roberta-sst2-distilled

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

  • Loss: 0.2485
  • Accuracy: 0.9300

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: 6e-05
  • train_batch_size: 128
  • eval_batch_size: 128
  • seed: 33
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 7
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.257 1.0 527 0.2575 0.9117
0.2386 2.0 1054 0.2469 0.9369
0.2331 3.0 1581 0.2484 0.9358
0.2289 4.0 2108 0.2516 0.9278
0.2266 5.0 2635 0.2499 0.9335
0.2252 6.0 3162 0.2477 0.9312
0.2238 7.0 3689 0.2485 0.9300

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
92
Safetensors
Model size
125M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for thewiz/roberta-sst2-distilled

Finetuned
(1697)
this model

Dataset used to train thewiz/roberta-sst2-distilled

Evaluation results