commentGPT
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3868
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 |
---|---|---|---|
1.4682 | 0.9231 | 3 | 1.2723 |
1.2439 | 1.8462 | 6 | 1.2178 |
1.1142 | 2.7692 | 9 | 1.2088 |
0.773 | 4.0 | 13 | 1.2318 |
0.938 | 4.9231 | 16 | 1.2727 |
0.8381 | 5.8462 | 19 | 1.2875 |
0.7523 | 6.7692 | 22 | 1.3204 |
0.5255 | 8.0 | 26 | 1.3666 |
0.6488 | 8.9231 | 29 | 1.3856 |
0.465 | 9.2308 | 30 | 1.3868 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for Zenith1618/commentGPT
Base model
mistralai/Mistral-7B-Instruct-v0.2