metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: Mistral-7B-Instruct-v0.2-GPTQ_retrained_network_corpus
results: []
Mistral-7B-Instruct-v0.2-GPTQ_retrained_network_corpus
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: 2.2183
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 |
|---|---|---|---|
| 2.2041 | 1.0 | 28 | 2.2674 |
| 1.9644 | 2.0 | 56 | 2.2183 |
| 1.7637 | 3.0 | 84 | 2.2315 |
| 1.5934 | 4.0 | 112 | 2.2831 |
| 1.4509 | 5.0 | 140 | 2.3071 |
| 1.3409 | 6.0 | 168 | 2.4755 |
| 1.2542 | 7.0 | 196 | 2.4905 |
| 1.179 | 8.0 | 224 | 2.6153 |
| 1.1211 | 9.0 | 252 | 2.6870 |
| 1.0801 | 10.0 | 280 | 2.7418 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1