shawgpt-ft / README.md
jitendra89's picture
jitendra89/llm_qlora
904acb7 verified
|
raw
history blame
1.92 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 an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.2317

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

Training results

Training Loss Epoch Step Validation Loss
4.6482 0.92 3 4.2317
4.6249 1.85 6 4.2317
4.6434 2.77 9 4.2317
3.4776 4.0 13 4.2317
4.6526 4.92 16 4.2317
4.6328 5.85 19 4.2317
4.6468 6.77 22 4.2317
3.4559 8.0 26 4.2317
4.6135 8.92 29 4.2317
3.0683 9.23 30 4.2317

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2