|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
model-index: |
|
- name: bert-because-trainer-oversample |
|
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. --> |
|
|
|
# bert-because-trainer-oversample |
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3274 |
|
- Accuracy: 0.8972 |
|
- F1: 0.8299 |
|
- Recall: 0.8342 |
|
- Precision: 0.8256 |
|
|
|
## 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: 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: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:| |
|
| 0.6383 | 0.07 | 25 | 0.5128 | 0.7461 | 0.2882 | 0.1710 | 0.9167 | |
|
| 0.5933 | 0.15 | 50 | 0.5335 | 0.7352 | 0.6545 | 0.8342 | 0.5385 | |
|
| 0.4774 | 0.22 | 75 | 0.4369 | 0.8131 | 0.5804 | 0.4301 | 0.8925 | |
|
| 0.4801 | 0.3 | 100 | 0.3538 | 0.8458 | 0.7429 | 0.7409 | 0.7448 | |
|
| 0.3765 | 0.37 | 125 | 0.3890 | 0.8536 | 0.7267 | 0.6477 | 0.8278 | |
|
| 0.3411 | 0.45 | 150 | 0.4052 | 0.8474 | 0.7710 | 0.8549 | 0.7021 | |
|
| 0.2802 | 0.52 | 175 | 0.3509 | 0.8660 | 0.7701 | 0.7461 | 0.7956 | |
|
| 0.2558 | 0.59 | 200 | 0.4704 | 0.8629 | 0.7179 | 0.5803 | 0.9412 | |
|
| 0.4603 | 0.67 | 225 | 0.3298 | 0.8801 | 0.7968 | 0.7824 | 0.8118 | |
|
| 0.3211 | 0.74 | 250 | 0.3053 | 0.8925 | 0.8189 | 0.8083 | 0.8298 | |
|
| 0.2475 | 0.82 | 275 | 0.3052 | 0.8879 | 0.8209 | 0.8549 | 0.7895 | |
|
| 0.2644 | 0.89 | 300 | 0.3688 | 0.8910 | 0.8077 | 0.7617 | 0.8596 | |
|
| 0.3206 | 0.96 | 325 | 0.3332 | 0.8988 | 0.8320 | 0.8342 | 0.8299 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.3.1 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.1 |
|
|
