Hugging Face's logo

jaki-1
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
shawgpt-ft / README.md
jaki-1's picture
jaki-1
jaki-1/shawgpt-ft
387698f verified
preview code
|
raw
history blame
No virus
1.97 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
  - name: shawgpt-ft
    results: []

shawgpt-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: 2.7929

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
3.921 0.9892 69 3.1268
2.7734 1.9928 139 2.7793
2.5538 2.9964 209 2.7026
2.4648 4.0 279 2.7008
2.4164 4.9892 348 2.7113
2.3266 5.9928 418 2.6972
2.2489 6.9964 488 2.7195
2.1813 8.0 558 2.7573
2.2002 8.9892 627 2.7826
2.0955 9.8925 690 2.7929

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1