metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: mobilebert_sa_GLUE_Experiment_data_aug_rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.48736462093862815
mobilebert_sa_GLUE_Experiment_data_aug_rte
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 2.9188
- Accuracy: 0.4874
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 |
|---|---|---|---|---|
| 0.2441 | 1.0 | 1136 | 2.9188 | 0.4874 |
| 0.0476 | 2.0 | 2272 | 4.3208 | 0.5054 |
| 0.0262 | 3.0 | 3408 | 5.1027 | 0.4801 |
| 0.0145 | 4.0 | 4544 | 7.7593 | 0.5199 |
| 0.0091 | 5.0 | 5680 | 7.3446 | 0.5018 |
| 0.0076 | 6.0 | 6816 | 9.3303 | 0.5054 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2