gokuls's picture
End of training
4cacfd0
|
raw
history blame
2.62 kB
---
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv1_no_pretrain_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
---
<!-- 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_no_pretrain_qnli
This model is a fine-tuned version of [](https://huggingface.co/) 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: 0.0005
- 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
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.715 | 1.0 | 819 | 0.6931 | 0.4946 |
| 0.6932 | 2.0 | 1638 | 0.6931 | 0.4946 |
| 0.6936 | 3.0 | 2457 | 0.6931 | 0.5054 |
| 0.6932 | 4.0 | 3276 | 0.6932 | 0.4946 |
| 0.6932 | 5.0 | 4095 | 0.6933 | 0.5054 |
| 0.6932 | 6.0 | 4914 | 0.6931 | 0.5054 |
| 0.6932 | 7.0 | 5733 | 0.6931 | 0.5054 |
| 0.6932 | 8.0 | 6552 | 0.6931 | 0.5054 |
| 0.6935 | 9.0 | 7371 | 0.6935 | 0.5054 |
| 0.6932 | 10.0 | 8190 | 0.6931 | 0.5054 |
| 0.6932 | 11.0 | 9009 | 0.6931 | 0.5054 |
| 0.6932 | 12.0 | 9828 | 0.6931 | 0.5054 |
| 0.6932 | 13.0 | 10647 | 0.6931 | 0.5054 |
| 0.6932 | 14.0 | 11466 | 0.6931 | 0.4946 |
| 0.6932 | 15.0 | 12285 | 0.6934 | 0.4946 |
| 0.6932 | 16.0 | 13104 | 0.6931 | 0.4946 |
### Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3