metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: micro_base_help_class_no_pre_seed_4
results: []
micro_base_help_class_no_pre_seed_4
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8233
- Accuracy: 0.852
- F1 Macro: 0.6640
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: 4
- 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 |
|---|---|---|---|---|---|
| 0.3665 | 1.0 | 313 | 0.3598 | 0.8536 | 0.4619 |
| 0.3132 | 2.0 | 626 | 0.3678 | 0.8634 | 0.5801 |
| 0.2547 | 3.0 | 939 | 0.3785 | 0.8456 | 0.6196 |
| 0.1904 | 4.0 | 1252 | 0.5449 | 0.8444 | 0.6189 |
| 0.1679 | 5.0 | 1565 | 0.7422 | 0.8528 | 0.5954 |
| 0.1157 | 6.0 | 1878 | 0.9005 | 0.8404 | 0.6468 |
| 0.094 | 7.0 | 2191 | 0.9842 | 0.8466 | 0.6246 |
| 0.0494 | 8.0 | 2504 | 1.0898 | 0.8476 | 0.6083 |
| 0.015 | 9.0 | 2817 | 1.2454 | 0.844 | 0.6390 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2