| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0221606648199446, | |
| "eval_steps": 2, | |
| "global_step": 2, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0110803324099723, | |
| "grad_norm": 3.4939091205596924, | |
| "learning_rate": 1e-05, | |
| "loss": 14.8747, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0110803324099723, | |
| "eval_loss": 0.9917307496070862, | |
| "eval_runtime": 54.4985, | |
| "eval_samples_per_second": 2.807, | |
| "eval_steps_per_second": 1.413, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0221606648199446, | |
| "grad_norm": 4.172488689422607, | |
| "learning_rate": 2e-05, | |
| "loss": 15.211, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0221606648199446, | |
| "eval_loss": NaN, | |
| "eval_runtime": 26.1998, | |
| "eval_samples_per_second": 5.84, | |
| "eval_steps_per_second": 2.939, | |
| "step": 2 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1628733135912960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |