<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Erlangshen-Longformer-110M-wallstreetcn-morning-news-market-overview-SSE50-f1-8
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:
- Loss: 1.3782
- F1: 0.5455
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 34 | 0.4790 | 0.7500 |
| No log | 2.0 | 68 | 0.6286 | 0.7500 |
| No log | 3.0 | 102 | 0.8222 | 0.3333 |
| No log | 4.0 | 136 | 0.6011 | 0.7407 |
| No log | 5.0 | 170 | 1.1117 | 0.4211 |
| No log | 6.0 | 204 | 1.1313 | 0.5455 |
| No log | 7.0 | 238 | 1.2961 | 0.4762 |
| No log | 8.0 | 272 | 1.1174 | 0.6667 |
| No log | 9.0 | 306 | 1.2210 | 0.6429 |
| No log | 10.0 | 340 | 1.3782 | 0.5455 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
