metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
datasets:
- conala
model-index:
- name: pythonexcel
results: []
pythonexcel
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the conala dataset. It achieves the following results on the evaluation set:
- Loss: 2.8689
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 |
|---|---|---|---|
| 2.5879 | 0.99 | 148 | 2.2851 |
| 2.1391 | 2.0 | 297 | 2.2367 |
| 1.965 | 3.0 | 446 | 2.2578 |
| 1.8145 | 4.0 | 595 | 2.3154 |
| 1.6989 | 4.99 | 743 | 2.3626 |
| 1.5826 | 6.0 | 892 | 2.4436 |
| 1.4981 | 7.0 | 1041 | 2.5986 |
| 1.4253 | 8.0 | 1190 | 2.6764 |
| 1.3716 | 8.99 | 1338 | 2.7948 |
| 1.3224 | 9.95 | 1480 | 2.8689 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2