metadata
library_name: transformers
license: mit
base_model: intfloat/multilingual-e5-large-instruct
tags:
- generated_from_trainer
model-index:
- name: e5_Eau_Multilabel_Topic_Sentiment
results: []
e5_Eau_Multilabel_Topic_Sentiment
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: 0.1566
- F1 Topic: 0.9104
- F1 Sentiment: 0.8933
- F1 Macro Avg: 0.9019
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Topic | F1 Sentiment | F1 Macro Avg |
|---|---|---|---|---|---|---|
| 0.5731 | 1.0 | 148 | 0.4031 | 0.4584 | 0.6075 | 0.5330 |
| 0.2812 | 2.0 | 296 | 0.1726 | 0.7873 | 0.8019 | 0.7946 |
| 0.1396 | 3.0 | 444 | 0.1214 | 0.8694 | 0.8576 | 0.8635 |
| 0.0982 | 4.0 | 592 | 0.1244 | 0.8886 | 0.8643 | 0.8765 |
| 0.0732 | 5.0 | 740 | 0.1311 | 0.9118 | 0.8850 | 0.8984 |
| 0.0508 | 6.0 | 888 | 0.1566 | 0.9104 | 0.8933 | 0.9019 |
Framework versions
- Transformers 4.53.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2