metadata
language:
- en
base_model: gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv1_new_pretrain_w_init_48_ver2_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: 0.5053999633900788
hBERTv1_new_pretrain_w_init_48_ver2_qnli
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48 on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6931
- Accuracy: 0.5054
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: 64
- eval_batch_size: 64
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.7034 | 1.0 | 1637 | 0.6952 | 0.5054 |
0.6953 | 2.0 | 3274 | 0.6950 | 0.4946 |
0.694 | 3.0 | 4911 | 0.6932 | 0.4946 |
0.6934 | 4.0 | 6548 | 0.6931 | 0.5054 |
0.6936 | 5.0 | 8185 | 0.6936 | 0.4946 |
0.6933 | 6.0 | 9822 | 0.6931 | 0.5054 |
0.6933 | 7.0 | 11459 | 0.6931 | 0.4946 |
0.6932 | 8.0 | 13096 | 0.6932 | 0.4946 |
0.6933 | 9.0 | 14733 | 0.6932 | 0.4946 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.14.1