finetuned_token_itr0_3e-05_all_16_02_2022-20_27_36
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: 0.1633
- Precision: 0.3632
- Recall: 0.3786
- F1: 0.3707
- Accuracy: 0.9482
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: 32
- eval_batch_size: 32
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 38 | 0.3227 | 0.1237 | 0.2397 | 0.1631 | 0.8566 |
| No log | 2.0 | 76 | 0.2874 | 0.2128 | 0.3328 | 0.2596 | 0.8721 |
| No log | 3.0 | 114 | 0.2762 | 0.2170 | 0.3603 | 0.2709 | 0.8844 |
| No log | 4.0 | 152 | 0.2770 | 0.2274 | 0.3690 | 0.2814 | 0.8819 |
| No log | 5.0 | 190 | 0.2771 | 0.2113 | 0.3741 | 0.2701 | 0.8823 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.1+cu113
- Datasets 1.18.0
- Tokenizers 0.10.3