Hugging Face's logo

Harshatheeswar
/
gpt2-scratch

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
gpt2-scratch / README.md
Harshatheeswar's picture
Harshatheeswar
End of training
3ab89b4 verified
preview code
|
raw
history blame
1.39 kB
metadata
library_name: transformers
base_model: Harshatheeswar/gpt2-scratch
tags:
  - generated_from_trainer
model-index:
  - name: gpt2-scratch
    results: []

gpt2-scratch

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

  • Loss: 4.2516

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
4.3012 1.0 1390 4.2516

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Tokenizers 0.19.1