|
--- |
|
base_model: vinai/bertweet-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: bertweet-base_3epoch10.2 |
|
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. --> |
|
|
|
# bertweet-base_3epoch10.2 |
|
|
|
This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8545 |
|
- Accuracy: 0.7493 |
|
- F1: 0.4663 |
|
- Precision: 0.5984 |
|
- Recall: 0.3819 |
|
- Precision Sarcastic: 0.5984 |
|
- Recall Sarcastic: 0.3819 |
|
- F1 Sarcastic: 0.4663 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- 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 | Accuracy | F1 | Precision | Recall | Precision Sarcastic | Recall Sarcastic | F1 Sarcastic | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------------:|:----------------:|:------------:| |
|
| No log | 1.0 | 174 | 1.8493 | 0.7464 | 0.4323 | 0.6036 | 0.3367 | 0.6036 | 0.3367 | 0.4323 | |
|
| No log | 2.0 | 348 | 1.5481 | 0.7522 | 0.5301 | 0.5808 | 0.4874 | 0.5808 | 0.4874 | 0.5301 | |
|
| 0.0477 | 3.0 | 522 | 1.6249 | 0.7565 | 0.4531 | 0.6364 | 0.3518 | 0.6364 | 0.3518 | 0.4531 | |
|
| 0.0477 | 4.0 | 696 | 1.6593 | 0.7464 | 0.4793 | 0.5827 | 0.4070 | 0.5827 | 0.4070 | 0.4793 | |
|
| 0.0477 | 5.0 | 870 | 1.7213 | 0.7493 | 0.42 | 0.6238 | 0.3166 | 0.6238 | 0.3166 | 0.42 | |
|
| 0.0277 | 6.0 | 1044 | 1.7249 | 0.7450 | 0.4381 | 0.5948 | 0.3467 | 0.5948 | 0.3467 | 0.4381 | |
|
| 0.0277 | 7.0 | 1218 | 1.8038 | 0.7450 | 0.4486 | 0.5902 | 0.3618 | 0.5902 | 0.3618 | 0.4486 | |
|
| 0.0277 | 8.0 | 1392 | 1.8409 | 0.7493 | 0.4387 | 0.6126 | 0.3417 | 0.6126 | 0.3417 | 0.4387 | |
|
| 0.0105 | 9.0 | 1566 | 1.8427 | 0.7522 | 0.4487 | 0.6195 | 0.3518 | 0.6195 | 0.3518 | 0.4487 | |
|
| 0.0105 | 10.0 | 1740 | 1.8545 | 0.7493 | 0.4663 | 0.5984 | 0.3819 | 0.5984 | 0.3819 | 0.4663 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
