| [ |
| { |
| "eval_loss": 1.2019327878952026, |
| "eval_runtime": 3.7296, |
| "eval_samples_per_second": 130.04, |
| "eval_steps_per_second": 16.356, |
| "epoch": 1.0, |
| "step": 486 |
| }, |
| { |
| "loss": 2.012456298828125, |
| "grad_norm": 61.2252311706543, |
| "learning_rate": 1.3155006858710564e-05, |
| "epoch": 1.02880658436214, |
| "step": 500 |
| }, |
| { |
| "eval_loss": 0.9657873511314392, |
| "eval_runtime": 3.8673, |
| "eval_samples_per_second": 125.41, |
| "eval_steps_per_second": 15.773, |
| "epoch": 2.0, |
| "step": 972 |
| }, |
| { |
| "loss": 1.1124793701171876, |
| "grad_norm": 51.13796615600586, |
| "learning_rate": 6.296296296296297e-06, |
| "epoch": 2.05761316872428, |
| "step": 1000 |
| }, |
| { |
| "eval_loss": 0.9960638284683228, |
| "eval_runtime": 3.7498, |
| "eval_samples_per_second": 129.34, |
| "eval_steps_per_second": 16.267, |
| "epoch": 3.0, |
| "step": 1458 |
| }, |
| { |
| "train_runtime": 714.5044, |
| "train_samples_per_second": 16.304, |
| "train_steps_per_second": 2.041, |
| "total_flos": 3043845919217664.0, |
| "train_loss": 1.3373331663866919, |
| "epoch": 3.0, |
| "step": 1458 |
| }, |
| { |
| "eval_loss": 0.9657873511314392, |
| "eval_runtime": 3.3404, |
| "eval_samples_per_second": 145.191, |
| "eval_steps_per_second": 18.261, |
| "epoch": 3.0, |
| "step": 1458 |
| } |
| ] |
