shawgpt-ft-lr0.002-wd0.01
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: 1.7489
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: 0.002
- 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: 12
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.3981 | 0.9231 | 3 | 2.9896 |
2.6737 | 1.8462 | 6 | 1.8393 |
1.4933 | 2.7692 | 9 | 1.3595 |
0.8827 | 4.0 | 13 | 1.3026 |
1.0672 | 4.9231 | 16 | 1.3407 |
0.933 | 5.8462 | 19 | 1.3902 |
0.819 | 6.7692 | 22 | 1.4243 |
0.5625 | 8.0 | 26 | 1.5474 |
0.6605 | 8.9231 | 29 | 1.6098 |
0.5878 | 9.8462 | 32 | 1.6611 |
0.5452 | 10.7692 | 35 | 1.7397 |
0.0983 | 11.0769 | 36 | 1.7489 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 4
Model tree for FrederikKlinkby/shawgpt-ft-lr0.002-wd0.01
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ