metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_stsb_256
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.1782922367618971
mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_stsb_256
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 1.3502
- Pearson: 0.1595
- Spearmanr: 0.1783
- Combined Score: 0.1689
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 | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 0.535 | 1.0 | 2518 | 1.3502 | 0.1595 | 0.1783 | 0.1689 |
| 0.3149 | 2.0 | 5036 | 1.4771 | 0.1504 | 0.1610 | 0.1557 |
| 0.2467 | 3.0 | 7554 | 1.5606 | 0.1609 | 0.1660 | 0.1634 |
| 0.1704 | 4.0 | 10072 | 1.5334 | 0.1662 | 0.1766 | 0.1714 |
| 0.1257 | 5.0 | 12590 | 1.4389 | 0.1712 | 0.1783 | 0.1747 |
| 0.0976 | 6.0 | 15108 | 1.5827 | 0.1437 | 0.1526 | 0.1482 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2