|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: SIRIS-Lab/affilgood-affilroberta |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# affilgood-span-v2 |
|
|
|
This model is a fine-tuned version of [SIRIS-Lab/affilgood-affilroberta](https://huggingface.co/SIRIS-Lab/affilgood-affilroberta) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2360 |
|
- Precision: 0.8321 |
|
- Recall: 0.8934 |
|
- F1: 0.8617 |
|
- Accuracy: 0.9612 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 93 | 0.1532 | 0.7861 | 0.8333 | 0.8090 | 0.9567 | |
|
| No log | 2.0 | 186 | 0.1135 | 0.8404 | 0.8634 | 0.8518 | 0.9610 | |
|
| No log | 3.0 | 279 | 0.1021 | 0.8333 | 0.9016 | 0.8661 | 0.9682 | |
|
| No log | 4.0 | 372 | 0.1183 | 0.8182 | 0.8852 | 0.8504 | 0.9673 | |
|
| No log | 5.0 | 465 | 0.1377 | 0.8564 | 0.8962 | 0.8758 | 0.9685 | |
|
| 0.0987 | 6.0 | 558 | 0.1296 | 0.8575 | 0.9044 | 0.8803 | 0.9682 | |
|
| 0.0987 | 7.0 | 651 | 0.1568 | 0.8583 | 0.8934 | 0.8755 | 0.9685 | |
|
| 0.0987 | 8.0 | 744 | 0.2092 | 0.8575 | 0.8880 | 0.8725 | 0.9649 | |
|
| 0.0987 | 9.0 | 837 | 0.2360 | 0.8321 | 0.8934 | 0.8617 | 0.9612 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.5.0+cu121 |
|
- Datasets 3.0.2 |
|
- Tokenizers 0.19.1 |
