| Epoch... (1/20 | Loss: 2.377821683883667, Learning Rate: 9.501103704678826e-06) | |
| Epoch... (1/20 | Eval Loss: 2.2912707328796387 | Eval rouge1: 17.1532 | Eval rouge2: 2.1991 | Eval rougeL: 12.1665 | Eval rougeLsum: 13.7971 | Eval gen_len: 58.3398 |) | |
| Predict Loss: 2.3000617027282715 | Predict rouge1: 17.3228 | Predict rouge2: 2.1974 | Predict rougeL: 12.2257 | Predict rougeLsum: 13.863 | Predict gen_len: 58.0887 |) | |
| Epoch... (2/20 | Loss: 2.318763017654419, Learning Rate: 9.001103535410948e-06) | |
| Epoch... (2/20 | Eval Loss: 2.2495603561401367 | Eval rouge1: 13.6938 | Eval rouge2: 0.963 | Eval rougeL: 10.0782 | Eval rougeLsum: 10.8405 | Eval gen_len: 58.3382 |) | |
| Predict Loss: 2.2592482566833496 | Predict rouge1: 13.7749 | Predict rouge2: 0.9371 | Predict rougeL: 10.0138 | Predict rougeLsum: 10.8695 | Predict gen_len: 58.1836 |) | |
| Epoch... (3/20 | Loss: 2.3419060707092285, Learning Rate: 8.501104275637772e-06) | |
| Epoch... (3/20 | Eval Loss: 2.22269344329834 | Eval rouge1: 12.0579 | Eval rouge2: 0.7251 | Eval rougeL: 9.092 | Eval rougeLsum: 9.3802 | Eval gen_len: 60.7578 |) | |
| Predict Loss: 2.233069896697998 | Predict rouge1: 12.5721 | Predict rouge2: 0.8881 | Predict rougeL: 9.4823 | Predict rougeLsum: 9.7638 | Predict gen_len: 60.5006 |) | |
| Epoch... (4/20 | Loss: 2.2800769805908203, Learning Rate: 8.001104106369894e-06) | |
| Epoch... (4/20 | Eval Loss: 2.2039794921875 | Eval rouge1: 14.2541 | Eval rouge2: 0.7585 | Eval rougeL: 10.3604 | Eval rougeLsum: 11.1679 | Eval gen_len: 60.3655 |) | |
| Predict Loss: 2.214798927307129 | Predict rouge1: 14.4009 | Predict rouge2: 0.8344 | Predict rougeL: 10.3895 | Predict rougeLsum: 11.2357 | Predict gen_len: 60.2483 |) | |
| Epoch... (5/20 | Loss: 2.220062494277954, Learning Rate: 7.501103482354665e-06) | |
| Epoch... (5/20 | Eval Loss: 2.1913952827453613 | Eval rouge1: 14.1698 | Eval rouge2: 0.8184 | Eval rougeL: 10.2918 | Eval rougeLsum: 11.245 | Eval gen_len: 60.1311 |) | |
| Predict Loss: 2.202223300933838 | Predict rouge1: 14.4567 | Predict rouge2: 0.9169 | Predict rougeL: 10.5117 | Predict rougeLsum: 11.3823 | Predict gen_len: 59.875 |) | |
| Epoch... (6/20 | Loss: 2.105752944946289, Learning Rate: 7.001103767834138e-06) | |
| Epoch... (6/20 | Eval Loss: 2.1800718307495117 | Eval rouge1: 14.6613 | Eval rouge2: 0.924 | Eval rougeL: 10.5021 | Eval rougeLsum: 11.672 | Eval gen_len: 61.7065 |) | |
| Predict Loss: 2.1911959648132324 | Predict rouge1: 14.972 | Predict rouge2: 0.9993 | Predict rougeL: 10.7166 | Predict rougeLsum: 11.843 | Predict gen_len: 61.8092 |) | |
| Epoch... (7/20 | Loss: 2.1191587448120117, Learning Rate: 6.50110359856626e-06) | |
| Epoch... (7/20 | Eval Loss: 2.1725244522094727 | Eval rouge1: 12.9676 | Eval rouge2: 1.1282 | Eval rougeL: 9.5649 | Eval rougeLsum: 10.702 | Eval gen_len: 59.4275 |) | |
| Predict Loss: 2.1837007999420166 | Predict rouge1: 13.161 | Predict rouge2: 1.1852 | Predict rougeL: 9.7344 | Predict rougeLsum: 10.9045 | Predict gen_len: 59.3945 |) | |