metadata
license: mit
base_model: mhr2004/roberta-large-nsp-1000000-1e-06-32
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: condaqa-roberta-large-nsp-1000000-1e-06-32-512-1e-05-8
results: []
condaqa-roberta-large-nsp-1000000-1e-06-32-512-1e-05-8
This model is a fine-tuned version of mhr2004/roberta-large-nsp-1000000-1e-06-32 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7947
- Accuracy: 0.6388
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 183 | 0.8783 | 0.4703 |
| 0.9921 | 2.0 | 366 | 0.7887 | 0.6027 |
| 0.8971 | 3.0 | 549 | 0.8484 | 0.5802 |
| 0.7713 | 4.0 | 732 | 0.7501 | 0.6595 |
| 0.638 | 5.0 | 915 | 0.9089 | 0.6486 |
| 0.5261 | 6.0 | 1098 | 0.8858 | 0.6604 |
| 0.4307 | 7.0 | 1281 | 0.9207 | 0.6477 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1