metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: mobilebert_sa_GLUE_Experiment_logit_kd_rte_128
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
config: rte
split: validation
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.5270758122743683
mobilebert_sa_GLUE_Experiment_logit_kd_rte_128
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: 0.3915
- Accuracy: 0.5271
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 |
---|---|---|---|---|
0.4093 | 1.0 | 20 | 0.3917 | 0.5271 |
0.4077 | 2.0 | 40 | 0.3922 | 0.5271 |
0.4076 | 3.0 | 60 | 0.3916 | 0.5271 |
0.4075 | 4.0 | 80 | 0.3921 | 0.5271 |
0.4075 | 5.0 | 100 | 0.3925 | 0.5271 |
0.4073 | 6.0 | 120 | 0.3915 | 0.5271 |
0.4066 | 7.0 | 140 | 0.3916 | 0.5271 |
0.4043 | 8.0 | 160 | 0.3937 | 0.5271 |
0.3902 | 9.0 | 180 | 0.4440 | 0.5054 |
0.3545 | 10.0 | 200 | 0.4575 | 0.4801 |
0.3116 | 11.0 | 220 | 0.4770 | 0.4440 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2