| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010036130068245684, | |
| "eval_steps": 500, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026763013515321826, | |
| "grad_norm": 37.0520133972168, | |
| "learning_rate": 1.546666666666667e-05, | |
| "loss": 1.5145, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005352602703064365, | |
| "grad_norm": 33.826324462890625, | |
| "learning_rate": 1.0133333333333335e-05, | |
| "loss": 1.2751, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008028904054596548, | |
| "grad_norm": 20.118314743041992, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.063, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010036130068245684, | |
| "step": 75, | |
| "total_flos": 7474249728.0, | |
| "train_loss": 1.2168165969848632, | |
| "train_runtime": 570.3408, | |
| "train_samples_per_second": 0.131, | |
| "train_steps_per_second": 0.132 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7474249728.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |