AnaSight
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: 1.6849
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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.6807 | 0.84 | 4 | 2.8842 |
| 2.3898 | 1.89 | 9 | 2.3594 |
| 2.025 | 2.95 | 14 | 2.0735 |
| 1.8054 | 4.0 | 19 | 1.9137 |
| 2.0621 | 4.84 | 23 | 1.8379 |
| 1.5615 | 5.89 | 28 | 1.7658 |
| 1.4873 | 6.95 | 33 | 1.7154 |
| 1.4352 | 8.0 | 38 | 1.6883 |
| 1.5129 | 8.42 | 40 | 1.6849 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1
Model tree for anaselgourch/AnaSight
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ