| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001505253334136135, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0105066682722702e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.0105066682722702e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 766.2942, | |
| "eval_samples_per_second": 18.253, | |
| "eval_steps_per_second": 9.127, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.0210133365445404e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.031520004816811e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012042026673089081, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00015052533341361352, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018063040009633623, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002107354667790589, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00024084053346178162, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002709456001445043, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00030105066682722703, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00033115573350994974, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00036126080019267245, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003913658668753951, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0003913658668753951, | |
| "eval_loss": NaN, | |
| "eval_runtime": 764.7494, | |
| "eval_samples_per_second": 18.29, | |
| "eval_steps_per_second": 9.145, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0004214709335581178, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0004515760002408405, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00048168106692356323, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005117861336062859, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0005418912002890087, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005719962669717314, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006021013336544541, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006322064003371768, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0006623114670198995, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0006924165337026222, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0007225216003853449, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007526266670680675, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0007827317337507902, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0007827317337507902, | |
| "eval_loss": NaN, | |
| "eval_runtime": 764.8818, | |
| "eval_samples_per_second": 18.286, | |
| "eval_steps_per_second": 9.144, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0008128368004335129, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0008429418671162356, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0008730469337989583, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.000903152000481681, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009332570671644038, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0009633621338471265, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.000993467200529849, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0010235722672125719, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0010536773338952945, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0010837824005780173, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00111388746726074, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0011439925339434627, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0011740976006261853, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0011740976006261853, | |
| "eval_loss": NaN, | |
| "eval_runtime": 765.0262, | |
| "eval_samples_per_second": 18.283, | |
| "eval_steps_per_second": 9.142, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0012042026673089081, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0012343077339916307, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.989850859999227e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0012644128006743536, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0012945178673570762, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.001324622934039799, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7248368952908053e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0013547280007225216, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0013848330674052444, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2235870926211619e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.001414938134087967, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.907519900580861e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0014450432007706898, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0014751482674534124, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.706665667180091e-08, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.001505253334136135, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7220000427278336e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |