PLN_TS / README.md
joaohonorato's picture
End of training
93feedd verified
|
raw
history blame
2 kB
metadata
license: mit
base_model: openai-community/gpt2-medium
tags:
  - generated_from_trainer
model-index:
  - name: PLN_TS
    results: []

PLN_TS

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

  • Loss: 10.7341

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: 0.002
  • 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: 15

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 91 4.6308
No log 2.0 182 5.1050
No log 3.0 273 5.5102
No log 4.0 364 6.2532
No log 5.0 455 6.6069
1.1628 6.0 546 7.0238
1.1628 7.0 637 7.1553
1.1628 8.0 728 7.7253
1.1628 9.0 819 8.2397
1.1628 10.0 910 8.9225
0.1611 11.0 1001 9.3999
0.1611 12.0 1092 9.8062
0.1611 13.0 1183 10.1804
0.1611 14.0 1274 10.5743
0.1611 15.0 1365 10.7341

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1