<!-- 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. -->
finetuned_sentence_itr1_0.0002_all_27_02_2022-18_01_22
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: 0.7600
- Accuracy: 0.8144
- F1: 0.8788
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: 0.0002
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 195 | 0.3514 | 0.8427 | 0.8979 |
| No log | 2.0 | 390 | 0.3853 | 0.8293 | 0.8936 |
| 0.3147 | 3.0 | 585 | 0.5494 | 0.8268 | 0.8868 |
| 0.3147 | 4.0 | 780 | 0.6235 | 0.8427 | 0.8995 |
| 0.3147 | 5.0 | 975 | 0.8302 | 0.8378 | 0.8965 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.1+cu113
- Datasets 1.18.0
- Tokenizers 0.10.3
