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: 0.2357
- F1 Topic: 0.9099
- F1 Sentiment: 0.8779
- F1 Macro Avg: 0.8939
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 |
|---|---|---|---|---|---|---|
| 1.0863 | 1.0 | 148 | 0.8031 | 0.5733 | 0.6922 | 0.6328 |
| 0.5734 | 2.0 | 296 | 0.3777 | 0.8058 | 0.8242 | 0.8150 |
| 0.2858 | 3.0 | 444 | 0.2523 | 0.8957 | 0.8652 | 0.8805 |
| 0.2023 | 4.0 | 592 | 0.2357 | 0.9099 | 0.8779 | 0.8939 |
Framework versions
- Transformers 4.53.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2