metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: mobilebert_add_GLUE_Experiment_stsb_128
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
config: stsb
split: validation
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.03419936685461868
mobilebert_add_GLUE_Experiment_stsb_128
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: 2.2820
- Pearson: 0.0445
- Spearmanr: 0.0342
- Combined Score: 0.0393
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 |
|---|---|---|---|---|---|---|
| 5.0491 | 1.0 | 45 | 2.6735 | -0.0094 | -0.0099 | -0.0097 |
| 2.2021 | 2.0 | 90 | 3.1489 | 0.0389 | 0.0330 | 0.0359 |
| 2.1522 | 3.0 | 135 | 2.2943 | 0.0413 | 0.0270 | 0.0341 |
| 2.125 | 4.0 | 180 | 2.5078 | 0.0421 | 0.0274 | 0.0348 |
| 2.1328 | 5.0 | 225 | 2.2820 | 0.0445 | 0.0342 | 0.0393 |
| 2.0676 | 6.0 | 270 | 2.3672 | 0.0464 | 0.0393 | 0.0428 |
| 2.0545 | 7.0 | 315 | 2.6386 | 0.0506 | 0.0463 | 0.0485 |
| 2.0677 | 8.0 | 360 | 2.4397 | 0.0556 | 0.0574 | 0.0565 |
| 1.9988 | 9.0 | 405 | 2.4024 | 0.0601 | 0.0630 | 0.0615 |
| 1.9683 | 10.0 | 450 | 2.7224 | 0.0576 | 0.0646 | 0.0611 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2