metadata
library_name: transformers
license: mit
base_model: intfloat/e5-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: intfloat-e5-base-v2-english-fp16-allagree
results: []
intfloat-e5-base-v2-english-fp16-allagree
This model is a fine-tuned version of intfloat/e5-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1038
- Accuracy: 0.9780
- Precision: 0.9779
- Recall: 0.9780
- F1: 0.9779
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- 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
- lr_scheduler_warmup_ratio: 0.3
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.8016 | 3.3448 | 50 | 0.3066 | 0.9339 | 0.9343 | 0.9339 | 0.9325 |
| 0.1009 | 6.6897 | 100 | 0.1038 | 0.9780 | 0.9779 | 0.9780 | 0.9779 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.6.0+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0