| { | |
| "best_metric": 25.4939, | |
| "best_model_checkpoint": "my-model/checkpoint-1528", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1528, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32722513089005234, | |
| "grad_norm": 1.691941261291504, | |
| "learning_rate": 4.181937172774869e-05, | |
| "loss": 0.0156, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6544502617801047, | |
| "grad_norm": 2.3052828311920166, | |
| "learning_rate": 3.3638743455497386e-05, | |
| "loss": 0.0188, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.981675392670157, | |
| "grad_norm": 1.2767335176467896, | |
| "learning_rate": 2.545811518324607e-05, | |
| "loss": 0.019, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 5.557580471038818, | |
| "eval_rouge1": 25.4939, | |
| "eval_rouge2": 10.2057, | |
| "eval_rougeL": 22.1893, | |
| "eval_runtime": 394.3343, | |
| "eval_samples_per_second": 5.566, | |
| "eval_steps_per_second": 0.558, | |
| "step": 1528 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3056, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7327420304523264.0, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |