metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: mobilebert_sa_GLUE_Experiment_data_aug_wnli_256
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE WNLI
type: glue
args: wnli
metrics:
- name: Accuracy
type: accuracy
value: 0.15492957746478872
mobilebert_sa_GLUE_Experiment_data_aug_wnli_256
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 2.3011
- Accuracy: 0.1549
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: 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 |
|---|---|---|---|---|
| 0.6528 | 1.0 | 435 | 2.3011 | 0.1549 |
| 0.4834 | 2.0 | 870 | 3.5400 | 0.0986 |
| 0.4353 | 3.0 | 1305 | 5.1022 | 0.1127 |
| 0.4022 | 4.0 | 1740 | 6.6353 | 0.1408 |
| 0.3757 | 5.0 | 2175 | 10.7943 | 0.0986 |
| 0.3399 | 6.0 | 2610 | 14.3396 | 0.0845 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2