Edit model card

gpt2-large-lora-2.95M-snli-model1

This model is a fine-tuned version of openai-community/gpt2-large on the snli dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3263
  • Accuracy: 0.8769

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: 128
  • eval_batch_size: 128
  • seed: 26
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.4349 1.0 4292 0.3539 0.8661
0.4061 2.0 8584 0.3339 0.8745
0.3941 3.0 12876 0.3263 0.8769

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
2
Safetensors
Model size
774M params
Tensor type
F32
·
Inference API
This model can be loaded on Inference API (serverless).

Finetuned from

Dataset used to train varun-v-rao/gpt2-large-lora-2.95M-snli-model1

Evaluation results