metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv1_new_pretrain_sst2
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE SST2
type: glue
config: sst2
split: validation
args: sst2
metrics:
- name: Accuracy
type: accuracy
value: 0.7878440366972477
hBERTv1_new_pretrain_sst2
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4752
- Accuracy: 0.7878
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 |
---|---|---|---|---|
0.4258 | 1.0 | 527 | 0.4994 | 0.8062 |
0.2652 | 2.0 | 1054 | 0.5633 | 0.8005 |
0.2214 | 3.0 | 1581 | 0.4752 | 0.7878 |
0.2014 | 4.0 | 2108 | 0.5329 | 0.7890 |
0.1813 | 5.0 | 2635 | 0.5410 | 0.7924 |
0.1679 | 6.0 | 3162 | 0.5857 | 0.8085 |
0.1526 | 7.0 | 3689 | 0.7654 | 0.8039 |
0.1405 | 8.0 | 4216 | 0.6715 | 0.7878 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3