---
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-arabic-fp16
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# intfloat-e5-base-v2-arabic-fp16

This model is a fine-tuned version of [intfloat/e5-base-v2](https://huggingface.co/intfloat/e5-base-v2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6556
- Accuracy: 0.7373
- Precision: 0.7334
- Recall: 0.7373
- F1: 0.7326

## 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     |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 1.0839        | 0.3636 | 50   | 0.9608          | 0.5914   | 0.6871    | 0.5914 | 0.5136 |
| 0.9231        | 0.7273 | 100  | 0.8409          | 0.6418   | 0.6989    | 0.6418 | 0.5666 |
| 0.842         | 1.0873 | 150  | 0.7770          | 0.6877   | 0.6719    | 0.6877 | 0.6606 |
| 0.7936        | 1.4509 | 200  | 0.7662          | 0.6836   | 0.6748    | 0.6836 | 0.6608 |
| 0.7691        | 1.8145 | 250  | 0.7656          | 0.6809   | 0.6841    | 0.6809 | 0.6780 |
| 0.7528        | 2.1745 | 300  | 0.7134          | 0.7091   | 0.7059    | 0.7091 | 0.7005 |
| 0.7215        | 2.5382 | 350  | 0.7003          | 0.7068   | 0.7161    | 0.7068 | 0.7093 |
| 0.7101        | 2.9018 | 400  | 0.6866          | 0.7227   | 0.7182    | 0.7227 | 0.7128 |
| 0.69          | 3.2618 | 450  | 0.6877          | 0.7164   | 0.7201    | 0.7164 | 0.7167 |
| 0.6578        | 3.6255 | 500  | 0.7134          | 0.6991   | 0.7178    | 0.6991 | 0.7041 |
| 0.6521        | 3.9891 | 550  | 0.6563          | 0.7377   | 0.7346    | 0.7377 | 0.7341 |
| 0.6031        | 4.3491 | 600  | 0.6556          | 0.7373   | 0.7334    | 0.7373 | 0.7326 |
| 0.6007        | 4.7127 | 650  | 0.6590          | 0.7341   | 0.7361    | 0.7341 | 0.7350 |
| 0.5876        | 5.0727 | 700  | 0.6783          | 0.7268   | 0.7324    | 0.7268 | 0.7285 |
| 0.5533        | 5.4364 | 750  | 0.6912          | 0.7205   | 0.7354    | 0.7205 | 0.7217 |


### Framework versions

- Transformers 4.51.1
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1