|
--- |
|
license: apache-2.0 |
|
base_model: allenai/longformer-base-4096 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: longformer_result_detection |
|
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. --> |
|
|
|
# longformer_result_detection |
|
|
|
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1156 |
|
- Precision: 0.6277 |
|
- Recall: 0.6694 |
|
- F1: 0.6479 |
|
- Accuracy: 0.9802 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 348 | 0.0716 | 0.4966 | 0.6050 | 0.5455 | 0.9740 | |
|
| 0.1189 | 2.0 | 696 | 0.0634 | 0.5302 | 0.6195 | 0.5714 | 0.9770 | |
|
| 0.0588 | 3.0 | 1044 | 0.0760 | 0.5518 | 0.6424 | 0.5937 | 0.9774 | |
|
| 0.0588 | 4.0 | 1392 | 0.0760 | 0.6121 | 0.6528 | 0.6318 | 0.9785 | |
|
| 0.0282 | 5.0 | 1740 | 0.0910 | 0.6107 | 0.6424 | 0.6261 | 0.9792 | |
|
| 0.0167 | 6.0 | 2088 | 0.1372 | 0.6 | 0.5364 | 0.5664 | 0.9745 | |
|
| 0.0167 | 7.0 | 2436 | 0.1144 | 0.6028 | 0.6216 | 0.6121 | 0.9793 | |
|
| 0.0087 | 8.0 | 2784 | 0.1011 | 0.6120 | 0.6590 | 0.6346 | 0.9805 | |
|
| 0.0061 | 9.0 | 3132 | 0.1239 | 0.6315 | 0.6341 | 0.6328 | 0.9802 | |
|
| 0.0061 | 10.0 | 3480 | 0.1156 | 0.6277 | 0.6694 | 0.6479 | 0.9802 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
