metadata
library_name: peft
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- base_model:adapter:mistralai/Mistral-7B-v0.1
- transformers
pipeline_tag: text-generation
model-index:
- name: Mistral-7B-v0.1-IA3-MathReasoning1
results: []
Mistral-7B-v0.1-IA3-MathReasoning1
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4240
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: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 50
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4834 | 0.2667 | 100 | 0.6361 |
| 0.5032 | 0.5333 | 200 | 0.5080 |
| 0.4852 | 0.8 | 300 | 0.4864 |
| 0.468 | 1.0667 | 400 | 0.4705 |
| 0.4525 | 1.3333 | 500 | 0.4573 |
| 0.4355 | 1.6 | 600 | 0.4467 |
| 0.4218 | 1.8667 | 700 | 0.4381 |
| 0.4277 | 2.1333 | 800 | 0.4315 |
| 0.4126 | 2.4 | 900 | 0.4269 |
| 0.4132 | 2.6667 | 1000 | 0.4240 |
| 0.4222 | 2.9333 | 1100 | 0.4228 |
Framework versions
- PEFT 0.17.1
- Transformers 4.56.2
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1