shawgpt-finetuned-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: 1.9151
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 |
|---|---|---|---|
| 4.3289 | 0.9231 | 3 | 2.7883 |
| 2.4131 | 1.8462 | 6 | 1.6604 |
| 1.4061 | 2.7692 | 9 | 1.3530 |
| 0.8503 | 4.0 | 13 | 1.3318 |
| 1.0117 | 4.9231 | 16 | 1.3497 |
| 0.8582 | 5.8462 | 19 | 1.4099 |
| 0.716 | 6.7692 | 22 | 1.5376 |
| 0.457 | 8.0 | 26 | 1.6587 |
| 0.5083 | 8.9231 | 29 | 1.7113 |
| 0.4285 | 9.8462 | 32 | 1.8327 |
| 0.3857 | 10.7692 | 35 | 1.9170 |
| 0.0753 | 11.0769 | 36 | 1.9151 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.2
- Tokenizers 0.19.1
- Downloads last month
- 1
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for FrederikKlinkby/shawgpt-finetuned-lr0.002-wd0.01
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ