metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: mobilebert_sa_GLUE_Experiment_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.6838235294117647
- name: F1
type: f1
value: 0.8122270742358079
mobilebert_sa_GLUE_Experiment_mrpc
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.6145
- Accuracy: 0.6838
- F1: 0.8122
- Combined Score: 0.7480
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6377 | 1.0 | 29 | 0.6240 | 0.6838 | 0.8122 | 0.7480 |
| 0.6309 | 2.0 | 58 | 0.6236 | 0.6838 | 0.8122 | 0.7480 |
| 0.6306 | 3.0 | 87 | 0.6233 | 0.6838 | 0.8122 | 0.7480 |
| 0.6291 | 4.0 | 116 | 0.6226 | 0.6838 | 0.8122 | 0.7480 |
| 0.6222 | 5.0 | 145 | 0.6145 | 0.6838 | 0.8122 | 0.7480 |
| 0.5736 | 6.0 | 174 | 0.6208 | 0.7010 | 0.7939 | 0.7474 |
| 0.488 | 7.0 | 203 | 0.6414 | 0.6936 | 0.7795 | 0.7366 |
| 0.3939 | 8.0 | 232 | 0.7659 | 0.7279 | 0.8122 | 0.7701 |
| 0.3038 | 9.0 | 261 | 0.8875 | 0.7083 | 0.8027 | 0.7555 |
| 0.2636 | 10.0 | 290 | 0.9829 | 0.7034 | 0.8033 | 0.7533 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2