| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1182, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 55.2449, | |
| "eval_loss": 0.9376491904258728, | |
| "eval_rouge1": 36.8596, | |
| "eval_rouge2": 20.4255, | |
| "eval_rougeL": 32.1955, | |
| "eval_rougeLsum": 32.0657, | |
| "eval_runtime": 125.0869, | |
| "eval_samples_per_second": 0.783, | |
| "eval_steps_per_second": 0.783, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 1.2690355329949239, | |
| "grad_norm": 6.749200344085693, | |
| "learning_rate": 1.160744500846024e-05, | |
| "loss": 1.0847, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 55.3367, | |
| "eval_loss": 0.9212109446525574, | |
| "eval_rouge1": 36.498, | |
| "eval_rouge2": 21.1133, | |
| "eval_rougeL": 30.8696, | |
| "eval_rougeLsum": 30.79, | |
| "eval_runtime": 126.0936, | |
| "eval_samples_per_second": 0.777, | |
| "eval_steps_per_second": 0.777, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 2.5380710659898478, | |
| "grad_norm": 6.482083320617676, | |
| "learning_rate": 3.1472081218274113e-06, | |
| "loss": 0.5957, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1182, | |
| "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": 5123035279392768.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |