bigbench_entailedpolarity-gpt2

This model is a fine-tuned version of gpt2 on the bigbench dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0213
  • Accuracy: 0.9167

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 24 0.5201 0.875
No log 2.0 48 0.3512 0.875
No log 3.0 72 0.4245 0.8333
No log 4.0 96 0.3220 0.9167
No log 5.0 120 0.3962 0.875
No log 6.0 144 0.5551 0.875
No log 7.0 168 0.8597 0.875
No log 8.0 192 0.4610 0.9583
No log 9.0 216 0.9003 0.9167
No log 10.0 240 0.8778 0.9167
No log 11.0 264 0.9036 0.9167
No log 12.0 288 0.9188 0.9167
No log 13.0 312 1.0192 0.9167
No log 14.0 336 0.9984 0.9167
No log 15.0 360 0.9718 0.9167
No log 16.0 384 0.9882 0.9167
No log 17.0 408 1.0189 0.9167
No log 18.0 432 1.0210 0.9167
No log 19.0 456 1.0211 0.9167
No log 20.0 480 1.0213 0.9167

Framework versions

  • Transformers 4.35.2
  • Pytorch 1.10.1+cu102
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
16
Safetensors
Model size
124M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for kennethge123/bigbench_entailedpolarity-gpt2

Finetuned
(1264)
this model

Dataset used to train kennethge123/bigbench_entailedpolarity-gpt2

Evaluation results