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 an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4187
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: 0.00015
- 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: 16
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.6052 | 0.9231 | 3 | 4.0324 |
| 4.1734 | 1.8462 | 6 | 3.6130 |
| 3.6811 | 2.7692 | 9 | 3.2101 |
| 2.429 | 4.0 | 13 | 2.7565 |
| 2.8731 | 4.9231 | 16 | 2.4814 |
| 2.5127 | 5.8462 | 19 | 2.2241 |
| 2.2188 | 6.7692 | 22 | 2.0188 |
| 1.4844 | 8.0 | 26 | 1.7915 |
| 1.7939 | 8.9231 | 29 | 1.6741 |
| 1.6437 | 9.8462 | 32 | 1.5920 |
| 1.5781 | 10.7692 | 35 | 1.5269 |
| 1.1047 | 12.0 | 39 | 1.4688 |
| 1.4528 | 12.9231 | 42 | 1.4402 |
| 1.3984 | 13.8462 | 45 | 1.4243 |
| 1.0591 | 14.7692 | 48 | 1.4187 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.2
- Tokenizers 0.19.1