metadata

library_name: transformers
language:
  - en
base_model: gokulsrinivasagan/distilbert_lda_20_v1_book
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - spearmanr
model-index:
  - name: distilbert_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: 0.7983467978702224

distilbert_lda_20_v1_book_stsb

This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_20_v1_book on the GLUE STSB dataset. It achieves the following results on the evaluation set:

Loss: 0.8337
Pearson: 0.7991
Spearmanr: 0.7983
Combined Score: 0.7987

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
2.788	1.0	23	2.8039	0.1297	0.1469	0.1383
1.7527	2.0	46	1.3525	0.6364	0.6289	0.6327
1.3257	3.0	69	1.3196	0.6664	0.6631	0.6647
1.0474	4.0	92	1.1084	0.7193	0.7287	0.7240
0.7714	5.0	115	1.0067	0.7785	0.7833	0.7809
0.6067	6.0	138	1.1074	0.7759	0.7891	0.7825
0.5478	7.0	161	0.8337	0.7991	0.7983	0.7987
0.3865	8.0	184	0.9860	0.7913	0.7958	0.7936
0.3404	9.0	207	1.0677	0.7898	0.7932	0.7915
0.2872	10.0	230	0.8463	0.8062	0.8041	0.8052
0.2609	11.0	253	1.0985	0.7946	0.7978	0.7962
0.2268	12.0	276	0.8654	0.8137	0.8137	0.8137

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3