metadata
license: mit
base_model: ltuzova/amazon_domain_pretrained_model
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: amazon_helpfulness_classification_on_25M_full_pretrained
results: []
amazon_helpfulness_classification_on_25M_full_pretrained
This model is a fine-tuned version of ltuzova/amazon_domain_pretrained_model on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3257
- Accuracy: 0.8723
- F1 Macro: 0.6231
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 |
|---|---|---|---|---|---|
| 0.3084 | 1.0 | 7204 | 0.3296 | 0.8702 | 0.6250 |
| 0.2698 | 2.0 | 14408 | 0.3508 | 0.876 | 0.6586 |
| 0.2399 | 3.0 | 21612 | 0.3712 | 0.8758 | 0.6785 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2