metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv1_new_pretrain_48_KD_wnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE WNLI
type: glue
config: wnli
split: validation
args: wnli
metrics:
- name: Accuracy
type: accuracy
value: 0.5633802816901409
hBERTv1_new_pretrain_48_KD_wnli
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48_KD on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6854
- Accuracy: 0.5634
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 |
---|---|---|---|---|
0.7548 | 1.0 | 5 | 0.7991 | 0.4366 |
0.7094 | 2.0 | 10 | 0.7048 | 0.4366 |
0.7546 | 3.0 | 15 | 0.6934 | 0.4789 |
0.7016 | 4.0 | 20 | 0.6999 | 0.4366 |
0.705 | 5.0 | 25 | 0.6859 | 0.5634 |
0.701 | 6.0 | 30 | 0.7016 | 0.4366 |
0.6975 | 7.0 | 35 | 0.6854 | 0.5634 |
0.6952 | 8.0 | 40 | 0.6945 | 0.4507 |
0.7021 | 9.0 | 45 | 0.7181 | 0.4366 |
0.7039 | 10.0 | 50 | 0.6879 | 0.5634 |
0.698 | 11.0 | 55 | 0.6941 | 0.4507 |
0.6953 | 12.0 | 60 | 0.6997 | 0.4225 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3