metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: finn-ft
results: []
finn-ft
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: 1.3278
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 |
|---|---|---|---|
| 2.9652 | 0.96 | 18 | 1.8270 |
| 1.6099 | 1.97 | 37 | 1.4804 |
| 1.3935 | 2.99 | 56 | 1.3577 |
| 1.2729 | 4.0 | 75 | 1.3076 |
| 1.2847 | 4.96 | 93 | 1.2950 |
| 1.1729 | 5.97 | 112 | 1.2954 |
| 1.1351 | 6.99 | 131 | 1.3042 |
| 1.1054 | 8.0 | 150 | 1.3159 |
| 1.1406 | 8.96 | 168 | 1.3242 |
| 1.0143 | 9.6 | 180 | 1.3278 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2