metadata
base_model: allenai/cs_roberta_base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: cs_roberta_base-1
results: []
cs_roberta_base-1
This model is a fine-tuned version of allenai/cs_roberta_base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3743
- Accuracy: 0.8905
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: 46
- eval_batch_size: 46
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3782 | 1.0 | 1044 | 0.9372 | 0.79 |
| 0.7908 | 2.0 | 2088 | 0.6508 | 0.8418 |
| 0.5942 | 3.0 | 3132 | 0.5638 | 0.8604 |
| 0.4986 | 4.0 | 4176 | 0.4780 | 0.8707 |
| 0.4301 | 5.0 | 5220 | 0.4408 | 0.8794 |
| 0.3798 | 6.0 | 6264 | 0.4103 | 0.8821 |
| 0.3388 | 7.0 | 7308 | 0.3938 | 0.8842 |
| 0.3082 | 8.0 | 8352 | 0.3821 | 0.8909 |
| 0.2842 | 9.0 | 9396 | 0.3852 | 0.887 |
| 0.2674 | 10.0 | 10440 | 0.3743 | 0.8905 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0