|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: mistralai/Mistral-7B-Instruct-v0.3 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify |
|
|
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. --> |
|
|
|
|
|
# mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify |
|
|
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- F1 Micro: 0.0005 |
|
|
- F1 Macro: 0.0000 |
|
|
- Precision At 5: 0.2847 |
|
|
- Recall At 5: 0.0664 |
|
|
- Precision At 8: 0.2542 |
|
|
- Recall At 8: 0.0910 |
|
|
- Precision At 15: 0.1926 |
|
|
- Recall At 15: 0.1252 |
|
|
- Rare F1 Micro: 0.0 |
|
|
- Rare F1 Macro: 0.0 |
|
|
- Rare Precision: 0.0 |
|
|
- Rare Recall: 0.0 |
|
|
- Rare Precision At 5: 0.0263 |
|
|
- Rare Recall At 5: 0.0069 |
|
|
- Rare Precision At 8: 0.0267 |
|
|
- Rare Recall At 8: 0.0118 |
|
|
- Rare Precision At 15: 0.0257 |
|
|
- Rare Recall At 15: 0.0219 |
|
|
- Not Rare F1 Micro: 0.0015 |
|
|
- Not Rare F1 Macro: 0.0003 |
|
|
- Not Rare Precision: 0.2576 |
|
|
- Not Rare Recall: 0.0007 |
|
|
- Not Rare Precision At 5: 0.2847 |
|
|
- Not Rare Recall At 5: 0.1756 |
|
|
- Not Rare Precision At 8: 0.2542 |
|
|
- Not Rare Recall At 8: 0.2401 |
|
|
- Not Rare Precision At 15: 0.1926 |
|
|
- Not Rare Recall At 15: 0.3324 |
|
|
- Loss: 0.0170 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Use 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_steps: 500 |
|
|
- num_epochs: 4 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | F1 Micro | F1 Macro | Precision At 5 | Recall At 5 | Precision At 8 | Recall At 8 | Precision At 15 | Recall At 15 | Rare F1 Micro | Rare F1 Macro | Rare Precision | Rare Recall | Rare Precision At 5 | Rare Recall At 5 | Rare Precision At 8 | Rare Recall At 8 | Rare Precision At 15 | Rare Recall At 15 | Not Rare F1 Micro | Not Rare F1 Macro | Not Rare Precision | Not Rare Recall | Not Rare Precision At 5 | Not Rare Recall At 5 | Not Rare Precision At 8 | Not Rare Recall At 8 | Not Rare Precision At 15 | Not Rare Recall At 15 | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:--------:|:--------:|:--------------:|:-----------:|:--------------:|:-----------:|:---------------:|:------------:|:-------------:|:-------------:|:--------------:|:-----------:|:-------------------:|:----------------:|:-------------------:|:----------------:|:--------------------:|:-----------------:|:-----------------:|:-----------------:|:------------------:|:---------------:|:-----------------------:|:--------------------:|:-----------------------:|:--------------------:|:------------------------:|:---------------------:|:---------------:| |
|
|
| 0.0229 | 0.9981 | 262 | 0.0 | 0.0 | 0.2769 | 0.0644 | 0.2472 | 0.0880 | 0.1883 | 0.1226 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0078 | 0.0025 | 0.0075 | 0.0040 | 0.0070 | 0.0065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2771 | 0.1707 | 0.2473 | 0.2341 | 0.1888 | 0.3243 | 0.0209 | |
|
|
| 0.0181 | 1.9981 | 524 | 0.0 | 0.0 | 0.2775 | 0.0651 | 0.2542 | 0.0910 | 0.1934 | 0.1270 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0295 | 0.0091 | 0.0251 | 0.0128 | 0.0230 | 0.0214 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2774 | 0.1715 | 0.2542 | 0.2401 | 0.1933 | 0.3366 | 0.0170 | |
|
|
| 0.0176 | 2.9981 | 786 | 0.0005 | 0.0000 | 0.2844 | 0.0665 | 0.2542 | 0.0910 | 0.1908 | 0.1227 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0282 | 0.0084 | 0.0246 | 0.0118 | 0.0273 | 0.0233 | 0.0013 | 0.0003 | 0.2830 | 0.0007 | 0.2844 | 0.1755 | 0.2542 | 0.2401 | 0.1908 | 0.3230 | 0.0170 | |
|
|
| 0.0167 | 3.9981 | 1048 | 0.0005 | 0.0000 | 0.2847 | 0.0664 | 0.2542 | 0.0910 | 0.1926 | 0.1252 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0263 | 0.0069 | 0.0267 | 0.0118 | 0.0257 | 0.0219 | 0.0015 | 0.0003 | 0.2576 | 0.0007 | 0.2847 | 0.1756 | 0.2542 | 0.2401 | 0.1926 | 0.3324 | 0.0170 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
