Alassea_glue_sst_classifier-finetuned-lora-rotten_tomatoes
This model is a fine-tuned version of Alassea/glue_sst_classifier on the rotten_tomatoes dataset. It achieves the following results on the evaluation set:
- accuracy: 0.8809
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: 0.0004
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| accuracy | train_loss | epoch |
|---|---|---|
| 0.8724 | None | 0 |
| 0.8715 | 0.3353 | 0 |
| 0.8724 | 0.3133 | 1 |
| 0.8799 | 0.3031 | 2 |
| 0.8809 | 0.2947 | 3 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.16.1
- Tokenizers 0.15.2
- Downloads last month
- 8
Model tree for TransferGraph/Alassea_glue_sst_classifier-finetuned-lora-rotten_tomatoes
Base model
Alassea/glue_sst_classifierDataset used to train TransferGraph/Alassea_glue_sst_classifier-finetuned-lora-rotten_tomatoes
Evaluation results
- accuracy on rotten_tomatoesvalidation set self-reported0.881