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

This model is a fine-tuned version of [intfloat/e5-base](https://huggingface.co/intfloat/e5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4020
- Accuracy: 0.8554
- Precision: 0.8542
- Recall: 0.8554
- F1: 0.8547

## 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     |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 1.0217        | 0.7463 | 50   | 0.8492          | 0.6707   | 0.7400    | 0.6707 | 0.5976 |
| 0.774         | 1.4925 | 100  | 0.6322          | 0.7612   | 0.7671    | 0.7612 | 0.7222 |
| 0.6181        | 2.2388 | 150  | 0.5103          | 0.8190   | 0.8151    | 0.8190 | 0.8113 |
| 0.5497        | 2.9851 | 200  | 0.4699          | 0.8218   | 0.8175    | 0.8218 | 0.8182 |
| 0.4594        | 3.7313 | 250  | 0.4475          | 0.8330   | 0.8330    | 0.8330 | 0.8304 |
| 0.4155        | 4.4776 | 300  | 0.4371          | 0.8218   | 0.8337    | 0.8218 | 0.8241 |
| 0.3722        | 5.2239 | 350  | 0.4166          | 0.8461   | 0.8423    | 0.8461 | 0.8427 |
| 0.3382        | 5.9701 | 400  | 0.4301          | 0.8340   | 0.8483    | 0.8340 | 0.8381 |
| 0.3087        | 6.7164 | 450  | 0.3906          | 0.8489   | 0.8476    | 0.8489 | 0.8461 |
| 0.2695        | 7.4627 | 500  | 0.4020          | 0.8601   | 0.8585    | 0.8601 | 0.8588 |
| 0.2685        | 8.2090 | 550  | 0.4136          | 0.8601   | 0.8601    | 0.8601 | 0.8592 |
| 0.2451        | 8.9552 | 600  | 0.4020          | 0.8554   | 0.8542    | 0.8554 | 0.8547 |


### Framework versions

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