| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 12585, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.1918951132300357, | |
| "grad_norm": 0.8493185043334961, | |
| "learning_rate": 0.00019872148733408694, | |
| "loss": 0.5421, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3837902264600714, | |
| "grad_norm": 0.4860774874687195, | |
| "learning_rate": 0.00019141307038722188, | |
| "loss": 0.2042, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.575685339690107, | |
| "grad_norm": 1.4351465702056885, | |
| "learning_rate": 0.00017808333307050135, | |
| "loss": 0.1613, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.767580452920143, | |
| "grad_norm": 0.7845919728279114, | |
| "learning_rate": 0.00015961029663941979, | |
| "loss": 0.1339, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.959475566150179, | |
| "grad_norm": 0.16761158406734467, | |
| "learning_rate": 0.00013721076816636165, | |
| "loss": 0.1194, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.151370679380214, | |
| "grad_norm": 0.18906846642494202, | |
| "learning_rate": 0.00011236019023846099, | |
| "loss": 0.1014, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 8.34326579261025, | |
| "grad_norm": 0.3582542836666107, | |
| "learning_rate": 8.669545449983509e-05, | |
| "loss": 0.0894, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 9.535160905840286, | |
| "grad_norm": 1.641005277633667, | |
| "learning_rate": 6.190708064788978e-05, | |
| "loss": 0.0815, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 10.727056019070321, | |
| "grad_norm": 0.1235262081027031, | |
| "learning_rate": 3.962786298411891e-05, | |
| "loss": 0.0732, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 11.918951132300357, | |
| "grad_norm": 0.12703625857830048, | |
| "learning_rate": 2.132531929974263e-05, | |
| "loss": 0.0674, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 13.110846245530393, | |
| "grad_norm": 0.35737335681915283, | |
| "learning_rate": 8.20502641916997e-06, | |
| "loss": 0.0645, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 14.302741358760429, | |
| "grad_norm": 0.10338258743286133, | |
| "learning_rate": 1.1312096270961526e-06, | |
| "loss": 0.0623, | |
| "step": 12000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 12585, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0572731031172128e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |