Mistral-MetaMath-camel_math
This model is a fine-tuned version of TheBloke/MetaMath-Mistral-7B-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.5238
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.3858 | 0.4 | 40 | 5.3966 |
| 5.1759 | 0.8 | 80 | 5.0450 |
| 4.5 | 1.2 | 120 | 4.7109 |
| 4.7549 | 1.6 | 160 | 4.5588 |
| 3.6274 | 2.0 | 200 | 4.5238 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0
Model tree for themanas021/Mistral-MetaMath-camel_math
Base model
meta-math/MetaMath-Mistral-7B
Quantized
TheBloke/MetaMath-Mistral-7B-GPTQ