GPT2_no_function_67 / README.md
xiulinyang's picture
Upload folder using huggingface_hub
39e8814 verified
metadata
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: GPT2_no_function_67
    results: []

GPT2_no_function_67

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.7260
  • Accuracy: 0.3103

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: 128
  • eval_batch_size: 128
  • seed: 67
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10000
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
6.3673 1.0 4702 6.0093 0.2210
5.5122 2.0 9404 5.3627 0.2531
5.1637 3.0 14106 5.0803 0.2754
5.0001 4.0 18808 4.9437 0.2882
4.8699 5.0 23510 4.8652 0.2950
4.7738 6.0 28212 4.8127 0.3002
4.6966 7.0 32914 4.7762 0.3044
4.6296 8.0 37616 4.7499 0.3069
4.5712 9.0 42318 4.7333 0.3087
4.5227 10.0 47020 4.7260 0.3103

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.9.1+cu128
  • Datasets 4.1.1
  • Tokenizers 0.13.3