gpt2_small_expandedbabyLM_5M_43

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

  • Loss: 3.3202

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: 43
  • 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
8.5971 1.0 255 6.2818
6.5929 2.0 510 4.9686
5.5723 3.0 765 4.4562
4.8384 4.0 1020 4.1974
4.6361 5.0 1275 4.0102
4.4927 6.0 1530 3.8702
4.3462 7.0 1785 3.7573
4.1438 8.0 2040 3.6666
4.0546 9.0 2295 3.5964
3.9827 10.0 2550 3.5370
3.8424 11.0 2805 3.4871
3.7629 12.0 3060 3.4416
3.7141 13.0 3315 3.4097
3.6457 14.0 3570 3.3824
3.5473 15.0 3825 3.3614
3.483 16.0 4080 3.3455
3.4248 17.0 4335 3.3265
3.3625 18.0 4590 3.3202
3.2092 19.0 4845 3.3202
3.16 20.0 5100 3.3262

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.11.0+cu130
  • Datasets 4.1.1
  • Tokenizers 0.13.3
Downloads last month
179
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support