|
--- |
|
license: apache-2.0 |
|
base_model: allenai/longformer-base-4096 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: relevance-classification-v1 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# relevance-classification-v1 |
|
|
|
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.5156 |
|
- Accuracy: 0.6069 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| No log | 1.0 | 338 | 0.6547 | 0.6138 | |
|
| 0.744 | 2.0 | 676 | 1.3339 | 0.6069 | |
|
| 0.8767 | 3.0 | 1014 | 0.6368 | 0.6207 | |
|
| 0.8767 | 4.0 | 1352 | 0.8089 | 0.5931 | |
|
| 0.82 | 5.0 | 1690 | 1.7406 | 0.6276 | |
|
| 0.7448 | 6.0 | 2028 | 1.5868 | 0.6345 | |
|
| 0.7448 | 7.0 | 2366 | 1.6950 | 0.6483 | |
|
| 0.5449 | 8.0 | 2704 | 1.8365 | 0.6276 | |
|
| 0.4678 | 9.0 | 3042 | 1.9301 | 0.6069 | |
|
| 0.4678 | 10.0 | 3380 | 2.1818 | 0.6138 | |
|
| 0.3283 | 11.0 | 3718 | 2.1599 | 0.6 | |
|
| 0.2159 | 12.0 | 4056 | 2.3001 | 0.6207 | |
|
| 0.2159 | 13.0 | 4394 | 2.3061 | 0.6138 | |
|
| 0.1953 | 14.0 | 4732 | 2.5816 | 0.6069 | |
|
| 0.1241 | 15.0 | 5070 | 2.7310 | 0.6069 | |
|
| 0.1241 | 16.0 | 5408 | 2.5896 | 0.6207 | |
|
| 0.1793 | 17.0 | 5746 | 2.7177 | 0.6207 | |
|
| 0.0978 | 18.0 | 6084 | 2.6936 | 0.6069 | |
|
| 0.0978 | 19.0 | 6422 | 2.4796 | 0.6069 | |
|
| 0.175 | 20.0 | 6760 | 3.1355 | 0.6 | |
|
| 0.1408 | 21.0 | 7098 | 3.0787 | 0.6069 | |
|
| 0.1408 | 22.0 | 7436 | 3.0301 | 0.6 | |
|
| 0.1127 | 23.0 | 7774 | 3.5055 | 0.5793 | |
|
| 0.0812 | 24.0 | 8112 | 2.7603 | 0.6414 | |
|
| 0.0812 | 25.0 | 8450 | 3.2282 | 0.5793 | |
|
| 0.078 | 26.0 | 8788 | 3.3855 | 0.6138 | |
|
| 0.0228 | 27.0 | 9126 | 3.2529 | 0.6 | |
|
| 0.0228 | 28.0 | 9464 | 3.5188 | 0.6 | |
|
| 0.0556 | 29.0 | 9802 | 3.3436 | 0.5931 | |
|
| 0.0564 | 30.0 | 10140 | 3.6578 | 0.6069 | |
|
| 0.0564 | 31.0 | 10478 | 3.6755 | 0.6069 | |
|
| 0.0339 | 32.0 | 10816 | 3.5301 | 0.6138 | |
|
| 0.0273 | 33.0 | 11154 | 3.8414 | 0.6069 | |
|
| 0.0273 | 34.0 | 11492 | 4.0242 | 0.6069 | |
|
| 0.0045 | 35.0 | 11830 | 4.2730 | 0.5931 | |
|
| 0.0503 | 36.0 | 12168 | 3.8472 | 0.6069 | |
|
| 0.0043 | 37.0 | 12506 | 4.1642 | 0.5931 | |
|
| 0.0043 | 38.0 | 12844 | 4.2903 | 0.5931 | |
|
| 0.0 | 39.0 | 13182 | 4.3893 | 0.5931 | |
|
| 0.0 | 40.0 | 13520 | 4.4723 | 0.5931 | |
|
| 0.0 | 41.0 | 13858 | 4.4564 | 0.5931 | |
|
| 0.0088 | 42.0 | 14196 | 4.5376 | 0.5931 | |
|
| 0.0375 | 43.0 | 14534 | 4.2578 | 0.6 | |
|
| 0.0375 | 44.0 | 14872 | 4.3456 | 0.6069 | |
|
| 0.0 | 45.0 | 15210 | 4.3547 | 0.6069 | |
|
| 0.0002 | 46.0 | 15548 | 4.4010 | 0.6138 | |
|
| 0.0002 | 47.0 | 15886 | 4.4475 | 0.6069 | |
|
| 0.0 | 48.0 | 16224 | 4.4869 | 0.6069 | |
|
| 0.0 | 49.0 | 16562 | 4.5066 | 0.6069 | |
|
| 0.0 | 50.0 | 16900 | 4.5156 | 0.6069 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.2.2+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.2 |
|
|
