metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_rand_10_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_base_rand_10_v2_stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.27121376913207584
bert_base_rand_10_v2_stsb
This model is a fine-tuned version of Hartunka/bert_base_rand_10_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.3000
- Pearson: 0.2717
- Spearmanr: 0.2712
- Combined Score: 0.2714
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 |
|---|---|---|---|---|---|---|
| 2.6698 | 1.0 | 23 | 2.3702 | 0.1154 | 0.0941 | 0.1048 |
| 1.9073 | 2.0 | 46 | 2.5553 | 0.1762 | 0.1591 | 0.1676 |
| 1.7118 | 3.0 | 69 | 2.5235 | 0.1830 | 0.1931 | 0.1880 |
| 1.3839 | 4.0 | 92 | 2.3000 | 0.2717 | 0.2712 | 0.2714 |
| 1.0676 | 5.0 | 115 | 2.6445 | 0.2323 | 0.2322 | 0.2322 |
| 0.8664 | 6.0 | 138 | 2.7314 | 0.2522 | 0.2583 | 0.2552 |
| 0.6989 | 7.0 | 161 | 2.6691 | 0.2727 | 0.2750 | 0.2738 |
| 0.568 | 8.0 | 184 | 2.8615 | 0.2635 | 0.2681 | 0.2658 |
| 0.4705 | 9.0 | 207 | 2.7113 | 0.2554 | 0.2386 | 0.2470 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1