metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: experiment_lr_20241215_145438-postcrash
results: []
experiment_lr_20241215_145438-postcrash
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0166
- Exact Match Accuracy: 0.5777
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match Accuracy |
|---|---|---|---|---|
| 0.0725 | 1.0 | 2297 | 0.0720 | 0.0 |
| 0.0661 | 2.0 | 4594 | 0.0607 | 0.0 |
| 0.0422 | 3.0 | 6891 | 0.0356 | 0.0245 |
| 0.0252 | 4.0 | 9188 | 0.0234 | 0.1441 |
| 0.0193 | 5.0 | 11485 | 0.0185 | 0.4620 |
| 0.0164 | 6.0 | 13782 | 0.0168 | 0.5711 |
| 0.0158 | 7.0 | 16079 | 0.0166 | 0.5777 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0