| { | |
| "epoch": 3.0, | |
| "human_eval_gen_len": 54.49603174603175, | |
| "human_eval_loss": NaN, | |
| "human_eval_rouge1": 26.8457, | |
| "human_eval_rouge2": 10.0254, | |
| "human_eval_rougeL": 23.075, | |
| "human_eval_rougeLsum": 25.3872, | |
| "human_eval_runtime": 1415.9889, | |
| "human_eval_samples": 252, | |
| "human_eval_samples_per_second": 0.178, | |
| "human_eval_steps_per_second": 0.023, | |
| "seen_eval_gen_len": 19.877, | |
| "seen_eval_loss": 0.6744544506072998, | |
| "seen_eval_rouge1": 56.8816, | |
| "seen_eval_rouge2": 33.1435, | |
| "seen_eval_rougeL": 55.5207, | |
| "seen_eval_rougeLsum": 55.9899, | |
| "seen_eval_runtime": 2573.0236, | |
| "seen_eval_samples": 1000, | |
| "seen_eval_samples_per_second": 0.389, | |
| "seen_eval_steps_per_second": 0.049, | |
| "train_loss": 0.5916195661747989, | |
| "train_runtime": 62605.4207, | |
| "train_samples": 128069, | |
| "train_samples_per_second": 6.137, | |
| "train_steps_per_second": 0.096, | |
| "unseen_eval_gen_len": 30.877, | |
| "unseen_eval_loss": 1.2411748170852661, | |
| "unseen_eval_rouge1": 50.6339, | |
| "unseen_eval_rouge2": 28.312, | |
| "unseen_eval_rougeL": 45.2223, | |
| "unseen_eval_rougeLsum": 47.6022, | |
| "unseen_eval_runtime": 3845.938, | |
| "unseen_eval_samples": 1000, | |
| "unseen_eval_samples_per_second": 0.26, | |
| "unseen_eval_steps_per_second": 0.033 | |
| } |