metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- unsloth
- generated_from_trainer
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
model-index:
- name: mistral-ViMMRC-Answer
results: []
mistral-ViMMRC-Answer
This model is a fine-tuned version of unsloth/mistral-7b-instruct-v0.2-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3510
- Accuracy: 0.7495
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
- ViMMRC train and test set
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 9.7542 | 0.3306 | 10 | 13.9251 |
| 1.028 | 0.6612 | 20 | 0.7210 |
| 0.7005 | 0.9917 | 30 | 0.4852 |
| 0.6566 | 1.3223 | 40 | 0.5006 |
| 0.6531 | 1.6529 | 50 | 0.5238 |
| 0.6723 | 1.9835 | 60 | 0.3989 |
| 0.6305 | 2.3140 | 70 | 0.3477 |
| 0.6254 | 2.6446 | 80 | 0.3510 |
| 0.6143 | 2.9752 | 90 | 0.3516 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1