|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: distilbert-base-uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: trainer_2f |
|
|
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. --> |
|
|
|
|
|
# trainer_2f |
|
|
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.6467 |
|
|
- Precision: 0.8276 |
|
|
- Recall: 0.8207 |
|
|
- F1: 0.8208 |
|
|
- Accuracy: 0.8207 |
|
|
|
|
|
## 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: 4 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 1.8981 | 0.27 | 30 | 1.7350 | 0.4229 | 0.4146 | 0.3885 | 0.4146 | |
|
|
| 1.5297 | 0.54 | 60 | 1.3572 | 0.4949 | 0.4286 | 0.3544 | 0.4286 | |
|
|
| 1.2565 | 0.81 | 90 | 1.0154 | 0.7047 | 0.6891 | 0.6859 | 0.6891 | |
|
|
| 0.9124 | 1.08 | 120 | 0.8039 | 0.7558 | 0.7535 | 0.7496 | 0.7535 | |
|
|
| 0.6233 | 1.35 | 150 | 0.6860 | 0.7788 | 0.7731 | 0.7692 | 0.7731 | |
|
|
| 0.5281 | 1.62 | 180 | 0.6874 | 0.7504 | 0.7395 | 0.7383 | 0.7395 | |
|
|
| 0.4313 | 1.89 | 210 | 0.6302 | 0.7992 | 0.7899 | 0.7888 | 0.7899 | |
|
|
| 0.3041 | 2.16 | 240 | 0.6437 | 0.7706 | 0.7619 | 0.7610 | 0.7619 | |
|
|
| 0.2096 | 2.43 | 270 | 0.6585 | 0.7847 | 0.7759 | 0.7731 | 0.7759 | |
|
|
| 0.2161 | 2.7 | 300 | 0.6198 | 0.8121 | 0.8039 | 0.8027 | 0.8039 | |
|
|
| 0.1888 | 2.97 | 330 | 0.6286 | 0.8298 | 0.8207 | 0.8201 | 0.8207 | |
|
|
| 0.1107 | 3.24 | 360 | 0.6106 | 0.8297 | 0.8263 | 0.8260 | 0.8263 | |
|
|
| 0.0834 | 3.51 | 390 | 0.6133 | 0.8223 | 0.8179 | 0.8170 | 0.8179 | |
|
|
| 0.0858 | 3.78 | 420 | 0.6481 | 0.8244 | 0.8179 | 0.8178 | 0.8179 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.39.3 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
