shawgpt-ft
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9092
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: 4
- eval_batch_size: 4
- 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: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.5935 | 0.9231 | 3 | 3.9622 |
4.048 | 1.8462 | 6 | 3.4378 |
3.479 | 2.7692 | 9 | 2.9948 |
2.2744 | 4.0 | 13 | 2.5835 |
2.7058 | 4.9231 | 16 | 2.3527 |
2.409 | 5.8462 | 19 | 2.1755 |
2.2017 | 6.7692 | 22 | 2.0422 |
1.5811 | 8.0 | 26 | 1.9963 |
2.0479 | 8.9231 | 29 | 1.9212 |
1.4017 | 9.2308 | 30 | 1.9092 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.1.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for anvarazizov/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
Adapter
this model