| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.32323232323232326, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9457994579945803e-05, | |
| "loss": 4.3763, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.878048780487805e-05, | |
| "loss": 3.8394, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.81029810298103e-05, | |
| "loss": 3.639, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7425474254742554e-05, | |
| "loss": 3.7962, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6747967479674795e-05, | |
| "loss": 3.5152, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.607046070460705e-05, | |
| "loss": 3.5752, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.53929539295393e-05, | |
| "loss": 3.4463, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.4715447154471546e-05, | |
| "loss": 3.5218, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 3.2419066429138184, | |
| "eval_rouge2_fmeasure": 0.0, | |
| "eval_rouge2_precision": 0.0, | |
| "eval_rouge2_recall": 0.0, | |
| "eval_runtime": 180.4791, | |
| "eval_samples_per_second": 0.15, | |
| "eval_steps_per_second": 0.078, | |
| "step": 40 | |
| } | |
| ], | |
| "max_steps": 369, | |
| "num_train_epochs": 3, | |
| "total_flos": 1560901173903360.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |