metadata

library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/bert_tiny_lda_20_v1_book
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - spearmanr
model-index:
  - name: bert_tiny_lda_20_v1_book_stsb
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE STSB
          type: glue
          args: stsb
        metrics:
          - name: Spearmanr
            type: spearmanr
            value: 0.6550260104726466

bert_tiny_lda_20_v1_book_stsb

This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_20_v1_book on the GLUE STSB dataset. It achieves the following results on the evaluation set:

Loss: 1.3015
Pearson: 0.6652
Spearmanr: 0.6550
Combined Score: 0.6601

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: 256
eval_batch_size: 256
seed: 10
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr	Combined Score
3.0179	1.0	23	2.6080	0.0861	0.0929	0.0895
2.035	2.0	46	2.3616	0.2683	0.2477	0.2580
1.5507	3.0	69	2.0235	0.4102	0.3826	0.3964
1.2619	4.0	92	1.7173	0.5300	0.5095	0.5198
1.0353	5.0	115	1.5564	0.5829	0.5638	0.5733
0.9021	6.0	138	1.3864	0.6315	0.6213	0.6264
0.7466	7.0	161	1.4336	0.6263	0.6143	0.6203
0.6538	8.0	184	1.3015	0.6652	0.6550	0.6601
0.5925	9.0	207	1.3561	0.6456	0.6322	0.6389
0.5308	10.0	230	1.5712	0.6372	0.6248	0.6310
0.4724	11.0	253	1.4731	0.6424	0.6304	0.6364
0.4354	12.0	276	1.4500	0.6696	0.6567	0.6632
0.3707	13.0	299	1.3024	0.6771	0.6673	0.6722

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3