metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: roberta-base-negcommonsensebalanced-1e-06-64
results: []
roberta-base-negcommonsensebalanced-1e-06-64
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3964
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-06
- train_batch_size: 256
- eval_batch_size: 1024
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6084 | 1.0 | 795 | 0.5485 |
| 0.5297 | 2.0 | 1590 | 0.5047 |
| 0.5021 | 3.0 | 2385 | 0.4816 |
| 0.4891 | 4.0 | 3180 | 0.4691 |
| 0.4716 | 5.0 | 3975 | 0.4565 |
| 0.4622 | 6.0 | 4770 | 0.4519 |
| 0.4537 | 7.0 | 5565 | 0.4408 |
| 0.4437 | 8.0 | 6360 | 0.4387 |
| 0.4345 | 9.0 | 7155 | 0.4311 |
| 0.4295 | 10.0 | 7950 | 0.4286 |
| 0.4219 | 11.0 | 8745 | 0.4229 |
| 0.4169 | 12.0 | 9540 | 0.4175 |
| 0.413 | 13.0 | 10335 | 0.4176 |
| 0.4098 | 14.0 | 11130 | 0.4139 |
| 0.4046 | 15.0 | 11925 | 0.4096 |
| 0.4012 | 16.0 | 12720 | 0.4079 |
| 0.3958 | 17.0 | 13515 | 0.4069 |
| 0.3915 | 18.0 | 14310 | 0.4066 |
| 0.3928 | 19.0 | 15105 | 0.4046 |
| 0.3896 | 20.0 | 15900 | 0.4017 |
| 0.3856 | 21.0 | 16695 | 0.4004 |
| 0.3795 | 22.0 | 17490 | 0.3984 |
| 0.3809 | 23.0 | 18285 | 0.3989 |
| 0.3796 | 24.0 | 19080 | 0.3983 |
| 0.3782 | 25.0 | 19875 | 0.3983 |
| 0.3793 | 26.0 | 20670 | 0.3977 |
| 0.3747 | 27.0 | 21465 | 0.3959 |
| 0.3743 | 28.0 | 22260 | 0.3970 |
| 0.3795 | 29.0 | 23055 | 0.3962 |
| 0.373 | 30.0 | 23850 | 0.3964 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0