metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_rand_100_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_base_rand_100_v2_stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.21780785979027786
bert_base_rand_100_v2_stsb
This model is a fine-tuned version of Hartunka/bert_base_rand_100_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.4307
- Pearson: 0.2244
- Spearmanr: 0.2178
- Combined Score: 0.2211
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 |
|---|---|---|---|---|---|---|
| 2.8477 | 1.0 | 23 | 2.5026 | 0.0881 | 0.0800 | 0.0840 |
| 1.9428 | 2.0 | 46 | 2.4721 | 0.1475 | 0.1358 | 0.1417 |
| 1.6984 | 3.0 | 69 | 2.4307 | 0.2244 | 0.2178 | 0.2211 |
| 1.3566 | 4.0 | 92 | 2.5091 | 0.2426 | 0.2407 | 0.2416 |
| 1.0597 | 5.0 | 115 | 2.5674 | 0.2486 | 0.2424 | 0.2455 |
| 0.8102 | 6.0 | 138 | 2.6909 | 0.2713 | 0.2666 | 0.2690 |
| 0.6127 | 7.0 | 161 | 2.7525 | 0.2639 | 0.2592 | 0.2616 |
| 0.4965 | 8.0 | 184 | 2.8618 | 0.2606 | 0.2565 | 0.2586 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1