distilbert-sentiment
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0367
- Accuracy: 0.8
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1099 | 1.0 | 16 | 1.0947 | 0.4 |
| 1.0034 | 2.0 | 32 | 1.0373 | 0.4667 |
| 0.7525 | 3.0 | 48 | 0.8114 | 0.6 |
| 0.4076 | 4.0 | 64 | 0.5849 | 0.7333 |
| 0.3685 | 5.0 | 80 | 0.6219 | 0.7333 |
| 0.1553 | 6.0 | 96 | 0.7386 | 0.6667 |
| 0.1413 | 7.0 | 112 | 1.0428 | 0.6 |
| 0.0877 | 8.0 | 128 | 0.7228 | 0.7333 |
| 0.0693 | 9.0 | 144 | 0.9355 | 0.6667 |
| 0.0758 | 10.0 | 160 | 1.0833 | 0.6667 |
| 0.0391 | 11.0 | 176 | 0.8923 | 0.8 |
| 0.0117 | 12.0 | 192 | 1.0124 | 0.8 |
| 0.0157 | 13.0 | 208 | 0.9896 | 0.8 |
| 0.0133 | 14.0 | 224 | 1.0390 | 0.8 |
| 0.0111 | 15.0 | 240 | 1.0367 | 0.8 |
Framework versions
- Transformers 5.10.2
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2