metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv2_new_pretrain_48_emb_com_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
hBERTv2_new_pretrain_48_emb_com_wnli
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6868
- 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 |
|---|---|---|---|---|
| 0.9415 | 1.0 | 5 | 0.7306 | 0.4366 |
| 0.7146 | 2.0 | 10 | 0.7870 | 0.4366 |
| 0.7207 | 3.0 | 15 | 0.7136 | 0.4225 |
| 0.6988 | 4.0 | 20 | 0.7277 | 0.4366 |
| 0.7058 | 5.0 | 25 | 0.7434 | 0.4366 |
| 0.7171 | 6.0 | 30 | 0.6963 | 0.4366 |
| 0.7007 | 7.0 | 35 | 0.6897 | 0.5634 |
| 0.7085 | 8.0 | 40 | 0.6900 | 0.5634 |
| 0.7282 | 9.0 | 45 | 0.6929 | 0.5634 |
| 0.695 | 10.0 | 50 | 0.6970 | 0.4366 |
| 0.6939 | 11.0 | 55 | 0.6868 | 0.5634 |
| 0.6955 | 12.0 | 60 | 0.6904 | 0.5634 |
| 0.6934 | 13.0 | 65 | 0.7015 | 0.4366 |
| 0.6974 | 14.0 | 70 | 0.6964 | 0.4366 |
| 0.695 | 15.0 | 75 | 0.6904 | 0.5634 |
| 0.7003 | 16.0 | 80 | 0.6981 | 0.4366 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3