shawgpt-ft / README.md
OpOp1's picture
OpOp1/TI-GPT-735M
1f8beb6 verified
metadata
license: cc-by-nc-4.0
library_name: peft
tags:
  - generated_from_trainer
base_model: MBZUAI/LaMini-GPT-774M
model-index:
  - name: shawgpt-ft
    results: []

shawgpt-ft

This model is a fine-tuned version of MBZUAI/LaMini-GPT-774M on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4635

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
3.5991 1.0 5 3.4306
3.3522 2.0 10 3.0302
2.9388 3.0 15 2.6452
2.621 4.0 20 2.3555
2.3501 5.0 25 2.1047
2.1243 6.0 30 1.8846
1.9309 7.0 35 1.6957
1.7786 8.0 40 1.5726
1.6718 9.0 45 1.4961
1.6283 10.0 50 1.4635

Framework versions

  • PEFT 0.10.0
  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2