| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.977777777777778, | |
| "eval_steps": 500, | |
| "global_step": 66, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.282157301902771, | |
| "learning_rate": 4.985837000525343e-05, | |
| "loss": 1.4149, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.36413487792015076, | |
| "learning_rate": 4.5067790948274094e-05, | |
| "loss": 0.8009, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3555555555555556, | |
| "grad_norm": 0.14728936553001404, | |
| "learning_rate": 3.472060438683302e-05, | |
| "loss": 0.7536, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.1090896874666214, | |
| "learning_rate": 2.1681861817906954e-05, | |
| "loss": 0.6814, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.2666666666666666, | |
| "grad_norm": 0.11192808300256729, | |
| "learning_rate": 9.561884626345205e-06, | |
| "loss": 0.7443, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.7111111111111112, | |
| "grad_norm": 0.1410437375307083, | |
| "learning_rate": 1.7165955636915392e-06, | |
| "loss": 0.6739, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 66, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2711448844435456e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |