hindi_gpt2 / README.md
NebulaByte's picture
Update README.md
1f62b22
|
raw
history blame
2.12 kB
metadata
license: mit
base_model: gpt2
tags:
  - generated_from_trainer
model-index:
  - name: hindi_gpt2
    results: []
widget:
  - text: अपने अनुप्रयोग को पहुंचनीयता व्यायाम
  - text: जनतंत्र की सफलता केवल इस बात से नहीं हो सकती है कि हर
  - text: अगर इसके बाद भी वे फैसले पर कायम रहते हैं और
  - text: मामले का खुलासा होने के बाद
  - text: My name is Julien and I like to
  - text: My name is Thomas and my main
inference:
  parameters:
    max_length: 200

hindi_gpt2

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9187

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: 0.0005
  • train_batch_size: 40
  • eval_batch_size: 40
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 160
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 400
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
4.694 0.18 400 2.7361
2.3952 0.35 800 2.1608
2.1311 0.53 1200 2.0237
2.0282 0.71 1600 1.9518
1.9731 0.89 2000 1.9187

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.2
  • Tokenizers 0.13.3