|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Mistral-7B-v0.1_district-court-db |
|
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-v0.1_district-court-db |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0357 |
|
- Precision Micro: 0.8047 |
|
- Precision Macro: 0.6995 |
|
- Recall Micro: 0.8047 |
|
- Recall Macro: 0.6609 |
|
- F1 Micro: 0.8047 |
|
- F1 Macro: 0.6661 |
|
- Accuracy: 0.8047 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- training_steps: 725 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision Micro | Precision Macro | Recall Micro | Recall Macro | F1 Micro | F1 Macro | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------------:|:---------------:|:------------:|:------------:|:--------:|:--------:|:--------:| |
|
| 0.0886 | 0.08 | 50 | 0.1082 | 0.5774 | 0.3988 | 0.5774 | 0.3124 | 0.5774 | 0.3222 | 0.5774 | |
|
| 0.0572 | 0.16 | 100 | 0.0832 | 0.5877 | 0.4716 | 0.5877 | 0.3681 | 0.5877 | 0.3797 | 0.5877 | |
|
| 0.0496 | 0.24 | 150 | 0.0525 | 0.7311 | 0.5911 | 0.7311 | 0.5747 | 0.7311 | 0.5703 | 0.7311 | |
|
| 0.0541 | 0.32 | 200 | 0.0464 | 0.7566 | 0.6151 | 0.7566 | 0.5606 | 0.7566 | 0.5584 | 0.7566 | |
|
| 0.0481 | 0.4 | 250 | 0.0433 | 0.7811 | 0.6636 | 0.7811 | 0.6514 | 0.7811 | 0.6369 | 0.7811 | |
|
| 0.053 | 0.48 | 300 | 0.0452 | 0.7632 | 0.6936 | 0.7632 | 0.6461 | 0.7632 | 0.6338 | 0.7632 | |
|
| 0.0401 | 0.56 | 350 | 0.0399 | 0.7943 | 0.7381 | 0.7943 | 0.6604 | 0.7943 | 0.6697 | 0.7943 | |
|
| 0.0509 | 0.64 | 400 | 0.0393 | 0.8009 | 0.6546 | 0.8009 | 0.6612 | 0.8009 | 0.6501 | 0.8009 | |
|
| 0.0474 | 0.72 | 450 | 0.0401 | 0.8019 | 0.7255 | 0.8019 | 0.6927 | 0.8019 | 0.6865 | 0.8019 | |
|
| 0.045 | 0.79 | 500 | 0.0379 | 0.8009 | 0.7147 | 0.8009 | 0.7108 | 0.8009 | 0.6977 | 0.8009 | |
|
| 0.0335 | 0.87 | 550 | 0.0369 | 0.8151 | 0.7046 | 0.8151 | 0.7335 | 0.8151 | 0.7135 | 0.8151 | |
|
| 0.0429 | 0.95 | 600 | 0.0367 | 0.7962 | 0.7081 | 0.7962 | 0.6959 | 0.7962 | 0.6878 | 0.7962 | |
|
| 0.0253 | 1.03 | 650 | 0.0342 | 0.8255 | 0.7370 | 0.8255 | 0.6975 | 0.8255 | 0.7098 | 0.8255 | |
|
| 0.0311 | 1.11 | 700 | 0.0357 | 0.8047 | 0.6995 | 0.8047 | 0.6609 | 0.8047 | 0.6661 | 0.8047 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.1 |
