README.md

metadata

language:
  - br
license: apache-2.0
tags:
  - generated_from_trainer
base_model: distilbert/distilgpt2
datasets:
  - gweltou/text-br
  - gweltou/wikipedia-br-20240325
widget:
  - text: E-kichen Plougerne
  - text: Emañ Katell
  - text: Yann a oa o
model-index:
  - name: tiny-gpt2-br
    results: []

tiny-gpt2-br

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

• eval_loss: 3.2672
• eval_runtime: 134.3513
• eval_samples_per_second: 259.023
• eval_steps_per_second: 16.189
• epoch: 3.42
• step: 134000

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: 0.0008
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 4

Framework versions

• Transformers 4.39.1
• Pytorch 2.0.1+cu117
• Datasets 2.18.0
• Tokenizers 0.15.2