metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: add_BERT_no_pretrain_stsb
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: 0.017883010860882925
add_BERT_no_pretrain_stsb
This model is a fine-tuned version of on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.2521
- Pearson: 0.0142
- Spearmanr: 0.0179
- Combined Score: 0.0161
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: 0.0005
- 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 | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 6.3185 | 1.0 | 45 | 2.7648 | 0.0033 | -0.0054 | -0.0010 |
| 2.2915 | 2.0 | 90 | 2.2692 | 0.0207 | 0.0100 | 0.0154 |
| 2.2747 | 3.0 | 135 | 2.3623 | 0.0167 | 0.0040 | 0.0103 |
| 2.2372 | 4.0 | 180 | 2.8836 | 0.0090 | 0.0044 | 0.0067 |
| 2.2573 | 5.0 | 225 | 2.2528 | 0.0337 | 0.0365 | 0.0351 |
| 2.1979 | 6.0 | 270 | 2.2521 | 0.0142 | 0.0179 | 0.0161 |
| 2.2244 | 7.0 | 315 | 2.3162 | 0.0157 | 0.0189 | 0.0173 |
| 2.1832 | 8.0 | 360 | 2.3739 | 0.0006 | 0.0039 | 0.0023 |
| 2.3249 | 9.0 | 405 | 2.3829 | nan | nan | nan |
| 2.1956 | 10.0 | 450 | 2.3083 | nan | nan | nan |
| 2.2148 | 11.0 | 495 | 2.2706 | -0.0283 | -0.0268 | -0.0276 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3