metadata
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: ashishgpt-ft
results: []
ashishgpt-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: 3.4594
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 |
|---|---|---|---|
| 5.2503 | 0.96 | 6 | 4.7676 |
| 4.7324 | 1.92 | 12 | 4.3738 |
| 4.4128 | 2.88 | 18 | 4.1228 |
| 3.5306 | 4.0 | 25 | 3.9499 |
| 4.0066 | 4.96 | 31 | 3.8357 |
| 3.8713 | 5.92 | 37 | 3.7406 |
| 3.8204 | 6.88 | 43 | 3.6348 |
| 3.1281 | 8.0 | 50 | 3.5377 |
| 3.5644 | 8.96 | 56 | 3.4754 |
| 3.1051 | 9.6 | 60 | 3.4594 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1