Samaksh Khatri
update model card README.md
71adff2
|
raw
history blame
1.99 kB
metadata
license: mit
base_model: gpt2-medium
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: gmra_model_gpt2-medium_14082023T134929
    results: []

gmra_model_gpt2-medium_14082023T134929

This model is a fine-tuned version of gpt2-medium on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3831
  • Accuracy: 0.9438

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 284 0.2626 0.9069
0.3464 2.0 568 0.2263 0.9262
0.3464 3.0 852 0.2545 0.9394
0.1022 4.0 1137 0.2577 0.9464
0.1022 5.0 1421 0.3485 0.9420
0.0292 6.0 1705 0.3445 0.9429
0.0292 7.0 1989 0.3127 0.9464
0.0125 8.0 2274 0.4068 0.9411
0.0085 9.0 2558 0.3853 0.9438
0.0085 9.99 2840 0.3831 0.9438

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3