This model is a fine-tuned version of IDEA-CCNL/Erlangshen-Longformer-110M on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 34 | 2.4781 | 0.5938 |
| No log | 2.0 | 68 | 2.7322 | 0.625 |
| No log | 3.0 | 102 | 2.9097 | 0.5625 |
| No log | 4.0 | 136 | 4.1589 | 0.4062 |
| No log | 5.0 | 170 | 3.0174 | 0.625 |
| No log | 6.0 | 204 | 3.7337 | 0.4062 |
| No log | 7.0 | 238 | 3.2421 | 0.5938 |
| No log | 8.0 | 272 | 3.4698 | 0.5 |
| No log | 9.0 | 306 | 3.2162 | 0.625 |
| No log | 10.0 | 340 | 3.8119 | 0.5312 |
pytorch_model.bin 477 MBtraining_args.bin 4.1 kB