metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
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: 1.8250
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 |
|---|---|---|---|
| 4.592 | 0.92 | 3 | 3.9556 |
| 4.0381 | 1.85 | 6 | 3.4300 |
| 3.4595 | 2.77 | 9 | 2.9801 |
| 2.2522 | 4.0 | 13 | 2.5503 |
| 2.6555 | 4.92 | 16 | 2.2883 |
| 2.3303 | 5.85 | 19 | 2.1013 |
| 2.099 | 6.77 | 22 | 1.9488 |
| 1.4765 | 8.0 | 26 | 1.8773 |
| 1.9247 | 8.92 | 29 | 1.8372 |
| 1.3414 | 9.23 | 30 | 1.8250 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2