| epoch 0: avg Loss = 4.075 / dev BLEU = 0.0584 | |
| /home/xinyue/.conda/envs/myenv/lib/python3.10/site-packages/transformers/modeling_utils.py:2758: UserWarning: Moving the following attributes in the config to the generation config: {'max_length': 200}. You are seeing this warning because you've set generation parameters in the model config, as opposed to in the generation config. | |
| warnings.warn( | |
| epoch 1: avg Loss = 3.953 / dev BLEU = 0.0543 | |
| epoch 2: avg Loss = 3.953 / dev BLEU = 0.0410 | |
| epoch 3: avg Loss = 3.856 / dev BLEU = 0.0523 | |
| epoch 4: avg Loss = 3.709 / dev BLEU = 0.0654 | |
| epoch 5: avg Loss = 3.649 / dev BLEU = 0.0189 | |
| epoch 6: avg Loss = 3.601 / dev BLEU = 0.1455 | |
| epoch 7: avg Loss = 3.659 / dev BLEU = 0.0379 | |
| epoch 8: avg Loss = 3.617 / dev BLEU = 0.0855 | |
| epoch 9: avg Loss = 3.651 / dev BLEU = 0.0384 | |
| epoch 10: avg Loss = 3.651 / dev BLEU = 0.0293 | |
| epoch 11: avg Loss = 3.617 / dev BLEU = 0.0883 | |
| epoch 12: avg Loss = 3.616 / dev BLEU = 0.1434 | |
| epoch 13: avg Loss = 3.556 / dev BLEU = 0.0918 | |
| epoch 14: avg Loss = 3.537 / dev BLEU = 0.1838 | |
| epoch 15: avg Loss = 3.475 / dev BLEU = 0.0489 | |
| epoch 16: avg Loss = 3.471 / dev BLEU = 0.0720 | |
| epoch 17: avg Loss = 3.433 / dev BLEU = 0.0698 | |
| epoch 18: avg Loss = 3.409 / dev BLEU = 0.0658 | |
| epoch 19: avg Loss = 3.394 / dev BLEU = 0.0633 | |
| epoch 20: avg Loss = 3.369 / dev BLEU = 0.0691 | |
| epoch 21: avg Loss = 3.355 / dev BLEU = 0.0391 | |
| epoch 22: avg Loss = 3.329 / dev BLEU = 0.0603 | |
| epoch 23: avg Loss = 3.301 / dev BLEU = 0.0240 | |
| epoch 24: avg Loss = 3.275 / dev BLEU = 0.0528 | |
| epoch 25: avg Loss = 3.261 / dev BLEU = 0.0717 | |
| epoch 26: avg Loss = 3.237 / dev BLEU = 0.0458 | |
| epoch 27: avg Loss = 3.216 / dev BLEU = 0.0495 | |
| epoch 28: avg Loss = 3.204 / dev BLEU = 0.0444 | |
| epoch 29: avg Loss = 3.196 / dev BLEU = 0.0863 | |
| epoch 30: avg Loss = 3.182 / dev BLEU = 0.0469 | |
| epoch 31: avg Loss = 3.181 / dev BLEU = 0.0799 | |
| epoch 32: avg Loss = 3.170 / dev BLEU = 0.0595 | |
| epoch 33: avg Loss = 3.169 / dev BLEU = 0.0302 | |
| epoch 34: avg Loss = 3.144 / dev BLEU = 0.0792 | |
| epoch 35: avg Loss = 3.136 / dev BLEU = 0.0381 | |
| epoch 36: avg Loss = 3.113 / dev BLEU = 0.0591 | |
| epoch 37: avg Loss = 3.098 / dev BLEU = 0.0567 | |
| epoch 38: avg Loss = 3.066 / dev BLEU = 0.0850 | |
| epoch 39: avg Loss = 3.053 / dev BLEU = 0.0423 | |
| epoch 40: avg Loss = 3.040 / dev BLEU = 0.0724 | |
| epoch 41: avg Loss = 3.019 / dev BLEU = 0.0630 | |
| epoch 42: avg Loss = 3.006 / dev BLEU = 0.0421 | |
| epoch 43: avg Loss = 3.005 / dev BLEU = 0.0432 | |
| epoch 44: avg Loss = 2.986 / dev BLEU = 0.0561 | |
| epoch 45: avg Loss = 2.966 / dev BLEU = 0.1177 | |
| epoch 46: avg Loss = 2.959 / dev BLEU = 0.0977 | |
| epoch 47: avg Loss = 2.959 / dev BLEU = 0.0246 | |
| epoch 48: avg Loss = 2.944 / dev BLEU = 0.0712 | |
| epoch 49: avg Loss = 2.946 / dev BLEU = 0.0230 | |
| epoch 50: avg Loss = 2.929 / dev BLEU = 0.1006 | |
| epoch 51: avg Loss = 2.911 / dev BLEU = 0.0544 | |
| epoch 52: avg Loss = 2.900 / dev BLEU = 0.0504 | |
| epoch 53: avg Loss = 2.881 / dev BLEU = 0.0928 | |
| epoch 54: avg Loss = 2.864 / dev BLEU = 0.0709 | |
| epoch 55: avg Loss = 2.852 / dev BLEU = 0.0560 | |
| epoch 56: avg Loss = 2.850 / dev BLEU = 0.0950 | |
| epoch 57: avg Loss = 2.840 / dev BLEU = 0.0303 | |
| epoch 58: avg Loss = 2.829 / dev BLEU = 0.0865 | |
| epoch 59: avg Loss = 2.816 / dev BLEU = 0.0631 | |
| epoch 60: avg Loss = 2.809 / dev BLEU = 0.0653 | |
| epoch 61: avg Loss = 2.804 / dev BLEU = 0.0610 | |
| epoch 62: avg Loss = 2.799 / dev BLEU = 0.0895 | |
| epoch 63: avg Loss = 2.789 / dev BLEU = 0.0710 | |
| epoch 64: avg Loss = 2.780 / dev BLEU = 0.0331 | |
| epoch 65: avg Loss = 2.765 / dev BLEU = 0.0655 | |
| epoch 66: avg Loss = 2.751 / dev BLEU = 0.0495 | |
| epoch 67: avg Loss = 2.739 / dev BLEU = 0.0792 | |
| epoch 68: avg Loss = 2.728 / dev BLEU = 0.0660 | |
| epoch 69: avg Loss = 2.719 / dev BLEU = 0.0284 | |
| epoch 70: avg Loss = 2.712 / dev BLEU = 0.0557 | |
| epoch 71: avg Loss = 2.702 / dev BLEU = 0.0566 | |
| epoch 72: avg Loss = 2.703 / dev BLEU = 0.0387 | |
| epoch 73: avg Loss = 2.699 / dev BLEU = 0.1095 | |
| epoch 74: avg Loss = 2.683 / dev BLEU = 0.0691 | |
| epoch 75: avg Loss = 2.678 / dev BLEU = 0.0534 | |
| epoch 76: avg Loss = 2.669 / dev BLEU = 0.0545 | |
| epoch 77: avg Loss = 2.659 / dev BLEU = 0.0723 | |
| epoch 78: avg Loss = 2.649 / dev BLEU = 0.0857 | |
| epoch 79: avg Loss = 2.641 / dev BLEU = 0.0775 | |
| epoch 80: avg Loss = 2.635 / dev BLEU = 0.0978 | |
| epoch 81: avg Loss = 2.627 / dev BLEU = 0.0597 | |
| epoch 82: avg Loss = 2.616 / dev BLEU = 0.1039 | |
| epoch 83: avg Loss = 2.604 / dev BLEU = 0.0568 | |
| epoch 84: avg Loss = 2.594 / dev BLEU = 0.0527 | |
| epoch 85: avg Loss = 2.590 / dev BLEU = 0.0490 | |
| epoch 86: avg Loss = 2.577 / dev BLEU = 0.0551 | |
| epoch 87: avg Loss = 2.576 / dev BLEU = 0.0658 | |
| epoch 88: avg Loss = 2.565 / dev BLEU = 0.0682 | |
| epoch 89: avg Loss = 2.558 / dev BLEU = 0.0501 | |
| epoch 90: avg Loss = 2.545 / dev BLEU = 0.0766 | |
| epoch 91: avg Loss = 2.536 / dev BLEU = 0.0397 | |
| epoch 92: avg Loss = 2.527 / dev BLEU = 0.0739 | |
| epoch 93: avg Loss = 2.515 / dev BLEU = 0.0515 | |
| epoch 94: avg Loss = 2.502 / dev BLEU = 0.0914 | |
| epoch 95: avg Loss = 2.494 / dev BLEU = 0.0631 | |
| epoch 96: avg Loss = 2.486 / dev BLEU = 0.0450 | |
| epoch 97: avg Loss = 2.475 / dev BLEU = 0.1280 | |
| epoch 98: avg Loss = 2.463 / dev BLEU = 0.0616 | |
| epoch 99: avg Loss = 2.451 / dev BLEU = 0.0568 | |
| epoch 100: avg Loss = 2.420 / dev BLEU = 0.0692 | |
|  | |
|  | |