distilgpt2-nepali / README.md
Sakonii's picture
update model card README.md
37204cc
|
raw
history blame
1.41 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: distilgpt2-nepali
    results: []

distilgpt2-nepali

This model is a fine-tuned version of Sakonii/distilgpt2-nepali on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.3749

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: 12
  • eval_batch_size: 12
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
3.7645 1.0 94395 3.6291
3.5857 2.0 188790 3.4442
3.505 3.0 283185 3.3749

Framework versions

  • Transformers 4.17.0
  • Pytorch 1.9.1
  • Datasets 2.0.0
  • Tokenizers 0.11.6