|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: trainerH |
|
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. --> |
|
|
|
# trainerH |
|
|
|
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: 1.3385 |
|
- Precision: 0.8173 |
|
- Recall: 0.8123 |
|
- F1: 0.8128 |
|
- Accuracy: 0.8123 |
|
|
|
## 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: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0142 | 0.14 | 30 | 0.9604 | 0.8284 | 0.8207 | 0.8202 | 0.8207 | |
|
| 0.0446 | 0.27 | 60 | 0.9032 | 0.8403 | 0.8347 | 0.8353 | 0.8347 | |
|
| 0.0995 | 0.41 | 90 | 1.0133 | 0.8310 | 0.8263 | 0.8258 | 0.8263 | |
|
| 0.0776 | 0.54 | 120 | 1.1968 | 0.8130 | 0.7983 | 0.7961 | 0.7983 | |
|
| 0.0517 | 0.68 | 150 | 1.1238 | 0.8363 | 0.8263 | 0.8263 | 0.8263 | |
|
| 0.1014 | 0.81 | 180 | 1.0750 | 0.8334 | 0.8291 | 0.8293 | 0.8291 | |
|
| 0.1166 | 0.95 | 210 | 1.1253 | 0.8009 | 0.7955 | 0.7955 | 0.7955 | |
|
| 0.0447 | 1.08 | 240 | 1.2334 | 0.7969 | 0.7899 | 0.7883 | 0.7899 | |
|
| 0.0411 | 1.22 | 270 | 1.1707 | 0.8369 | 0.8319 | 0.8324 | 0.8319 | |
|
| 0.1145 | 1.35 | 300 | 1.3773 | 0.8320 | 0.8039 | 0.8021 | 0.8039 | |
|
| 0.06 | 1.49 | 330 | 1.1480 | 0.8320 | 0.8291 | 0.8274 | 0.8291 | |
|
| 0.0622 | 1.62 | 360 | 1.0856 | 0.8252 | 0.8235 | 0.8235 | 0.8235 | |
|
| 0.0366 | 1.76 | 390 | 1.2860 | 0.8236 | 0.8151 | 0.8162 | 0.8151 | |
|
| 0.0565 | 1.89 | 420 | 1.2558 | 0.8116 | 0.8011 | 0.8024 | 0.8011 | |
|
| 0.0019 | 2.03 | 450 | 1.2740 | 0.8208 | 0.8179 | 0.8180 | 0.8179 | |
|
| 0.0024 | 2.16 | 480 | 1.3075 | 0.8201 | 0.8151 | 0.8155 | 0.8151 | |
|
| 0.024 | 2.3 | 510 | 1.3170 | 0.8188 | 0.8151 | 0.8154 | 0.8151 | |
|
| 0.0008 | 2.43 | 540 | 1.3992 | 0.8099 | 0.8011 | 0.8024 | 0.8011 | |
|
| 0.0445 | 2.57 | 570 | 1.2633 | 0.8237 | 0.8207 | 0.8209 | 0.8207 | |
|
| 0.01 | 2.7 | 600 | 1.2843 | 0.8270 | 0.8235 | 0.8235 | 0.8235 | |
|
| 0.0175 | 2.84 | 630 | 1.2997 | 0.8246 | 0.8207 | 0.8208 | 0.8207 | |
|
| 0.0111 | 2.97 | 660 | 1.3486 | 0.8147 | 0.8095 | 0.8099 | 0.8095 | |
|
| 0.0006 | 3.11 | 690 | 1.3543 | 0.8154 | 0.8123 | 0.8120 | 0.8123 | |
|
| 0.0005 | 3.24 | 720 | 1.3493 | 0.8185 | 0.8151 | 0.8148 | 0.8151 | |
|
| 0.0129 | 3.38 | 750 | 1.3294 | 0.8136 | 0.8095 | 0.8098 | 0.8095 | |
|
| 0.0005 | 3.51 | 780 | 1.3441 | 0.8143 | 0.8095 | 0.8100 | 0.8095 | |
|
| 0.0005 | 3.65 | 810 | 1.3428 | 0.8143 | 0.8095 | 0.8100 | 0.8095 | |
|
| 0.0005 | 3.78 | 840 | 1.3402 | 0.8173 | 0.8123 | 0.8128 | 0.8123 | |
|
| 0.0005 | 3.92 | 870 | 1.3395 | 0.8173 | 0.8123 | 0.8128 | 0.8123 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|