metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: micro_base_help_class_no_pre_seed_3
results: []
micro_base_help_class_no_pre_seed_3
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3318
- Accuracy: 0.8454
- F1 Macro: 0.6580
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: 3
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 0.3515 | 1.0 | 313 | 0.3439 | 0.8536 | 0.6099 |
| 0.3166 | 2.0 | 626 | 0.3352 | 0.8598 | 0.5733 |
| 0.2622 | 3.0 | 939 | 0.3453 | 0.8458 | 0.6676 |
| 0.2173 | 4.0 | 1252 | 0.5821 | 0.8618 | 0.5924 |
| 0.1634 | 5.0 | 1565 | 0.7321 | 0.8542 | 0.6490 |
| 0.126 | 6.0 | 1878 | 0.8761 | 0.8264 | 0.6615 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2