2fffa573bd
Model: fpadovani/ind-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2334176230305388,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.868724536895752,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 17.5,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.1486,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 8095.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.891779136657715,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 26.125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.148,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 17329.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.949541425704956,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 23.25,
|
|
"learning_rate": 7e-06,
|
|
"loss": 13.9134,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 25729.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.25663423538208,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 35.0,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.3982,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 33980.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.6940947532653805,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 26.0,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 12.2791,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 41675.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 9.23413438796997,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 6.84375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 11.2025,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 50277.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.568378067016601,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.7304,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 58790.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.704268169403075,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.5063,
|
|
"mean_token_accuracy": 0.024650751310400666,
|
|
"num_tokens": 67247.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.695908069610596,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.1754,
|
|
"mean_token_accuracy": 0.04813225194811821,
|
|
"num_tokens": 75174.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.63707094192505,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.8604,
|
|
"mean_token_accuracy": 0.05086616277694702,
|
|
"num_tokens": 83203.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.510939502716065,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.6639,
|
|
"mean_token_accuracy": 0.04917947538197041,
|
|
"num_tokens": 91798.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.447108936309814,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.6115,
|
|
"mean_token_accuracy": 0.047414034977555274,
|
|
"num_tokens": 100869.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.47428493499756,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.5064,
|
|
"mean_token_accuracy": 0.043885057978332045,
|
|
"num_tokens": 109697.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.48178014755249,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.4411,
|
|
"mean_token_accuracy": 0.04529423713684082,
|
|
"num_tokens": 118656.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.426056289672852,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.4078,
|
|
"mean_token_accuracy": 0.04362858422100544,
|
|
"num_tokens": 127748.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.388638496398926,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.2589,
|
|
"mean_token_accuracy": 0.04771117903292179,
|
|
"num_tokens": 136621.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.360412406921387,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.0947,
|
|
"mean_token_accuracy": 0.05321100503206253,
|
|
"num_tokens": 145793.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.309724712371827,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.9975,
|
|
"mean_token_accuracy": 0.05680464021861553,
|
|
"num_tokens": 154466.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.248615932464599,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.9498,
|
|
"mean_token_accuracy": 0.05836099237203598,
|
|
"num_tokens": 163297.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.143774604797363,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.7819,
|
|
"mean_token_accuracy": 0.06600868813693524,
|
|
"num_tokens": 171747.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.016874027252197,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.7019,
|
|
"mean_token_accuracy": 0.062353368103504184,
|
|
"num_tokens": 180499.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.008924961090088,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.5723,
|
|
"mean_token_accuracy": 0.06311165988445282,
|
|
"num_tokens": 189227.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.854091453552247,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.4385,
|
|
"mean_token_accuracy": 0.06438967436552048,
|
|
"num_tokens": 198388.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.726921844482423,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.3286,
|
|
"mean_token_accuracy": 0.06439770273864269,
|
|
"num_tokens": 206854.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.583395957946777,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.2097,
|
|
"mean_token_accuracy": 0.06303132474422454,
|
|
"num_tokens": 215506.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.42068099975586,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.1093,
|
|
"mean_token_accuracy": 0.06823768317699433,
|
|
"num_tokens": 223717.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.187827396392823,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.9995,
|
|
"mean_token_accuracy": 0.06632016785442829,
|
|
"num_tokens": 232480.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.082991695404052,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.9293,
|
|
"mean_token_accuracy": 0.06358420252799987,
|
|
"num_tokens": 241350.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.822460651397705,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.8758,
|
|
"mean_token_accuracy": 0.06782571263611317,
|
|
"num_tokens": 250610.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.690089511871339,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.7822,
|
|
"mean_token_accuracy": 0.060015364363789556,
|
|
"num_tokens": 259672.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.512046813964844,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.7639,
|
|
"mean_token_accuracy": 0.06780118122696877,
|
|
"num_tokens": 267826.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.466501140594483,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.7686,
|
|
"mean_token_accuracy": 0.060590619966387746,
|
|
"num_tokens": 277324.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.349157810211182,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.6015,
|
|
"mean_token_accuracy": 0.06816631369292736,
|
|
"num_tokens": 285482.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.220991134643555,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.6413,
|
|
"mean_token_accuracy": 0.06899847462773323,
|
|
"num_tokens": 293684.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.094815015792847,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.602,
|
|
"mean_token_accuracy": 0.06723922677338123,
|
|
"num_tokens": 302605.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.08293595314026,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.6409,
|
|
"mean_token_accuracy": 0.0671521469950676,
|
|
"num_tokens": 310849.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.118443584442138,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.646,
|
|
"mean_token_accuracy": 0.06186659783124924,
|
|
"num_tokens": 319752.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.10387020111084,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.681,
|
|
"mean_token_accuracy": 0.06433467343449592,
|
|
"num_tokens": 328009.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.984123754501343,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.5648,
|
|
"mean_token_accuracy": 0.0687804438173771,
|
|
"num_tokens": 337414.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.993130111694336,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.5609,
|
|
"mean_token_accuracy": 0.06835784390568733,
|
|
"num_tokens": 345419.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.953881740570068,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.5415,
|
|
"mean_token_accuracy": 0.07114643156528473,
|
|
"num_tokens": 353435.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.923952913284301,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.5578,
|
|
"mean_token_accuracy": 0.07233858108520508,
|
|
"num_tokens": 361840.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.9594556331634525,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.6335,
|
|
"mean_token_accuracy": 0.06823679059743881,
|
|
"num_tokens": 370873.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.93640627861023,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.5629,
|
|
"mean_token_accuracy": 0.06850668452680111,
|
|
"num_tokens": 379558.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.873511123657226,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.5426,
|
|
"mean_token_accuracy": 0.07185782194137573,
|
|
"num_tokens": 387870.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.965339994430542,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.6015,
|
|
"mean_token_accuracy": 0.07074649557471276,
|
|
"num_tokens": 396442.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.89727029800415,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.5481,
|
|
"mean_token_accuracy": 0.0699117787182331,
|
|
"num_tokens": 404764.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.8868903636932375,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.4854,
|
|
"mean_token_accuracy": 0.0721463244408369,
|
|
"num_tokens": 413355.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.873054361343383,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.4,
|
|
"mean_token_accuracy": 0.07351703196763992,
|
|
"num_tokens": 421868.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.893638324737549,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.4402,
|
|
"mean_token_accuracy": 0.07299891375005245,
|
|
"num_tokens": 431106.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.8072466373443605,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.5599,
|
|
"mean_token_accuracy": 0.06760080493986606,
|
|
"num_tokens": 439459.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.876844310760498,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.3982,
|
|
"mean_token_accuracy": 0.07463918179273606,
|
|
"num_tokens": 447943.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.733979797363281,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.5169,
|
|
"mean_token_accuracy": 0.07182875908911228,
|
|
"num_tokens": 456691.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.837671566009521,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.4317,
|
|
"mean_token_accuracy": 0.07321453914046287,
|
|
"num_tokens": 466388.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.768101596832276,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.494,
|
|
"mean_token_accuracy": 0.07455857545137405,
|
|
"num_tokens": 474544.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.842556571960449,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.516,
|
|
"mean_token_accuracy": 0.074214668571949,
|
|
"num_tokens": 483561.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.771492433547974,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.3561,
|
|
"mean_token_accuracy": 0.07050973400473595,
|
|
"num_tokens": 492036.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.75999813079834,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.4784,
|
|
"mean_token_accuracy": 0.06661519259214402,
|
|
"num_tokens": 500978.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.853191137313843,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.475,
|
|
"mean_token_accuracy": 0.07539443038403988,
|
|
"num_tokens": 509719.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.738577365875244,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.4126,
|
|
"mean_token_accuracy": 0.07369871325790882,
|
|
"num_tokens": 518422.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.7334229946136475,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.4423,
|
|
"mean_token_accuracy": 0.0712751142680645,
|
|
"num_tokens": 527172.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.780814075469971,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.3618,
|
|
"mean_token_accuracy": 0.07441995665431023,
|
|
"num_tokens": 536070.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.7062712669372555,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.3546,
|
|
"mean_token_accuracy": 0.07498554512858391,
|
|
"num_tokens": 544556.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.870984935760498,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.3584,
|
|
"mean_token_accuracy": 0.07835289165377617,
|
|
"num_tokens": 553122.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.6616284370422365,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.4064,
|
|
"mean_token_accuracy": 0.0707610372453928,
|
|
"num_tokens": 562265.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.606665897369385,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.359,
|
|
"mean_token_accuracy": 0.08119581118226052,
|
|
"num_tokens": 570938.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.7274675369262695,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.3081,
|
|
"mean_token_accuracy": 0.07931275889277459,
|
|
"num_tokens": 578568.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.719749879837036,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.3575,
|
|
"mean_token_accuracy": 0.07647890225052834,
|
|
"num_tokens": 587013.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.669827508926391,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.3932,
|
|
"mean_token_accuracy": 0.07862738743424416,
|
|
"num_tokens": 595354.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.759836196899414,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.3681,
|
|
"mean_token_accuracy": 0.07964789792895317,
|
|
"num_tokens": 603971.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.578008699417114,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.2821,
|
|
"mean_token_accuracy": 0.08256564736366272,
|
|
"num_tokens": 612097.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.757014989852905,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.3505,
|
|
"mean_token_accuracy": 0.07818787395954133,
|
|
"num_tokens": 621445.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.615339231491089,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.4092,
|
|
"mean_token_accuracy": 0.0784608293324709,
|
|
"num_tokens": 630041.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.631348466873169,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.2121,
|
|
"mean_token_accuracy": 0.08307572454214096,
|
|
"num_tokens": 638317.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.66585636138916,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.3499,
|
|
"mean_token_accuracy": 0.07931018397212028,
|
|
"num_tokens": 647297.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.729125881195069,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.3836,
|
|
"mean_token_accuracy": 0.08041680678725242,
|
|
"num_tokens": 655309.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.609511232376098,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.2463,
|
|
"mean_token_accuracy": 0.07354939132928848,
|
|
"num_tokens": 663879.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.602015590667724,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.1702,
|
|
"mean_token_accuracy": 0.08083694204688072,
|
|
"num_tokens": 672913.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.568642234802246,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.2686,
|
|
"mean_token_accuracy": 0.08029174320399761,
|
|
"num_tokens": 682282.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.541975831985473,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.2759,
|
|
"mean_token_accuracy": 0.07506514936685563,
|
|
"num_tokens": 691432.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.6201324462890625,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.263,
|
|
"mean_token_accuracy": 0.08165091350674629,
|
|
"num_tokens": 700639.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.666884183883667,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.3413,
|
|
"mean_token_accuracy": 0.07532657012343406,
|
|
"num_tokens": 709200.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.459015941619873,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.1665,
|
|
"mean_token_accuracy": 0.08444926962256431,
|
|
"num_tokens": 717266.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.566874313354492,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.1734,
|
|
"mean_token_accuracy": 0.08190047703683376,
|
|
"num_tokens": 725799.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.5747381210327145,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.2685,
|
|
"mean_token_accuracy": 0.08348871022462845,
|
|
"num_tokens": 734375.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.568057584762573,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.3127,
|
|
"mean_token_accuracy": 0.07849649339914322,
|
|
"num_tokens": 743453.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.540275430679321,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.1611,
|
|
"mean_token_accuracy": 0.0852227695286274,
|
|
"num_tokens": 752443.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.473781156539917,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.1522,
|
|
"mean_token_accuracy": 0.07828448340296745,
|
|
"num_tokens": 761294.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.516408538818359,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.1092,
|
|
"mean_token_accuracy": 0.08720964565873146,
|
|
"num_tokens": 769489.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.519400596618652,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.1954,
|
|
"mean_token_accuracy": 0.07971547171473503,
|
|
"num_tokens": 777836.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.5304583549499515,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.212,
|
|
"mean_token_accuracy": 0.07866286486387253,
|
|
"num_tokens": 786543.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.456272268295288,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.2535,
|
|
"mean_token_accuracy": 0.08314662128686905,
|
|
"num_tokens": 794525.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.433866357803344,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.1606,
|
|
"mean_token_accuracy": 0.08660675287246704,
|
|
"num_tokens": 803537.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.4901923656463625,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.1265,
|
|
"mean_token_accuracy": 0.08419004380702973,
|
|
"num_tokens": 811706.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.434392309188842,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.1685,
|
|
"mean_token_accuracy": 0.0864868015050888,
|
|
"num_tokens": 820182.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.459165287017822,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.1077,
|
|
"mean_token_accuracy": 0.08410876803100109,
|
|
"num_tokens": 829808.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.448411321640014,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.048,
|
|
"mean_token_accuracy": 0.08421071916818619,
|
|
"num_tokens": 838838.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.44689908027649,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.1524,
|
|
"mean_token_accuracy": 0.08371994793415069,
|
|
"num_tokens": 847800.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.513600492477417,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.2233,
|
|
"mean_token_accuracy": 0.08270580545067788,
|
|
"num_tokens": 856503.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.354915380477905,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.1189,
|
|
"mean_token_accuracy": 0.08470338881015778,
|
|
"num_tokens": 865245.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.403017473220825,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.1297,
|
|
"mean_token_accuracy": 0.08570023030042648,
|
|
"num_tokens": 874485.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.318638038635254,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.9894,
|
|
"mean_token_accuracy": 0.09045747816562652,
|
|
"num_tokens": 883301.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.306433153152466,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.0393,
|
|
"mean_token_accuracy": 0.08763011917471886,
|
|
"num_tokens": 892387.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.318406486511231,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.036,
|
|
"mean_token_accuracy": 0.09374425634741783,
|
|
"num_tokens": 901522.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.283069658279419,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.9894,
|
|
"mean_token_accuracy": 0.08943136781454086,
|
|
"num_tokens": 909848.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.451201486587524,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.2176,
|
|
"mean_token_accuracy": 0.08226554542779922,
|
|
"num_tokens": 919079.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.3233407497406,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.963,
|
|
"mean_token_accuracy": 0.09083623737096787,
|
|
"num_tokens": 927807.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.230840492248535,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.0691,
|
|
"mean_token_accuracy": 0.091452506929636,
|
|
"num_tokens": 936498.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.414189958572388,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.1387,
|
|
"mean_token_accuracy": 0.09394621923565864,
|
|
"num_tokens": 945436.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.326435708999634,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.0618,
|
|
"mean_token_accuracy": 0.08727624863386155,
|
|
"num_tokens": 953990.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.232479190826416,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.9777,
|
|
"mean_token_accuracy": 0.09197546169161797,
|
|
"num_tokens": 962008.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.343172931671143,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.1391,
|
|
"mean_token_accuracy": 0.08779035359621049,
|
|
"num_tokens": 970935.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.3697394847869875,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.0947,
|
|
"mean_token_accuracy": 0.08397784754633904,
|
|
"num_tokens": 979492.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.260292625427246,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.9991,
|
|
"mean_token_accuracy": 0.08743947520852088,
|
|
"num_tokens": 987866.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.262716388702392,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.0328,
|
|
"mean_token_accuracy": 0.09108475595712662,
|
|
"num_tokens": 996760.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.308055782318116,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.9709,
|
|
"mean_token_accuracy": 0.09112134501338005,
|
|
"num_tokens": 1005432.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.290707445144653,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.0545,
|
|
"mean_token_accuracy": 0.0900682970881462,
|
|
"num_tokens": 1013729.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.068312883377075,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.8894,
|
|
"mean_token_accuracy": 0.09857918545603753,
|
|
"num_tokens": 1022485.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.210888338088989,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.9469,
|
|
"mean_token_accuracy": 0.09099083542823791,
|
|
"num_tokens": 1030523.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.292349624633789,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.0544,
|
|
"mean_token_accuracy": 0.09193994700908661,
|
|
"num_tokens": 1039268.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.170610523223877,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.9503,
|
|
"mean_token_accuracy": 0.09305147007107735,
|
|
"num_tokens": 1048590.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.1161217212677,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.8817,
|
|
"mean_token_accuracy": 0.09100724905729293,
|
|
"num_tokens": 1057232.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.188746976852417,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.9444,
|
|
"mean_token_accuracy": 0.08997739925980568,
|
|
"num_tokens": 1066404.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.160967588424683,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.0056,
|
|
"mean_token_accuracy": 0.08781350031495094,
|
|
"num_tokens": 1075093.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.1323071956634525,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.9276,
|
|
"mean_token_accuracy": 0.09003649577498436,
|
|
"num_tokens": 1084454.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.157799243927002,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.8467,
|
|
"mean_token_accuracy": 0.09403926953673362,
|
|
"num_tokens": 1093452.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.186054420471192,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.8691,
|
|
"mean_token_accuracy": 0.09542709589004517,
|
|
"num_tokens": 1101814.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.078825283050537,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.9504,
|
|
"mean_token_accuracy": 0.09376255795359612,
|
|
"num_tokens": 1110386.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.1958681583404545,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.0501,
|
|
"mean_token_accuracy": 0.08292681574821473,
|
|
"num_tokens": 1120141.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.147344017028809,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.9687,
|
|
"mean_token_accuracy": 0.09161446392536163,
|
|
"num_tokens": 1129920.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.015273141860962,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.8553,
|
|
"mean_token_accuracy": 0.09384810253977775,
|
|
"num_tokens": 1138518.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.139459609985352,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.9721,
|
|
"mean_token_accuracy": 0.08497107923030853,
|
|
"num_tokens": 1147113.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.057343339920044,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.8095,
|
|
"mean_token_accuracy": 0.09642426520586014,
|
|
"num_tokens": 1155886.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.103746461868286,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.9542,
|
|
"mean_token_accuracy": 0.09668822288513183,
|
|
"num_tokens": 1164200.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.031191968917847,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.8286,
|
|
"mean_token_accuracy": 0.09215016961097718,
|
|
"num_tokens": 1172720.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.015228414535523,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.7712,
|
|
"mean_token_accuracy": 0.09318645074963569,
|
|
"num_tokens": 1181225.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.15850133895874,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.9747,
|
|
"mean_token_accuracy": 0.09126665517687797,
|
|
"num_tokens": 1190070.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.017357587814331,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.8557,
|
|
"mean_token_accuracy": 0.09437393769621849,
|
|
"num_tokens": 1198995.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.108525228500366,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.9139,
|
|
"mean_token_accuracy": 0.09893580600619316,
|
|
"num_tokens": 1207664.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.1310450553894045,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.8008,
|
|
"mean_token_accuracy": 0.10891369134187698,
|
|
"num_tokens": 1216232.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.994553136825561,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.884,
|
|
"mean_token_accuracy": 0.09593645855784416,
|
|
"num_tokens": 1224106.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.933602619171142,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.7804,
|
|
"mean_token_accuracy": 0.10029099360108376,
|
|
"num_tokens": 1232514.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.105175018310547,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.8244,
|
|
"mean_token_accuracy": 0.10292564630508423,
|
|
"num_tokens": 1240178.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.9011462211608885,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.75,
|
|
"mean_token_accuracy": 0.1004354253411293,
|
|
"num_tokens": 1248635.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.058794069290161,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.8454,
|
|
"mean_token_accuracy": 0.10295553430914879,
|
|
"num_tokens": 1256389.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.923951578140259,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.8013,
|
|
"mean_token_accuracy": 0.09758390784263611,
|
|
"num_tokens": 1264035.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.092983961105347,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.8054,
|
|
"mean_token_accuracy": 0.09857210367918015,
|
|
"num_tokens": 1272941.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.776862668991089,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.7916,
|
|
"mean_token_accuracy": 0.10023090690374374,
|
|
"num_tokens": 1281767.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.078878498077392,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.8725,
|
|
"mean_token_accuracy": 0.1040918543934822,
|
|
"num_tokens": 1290049.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.88560905456543,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.6878,
|
|
"mean_token_accuracy": 0.10409798175096512,
|
|
"num_tokens": 1299032.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.961802768707275,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.9603,
|
|
"mean_token_accuracy": 0.09438887834548951,
|
|
"num_tokens": 1308508.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.064554643630982,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.7931,
|
|
"mean_token_accuracy": 0.10270294025540352,
|
|
"num_tokens": 1317044.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.964282894134522,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.809,
|
|
"mean_token_accuracy": 0.10116439014673233,
|
|
"num_tokens": 1325554.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.90094223022461,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.6974,
|
|
"mean_token_accuracy": 0.09834365025162697,
|
|
"num_tokens": 1334201.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.887777614593506,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.7209,
|
|
"mean_token_accuracy": 0.10774503573775292,
|
|
"num_tokens": 1343061.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.859195232391357,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.6786,
|
|
"mean_token_accuracy": 0.10537986010313034,
|
|
"num_tokens": 1352262.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.866818618774414,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.7495,
|
|
"mean_token_accuracy": 0.09941672831773758,
|
|
"num_tokens": 1361400.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.006886291503906,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.8369,
|
|
"mean_token_accuracy": 0.0997631348669529,
|
|
"num_tokens": 1369850.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.788526773452759,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.6824,
|
|
"mean_token_accuracy": 0.10736593306064605,
|
|
"num_tokens": 1378342.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.927976512908936,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.7924,
|
|
"mean_token_accuracy": 0.09832986444234848,
|
|
"num_tokens": 1386981.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.989340591430664,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.8623,
|
|
"mean_token_accuracy": 0.09800197407603264,
|
|
"num_tokens": 1395801.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.974379205703736,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.7523,
|
|
"mean_token_accuracy": 0.10530616566538811,
|
|
"num_tokens": 1403715.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.0467917919158936,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.8484,
|
|
"mean_token_accuracy": 0.09779960736632347,
|
|
"num_tokens": 1413199.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.8538792610168455,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.8357,
|
|
"mean_token_accuracy": 0.10221734568476677,
|
|
"num_tokens": 1421918.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.861208772659301,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.713,
|
|
"mean_token_accuracy": 0.099763373285532,
|
|
"num_tokens": 1430625.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.8965160846710205,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.7463,
|
|
"mean_token_accuracy": 0.101302270591259,
|
|
"num_tokens": 1439158.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.761336946487427,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.7006,
|
|
"mean_token_accuracy": 0.10375607237219811,
|
|
"num_tokens": 1448266.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.932992315292358,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.7856,
|
|
"mean_token_accuracy": 0.10553251951932907,
|
|
"num_tokens": 1457322.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.940921783447266,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.905,
|
|
"mean_token_accuracy": 0.09642096757888793,
|
|
"num_tokens": 1466120.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.877140855789184,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.6655,
|
|
"mean_token_accuracy": 0.10028111264109611,
|
|
"num_tokens": 1474965.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.782597208023072,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.7623,
|
|
"mean_token_accuracy": 0.10180079340934753,
|
|
"num_tokens": 1483483.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.930035066604614,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.6985,
|
|
"mean_token_accuracy": 0.0988282911479473,
|
|
"num_tokens": 1492313.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.802086067199707,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.6205,
|
|
"mean_token_accuracy": 0.10422073453664779,
|
|
"num_tokens": 1501081.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.703395795822144,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.6475,
|
|
"mean_token_accuracy": 0.1006127305328846,
|
|
"num_tokens": 1510169.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.842187690734863,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5884,
|
|
"mean_token_accuracy": 0.10198393240571021,
|
|
"num_tokens": 1519546.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.701787328720092,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.6955,
|
|
"mean_token_accuracy": 0.09849147126078606,
|
|
"num_tokens": 1529104.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.727069425582886,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.653,
|
|
"mean_token_accuracy": 0.11421328037977219,
|
|
"num_tokens": 1537033.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.807587718963623,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.6796,
|
|
"mean_token_accuracy": 0.10756831169128418,
|
|
"num_tokens": 1545059.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.851893138885498,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.6941,
|
|
"mean_token_accuracy": 0.10561164915561676,
|
|
"num_tokens": 1553784.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.693432712554932,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.6167,
|
|
"mean_token_accuracy": 0.10881831496953964,
|
|
"num_tokens": 1562059.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.777541732788086,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.6848,
|
|
"mean_token_accuracy": 0.10598696693778038,
|
|
"num_tokens": 1570061.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.781379699707031,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.6588,
|
|
"mean_token_accuracy": 0.10451298281550407,
|
|
"num_tokens": 1578261.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.708835935592651,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.5728,
|
|
"mean_token_accuracy": 0.108784069865942,
|
|
"num_tokens": 1586260.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.839280271530152,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.7433,
|
|
"mean_token_accuracy": 0.10013837367296219,
|
|
"num_tokens": 1595234.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.70526909828186,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.6588,
|
|
"mean_token_accuracy": 0.10594909787178039,
|
|
"num_tokens": 1604212.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.769180774688721,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.6854,
|
|
"mean_token_accuracy": 0.10409966185688972,
|
|
"num_tokens": 1612925.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.6779365062713625,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.5829,
|
|
"mean_token_accuracy": 0.10564278215169906,
|
|
"num_tokens": 1621804.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.673547887802124,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.5768,
|
|
"mean_token_accuracy": 0.10946961864829063,
|
|
"num_tokens": 1630943.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.686461353302002,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.479,
|
|
"mean_token_accuracy": 0.109093077480793,
|
|
"num_tokens": 1638899.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.665160274505615,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.6837,
|
|
"mean_token_accuracy": 0.10972491055727004,
|
|
"num_tokens": 1647485.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.800267505645752,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.6331,
|
|
"mean_token_accuracy": 0.11150100603699684,
|
|
"num_tokens": 1656290.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.686690902709961,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.673,
|
|
"mean_token_accuracy": 0.11151936575770378,
|
|
"num_tokens": 1665474.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.701140642166138,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.5381,
|
|
"mean_token_accuracy": 0.11096475347876548,
|
|
"num_tokens": 1673599.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.659738826751709,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.53,
|
|
"mean_token_accuracy": 0.1062575913965702,
|
|
"num_tokens": 1683282.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.715300607681274,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.6514,
|
|
"mean_token_accuracy": 0.11183567643165589,
|
|
"num_tokens": 1691094.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.577898406982422,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.506,
|
|
"mean_token_accuracy": 0.11562167555093765,
|
|
"num_tokens": 1700053.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.557030916213989,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4294,
|
|
"mean_token_accuracy": 0.11256621927022933,
|
|
"num_tokens": 1707732.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.711409378051758,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.6956,
|
|
"mean_token_accuracy": 0.106421110779047,
|
|
"num_tokens": 1716406.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.768523073196411,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.7278,
|
|
"mean_token_accuracy": 0.10514088124036788,
|
|
"num_tokens": 1725832.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.696955347061158,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.6202,
|
|
"mean_token_accuracy": 0.10349752753973007,
|
|
"num_tokens": 1734853.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.6868829250335695,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.6371,
|
|
"mean_token_accuracy": 0.11080349832773209,
|
|
"num_tokens": 1744240.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.718117666244507,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.6374,
|
|
"mean_token_accuracy": 0.10706623718142509,
|
|
"num_tokens": 1753334.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.530433320999146,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.5341,
|
|
"mean_token_accuracy": 0.10991563349962234,
|
|
"num_tokens": 1762032.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.689446020126343,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.544,
|
|
"mean_token_accuracy": 0.11081757172942161,
|
|
"num_tokens": 1770508.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.560748434066772,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.426,
|
|
"mean_token_accuracy": 0.11921553984284401,
|
|
"num_tokens": 1780167.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.652446746826172,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.6517,
|
|
"mean_token_accuracy": 0.10580526143312455,
|
|
"num_tokens": 1788809.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.66084303855896,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.11268438398838043,
|
|
"num_tokens": 1797445.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.660087299346924,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.5697,
|
|
"mean_token_accuracy": 0.11011887267231942,
|
|
"num_tokens": 1806488.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.649512672424317,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.6358,
|
|
"mean_token_accuracy": 0.11133731156587601,
|
|
"num_tokens": 1815692.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.6660400390625,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.5694,
|
|
"mean_token_accuracy": 0.11109899133443832,
|
|
"num_tokens": 1824599.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.704316091537476,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.7123,
|
|
"mean_token_accuracy": 0.10897875279188156,
|
|
"num_tokens": 1833411.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.60129189491272,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.5145,
|
|
"mean_token_accuracy": 0.10535632520914077,
|
|
"num_tokens": 1842177.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.544263887405395,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.4816,
|
|
"mean_token_accuracy": 0.11858308389782905,
|
|
"num_tokens": 1850176.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.632837915420533,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.5469,
|
|
"mean_token_accuracy": 0.10982977524399758,
|
|
"num_tokens": 1859464.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.580215501785278,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.4394,
|
|
"mean_token_accuracy": 0.11119021698832512,
|
|
"num_tokens": 1867733.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.4762852668762205,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.4287,
|
|
"mean_token_accuracy": 0.11978307366371155,
|
|
"num_tokens": 1876010.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.604893350601197,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.6016,
|
|
"mean_token_accuracy": 0.11037462204694748,
|
|
"num_tokens": 1884906.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.618666505813598,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.4995,
|
|
"mean_token_accuracy": 0.11649383753538131,
|
|
"num_tokens": 1893464.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.576593685150146,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.5487,
|
|
"mean_token_accuracy": 0.11343064531683922,
|
|
"num_tokens": 1902769.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.619402933120727,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.4742,
|
|
"mean_token_accuracy": 0.11150655373930932,
|
|
"num_tokens": 1911968.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.530769681930542,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.463,
|
|
"mean_token_accuracy": 0.11413491815328598,
|
|
"num_tokens": 1920063.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.437048149108887,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.4509,
|
|
"mean_token_accuracy": 0.11341893821954727,
|
|
"num_tokens": 1929192.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.676905298233033,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.644,
|
|
"mean_token_accuracy": 0.11029372960329056,
|
|
"num_tokens": 1939082.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.419079971313477,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.504,
|
|
"mean_token_accuracy": 0.11239467188715935,
|
|
"num_tokens": 1948313.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.685780143737793,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.4964,
|
|
"mean_token_accuracy": 0.11267818436026573,
|
|
"num_tokens": 1957035.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.490918064117432,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.484,
|
|
"mean_token_accuracy": 0.1103479541838169,
|
|
"num_tokens": 1966041.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.564761972427368,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.5039,
|
|
"mean_token_accuracy": 0.1088343806564808,
|
|
"num_tokens": 1975019.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.590786552429199,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.4347,
|
|
"mean_token_accuracy": 0.12605319619178773,
|
|
"num_tokens": 1982930.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.5897198677062985,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.5418,
|
|
"mean_token_accuracy": 0.11301586031913757,
|
|
"num_tokens": 1991888.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.486571311950684,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.4041,
|
|
"mean_token_accuracy": 0.11347272992134094,
|
|
"num_tokens": 2000202.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.517371654510498,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.4403,
|
|
"mean_token_accuracy": 0.11478241458535195,
|
|
"num_tokens": 2009281.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.524582719802856,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.4493,
|
|
"mean_token_accuracy": 0.11818324699997902,
|
|
"num_tokens": 2017806.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.5087179183959964,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.5419,
|
|
"mean_token_accuracy": 0.11332567036151886,
|
|
"num_tokens": 2027582.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.556246519088745,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.389,
|
|
"mean_token_accuracy": 0.11757862493395806,
|
|
"num_tokens": 2035427.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.627065515518188,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.5817,
|
|
"mean_token_accuracy": 0.11226092055439948,
|
|
"num_tokens": 2044603.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.501073837280273,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.4133,
|
|
"mean_token_accuracy": 0.11716802939772605,
|
|
"num_tokens": 2053272.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.524116849899292,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.4342,
|
|
"mean_token_accuracy": 0.11659721657633781,
|
|
"num_tokens": 2061677.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.492729616165161,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.4621,
|
|
"mean_token_accuracy": 0.11502088606357574,
|
|
"num_tokens": 2070282.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.6285412311553955,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.5401,
|
|
"mean_token_accuracy": 0.11611524373292922,
|
|
"num_tokens": 2078812.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.4900905132293705,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.432,
|
|
"mean_token_accuracy": 0.10967228636145591,
|
|
"num_tokens": 2087020.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.501610469818115,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.3804,
|
|
"mean_token_accuracy": 0.11955688148736954,
|
|
"num_tokens": 2095933.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.39524621963501,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.404,
|
|
"mean_token_accuracy": 0.11746799275279045,
|
|
"num_tokens": 2105218.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.402376556396485,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.3215,
|
|
"mean_token_accuracy": 0.12029565200209617,
|
|
"num_tokens": 2113808.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.5325843334198,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.4858,
|
|
"mean_token_accuracy": 0.11363726928830147,
|
|
"num_tokens": 2123014.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.529097700119019,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.4078,
|
|
"mean_token_accuracy": 0.12257340103387833,
|
|
"num_tokens": 2131840.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.576442623138428,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.5001,
|
|
"mean_token_accuracy": 0.11559791788458824,
|
|
"num_tokens": 2140467.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.446888017654419,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.4351,
|
|
"mean_token_accuracy": 0.12105798646807671,
|
|
"num_tokens": 2149282.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.533386898040772,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.4277,
|
|
"mean_token_accuracy": 0.11944963932037353,
|
|
"num_tokens": 2157781.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.454381942749023,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.4188,
|
|
"mean_token_accuracy": 0.11854116097092629,
|
|
"num_tokens": 2166482.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.428623056411743,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.4369,
|
|
"mean_token_accuracy": 0.11538697481155395,
|
|
"num_tokens": 2174559.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.477071905136109,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.3211,
|
|
"mean_token_accuracy": 0.12279326990246772,
|
|
"num_tokens": 2182374.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.449340200424194,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.4127,
|
|
"mean_token_accuracy": 0.12096217796206474,
|
|
"num_tokens": 2191427.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.572444152832031,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.4932,
|
|
"mean_token_accuracy": 0.11495474576950074,
|
|
"num_tokens": 2199698.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.452260112762451,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.3453,
|
|
"mean_token_accuracy": 0.12533242255449295,
|
|
"num_tokens": 2208519.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.402873182296753,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.3615,
|
|
"mean_token_accuracy": 0.12151595205068588,
|
|
"num_tokens": 2217453.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.4074461460113525,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.4644,
|
|
"mean_token_accuracy": 0.11735093221068382,
|
|
"num_tokens": 2225623.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.501673412322998,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.4157,
|
|
"mean_token_accuracy": 0.11887598559260368,
|
|
"num_tokens": 2234519.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.473206901550293,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.4207,
|
|
"mean_token_accuracy": 0.11706000119447708,
|
|
"num_tokens": 2242994.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.490306758880616,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.4227,
|
|
"mean_token_accuracy": 0.12089471891522408,
|
|
"num_tokens": 2251687.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.406135559082031,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.3499,
|
|
"mean_token_accuracy": 0.1211350217461586,
|
|
"num_tokens": 2260751.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.49813494682312,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.1254826083779335,
|
|
"num_tokens": 2269125.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.301623916625976,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.12722386717796325,
|
|
"num_tokens": 2277098.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.510185956954956,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.5162,
|
|
"mean_token_accuracy": 0.117816873639822,
|
|
"num_tokens": 2285953.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.437057304382324,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.4151,
|
|
"mean_token_accuracy": 0.12368793934583663,
|
|
"num_tokens": 2294487.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.528111314773559,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.4525,
|
|
"mean_token_accuracy": 0.11401506140828133,
|
|
"num_tokens": 2302915.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.398245716094971,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.4152,
|
|
"mean_token_accuracy": 0.11596530675888062,
|
|
"num_tokens": 2310769.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.374190855026245,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.2874,
|
|
"mean_token_accuracy": 0.11599803119897842,
|
|
"num_tokens": 2319987.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.437367486953735,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.4054,
|
|
"mean_token_accuracy": 0.1133360095322132,
|
|
"num_tokens": 2328964.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.47161374092102,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.3552,
|
|
"mean_token_accuracy": 0.11501636877655982,
|
|
"num_tokens": 2337945.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.456685209274292,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.2612,
|
|
"mean_token_accuracy": 0.11833763271570205,
|
|
"num_tokens": 2345989.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.304389333724975,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.3725,
|
|
"mean_token_accuracy": 0.12045516222715377,
|
|
"num_tokens": 2353752.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.450414657592773,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.3546,
|
|
"mean_token_accuracy": 0.11809542030096054,
|
|
"num_tokens": 2361961.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.352401399612427,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.2651,
|
|
"mean_token_accuracy": 0.12437428683042526,
|
|
"num_tokens": 2370148.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.429590368270874,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.125085686147213,
|
|
"num_tokens": 2379105.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.433341217041016,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.39,
|
|
"mean_token_accuracy": 0.12164573967456818,
|
|
"num_tokens": 2387417.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.49081072807312,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.4107,
|
|
"mean_token_accuracy": 0.12515631392598153,
|
|
"num_tokens": 2396163.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.248341655731201,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.2564,
|
|
"mean_token_accuracy": 0.12287922278046608,
|
|
"num_tokens": 2404661.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.356365108489991,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.3524,
|
|
"mean_token_accuracy": 0.11748461276292801,
|
|
"num_tokens": 2413459.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.453977441787719,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.3129,
|
|
"mean_token_accuracy": 0.12602921575307846,
|
|
"num_tokens": 2421401.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.392508220672608,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.3072,
|
|
"mean_token_accuracy": 0.12456106916069984,
|
|
"num_tokens": 2429983.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.474859046936035,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.4411,
|
|
"mean_token_accuracy": 0.11389126777648925,
|
|
"num_tokens": 2439206.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.379395532608032,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.3657,
|
|
"mean_token_accuracy": 0.12810833156108856,
|
|
"num_tokens": 2448801.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.400861072540283,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.4086,
|
|
"mean_token_accuracy": 0.12141750380396843,
|
|
"num_tokens": 2458007.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.39118766784668,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.3,
|
|
"mean_token_accuracy": 0.13179884999990463,
|
|
"num_tokens": 2466574.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.468687915802002,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.3711,
|
|
"mean_token_accuracy": 0.11950016170740127,
|
|
"num_tokens": 2475263.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.185061025619507,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.1305,
|
|
"mean_token_accuracy": 0.12724639102816582,
|
|
"num_tokens": 2483738.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.326748466491699,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.232,
|
|
"mean_token_accuracy": 0.11938041299581528,
|
|
"num_tokens": 2492937.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.304116439819336,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.11935702487826347,
|
|
"num_tokens": 2500716.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.360095405578614,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.11632756739854813,
|
|
"num_tokens": 2509385.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.516259574890137,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.3697,
|
|
"mean_token_accuracy": 0.11724613457918168,
|
|
"num_tokens": 2518179.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.297982025146484,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.33,
|
|
"mean_token_accuracy": 0.12113318666815757,
|
|
"num_tokens": 2526644.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.390083694458008,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.2294,
|
|
"mean_token_accuracy": 0.12677537202835082,
|
|
"num_tokens": 2534998.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.299189186096191,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.3009,
|
|
"mean_token_accuracy": 0.12109575122594833,
|
|
"num_tokens": 2543562.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.413508653640747,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.3233,
|
|
"mean_token_accuracy": 0.11768989339470863,
|
|
"num_tokens": 2551688.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.353024053573608,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.12517470344901085,
|
|
"num_tokens": 2560227.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.358402109146118,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.2573,
|
|
"mean_token_accuracy": 0.12913090363144875,
|
|
"num_tokens": 2569245.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.319776582717895,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.2771,
|
|
"mean_token_accuracy": 0.12657519578933715,
|
|
"num_tokens": 2577706.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.3895636081695555,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.12418374568223953,
|
|
"num_tokens": 2586075.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.328500509262085,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.3166,
|
|
"mean_token_accuracy": 0.11702506840229035,
|
|
"num_tokens": 2594965.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.343495893478393,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.2299,
|
|
"mean_token_accuracy": 0.12473512664437295,
|
|
"num_tokens": 2603355.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.428485584259033,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.3809,
|
|
"mean_token_accuracy": 0.11869822889566421,
|
|
"num_tokens": 2611697.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.2671410083770756,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.2445,
|
|
"mean_token_accuracy": 0.12823037803173065,
|
|
"num_tokens": 2620821.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.389608240127563,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.1255895458161831,
|
|
"num_tokens": 2628891.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.372634601593018,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.371,
|
|
"mean_token_accuracy": 0.12320602610707283,
|
|
"num_tokens": 2638641.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.3987085819244385,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.264,
|
|
"mean_token_accuracy": 0.12482255175709725,
|
|
"num_tokens": 2646898.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.377302169799805,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.3393,
|
|
"mean_token_accuracy": 0.11689784750342369,
|
|
"num_tokens": 2655404.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.296369886398315,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.1269844152033329,
|
|
"num_tokens": 2663851.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.27218918800354,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.2599,
|
|
"mean_token_accuracy": 0.124675901979208,
|
|
"num_tokens": 2672231.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.31765775680542,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.2452,
|
|
"mean_token_accuracy": 0.1260676108300686,
|
|
"num_tokens": 2680198.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.392157125473022,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.2862,
|
|
"mean_token_accuracy": 0.11980032101273537,
|
|
"num_tokens": 2689208.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.420441484451294,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.3474,
|
|
"mean_token_accuracy": 0.11860086098313331,
|
|
"num_tokens": 2698116.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.286598205566406,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.2261,
|
|
"mean_token_accuracy": 0.11801384165883064,
|
|
"num_tokens": 2707046.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.2947837829589846,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.238,
|
|
"mean_token_accuracy": 0.12088324874639511,
|
|
"num_tokens": 2714929.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.297727441787719,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.12293168380856515,
|
|
"num_tokens": 2723436.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.305335235595703,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.3148,
|
|
"mean_token_accuracy": 0.12060637921094894,
|
|
"num_tokens": 2731935.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.29901385307312,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.142,
|
|
"mean_token_accuracy": 0.13157675340771674,
|
|
"num_tokens": 2740307.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.158562135696411,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.1256,
|
|
"mean_token_accuracy": 0.1322464384138584,
|
|
"num_tokens": 2749077.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.349336957931518,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.2515,
|
|
"mean_token_accuracy": 0.12292205169796944,
|
|
"num_tokens": 2758133.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.304586410522461,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.183,
|
|
"mean_token_accuracy": 0.12989940419793128,
|
|
"num_tokens": 2766509.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.194839763641357,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.3616,
|
|
"mean_token_accuracy": 0.12518828511238098,
|
|
"num_tokens": 2775908.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.344752550125122,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.13455261215567588,
|
|
"num_tokens": 2784803.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.332213401794434,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.2889,
|
|
"mean_token_accuracy": 0.12206416502594948,
|
|
"num_tokens": 2793897.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.274225473403931,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.12973754331469536,
|
|
"num_tokens": 2802652.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.226436805725098,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.12090609893202782,
|
|
"num_tokens": 2811527.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.277534484863281,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.1338588200509548,
|
|
"num_tokens": 2819410.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.044222688674926,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.12,
|
|
"mean_token_accuracy": 0.13493081852793692,
|
|
"num_tokens": 2828079.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.299578428268433,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.2427,
|
|
"mean_token_accuracy": 0.1260551355779171,
|
|
"num_tokens": 2836326.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.397226285934448,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.28,
|
|
"mean_token_accuracy": 0.12439439222216606,
|
|
"num_tokens": 2845271.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.166529750823974,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.13345591425895692,
|
|
"num_tokens": 2853688.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.2988574504852295,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.2329,
|
|
"mean_token_accuracy": 0.13125427886843682,
|
|
"num_tokens": 2862261.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.290777921676636,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.12467502355575562,
|
|
"num_tokens": 2871324.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.363094997406006,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.3015,
|
|
"mean_token_accuracy": 0.11913043558597565,
|
|
"num_tokens": 2880268.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.2725090980529785,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.2154,
|
|
"mean_token_accuracy": 0.12513224706053733,
|
|
"num_tokens": 2888510.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.255806159973145,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.1155,
|
|
"mean_token_accuracy": 0.134560976177454,
|
|
"num_tokens": 2897616.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.2078857421875,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.2119,
|
|
"mean_token_accuracy": 0.13180608600378035,
|
|
"num_tokens": 2905703.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.257840871810913,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 6.0924,
|
|
"mean_token_accuracy": 0.13349219858646394,
|
|
"num_tokens": 2914881.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.152332448959351,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.1496,
|
|
"mean_token_accuracy": 0.12726475298404694,
|
|
"num_tokens": 2923563.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.314036417007446,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.3568,
|
|
"mean_token_accuracy": 0.12228120416402817,
|
|
"num_tokens": 2932821.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.361423540115356,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.2519,
|
|
"mean_token_accuracy": 0.12628840357065202,
|
|
"num_tokens": 2940926.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.251637029647827,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.12774975672364236,
|
|
"num_tokens": 2950028.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.2219006538391115,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.1321553736925125,
|
|
"num_tokens": 2957636.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.136737251281739,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 5.9691,
|
|
"mean_token_accuracy": 0.1330525793135166,
|
|
"num_tokens": 2966544.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.201963996887207,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.2068,
|
|
"mean_token_accuracy": 0.12606080621480942,
|
|
"num_tokens": 2976236.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.247957944869995,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.1593,
|
|
"mean_token_accuracy": 0.13033938258886338,
|
|
"num_tokens": 2984261.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.17896146774292,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.1346,
|
|
"mean_token_accuracy": 0.12553048729896546,
|
|
"num_tokens": 2992970.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.274186754226685,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.1571,
|
|
"mean_token_accuracy": 0.13733121678233146,
|
|
"num_tokens": 3001356.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.217675352096558,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.1756,
|
|
"mean_token_accuracy": 0.13170652091503143,
|
|
"num_tokens": 3009509.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.264265441894532,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 6.1947,
|
|
"mean_token_accuracy": 0.12841238230466842,
|
|
"num_tokens": 3017675.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.189158773422241,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.1458,
|
|
"mean_token_accuracy": 0.13517939075827598,
|
|
"num_tokens": 3025527.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.226872253417969,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.1199,
|
|
"mean_token_accuracy": 0.12841131687164306,
|
|
"num_tokens": 3034251.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.166691827774048,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.12151764705777168,
|
|
"num_tokens": 3043272.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.374958848953247,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.1882,
|
|
"mean_token_accuracy": 0.1262716494500637,
|
|
"num_tokens": 3051092.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.144443225860596,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 6.1727,
|
|
"mean_token_accuracy": 0.12414734214544296,
|
|
"num_tokens": 3060584.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.250931119918823,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.1511,
|
|
"mean_token_accuracy": 0.13213173300027847,
|
|
"num_tokens": 3069990.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.308782005310059,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 6.1321,
|
|
"mean_token_accuracy": 0.12601641267538072,
|
|
"num_tokens": 3078837.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.052882099151612,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.13299693092703818,
|
|
"num_tokens": 3087557.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.232021903991699,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.12982656732201575,
|
|
"num_tokens": 3096524.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.301290035247803,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 6.2168,
|
|
"mean_token_accuracy": 0.13102202489972115,
|
|
"num_tokens": 3105271.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.1726874828338625,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.12439190596342087,
|
|
"num_tokens": 3114479.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.19274673461914,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.13765334486961364,
|
|
"num_tokens": 3123319.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.169351577758789,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.1431,
|
|
"mean_token_accuracy": 0.1253248445689678,
|
|
"num_tokens": 3132532.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.320477867126465,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 6.2178,
|
|
"mean_token_accuracy": 0.12777107432484627,
|
|
"num_tokens": 3140798.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.137387990951538,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 6.1878,
|
|
"mean_token_accuracy": 0.13269276320934295,
|
|
"num_tokens": 3149607.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.1910168647766115,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.1368260033428669,
|
|
"num_tokens": 3157537.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.140592384338379,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.12532128095626832,
|
|
"num_tokens": 3166351.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.161713981628418,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 6.0296,
|
|
"mean_token_accuracy": 0.13651844039559363,
|
|
"num_tokens": 3174690.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.136564493179321,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.1637,
|
|
"mean_token_accuracy": 0.1232847586274147,
|
|
"num_tokens": 3183460.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.285676670074463,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 6.1164,
|
|
"mean_token_accuracy": 0.12833876982331277,
|
|
"num_tokens": 3192183.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.160711622238159,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.12972862496972085,
|
|
"num_tokens": 3200875.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.196098470687867,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 6.0473,
|
|
"mean_token_accuracy": 0.13408101424574853,
|
|
"num_tokens": 3209797.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.224760866165161,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.1883,
|
|
"mean_token_accuracy": 0.12606970742344856,
|
|
"num_tokens": 3218612.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.182671165466308,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 6.1049,
|
|
"mean_token_accuracy": 0.12787139862775804,
|
|
"num_tokens": 3227364.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.14884614944458,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 6.1123,
|
|
"mean_token_accuracy": 0.12965136021375656,
|
|
"num_tokens": 3236448.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.170213508605957,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 6.0578,
|
|
"mean_token_accuracy": 0.13230266496539117,
|
|
"num_tokens": 3244957.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.124844217300415,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 6.1312,
|
|
"mean_token_accuracy": 0.12952700182795523,
|
|
"num_tokens": 3253250.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.199846649169922,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 6.0482,
|
|
"mean_token_accuracy": 0.13997920900583266,
|
|
"num_tokens": 3261455.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.061277914047241,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 6.096,
|
|
"mean_token_accuracy": 0.13030619099736213,
|
|
"num_tokens": 3270108.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.309679841995239,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.13158586323261262,
|
|
"num_tokens": 3278425.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.191829681396484,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 6.1462,
|
|
"mean_token_accuracy": 0.12819165959954262,
|
|
"num_tokens": 3288358.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.18556809425354,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.12729835957288743,
|
|
"num_tokens": 3297199.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.178153467178345,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 6.1506,
|
|
"mean_token_accuracy": 0.12357342168688774,
|
|
"num_tokens": 3306350.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.1408665657043455,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.13374814838171006,
|
|
"num_tokens": 3314921.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.011826419830323,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.1307,
|
|
"mean_token_accuracy": 0.13305978029966353,
|
|
"num_tokens": 3323324.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.364898824691773,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.12814974039793015,
|
|
"num_tokens": 3331614.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.1918212890625,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.13158948644995688,
|
|
"num_tokens": 3339573.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.158113813400268,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.13647124394774438,
|
|
"num_tokens": 3347775.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.0896648406982425,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.13345661535859107,
|
|
"num_tokens": 3356947.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.188624572753906,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 6.116,
|
|
"mean_token_accuracy": 0.13309542015194892,
|
|
"num_tokens": 3365420.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.1624736309051515,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 6.2005,
|
|
"mean_token_accuracy": 0.128976671397686,
|
|
"num_tokens": 3373483.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.264059114456177,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 6.1881,
|
|
"mean_token_accuracy": 0.12472899630665779,
|
|
"num_tokens": 3382557.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.211884689331055,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 6.1242,
|
|
"mean_token_accuracy": 0.12660180181264877,
|
|
"num_tokens": 3392079.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.159574842453003,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.1291268937289715,
|
|
"num_tokens": 3401070.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.1600908756256105,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 6.0782,
|
|
"mean_token_accuracy": 0.1298006922006607,
|
|
"num_tokens": 3409921.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.146826696395874,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 6.1052,
|
|
"mean_token_accuracy": 0.12948946729302407,
|
|
"num_tokens": 3419149.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.094645309448242,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 5.9952,
|
|
"mean_token_accuracy": 0.13366427645087242,
|
|
"num_tokens": 3427435.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.211178398132324,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 6.1954,
|
|
"mean_token_accuracy": 0.12369204685091972,
|
|
"num_tokens": 3436377.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.176980257034302,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 6.0885,
|
|
"mean_token_accuracy": 0.13029382526874542,
|
|
"num_tokens": 3444997.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.191714239120484,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.13196599557995797,
|
|
"num_tokens": 3454254.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.185032701492309,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 6.0932,
|
|
"mean_token_accuracy": 0.13326400965452195,
|
|
"num_tokens": 3462853.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.061761045455933,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.12793660834431647,
|
|
"num_tokens": 3471288.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.056248712539673,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 5.9365,
|
|
"mean_token_accuracy": 0.13281023353338242,
|
|
"num_tokens": 3479479.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.097038793563843,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 5.9666,
|
|
"mean_token_accuracy": 0.13581353425979614,
|
|
"num_tokens": 3488621.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.058021783828735,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 6.0255,
|
|
"mean_token_accuracy": 0.13270611315965652,
|
|
"num_tokens": 3497792.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.070380449295044,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.1334388241171837,
|
|
"num_tokens": 3506548.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.062567090988159,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.1377915136516094,
|
|
"num_tokens": 3515086.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.19374680519104,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.12722084745764733,
|
|
"num_tokens": 3523985.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.161553239822387,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 6.1462,
|
|
"mean_token_accuracy": 0.13290010020136833,
|
|
"num_tokens": 3532575.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.14690637588501,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 6.1174,
|
|
"mean_token_accuracy": 0.13246945217251777,
|
|
"num_tokens": 3541558.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.174297761917114,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.1349615588784218,
|
|
"num_tokens": 3549697.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.183842468261719,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.12634108141064643,
|
|
"num_tokens": 3558673.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.201715040206909,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.1356561675667763,
|
|
"num_tokens": 3567176.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.166228723526001,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 6.1923,
|
|
"mean_token_accuracy": 0.1288422577083111,
|
|
"num_tokens": 3576020.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.133847093582153,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.13646728843450545,
|
|
"num_tokens": 3584705.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.148935461044312,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.12454503774642944,
|
|
"num_tokens": 3593339.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.174338722229004,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 5.9522,
|
|
"mean_token_accuracy": 0.14272483959794044,
|
|
"num_tokens": 3601206.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.9944499969482425,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.13079817742109298,
|
|
"num_tokens": 3610371.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.26822681427002,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 6.0661,
|
|
"mean_token_accuracy": 0.12999794706702233,
|
|
"num_tokens": 3618834.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.992048168182373,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 6.0897,
|
|
"mean_token_accuracy": 0.13502170965075494,
|
|
"num_tokens": 3627426.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.1902689933776855,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 6.11,
|
|
"mean_token_accuracy": 0.13337679505348204,
|
|
"num_tokens": 3636020.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.184276056289673,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 6.0313,
|
|
"mean_token_accuracy": 0.13348037749528885,
|
|
"num_tokens": 3644419.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.074879598617554,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 6.1447,
|
|
"mean_token_accuracy": 0.12506258115172386,
|
|
"num_tokens": 3653223.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.210933208465576,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.13025981783866883,
|
|
"num_tokens": 3662409.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.18992509841919,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 6.1217,
|
|
"mean_token_accuracy": 0.1288077488541603,
|
|
"num_tokens": 3670635.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.055357551574707,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 6.0277,
|
|
"mean_token_accuracy": 0.1416458807885647,
|
|
"num_tokens": 3679303.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.251597690582275,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.12960903346538544,
|
|
"num_tokens": 3689299.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.15298285484314,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 6.1215,
|
|
"mean_token_accuracy": 0.13158850744366646,
|
|
"num_tokens": 3697843.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.209942436218261,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 6.076,
|
|
"mean_token_accuracy": 0.1307775042951107,
|
|
"num_tokens": 3705876.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.12683482170105,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.12918348461389542,
|
|
"num_tokens": 3714835.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.12851095199585,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 6.0364,
|
|
"mean_token_accuracy": 0.13037344813346863,
|
|
"num_tokens": 3723421.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.1327372074127195,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 6.0615,
|
|
"mean_token_accuracy": 0.13242582008242607,
|
|
"num_tokens": 3731590.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.019791984558106,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 5.9754,
|
|
"mean_token_accuracy": 0.13794221505522727,
|
|
"num_tokens": 3740700.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.113742160797119,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 6.0592,
|
|
"mean_token_accuracy": 0.13774652481079103,
|
|
"num_tokens": 3749516.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.097338151931763,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.138454669713974,
|
|
"num_tokens": 3757696.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.080916881561279,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.1338729217648506,
|
|
"num_tokens": 3765786.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.08872880935669,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.13815502300858498,
|
|
"num_tokens": 3773265.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.091851711273193,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 6.0857,
|
|
"mean_token_accuracy": 0.12940960824489595,
|
|
"num_tokens": 3782402.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.111265754699707,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 6.1536,
|
|
"mean_token_accuracy": 0.12703027427196503,
|
|
"num_tokens": 3791901.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.167774677276611,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.1401320591568947,
|
|
"num_tokens": 3799872.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.025020885467529,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 5.9304,
|
|
"mean_token_accuracy": 0.14193431213498114,
|
|
"num_tokens": 3808949.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.096840572357178,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 6.046,
|
|
"mean_token_accuracy": 0.13580235317349434,
|
|
"num_tokens": 3817429.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.2811767101287845,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 6.3187,
|
|
"mean_token_accuracy": 0.12173992693424225,
|
|
"num_tokens": 3827101.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.186968183517456,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 6.064,
|
|
"mean_token_accuracy": 0.12950773164629936,
|
|
"num_tokens": 3836147.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.04772801399231,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.13448109477758408,
|
|
"num_tokens": 3845300.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.171705484390259,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.13789453059434892,
|
|
"num_tokens": 3853620.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.069169330596924,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 6.0595,
|
|
"mean_token_accuracy": 0.1349787399172783,
|
|
"num_tokens": 3861734.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.176798486709595,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 6.0786,
|
|
"mean_token_accuracy": 0.13317364156246186,
|
|
"num_tokens": 3870753.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.061793375015259,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.9548,
|
|
"mean_token_accuracy": 0.13736256137490271,
|
|
"num_tokens": 3879382.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.092678499221802,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 6.1108,
|
|
"mean_token_accuracy": 0.1346526972949505,
|
|
"num_tokens": 3888417.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.073836374282837,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 5.9869,
|
|
"mean_token_accuracy": 0.13438915610313415,
|
|
"num_tokens": 3897083.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.004721164703369,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 5.9588,
|
|
"mean_token_accuracy": 0.13743010833859443,
|
|
"num_tokens": 3905564.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.127100706100464,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.12591039165854453,
|
|
"num_tokens": 3914896.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.121838665008545,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 6.0954,
|
|
"mean_token_accuracy": 0.1338363006711006,
|
|
"num_tokens": 3924151.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.209240961074829,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 6.0515,
|
|
"mean_token_accuracy": 0.13761386051774024,
|
|
"num_tokens": 3933163.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.0434469223022464,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 5.97,
|
|
"mean_token_accuracy": 0.139447121322155,
|
|
"num_tokens": 3941120.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.9832147598266605,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.8716,
|
|
"mean_token_accuracy": 0.13407945334911348,
|
|
"num_tokens": 3949896.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.099995136260986,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.13756617158651352,
|
|
"num_tokens": 3958794.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.031581878662109,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 6.0827,
|
|
"mean_token_accuracy": 0.13277505114674568,
|
|
"num_tokens": 3967267.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.035991859436035,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 5.9947,
|
|
"mean_token_accuracy": 0.13988595828413963,
|
|
"num_tokens": 3976536.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.2207560539245605,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 6.0652,
|
|
"mean_token_accuracy": 0.13461703062057495,
|
|
"num_tokens": 3986006.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.9804434299469,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 6.0132,
|
|
"mean_token_accuracy": 0.129325582832098,
|
|
"num_tokens": 3994478.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.138697957992553,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.13380764052271843,
|
|
"num_tokens": 4003190.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.132336902618408,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.13556784838438035,
|
|
"num_tokens": 4011886.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.926994562149048,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 5.8736,
|
|
"mean_token_accuracy": 0.13585432842373849,
|
|
"num_tokens": 4020792.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.999753761291504,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 5.8524,
|
|
"mean_token_accuracy": 0.13412006422877312,
|
|
"num_tokens": 4029235.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.0219508647918705,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 6.0882,
|
|
"mean_token_accuracy": 0.13498658463358879,
|
|
"num_tokens": 4037341.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.037039661407471,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.1305742658674717,
|
|
"num_tokens": 4046324.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.062641859054565,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.13607652485370636,
|
|
"num_tokens": 4054579.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.14380373954773,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.9767,
|
|
"mean_token_accuracy": 0.13501785844564437,
|
|
"num_tokens": 4063087.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.033124876022339,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.1377527207136154,
|
|
"num_tokens": 4072309.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.117186975479126,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 6.1177,
|
|
"mean_token_accuracy": 0.13360145166516305,
|
|
"num_tokens": 4081017.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.075238609313965,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 6.1195,
|
|
"mean_token_accuracy": 0.12870020866394044,
|
|
"num_tokens": 4089799.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.079360723495483,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 6.0327,
|
|
"mean_token_accuracy": 0.1406281881034374,
|
|
"num_tokens": 4097948.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.1009117603302006,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 5.9017,
|
|
"mean_token_accuracy": 0.14306575134396554,
|
|
"num_tokens": 4107050.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.032208967208862,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 5.9622,
|
|
"mean_token_accuracy": 0.13016203418374062,
|
|
"num_tokens": 4115547.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.0398108005523685,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.13297787085175514,
|
|
"num_tokens": 4124047.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.943724346160889,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.8968,
|
|
"mean_token_accuracy": 0.145902356505394,
|
|
"num_tokens": 4132005.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.1200315952301025,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.1263026289641857,
|
|
"num_tokens": 4140199.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.068143510818482,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.13453146889805795,
|
|
"num_tokens": 4149353.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.977908182144165,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.9865,
|
|
"mean_token_accuracy": 0.13498907014727593,
|
|
"num_tokens": 4158531.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.940221500396729,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.7874,
|
|
"mean_token_accuracy": 0.14433993101119996,
|
|
"num_tokens": 4166743.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.098818731307984,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.13165030181407927,
|
|
"num_tokens": 4175416.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.116787719726562,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.13178250938653946,
|
|
"num_tokens": 4185324.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.0655097484588625,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 5.9928,
|
|
"mean_token_accuracy": 0.13624793738126756,
|
|
"num_tokens": 4193361.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.1048424243927,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.12900563478469848,
|
|
"num_tokens": 4202553.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.989557075500488,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.1428642563521862,
|
|
"num_tokens": 4211585.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.038365507125855,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 5.9981,
|
|
"mean_token_accuracy": 0.12849293798208236,
|
|
"num_tokens": 4220829.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.955444860458374,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.9165,
|
|
"mean_token_accuracy": 0.14009664207696915,
|
|
"num_tokens": 4228658.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.089463567733764,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 6.0069,
|
|
"mean_token_accuracy": 0.13533291295170785,
|
|
"num_tokens": 4237650.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.035800504684448,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.9774,
|
|
"mean_token_accuracy": 0.13687002435326576,
|
|
"num_tokens": 4246701.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.017635250091553,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.9504,
|
|
"mean_token_accuracy": 0.1353508435189724,
|
|
"num_tokens": 4254541.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.067923736572266,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.9673,
|
|
"mean_token_accuracy": 0.1318634532392025,
|
|
"num_tokens": 4263111.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.993190145492553,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.9944,
|
|
"mean_token_accuracy": 0.13662618547677993,
|
|
"num_tokens": 4272796.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.009687709808349,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.1403819091618061,
|
|
"num_tokens": 4281361.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.065948390960694,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 5.9727,
|
|
"mean_token_accuracy": 0.13534120246767997,
|
|
"num_tokens": 4290470.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.068803882598877,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 6.0308,
|
|
"mean_token_accuracy": 0.13365093022584915,
|
|
"num_tokens": 4299087.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.988065528869629,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.1456553541123867,
|
|
"num_tokens": 4307572.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.013512992858887,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.13854917660355567,
|
|
"num_tokens": 4316337.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.133624935150147,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.13632312491536142,
|
|
"num_tokens": 4326258.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.984883785247803,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.14192752689123153,
|
|
"num_tokens": 4334711.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.024339723587036,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.13177428618073464,
|
|
"num_tokens": 4343739.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.996756887435913,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 5.9476,
|
|
"mean_token_accuracy": 0.13979061022400857,
|
|
"num_tokens": 4352905.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.098079061508178,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.14360451996326445,
|
|
"num_tokens": 4361333.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.932000255584716,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.9141,
|
|
"mean_token_accuracy": 0.13802293092012405,
|
|
"num_tokens": 4369872.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.033679389953614,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.14147183522582055,
|
|
"num_tokens": 4378097.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.968611574172973,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.9189,
|
|
"mean_token_accuracy": 0.14388937279582023,
|
|
"num_tokens": 4387414.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.1040074825286865,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 6.0318,
|
|
"mean_token_accuracy": 0.14406417012214662,
|
|
"num_tokens": 4395922.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.995774126052856,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.13444236814975738,
|
|
"num_tokens": 4404500.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.907389211654663,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.1347421184182167,
|
|
"num_tokens": 4413433.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.097556447982788,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.14098930060863496,
|
|
"num_tokens": 4421789.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.943789005279541,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.8737,
|
|
"mean_token_accuracy": 0.14472436904907227,
|
|
"num_tokens": 4430256.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.98599910736084,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.9308,
|
|
"mean_token_accuracy": 0.1392303802073002,
|
|
"num_tokens": 4438431.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.054162168502808,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.13681029602885247,
|
|
"num_tokens": 4447150.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.967094993591308,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.8782,
|
|
"mean_token_accuracy": 0.14383712857961656,
|
|
"num_tokens": 4455181.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.973532247543335,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.13384012654423713,
|
|
"num_tokens": 4463361.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.9947929859161375,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.14294253960251807,
|
|
"num_tokens": 4471853.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.944393157958984,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 5.8836,
|
|
"mean_token_accuracy": 0.1416514605283737,
|
|
"num_tokens": 4480812.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.001008462905884,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.9292,
|
|
"mean_token_accuracy": 0.14392636716365814,
|
|
"num_tokens": 4489180.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.991946077346801,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.9977,
|
|
"mean_token_accuracy": 0.1375030979514122,
|
|
"num_tokens": 4498013.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.1099851608276365,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 6.0428,
|
|
"mean_token_accuracy": 0.12695643529295922,
|
|
"num_tokens": 4506767.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.122916030883789,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.13464597910642623,
|
|
"num_tokens": 4516657.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.863552236557007,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 5.8851,
|
|
"mean_token_accuracy": 0.14413899555802345,
|
|
"num_tokens": 4524980.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.983160829544067,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 5.9378,
|
|
"mean_token_accuracy": 0.140546715259552,
|
|
"num_tokens": 4533236.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.957806062698364,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.8374,
|
|
"mean_token_accuracy": 0.14236027672886847,
|
|
"num_tokens": 4541778.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.048499488830567,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.9587,
|
|
"mean_token_accuracy": 0.13639849424362183,
|
|
"num_tokens": 4551131.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.044900178909302,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.13491834998130797,
|
|
"num_tokens": 4559530.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.8130594253540036,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.8277,
|
|
"mean_token_accuracy": 0.14135022163391114,
|
|
"num_tokens": 4567533.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.064992189407349,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.978,
|
|
"mean_token_accuracy": 0.13598859161138535,
|
|
"num_tokens": 4576414.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.019899988174439,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.9119,
|
|
"mean_token_accuracy": 0.1416245199739933,
|
|
"num_tokens": 4585331.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.9772216796875,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.144110806286335,
|
|
"num_tokens": 4593526.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.955821752548218,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.1401088260114193,
|
|
"num_tokens": 4602400.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.917225313186646,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.14242400079965592,
|
|
"num_tokens": 4611037.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.003968095779419,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.13950355872511863,
|
|
"num_tokens": 4619030.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.95154185295105,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.8944,
|
|
"mean_token_accuracy": 0.13457175344228745,
|
|
"num_tokens": 4628649.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.90372486114502,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 5.7891,
|
|
"mean_token_accuracy": 0.14544083476066588,
|
|
"num_tokens": 4636935.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.975887823104858,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.9827,
|
|
"mean_token_accuracy": 0.13934769332408906,
|
|
"num_tokens": 4645532.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.0481304168701175,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 6.0577,
|
|
"mean_token_accuracy": 0.13306401297450066,
|
|
"num_tokens": 4654433.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.116953277587891,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.13022227212786674,
|
|
"num_tokens": 4662913.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.076945877075195,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.13053162321448325,
|
|
"num_tokens": 4672270.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.091213703155518,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.1330445796251297,
|
|
"num_tokens": 4681428.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.059315538406372,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.889,
|
|
"mean_token_accuracy": 0.14305261075496672,
|
|
"num_tokens": 4690492.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.9609434604644775,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.13601114600896835,
|
|
"num_tokens": 4699667.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.870917129516601,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.6888,
|
|
"mean_token_accuracy": 0.1551996573805809,
|
|
"num_tokens": 4708529.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.874881172180176,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.9372,
|
|
"mean_token_accuracy": 0.13897888511419296,
|
|
"num_tokens": 4717684.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.014762020111084,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.14865887761116028,
|
|
"num_tokens": 4727067.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.8886195659637455,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.8669,
|
|
"mean_token_accuracy": 0.14542917907238007,
|
|
"num_tokens": 4735434.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.017463541030883,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.14075807183980943,
|
|
"num_tokens": 4743843.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.023525381088257,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.9474,
|
|
"mean_token_accuracy": 0.13808054327964783,
|
|
"num_tokens": 4753228.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.975101375579834,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 6.0146,
|
|
"mean_token_accuracy": 0.13901024162769318,
|
|
"num_tokens": 4763401.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.985175466537475,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.13853829503059387,
|
|
"num_tokens": 4771812.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.947464084625244,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.14195793271064758,
|
|
"num_tokens": 4780616.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.950645589828492,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 5.9087,
|
|
"mean_token_accuracy": 0.13782943710684775,
|
|
"num_tokens": 4789886.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.94676365852356,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.8879,
|
|
"mean_token_accuracy": 0.14307310357689856,
|
|
"num_tokens": 4799189.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.99482946395874,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.9339,
|
|
"mean_token_accuracy": 0.14143783524632453,
|
|
"num_tokens": 4807850.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.996881151199341,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.8407,
|
|
"mean_token_accuracy": 0.14409077540040016,
|
|
"num_tokens": 4815742.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.928023815155029,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.9279,
|
|
"mean_token_accuracy": 0.14160390421748162,
|
|
"num_tokens": 4824761.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.08947377204895,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 6.0725,
|
|
"mean_token_accuracy": 0.1348046600818634,
|
|
"num_tokens": 4832805.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.996554565429688,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.14150556772947312,
|
|
"num_tokens": 4841938.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.940557479858398,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.1395154818892479,
|
|
"num_tokens": 4849932.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.892970848083496,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.8184,
|
|
"mean_token_accuracy": 0.1439179942011833,
|
|
"num_tokens": 4859054.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.062068367004395,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.9724,
|
|
"mean_token_accuracy": 0.1457817457616329,
|
|
"num_tokens": 4867415.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.05829119682312,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.9968,
|
|
"mean_token_accuracy": 0.1384667731821537,
|
|
"num_tokens": 4875965.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.974689674377442,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.1377502866089344,
|
|
"num_tokens": 4884629.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.95506272315979,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.9429,
|
|
"mean_token_accuracy": 0.1401269853115082,
|
|
"num_tokens": 4893573.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.953045749664307,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.8819,
|
|
"mean_token_accuracy": 0.1408964700996876,
|
|
"num_tokens": 4902831.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.035543966293335,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.9353,
|
|
"mean_token_accuracy": 0.1345332682132721,
|
|
"num_tokens": 4911360.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.9824096202850345,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.8991,
|
|
"mean_token_accuracy": 0.14080488830804824,
|
|
"num_tokens": 4919758.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.828854990005493,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.14767343401908875,
|
|
"num_tokens": 4928934.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.861857986450195,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.8351,
|
|
"mean_token_accuracy": 0.14466070234775544,
|
|
"num_tokens": 4937780.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.097094631195068,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.13491297960281373,
|
|
"num_tokens": 4946862.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.935989952087402,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.9189,
|
|
"mean_token_accuracy": 0.1431422159075737,
|
|
"num_tokens": 4954883.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.854018354415894,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.7182,
|
|
"mean_token_accuracy": 0.1529537945985794,
|
|
"num_tokens": 4962840.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.892796182632447,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.14130814969539643,
|
|
"num_tokens": 4972334.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.061372137069702,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.916,
|
|
"mean_token_accuracy": 0.14689642414450646,
|
|
"num_tokens": 4981032.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.977332258224488,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.9364,
|
|
"mean_token_accuracy": 0.136233139783144,
|
|
"num_tokens": 4990502.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.0572460174560545,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.13143445029854775,
|
|
"num_tokens": 4999121.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.014243221282959,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.8681,
|
|
"mean_token_accuracy": 0.14159790500998498,
|
|
"num_tokens": 5007271.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.872592258453369,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.9069,
|
|
"mean_token_accuracy": 0.1393379971385002,
|
|
"num_tokens": 5015940.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.897215223312378,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.8309,
|
|
"mean_token_accuracy": 0.14309723377227784,
|
|
"num_tokens": 5024294.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.909600305557251,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.1465318411588669,
|
|
"num_tokens": 5033401.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.946053552627563,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.8857,
|
|
"mean_token_accuracy": 0.14171253219246865,
|
|
"num_tokens": 5041955.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.011700201034546,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.13371872827410697,
|
|
"num_tokens": 5051132.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.881177234649658,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.8391,
|
|
"mean_token_accuracy": 0.15032089352607728,
|
|
"num_tokens": 5059492.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.902948617935181,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.14851512461900712,
|
|
"num_tokens": 5069015.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.968337202072144,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.1448035165667534,
|
|
"num_tokens": 5077614.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.878965139389038,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.14750696420669557,
|
|
"num_tokens": 5086300.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.818942022323609,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.14237508922815323,
|
|
"num_tokens": 5095967.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.032419204711914,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.14276775270700454,
|
|
"num_tokens": 5104611.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.827592563629151,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.7944,
|
|
"mean_token_accuracy": 0.1462033912539482,
|
|
"num_tokens": 5113452.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.833715486526489,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.1478416822850704,
|
|
"num_tokens": 5121558.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.861429166793823,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.1565452352166176,
|
|
"num_tokens": 5129942.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.958620166778564,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.13326751589775085,
|
|
"num_tokens": 5139012.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.977751779556274,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.891,
|
|
"mean_token_accuracy": 0.1418101616203785,
|
|
"num_tokens": 5148185.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.962037992477417,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.13784476593136788,
|
|
"num_tokens": 5157086.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.051717805862427,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.9769,
|
|
"mean_token_accuracy": 0.13798867762088776,
|
|
"num_tokens": 5165842.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.972775411605835,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.986,
|
|
"mean_token_accuracy": 0.13841650187969207,
|
|
"num_tokens": 5174161.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.012486743927002,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.9191,
|
|
"mean_token_accuracy": 0.13878133594989778,
|
|
"num_tokens": 5183830.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.924656009674072,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.8498,
|
|
"mean_token_accuracy": 0.13782228529453278,
|
|
"num_tokens": 5192248.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.876343250274658,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.8061,
|
|
"mean_token_accuracy": 0.1474793091416359,
|
|
"num_tokens": 5201212.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.893640851974487,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.14440894722938538,
|
|
"num_tokens": 5209338.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.071593999862671,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.13977692127227784,
|
|
"num_tokens": 5217590.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.784550465518632,
|
|
"eval_loss": 5.93321418762207,
|
|
"eval_mean_token_accuracy": 0.1467212013470025,
|
|
"eval_num_tokens": 5217590.0,
|
|
"eval_runtime": 28.6214,
|
|
"eval_samples_per_second": 1451.991,
|
|
"eval_steps_per_second": 181.508,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 128520,
|
|
"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": 7083226884096000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|