metadata
license: mit
base_model: BigTMiami/tapt_helpfulness_base_pretraining_model_final
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: tapt_amazon_helpfulness_classification
results: []
tapt_amazon_helpfulness_classification
This model is a fine-tuned version of BigTMiami/tapt_helpfulness_base_pretraining_model_final on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3873
- Accuracy: 0.87
- F1 Macro: 0.6868
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 0.3226 | 1.0 | 1563 | 0.3149 | 0.8688 | 0.6717 |
| 0.2854 | 2.0 | 3126 | 0.3745 | 0.8682 | 0.6249 |
| 0.2016 | 3.0 | 4689 | 0.3873 | 0.87 | 0.6868 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2