bert-tiny-distilled
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the hate_speech18 dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.4745
- eval_accuracy: 0.8556
- eval_runtime: 20.4101
- eval_samples_per_second: 107.202
- eval_steps_per_second: 0.882
- epoch: 1.0
- step: 479
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: 7.474176155523857e-05
- train_batch_size: 16
- eval_batch_size: 128
- seed: 23
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for joseph10/bert-tiny-distilled
Base model
google/bert_uncased_L-2_H-128_A-2