metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: balagpt-ft2
results: []
balagpt-ft2
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: 0.5664
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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 |
|---|---|---|---|
| 2.092 | 0.92 | 9 | 1.4516 |
| 1.0312 | 1.95 | 19 | 0.7849 |
| 0.5407 | 2.97 | 29 | 0.5922 |
| 0.4035 | 4.0 | 39 | 0.5433 |
| 0.3684 | 4.92 | 48 | 0.5227 |
| 0.2708 | 5.95 | 58 | 0.5200 |
| 0.2348 | 6.97 | 68 | 0.5358 |
| 0.2091 | 8.0 | 78 | 0.5485 |
| 0.2125 | 8.92 | 87 | 0.5655 |
| 0.1607 | 9.23 | 90 | 0.5664 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2