eli5_distilgpt / README.md
gremlin97's picture
Upload tokenizer
044aad4 verified
|
raw
history blame
1.43 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - eli5_category
base_model: distilbert/distilgpt2
model-index:
  - name: eli5_distilgpt
    results: []

eli5_distilgpt

This model is a fine-tuned version of distilbert/distilgpt2 on the eli5_category dataset. It achieves the following results on the evaluation set:

  • Loss: 3.8251

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
3.9573 1.0 1323 3.8356
3.8591 2.0 2646 3.8269
3.8181 3.0 3969 3.8251

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2