<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
hBERTv1_new_pretrain_48_KD_w_init_sst2
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48_KD_wt_init on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3751
- Accuracy: 0.8463
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 |
---|---|---|---|---|
0.3378 | 1.0 | 527 | 0.3751 | 0.8463 |
0.2032 | 2.0 | 1054 | 0.5684 | 0.8062 |
0.1549 | 3.0 | 1581 | 0.4930 | 0.8257 |
0.1241 | 4.0 | 2108 | 0.5828 | 0.8360 |
0.1048 | 5.0 | 2635 | 0.4589 | 0.8142 |
0.0872 | 6.0 | 3162 | 0.5902 | 0.8268 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3