metadata
library_name: transformers
language:
- en
base_model: Hartunka/distilbert_rand_50_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: distilbert_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: 0.23672264638416732
distilbert_rand_50_v2_stsb
This model is a fine-tuned version of Hartunka/distilbert_rand_50_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.2659
- Pearson: 0.2493
- Spearmanr: 0.2367
- Combined Score: 0.2430
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 |
|---|---|---|---|---|---|---|
| 3.0153 | 1.0 | 23 | 2.4353 | 0.1203 | 0.1031 | 0.1117 |
| 1.9567 | 2.0 | 46 | 2.4981 | 0.1854 | 0.1692 | 0.1773 |
| 1.7232 | 3.0 | 69 | 2.2659 | 0.2493 | 0.2367 | 0.2430 |
| 1.4358 | 4.0 | 92 | 2.2973 | 0.2887 | 0.2818 | 0.2852 |
| 1.0785 | 5.0 | 115 | 2.6259 | 0.2453 | 0.2340 | 0.2396 |
| 0.7743 | 6.0 | 138 | 2.5245 | 0.2873 | 0.2825 | 0.2849 |
| 0.5991 | 7.0 | 161 | 2.6255 | 0.3081 | 0.3047 | 0.3064 |
| 0.479 | 8.0 | 184 | 2.6337 | 0.2887 | 0.2803 | 0.2845 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1