|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: intfloat/multilingual-e5-large-instruct |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: e5_Eau_MultiLabel_Augmented_v1 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# e5_Eau_MultiLabel_Augmented_v1 |
|
|
|
|
|
This model is a fine-tuned version of [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1429 |
|
|
- F1 Weighted: 0.9465 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-----------:| |
|
|
| 0.8715 | 1.0 | 296 | 0.4957 | 0.7559 | |
|
|
| 0.4536 | 2.0 | 592 | 0.3266 | 0.8547 | |
|
|
| 0.3144 | 3.0 | 888 | 0.2843 | 0.8657 | |
|
|
| 0.2448 | 4.0 | 1184 | 0.2369 | 0.8989 | |
|
|
| 0.1999 | 5.0 | 1480 | 0.1980 | 0.9154 | |
|
|
| 0.1683 | 6.0 | 1776 | 0.1881 | 0.9245 | |
|
|
| 0.1452 | 7.0 | 2072 | 0.1763 | 0.9293 | |
|
|
| 0.1261 | 8.0 | 2368 | 0.1671 | 0.9326 | |
|
|
| 0.1098 | 9.0 | 2664 | 0.1557 | 0.9432 | |
|
|
| 0.0985 | 10.0 | 2960 | 0.1541 | 0.9430 | |
|
|
| 0.0899 | 11.0 | 3256 | 0.1508 | 0.9440 | |
|
|
| 0.083 | 12.0 | 3552 | 0.1429 | 0.9465 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.53.2 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.21.2 |
|
|
|
