amazon_helpfulness_classification_dapt_tap
This model is a fine-tuned version of BigTMiami/dapt_plus_tapt_helpfulness_base_pretraining_model on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3428
- Accuracy: 0.8785
- F1 Macro: 0.6863
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=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
---|---|---|---|---|---|
0.315 | 1.0 | 7204 | 0.3045 | 0.874 | 0.6410 |
0.3083 | 2.0 | 14408 | 0.3373 | 0.8722 | 0.6349 |
0.2639 | 3.0 | 21612 | 0.3507 | 0.8768 | 0.6922 |
0.2388 | 4.0 | 28816 | 0.4179 | 0.87 | 0.6659 |
0.1534 | 5.0 | 36020 | 0.5956 | 0.8738 | 0.6830 |
0.1524 | 6.0 | 43224 | 0.6679 | 0.8684 | 0.6796 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 1