metadata
library_name: transformers
license: mit
base_model: intfloat/multilingual-e5-large-instruct
tags:
- generated_from_trainer
model-index:
- name: e5_Eau_MultiLabel_Simple_v2
results: []
e5_Eau_MultiLabel_Simple_v2
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: 0.2521
- F1 Weighted: 0.9002
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: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Weighted |
|---|---|---|---|---|
| 1.0079 | 1.0 | 148 | 0.7728 | 0.6280 |
| 0.7019 | 2.0 | 296 | 0.4871 | 0.7514 |
| 0.4819 | 3.0 | 444 | 0.3662 | 0.8241 |
| 0.3789 | 4.0 | 592 | 0.3188 | 0.8487 |
| 0.3105 | 5.0 | 740 | 0.2885 | 0.8662 |
| 0.2679 | 6.0 | 888 | 0.2747 | 0.8797 |
| 0.23 | 7.0 | 1036 | 0.2605 | 0.8822 |
| 0.2067 | 8.0 | 1184 | 0.2539 | 0.8880 |
| 0.1868 | 9.0 | 1332 | 0.2489 | 0.8940 |
| 0.1676 | 10.0 | 1480 | 0.2507 | 0.8980 |
| 0.1545 | 11.0 | 1628 | 0.2518 | 0.9008 |
| 0.1429 | 12.0 | 1776 | 0.2521 | 0.9002 |
Framework versions
- Transformers 4.53.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2