|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: trainer7 |
|
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. --> |
|
|
|
# trainer7 |
|
|
|
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3387 |
|
- Precision: 0.7247 |
|
- Recall: 0.6905 |
|
- F1: 0.6847 |
|
- Accuracy: 0.6905 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 1.8743 | 0.57 | 30 | 1.7616 | 0.1668 | 0.2857 | 0.1788 | 0.2857 | |
|
| 1.7125 | 1.13 | 60 | 1.6249 | 0.2572 | 0.3810 | 0.2914 | 0.3810 | |
|
| 1.4398 | 1.7 | 90 | 1.3244 | 0.4911 | 0.4881 | 0.4326 | 0.4881 | |
|
| 1.0265 | 2.26 | 120 | 1.0496 | 0.6570 | 0.6429 | 0.6197 | 0.6429 | |
|
| 0.6366 | 2.83 | 150 | 0.9035 | 0.6304 | 0.5952 | 0.5764 | 0.5952 | |
|
| 0.3959 | 3.4 | 180 | 0.8226 | 0.6881 | 0.6667 | 0.6557 | 0.6667 | |
|
| 0.2172 | 3.96 | 210 | 1.0152 | 0.6932 | 0.6429 | 0.6356 | 0.6429 | |
|
| 0.0946 | 4.53 | 240 | 1.0485 | 0.7357 | 0.6786 | 0.6913 | 0.6786 | |
|
| 0.0416 | 5.09 | 270 | 1.1458 | 0.6983 | 0.6548 | 0.6565 | 0.6548 | |
|
| 0.0238 | 5.66 | 300 | 1.4215 | 0.6839 | 0.6310 | 0.6272 | 0.6310 | |
|
| 0.0132 | 6.23 | 330 | 1.2009 | 0.7481 | 0.7024 | 0.7090 | 0.7024 | |
|
| 0.0077 | 6.79 | 360 | 1.2686 | 0.6968 | 0.6548 | 0.6538 | 0.6548 | |
|
| 0.0064 | 7.36 | 390 | 1.2725 | 0.7128 | 0.6786 | 0.6717 | 0.6786 | |
|
| 0.0057 | 7.92 | 420 | 1.3092 | 0.7161 | 0.6786 | 0.6731 | 0.6786 | |
|
| 0.0053 | 8.49 | 450 | 1.3306 | 0.7065 | 0.6667 | 0.6640 | 0.6667 | |
|
| 0.0046 | 9.06 | 480 | 1.3377 | 0.7156 | 0.6786 | 0.6749 | 0.6786 | |
|
| 0.0044 | 9.62 | 510 | 1.3387 | 0.7247 | 0.6905 | 0.6847 | 0.6905 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
