| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 17055, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4752, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_gen_len": 34.6, | |
| "eval_loss": 0.53515625, | |
| "eval_rouge1": 18.7991, | |
| "eval_rouge2": 11.6667, | |
| "eval_rougeL": 18.5494, | |
| "eval_rougeLsum": 18.6653, | |
| "eval_runtime": 2021.8236, | |
| "eval_samples_per_second": 1.688, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2688, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_gen_len": 33.6, | |
| "eval_loss": 0.61572265625, | |
| "eval_rouge1": 20.5977, | |
| "eval_rouge2": 12.9504, | |
| "eval_rougeL": 20.3605, | |
| "eval_rougeLsum": 20.4447, | |
| "eval_runtime": 1913.6134, | |
| "eval_samples_per_second": 1.784, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1309, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_gen_len": 33.2, | |
| "eval_loss": 0.89453125, | |
| "eval_rouge1": 21.4721, | |
| "eval_rouge2": 13.2325, | |
| "eval_rougeL": 21.2104, | |
| "eval_rougeLsum": 21.2775, | |
| "eval_runtime": 1900.2716, | |
| "eval_samples_per_second": 1.796, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 17055, | |
| "total_flos": 1.095854652102017e+18, | |
| "train_runtime": 101377.3904, | |
| "train_samples_per_second": 0.168 | |
| } | |
| ], | |
| "max_steps": 17055, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.095854652102017e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |