hBERTv2_new_pretrain_48_KD_w_init_sst2
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48_KD_wt_init on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4188
- Accuracy: 0.8394
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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.3594 | 1.0 | 527 | 0.4188 | 0.8394 |
0.2344 | 2.0 | 1054 | 0.5086 | 0.8337 |
0.2012 | 3.0 | 1581 | 0.5127 | 0.8177 |
0.1723 | 4.0 | 2108 | 0.4814 | 0.8200 |
0.1425 | 5.0 | 2635 | 0.4872 | 0.8314 |
0.12 | 6.0 | 3162 | 0.5835 | 0.8222 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train gokuls/hBERTv2_new_pretrain_48_KD_w_init_sst2
Evaluation results
- Accuracy on GLUE SST2validation set self-reported0.839