metadata
library_name: transformers
license: mit
base_model: intfloat/e5-small-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: RewardModel_deberta-v3-large
results: []
RewardModel_deberta-v3-large
This model is a fine-tuned version of intfloat/e5-small-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5170
- Accuracy: 1.0
- F1: 1.0
- Roc Auc: 1.0
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: 8
- eval_batch_size: 8
- 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: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Roc Auc |
|---|---|---|---|---|---|---|
| No log | 1.0 | 20 | 0.6583 | 0.56 | 0.4544 | 0.56 |
| No log | 2.0 | 40 | 0.5170 | 1.0 | 1.0 | 1.0 |
| No log | 3.0 | 60 | 0.3450 | 1.0 | 1.0 | 1.0 |
| No log | 4.0 | 80 | 0.2474 | 1.0 | 1.0 | 1.0 |
| 0.4644 | 5.0 | 100 | 0.2256 | 1.0 | 1.0 | 1.0 |
Framework versions
- Transformers 4.54.0
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2