metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: micro_base_help_class_no_pre_seed_0
results: []
micro_base_help_class_no_pre_seed_0
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9454
- Accuracy: 0.8456
- F1 Macro: 0.6500
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: 0
- 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 |
|---|---|---|---|---|---|
| 0.3239 | 1.0 | 313 | 0.3666 | 0.8572 | 0.5370 |
| 0.3208 | 2.0 | 626 | 0.3962 | 0.8536 | 0.4632 |
| 0.2688 | 3.0 | 939 | 0.3881 | 0.8622 | 0.5912 |
| 0.2105 | 4.0 | 1252 | 0.5269 | 0.8616 | 0.5922 |
| 0.1625 | 5.0 | 1565 | 0.6255 | 0.859 | 0.6338 |
| 0.1188 | 6.0 | 1878 | 0.8231 | 0.8572 | 0.6169 |
| 0.052 | 7.0 | 2191 | 0.8230 | 0.8616 | 0.6189 |
| 0.053 | 8.0 | 2504 | 0.9466 | 0.8422 | 0.6496 |
| 0.0365 | 9.0 | 2817 | 0.9747 | 0.8556 | 0.6365 |
| 0.0452 | 10.0 | 3130 | 0.9923 | 0.8578 | 0.6360 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2