metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_km_50_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_base_km_50_v2_stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.2528909067613722
bert_base_km_50_v2_stsb
This model is a fine-tuned version of Hartunka/bert_base_km_50_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.2956
- Pearson: 0.2660
- Spearmanr: 0.2529
- Combined Score: 0.2595
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 |
|---|---|---|---|---|---|---|
| 2.863 | 1.0 | 23 | 2.9546 | 0.1062 | 0.1142 | 0.1102 |
| 1.9987 | 2.0 | 46 | 2.3012 | 0.2302 | 0.2091 | 0.2197 |
| 1.7872 | 3.0 | 69 | 2.2956 | 0.2660 | 0.2529 | 0.2595 |
| 1.5246 | 4.0 | 92 | 2.4771 | 0.2736 | 0.2569 | 0.2652 |
| 1.247 | 5.0 | 115 | 2.5712 | 0.2505 | 0.2352 | 0.2428 |
| 0.9895 | 6.0 | 138 | 2.4369 | 0.3222 | 0.3227 | 0.3225 |
| 0.77 | 7.0 | 161 | 2.3281 | 0.3366 | 0.3382 | 0.3374 |
| 0.6098 | 8.0 | 184 | 2.4814 | 0.3255 | 0.3204 | 0.3230 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1