metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: hBERTv2_new_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: 0.20926356415783265
hBERTv2_new_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: 2.2174
- Pearson: 0.1946
- Spearmanr: 0.2093
- Combined Score: 0.2019
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: 4e-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 |
|---|---|---|---|---|---|---|
| 2.3893 | 1.0 | 45 | 2.3698 | 0.1204 | 0.1138 | 0.1171 |
| 1.9589 | 2.0 | 90 | 2.2174 | 0.1946 | 0.2093 | 0.2019 |
| 1.6743 | 3.0 | 135 | 2.3481 | 0.2144 | 0.2207 | 0.2175 |
| 1.4068 | 4.0 | 180 | 2.5921 | 0.2472 | 0.2519 | 0.2496 |
| 1.2205 | 5.0 | 225 | 2.6279 | 0.2718 | 0.2701 | 0.2709 |
| 0.9353 | 6.0 | 270 | 2.5440 | 0.3117 | 0.3213 | 0.3165 |
| 0.7662 | 7.0 | 315 | 2.3053 | 0.3501 | 0.3519 | 0.3510 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3