GPT2-705M

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

  • Loss: 3.3542

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: 0.00025
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
6.7388 1.0 3 6.6745
7.7712 2.0 6 6.9355
5.7851 3.0 9 6.0090
4.8315 4.0 12 5.7252
4.7133 5.0 15 5.2462
4.7276 6.0 18 4.9371
4.2828 7.0 21 4.8806
4.3069 8.0 24 4.4319
4.1875 9.0 27 4.2952
3.8318 10.0 30 4.1134
3.6746 11.0 33 3.9505
3.5241 12.0 36 3.7828
3.2439 13.0 39 3.7290
3.2954 14.0 42 3.5655
2.9475 15.0 45 3.4805
2.9343 16.0 48 3.5263
2.8517 17.0 51 3.4318
2.5458 18.0 54 3.3942
2.4846 19.0 57 3.3714
2.5766 20.0 60 3.3542

Framework versions

  • Transformers 4.39.1
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0
Downloads last month
1
Safetensors
Model size
0.7B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support