---
library_name: transformers
license: mit
base_model: intfloat/multilingual-e5-large-instruct
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: e5_Sentiment_EC_v2
  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. -->

# e5_Sentiment_EC_v2

This model is a fine-tuned version of [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7983
- Accuracy: 0.9264
- F1: 0.9272

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.9261        | 1.0   | 60   | 0.4343          | 0.8738   | 0.8831 |
| 0.4464        | 2.0   | 120  | 0.5634          | 0.8780   | 0.8798 |
| 0.3124        | 3.0   | 180  | 0.4483          | 0.8833   | 0.8886 |
| 0.1974        | 4.0   | 240  | 0.6330          | 0.9169   | 0.9166 |
| 0.0894        | 5.0   | 300  | 0.5516          | 0.9317   | 0.9322 |
| 0.0702        | 6.0   | 360  | 0.5297          | 0.9338   | 0.9343 |
| 0.0359        | 7.0   | 420  | 0.7433          | 0.9338   | 0.9327 |
| 0.0269        | 8.0   | 480  | 0.7983          | 0.9264   | 0.9272 |


### Framework versions

- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1