<!-- 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_distilbert_model
This model is a fine-tuned version of distilbert-base-uncased on the rotten_tomatoes dataset. It achieves the following results on the evaluation set:
- Loss: 0.5418
- Accuracy: 0.8471
- F1: 0.8471
- Precision: 0.8471
- Recall: 0.8471
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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.4213 | 1.0 | 534 | 0.3852 | 0.8415 | 0.8411 | 0.8444 | 0.8415 |
0.2557 | 2.0 | 1068 | 0.4643 | 0.8377 | 0.8377 | 0.8381 | 0.8377 |
0.1571 | 3.0 | 1602 | 0.5418 | 0.8471 | 0.8471 | 0.8471 | 0.8471 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1