|
|
--- |
|
|
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: 0.0 |
|
|
- F1 Macro: 0.0 |
|
|
- Precision At 5: 0.2279 |
|
|
- Recall At 5: 0.0949 |
|
|
- Precision At 8: 0.1664 |
|
|
- Recall At 8: 0.1038 |
|
|
- Precision At 15: 0.1137 |
|
|
- Recall At 15: 0.1285 |
|
|
- Rare F1 Micro: 0.0 |
|
|
- Rare F1 Macro: 0.0 |
|
|
- Rare Precision: 0.0 |
|
|
- Rare Recall: 0.0 |
|
|
- Rare Precision At 5: 0.15 |
|
|
- Rare Recall At 5: 0.0645 |
|
|
- Rare Precision At 8: 0.1204 |
|
|
- Rare Recall At 8: 0.0788 |
|
|
- Rare Precision At 15: 0.0873 |
|
|
- Rare Recall At 15: 0.0997 |
|
|
- Not Rare F1 Micro: 0.5956 |
|
|
- Not Rare F1 Macro: 0.3733 |
|
|
- Not Rare Precision: 0.5956 |
|
|
- Not Rare Recall: 0.5956 |
|
|
- Not Rare Precision At 5: 0.0809 |
|
|
- Not Rare Recall At 5: 0.4044 |
|
|
- Not Rare Precision At 8: 0.0506 |
|
|
- Not Rare Recall At 8: 0.4044 |
|
|
- Not Rare Precision At 15: 0.0270 |
|
|
- Not Rare Recall At 15: 0.4044 |
|
|
- Loss: 0.1048 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:------:|:----:|:--------:|:--------:|:--------------:|:-----------:|:--------------:|:-----------:|:---------------:|:------------:|:-------------:|:-------------:|:--------------:|:-----------:|:-------------------:|:----------------:|:-------------------:|:----------------:|:--------------------:|:-----------------:|:-----------------:|:-----------------:|:------------------:|:---------------:|:-----------------------:|:--------------------:|:-----------------------:|:--------------------:|:------------------------:|:---------------------:|:---------------:| |
|
|
| 0.6384 | 1.0 | 18 | 0.0 | 0.0 | 0.0368 | 0.0087 | 0.0377 | 0.0174 | 0.0377 | 0.0324 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0294 | 0.0081 | 0.0267 | 0.0107 | 0.0275 | 0.0211 | 0.5956 | 0.3733 | 0.5956 | 0.5956 | 0.0809 | 0.4044 | 0.0506 | 0.4044 | 0.0270 | 0.4044 | 0.2291 | |
|
|
| 0.1265 | 2.0 | 36 | 0.0 | 0.0 | 0.0412 | 0.0096 | 0.0395 | 0.0166 | 0.0373 | 0.0303 | 0.0 | 0.0 | 0.0 | 0.0 | 0.025 | 0.0048 | 0.0276 | 0.0109 | 0.0284 | 0.0244 | 0.5956 | 0.3733 | 0.5956 | 0.5956 | 0.0809 | 0.4044 | 0.0506 | 0.4044 | 0.0270 | 0.4044 | 0.1216 | |
|
|
| 0.1092 | 3.0 | 54 | 0.0 | 0.0 | 0.1162 | 0.0391 | 0.1002 | 0.0595 | 0.0814 | 0.0890 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0603 | 0.0208 | 0.0579 | 0.0332 | 0.0564 | 0.0595 | 0.5956 | 0.3733 | 0.5956 | 0.5956 | 0.0809 | 0.4044 | 0.0506 | 0.4044 | 0.0270 | 0.4044 | 0.1069 | |
|
|
| 0.1033 | 3.7887 | 68 | 0.0 | 0.0 | 0.2279 | 0.0949 | 0.1664 | 0.1038 | 0.1137 | 0.1285 | 0.0 | 0.0 | 0.0 | 0.0 | 0.15 | 0.0645 | 0.1204 | 0.0788 | 0.0873 | 0.0997 | 0.5956 | 0.3733 | 0.5956 | 0.5956 | 0.0809 | 0.4044 | 0.0506 | 0.4044 | 0.0270 | 0.4044 | 0.1048 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
