---
library_name: transformers
license: mit
base_model: intfloat/e5-small-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: intfloat-e5-small-v2-arabic-fp16-allagree
  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-small-v2-arabic-fp16-allagree

This model is a fine-tuned version of [intfloat/e5-small-v2](https://huggingface.co/intfloat/e5-small-v2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4486
- Accuracy: 0.8451
- Precision: 0.8477
- Recall: 0.8451
- F1: 0.8458

## 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     |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 1.0892        | 0.7463 | 50   | 1.0692          | 0.4198   | 0.7313    | 0.4198 | 0.2920 |
| 1.0058        | 1.4925 | 100  | 0.8471          | 0.7155   | 0.7762    | 0.7155 | 0.6375 |
| 0.7971        | 2.2388 | 150  | 0.7135          | 0.7295   | 0.7177    | 0.7295 | 0.6688 |
| 0.7025        | 2.9851 | 200  | 0.6560          | 0.7603   | 0.7719    | 0.7603 | 0.7341 |
| 0.6405        | 3.7313 | 250  | 0.5768          | 0.8060   | 0.8070    | 0.8060 | 0.8047 |
| 0.5794        | 4.4776 | 300  | 0.5331          | 0.8209   | 0.8213    | 0.8209 | 0.8108 |
| 0.5474        | 5.2239 | 350  | 0.5227          | 0.8116   | 0.8265    | 0.8116 | 0.8156 |
| 0.5228        | 5.9701 | 400  | 0.5046          | 0.8237   | 0.8291    | 0.8237 | 0.8246 |
| 0.472         | 6.7164 | 450  | 0.4832          | 0.8302   | 0.8315    | 0.8302 | 0.8260 |
| 0.4527        | 7.4627 | 500  | 0.4739          | 0.8368   | 0.8435    | 0.8368 | 0.8391 |
| 0.4347        | 8.2090 | 550  | 0.4526          | 0.8414   | 0.8443    | 0.8414 | 0.8425 |
| 0.4322        | 8.9552 | 600  | 0.4486          | 0.8451   | 0.8477    | 0.8451 | 0.8458 |
| 0.4111        | 9.7015 | 650  | 0.4545          | 0.8405   | 0.8488    | 0.8405 | 0.8435 |


### Framework versions

- Transformers 4.48.2
- Pytorch 2.6.0+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0