|
--- |
|
base_model: mistralai/Mistral-7B-Instruct-v0.1 |
|
datasets: |
|
- krishnapal2308/SROIE |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- trl |
|
- sft |
|
model-index: |
|
- name: mistral-instruct-7b-finetuned-sroie |
|
results: [] |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/krishnapal-exl/huggingface/runs/cu7whasc) |
|
# mistral-instruct-7b-finetuned-sroie |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7668 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_steps: 50 |
|
- training_steps: 120 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.4458 | 0.4848 | 20 | 1.3313 | |
|
| 1.1796 | 0.9697 | 40 | 1.1143 | |
|
| 1.0555 | 1.4545 | 60 | 0.9733 | |
|
| 0.9514 | 1.9394 | 80 | 0.8829 | |
|
| 0.8599 | 2.4242 | 100 | 0.8150 | |
|
| 0.857 | 2.9091 | 120 | 0.7668 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
