Prajapat's picture
Prajapat/gpt2-lora-instruction
3b54b56 verified
metadata
library_name: peft
license: mit
base_model: gpt2
tags:
  - base_model:adapter:gpt2
  - lora
  - transformers
pipeline_tag: text-generation
model-index:
  - name: gpt2_lora_instruction
    results: []

gpt2_lora_instruction

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: nan

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: 0.0003
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.577 1.0 10530 1.5139
1.5405 2.0 21060 1.4920
1.4831 3.0 31590 1.4804
1.5491 4.0 42120 1.4737
0.0 5.0 52650 nan
0.0 6.0 63180 nan
0.0 7.0 73710 nan
0.0 8.0 84240 nan
0.0 9.0 94770 nan
0.0 10.0 105300 nan

Framework versions

  • PEFT 0.17.1
  • Transformers 4.57.1
  • Pytorch 2.8.0+cu126
  • Datasets 4.4.2
  • Tokenizers 0.22.1