s444465/projekt-glebokie
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
7ce408fb11
projekt-glebokie/models/gpt2
History
Andrzej Preibisz a5fb14928c GPT-2
2023-02-12 20:03:40 +01:00
..
all_results.json GPT-2 2023-02-12 20:03:40 +01:00
config.json GPT-2 2023-02-12 20:03:40 +01:00
eval_results.json GPT-2 2023-02-12 20:03:40 +01:00
merges.txt GPT-2 2023-02-12 20:03:40 +01:00
predict_results_None.txt GPT-2 2023-02-12 20:03:40 +01:00
README.md GPT-2 2023-02-12 20:03:40 +01:00
special_tokens_map.json GPT-2 2023-02-12 20:03:40 +01:00
tokenizer_config.json GPT-2 2023-02-12 20:03:40 +01:00
tokenizer.json GPT-2 2023-02-12 20:03:40 +01:00
train_results.json GPT-2 2023-02-12 20:03:40 +01:00
trainer_state.json GPT-2 2023-02-12 20:03:40 +01:00
training_args.bin GPT-2 2023-02-12 20:03:40 +01:00
vocab.json GPT-2 2023-02-12 20:03:40 +01:00

README.md

license tags metrics model-index
mit
generated_from_trainer
accuracy
name results
gpt2

gpt2

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

  • Loss: 0.2178
  • Accuracy: 0.9231

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: 24
  • eval_batch_size: 24
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Framework versions

  • Transformers 4.26.1
  • Pytorch 1.13.1+cu116
  • Datasets 2.9.0
  • Tokenizers 0.13.2