| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.6, | |
| "eval_steps": 1, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.9725093245506287, | |
| "eval_runtime": 0.0731, | |
| "eval_samples_per_second": 54.712, | |
| "eval_steps_per_second": 13.678, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.9742918610572815, | |
| "eval_runtime": 0.0723, | |
| "eval_samples_per_second": 55.293, | |
| "eval_steps_per_second": 13.823, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.8758761286735535, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3054, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.9725667834281921, | |
| "eval_runtime": 0.0761, | |
| "eval_samples_per_second": 52.532, | |
| "eval_steps_per_second": 13.133, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.9695970416069031, | |
| "eval_runtime": 0.0727, | |
| "eval_samples_per_second": 55.054, | |
| "eval_steps_per_second": 13.764, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 8, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 540715725619200.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |