<!-- 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. -->
my_SA_distilbert_model_finalversion
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: 0.3031
- Accuracy: 0.9115
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-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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.3696 | 1.0 | 2248 | 0.3310 | 0.8852 |
0.2624 | 2.0 | 4496 | 0.3118 | 0.9063 |
0.1817 | 3.0 | 6744 | 0.3314 | 0.9072 |
0.1398 | 4.0 | 8992 | 0.3031 | 0.9115 |
0.1294 | 5.0 | 11240 | 0.3801 | 0.9110 |
0.0974 | 6.0 | 13488 | 0.3968 | 0.9059 |
0.0662 | 7.0 | 15736 | 0.4742 | 0.9177 |
0.0634 | 8.0 | 17984 | 0.5182 | 0.9150 |
0.0377 | 9.0 | 20232 | 0.5356 | 0.9159 |
0.0298 | 10.0 | 22480 | 0.5717 | 0.9139 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3