Hugging Face's logo

Hartunka
/
bert_base_km_5_v1_stsb

Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Metrics Community
How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-classification", model="Hartunka/bert_base_km_5_v1_stsb")
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("Hartunka/bert_base_km_5_v1_stsb")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/bert_base_km_5_v1_stsb")
Quick Links

bert_base_km_5_v1_stsb

This model is a fine-tuned version of Hartunka/bert_base_km_5_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:

  • Loss: 2.2394
  • Pearson: 0.3227
  • Spearmanr: 0.3216
  • Combined Score: 0.3221

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
2.6517 1.0 23 2.3255 0.1330 0.1205 0.1268
1.9658 2.0 46 2.3461 0.2386 0.2286 0.2336
1.6725 3.0 69 2.4374 0.2424 0.2349 0.2387
1.2633 4.0 92 2.2394 0.3227 0.3216 0.3221
0.877 5.0 115 2.4882 0.3102 0.3147 0.3125
0.6898 6.0 138 2.4795 0.3147 0.3068 0.3107
0.4742 7.0 161 2.6675 0.2998 0.2927 0.2963
0.3676 8.0 184 2.3370 0.3624 0.3603 0.3614
0.3107 9.0 207 2.4862 0.3395 0.3334 0.3364

Framework versions

  • Transformers 4.50.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.21.1
Downloads last month
3
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
Text Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Hartunka/bert_base_km_5_v1_stsb

Base model

Hartunka/bert_base_km_5_v1
Finetuned
(9)
this model

Dataset used to train Hartunka/bert_base_km_5_v1_stsb

Evaluation results