|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.27654867256637167, |
|
"eval_steps": 500, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.1049723756906078e-06, |
|
"loss": 1.1037, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 5.524861878453038e-06, |
|
"loss": 1.3919, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.1049723756906077e-05, |
|
"loss": 1.2966, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.6574585635359117e-05, |
|
"loss": 1.2584, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 2.2099447513812153e-05, |
|
"loss": 1.4187, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 2.7624309392265197e-05, |
|
"loss": 1.311, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 3.3149171270718233e-05, |
|
"loss": 1.2543, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 3.867403314917128e-05, |
|
"loss": 1.2731, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.419889502762431e-05, |
|
"loss": 1.3057, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.972375690607735e-05, |
|
"loss": 1.1688, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 5.5248618784530394e-05, |
|
"loss": 1.0797, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 6.077348066298343e-05, |
|
"loss": 1.2013, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 6.629834254143647e-05, |
|
"loss": 1.2202, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 7.182320441988951e-05, |
|
"loss": 1.202, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 7.734806629834255e-05, |
|
"loss": 1.1622, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 8.287292817679558e-05, |
|
"loss": 1.1161, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 8.839779005524861e-05, |
|
"loss": 1.1511, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.392265193370167e-05, |
|
"loss": 1.0876, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.94475138121547e-05, |
|
"loss": 1.0691, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00010497237569060774, |
|
"loss": 1.1271, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00011049723756906079, |
|
"loss": 1.1469, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0001160220994475138, |
|
"loss": 1.0098, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00012154696132596686, |
|
"loss": 1.0495, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00012707182320441992, |
|
"loss": 1.1562, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00013259668508287293, |
|
"loss": 1.1193, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00013812154696132598, |
|
"loss": 1.1665, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00014364640883977902, |
|
"loss": 1.0206, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00014917127071823204, |
|
"loss": 0.9299, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0001546961325966851, |
|
"loss": 1.0058, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00016022099447513812, |
|
"loss": 0.9774, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00016574585635359117, |
|
"loss": 1.1074, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0001712707182320442, |
|
"loss": 0.909, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00017679558011049723, |
|
"loss": 0.8917, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0001823204419889503, |
|
"loss": 0.9895, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00018784530386740334, |
|
"loss": 0.9645, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00019337016574585636, |
|
"loss": 1.0363, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0001988950276243094, |
|
"loss": 0.9327, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00019999701728012887, |
|
"loss": 0.978, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0001999849002856042, |
|
"loss": 0.9193, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00019996346372498712, |
|
"loss": 1.052, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00019993270959637368, |
|
"loss": 0.9958, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00019989264076634812, |
|
"loss": 0.9828, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019984326096971551, |
|
"loss": 0.9844, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0001997845748091536, |
|
"loss": 0.9933, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019971658775478385, |
|
"loss": 0.9467, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019963930614366163, |
|
"loss": 0.9933, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00019955273717918548, |
|
"loss": 1.0004, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00019945688893042562, |
|
"loss": 0.952, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.000199351770331372, |
|
"loss": 0.9518, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00019923739118010142, |
|
"loss": 0.8675, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00019911376213786421, |
|
"loss": 0.8663, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00019898089472809077, |
|
"loss": 0.9652, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00019883880133531715, |
|
"loss": 1.0145, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00019868749520403093, |
|
"loss": 0.8834, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00019852699043743647, |
|
"loss": 0.9509, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00019835730199614066, |
|
"loss": 0.9722, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0001981784456967582, |
|
"loss": 0.8833, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00019799043821043739, |
|
"loss": 0.9029, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00019779329706130628, |
|
"loss": 1.0654, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0001975870406248392, |
|
"loss": 0.9963, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.000197371688126144, |
|
"loss": 1.0004, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0001971472596381701, |
|
"loss": 0.9371, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00019691377607983744, |
|
"loss": 1.0174, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.00019667125921408673, |
|
"loss": 1.0247, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0001964197316458508, |
|
"loss": 0.9945, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00019615921681994774, |
|
"loss": 0.9919, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.00019588973901889548, |
|
"loss": 0.9358, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00019561132336064864, |
|
"loss": 1.0385, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00019532399579625688, |
|
"loss": 0.9538, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00019502778310744655, |
|
"loss": 0.9048, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.00019472271290412396, |
|
"loss": 0.9912, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019440881362180198, |
|
"loss": 1.0602, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019408611451894966, |
|
"loss": 0.8916, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019375464567426492, |
|
"loss": 0.906, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0001934144379838711, |
|
"loss": 0.9104, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00019306552315843698, |
|
"loss": 0.9208, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00019270793372022104, |
|
"loss": 1.0013, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00019234170300004021, |
|
"loss": 0.9522, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.000191966865134163, |
|
"loss": 0.937, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00019158345506112764, |
|
"loss": 1.0136, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00019119150851848557, |
|
"loss": 0.9248, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00019079106203947032, |
|
"loss": 0.8795, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00019038215294959218, |
|
"loss": 1.0681, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00018996481936315923, |
|
"loss": 1.072, |
|
"step": 415 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00018953910017972456, |
|
"loss": 0.999, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00018910503508046058, |
|
"loss": 1.0072, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00018866266452446036, |
|
"loss": 1.0921, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0001882120297449663, |
|
"loss": 0.9897, |
|
"step": 435 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00018775317274552692, |
|
"loss": 0.9681, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00018728613629608173, |
|
"loss": 0.9956, |
|
"step": 445 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00018681096392897457, |
|
"loss": 0.987, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00018632769993489595, |
|
"loss": 0.8797, |
|
"step": 455 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00018583638935875491, |
|
"loss": 0.9693, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.0001853370779954802, |
|
"loss": 1.0626, |
|
"step": 465 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00018482981238575187, |
|
"loss": 1.059, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.00018431463981166308, |
|
"loss": 1.0953, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00018379160829231316, |
|
"loss": 1.0301, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00018326076657933156, |
|
"loss": 1.0673, |
|
"step": 485 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0001827221641523339, |
|
"loss": 1.0703, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00018217585121430973, |
|
"loss": 1.0311, |
|
"step": 495 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00018162187868694355, |
|
"loss": 1.0688, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 1808, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"total_flos": 3.17389493239808e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|