metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: usermanualv2
results: []
usermanualv2
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: 1.1145
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 |
|---|---|---|---|
| 4.3547 | 0.92 | 3 | 3.8202 |
| 3.6459 | 1.85 | 6 | 3.1400 |
| 3.0157 | 2.77 | 9 | 2.6629 |
| 1.9263 | 4.0 | 13 | 2.2040 |
| 2.1832 | 4.92 | 16 | 1.9006 |
| 1.8458 | 5.85 | 19 | 1.6241 |
| 1.5672 | 6.77 | 22 | 1.4101 |
| 1.0098 | 8.0 | 26 | 1.1936 |
| 1.1993 | 8.92 | 29 | 1.1223 |
| 0.7821 | 9.23 | 30 | 1.1145 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2