| Epoch... (1/10 | Loss: 2.3940577507019043, Learning Rate: 1.8007936887443066e-05) | |
| Epoch... (1/10 | Eval Loss: 2.393078327178955 | Eval rouge1: 12.8071 | Eval rouge2: 2.0016 | Eval rougeL: 11.3098 | Eval rougeLsum: 11.3162 | Eval gen_len: 31.3255 |) | |
| Epoch... (2/10 | Loss: 2.1883292198181152, Learning Rate: 1.6007936210371554e-05) | |
| Epoch... (2/10 | Eval Loss: 2.2480881214141846 | Eval rouge1: 15.861 | Eval rouge2: 3.108 | Eval rougeL: 13.6457 | Eval rougeLsum: 13.6531 | Eval gen_len: 31.5794 |) | |
| Epoch... (3/10 | Loss: 2.1005117893218994, Learning Rate: 1.4007936442794744e-05) | |
| Epoch... (3/10 | Eval Loss: 2.182466506958008 | Eval rouge1: 18.7278 | Eval rouge2: 3.4425 | Eval rougeL: 15.3744 | Eval rougeLsum: 15.3757 | Eval gen_len: 31.9742 |) | |
| Epoch... (4/10 | Loss: 1.9504339694976807, Learning Rate: 1.2007935765723232e-05) | |
| Epoch... (4/10 | Eval Loss: 2.1522512435913086 | Eval rouge1: 18.217 | Eval rouge2: 2.819 | Eval rougeL: 15.1391 | Eval rougeLsum: 15.1443 | Eval gen_len: 31.9922 |) | |
| Epoch... (5/10 | Loss: 1.9127023220062256, Learning Rate: 1.0007936907641124e-05) | |
| Epoch... (5/10 | Eval Loss: 2.1301980018615723 | Eval rouge1: 19.1425 | Eval rouge2: 3.3425 | Eval rougeL: 15.796 | Eval rougeLsum: 15.8031 | Eval gen_len: 31.9547 |) | |
| Epoch... (6/10 | Loss: 1.9510844945907593, Learning Rate: 8.007936230569612e-06) | |
| Epoch... (6/10 | Eval Loss: 2.1168270111083984 | Eval rouge1: 18.8478 | Eval rouge2: 3.2246 | Eval rougeL: 15.519 | Eval rougeLsum: 15.5254 | Eval gen_len: 31.9568 |) | |