metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: LLM
results: []
LLM
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: 0.1231
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 |
|---|---|---|---|
| 2.052 | 0.92 | 6 | 1.5328 |
| 1.1672 | 2.0 | 13 | 0.9510 |
| 0.7973 | 2.92 | 19 | 0.4888 |
| 0.2867 | 4.0 | 26 | 0.1823 |
| 0.1727 | 4.92 | 32 | 0.1506 |
| 0.1301 | 6.0 | 39 | 0.1380 |
| 0.1382 | 6.92 | 45 | 0.1286 |
| 0.1099 | 8.0 | 52 | 0.1241 |
| 0.1245 | 8.92 | 58 | 0.1232 |
| 0.0877 | 9.23 | 60 | 0.1231 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2