| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 50.0, | |
| "global_step": 59, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 14.407925737264305, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.8838487863540649, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 2.35870387379783, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.7208460569381714, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 1.439498142463802, | |
| "learning_rate": 1.972022914080411e-05, | |
| "loss": 0.4741680145263672, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 0.9460031668600737, | |
| "learning_rate": 1.8610436117673557e-05, | |
| "loss": 0.4118507385253906, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.9009799887435224, | |
| "learning_rate": 1.6749830015182106e-05, | |
| "loss": 0.40839252471923826, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42735042735042733, | |
| "grad_norm": 0.8943238789195507, | |
| "learning_rate": 1.4300652022765207e-05, | |
| "loss": 0.3522554874420166, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 0.8778590752855872, | |
| "learning_rate": 1.1476465640024814e-05, | |
| "loss": 0.33121280670166015, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5982905982905983, | |
| "grad_norm": 0.7649988422695874, | |
| "learning_rate": 8.52353435997519e-06, | |
| "loss": 0.3183881759643555, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.8367576325012144, | |
| "learning_rate": 5.699347977234799e-06, | |
| "loss": 0.31059505939483645, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.8182783819328651, | |
| "learning_rate": 3.250169984817897e-06, | |
| "loss": 0.31551196575164797, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 0.7554036810396093, | |
| "learning_rate": 1.3895638823264447e-06, | |
| "loss": 0.3017631769180298, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9401709401709402, | |
| "grad_norm": 0.8070523190062113, | |
| "learning_rate": 2.7977085919589253e-07, | |
| "loss": 0.2991445779800415, | |
| "step": 55 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 59, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 285666279424000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |