<!-- 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_cola
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48_KD_wt_init on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6182
- Matthews Correlation: 0.0
- Accuracy: 0.6913
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 | Matthews Correlation | Accuracy |
---|---|---|---|---|---|
0.6338 | 1.0 | 67 | 0.6182 | 0.0 | 0.6913 |
0.6194 | 2.0 | 134 | 0.6405 | 0.0 | 0.6913 |
0.6131 | 3.0 | 201 | 0.6188 | 0.0 | 0.6913 |
0.6128 | 4.0 | 268 | 0.6199 | 0.0 | 0.6913 |
0.6281 | 5.0 | 335 | 0.6197 | 0.0 | 0.6913 |
0.6146 | 6.0 | 402 | 0.6196 | 0.0 | 0.6913 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3