|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: DIALOGUE_second_model |
|
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. --> |
|
|
|
# DIALOGUE_second_model |
|
|
|
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: 0.3364 |
|
- Precision: 0.9762 |
|
- Recall: 0.9737 |
|
- F1: 0.9736 |
|
- Accuracy: 0.9737 |
|
|
|
## 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: 1e-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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 1.3667 | 0.31 | 15 | 1.2505 | 0.2468 | 0.4868 | 0.3263 | 0.4868 | |
|
| 1.1649 | 0.62 | 30 | 1.0587 | 0.8659 | 0.7105 | 0.6935 | 0.7105 | |
|
| 1.0288 | 0.94 | 45 | 0.8905 | 0.9479 | 0.9342 | 0.9331 | 0.9342 | |
|
| 0.8541 | 1.25 | 60 | 0.7069 | 0.9762 | 0.9737 | 0.9736 | 0.9737 | |
|
| 0.6833 | 1.56 | 75 | 0.5616 | 0.9762 | 0.9737 | 0.9736 | 0.9737 | |
|
| 0.6072 | 1.88 | 90 | 0.4586 | 0.9762 | 0.9737 | 0.9736 | 0.9737 | |
|
| 0.4665 | 2.19 | 105 | 0.3944 | 0.9762 | 0.9737 | 0.9736 | 0.9737 | |
|
| 0.4274 | 2.5 | 120 | 0.3563 | 0.9762 | 0.9737 | 0.9736 | 0.9737 | |
|
| 0.4116 | 2.81 | 135 | 0.3364 | 0.9762 | 0.9737 | 0.9736 | 0.9737 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
