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

This model is a fine-tuned version of [intfloat/e5-large](https://huggingface.co/intfloat/e5-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6571
- Accuracy: 0.7295
- Precision: 0.7252
- Recall: 0.7295
- F1: 0.7229

## 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     |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 1.1453        | 0.3636 | 50   | 0.9382          | 0.5823   | 0.4522    | 0.5823 | 0.5088 |
| 0.9116        | 0.7273 | 100  | 0.8151          | 0.6568   | 0.6543    | 0.6568 | 0.6162 |
| 0.8321        | 1.0873 | 150  | 0.8027          | 0.6645   | 0.6610    | 0.6645 | 0.6379 |
| 0.8035        | 1.4509 | 200  | 0.7924          | 0.6777   | 0.6807    | 0.6777 | 0.6628 |
| 0.7746        | 1.8145 | 250  | 0.9196          | 0.6141   | 0.6605    | 0.6141 | 0.6040 |
| 0.7751        | 2.1745 | 300  | 0.7843          | 0.6677   | 0.6741    | 0.6677 | 0.6650 |
| 0.753         | 2.5382 | 350  | 0.7799          | 0.6568   | 0.6968    | 0.6568 | 0.6672 |
| 0.731         | 2.9018 | 400  | 0.7178          | 0.7123   | 0.7160    | 0.7123 | 0.6950 |
| 0.7133        | 3.2618 | 450  | 0.6932          | 0.71     | 0.7151    | 0.71   | 0.7117 |
| 0.7057        | 3.6255 | 500  | 0.7281          | 0.6986   | 0.7044    | 0.6986 | 0.6988 |
| 0.6831        | 3.9891 | 550  | 0.6745          | 0.7309   | 0.7296    | 0.7309 | 0.7195 |
| 0.6486        | 4.3491 | 600  | 0.6571          | 0.7295   | 0.7252    | 0.7295 | 0.7229 |
| 0.6378        | 4.7127 | 650  | 0.6701          | 0.7232   | 0.7217    | 0.7232 | 0.7223 |
| 0.6281        | 5.0727 | 700  | 0.6627          | 0.7386   | 0.7350    | 0.7386 | 0.7360 |
| 0.5938        | 5.4364 | 750  | 0.6814          | 0.7155   | 0.7229    | 0.7155 | 0.7181 |


### Framework versions

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