metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: agrobot-ft
results: []
agrobot-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: 0.6340
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 |
|---|---|---|---|
| 2.3654 | 1.0 | 55 | 1.7484 |
| 1.4862 | 2.0 | 110 | 1.4445 |
| 1.1414 | 3.0 | 165 | 1.2022 |
| 0.9024 | 4.0 | 220 | 0.9942 |
| 0.754 | 5.0 | 275 | 0.8629 |
| 0.669 | 6.0 | 330 | 0.7686 |
| 0.6318 | 7.0 | 385 | 0.7093 |
| 0.6093 | 8.0 | 440 | 0.6699 |
| 0.5952 | 9.0 | 495 | 0.6463 |
| 0.5859 | 10.0 | 550 | 0.6340 |
Framework versions
- PEFT 0.11.1
- Transformers 4.39.3
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2