|
|
"num_tokens": 573814.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.617346477508544,
|
||
|
|
"epoch": 0.028894001819251967,
|
||
|
|
"grad_norm": 0.6875,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 8.2583,
|
||
|
|
"mean_token_accuracy": 0.0664129201322794,
|
||
|
|
"num_tokens": 585367.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.633615016937256,
|
||
|
|
"epoch": 0.02942907592701589,
|
||
|
|
"grad_norm": 2.453125,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 8.3346,
|
||
|
|
"mean_token_accuracy": 0.06159670241177082,
|
||
|
|
"num_tokens": 595902.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.68937931060791,
|
||
|
|
"epoch": 0.029964150034779816,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 8.229,
|
||
|
|
"mean_token_accuracy": 0.05921008288860321,
|
||
|
|
"num_tokens": 607178.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.568243312835694,
|
||
|
|
"epoch": 0.030499224142543743,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 8.2176,
|
||
|
|
"mean_token_accuracy": 0.06554121486842632,
|
||
|
|
"num_tokens": 618604.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.536308574676514,
|
||
|
|
"epoch": 0.03103429825030767,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 8.2832,
|
||
|
|
"mean_token_accuracy": 0.06573930382728577,
|
||
|
|
"num_tokens": 628111.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.680528736114502,
|
||
|
|
"epoch": 0.03156937235807159,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 8.3211,
|
||
|
|
"mean_token_accuracy": 0.06876323223114014,
|
||
|
|
"num_tokens": 639358.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.595854473114013,
|
||
|
|
"epoch": 0.03210444646583552,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 8.1939,
|
||
|
|
"mean_token_accuracy": 0.0666448600590229,
|
||
|
|
"num_tokens": 649504.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.553579330444336,
|
||
|
|
"epoch": 0.032639520573599444,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 8.2016,
|
||
|
|
"mean_token_accuracy": 0.06504374705255031,
|
||
|
|
"num_tokens": 659924.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.563442516326905,
|
||
|
|
"epoch": 0.03317459468136337,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 8.2419,
|
||
|
|
"mean_token_accuracy": 0.06233549639582634,
|
||
|
|
"num_tokens": 671120.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.586988162994384,
|
||
|
|
"epoch": 0.033709668789127296,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 8.2807,
|
||
|
|
"mean_token_accuracy": 0.06455633044242859,
|
||
|
|
"num_tokens": 681956.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.551072597503662,
|
||
|
|
"epoch": 0.03424474289689122,
|
||
|
|
"grad_norm": 0.74609375,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 8.2646,
|
||
|
|
"mean_token_accuracy": 0.0649121094495058,
|
||
|
|
"num_tokens": 693226.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.662254047393798,
|
||
|
|
"epoch": 0.03477981700465514,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 8.2671,
|
||
|
|
"mean_token_accuracy": 0.06917282193899155,
|
||
|
|
"num_tokens": 704691.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.417178916931153,
|
||
|
|
"epoch": 0.03531489111241907,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 8.2299,
|
||
|
|
"mean_token_accuracy": 0.05973314344882965,
|
||
|
|
"num_tokens": 716000.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.528615379333496,
|
||
|
|
"epoch": 0.035849965220182994,
|
||
|
|
"grad_norm": 0.72265625,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 8.1406,
|
||
|
|
"mean_token_accuracy": 0.06505260914564133,
|
||
|
|
"num_tokens": 726723.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.503752326965332,
|
||
|
|
"epoch": 0.03638503932794692,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 8.1503,
|
||
|
|
"mean_token_accuracy": 0.06767830736935139,
|
||
|
|
"num_tokens": 736740.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.526687812805175,
|
||
|
|
"epoch": 0.03692011343571085,
|
||
|
|
"grad_norm": 1.6953125,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 8.211,
|
||
|
|
"mean_token_accuracy": 0.06581731289625167,
|
||
|
|
"num_tokens": 747567.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.503904342651367,
|
||
|
|
"epoch": 0.03745518754347477,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 8.1534,
|
||
|
|
"mean_token_accuracy": 0.06844821311533451,
|
||
|
|
"num_tokens": 757937.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.430353832244872,
|
||
|
|
"epoch": 0.0379902616512387,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 8.1759,
|
||
|
|
"mean_token_accuracy": 0.07079985812306404,
|
||
|
|
"num_tokens": 768003.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.572574520111084,
|
||
|
|
"epoch": 0.03852533575900262,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 8.2185,
|
||
|
|
"mean_token_accuracy": 0.06302542686462402,
|
||
|
|
"num_tokens": 779098.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.457394027709961,
|
||
|
|
"epoch": 0.039060409866766545,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 8.1942,
|
||
|
|
"mean_token_accuracy": 0.06275034993886948,
|
||
|
|
"num_tokens": 790002.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.509715270996093,
|
||
|
|
"epoch": 0.03959548397453047,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 8.1721,
|
||
|
|
"mean_token_accuracy": 0.06606314815580845,
|
||
|
|
"num_tokens": 800444.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.493050575256348,
|
||
|
|
"epoch": 0.0401305580822944,
|
||
|
|
"grad_norm": 0.75390625,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 8.1172,
|
||
|
|
"mean_token_accuracy": 0.06942100189626217,
|
||
|
|
"num_tokens": 810912.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.490777015686035,
|
||
|
|
"epoch": 0.04066563219005832,
|
||
|
|
"grad_norm": 0.75390625,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 8.2116,
|
||
|
|
"mean_token_accuracy": 0.0633488953113556,
|
||
|
|
"num_tokens": 822809.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.404875659942627,
|
||
|
|
"epoch": 0.04120070629782225,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 8.1156,
|
||
|
|
"mean_token_accuracy": 0.06941530928015709,
|
||
|
|
"num_tokens": 833362.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.491305160522462,
|
||
|
|
"epoch": 0.041735780405586176,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 8.1304,
|
||
|
|
"mean_token_accuracy": 0.0708375744521618,
|
||
|
|
"num_tokens": 844239.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.351639652252198,
|
||
|
|
"epoch": 0.0422708545133501,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 8.1313,
|
||
|
|
"mean_token_accuracy": 0.06419948525726796,
|
||
|
|
"num_tokens": 855178.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.44887342453003,
|
||
|
|
"epoch": 0.04280592862111402,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 8.1241,
|
||
|
|
"mean_token_accuracy": 0.06882764175534248,
|
||
|
|
"num_tokens": 866120.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.451717185974122,
|
||
|
|
"epoch": 0.04334100272887795,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 8.1179,
|
||
|
|
"mean_token_accuracy": 0.07001868635416031,
|
||
|
|
"num_tokens": 876569.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.462645149230957,
|
||
|
|
"epoch": 0.043876076836641874,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 8.1782,
|
||
|
|
"mean_token_accuracy": 0.05914541408419609,
|
||
|
|
"num_tokens": 887580.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.390836906433105,
|
||
|
|
"epoch": 0.0444111509444058,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 8.1122,
|
||
|
|
"mean_token_accuracy": 0.06334667056798934,
|
||
|
|
"num_tokens": 897922.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.458688259124756,
|
||
|
|
"epoch": 0.044946225052169726,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 8.0675,
|
||
|
|
"mean_token_accuracy": 0.06874303668737411,
|
||
|
|
"num_tokens": 908522.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.417051124572755,
|
||
|
|
"epoch": 0.04548129915993365,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 8.0935,
|
||
|
|
"mean_token_accuracy": 0.06554699912667275,
|
||
|
|
"num_tokens": 918253.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.360801124572754,
|
||
|
|
"epoch": 0.04601637326769758,
|
||
|
|
"grad_norm": 0.73828125,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 8.0775,
|
||
|
|
"mean_token_accuracy": 0.07234423086047173,
|
||
|
|
"num_tokens": 929150.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.457652568817139,
|
||
|
|
"epoch": 0.0465514473754615,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 8.1172,
|
||
|
|
"mean_token_accuracy": 0.06926538720726967,
|
||
|
|
"num_tokens": 941041.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.334060573577881,
|
||
|
|
"epoch": 0.047086521483225424,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 8.0663,
|
||
|
|
"mean_token_accuracy": 0.07295753248035908,
|
||
|
|
"num_tokens": 952714.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.448612403869628,
|
||
|
|
"epoch": 0.04762159559098935,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 8.1236,
|
||
|
|
"mean_token_accuracy": 0.06220442913472653,
|
||
|
|
"num_tokens": 964330.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.33154468536377,
|
||
|
|
"epoch": 0.04815666969875328,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 8.0483,
|
||
|
|
"mean_token_accuracy": 0.06833712309598923,
|
||
|
|
"num_tokens": 975257.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.419320106506348,
|
||
|
|
"epoch": 0.0486917438065172,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 8.0769,
|
||
|
|
"mean_token_accuracy": 0.06652066558599472,
|
||
|
|
"num_tokens": 986335.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.301145553588867,
|
||
|
|
"epoch": 0.04922681791428113,
|
||
|
|
"grad_norm": 0.75,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 7.9671,
|
||
|
|
"mean_token_accuracy": 0.07098020166158676,
|
||
|
|
"num_tokens": 997521.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.32881212234497,
|
||
|
|
"epoch": 0.049761892022045055,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 8.0134,
|
||
|
|
"mean_token_accuracy": 0.06557687968015671,
|
||
|
|
"num_tokens": 1008383.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.357664775848388,
|
||
|
|
"epoch": 0.05029696612980898,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 8.0778,
|
||
|
|
"mean_token_accuracy": 0.0682313721626997,
|
||
|
|
"num_tokens": 1020552.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.34301462173462,
|
||
|
|
"epoch": 0.0508320402375729,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 8.0512,
|
||
|
|
"mean_token_accuracy": 0.07024195492267608,
|
||
|
|
"num_tokens": 1031127.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.236884784698486,
|
||
|
|
"epoch": 0.05136711434533683,
|
||
|
|
"grad_norm": 0.74609375,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 7.9657,
|
||
|
|
"mean_token_accuracy": 0.07320996709167957,
|
||
|
|
"num_tokens": 1043209.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.421635818481445,
|
||
|
|
"epoch": 0.05190218845310075,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 8.1023,
|
||
|
|
"mean_token_accuracy": 0.06352589540183544,
|
||
|
|
"num_tokens": 1054032.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.233527374267577,
|
||
|
|
"epoch": 0.05243726256086468,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 7.9292,
|
||
|
|
"mean_token_accuracy": 0.07238206267356873,
|
||
|
|
"num_tokens": 1064565.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.403174209594727,
|
||
|
|
"epoch": 0.052972336668628606,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 8.0765,
|
||
|
|
"mean_token_accuracy": 0.07412495836615562,
|
||
|
|
"num_tokens": 1076352.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.31511640548706,
|
||
|
|
"epoch": 0.05350741077639253,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 8.0,
|
||
|
|
"mean_token_accuracy": 0.0721416525542736,
|
||
|
|
"num_tokens": 1087697.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.30199728012085,
|
||
|
|
"epoch": 0.05404248488415646,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 7.9346,
|
||
|
|
"mean_token_accuracy": 0.07342750616371632,
|
||
|
|
"num_tokens": 1098056.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.233750343322754,
|
||
|
|
"epoch": 0.054577558991920384,
|
||
|
|
"grad_norm": 0.7578125,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 7.9036,
|
||
|
|
"mean_token_accuracy": 0.08062965869903564,
|
||
|
|
"num_tokens": 1109219.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.323031330108643,
|
||
|
|
"epoch": 0.055112633099684304,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 7.987,
|
||
|
|
"mean_token_accuracy": 0.06857425346970558,
|
||
|
|
"num_tokens": 1120248.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.24481725692749,
|
||
|
|
"epoch": 0.05564770720744823,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 8.0086,
|
||
|
|
"mean_token_accuracy": 0.07023427784442901,
|
||
|
|
"num_tokens": 1131278.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.313823032379151,
|
||
|
|
"epoch": 0.056182781315212156,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 8.0227,
|
||
|
|
"mean_token_accuracy": 0.06274679154157639,
|
||
|
|
"num_tokens": 1143147.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.287971687316894,
|
||
|
|
"epoch": 0.05671785542297608,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 7.9215,
|
||
|
|
"mean_token_accuracy": 0.07099093310534954,
|
||
|
|
"num_tokens": 1154316.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.246630001068116,
|
||
|
|
"epoch": 0.05725292953074001,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 7.9763,
|
||
|
|
"mean_token_accuracy": 0.07050252221524715,
|
||
|
|
"num_tokens": 1164696.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.212139987945557,
|
||
|
|
"epoch": 0.057788003638503935,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 7.9621,
|
||
|
|
"mean_token_accuracy": 0.07535928599536419,
|
||
|
|
"num_tokens": 1176129.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.316623306274414,
|
||
|
|
"epoch": 0.05832307774626786,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 7.9772,
|
||
|
|
"mean_token_accuracy": 0.07082564979791642,
|
||
|
|
"num_tokens": 1186499.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.1876971244812,
|
||
|
|
"epoch": 0.05885815185403178,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 7.9314,
|
||
|
|
"mean_token_accuracy": 0.07009159363806247,
|
||
|
|
"num_tokens": 1196841.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.286906814575195,
|
||
|
|
"epoch": 0.059393225961795706,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 7.8784,
|
||
|
|
"mean_token_accuracy": 0.07358456589281559,
|
||
|
|
"num_tokens": 1207647.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.175436544418336,
|
||
|
|
"epoch": 0.05992830006955963,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 7.8812,
|
||
|
|
"mean_token_accuracy": 0.07417330220341682,
|
||
|
|
"num_tokens": 1217072.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.201017284393311,
|
||
|
|
"epoch": 0.06046337417732356,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 7.9853,
|
||
|
|
"mean_token_accuracy": 0.07028395347297192,
|
||
|
|
"num_tokens": 1228564.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.22887988090515,
|
||
|
|
"epoch": 0.060998448285087485,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 7.9124,
|
||
|
|
"mean_token_accuracy": 0.072603465244174,
|
||
|
|
"num_tokens": 1238755.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.181446075439453,
|
||
|
|
"epoch": 0.06153352239285141,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 7.8745,
|
||
|
|
"mean_token_accuracy": 0.07408057898283005,
|
||
|
|
"num_tokens": 1248968.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.16532106399536,
|
||
|
|
"epoch": 0.06206859650061534,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 7.8461,
|
||
|
|
"mean_token_accuracy": 0.07231933623552322,
|
||
|
|
"num_tokens": 1259256.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.09881591796875,
|
||
|
|
"epoch": 0.06260367060837926,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 7.8866,
|
||
|
|
"mean_token_accuracy": 0.07566695511341096,
|
||
|
|
"num_tokens": 1270469.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.216452407836915,
|
||
|
|
"epoch": 0.06313874471614318,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 7.8552,
|
||
|
|
"mean_token_accuracy": 0.07371087111532688,
|
||
|
|
"num_tokens": 1280558.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.129891967773437,
|
||
|
|
"epoch": 0.06367381882390712,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 7.8999,
|
||
|
|
"mean_token_accuracy": 0.06837657615542411,
|
||
|
|
"num_tokens": 1291372.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.213308429718017,
|
||
|
|
"epoch": 0.06420889293167104,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 7.9753,
|
||
|
|
"mean_token_accuracy": 0.06709825992584229,
|
||
|
|
"num_tokens": 1302521.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.23453779220581,
|
||
|
|
"epoch": 0.06474396703943497,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 7.8081,
|
||
|
|
"mean_token_accuracy": 0.07309315800666809,
|
||
|
|
"num_tokens": 1313632.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.05699348449707,
|
||
|
|
"epoch": 0.06527904114719889,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 7.8949,
|
||
|
|
"mean_token_accuracy": 0.07557445764541626,
|
||
|
|
"num_tokens": 1325247.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.185565948486328,
|
||
|
|
"epoch": 0.06581411525496281,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 7.8687,
|
||
|
|
"mean_token_accuracy": 0.07852845974266529,
|
||
|
|
"num_tokens": 1336026.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.095359706878662,
|
||
|
|
"epoch": 0.06634918936272674,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 7.7947,
|
||
|
|
"mean_token_accuracy": 0.07415896467864513,
|
||
|
|
"num_tokens": 1346920.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.091093444824219,
|
||
|
|
"epoch": 0.06688426347049066,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 7.9316,
|
||
|
|
"mean_token_accuracy": 0.0739424929022789,
|
||
|
|
"num_tokens": 1359752.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.266688632965089,
|
||
|
|
"epoch": 0.06741933757825459,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 7.938,
|
||
|
|
"mean_token_accuracy": 0.07053884975612164,
|
||
|
|
"num_tokens": 1370874.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.154129219055175,
|
||
|
|
"epoch": 0.06795441168601851,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 7.8375,
|
||
|
|
"mean_token_accuracy": 0.07769538760185242,
|
||
|
|
"num_tokens": 1382316.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.086437702178955,
|
||
|
|
"epoch": 0.06848948579378245,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 7.8429,
|
||
|
|
"mean_token_accuracy": 0.0740839570760727,
|
||
|
|
"num_tokens": 1394656.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.045439958572388,
|
||
|
|
"epoch": 0.06902455990154636,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 7.8192,
|
||
|
|
"mean_token_accuracy": 0.07973718792200088,
|
||
|
|
"num_tokens": 1405061.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.166390562057495,
|
||
|
|
"epoch": 0.06955963400931028,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 7.7751,
|
||
|
|
"mean_token_accuracy": 0.08227450475096702,
|
||
|
|
"num_tokens": 1415573.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.016403913497925,
|
||
|
|
"epoch": 0.07009470811707422,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 7.8142,
|
||
|
|
"mean_token_accuracy": 0.07414669394493104,
|
||
|
|
"num_tokens": 1426103.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.006370496749877,
|
||
|
|
"epoch": 0.07062978222483814,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 7.8224,
|
||
|
|
"mean_token_accuracy": 0.07035662531852722,
|
||
|
|
"num_tokens": 1437256.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.223912525177003,
|
||
|
|
"epoch": 0.07116485633260207,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 7.7861,
|
||
|
|
"mean_token_accuracy": 0.07515646256506443,
|
||
|
|
"num_tokens": 1446975.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.001112079620361,
|
||
|
|
"epoch": 0.07169993044036599,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 7.8084,
|
||
|
|
"mean_token_accuracy": 0.07363461852073669,
|
||
|
|
"num_tokens": 1457751.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.052605438232423,
|
||
|
|
"epoch": 0.07223500454812992,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 7.7689,
|
||
|
|
"mean_token_accuracy": 0.07661298438906669,
|
||
|
|
"num_tokens": 1468186.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.094243955612182,
|
||
|
|
"epoch": 0.07277007865589384,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 7.8108,
|
||
|
|
"mean_token_accuracy": 0.07768909595906734,
|
||
|
|
"num_tokens": 1479780.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.057337331771851,
|
||
|
|
"epoch": 0.07330515276365776,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 7.7533,
|
||
|
|
"mean_token_accuracy": 0.0778307005763054,
|
||
|
|
"num_tokens": 1490565.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.113437938690186,
|
||
|
|
"epoch": 0.0738402268714217,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 7.7855,
|
||
|
|
"mean_token_accuracy": 0.0767733097076416,
|
||
|
|
"num_tokens": 1501552.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.02952961921692,
|
||
|
|
"epoch": 0.07437530097918561,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 7.7837,
|
||
|
|
"mean_token_accuracy": 0.070881437510252,
|
||
|
|
"num_tokens": 1513311.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.041796684265137,
|
||
|
|
"epoch": 0.07491037508694955,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 7.8081,
|
||
|
|
"mean_token_accuracy": 0.07614933587610721,
|
||
|
|
"num_tokens": 1524142.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.079885721206665,
|
||
|
|
"epoch": 0.07544544919471347,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 7.7634,
|
||
|
|
"mean_token_accuracy": 0.08070720061659813,
|
||
|
|
"num_tokens": 1535571.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.080323457717896,
|
||
|
|
"epoch": 0.0759805233024774,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 7.7663,
|
||
|
|
"mean_token_accuracy": 0.07677763924002648,
|
||
|
|
"num_tokens": 1546528.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.932172536849976,
|
||
|
|
"epoch": 0.07651559741024132,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 7.7928,
|
||
|
|
"mean_token_accuracy": 0.06920730993151665,
|
||
|
|
"num_tokens": 1557264.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.126523494720459,
|
||
|
|
"epoch": 0.07705067151800524,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 7.7492,
|
||
|
|
"mean_token_accuracy": 0.07938187122344971,
|
||
|
|
"num_tokens": 1566773.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.902943658828735,
|
||
|
|
"epoch": 0.07758574562576917,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 7.7072,
|
||
|
|
"mean_token_accuracy": 0.0833115503191948,
|
||
|
|
"num_tokens": 1578173.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.02185640335083,
|
||
|
|
"epoch": 0.07812081973353309,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 7.6767,
|
||
|
|
"mean_token_accuracy": 0.08211550787091255,
|
||
|
|
"num_tokens": 1588537.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.918304061889648,
|
||
|
|
"epoch": 0.07865589384129702,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 7.695,
|
||
|
|
"mean_token_accuracy": 0.08645991012454032,
|
||
|
|
"num_tokens": 1599159.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.982047033309937,
|
||
|
|
"epoch": 0.07919096794906094,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 7.7685,
|
||
|
|
"mean_token_accuracy": 0.07947736382484435,
|
||
|
|
"num_tokens": 1610378.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.9871502876281735,
|
||
|
|
"epoch": 0.07972604205682488,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 7.7684,
|
||
|
|
"mean_token_accuracy": 0.0792300634086132,
|
||
|
|
"num_tokens": 1621215.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.980308580398559,
|
||
|
|
"epoch": 0.0802611161645888,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 7.7133,
|
||
|
|
"mean_token_accuracy": 0.07562910728156566,
|
||
|
|
"num_tokens": 1631170.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.027432918548584,
|
||
|
|
"epoch": 0.08079619027235273,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 7.7105,
|
||
|
|
"mean_token_accuracy": 0.0776789553463459,
|
||
|
|
"num_tokens": 1641897.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.974108934402466,
|
||
|
|
"epoch": 0.08133126438011665,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 7.7762,
|
||
|
|
"mean_token_accuracy": 0.07812840193510055,
|
||
|
|
"num_tokens": 1653592.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.944252681732178,
|
||
|
|
"epoch": 0.08186633848788057,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 7.7089,
|
||
|
|
"mean_token_accuracy": 0.0731413435190916,
|
||
|
|
"num_tokens": 1665760.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.967342901229858,
|
||
|
|
"epoch": 0.0824014125956445,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 7.7065,
|
||
|
|
"mean_token_accuracy": 0.08256332576274872,
|
||
|
|
"num_tokens": 1676211.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.979905366897583,
|
||
|
|
"epoch": 0.08293648670340842,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 7.7411,
|
||
|
|
"mean_token_accuracy": 0.0778872437775135,
|
||
|
|
"num_tokens": 1686405.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.09218454360962,
|
||
|
|
"epoch": 0.08347156081117235,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 7.7171,
|
||
|
|
"mean_token_accuracy": 0.07889893390238285,
|
||
|
|
"num_tokens": 1697340.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.979829883575439,
|
||
|
|
"epoch": 0.08400663491893627,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 7.6184,
|
||
|
|
"mean_token_accuracy": 0.08763319551944733,
|
||
|
|
"num_tokens": 1707250.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.876405382156372,
|
||
|
|
"epoch": 0.0845417090267002,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 7.5864,
|
||
|
|
"mean_token_accuracy": 0.08063115775585175,
|
||
|
|
"num_tokens": 1718333.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.940855836868286,
|
||
|
|
"epoch": 0.08507678313446412,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 7.6984,
|
||
|
|
"mean_token_accuracy": 0.07467846013605595,
|
||
|
|
"num_tokens": 1730520.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.936916255950928,
|
||
|
|
"epoch": 0.08561185724222804,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 7.7522,
|
||
|
|
"mean_token_accuracy": 0.07317487969994545,
|
||
|
|
"num_tokens": 1741898.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.9014006614685055,
|
||
|
|
"epoch": 0.08614693134999198,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 7.6984,
|
||
|
|
"mean_token_accuracy": 0.08368097692728042,
|
||
|
|
"num_tokens": 1751671.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.829085969924927,
|
||
|
|
"epoch": 0.0866820054577559,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 7.7182,
|
||
|
|
"mean_token_accuracy": 0.08191005513072014,
|
||
|
|
"num_tokens": 1762076.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.061158800125122,
|
||
|
|
"epoch": 0.08721707956551983,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 7.685,
|
||
|
|
"mean_token_accuracy": 0.07685056664049625,
|
||
|
|
"num_tokens": 1772666.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.887774229049683,
|
||
|
|
"epoch": 0.08775215367328375,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 7.6979,
|
||
|
|
"mean_token_accuracy": 0.08384055867791176,
|
||
|
|
"num_tokens": 1783621.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.9562437534332275,
|
||
|
|
"epoch": 0.08828722778104768,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 7.7515,
|
||
|
|
"mean_token_accuracy": 0.07828780002892018,
|
||
|
|
"num_tokens": 1794654.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.825522232055664,
|
||
|
|
"epoch": 0.0888223018888116,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 7.6368,
|
||
|
|
"mean_token_accuracy": 0.08319875784218311,
|
||
|
|
"num_tokens": 1805853.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7365336418151855,
|
||
|
|
"epoch": 0.08935737599657552,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 7.6227,
|
||
|
|
"mean_token_accuracy": 0.0816656306385994,
|
||
|
|
"num_tokens": 1817006.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.006308937072754,
|
||
|
|
"epoch": 0.08989245010433945,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 7.623,
|
||
|
|
"mean_token_accuracy": 0.0778016533702612,
|
||
|
|
"num_tokens": 1827166.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.007753992080689,
|
||
|
|
"epoch": 0.09042752421210337,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 7.7146,
|
||
|
|
"mean_token_accuracy": 0.08085944950580597,
|
||
|
|
"num_tokens": 1837182.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7709431648254395,
|
||
|
|
"epoch": 0.0909625983198673,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 7.6545,
|
||
|
|
"mean_token_accuracy": 0.08275943025946617,
|
||
|
|
"num_tokens": 1849034.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.842226839065551,
|
||
|
|
"epoch": 0.09149767242763122,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 7.5383,
|
||
|
|
"mean_token_accuracy": 0.08894663602113724,
|
||
|
|
"num_tokens": 1859033.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.813801717758179,
|
||
|
|
"epoch": 0.09203274653539516,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 7.6562,
|
||
|
|
"mean_token_accuracy": 0.07978184968233108,
|
||
|
|
"num_tokens": 1870274.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.786420011520386,
|
||
|
|
"epoch": 0.09256782064315908,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 7.5977,
|
||
|
|
"mean_token_accuracy": 0.085463797301054,
|
||
|
|
"num_tokens": 1881306.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.810677576065063,
|
||
|
|
"epoch": 0.093102894750923,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 7.5858,
|
||
|
|
"mean_token_accuracy": 0.07887605726718902,
|
||
|
|
"num_tokens": 1892464.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.883417320251465,
|
||
|
|
"epoch": 0.09363796885868693,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 7.6601,
|
||
|
|
"mean_token_accuracy": 0.07597660236060619,
|
||
|
|
"num_tokens": 1903743.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.838293743133545,
|
||
|
|
"epoch": 0.09417304296645085,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 7.6112,
|
||
|
|
"mean_token_accuracy": 0.08703320100903511,
|
||
|
|
"num_tokens": 1915253.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.873800992965698,
|
||
|
|
"epoch": 0.09470811707421478,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 7.5604,
|
||
|
|
"mean_token_accuracy": 0.08356410227715969,
|
||
|
|
"num_tokens": 1926113.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.816686487197876,
|
||
|
|
"epoch": 0.0952431911819787,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 7.6579,
|
||
|
|
"mean_token_accuracy": 0.08339532688260079,
|
||
|
|
"num_tokens": 1937718.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.857083654403686,
|
||
|
|
"epoch": 0.09577826528974263,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 7.6419,
|
||
|
|
"mean_token_accuracy": 0.07871352508664131,
|
||
|
|
"num_tokens": 1948307.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7142290592193605,
|
||
|
|
"epoch": 0.09631333939750655,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 7.4658,
|
||
|
|
"mean_token_accuracy": 0.09317997246980667,
|
||
|
|
"num_tokens": 1957861.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.769102573394775,
|
||
|
|
"epoch": 0.09684841350527049,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 7.5118,
|
||
|
|
"mean_token_accuracy": 0.09313379377126693,
|
||
|
|
"num_tokens": 1967984.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.776102876663208,
|
||
|
|
"epoch": 0.0973834876130344,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 7.531,
|
||
|
|
"mean_token_accuracy": 0.08627012819051742,
|
||
|
|
"num_tokens": 1978608.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.774751234054565,
|
||
|
|
"epoch": 0.09791856172079832,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 7.5571,
|
||
|
|
"mean_token_accuracy": 0.08207484185695649,
|
||
|
|
"num_tokens": 1989355.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.759360122680664,
|
||
|
|
"epoch": 0.09845363582856226,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 7.5519,
|
||
|
|
"mean_token_accuracy": 0.09099748730659485,
|
||
|
|
"num_tokens": 1999754.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7610972881317135,
|
||
|
|
"epoch": 0.09898870993632618,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 7.5582,
|
||
|
|
"mean_token_accuracy": 0.08363260142505169,
|
||
|
|
"num_tokens": 2010877.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.894351291656494,
|
||
|
|
"epoch": 0.09952378404409011,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 7.6443,
|
||
|
|
"mean_token_accuracy": 0.08178722113370895,
|
||
|
|
"num_tokens": 2022301.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.720238924026489,
|
||
|
|
"epoch": 0.10005885815185403,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 7.5376,
|
||
|
|
"mean_token_accuracy": 0.08469678834080696,
|
||
|
|
"num_tokens": 2033537.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.747068881988525,
|
||
|
|
"epoch": 0.10059393225961796,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 7.4595,
|
||
|
|
"mean_token_accuracy": 0.08593985140323639,
|
||
|
|
"num_tokens": 2044360.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.767273759841919,
|
||
|
|
"epoch": 0.10112900636738188,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 7.5692,
|
||
|
|
"mean_token_accuracy": 0.08553824871778488,
|
||
|
|
"num_tokens": 2055000.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.675411987304687,
|
||
|
|
"epoch": 0.1016640804751458,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 7.5747,
|
||
|
|
"mean_token_accuracy": 0.08887513428926468,
|
||
|
|
"num_tokens": 2064807.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.846766614913941,
|
||
|
|
"epoch": 0.10219915458290973,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 7.5338,
|
||
|
|
"mean_token_accuracy": 0.08006390556693077,
|
||
|
|
"num_tokens": 2075618.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.665963554382325,
|
||
|
|
"epoch": 0.10273422869067365,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 7.5318,
|
||
|
|
"mean_token_accuracy": 0.08242494091391564,
|
||
|
|
"num_tokens": 2086226.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.758722734451294,
|
||
|
|
"epoch": 0.10326930279843759,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 7.5213,
|
||
|
|
"mean_token_accuracy": 0.08128740042448043,
|
||
|
|
"num_tokens": 2097222.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.718167400360107,
|
||
|
|
"epoch": 0.1038043769062015,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 7.566,
|
||
|
|
"mean_token_accuracy": 0.08480455204844475,
|
||
|
|
"num_tokens": 2108919.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.67155704498291,
|
||
|
|
"epoch": 0.10433945101396544,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 7.5121,
|
||
|
|
"mean_token_accuracy": 0.08769758641719819,
|
||
|
|
"num_tokens": 2120215.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.774061918258667,
|
||
|
|
"epoch": 0.10487452512172936,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 7.5377,
|
||
|
|
"mean_token_accuracy": 0.08079898655414582,
|
||
|
|
"num_tokens": 2131503.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.695115470886231,
|
||
|
|
"epoch": 0.10540959922949328,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 7.4754,
|
||
|
|
"mean_token_accuracy": 0.09231993854045868,
|
||
|
|
"num_tokens": 2141551.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.619196653366089,
|
||
|
|
"epoch": 0.10594467333725721,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 7.4805,
|
||
|
|
"mean_token_accuracy": 0.0900322899222374,
|
||
|
|
"num_tokens": 2151821.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.718583822250366,
|
||
|
|
"epoch": 0.10647974744502113,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 7.5276,
|
||
|
|
"mean_token_accuracy": 0.08750699013471604,
|
||
|
|
"num_tokens": 2162474.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.677374029159546,
|
||
|
|
"epoch": 0.10701482155278506,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 7.5581,
|
||
|
|
"mean_token_accuracy": 0.08569178096950054,
|
||
|
|
"num_tokens": 2173985.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.77434720993042,
|
||
|
|
"epoch": 0.10754989566054898,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004999999979210101,
|
||
|
|
"loss": 7.588,
|
||
|
|
"mean_token_accuracy": 0.08118958622217179,
|
||
|
|
"num_tokens": 2186432.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.720741939544678,
|
||
|
|
"epoch": 0.10808496976831292,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999999894751138,
|
||
|
|
"loss": 7.4482,
|
||
|
|
"mean_token_accuracy": 0.08467482179403304,
|
||
|
|
"num_tokens": 2197085.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.661213302612305,
|
||
|
|
"epoch": 0.10862004387607684,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999999745323744,
|
||
|
|
"loss": 7.4699,
|
||
|
|
"mean_token_accuracy": 0.09365503117442131,
|
||
|
|
"num_tokens": 2207162.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.673577928543091,
|
||
|
|
"epoch": 0.10915511798384077,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999999530927923,
|
||
|
|
"loss": 7.5611,
|
||
|
|
"mean_token_accuracy": 0.08068385906517506,
|
||
|
|
"num_tokens": 2218714.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6879801750183105,
|
||
|
|
"epoch": 0.10969019209160469,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999999251563682,
|
||
|
|
"loss": 7.48,
|
||
|
|
"mean_token_accuracy": 0.08622352927923202,
|
||
|
|
"num_tokens": 2229711.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.641462993621826,
|
||
|
|
"epoch": 0.11022526619936861,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004999998907231029,
|
||
|
|
"loss": 7.4825,
|
||
|
|
"mean_token_accuracy": 0.08603335320949554,
|
||
|
|
"num_tokens": 2239885.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.723711681365967,
|
||
|
|
"epoch": 0.11076034030713254,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999998497929974,
|
||
|
|
"loss": 7.4942,
|
||
|
|
"mean_token_accuracy": 0.08984629586338996,
|
||
|
|
"num_tokens": 2250221.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.636352014541626,
|
||
|
|
"epoch": 0.11129541441489646,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999998023660527,
|
||
|
|
"loss": 7.5667,
|
||
|
|
"mean_token_accuracy": 0.07426251731812954,
|
||
|
|
"num_tokens": 2261059.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.627584838867188,
|
||
|
|
"epoch": 0.11183048852266039,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004999997484422705,
|
||
|
|
"loss": 7.4364,
|
||
|
|
"mean_token_accuracy": 0.08743720948696136,
|
||
|
|
"num_tokens": 2271174.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.669003200531006,
|
||
|
|
"epoch": 0.11236556263042431,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999996880216521,
|
||
|
|
"loss": 7.5139,
|
||
|
|
"mean_token_accuracy": 0.08555590137839317,
|
||
|
|
"num_tokens": 2282431.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.61585578918457,
|
||
|
|
"epoch": 0.11290063673818825,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999996211041994,
|
||
|
|
"loss": 7.4858,
|
||
|
|
"mean_token_accuracy": 0.0835509292781353,
|
||
|
|
"num_tokens": 2292891.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.677904653549194,
|
||
|
|
"epoch": 0.11343571084595216,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999995476899141,
|
||
|
|
"loss": 7.5005,
|
||
|
|
"mean_token_accuracy": 0.08647905215620995,
|
||
|
|
"num_tokens": 2303764.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.639417934417724,
|
||
|
|
"epoch": 0.11397078495371608,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999994677787987,
|
||
|
|
"loss": 7.4227,
|
||
|
|
"mean_token_accuracy": 0.08917138800024986,
|
||
|
|
"num_tokens": 2314172.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.604849863052368,
|
||
|
|
"epoch": 0.11450585906148002,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999993813708551,
|
||
|
|
"loss": 7.3983,
|
||
|
|
"mean_token_accuracy": 0.09371343329548835,
|
||
|
|
"num_tokens": 2324848.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.562433481216431,
|
||
|
|
"epoch": 0.11504093316924394,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.000499999288466086,
|
||
|
|
"loss": 7.4262,
|
||
|
|
"mean_token_accuracy": 0.0858787901699543,
|
||
|
|
"num_tokens": 2336601.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.615593194961548,
|
||
|
|
"epoch": 0.11557600727700787,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999991890644941,
|
||
|
|
"loss": 7.4123,
|
||
|
|
"mean_token_accuracy": 0.08523132391273976,
|
||
|
|
"num_tokens": 2347281.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5736212730407715,
|
||
|
|
"epoch": 0.11611108138477179,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999990831660822,
|
||
|
|
"loss": 7.4363,
|
||
|
|
"mean_token_accuracy": 0.09456784278154373,
|
||
|
|
"num_tokens": 2358199.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.702199506759643,
|
||
|
|
"epoch": 0.11664615549253572,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999989707708534,
|
||
|
|
"loss": 7.4808,
|
||
|
|
"mean_token_accuracy": 0.08690382875502109,
|
||
|
|
"num_tokens": 2369092.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.544908285140991,
|
||
|
|
"epoch": 0.11718122960029964,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999988518788111,
|
||
|
|
"loss": 7.4507,
|
||
|
|
"mean_token_accuracy": 0.08844347447156906,
|
||
|
|
"num_tokens": 2378849.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.622500801086426,
|
||
|
|
"epoch": 0.11771630370806356,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004999987264899583,
|
||
|
|
"loss": 7.4509,
|
||
|
|
"mean_token_accuracy": 0.09384607821702957,
|
||
|
|
"num_tokens": 2389587.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.658657217025757,
|
||
|
|
"epoch": 0.1182513778158275,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.000499998594604299,
|
||
|
|
"loss": 7.4222,
|
||
|
|
"mean_token_accuracy": 0.09075777530670166,
|
||
|
|
"num_tokens": 2400442.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.513382863998413,
|
||
|
|
"epoch": 0.11878645192359141,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.000499998456221837,
|
||
|
|
"loss": 7.4165,
|
||
|
|
"mean_token_accuracy": 0.09110527783632279,
|
||
|
|
"num_tokens": 2410771.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.624029874801636,
|
||
|
|
"epoch": 0.11932152603135535,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999983113425762,
|
||
|
|
"loss": 7.4209,
|
||
|
|
"mean_token_accuracy": 0.09688404947519302,
|
||
|
|
"num_tokens": 2421112.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.630374145507813,
|
||
|
|
"epoch": 0.11985660013911927,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999981599665207,
|
||
|
|
"loss": 7.4046,
|
||
|
|
"mean_token_accuracy": 0.08740727975964546,
|
||
|
|
"num_tokens": 2431891.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.452549457550049,
|
||
|
|
"epoch": 0.1203916742468832,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999980020936748,
|
||
|
|
"loss": 7.3562,
|
||
|
|
"mean_token_accuracy": 0.0897531658411026,
|
||
|
|
"num_tokens": 2442987.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.609330129623413,
|
||
|
|
"epoch": 0.12092674835464712,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999978377240434,
|
||
|
|
"loss": 7.3982,
|
||
|
|
"mean_token_accuracy": 0.08765116408467293,
|
||
|
|
"num_tokens": 2452703.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.556497859954834,
|
||
|
|
"epoch": 0.12146182246241104,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000499997666857631,
|
||
|
|
"loss": 7.4509,
|
||
|
|
"mean_token_accuracy": 0.09336601346731185,
|
||
|
|
"num_tokens": 2462975.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.558685207366944,
|
||
|
|
"epoch": 0.12199689657017497,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0004999974894944426,
|
||
|
|
"loss": 7.3995,
|
||
|
|
"mean_token_accuracy": 0.08522969335317612,
|
||
|
|
"num_tokens": 2473853.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.575222444534302,
|
||
|
|
"epoch": 0.12253197067793889,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004999973056344832,
|
||
|
|
"loss": 7.3681,
|
||
|
|
"mean_token_accuracy": 0.0891667477786541,
|
||
|
|
"num_tokens": 2485633.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.465674591064453,
|
||
|
|
"epoch": 0.12306704478570282,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999971152777583,
|
||
|
|
"loss": 7.3416,
|
||
|
|
"mean_token_accuracy": 0.08593353554606438,
|
||
|
|
"num_tokens": 2496922.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.701901197433472,
|
||
|
|
"epoch": 0.12360211889346674,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0004999969184242733,
|
||
|
|
"loss": 7.4062,
|
||
|
|
"mean_token_accuracy": 0.09027116596698762,
|
||
|
|
"num_tokens": 2507890.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.481602525711059,
|
||
|
|
"epoch": 0.12413719300123068,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000499996715074034,
|
||
|
|
"loss": 7.4012,
|
||
|
|
"mean_token_accuracy": 0.0900260142982006,
|
||
|
|
"num_tokens": 2519749.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.518426036834716,
|
||
|
|
"epoch": 0.1246722671089946,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999965052270461,
|
||
|
|
"loss": 7.4146,
|
||
|
|
"mean_token_accuracy": 0.08937735855579376,
|
||
|
|
"num_tokens": 2530666.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.581199979782104,
|
||
|
|
"epoch": 0.12520734121675853,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999962888833157,
|
||
|
|
"loss": 7.419,
|
||
|
|
"mean_token_accuracy": 0.08899203762412071,
|
||
|
|
"num_tokens": 2541594.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.519051456451416,
|
||
|
|
"epoch": 0.12574241532452243,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004999960660428491,
|
||
|
|
"loss": 7.4116,
|
||
|
|
"mean_token_accuracy": 0.0924226313829422,
|
||
|
|
"num_tokens": 2552330.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.657570695877075,
|
||
|
|
"epoch": 0.12627748943228637,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999958367056526,
|
||
|
|
"loss": 7.4478,
|
||
|
|
"mean_token_accuracy": 0.08449417613446712,
|
||
|
|
"num_tokens": 2564601.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.51881742477417,
|
||
|
|
"epoch": 0.1268125635400503,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000499995600871733,
|
||
|
|
"loss": 7.4143,
|
||
|
|
"mean_token_accuracy": 0.09234437346458435,
|
||
|
|
"num_tokens": 2575539.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.498287916183472,
|
||
|
|
"epoch": 0.12734763764781423,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004999953585410971,
|
||
|
|
"loss": 7.3524,
|
||
|
|
"mean_token_accuracy": 0.08859748020768166,
|
||
|
|
"num_tokens": 2586635.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.593882083892822,
|
||
|
|
"epoch": 0.12788271175557814,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999951097137518,
|
||
|
|
"loss": 7.3818,
|
||
|
|
"mean_token_accuracy": 0.09308656603097916,
|
||
|
|
"num_tokens": 2596814.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.515226888656616,
|
||
|
|
"epoch": 0.12841778586334207,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999948543897044,
|
||
|
|
"loss": 7.3996,
|
||
|
|
"mean_token_accuracy": 0.08756894245743752,
|
||
|
|
"num_tokens": 2608087.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.600381469726562,
|
||
|
|
"epoch": 0.128952859971106,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004999945925689621,
|
||
|
|
"loss": 7.3998,
|
||
|
|
"mean_token_accuracy": 0.09394723773002625,
|
||
|
|
"num_tokens": 2619377.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.480240154266357,
|
||
|
|
"epoch": 0.12948793407886994,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999943242515325,
|
||
|
|
"loss": 7.2998,
|
||
|
|
"mean_token_accuracy": 0.0932411678135395,
|
||
|
|
"num_tokens": 2629089.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.522952890396118,
|
||
|
|
"epoch": 0.13002300818663384,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999940494374236,
|
||
|
|
"loss": 7.3684,
|
||
|
|
"mean_token_accuracy": 0.09049427583813667,
|
||
|
|
"num_tokens": 2639743.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.585643148422241,
|
||
|
|
"epoch": 0.13055808229439778,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000499993768126643,
|
||
|
|
"loss": 7.397,
|
||
|
|
"mean_token_accuracy": 0.08678129985928536,
|
||
|
|
"num_tokens": 2650631.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.525626993179321,
|
||
|
|
"epoch": 0.1310931564021617,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.000499993480319199,
|
||
|
|
"loss": 7.366,
|
||
|
|
"mean_token_accuracy": 0.09070794358849525,
|
||
|
|
"num_tokens": 2660197.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.495192050933838,
|
||
|
|
"epoch": 0.13162823050992561,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999931860150999,
|
||
|
|
"loss": 7.3461,
|
||
|
|
"mean_token_accuracy": 0.08914455473423004,
|
||
|
|
"num_tokens": 2670162.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.548467350006104,
|
||
|
|
"epoch": 0.13216330461768955,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004999928852143541,
|
||
|
|
"loss": 7.3309,
|
||
|
|
"mean_token_accuracy": 0.0927185446023941,
|
||
|
|
"num_tokens": 2681233.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.398493242263794,
|
||
|
|
"epoch": 0.13269837872545348,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004999925779169703,
|
||
|
|
"loss": 7.2982,
|
||
|
|
"mean_token_accuracy": 0.09300850480794906,
|
||
|
|
"num_tokens": 2692145.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.526278877258301,
|
||
|
|
"epoch": 0.13323345283321741,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999922641229575,
|
||
|
|
"loss": 7.3431,
|
||
|
|
"mean_token_accuracy": 0.0936188168823719,
|
||
|
|
"num_tokens": 2703192.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.520468711853027,
|
||
|
|
"epoch": 0.13376852694098132,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004999919438323248,
|
||
|
|
"loss": 7.3363,
|
||
|
|
"mean_token_accuracy": 0.09251101464033126,
|
||
|
|
"num_tokens": 2714804.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4432690143585205,
|
||
|
|
"epoch": 0.13430360104874525,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999916170450812,
|
||
|
|
"loss": 7.3068,
|
||
|
|
"mean_token_accuracy": 0.09502202421426773,
|
||
|
|
"num_tokens": 2724340.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.475179243087768,
|
||
|
|
"epoch": 0.13483867515650919,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999912837612364,
|
||
|
|
"loss": 7.3071,
|
||
|
|
"mean_token_accuracy": 0.09392300024628639,
|
||
|
|
"num_tokens": 2735767.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.569590282440186,
|
||
|
|
"epoch": 0.1353737492642731,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999909439807997,
|
||
|
|
"loss": 7.3779,
|
||
|
|
"mean_token_accuracy": 0.08663228303194045,
|
||
|
|
"num_tokens": 2747658.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.444280576705933,
|
||
|
|
"epoch": 0.13590882337203702,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999905977037813,
|
||
|
|
"loss": 7.2372,
|
||
|
|
"mean_token_accuracy": 0.09776455760002137,
|
||
|
|
"num_tokens": 2757901.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.465328884124756,
|
||
|
|
"epoch": 0.13644389747980096,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999902449301909,
|
||
|
|
"loss": 7.2776,
|
||
|
|
"mean_token_accuracy": 0.09301821067929268,
|
||
|
|
"num_tokens": 2768945.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.314613389968872,
|
||
|
|
"epoch": 0.1369789715875649,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0004999898856600387,
|
||
|
|
"loss": 7.2582,
|
||
|
|
"mean_token_accuracy": 0.1052941657602787,
|
||
|
|
"num_tokens": 2780276.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.536267852783203,
|
||
|
|
"epoch": 0.1375140456953288,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999895198933354,
|
||
|
|
"loss": 7.3323,
|
||
|
|
"mean_token_accuracy": 0.09816832616925239,
|
||
|
|
"num_tokens": 2791183.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4270100593566895,
|
||
|
|
"epoch": 0.13804911980309273,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999891476300911,
|
||
|
|
"loss": 7.2426,
|
||
|
|
"mean_token_accuracy": 0.09529703482985497,
|
||
|
|
"num_tokens": 2801928.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.473166513442993,
|
||
|
|
"epoch": 0.13858419391085666,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.000499988768870317,
|
||
|
|
"loss": 7.3295,
|
||
|
|
"mean_token_accuracy": 0.08986801654100418,
|
||
|
|
"num_tokens": 2813415.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.48001651763916,
|
||
|
|
"epoch": 0.13911926801862057,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999883836140236,
|
||
|
|
"loss": 7.3364,
|
||
|
|
"mean_token_accuracy": 0.09272250309586524,
|
||
|
|
"num_tokens": 2825288.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.421426439285279,
|
||
|
|
"epoch": 0.1396543421263845,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999879918612224,
|
||
|
|
"loss": 7.2918,
|
||
|
|
"mean_token_accuracy": 0.096827931702137,
|
||
|
|
"num_tokens": 2836298.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.523803615570069,
|
||
|
|
"epoch": 0.14018941623414843,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999875936119245,
|
||
|
|
"loss": 7.2778,
|
||
|
|
"mean_token_accuracy": 0.0943089857697487,
|
||
|
|
"num_tokens": 2846367.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3315290927886965,
|
||
|
|
"epoch": 0.14072449034191237,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999871888661415,
|
||
|
|
"loss": 7.2799,
|
||
|
|
"mean_token_accuracy": 0.09142087027430534,
|
||
|
|
"num_tokens": 2856832.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.507561445236206,
|
||
|
|
"epoch": 0.14125956444967627,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.000499986777623885,
|
||
|
|
"loss": 7.3088,
|
||
|
|
"mean_token_accuracy": 0.0900144100189209,
|
||
|
|
"num_tokens": 2867954.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.509339809417725,
|
||
|
|
"epoch": 0.1417946385574402,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999863598851669,
|
||
|
|
"loss": 7.3334,
|
||
|
|
"mean_token_accuracy": 0.09359355568885804,
|
||
|
|
"num_tokens": 2878714.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.325873184204101,
|
||
|
|
"epoch": 0.14232971266520414,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004999859356499992,
|
||
|
|
"loss": 7.28,
|
||
|
|
"mean_token_accuracy": 0.09667187854647637,
|
||
|
|
"num_tokens": 2890697.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.467297649383545,
|
||
|
|
"epoch": 0.14286478677296804,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999855049183943,
|
||
|
|
"loss": 7.292,
|
||
|
|
"mean_token_accuracy": 0.09200986102223396,
|
||
|
|
"num_tokens": 2901468.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.420497417449951,
|
||
|
|
"epoch": 0.14339986088073198,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004999850676903646,
|
||
|
|
"loss": 7.256,
|
||
|
|
"mean_token_accuracy": 0.09620093181729317,
|
||
|
|
"num_tokens": 2913466.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.381121587753296,
|
||
|
|
"epoch": 0.1439349349884959,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004999846239659226,
|
||
|
|
"loss": 7.2224,
|
||
|
|
"mean_token_accuracy": 0.10079324766993522,
|
||
|
|
"num_tokens": 2923638.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.451461362838745,
|
||
|
|
"epoch": 0.14447000909625984,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999841737450812,
|
||
|
|
"loss": 7.2969,
|
||
|
|
"mean_token_accuracy": 0.1001754067838192,
|
||
|
|
"num_tokens": 2934790.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.389082574844361,
|
||
|
|
"epoch": 0.14500508320402375,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999837170278535,
|
||
|
|
"loss": 7.248,
|
||
|
|
"mean_token_accuracy": 0.0918399602174759,
|
||
|
|
"num_tokens": 2946320.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.486172676086426,
|
||
|
|
"epoch": 0.14554015731178768,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999832538142526,
|
||
|
|
"loss": 7.2238,
|
||
|
|
"mean_token_accuracy": 0.091259303689003,
|
||
|
|
"num_tokens": 2957077.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.342933654785156,
|
||
|
|
"epoch": 0.14607523141955162,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999827841042917,
|
||
|
|
"loss": 7.2296,
|
||
|
|
"mean_token_accuracy": 0.09233908951282502,
|
||
|
|
"num_tokens": 2967286.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4447362422943115,
|
||
|
|
"epoch": 0.14661030552731552,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004999823078979846,
|
||
|
|
"loss": 7.2744,
|
||
|
|
"mean_token_accuracy": 0.09223584830760956,
|
||
|
|
"num_tokens": 2979516.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.485718393325806,
|
||
|
|
"epoch": 0.14714537963507945,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999818251953449,
|
||
|
|
"loss": 7.399,
|
||
|
|
"mean_token_accuracy": 0.08901449739933014,
|
||
|
|
"num_tokens": 2991594.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.445301294326782,
|
||
|
|
"epoch": 0.1476804537428434,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999813359963867,
|
||
|
|
"loss": 7.286,
|
||
|
|
"mean_token_accuracy": 0.09267361760139466,
|
||
|
|
"num_tokens": 3002487.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.488003301620483,
|
||
|
|
"epoch": 0.14821552785060732,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999808403011241,
|
||
|
|
"loss": 7.2851,
|
||
|
|
"mean_token_accuracy": 0.09769331067800521,
|
||
|
|
"num_tokens": 3013197.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3263664722442625,
|
||
|
|
"epoch": 0.14875060195837123,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999803381095712,
|
||
|
|
"loss": 7.3105,
|
||
|
|
"mean_token_accuracy": 0.09277946949005127,
|
||
|
|
"num_tokens": 3024512.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.529593801498413,
|
||
|
|
"epoch": 0.14928567606613516,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999798294217428,
|
||
|
|
"loss": 7.2724,
|
||
|
|
"mean_token_accuracy": 0.09323014095425605,
|
||
|
|
"num_tokens": 3035621.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.383570957183838,
|
||
|
|
"epoch": 0.1498207501738991,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999793142376533,
|
||
|
|
"loss": 7.2703,
|
||
|
|
"mean_token_accuracy": 0.09348074868321418,
|
||
|
|
"num_tokens": 3046492.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.38762936592102,
|
||
|
|
"epoch": 0.150355824281663,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999787925573177,
|
||
|
|
"loss": 7.2831,
|
||
|
|
"mean_token_accuracy": 0.09317544624209403,
|
||
|
|
"num_tokens": 3057715.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.511090230941773,
|
||
|
|
"epoch": 0.15089089838942693,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999782643807513,
|
||
|
|
"loss": 7.2558,
|
||
|
|
"mean_token_accuracy": 0.0898089624941349,
|
||
|
|
"num_tokens": 3068344.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.340856122970581,
|
||
|
|
"epoch": 0.15142597249719086,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004999777297079689,
|
||
|
|
"loss": 7.2191,
|
||
|
|
"mean_token_accuracy": 0.0933483250439167,
|
||
|
|
"num_tokens": 3079576.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.457035493850708,
|
||
|
|
"epoch": 0.1519610466049548,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999771885389863,
|
||
|
|
"loss": 7.2075,
|
||
|
|
"mean_token_accuracy": 0.09207480028271675,
|
||
|
|
"num_tokens": 3090201.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.333426856994629,
|
||
|
|
"epoch": 0.1524961207127187,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999766408738189,
|
||
|
|
"loss": 7.172,
|
||
|
|
"mean_token_accuracy": 0.10389826074242592,
|
||
|
|
"num_tokens": 3099824.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.333724737167358,
|
||
|
|
"epoch": 0.15303119482048264,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999760867124827,
|
||
|
|
"loss": 7.2405,
|
||
|
|
"mean_token_accuracy": 0.09329254552721977,
|
||
|
|
"num_tokens": 3109948.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4186999797821045,
|
||
|
|
"epoch": 0.15356626892824657,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004999755260549937,
|
||
|
|
"loss": 7.2413,
|
||
|
|
"mean_token_accuracy": 0.09903448224067687,
|
||
|
|
"num_tokens": 3121492.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.313020372390747,
|
||
|
|
"epoch": 0.15410134303601047,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004999749589013677,
|
||
|
|
"loss": 7.0092,
|
||
|
|
"mean_token_accuracy": 0.11508586779236793,
|
||
|
|
"num_tokens": 3131990.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2625288486480715,
|
||
|
|
"epoch": 0.1546364171437744,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999743852516217,
|
||
|
|
"loss": 7.2038,
|
||
|
|
"mean_token_accuracy": 0.09737641140818595,
|
||
|
|
"num_tokens": 3142567.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4858119010925295,
|
||
|
|
"epoch": 0.15517149125153834,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004999738051057717,
|
||
|
|
"loss": 7.2253,
|
||
|
|
"mean_token_accuracy": 0.09757704138755799,
|
||
|
|
"num_tokens": 3153083.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.336223459243774,
|
||
|
|
"epoch": 0.15570656535930227,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999732184638347,
|
||
|
|
"loss": 7.2224,
|
||
|
|
"mean_token_accuracy": 0.09092248976230621,
|
||
|
|
"num_tokens": 3163985.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.436727666854859,
|
||
|
|
"epoch": 0.15624163946706618,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999726253258278,
|
||
|
|
"loss": 7.2157,
|
||
|
|
"mean_token_accuracy": 0.09606200903654098,
|
||
|
|
"num_tokens": 3175259.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.293716049194336,
|
||
|
|
"epoch": 0.1567767135748301,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999720256917678,
|
||
|
|
"loss": 7.1804,
|
||
|
|
"mean_token_accuracy": 0.09885367155075073,
|
||
|
|
"num_tokens": 3185487.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.31433138847351,
|
||
|
|
"epoch": 0.15731178768259405,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999714195616723,
|
||
|
|
"loss": 7.1717,
|
||
|
|
"mean_token_accuracy": 0.10157929807901382,
|
||
|
|
"num_tokens": 3196200.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.441909456253052,
|
||
|
|
"epoch": 0.15784686179035795,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999708069355586,
|
||
|
|
"loss": 7.2733,
|
||
|
|
"mean_token_accuracy": 0.08783909082412719,
|
||
|
|
"num_tokens": 3207675.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.31417498588562,
|
||
|
|
"epoch": 0.15838193589812188,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999701878134445,
|
||
|
|
"loss": 7.1471,
|
||
|
|
"mean_token_accuracy": 0.09791682288050652,
|
||
|
|
"num_tokens": 3218117.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3960308074951175,
|
||
|
|
"epoch": 0.15891701000588582,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999695621953477,
|
||
|
|
"loss": 7.2164,
|
||
|
|
"mean_token_accuracy": 0.10362501963973045,
|
||
|
|
"num_tokens": 3229208.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.309657001495362,
|
||
|
|
"epoch": 0.15945208411364975,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999689300812866,
|
||
|
|
"loss": 7.1036,
|
||
|
|
"mean_token_accuracy": 0.10788998156785964,
|
||
|
|
"num_tokens": 3239586.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.392857885360717,
|
||
|
|
"epoch": 0.15998715822141366,
|
||
|
|
"grad_norm": 0.78515625,
|
||
|
|
"learning_rate": 0.0004999682914712791,
|
||
|
|
"loss": 7.1983,
|
||
|
|
"mean_token_accuracy": 0.09886570796370506,
|
||
|
|
"num_tokens": 3250103.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.331405687332153,
|
||
|
|
"epoch": 0.1605222323291776,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004999676463653439,
|
||
|
|
"loss": 7.1785,
|
||
|
|
"mean_token_accuracy": 0.10397682413458824,
|
||
|
|
"num_tokens": 3261844.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.361588764190674,
|
||
|
|
"epoch": 0.16105730643694152,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999669947634996,
|
||
|
|
"loss": 7.1436,
|
||
|
|
"mean_token_accuracy": 0.0984138660132885,
|
||
|
|
"num_tokens": 3272073.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.343551349639893,
|
||
|
|
"epoch": 0.16159238054470546,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999663366657647,
|
||
|
|
"loss": 7.1261,
|
||
|
|
"mean_token_accuracy": 0.1005841538310051,
|
||
|
|
"num_tokens": 3281725.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.326076507568359,
|
||
|
|
"epoch": 0.16212745465246936,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999656720721586,
|
||
|
|
"loss": 7.2726,
|
||
|
|
"mean_token_accuracy": 0.0962200105190277,
|
||
|
|
"num_tokens": 3292708.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3782445907592775,
|
||
|
|
"epoch": 0.1626625287602333,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004999650009827004,
|
||
|
|
"loss": 7.2564,
|
||
|
|
"mean_token_accuracy": 0.09442284628748894,
|
||
|
|
"num_tokens": 3303548.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.326221704483032,
|
||
|
|
"epoch": 0.16319760286799723,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999643233974092,
|
||
|
|
"loss": 7.117,
|
||
|
|
"mean_token_accuracy": 0.10348235741257668,
|
||
|
|
"num_tokens": 3314261.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2751476764678955,
|
||
|
|
"epoch": 0.16373267697576113,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004999636393163049,
|
||
|
|
"loss": 7.1271,
|
||
|
|
"mean_token_accuracy": 0.10080837979912757,
|
||
|
|
"num_tokens": 3324833.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2360046863555905,
|
||
|
|
"epoch": 0.16426775108352507,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999629487394071,
|
||
|
|
"loss": 7.036,
|
||
|
|
"mean_token_accuracy": 0.11096755266189576,
|
||
|
|
"num_tokens": 3334790.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.339627885818482,
|
||
|
|
"epoch": 0.164802825191289,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999622516667358,
|
||
|
|
"loss": 7.1602,
|
||
|
|
"mean_token_accuracy": 0.09869524762034416,
|
||
|
|
"num_tokens": 3345115.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.268951654434204,
|
||
|
|
"epoch": 0.16533789929905293,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.000499961548098311,
|
||
|
|
"loss": 7.0592,
|
||
|
|
"mean_token_accuracy": 0.10297729372978211,
|
||
|
|
"num_tokens": 3356187.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.235326194763184,
|
||
|
|
"epoch": 0.16587297340681684,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999608380341533,
|
||
|
|
"loss": 7.0744,
|
||
|
|
"mean_token_accuracy": 0.10658099949359894,
|
||
|
|
"num_tokens": 3367218.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.27059588432312,
|
||
|
|
"epoch": 0.16640804751458077,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999601214742829,
|
||
|
|
"loss": 7.2223,
|
||
|
|
"mean_token_accuracy": 0.09261110052466393,
|
||
|
|
"num_tokens": 3377557.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.427518892288208,
|
||
|
|
"epoch": 0.1669431216223447,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999593984187206,
|
||
|
|
"loss": 7.2095,
|
||
|
|
"mean_token_accuracy": 0.10194377526640892,
|
||
|
|
"num_tokens": 3387402.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.248392057418823,
|
||
|
|
"epoch": 0.1674781957301086,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004999586688674872,
|
||
|
|
"loss": 7.0941,
|
||
|
|
"mean_token_accuracy": 0.10278604626655578,
|
||
|
|
"num_tokens": 3397924.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3578520774841305,
|
||
|
|
"epoch": 0.16801326983787254,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.000499957932820604,
|
||
|
|
"loss": 7.1743,
|
||
|
|
"mean_token_accuracy": 0.09474834129214287,
|
||
|
|
"num_tokens": 3408622.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.343464088439942,
|
||
|
|
"epoch": 0.16854834394563648,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000499957190278092,
|
||
|
|
"loss": 7.1367,
|
||
|
|
"mean_token_accuracy": 0.10084123015403748,
|
||
|
|
"num_tokens": 3419692.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.277517509460449,
|
||
|
|
"epoch": 0.1690834180534004,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999564412399728,
|
||
|
|
"loss": 7.1842,
|
||
|
|
"mean_token_accuracy": 0.09453171491622925,
|
||
|
|
"num_tokens": 3430986.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.289031267166138,
|
||
|
|
"epoch": 0.1696184921611643,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000499955685706268,
|
||
|
|
"loss": 7.1056,
|
||
|
|
"mean_token_accuracy": 0.10056664869189262,
|
||
|
|
"num_tokens": 3442211.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.181107234954834,
|
||
|
|
"epoch": 0.17015356626892825,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999549236769993,
|
||
|
|
"loss": 7.0973,
|
||
|
|
"mean_token_accuracy": 0.10596697479486465,
|
||
|
|
"num_tokens": 3453585.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.261494874954224,
|
||
|
|
"epoch": 0.17068864037669218,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999541551521888,
|
||
|
|
"loss": 7.1281,
|
||
|
|
"mean_token_accuracy": 0.10282958298921585,
|
||
|
|
"num_tokens": 3464156.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3783262252807615,
|
||
|
|
"epoch": 0.17122371448445609,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999533801318587,
|
||
|
|
"loss": 7.1901,
|
||
|
|
"mean_token_accuracy": 0.095138331502676,
|
||
|
|
"num_tokens": 3474853.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3372804641723635,
|
||
|
|
"epoch": 0.17175878859222002,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999525986160313,
|
||
|
|
"loss": 7.1634,
|
||
|
|
"mean_token_accuracy": 0.10265101641416549,
|
||
|
|
"num_tokens": 3486841.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3480212688446045,
|
||
|
|
"epoch": 0.17229386269998395,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004999518106047293,
|
||
|
|
"loss": 7.1702,
|
||
|
|
"mean_token_accuracy": 0.0980787456035614,
|
||
|
|
"num_tokens": 3498735.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.253286647796631,
|
||
|
|
"epoch": 0.17282893680774788,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0004999510160979754,
|
||
|
|
"loss": 7.2008,
|
||
|
|
"mean_token_accuracy": 0.10094587206840515,
|
||
|
|
"num_tokens": 3508829.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2795453548431395,
|
||
|
|
"epoch": 0.1733640109155118,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999502150957925,
|
||
|
|
"loss": 7.1209,
|
||
|
|
"mean_token_accuracy": 0.10228936895728111,
|
||
|
|
"num_tokens": 3519465.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.299279642105103,
|
||
|
|
"epoch": 0.17389908502327572,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999494075982037,
|
||
|
|
"loss": 7.0647,
|
||
|
|
"mean_token_accuracy": 0.10867529138922691,
|
||
|
|
"num_tokens": 3530401.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.235185194015503,
|
||
|
|
"epoch": 0.17443415913103966,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999485936052324,
|
||
|
|
"loss": 7.141,
|
||
|
|
"mean_token_accuracy": 0.10203565210103989,
|
||
|
|
"num_tokens": 3541136.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.373658609390259,
|
||
|
|
"epoch": 0.17496923323880356,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000499947773116902,
|
||
|
|
"loss": 7.1322,
|
||
|
|
"mean_token_accuracy": 0.1018851414322853,
|
||
|
|
"num_tokens": 3552525.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.22913932800293,
|
||
|
|
"epoch": 0.1755043073465675,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999469461332365,
|
||
|
|
"loss": 7.0903,
|
||
|
|
"mean_token_accuracy": 0.10703189074993133,
|
||
|
|
"num_tokens": 3563028.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.259391117095947,
|
||
|
|
"epoch": 0.17603938145433143,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999461126542592,
|
||
|
|
"loss": 7.0522,
|
||
|
|
"mean_token_accuracy": 0.10235123336315155,
|
||
|
|
"num_tokens": 3573354.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.158776950836182,
|
||
|
|
"epoch": 0.17657445556209536,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0004999452726799947,
|
||
|
|
"loss": 7.0373,
|
||
|
|
"mean_token_accuracy": 0.10366476848721504,
|
||
|
|
"num_tokens": 3585576.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.320888566970825,
|
||
|
|
"epoch": 0.17710952966985927,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999444262104671,
|
||
|
|
"loss": 7.1598,
|
||
|
|
"mean_token_accuracy": 0.09593332335352897,
|
||
|
|
"num_tokens": 3596478.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.289003372192383,
|
||
|
|
"epoch": 0.1776446037776232,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999435732457007,
|
||
|
|
"loss": 7.123,
|
||
|
|
"mean_token_accuracy": 0.09818345233798027,
|
||
|
|
"num_tokens": 3608014.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.291224193572998,
|
||
|
|
"epoch": 0.17817967788538713,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999427137857203,
|
||
|
|
"loss": 7.1694,
|
||
|
|
"mean_token_accuracy": 0.09814337715506553,
|
||
|
|
"num_tokens": 3620120.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.274828290939331,
|
||
|
|
"epoch": 0.17871475199315104,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004999418478305506,
|
||
|
|
"loss": 7.0748,
|
||
|
|
"mean_token_accuracy": 0.09978235512971878,
|
||
|
|
"num_tokens": 3632578.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.185247135162354,
|
||
|
|
"epoch": 0.17924982610091497,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999409753802167,
|
||
|
|
"loss": 7.0939,
|
||
|
|
"mean_token_accuracy": 0.10724005252122878,
|
||
|
|
"num_tokens": 3643245.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.27445502281189,
|
||
|
|
"epoch": 0.1797849002086789,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999400964347437,
|
||
|
|
"loss": 7.0967,
|
||
|
|
"mean_token_accuracy": 0.10385240912437439,
|
||
|
|
"num_tokens": 3655832.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2620195865631105,
|
||
|
|
"epoch": 0.18031997431644284,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999392109941571,
|
||
|
|
"loss": 7.0683,
|
||
|
|
"mean_token_accuracy": 0.10449369996786118,
|
||
|
|
"num_tokens": 3666566.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.303769207000732,
|
||
|
|
"epoch": 0.18085504842420674,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999383190584822,
|
||
|
|
"loss": 7.0852,
|
||
|
|
"mean_token_accuracy": 0.10249918699264526,
|
||
|
|
"num_tokens": 3677572.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2038905143737795,
|
||
|
|
"epoch": 0.18139012253197068,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999374206277451,
|
||
|
|
"loss": 7.0113,
|
||
|
|
"mean_token_accuracy": 0.10162734165787697,
|
||
|
|
"num_tokens": 3687116.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.175737571716309,
|
||
|
|
"epoch": 0.1819251966397346,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999365157019717,
|
||
|
|
"loss": 7.1189,
|
||
|
|
"mean_token_accuracy": 0.10182299092411995,
|
||
|
|
"num_tokens": 3697961.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.309969711303711,
|
||
|
|
"epoch": 0.18246027074749852,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999356042811878,
|
||
|
|
"loss": 7.0444,
|
||
|
|
"mean_token_accuracy": 0.10850266963243485,
|
||
|
|
"num_tokens": 3708834.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.182546806335449,
|
||
|
|
"epoch": 0.18299534485526245,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.00049993468636542,
|
||
|
|
"loss": 7.0991,
|
||
|
|
"mean_token_accuracy": 0.10176495090126991,
|
||
|
|
"num_tokens": 3719835.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.250284337997437,
|
||
|
|
"epoch": 0.18353041896302638,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999337619546948,
|
||
|
|
"loss": 7.0009,
|
||
|
|
"mean_token_accuracy": 0.10658760368824005,
|
||
|
|
"num_tokens": 3730408.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.171570301055908,
|
||
|
|
"epoch": 0.18406549307079031,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999328310490387,
|
||
|
|
"loss": 7.0695,
|
||
|
|
"mean_token_accuracy": 0.10707555189728737,
|
||
|
|
"num_tokens": 3741257.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.23467698097229,
|
||
|
|
"epoch": 0.18460056717855422,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999318936484789,
|
||
|
|
"loss": 7.0647,
|
||
|
|
"mean_token_accuracy": 0.10648670792579651,
|
||
|
|
"num_tokens": 3752615.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.214528036117554,
|
||
|
|
"epoch": 0.18513564128631815,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999309497530422,
|
||
|
|
"loss": 7.0949,
|
||
|
|
"mean_token_accuracy": 0.09849463924765586,
|
||
|
|
"num_tokens": 3763656.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.150198459625244,
|
||
|
|
"epoch": 0.1856707153940821,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004999299993627558,
|
||
|
|
"loss": 7.0733,
|
||
|
|
"mean_token_accuracy": 0.10403963699936866,
|
||
|
|
"num_tokens": 3775257.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.201783800125122,
|
||
|
|
"epoch": 0.186205789501846,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999290424776475,
|
||
|
|
"loss": 7.0384,
|
||
|
|
"mean_token_accuracy": 0.11034373492002487,
|
||
|
|
"num_tokens": 3786094.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.355918598175049,
|
||
|
|
"epoch": 0.18674086360960993,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999280790977445,
|
||
|
|
"loss": 7.1286,
|
||
|
|
"mean_token_accuracy": 0.09715545624494552,
|
||
|
|
"num_tokens": 3796672.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.305685806274414,
|
||
|
|
"epoch": 0.18727593771737386,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000499927109223075,
|
||
|
|
"loss": 7.0958,
|
||
|
|
"mean_token_accuracy": 0.10413563027977943,
|
||
|
|
"num_tokens": 3807910.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1276421546936035,
|
||
|
|
"epoch": 0.1878110118251378,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999261328536667,
|
||
|
|
"loss": 7.0578,
|
||
|
|
"mean_token_accuracy": 0.10628265142440796,
|
||
|
|
"num_tokens": 3820792.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.157390975952149,
|
||
|
|
"epoch": 0.1883460859329017,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999251499895479,
|
||
|
|
"loss": 6.9844,
|
||
|
|
"mean_token_accuracy": 0.10621865093708038,
|
||
|
|
"num_tokens": 3831126.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.23041090965271,
|
||
|
|
"epoch": 0.18888116004066563,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999241606307471,
|
||
|
|
"loss": 7.0942,
|
||
|
|
"mean_token_accuracy": 0.10165138021111489,
|
||
|
|
"num_tokens": 3841923.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.243416452407837,
|
||
|
|
"epoch": 0.18941623414842956,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999231647772927,
|
||
|
|
"loss": 7.0078,
|
||
|
|
"mean_token_accuracy": 0.10644997358322143,
|
||
|
|
"num_tokens": 3852504.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0957677364349365,
|
||
|
|
"epoch": 0.1899513082561935,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999221624292136,
|
||
|
|
"loss": 7.0087,
|
||
|
|
"mean_token_accuracy": 0.1103954017162323,
|
||
|
|
"num_tokens": 3862761.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.252035474777221,
|
||
|
|
"epoch": 0.1904863823639574,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999211535865385,
|
||
|
|
"loss": 7.0234,
|
||
|
|
"mean_token_accuracy": 0.1052067756652832,
|
||
|
|
"num_tokens": 3873662.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.154085254669189,
|
||
|
|
"epoch": 0.19102145647172133,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999201382492969,
|
||
|
|
"loss": 6.9621,
|
||
|
|
"mean_token_accuracy": 0.10425644144415855,
|
||
|
|
"num_tokens": 3884835.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.187242269515991,
|
||
|
|
"epoch": 0.19155653057948527,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999191164175178,
|
||
|
|
"loss": 7.1166,
|
||
|
|
"mean_token_accuracy": 0.10480258762836456,
|
||
|
|
"num_tokens": 3895073.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2901567935943605,
|
||
|
|
"epoch": 0.19209160468724917,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004999180880912309,
|
||
|
|
"loss": 7.0556,
|
||
|
|
"mean_token_accuracy": 0.10658993124961853,
|
||
|
|
"num_tokens": 3905440.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.176698493957519,
|
||
|
|
"epoch": 0.1926266787950131,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999170532704657,
|
||
|
|
"loss": 7.0712,
|
||
|
|
"mean_token_accuracy": 0.10166745483875275,
|
||
|
|
"num_tokens": 3917135.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2208339214324955,
|
||
|
|
"epoch": 0.19316175290277704,
|
||
|
|
"grad_norm": 0.76953125,
|
||
|
|
"learning_rate": 0.0004999160119552523,
|
||
|
|
"loss": 7.0716,
|
||
|
|
"mean_token_accuracy": 0.10915103554725647,
|
||
|
|
"num_tokens": 3928247.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.223503684997558,
|
||
|
|
"epoch": 0.19369682701054097,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999149641456206,
|
||
|
|
"loss": 7.0491,
|
||
|
|
"mean_token_accuracy": 0.1053008608520031,
|
||
|
|
"num_tokens": 3938609.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.265676212310791,
|
||
|
|
"epoch": 0.19423190111830488,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.000499913909841601,
|
||
|
|
"loss": 7.0274,
|
||
|
|
"mean_token_accuracy": 0.10771157816052437,
|
||
|
|
"num_tokens": 3949221.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.100171852111816,
|
||
|
|
"epoch": 0.1947669752260688,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999128490432238,
|
||
|
|
"loss": 7.0149,
|
||
|
|
"mean_token_accuracy": 0.09949721470475197,
|
||
|
|
"num_tokens": 3959475.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.136339998245239,
|
||
|
|
"epoch": 0.19530204933383274,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999117817505196,
|
||
|
|
"loss": 7.0138,
|
||
|
|
"mean_token_accuracy": 0.11632085666060447,
|
||
|
|
"num_tokens": 3969638.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.178588724136352,
|
||
|
|
"epoch": 0.19583712344159665,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004999107079635194,
|
||
|
|
"loss": 7.0644,
|
||
|
|
"mean_token_accuracy": 0.10715136379003525,
|
||
|
|
"num_tokens": 3980543.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.336812162399292,
|
||
|
|
"epoch": 0.19637219754936058,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000499909627682254,
|
||
|
|
"loss": 7.1143,
|
||
|
|
"mean_token_accuracy": 0.0920241579413414,
|
||
|
|
"num_tokens": 3993518.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.216370439529419,
|
||
|
|
"epoch": 0.19690727165712452,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999085409067549,
|
||
|
|
"loss": 7.0948,
|
||
|
|
"mean_token_accuracy": 0.10310237035155297,
|
||
|
|
"num_tokens": 4002940.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.141087865829467,
|
||
|
|
"epoch": 0.19744234576488845,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999074476370531,
|
||
|
|
"loss": 7.0291,
|
||
|
|
"mean_token_accuracy": 0.10522487610578538,
|
||
|
|
"num_tokens": 4013982.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2277580261230465,
|
||
|
|
"epoch": 0.19797741987265235,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999063478731805,
|
||
|
|
"loss": 6.9933,
|
||
|
|
"mean_token_accuracy": 0.11192195788025856,
|
||
|
|
"num_tokens": 4025607.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.117806482315063,
|
||
|
|
"epoch": 0.1985124939804163,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004999052416151687,
|
||
|
|
"loss": 7.0568,
|
||
|
|
"mean_token_accuracy": 0.10609380379319192,
|
||
|
|
"num_tokens": 4037467.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.221655082702637,
|
||
|
|
"epoch": 0.19904756808818022,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004999041288630496,
|
||
|
|
"loss": 7.065,
|
||
|
|
"mean_token_accuracy": 0.10668069496750832,
|
||
|
|
"num_tokens": 4049146.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2340247631073,
|
||
|
|
"epoch": 0.19958264219594413,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004999030096168553,
|
||
|
|
"loss": 7.1116,
|
||
|
|
"mean_token_accuracy": 0.10125580132007599,
|
||
|
|
"num_tokens": 4060500.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.248100090026855,
|
||
|
|
"epoch": 0.20011771630370806,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999018838766182,
|
||
|
|
"loss": 7.0427,
|
||
|
|
"mean_token_accuracy": 0.10293570905923843,
|
||
|
|
"num_tokens": 4070553.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2189253807067875,
|
||
|
|
"epoch": 0.200652790411472,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000499900751642371,
|
||
|
|
"loss": 6.988,
|
||
|
|
"mean_token_accuracy": 0.1170131392776966,
|
||
|
|
"num_tokens": 4079653.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.100331258773804,
|
||
|
|
"epoch": 0.20118786451923593,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004998996129141461,
|
||
|
|
"loss": 7.0654,
|
||
|
|
"mean_token_accuracy": 0.10362578108906746,
|
||
|
|
"num_tokens": 4089912.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.275002813339233,
|
||
|
|
"epoch": 0.20172293862699983,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998984676919764,
|
||
|
|
"loss": 7.0342,
|
||
|
|
"mean_token_accuracy": 0.10268538147211075,
|
||
|
|
"num_tokens": 4100577.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.187543249130249,
|
||
|
|
"epoch": 0.20225801273476376,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998973159758952,
|
||
|
|
"loss": 7.0658,
|
||
|
|
"mean_token_accuracy": 0.10256308168172837,
|
||
|
|
"num_tokens": 4111752.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.10661129951477,
|
||
|
|
"epoch": 0.2027930868425277,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004998961577659355,
|
||
|
|
"loss": 7.015,
|
||
|
|
"mean_token_accuracy": 0.10711082518100738,
|
||
|
|
"num_tokens": 4122616.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.239635181427002,
|
||
|
|
"epoch": 0.2033281609502916,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004998949930621309,
|
||
|
|
"loss": 7.1135,
|
||
|
|
"mean_token_accuracy": 0.10389721244573594,
|
||
|
|
"num_tokens": 4134275.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.159951686859131,
|
||
|
|
"epoch": 0.20386323505805554,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004998938218645149,
|
||
|
|
"loss": 7.0093,
|
||
|
|
"mean_token_accuracy": 0.10267628878355026,
|
||
|
|
"num_tokens": 4146412.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.137516021728516,
|
||
|
|
"epoch": 0.20439830916581947,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004998926441731215,
|
||
|
|
"loss": 7.0056,
|
||
|
|
"mean_token_accuracy": 0.10260871946811675,
|
||
|
|
"num_tokens": 4157592.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.170009613037109,
|
||
|
|
"epoch": 0.2049333832735834,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004998914599879845,
|
||
|
|
"loss": 6.9763,
|
||
|
|
"mean_token_accuracy": 0.1078723892569542,
|
||
|
|
"num_tokens": 4168637.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.15439133644104,
|
||
|
|
"epoch": 0.2054684573813473,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004998902693091382,
|
||
|
|
"loss": 7.0316,
|
||
|
|
"mean_token_accuracy": 0.10298030972480773,
|
||
|
|
"num_tokens": 4179951.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.146353483200073,
|
||
|
|
"epoch": 0.20600353148911124,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004998890721366171,
|
||
|
|
"loss": 6.9259,
|
||
|
|
"mean_token_accuracy": 0.1077031098306179,
|
||
|
|
"num_tokens": 4189895.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1884785175323485,
|
||
|
|
"epoch": 0.20653860559687517,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004998878684704556,
|
||
|
|
"loss": 6.9636,
|
||
|
|
"mean_token_accuracy": 0.11009967923164368,
|
||
|
|
"num_tokens": 4199796.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.076934337615967,
|
||
|
|
"epoch": 0.20707367970463908,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004998866583106884,
|
||
|
|
"loss": 7.0095,
|
||
|
|
"mean_token_accuracy": 0.10127623230218888,
|
||
|
|
"num_tokens": 4210428.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.256487798690796,
|
||
|
|
"epoch": 0.207608753812403,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004998854416573506,
|
||
|
|
"loss": 7.0649,
|
||
|
|
"mean_token_accuracy": 0.1079666055738926,
|
||
|
|
"num_tokens": 4221515.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.144673681259155,
|
||
|
|
"epoch": 0.20814382792016695,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998842185104772,
|
||
|
|
"loss": 7.0776,
|
||
|
|
"mean_token_accuracy": 0.11020539179444314,
|
||
|
|
"num_tokens": 4232580.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1092174530029295,
|
||
|
|
"epoch": 0.20867890202793088,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004998829888701036,
|
||
|
|
"loss": 6.9893,
|
||
|
|
"mean_token_accuracy": 0.11271198317408562,
|
||
|
|
"num_tokens": 4242871.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.213183069229126,
|
||
|
|
"epoch": 0.20921397613569478,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004998817527362654,
|
||
|
|
"loss": 7.0261,
|
||
|
|
"mean_token_accuracy": 0.10301245972514153,
|
||
|
|
"num_tokens": 4253419.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.153800678253174,
|
||
|
|
"epoch": 0.20974905024345872,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004998805101089982,
|
||
|
|
"loss": 6.9999,
|
||
|
|
"mean_token_accuracy": 0.10977082848548889,
|
||
|
|
"num_tokens": 4264327.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.214887237548828,
|
||
|
|
"epoch": 0.21028412435122265,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004998792609883378,
|
||
|
|
"loss": 6.9766,
|
||
|
|
"mean_token_accuracy": 0.10818460211157799,
|
||
|
|
"num_tokens": 4274568.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.140443277359009,
|
||
|
|
"epoch": 0.21081919845898656,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998780053743203,
|
||
|
|
"loss": 6.9731,
|
||
|
|
"mean_token_accuracy": 0.11215656697750091,
|
||
|
|
"num_tokens": 4284895.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1276960372924805,
|
||
|
|
"epoch": 0.2113542725667505,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004998767432669822,
|
||
|
|
"loss": 7.0104,
|
||
|
|
"mean_token_accuracy": 0.10507805719971657,
|
||
|
|
"num_tokens": 4297258.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.149711656570434,
|
||
|
|
"epoch": 0.21188934667451442,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004998754746663595,
|
||
|
|
"loss": 6.9365,
|
||
|
|
"mean_token_accuracy": 0.10693479850888252,
|
||
|
|
"num_tokens": 4308307.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.124268484115601,
|
||
|
|
"epoch": 0.21242442078227836,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004998741995724892,
|
||
|
|
"loss": 7.0014,
|
||
|
|
"mean_token_accuracy": 0.10538375228643418,
|
||
|
|
"num_tokens": 4318801.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.139152193069458,
|
||
|
|
"epoch": 0.21295949489004226,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004998729179854079,
|
||
|
|
"loss": 6.9777,
|
||
|
|
"mean_token_accuracy": 0.10666713044047356,
|
||
|
|
"num_tokens": 4329531.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1325037479400635,
|
||
|
|
"epoch": 0.2134945689978062,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004998716299051527,
|
||
|
|
"loss": 6.9611,
|
||
|
|
"mean_token_accuracy": 0.11172771900892257,
|
||
|
|
"num_tokens": 4341203.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.091319608688354,
|
||
|
|
"epoch": 0.21402964310557013,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004998703353317609,
|
||
|
|
"loss": 7.0092,
|
||
|
|
"mean_token_accuracy": 0.10446273684501647,
|
||
|
|
"num_tokens": 4352426.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.161164569854736,
|
||
|
|
"epoch": 0.21456471721333403,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004998690342652697,
|
||
|
|
"loss": 6.9493,
|
||
|
|
"mean_token_accuracy": 0.11236951574683189,
|
||
|
|
"num_tokens": 4363413.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.104535961151123,
|
||
|
|
"epoch": 0.21509979132109797,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004998677267057166,
|
||
|
|
"loss": 6.8913,
|
||
|
|
"mean_token_accuracy": 0.11243644654750824,
|
||
|
|
"num_tokens": 4373470.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.114715242385865,
|
||
|
|
"epoch": 0.2156348654288619,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004998664126531397,
|
||
|
|
"loss": 6.9596,
|
||
|
|
"mean_token_accuracy": 0.1114291749894619,
|
||
|
|
"num_tokens": 4384438.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.101155853271484,
|
||
|
|
"epoch": 0.21616993953662583,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004998650921075766,
|
||
|
|
"loss": 6.9454,
|
||
|
|
"mean_token_accuracy": 0.10823875814676284,
|
||
|
|
"num_tokens": 4395100.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.117280292510986,
|
||
|
|
"epoch": 0.21670501364438974,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004998637650690656,
|
||
|
|
"loss": 7.0544,
|
||
|
|
"mean_token_accuracy": 0.10239638835191726,
|
||
|
|
"num_tokens": 4407131.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1200460433959964,
|
||
|
|
"epoch": 0.21724008775215367,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.000499862431537645,
|
||
|
|
"loss": 6.8888,
|
||
|
|
"mean_token_accuracy": 0.10876853093504905,
|
||
|
|
"num_tokens": 4417701.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.097174835205078,
|
||
|
|
"epoch": 0.2177751618599176,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998610915133533,
|
||
|
|
"loss": 6.949,
|
||
|
|
"mean_token_accuracy": 0.11059459373354912,
|
||
|
|
"num_tokens": 4429309.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.08780870437622,
|
||
|
|
"epoch": 0.21831023596768154,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998597449962292,
|
||
|
|
"loss": 7.0251,
|
||
|
|
"mean_token_accuracy": 0.10617428198456764,
|
||
|
|
"num_tokens": 4440850.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.156359386444092,
|
||
|
|
"epoch": 0.21884531007544544,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998583919863115,
|
||
|
|
"loss": 7.0009,
|
||
|
|
"mean_token_accuracy": 0.10219309031963349,
|
||
|
|
"num_tokens": 4451995.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.987979745864868,
|
||
|
|
"epoch": 0.21938038418320938,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998570324836393,
|
||
|
|
"loss": 6.9059,
|
||
|
|
"mean_token_accuracy": 0.11296729370951653,
|
||
|
|
"num_tokens": 4461916.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.093602132797241,
|
||
|
|
"epoch": 0.2199154582909733,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499855666488252,
|
||
|
|
"loss": 6.9953,
|
||
|
|
"mean_token_accuracy": 0.1073579765856266,
|
||
|
|
"num_tokens": 4471603.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.243840980529785,
|
||
|
|
"epoch": 0.22045053239873721,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004998542940001889,
|
||
|
|
"loss": 7.0352,
|
||
|
|
"mean_token_accuracy": 0.10500341430306434,
|
||
|
|
"num_tokens": 4483166.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.074850082397461,
|
||
|
|
"epoch": 0.22098560650650115,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004998529150194895,
|
||
|
|
"loss": 6.9424,
|
||
|
|
"mean_token_accuracy": 0.1041251115500927,
|
||
|
|
"num_tokens": 4493824.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.116635465621949,
|
||
|
|
"epoch": 0.22152068061426508,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004998515295461939,
|
||
|
|
"loss": 6.837,
|
||
|
|
"mean_token_accuracy": 0.1261841081082821,
|
||
|
|
"num_tokens": 4505674.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0095867156982425,
|
||
|
|
"epoch": 0.22205575472202901,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000499850137580342,
|
||
|
|
"loss": 6.9422,
|
||
|
|
"mean_token_accuracy": 0.11334002017974854,
|
||
|
|
"num_tokens": 4516516.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.119809246063232,
|
||
|
|
"epoch": 0.22259082882979292,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004998487391219739,
|
||
|
|
"loss": 6.9453,
|
||
|
|
"mean_token_accuracy": 0.10056448429822921,
|
||
|
|
"num_tokens": 4527811.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.050966739654541,
|
||
|
|
"epoch": 0.22312590293755685,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004998473341711301,
|
||
|
|
"loss": 6.8806,
|
||
|
|
"mean_token_accuracy": 0.10502795204520225,
|
||
|
|
"num_tokens": 4538988.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.119756889343262,
|
||
|
|
"epoch": 0.22366097704532079,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998459227278512,
|
||
|
|
"loss": 6.8997,
|
||
|
|
"mean_token_accuracy": 0.11361236721277237,
|
||
|
|
"num_tokens": 4550049.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.177942180633545,
|
||
|
|
"epoch": 0.2241960511530847,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004998445047921777,
|
||
|
|
"loss": 7.0332,
|
||
|
|
"mean_token_accuracy": 0.10892037376761436,
|
||
|
|
"num_tokens": 4559784.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.094767713546753,
|
||
|
|
"epoch": 0.22473112526084862,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998430803641509,
|
||
|
|
"loss": 6.873,
|
||
|
|
"mean_token_accuracy": 0.11253026425838471,
|
||
|
|
"num_tokens": 4569982.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.99695782661438,
|
||
|
|
"epoch": 0.22526619936861256,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004998416494438118,
|
||
|
|
"loss": 6.8769,
|
||
|
|
"mean_token_accuracy": 0.11211913973093032,
|
||
|
|
"num_tokens": 4581117.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.084139013290406,
|
||
|
|
"epoch": 0.2258012734763765,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998402120312014,
|
||
|
|
"loss": 6.9462,
|
||
|
|
"mean_token_accuracy": 0.11116094216704368,
|
||
|
|
"num_tokens": 4592012.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.116655254364014,
|
||
|
|
"epoch": 0.2263363475841404,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998387681263616,
|
||
|
|
"loss": 6.9931,
|
||
|
|
"mean_token_accuracy": 0.10694418773055077,
|
||
|
|
"num_tokens": 4602591.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.098616075515747,
|
||
|
|
"epoch": 0.22687142169190433,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.000499837317729334,
|
||
|
|
"loss": 6.9291,
|
||
|
|
"mean_token_accuracy": 0.10939419046044349,
|
||
|
|
"num_tokens": 4613418.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.091100645065308,
|
||
|
|
"epoch": 0.22740649579966826,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004998358608401603,
|
||
|
|
"loss": 6.8499,
|
||
|
|
"mean_token_accuracy": 0.11751434430480004,
|
||
|
|
"num_tokens": 4625156.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1228173732757565,
|
||
|
|
"epoch": 0.22794156990743217,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.000499834397458883,
|
||
|
|
"loss": 6.8865,
|
||
|
|
"mean_token_accuracy": 0.11367959231138229,
|
||
|
|
"num_tokens": 4634523.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.990410232543946,
|
||
|
|
"epoch": 0.2284766440151961,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004998329275855438,
|
||
|
|
"loss": 6.87,
|
||
|
|
"mean_token_accuracy": 0.11853560954332351,
|
||
|
|
"num_tokens": 4646292.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.091177034378052,
|
||
|
|
"epoch": 0.22901171812296003,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004998314512201855,
|
||
|
|
"loss": 6.8548,
|
||
|
|
"mean_token_accuracy": 0.10857467800378799,
|
||
|
|
"num_tokens": 4656417.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.000166225433349,
|
||
|
|
"epoch": 0.22954679223072397,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998299683628507,
|
||
|
|
"loss": 6.8661,
|
||
|
|
"mean_token_accuracy": 0.11203439608216285,
|
||
|
|
"num_tokens": 4666933.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.122287797927856,
|
||
|
|
"epoch": 0.23008186633848787,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004998284790135821,
|
||
|
|
"loss": 7.0464,
|
||
|
|
"mean_token_accuracy": 0.10003090128302575,
|
||
|
|
"num_tokens": 4678482.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.111646604537964,
|
||
|
|
"epoch": 0.2306169404462518,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998269831724228,
|
||
|
|
"loss": 6.894,
|
||
|
|
"mean_token_accuracy": 0.11034037619829178,
|
||
|
|
"num_tokens": 4688454.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.016481971740722,
|
||
|
|
"epoch": 0.23115201455401574,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998254808394159,
|
||
|
|
"loss": 6.9201,
|
||
|
|
"mean_token_accuracy": 0.11088593229651451,
|
||
|
|
"num_tokens": 4699545.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.125952577590942,
|
||
|
|
"epoch": 0.23168708866177964,
|
||
|
|
"grad_norm": 0.7578125,
|
||
|
|
"learning_rate": 0.0004998239720146048,
|
||
|
|
"loss": 6.9256,
|
||
|
|
"mean_token_accuracy": 0.11005692854523659,
|
||
|
|
"num_tokens": 4711149.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9970673561096195,
|
||
|
|
"epoch": 0.23222216276954358,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004998224566980332,
|
||
|
|
"loss": 6.9387,
|
||
|
|
"mean_token_accuracy": 0.10672764554619789,
|
||
|
|
"num_tokens": 4722651.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.063665342330933,
|
||
|
|
"epoch": 0.2327572368773075,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004998209348897447,
|
||
|
|
"loss": 6.9388,
|
||
|
|
"mean_token_accuracy": 0.10191527009010315,
|
||
|
|
"num_tokens": 4733883.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.244954586029053,
|
||
|
|
"epoch": 0.23329231098507144,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004998194065897833,
|
||
|
|
"loss": 6.9158,
|
||
|
|
"mean_token_accuracy": 0.10730345025658608,
|
||
|
|
"num_tokens": 4744517.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.010083484649658,
|
||
|
|
"epoch": 0.23382738509283535,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.000499817871798193,
|
||
|
|
"loss": 6.9234,
|
||
|
|
"mean_token_accuracy": 0.1180235929787159,
|
||
|
|
"num_tokens": 4755481.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.012146234512329,
|
||
|
|
"epoch": 0.23436245920059928,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998163305150185,
|
||
|
|
"loss": 6.8316,
|
||
|
|
"mean_token_accuracy": 0.11478903293609619,
|
||
|
|
"num_tokens": 4765535.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.069972801208496,
|
||
|
|
"epoch": 0.23489753330836322,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004998147827403038,
|
||
|
|
"loss": 6.9619,
|
||
|
|
"mean_token_accuracy": 0.10954375863075257,
|
||
|
|
"num_tokens": 4777045.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.119951629638672,
|
||
|
|
"epoch": 0.23543260741612712,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000499813228474094,
|
||
|
|
"loss": 6.8399,
|
||
|
|
"mean_token_accuracy": 0.1167965590953827,
|
||
|
|
"num_tokens": 4787958.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.953368234634399,
|
||
|
|
"epoch": 0.23596768152389105,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004998116677164338,
|
||
|
|
"loss": 6.8911,
|
||
|
|
"mean_token_accuracy": 0.10928420349955559,
|
||
|
|
"num_tokens": 4798502.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.026491498947143,
|
||
|
|
"epoch": 0.236502755631655,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004998101004673682,
|
||
|
|
"loss": 6.8906,
|
||
|
|
"mean_token_accuracy": 0.11567377597093582,
|
||
|
|
"num_tokens": 4809179.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.102079772949219,
|
||
|
|
"epoch": 0.23703782973941892,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004998085267269426,
|
||
|
|
"loss": 6.9476,
|
||
|
|
"mean_token_accuracy": 0.10375262200832366,
|
||
|
|
"num_tokens": 4819803.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.111145877838135,
|
||
|
|
"epoch": 0.23757290384718283,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004998069464952025,
|
||
|
|
"loss": 6.9275,
|
||
|
|
"mean_token_accuracy": 0.1055069126188755,
|
||
|
|
"num_tokens": 4831226.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.114426469802856,
|
||
|
|
"epoch": 0.23810797795494676,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004998053597721932,
|
||
|
|
"loss": 6.955,
|
||
|
|
"mean_token_accuracy": 0.11139222607016563,
|
||
|
|
"num_tokens": 4842168.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.013771915435791,
|
||
|
|
"epoch": 0.2386430520627107,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004998037665579608,
|
||
|
|
"loss": 6.9151,
|
||
|
|
"mean_token_accuracy": 0.11002311557531357,
|
||
|
|
"num_tokens": 4852655.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.965934324264526,
|
||
|
|
"epoch": 0.2391781261704746,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004998021668525513,
|
||
|
|
"loss": 6.8002,
|
||
|
|
"mean_token_accuracy": 0.11136664599180221,
|
||
|
|
"num_tokens": 4862164.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1173601150512695,
|
||
|
|
"epoch": 0.23971320027823853,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004998005606560107,
|
||
|
|
"loss": 6.9347,
|
||
|
|
"mean_token_accuracy": 0.11432894393801689,
|
||
|
|
"num_tokens": 4874233.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.07620940208435,
|
||
|
|
"epoch": 0.24024827438600246,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004997989479683856,
|
||
|
|
"loss": 6.924,
|
||
|
|
"mean_token_accuracy": 0.11140381470322609,
|
||
|
|
"num_tokens": 4885948.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.045759534835815,
|
||
|
|
"epoch": 0.2407833484937664,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004997973287897224,
|
||
|
|
"loss": 6.9123,
|
||
|
|
"mean_token_accuracy": 0.11342343240976334,
|
||
|
|
"num_tokens": 4897128.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.03762469291687,
|
||
|
|
"epoch": 0.2413184226015303,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004997957031200681,
|
||
|
|
"loss": 6.8835,
|
||
|
|
"mean_token_accuracy": 0.11781226769089699,
|
||
|
|
"num_tokens": 4907699.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.970374584197998,
|
||
|
|
"epoch": 0.24185349670929424,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004997940709594692,
|
||
|
|
"loss": 6.806,
|
||
|
|
"mean_token_accuracy": 0.11417917162179947,
|
||
|
|
"num_tokens": 4918772.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.130536031723023,
|
||
|
|
"epoch": 0.24238857081705817,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004997924323079733,
|
||
|
|
"loss": 6.8628,
|
||
|
|
"mean_token_accuracy": 0.10981507375836372,
|
||
|
|
"num_tokens": 4930046.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.969363880157471,
|
||
|
|
"epoch": 0.24292364492482207,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004997907871656273,
|
||
|
|
"loss": 6.8944,
|
||
|
|
"mean_token_accuracy": 0.11376282870769501,
|
||
|
|
"num_tokens": 4940609.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0445019721984865,
|
||
|
|
"epoch": 0.243458719032586,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997891355324791,
|
||
|
|
"loss": 6.9047,
|
||
|
|
"mean_token_accuracy": 0.11144462153315544,
|
||
|
|
"num_tokens": 4951339.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.013249683380127,
|
||
|
|
"epoch": 0.24399379314034994,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004997874774085761,
|
||
|
|
"loss": 6.8215,
|
||
|
|
"mean_token_accuracy": 0.10943349301815034,
|
||
|
|
"num_tokens": 4961083.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.997879314422607,
|
||
|
|
"epoch": 0.24452886724811387,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004997858127939662,
|
||
|
|
"loss": 6.824,
|
||
|
|
"mean_token_accuracy": 0.1134270079433918,
|
||
|
|
"num_tokens": 4971399.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0827906131744385,
|
||
|
|
"epoch": 0.24506394135587778,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004997841416886976,
|
||
|
|
"loss": 6.9026,
|
||
|
|
"mean_token_accuracy": 0.10839502215385437,
|
||
|
|
"num_tokens": 4982429.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.065428256988525,
|
||
|
|
"epoch": 0.2455990154636417,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004997824640928186,
|
||
|
|
"loss": 6.9601,
|
||
|
|
"mean_token_accuracy": 0.10927876681089402,
|
||
|
|
"num_tokens": 4993706.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.042297983169556,
|
||
|
|
"epoch": 0.24613408957140565,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004997807800063774,
|
||
|
|
"loss": 6.8437,
|
||
|
|
"mean_token_accuracy": 0.11474441438913345,
|
||
|
|
"num_tokens": 5005411.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.061811208724976,
|
||
|
|
"epoch": 0.24666916367916958,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.000499779089429423,
|
||
|
|
"loss": 6.963,
|
||
|
|
"mean_token_accuracy": 0.1087774895131588,
|
||
|
|
"num_tokens": 5016011.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.043573570251465,
|
||
|
|
"epoch": 0.24720423778693348,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004997773923620037,
|
||
|
|
"loss": 6.9238,
|
||
|
|
"mean_token_accuracy": 0.10597949847579002,
|
||
|
|
"num_tokens": 5027841.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.102751350402832,
|
||
|
|
"epoch": 0.24773931189469742,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004997756888041689,
|
||
|
|
"loss": 6.9271,
|
||
|
|
"mean_token_accuracy": 0.10425131991505623,
|
||
|
|
"num_tokens": 5038640.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.972273588180542,
|
||
|
|
"epoch": 0.24827438600246135,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997739787559677,
|
||
|
|
"loss": 6.8668,
|
||
|
|
"mean_token_accuracy": 0.11417348384857177,
|
||
|
|
"num_tokens": 5050423.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.035957622528076,
|
||
|
|
"epoch": 0.24880946011022526,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997722622174494,
|
||
|
|
"loss": 6.8771,
|
||
|
|
"mean_token_accuracy": 0.11295794397592544,
|
||
|
|
"num_tokens": 5060654.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.993176651000977,
|
||
|
|
"epoch": 0.2493445342179892,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004997705391886636,
|
||
|
|
"loss": 6.799,
|
||
|
|
"mean_token_accuracy": 0.11571635380387306,
|
||
|
|
"num_tokens": 5070165.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.959088754653931,
|
||
|
|
"epoch": 0.24987960832575312,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997688096696601,
|
||
|
|
"loss": 6.8572,
|
||
|
|
"mean_token_accuracy": 0.1051781103014946,
|
||
|
|
"num_tokens": 5080937.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.938587760925293,
|
||
|
|
"epoch": 0.25041468243351706,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004997670736604888,
|
||
|
|
"loss": 6.808,
|
||
|
|
"mean_token_accuracy": 0.11930364593863488,
|
||
|
|
"num_tokens": 5090955.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.089204788208008,
|
||
|
|
"epoch": 0.250949756541281,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004997653311611998,
|
||
|
|
"loss": 6.9384,
|
||
|
|
"mean_token_accuracy": 0.10624079629778863,
|
||
|
|
"num_tokens": 5102201.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0677807331085205,
|
||
|
|
"epoch": 0.25148483064904487,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997635821718435,
|
||
|
|
"loss": 6.8653,
|
||
|
|
"mean_token_accuracy": 0.11593251675367355,
|
||
|
|
"num_tokens": 5112235.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.948492336273193,
|
||
|
|
"epoch": 0.2520199047568088,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004997618266924704,
|
||
|
|
"loss": 6.7418,
|
||
|
|
"mean_token_accuracy": 0.11052383631467819,
|
||
|
|
"num_tokens": 5122360.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.005466365814209,
|
||
|
|
"epoch": 0.25255497886457273,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000499760064723131,
|
||
|
|
"loss": 6.9121,
|
||
|
|
"mean_token_accuracy": 0.10666457489132881,
|
||
|
|
"num_tokens": 5133084.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.970629024505615,
|
||
|
|
"epoch": 0.25309005297233667,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004997582962638764,
|
||
|
|
"loss": 6.8565,
|
||
|
|
"mean_token_accuracy": 0.1083373948931694,
|
||
|
|
"num_tokens": 5144495.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.105882930755615,
|
||
|
|
"epoch": 0.2536251270801006,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004997565213147575,
|
||
|
|
"loss": 6.865,
|
||
|
|
"mean_token_accuracy": 0.11402732953429222,
|
||
|
|
"num_tokens": 5154824.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.978338050842285,
|
||
|
|
"epoch": 0.25416020118786453,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004997547398758257,
|
||
|
|
"loss": 6.8449,
|
||
|
|
"mean_token_accuracy": 0.10908161997795104,
|
||
|
|
"num_tokens": 5165061.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9950824737548825,
|
||
|
|
"epoch": 0.25469527529562846,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004997529519471323,
|
||
|
|
"loss": 6.8105,
|
||
|
|
"mean_token_accuracy": 0.11739344000816346,
|
||
|
|
"num_tokens": 5174964.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.959466028213501,
|
||
|
|
"epoch": 0.25523034940339234,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997511575287291,
|
||
|
|
"loss": 6.8388,
|
||
|
|
"mean_token_accuracy": 0.11174839809536934,
|
||
|
|
"num_tokens": 5185458.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.014845609664917,
|
||
|
|
"epoch": 0.2557654235111563,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004997493566206677,
|
||
|
|
"loss": 6.8452,
|
||
|
|
"mean_token_accuracy": 0.11382765620946884,
|
||
|
|
"num_tokens": 5196193.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.993070125579834,
|
||
|
|
"epoch": 0.2563004976189202,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0004997475492230003,
|
||
|
|
"loss": 6.9517,
|
||
|
|
"mean_token_accuracy": 0.10821824818849564,
|
||
|
|
"num_tokens": 5208541.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.031092548370362,
|
||
|
|
"epoch": 0.25683557172668414,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.000499745735335779,
|
||
|
|
"loss": 6.7908,
|
||
|
|
"mean_token_accuracy": 0.11512782797217369,
|
||
|
|
"num_tokens": 5218567.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.993920040130615,
|
||
|
|
"epoch": 0.2573706458344481,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004997439149590561,
|
||
|
|
"loss": 6.8965,
|
||
|
|
"mean_token_accuracy": 0.11021987870335578,
|
||
|
|
"num_tokens": 5228293.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.987144422531128,
|
||
|
|
"epoch": 0.257905719942212,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004997420880928843,
|
||
|
|
"loss": 6.8368,
|
||
|
|
"mean_token_accuracy": 0.11468688249588013,
|
||
|
|
"num_tokens": 5238880.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0282874584198,
|
||
|
|
"epoch": 0.25844079404997594,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004997402547373162,
|
||
|
|
"loss": 6.9248,
|
||
|
|
"mean_token_accuracy": 0.10779067873954773,
|
||
|
|
"num_tokens": 5250104.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.077765417098999,
|
||
|
|
"epoch": 0.2589758681577399,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004997384148924049,
|
||
|
|
"loss": 6.9476,
|
||
|
|
"mean_token_accuracy": 0.10701018646359443,
|
||
|
|
"num_tokens": 5260355.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.013334131240844,
|
||
|
|
"epoch": 0.25951094226550375,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997365685582035,
|
||
|
|
"loss": 6.8839,
|
||
|
|
"mean_token_accuracy": 0.11221425458788872,
|
||
|
|
"num_tokens": 5272117.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.025537967681885,
|
||
|
|
"epoch": 0.2600460163732677,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.0004997347157347651,
|
||
|
|
"loss": 6.9641,
|
||
|
|
"mean_token_accuracy": 0.11001334488391876,
|
||
|
|
"num_tokens": 5284583.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.070367336273193,
|
||
|
|
"epoch": 0.2605810904810316,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004997328564221435,
|
||
|
|
"loss": 6.7554,
|
||
|
|
"mean_token_accuracy": 0.12274964973330497,
|
||
|
|
"num_tokens": 5295846.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.974102544784546,
|
||
|
|
"epoch": 0.26111616458879555,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004997309906203922,
|
||
|
|
"loss": 6.9064,
|
||
|
|
"mean_token_accuracy": 0.10685541406273842,
|
||
|
|
"num_tokens": 5307802.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.062164688110352,
|
||
|
|
"epoch": 0.2616512386965595,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997291183295652,
|
||
|
|
"loss": 6.8217,
|
||
|
|
"mean_token_accuracy": 0.11616088747978211,
|
||
|
|
"num_tokens": 5318263.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.043830013275146,
|
||
|
|
"epoch": 0.2621863128043234,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004997272395497164,
|
||
|
|
"loss": 6.8821,
|
||
|
|
"mean_token_accuracy": 0.11346295177936554,
|
||
|
|
"num_tokens": 5328555.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.941327333450317,
|
||
|
|
"epoch": 0.26272138691208735,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004997253542809002,
|
||
|
|
"loss": 6.8354,
|
||
|
|
"mean_token_accuracy": 0.11198842748999596,
|
||
|
|
"num_tokens": 5339954.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.107675504684448,
|
||
|
|
"epoch": 0.26325646101985123,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004997234625231709,
|
||
|
|
"loss": 6.8836,
|
||
|
|
"mean_token_accuracy": 0.11381551921367646,
|
||
|
|
"num_tokens": 5350919.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.949951696395874,
|
||
|
|
"epoch": 0.26379153512761516,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004997215642765832,
|
||
|
|
"loss": 6.8624,
|
||
|
|
"mean_token_accuracy": 0.11542123556137085,
|
||
|
|
"num_tokens": 5361844.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.018435907363892,
|
||
|
|
"epoch": 0.2643266092353791,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000499719659541192,
|
||
|
|
"loss": 6.8726,
|
||
|
|
"mean_token_accuracy": 0.10965746343135833,
|
||
|
|
"num_tokens": 5372026.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0428282737731935,
|
||
|
|
"epoch": 0.26486168334314303,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004997177483170521,
|
||
|
|
"loss": 6.9163,
|
||
|
|
"mean_token_accuracy": 0.11546080112457276,
|
||
|
|
"num_tokens": 5382965.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.963793182373047,
|
||
|
|
"epoch": 0.26539675745090696,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004997158306042188,
|
||
|
|
"loss": 6.874,
|
||
|
|
"mean_token_accuracy": 0.11316567808389663,
|
||
|
|
"num_tokens": 5393738.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.974194860458374,
|
||
|
|
"epoch": 0.2659318315586709,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004997139064027476,
|
||
|
|
"loss": 6.74,
|
||
|
|
"mean_token_accuracy": 0.12156007960438728,
|
||
|
|
"num_tokens": 5404059.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.964081430435181,
|
||
|
|
"epoch": 0.26646690566643483,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004997119757126938,
|
||
|
|
"loss": 6.7804,
|
||
|
|
"mean_token_accuracy": 0.11532729938626289,
|
||
|
|
"num_tokens": 5414152.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.028856039047241,
|
||
|
|
"epoch": 0.2670019797741987,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004997100385341133,
|
||
|
|
"loss": 6.9634,
|
||
|
|
"mean_token_accuracy": 0.1126515194773674,
|
||
|
|
"num_tokens": 5425227.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9782177925109865,
|
||
|
|
"epoch": 0.26753705388196264,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004997080948670621,
|
||
|
|
"loss": 6.789,
|
||
|
|
"mean_token_accuracy": 0.11695293188095093,
|
||
|
|
"num_tokens": 5435716.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.985808944702148,
|
||
|
|
"epoch": 0.26807212798972657,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0004997061447115962,
|
||
|
|
"loss": 6.8623,
|
||
|
|
"mean_token_accuracy": 0.10614107474684716,
|
||
|
|
"num_tokens": 5446519.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.017519235610962,
|
||
|
|
"epoch": 0.2686072020974905,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997041880677719,
|
||
|
|
"loss": 6.8421,
|
||
|
|
"mean_token_accuracy": 0.11282496824860573,
|
||
|
|
"num_tokens": 5457496.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.900492763519287,
|
||
|
|
"epoch": 0.26914227620525444,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004997022249356457,
|
||
|
|
"loss": 6.7495,
|
||
|
|
"mean_token_accuracy": 0.11760077178478241,
|
||
|
|
"num_tokens": 5469059.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.010392713546753,
|
||
|
|
"epoch": 0.26967735031301837,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004997002553152745,
|
||
|
|
"loss": 6.8399,
|
||
|
|
"mean_token_accuracy": 0.1156559094786644,
|
||
|
|
"num_tokens": 5480324.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.005701923370362,
|
||
|
|
"epoch": 0.2702124244207823,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004996982792067148,
|
||
|
|
"loss": 6.845,
|
||
|
|
"mean_token_accuracy": 0.1095408894121647,
|
||
|
|
"num_tokens": 5491513.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.884131574630738,
|
||
|
|
"epoch": 0.2707474985285462,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.000499696296610024,
|
||
|
|
"loss": 6.7724,
|
||
|
|
"mean_token_accuracy": 0.11539606228470803,
|
||
|
|
"num_tokens": 5502414.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.973390340805054,
|
||
|
|
"epoch": 0.2712825726363101,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004996943075252592,
|
||
|
|
"loss": 6.8968,
|
||
|
|
"mean_token_accuracy": 0.11106460094451905,
|
||
|
|
"num_tokens": 5512962.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.999091625213623,
|
||
|
|
"epoch": 0.27181764674407405,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004996923119524777,
|
||
|
|
"loss": 6.7602,
|
||
|
|
"mean_token_accuracy": 0.11408493369817733,
|
||
|
|
"num_tokens": 5524648.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.898416757583618,
|
||
|
|
"epoch": 0.272352720851838,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004996903098917375,
|
||
|
|
"loss": 6.8386,
|
||
|
|
"mean_token_accuracy": 0.10790063142776489,
|
||
|
|
"num_tokens": 5536158.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9561662673950195,
|
||
|
|
"epoch": 0.2728877949596019,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.000499688301343096,
|
||
|
|
"loss": 6.7565,
|
||
|
|
"mean_token_accuracy": 0.11405683234333992,
|
||
|
|
"num_tokens": 5547374.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.05834732055664,
|
||
|
|
"epoch": 0.27342286906736585,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004996862863066114,
|
||
|
|
"loss": 6.8386,
|
||
|
|
"mean_token_accuracy": 0.11390230059623718,
|
||
|
|
"num_tokens": 5559212.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.979931354522705,
|
||
|
|
"epoch": 0.2739579431751298,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004996842647823419,
|
||
|
|
"loss": 6.8098,
|
||
|
|
"mean_token_accuracy": 0.11664133742451668,
|
||
|
|
"num_tokens": 5569302.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.945258140563965,
|
||
|
|
"epoch": 0.27449301728289366,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004996822367703458,
|
||
|
|
"loss": 6.8112,
|
||
|
|
"mean_token_accuracy": 0.10886863917112351,
|
||
|
|
"num_tokens": 5581688.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.029229307174683,
|
||
|
|
"epoch": 0.2750280913906576,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004996802022706817,
|
||
|
|
"loss": 6.7402,
|
||
|
|
"mean_token_accuracy": 0.11893118396401406,
|
||
|
|
"num_tokens": 5591376.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.872675561904908,
|
||
|
|
"epoch": 0.2755631654984215,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004996781612834083,
|
||
|
|
"loss": 6.7905,
|
||
|
|
"mean_token_accuracy": 0.11670346409082413,
|
||
|
|
"num_tokens": 5601510.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.052143335342407,
|
||
|
|
"epoch": 0.27609823960618546,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004996761138085846,
|
||
|
|
"loss": 6.868,
|
||
|
|
"mean_token_accuracy": 0.1093013696372509,
|
||
|
|
"num_tokens": 5611436.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.98383355140686,
|
||
|
|
"epoch": 0.2766333137139494,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004996740598462697,
|
||
|
|
"loss": 6.8517,
|
||
|
|
"mean_token_accuracy": 0.11311317384243011,
|
||
|
|
"num_tokens": 5620470.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.922229051589966,
|
||
|
|
"epoch": 0.2771683878217133,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004996719993965229,
|
||
|
|
"loss": 6.7627,
|
||
|
|
"mean_token_accuracy": 0.11485590264201165,
|
||
|
|
"num_tokens": 5630740.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.873901319503784,
|
||
|
|
"epoch": 0.27770346192947726,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004996699324594036,
|
||
|
|
"loss": 6.7591,
|
||
|
|
"mean_token_accuracy": 0.11999578103423118,
|
||
|
|
"num_tokens": 5641138.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.053933334350586,
|
||
|
|
"epoch": 0.27823853603724114,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004996678590349717,
|
||
|
|
"loss": 6.89,
|
||
|
|
"mean_token_accuracy": 0.11600473672151565,
|
||
|
|
"num_tokens": 5652474.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.952626085281372,
|
||
|
|
"epoch": 0.27877361014500507,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004996657791232868,
|
||
|
|
"loss": 6.7958,
|
||
|
|
"mean_token_accuracy": 0.11903122812509537,
|
||
|
|
"num_tokens": 5663178.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.984945917129517,
|
||
|
|
"epoch": 0.279308684252769,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004996636927244092,
|
||
|
|
"loss": 6.8051,
|
||
|
|
"mean_token_accuracy": 0.11196058839559556,
|
||
|
|
"num_tokens": 5673565.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.001294422149658,
|
||
|
|
"epoch": 0.27984375836053293,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.000499661599838399,
|
||
|
|
"loss": 6.8497,
|
||
|
|
"mean_token_accuracy": 0.1122498370707035,
|
||
|
|
"num_tokens": 5684651.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.904658508300781,
|
||
|
|
"epoch": 0.28037883246829687,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004996595004653167,
|
||
|
|
"loss": 6.7432,
|
||
|
|
"mean_token_accuracy": 0.11533383056521415,
|
||
|
|
"num_tokens": 5696081.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9526012420654295,
|
||
|
|
"epoch": 0.2809139065760608,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004996573946052229,
|
||
|
|
"loss": 6.7812,
|
||
|
|
"mean_token_accuracy": 0.1164487712085247,
|
||
|
|
"num_tokens": 5706830.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8979075908660885,
|
||
|
|
"epoch": 0.28144898068382473,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004996552822581783,
|
||
|
|
"loss": 6.7986,
|
||
|
|
"mean_token_accuracy": 0.11754084527492523,
|
||
|
|
"num_tokens": 5717261.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.005229568481445,
|
||
|
|
"epoch": 0.2819840547915886,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000499653163424244,
|
||
|
|
"loss": 6.7734,
|
||
|
|
"mean_token_accuracy": 0.11206443011760711,
|
||
|
|
"num_tokens": 5727280.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.993945360183716,
|
||
|
|
"epoch": 0.28251912889935255,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004996510381034814,
|
||
|
|
"loss": 6.8241,
|
||
|
|
"mean_token_accuracy": 0.10772419720888138,
|
||
|
|
"num_tokens": 5737485.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9192140102386475,
|
||
|
|
"epoch": 0.2830542030071165,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004996489062959515,
|
||
|
|
"loss": 6.7957,
|
||
|
|
"mean_token_accuracy": 0.11468210741877556,
|
||
|
|
"num_tokens": 5747683.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.915011835098267,
|
||
|
|
"epoch": 0.2835892771148804,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004996467680017159,
|
||
|
|
"loss": 6.862,
|
||
|
|
"mean_token_accuracy": 0.10823372080922126,
|
||
|
|
"num_tokens": 5758148.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.931305360794068,
|
||
|
|
"epoch": 0.28412435122264434,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004996446232208365,
|
||
|
|
"loss": 6.7896,
|
||
|
|
"mean_token_accuracy": 0.11629763916134835,
|
||
|
|
"num_tokens": 5769109.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.928414344787598,
|
||
|
|
"epoch": 0.2846594253304083,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004996424719533753,
|
||
|
|
"loss": 6.8193,
|
||
|
|
"mean_token_accuracy": 0.11202871650457383,
|
||
|
|
"num_tokens": 5780344.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.936452388763428,
|
||
|
|
"epoch": 0.2851944994381722,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004996403141993941,
|
||
|
|
"loss": 6.627,
|
||
|
|
"mean_token_accuracy": 0.12468865811824799,
|
||
|
|
"num_tokens": 5790167.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.922191047668457,
|
||
|
|
"epoch": 0.2857295735459361,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004996381499589555,
|
||
|
|
"loss": 6.791,
|
||
|
|
"mean_token_accuracy": 0.11766616478562356,
|
||
|
|
"num_tokens": 5800076.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.001429510116577,
|
||
|
|
"epoch": 0.2862646476537,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004996359792321219,
|
||
|
|
"loss": 6.7247,
|
||
|
|
"mean_token_accuracy": 0.12332994639873504,
|
||
|
|
"num_tokens": 5810547.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.842127323150635,
|
||
|
|
"epoch": 0.28679972176146395,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000499633802018956,
|
||
|
|
"loss": 6.7651,
|
||
|
|
"mean_token_accuracy": 0.11882570460438728,
|
||
|
|
"num_tokens": 5821210.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.933741283416748,
|
||
|
|
"epoch": 0.2873347958692279,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004996316183195204,
|
||
|
|
"loss": 6.8064,
|
||
|
|
"mean_token_accuracy": 0.11239668801426887,
|
||
|
|
"num_tokens": 5832361.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.997045278549194,
|
||
|
|
"epoch": 0.2878698699769918,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004996294281338786,
|
||
|
|
"loss": 6.7965,
|
||
|
|
"mean_token_accuracy": 0.11312427893280982,
|
||
|
|
"num_tokens": 5843242.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.942799377441406,
|
||
|
|
"epoch": 0.28840494408475575,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004996272314620936,
|
||
|
|
"loss": 6.8534,
|
||
|
|
"mean_token_accuracy": 0.11269704699516296,
|
||
|
|
"num_tokens": 5855163.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.908647918701172,
|
||
|
|
"epoch": 0.2889400181925197,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004996250283042288,
|
||
|
|
"loss": 6.7873,
|
||
|
|
"mean_token_accuracy": 0.11659785062074661,
|
||
|
|
"num_tokens": 5866908.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.983246564865112,
|
||
|
|
"epoch": 0.28947509230028357,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000499622818660348,
|
||
|
|
"loss": 6.8308,
|
||
|
|
"mean_token_accuracy": 0.11280549988150597,
|
||
|
|
"num_tokens": 5877342.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.902181339263916,
|
||
|
|
"epoch": 0.2900101664080475,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004996206025305147,
|
||
|
|
"loss": 6.7809,
|
||
|
|
"mean_token_accuracy": 0.11292893514037132,
|
||
|
|
"num_tokens": 5887960.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.913876533508301,
|
||
|
|
"epoch": 0.29054524051581143,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004996183799147932,
|
||
|
|
"loss": 6.7618,
|
||
|
|
"mean_token_accuracy": 0.11444101110100746,
|
||
|
|
"num_tokens": 5899887.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.982015180587768,
|
||
|
|
"epoch": 0.29108031462357536,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004996161508132475,
|
||
|
|
"loss": 6.7616,
|
||
|
|
"mean_token_accuracy": 0.10974067524075508,
|
||
|
|
"num_tokens": 5911022.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.94197039604187,
|
||
|
|
"epoch": 0.2916153887313393,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000499613915225942,
|
||
|
|
"loss": 6.8321,
|
||
|
|
"mean_token_accuracy": 0.11855507642030716,
|
||
|
|
"num_tokens": 5922780.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.964428901672363,
|
||
|
|
"epoch": 0.29215046283910323,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004996116731529412,
|
||
|
|
"loss": 6.8632,
|
||
|
|
"mean_token_accuracy": 0.11426409929990769,
|
||
|
|
"num_tokens": 5934112.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.972011709213257,
|
||
|
|
"epoch": 0.29268553694686716,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00049960942459431,
|
||
|
|
"loss": 6.8045,
|
||
|
|
"mean_token_accuracy": 0.1121431604027748,
|
||
|
|
"num_tokens": 5944386.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.87826681137085,
|
||
|
|
"epoch": 0.29322061105463104,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004996071695501132,
|
||
|
|
"loss": 6.7394,
|
||
|
|
"mean_token_accuracy": 0.1182074099779129,
|
||
|
|
"num_tokens": 5955552.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.928379726409912,
|
||
|
|
"epoch": 0.293755685162395,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004996049080204159,
|
||
|
|
"loss": 6.7346,
|
||
|
|
"mean_token_accuracy": 0.11500842422246933,
|
||
|
|
"num_tokens": 5966790.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.979641532897949,
|
||
|
|
"epoch": 0.2942907592701589,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004996026400052835,
|
||
|
|
"loss": 6.7392,
|
||
|
|
"mean_token_accuracy": 0.11592580303549767,
|
||
|
|
"num_tokens": 5977704.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8253716945648195,
|
||
|
|
"epoch": 0.29482583337792284,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004996003655047814,
|
||
|
|
"loss": 6.7484,
|
||
|
|
"mean_token_accuracy": 0.11899459958076478,
|
||
|
|
"num_tokens": 5989221.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.908860492706299,
|
||
|
|
"epoch": 0.2953609074856868,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.0004995980845189753,
|
||
|
|
"loss": 6.8069,
|
||
|
|
"mean_token_accuracy": 0.11177898719906806,
|
||
|
|
"num_tokens": 6000906.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.967212343215943,
|
||
|
|
"epoch": 0.2958959815934507,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004995957970479312,
|
||
|
|
"loss": 6.8099,
|
||
|
|
"mean_token_accuracy": 0.11111435741186142,
|
||
|
|
"num_tokens": 6012039.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8845288276672365,
|
||
|
|
"epoch": 0.29643105570121464,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0004995935030917148,
|
||
|
|
"loss": 6.6981,
|
||
|
|
"mean_token_accuracy": 0.11647267341613769,
|
||
|
|
"num_tokens": 6024383.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.988625144958496,
|
||
|
|
"epoch": 0.2969661298089785,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004995912026503926,
|
||
|
|
"loss": 6.7698,
|
||
|
|
"mean_token_accuracy": 0.11584996357560158,
|
||
|
|
"num_tokens": 6034904.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.852597904205322,
|
||
|
|
"epoch": 0.29750120391674245,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.000499588895724031,
|
||
|
|
"loss": 6.7743,
|
||
|
|
"mean_token_accuracy": 0.111159298568964,
|
||
|
|
"num_tokens": 6044449.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.959954643249512,
|
||
|
|
"epoch": 0.2980362780245064,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004995865823126968,
|
||
|
|
"loss": 6.7933,
|
||
|
|
"mean_token_accuracy": 0.11641821041703224,
|
||
|
|
"num_tokens": 6054465.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.91104040145874,
|
||
|
|
"epoch": 0.2985713521322703,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004995842624164564,
|
||
|
|
"loss": 6.8124,
|
||
|
|
"mean_token_accuracy": 0.11264995485544205,
|
||
|
|
"num_tokens": 6065539.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.946519184112549,
|
||
|
|
"epoch": 0.29910642624003425,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.000499581936035377,
|
||
|
|
"loss": 6.7705,
|
||
|
|
"mean_token_accuracy": 0.11285096481442451,
|
||
|
|
"num_tokens": 6076135.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.859121942520142,
|
||
|
|
"epoch": 0.2996415003477982,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004995796031695257,
|
||
|
|
"loss": 6.7652,
|
||
|
|
"mean_token_accuracy": 0.11385954692959785,
|
||
|
|
"num_tokens": 6086604.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.977310657501221,
|
||
|
|
"epoch": 0.3001765744555621,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00049957726381897,
|
||
|
|
"loss": 6.785,
|
||
|
|
"mean_token_accuracy": 0.11666215732693672,
|
||
|
|
"num_tokens": 6095672.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.85119218826294,
|
||
|
|
"epoch": 0.300711648563326,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004995749179837773,
|
||
|
|
"loss": 6.6622,
|
||
|
|
"mean_token_accuracy": 0.12312485352158546,
|
||
|
|
"num_tokens": 6105652.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.840598678588867,
|
||
|
|
"epoch": 0.30124672267108993,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004995725656640155,
|
||
|
|
"loss": 6.7056,
|
||
|
|
"mean_token_accuracy": 0.1178930640220642,
|
||
|
|
"num_tokens": 6116930.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.875258922576904,
|
||
|
|
"epoch": 0.30178179677885386,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004995702068597524,
|
||
|
|
"loss": 6.7157,
|
||
|
|
"mean_token_accuracy": 0.12197659760713578,
|
||
|
|
"num_tokens": 6126659.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.899388074874878,
|
||
|
|
"epoch": 0.3023168708866178,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004995678415710561,
|
||
|
|
"loss": 6.7457,
|
||
|
|
"mean_token_accuracy": 0.115099136531353,
|
||
|
|
"num_tokens": 6137227.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.978420209884644,
|
||
|
|
"epoch": 0.3028519449943817,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000499565469797995,
|
||
|
|
"loss": 6.7977,
|
||
|
|
"mean_token_accuracy": 0.1148864470422268,
|
||
|
|
"num_tokens": 6147800.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.862562036514282,
|
||
|
|
"epoch": 0.30338701910214566,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004995630915406374,
|
||
|
|
"loss": 6.6492,
|
||
|
|
"mean_token_accuracy": 0.12218020334839821,
|
||
|
|
"num_tokens": 6157671.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.896828746795654,
|
||
|
|
"epoch": 0.3039220932099096,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004995607067990521,
|
||
|
|
"loss": 6.7933,
|
||
|
|
"mean_token_accuracy": 0.11226967573165894,
|
||
|
|
"num_tokens": 6168651.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8445981502532955,
|
||
|
|
"epoch": 0.30445716731767347,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000499558315573308,
|
||
|
|
"loss": 6.7653,
|
||
|
|
"mean_token_accuracy": 0.11298804879188537,
|
||
|
|
"num_tokens": 6179925.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.870256233215332,
|
||
|
|
"epoch": 0.3049922414254374,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004995559178634741,
|
||
|
|
"loss": 6.7605,
|
||
|
|
"mean_token_accuracy": 0.11938253119587898,
|
||
|
|
"num_tokens": 6190541.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.023727226257324,
|
||
|
|
"epoch": 0.30552731553320134,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004995535136696196,
|
||
|
|
"loss": 6.7961,
|
||
|
|
"mean_token_accuracy": 0.11052935272455215,
|
||
|
|
"num_tokens": 6201491.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.799321126937866,
|
||
|
|
"epoch": 0.30606238964096527,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.000499551102991814,
|
||
|
|
"loss": 6.616,
|
||
|
|
"mean_token_accuracy": 0.12260399758815765,
|
||
|
|
"num_tokens": 6212443.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.903628635406494,
|
||
|
|
"epoch": 0.3065974637487292,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004995486858301268,
|
||
|
|
"loss": 6.8178,
|
||
|
|
"mean_token_accuracy": 0.108098603785038,
|
||
|
|
"num_tokens": 6222623.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.90746922492981,
|
||
|
|
"epoch": 0.30713253785649314,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004995462621846279,
|
||
|
|
"loss": 6.7064,
|
||
|
|
"mean_token_accuracy": 0.11651685237884521,
|
||
|
|
"num_tokens": 6233712.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9290708065032955,
|
||
|
|
"epoch": 0.30766761196425707,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004995438320553871,
|
||
|
|
"loss": 6.7715,
|
||
|
|
"mean_token_accuracy": 0.11282215490937234,
|
||
|
|
"num_tokens": 6244254.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.881653308868408,
|
||
|
|
"epoch": 0.30820268607202095,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004995413954424748,
|
||
|
|
"loss": 6.6712,
|
||
|
|
"mean_token_accuracy": 0.12289544939994812,
|
||
|
|
"num_tokens": 6254202.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.872118377685547,
|
||
|
|
"epoch": 0.3087377601797849,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004995389523459612,
|
||
|
|
"loss": 6.7368,
|
||
|
|
"mean_token_accuracy": 0.11404762491583824,
|
||
|
|
"num_tokens": 6264496.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.84141526222229,
|
||
|
|
"epoch": 0.3092728342875488,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000499536502765917,
|
||
|
|
"loss": 6.7556,
|
||
|
|
"mean_token_accuracy": 0.12146841287612915,
|
||
|
|
"num_tokens": 6275835.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.885162115097046,
|
||
|
|
"epoch": 0.30980790839531275,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004995340467024128,
|
||
|
|
"loss": 6.6989,
|
||
|
|
"mean_token_accuracy": 0.11953729987144471,
|
||
|
|
"num_tokens": 6286805.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.878981494903565,
|
||
|
|
"epoch": 0.3103429825030767,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004995315841555195,
|
||
|
|
"loss": 6.7113,
|
||
|
|
"mean_token_accuracy": 0.11021909192204475,
|
||
|
|
"num_tokens": 6298444.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.813249588012695,
|
||
|
|
"epoch": 0.3108780566108406,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004995291151253083,
|
||
|
|
"loss": 6.6436,
|
||
|
|
"mean_token_accuracy": 0.12175455540418625,
|
||
|
|
"num_tokens": 6308259.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.857611513137817,
|
||
|
|
"epoch": 0.31141313071860455,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004995266396118505,
|
||
|
|
"loss": 6.72,
|
||
|
|
"mean_token_accuracy": 0.11006433069705963,
|
||
|
|
"num_tokens": 6320058.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8574628829956055,
|
||
|
|
"epoch": 0.3119482048263684,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004995241576152174,
|
||
|
|
"loss": 6.6938,
|
||
|
|
"mean_token_accuracy": 0.11197758540511131,
|
||
|
|
"num_tokens": 6331203.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.926673221588135,
|
||
|
|
"epoch": 0.31248327893413236,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.000499521669135481,
|
||
|
|
"loss": 6.8007,
|
||
|
|
"mean_token_accuracy": 0.11380135864019394,
|
||
|
|
"num_tokens": 6342027.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.901452732086182,
|
||
|
|
"epoch": 0.3130183530418963,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004995191741727128,
|
||
|
|
"loss": 6.6965,
|
||
|
|
"mean_token_accuracy": 0.11690429598093033,
|
||
|
|
"num_tokens": 6352580.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.897034406661987,
|
||
|
|
"epoch": 0.3135534271496602,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.000499516672726985,
|
||
|
|
"loss": 6.699,
|
||
|
|
"mean_token_accuracy": 0.12443051934242248,
|
||
|
|
"num_tokens": 6363997.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.855990314483643,
|
||
|
|
"epoch": 0.31408850125742416,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004995141647983699,
|
||
|
|
"loss": 6.7583,
|
||
|
|
"mean_token_accuracy": 0.11855747178196907,
|
||
|
|
"num_tokens": 6375284.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.844248676300049,
|
||
|
|
"epoch": 0.3146235753651881,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004995116503869398,
|
||
|
|
"loss": 6.6672,
|
||
|
|
"mean_token_accuracy": 0.12428331449627876,
|
||
|
|
"num_tokens": 6386698.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.867465877532959,
|
||
|
|
"epoch": 0.315158649472952,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004995091294927673,
|
||
|
|
"loss": 6.7408,
|
||
|
|
"mean_token_accuracy": 0.11660289838910103,
|
||
|
|
"num_tokens": 6397237.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.98031268119812,
|
||
|
|
"epoch": 0.3156937235807159,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004995066021159253,
|
||
|
|
"loss": 6.8387,
|
||
|
|
"mean_token_accuracy": 0.11507428362965584,
|
||
|
|
"num_tokens": 6408266.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.814388084411621,
|
||
|
|
"epoch": 0.31622879768847983,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004995040682564867,
|
||
|
|
"loss": 6.7375,
|
||
|
|
"mean_token_accuracy": 0.12039956524968147,
|
||
|
|
"num_tokens": 6419563.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.865634298324585,
|
||
|
|
"epoch": 0.31676387179624377,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004995015279145247,
|
||
|
|
"loss": 6.6945,
|
||
|
|
"mean_token_accuracy": 0.12165094465017319,
|
||
|
|
"num_tokens": 6430220.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.879283094406128,
|
||
|
|
"epoch": 0.3172989459040077,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004994989810901126,
|
||
|
|
"loss": 6.7139,
|
||
|
|
"mean_token_accuracy": 0.1167122632265091,
|
||
|
|
"num_tokens": 6440157.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.871557569503784,
|
||
|
|
"epoch": 0.31783402001177163,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004994964277833239,
|
||
|
|
"loss": 6.7633,
|
||
|
|
"mean_token_accuracy": 0.1225232295691967,
|
||
|
|
"num_tokens": 6449511.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.925748014450074,
|
||
|
|
"epoch": 0.31836909411953557,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004994938679942324,
|
||
|
|
"loss": 6.7496,
|
||
|
|
"mean_token_accuracy": 0.11134742796421052,
|
||
|
|
"num_tokens": 6460608.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8563477993011475,
|
||
|
|
"epoch": 0.3189041682272995,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004994913017229121,
|
||
|
|
"loss": 6.7304,
|
||
|
|
"mean_token_accuracy": 0.12039977535605431,
|
||
|
|
"num_tokens": 6472737.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.803793001174927,
|
||
|
|
"epoch": 0.31943924233506343,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004994887289694371,
|
||
|
|
"loss": 6.6205,
|
||
|
|
"mean_token_accuracy": 0.12295867651700973,
|
||
|
|
"num_tokens": 6482993.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9399620532989506,
|
||
|
|
"epoch": 0.3199743164428273,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004994861497338814,
|
||
|
|
"loss": 6.8293,
|
||
|
|
"mean_token_accuracy": 0.11786540225148201,
|
||
|
|
"num_tokens": 6494530.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.926778125762939,
|
||
|
|
"epoch": 0.32050939055059124,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004994835640163198,
|
||
|
|
"loss": 6.6588,
|
||
|
|
"mean_token_accuracy": 0.11456671357154846,
|
||
|
|
"num_tokens": 6504691.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.821675395965576,
|
||
|
|
"epoch": 0.3210444646583552,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004994809718168267,
|
||
|
|
"loss": 6.684,
|
||
|
|
"mean_token_accuracy": 0.11950030028820038,
|
||
|
|
"num_tokens": 6514924.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3210444646583552,
|
||
|
|
"eval_entropy": 6.548516875521513,
|
||
|
|
"eval_loss": 6.794521331787109,
|
||
|
|
"eval_mean_token_accuracy": 0.12106629688332907,
|
||
|
|
"eval_num_tokens": 6514924.0,
|
||
|
|
"eval_runtime": 17.6213,
|
||
|
|
"eval_samples_per_second": 1684.272,
|
||
|
|
"eval_steps_per_second": 210.541,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 93440,
|
||
|
|
"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": 1414915727523840.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|