metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_rand_50_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_base_rand_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: 0.2921098166729177
bert_base_rand_50_v2_stsb
This model is a fine-tuned version of Hartunka/bert_base_rand_50_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.1775
- Pearson: 0.3055
- Spearmanr: 0.2921
- Combined Score: 0.2988
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 |
|---|---|---|---|---|---|---|
| 2.7742 | 1.0 | 23 | 2.6998 | 0.1242 | 0.1041 | 0.1142 |
| 1.9014 | 2.0 | 46 | 2.2005 | 0.2317 | 0.2121 | 0.2219 |
| 1.647 | 3.0 | 69 | 2.1775 | 0.3055 | 0.2921 | 0.2988 |
| 1.2684 | 4.0 | 92 | 2.2438 | 0.3100 | 0.2998 | 0.3049 |
| 0.9726 | 5.0 | 115 | 2.6894 | 0.2978 | 0.2932 | 0.2955 |
| 0.7533 | 6.0 | 138 | 2.5985 | 0.3103 | 0.3100 | 0.3101 |
| 0.5559 | 7.0 | 161 | 2.5141 | 0.3397 | 0.3405 | 0.3401 |
| 0.4489 | 8.0 | 184 | 2.7038 | 0.3280 | 0.3296 | 0.3288 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1