| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 16875, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.90167244633686e-05, | |
| "loss": 1.8507, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 118.742, | |
| "eval_loss": 1.7119792699813843, | |
| "eval_rouge1": 43.9318, | |
| "eval_rouge2": 20.5803, | |
| "eval_rougeL": 29.8807, | |
| "eval_rougeLsum": 29.8748, | |
| "eval_runtime": 8010.5572, | |
| "eval_samples_per_second": 2.497, | |
| "eval_steps_per_second": 2.497, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.914182871691323e-05, | |
| "loss": 1.7161, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 110.7688, | |
| "eval_loss": 1.6913355588912964, | |
| "eval_rouge1": 43.936, | |
| "eval_rouge2": 20.632, | |
| "eval_rougeL": 30.1181, | |
| "eval_rougeLsum": 30.1042, | |
| "eval_runtime": 7456.3007, | |
| "eval_samples_per_second": 2.682, | |
| "eval_steps_per_second": 2.682, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 5.92686888196304e-05, | |
| "loss": 1.6018, | |
| "step": 16875 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 114.912, | |
| "eval_loss": 1.6871464252471924, | |
| "eval_rouge1": 44.5277, | |
| "eval_rouge2": 21.0646, | |
| "eval_rougeL": 30.3498, | |
| "eval_rougeLsum": 30.3357, | |
| "eval_runtime": 7764.9424, | |
| "eval_samples_per_second": 2.576, | |
| "eval_steps_per_second": 2.576, | |
| "step": 16875 | |
| } | |
| ], | |
| "max_steps": 50625, | |
| "num_train_epochs": 9, | |
| "total_flos": 1.5024380365403136e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |