| { | |
| "epoch": 0.9999754305791012, | |
| "eval_gen_len": 30.24, | |
| "eval_loss": 2.2113382816314697, | |
| "eval_rouge1": 48.6654, | |
| "eval_rouge2": 31.8667, | |
| "eval_rougeL": 44.9897, | |
| "eval_rougeLsum": 45.4126, | |
| "eval_runtime": 91.256, | |
| "eval_samples": 200, | |
| "eval_samples_per_second": 2.192, | |
| "eval_steps_per_second": 0.548, | |
| "num_input_tokens_seen": 524625736, | |
| "predict_gen_len": 64.26315789473684, | |
| "predict_loss": 5.781242370605469, | |
| "predict_rouge1": 12.9534, | |
| "predict_rouge2": 2.8458, | |
| "predict_rougeL": 9.9173, | |
| "predict_rougeLsum": 11.9501, | |
| "predict_runtime": 36.282, | |
| "predict_samples": 19, | |
| "predict_samples_per_second": 0.524, | |
| "predict_steps_per_second": 0.138, | |
| "total_flos": 1.8734435060870185e+18, | |
| "train_loss": 51.37127453965696, | |
| "train_runtime": 54286.9149, | |
| "train_samples": 651215, | |
| "train_samples_per_second": 11.996, | |
| "train_steps_per_second": 0.187, | |
| "train_tokens_per_second": 9664.096 | |
| } |