electra-small-finetuned-sst2

This model is a fine-tuned version of google/electra-small-discriminator on the sst2 dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.2875
• eval_accuracy: 0.9014
• eval_runtime: 0.5682
• eval_samples_per_second: 1534.758
• eval_steps_per_second: 3.52
• epoch: 3.0
• step: 393

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: 6.68561343998775e-05
• train_batch_size: 512
• eval_batch_size: 512
• seed: 39
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.27.1
• Pytorch 2.0.0+cu117
• Datasets 2.10.1
• Tokenizers 0.12.1