JuanjoLopez19's picture
Training with 90/10 dataset, 5 epochs, 2 Batch Size
505cd38 verified
|
raw
history blame
1.68 kB
---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: Mistral-7B-Instruct-v0.2-finetune-SWE_90_10
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-v0.2-finetune-SWE_90_10
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1233
## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 5
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.4939 | 0.9995 | 1847 | 0.9488 |
| 0.7585 | 1.9989 | 3694 | 0.8857 |
| 0.4374 | 2.9984 | 5541 | 0.9555 |
| 0.2946 | 3.9978 | 7388 | 1.0790 |
| 0.2287 | 4.9973 | 9235 | 1.1233 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1