| { | |
| "epoch": 4.71, | |
| "eval_loss": 1.5495115518569946, | |
| "eval_runtime": 200.1691, | |
| "eval_samples": 181300, | |
| "eval_samples_per_second": 905.734, | |
| "eval_steps_per_second": 3.542, | |
| "perplexity": 4.709169435672752, | |
| "train_loss": 0.5639808364868164, | |
| "train_runtime": 35161.1614, | |
| "train_samples": 4349088, | |
| "train_samples_per_second": 582.461, | |
| "train_steps_per_second": 0.284 | |
| } |