| {"loss": 1.4885, "grad_norm": 2.976400136947632, "learning_rate": 3.336666666666667e-05, "epoch": 1.0, "step": 500} | |
| {"loss": 1.1504, "grad_norm": 4.292872428894043, "learning_rate": 1.6700000000000003e-05, "epoch": 2.0, "step": 1000} | |
| {"loss": 1.0006, "grad_norm": 7.022700309753418, "learning_rate": 3.3333333333333334e-08, "epoch": 3.0, "step": 1500} | |
| {"train_runtime": 11730.008, "train_samples_per_second": 4.092, "train_steps_per_second": 0.128, "total_flos": 1020745916282304.0, "train_loss": 1.2131712443033855, "epoch": 3.0, "step": 1500} | |