gpt2_small_expandedbabyLM_5M_44

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

  • Loss: 3.3213

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: 0.0001
  • train_batch_size: 256
  • eval_batch_size: 256
  • seed: 44
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 4000
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss
8.6295 1.0 255 6.2873
6.5783 2.0 510 4.9779
5.5802 3.0 765 4.4616
4.8375 4.0 1020 4.2023
4.6412 5.0 1275 4.0124
4.4818 6.0 1530 3.8725
4.3587 7.0 1785 3.7651
4.1461 8.0 2040 3.6660
4.0495 9.0 2295 3.5963
3.978 10.0 2550 3.5352
3.8398 11.0 2805 3.4862
3.7635 12.0 3060 3.4428
3.7116 13.0 3315 3.4119
3.652 14.0 3570 3.3824
3.5468 15.0 3825 3.3630
3.4833 16.0 4080 3.3462
3.4251 17.0 4335 3.3264
3.3552 18.0 4590 3.3213
3.2107 19.0 4845 3.3213
3.1577 20.0 5100 3.3263

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.11.0+cu130
  • Datasets 4.1.1
  • Tokenizers 0.13.3
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support