metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: neural-matia-ft
results: []
neural-matia-ft
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: 0.6516
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 |
|---|---|---|---|
| 3.9004 | 0.89 | 6 | 3.0020 |
| 2.3511 | 1.93 | 13 | 1.9686 |
| 1.4935 | 2.96 | 20 | 1.1307 |
| 0.9547 | 4.0 | 27 | 0.8176 |
| 0.8782 | 4.89 | 33 | 0.7137 |
| 0.6879 | 5.93 | 40 | 0.6794 |
| 0.6661 | 6.96 | 47 | 0.6609 |
| 0.6421 | 8.0 | 54 | 0.6534 |
| 0.6662 | 8.89 | 60 | 0.6516 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2