Edit model card

roberta-base-fp-sick

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

  • Loss: 0.3257
  • Accuracy: 0.8788

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: 64
  • eval_batch_size: 32
  • seed: 59
  • 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
No log 1.0 70 0.3581 0.8768
No log 2.0 140 0.3995 0.8465
No log 3.0 210 0.3257 0.8788

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
27
Safetensors
Model size
125M params
Tensor type
F32
·

Finetuned from

Dataset used to train varun-v-rao/roberta-base-fp-sick

Evaluation results