results
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7839
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: 20
- eval_batch_size: 20
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 80
- 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 |
|---|---|---|---|
| 2.1649 | 1.0 | 1 | 4.3052 |
| 2.1595 | 2.0 | 2 | 3.9177 |
| 1.9661 | 3.0 | 3 | 3.1663 |
| 1.5727 | 4.0 | 4 | 2.6769 |
| 1.3371 | 5.0 | 5 | 2.4213 |
| 1.2116 | 6.0 | 6 | 2.2232 |
| 1.1114 | 7.0 | 7 | 2.0560 |
| 1.0296 | 8.0 | 8 | 1.9239 |
| 0.9679 | 9.0 | 9 | 1.8329 |
| 0.9227 | 10.0 | 10 | 1.7839 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.0.1+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for rejozacharia/results
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ