metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv1_new_pretrain_48_KD_w_init_qnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QNLI
type: glue
config: qnli
split: validation
args: qnli
metrics:
- name: Accuracy
type: accuracy
value: 0.6141314296174263
hBERTv1_new_pretrain_48_KD_w_init_qnli
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48_KD_wt_init on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6519
- Accuracy: 0.6141
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 |
---|---|---|---|---|
0.671 | 1.0 | 819 | 0.6635 | 0.5852 |
0.6464 | 2.0 | 1638 | 0.6519 | 0.6141 |
0.6249 | 3.0 | 2457 | 0.6722 | 0.6035 |
0.6094 | 4.0 | 3276 | 0.6657 | 0.6072 |
0.5982 | 5.0 | 4095 | 0.6642 | 0.5997 |
0.5798 | 6.0 | 4914 | 0.6800 | 0.6125 |
0.5594 | 7.0 | 5733 | 0.7102 | 0.6172 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3