metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: mobilebert_add_GLUE_Experiment_logit_kd_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: 0.801605504587156
mobilebert_add_GLUE_Experiment_logit_kd_sst2
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7778
- Accuracy: 0.8016
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 |
|---|---|---|---|---|
| 1.5405 | 1.0 | 527 | 1.4225 | 0.5539 |
| 1.3567 | 2.0 | 1054 | 1.4707 | 0.5482 |
| 1.2859 | 3.0 | 1581 | 1.4661 | 0.5677 |
| 1.2563 | 4.0 | 2108 | 1.4136 | 0.5665 |
| 1.2414 | 5.0 | 2635 | 1.4239 | 0.5940 |
| 1.2288 | 6.0 | 3162 | 1.4443 | 0.5745 |
| 0.7679 | 7.0 | 3689 | 0.7870 | 0.7878 |
| 0.4135 | 8.0 | 4216 | 0.7778 | 0.8016 |
| 0.3376 | 9.0 | 4743 | 0.8673 | 0.7993 |
| 0.2972 | 10.0 | 5270 | 0.8790 | 0.7901 |
| 0.2734 | 11.0 | 5797 | 0.9525 | 0.7913 |
| 0.2569 | 12.0 | 6324 | 0.9557 | 0.7936 |
| 0.2431 | 13.0 | 6851 | 0.9595 | 0.7878 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2