metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased-finetuned-sst-2-english
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: imdb
results: []
imdb
This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2032
- Accuracy: 0.927
- Precision: 0.9241
- Recall: 0.9318
- F1: 0.9280
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: 2e-06
- train_batch_size: 64
- eval_batch_size: 64
- 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 | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2612 | 1.0 | 625 | 0.2290 | 0.9122 | 0.9080 | 0.9191 | 0.9135 |
| 0.218 | 2.0 | 1250 | 0.2174 | 0.919 | 0.9114 | 0.9298 | 0.9205 |
| 0.2019 | 3.0 | 1875 | 0.2120 | 0.922 | 0.9197 | 0.9263 | 0.9230 |
| 0.1806 | 4.0 | 2500 | 0.2070 | 0.9214 | 0.9122 | 0.9342 | 0.9230 |
| 0.1711 | 5.0 | 3125 | 0.2052 | 0.9244 | 0.9191 | 0.9322 | 0.9256 |
| 0.1605 | 6.0 | 3750 | 0.2032 | 0.9236 | 0.9164 | 0.9338 | 0.9250 |
| 0.1639 | 7.0 | 4375 | 0.2062 | 0.9244 | 0.9152 | 0.9370 | 0.9260 |
| 0.1544 | 8.0 | 5000 | 0.2026 | 0.9268 | 0.9265 | 0.9287 | 0.9276 |
| 0.148 | 9.0 | 5625 | 0.2035 | 0.9274 | 0.9212 | 0.9362 | 0.9286 |
| 0.144 | 10.0 | 6250 | 0.2032 | 0.927 | 0.9241 | 0.9318 | 0.9280 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1