metadata
library_name: transformers
license: mit
base_model: intfloat/multilingual-e5-large-instruct
tags:
- generated_from_trainer
model-index:
- name: e5_Dechets_MultiLabel_08092025
results: []
e5_Dechets_MultiLabel_08092025
This model is a fine-tuned version of intfloat/multilingual-e5-large-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1811
- F1 Weighted: 0.9499
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: 5e-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Weighted |
|---|---|---|---|---|
| 0.8583 | 1.0 | 199 | 0.5295 | 0.7662 |
| 0.4704 | 2.0 | 398 | 0.3538 | 0.8660 |
| 0.3289 | 3.0 | 597 | 0.2997 | 0.8879 |
| 0.2543 | 4.0 | 796 | 0.2687 | 0.9014 |
| 0.2075 | 5.0 | 995 | 0.2480 | 0.9182 |
| 0.1755 | 6.0 | 1194 | 0.2326 | 0.9248 |
| 0.1486 | 7.0 | 1393 | 0.2227 | 0.9290 |
| 0.1285 | 8.0 | 1592 | 0.2051 | 0.9391 |
| 0.1114 | 9.0 | 1791 | 0.1907 | 0.9434 |
| 0.1007 | 10.0 | 1990 | 0.1889 | 0.9459 |
| 0.0896 | 11.0 | 2189 | 0.1811 | 0.9499 |
Framework versions
- Transformers 4.56.0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0