metadata
library_name: transformers
license: mit
base_model: intfloat/multilingual-e5-large-instruct
tags:
- generated_from_trainer
model-index:
- name: e5_Dechets_MultiLabel_07082025
results: []
e5_Dechets_MultiLabel_07082025
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: 0.2103
- F1 Weighted: 0.9299
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 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 |
|---|---|---|---|---|
| 0.9037 | 1.0 | 180 | 0.5881 | 0.7452 |
| 0.5128 | 2.0 | 360 | 0.3669 | 0.8503 |
| 0.3466 | 3.0 | 540 | 0.3095 | 0.8792 |
| 0.2719 | 4.0 | 720 | 0.2777 | 0.8974 |
| 0.2186 | 5.0 | 900 | 0.2298 | 0.9143 |
| 0.1839 | 6.0 | 1080 | 0.2198 | 0.9188 |
| 0.1587 | 7.0 | 1260 | 0.2159 | 0.9219 |
| 0.1343 | 8.0 | 1440 | 0.2041 | 0.9278 |
| 0.117 | 9.0 | 1620 | 0.2101 | 0.9261 |
| 0.1037 | 10.0 | 1800 | 0.1985 | 0.9273 |
| 0.095 | 11.0 | 1980 | 0.2103 | 0.9299 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4