metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv1_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
config: mnli
split: validation_matched
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.3522172497965826
hBERTv1_mnli
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 1.0982
- Accuracy: 0.3522
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- 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 |
|---|---|---|---|---|
| 1.1001 | 1.0 | 1534 | 1.0994 | 0.3182 |
| 1.0988 | 2.0 | 3068 | 1.0990 | 0.3182 |
| 1.0987 | 3.0 | 4602 | 1.0992 | 0.3274 |
| 1.0987 | 4.0 | 6136 | 1.0986 | 0.3274 |
| 1.0987 | 5.0 | 7670 | 1.0985 | 0.3545 |
| 1.0986 | 6.0 | 9204 | 1.0987 | 0.3274 |
| 1.105 | 7.0 | 10738 | 1.0986 | 0.3274 |
| 1.1045 | 8.0 | 12272 | 1.0986 | 0.3182 |
| 1.0988 | 9.0 | 13806 | 1.0983 | 0.3274 |
| 1.0987 | 10.0 | 15340 | 1.0987 | 0.3182 |
| 1.0987 | 11.0 | 16874 | 1.0991 | 0.3182 |
| 1.0986 | 12.0 | 18408 | 1.0986 | 0.3545 |
| 1.0986 | 13.0 | 19942 | 1.0982 | 0.3545 |
| 1.0986 | 14.0 | 21476 | 1.0989 | 0.3545 |
| 1.0986 | 15.0 | 23010 | 1.0987 | 0.3182 |
| 1.0986 | 16.0 | 24544 | 1.0986 | 0.3545 |
| 1.0986 | 17.0 | 26078 | 1.0986 | 0.3545 |
| 1.0986 | 18.0 | 27612 | 1.0983 | 0.3182 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.10.1
- Tokenizers 0.13.2