<!-- 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_token_2e-05_16_02_2022-14_15_41
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: 0.1746
- Precision: 0.3191
- Recall: 0.3382
- F1: 0.3284
- Accuracy: 0.9439
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: 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 | 0.2908 | 0.1104 | 0.1905 | 0.1398 | 0.8731 |
No log | 2.0 | 76 | 0.2253 | 0.1682 | 0.3206 | 0.2206 | 0.9114 |
No log | 3.0 | 114 | 0.2041 | 0.2069 | 0.3444 | 0.2585 | 0.9249 |
No log | 4.0 | 152 | 0.1974 | 0.2417 | 0.3603 | 0.2894 | 0.9269 |
No log | 5.0 | 190 | 0.1958 | 0.2707 | 0.3683 | 0.3120 | 0.9299 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.1+cu113
- Datasets 1.18.0
- Tokenizers 0.10.3