metadata
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: shawgpt-ft
results: []
shawgpt-ft
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: 2.1086
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 |
|---|---|---|---|
| 5.2587 | 1.0 | 9 | 4.5854 |
| 4.3895 | 2.0 | 18 | 3.7220 |
| 3.4806 | 3.0 | 27 | 2.9834 |
| 2.8652 | 4.0 | 36 | 2.6969 |
| 2.4777 | 5.0 | 45 | 2.3747 |
| 2.2046 | 6.0 | 54 | 2.1974 |
| 2.0328 | 7.0 | 63 | 2.1851 |
| 1.901 | 8.0 | 72 | 2.1169 |
| 1.8406 | 9.0 | 81 | 2.1077 |
| 1.837 | 10.0 | 90 | 2.1086 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1