metadata

language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - spearmanr
model-index:
  - name: hBERTv1_new_pretrain_w_init__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: 0.08916919703003628

hBERTv1_new_pretrain_w_init__stsb

This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init on the GLUE STSB dataset. It achieves the following results on the evaluation set:

Loss: 2.2584
Pearson: 0.0949
Spearmanr: 0.0892
Combined Score: 0.0920

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
2.5056	1.0	45	2.2584	0.0949	0.0892	0.0920
2.1254	2.0	90	2.6871	0.1250	0.1231	0.1241
1.9839	3.0	135	2.2709	0.1790	0.1840	0.1815
1.6299	4.0	180	2.5115	0.2691	0.2797	0.2744
1.3155	5.0	225	2.4555	0.3453	0.3437	0.3445
0.9686	6.0	270	2.8004	0.4571	0.4406	0.4489

Framework versions

Transformers 4.29.2
Pytorch 1.14.0a0+410ce96
Datasets 2.12.0
Tokenizers 0.13.3