metadata
language:
- en
base_model: Hartunka/tiny_bert_km_100_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tiny_bert_km_100_v1_sst2
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE SST2
type: glue
args: sst2
metrics:
- name: Accuracy
type: accuracy
value: 0.8096330275229358
tiny_bert_km_100_v1_sst2
This model is a fine-tuned version of Hartunka/tiny_bert_km_100_v1 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4891
- Accuracy: 0.8096
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4472 | 1.0 | 264 | 0.4903 | 0.7706 |
| 0.2467 | 2.0 | 528 | 0.4891 | 0.8096 |
| 0.1937 | 3.0 | 792 | 0.5007 | 0.8119 |
| 0.1599 | 4.0 | 1056 | 0.5037 | 0.8211 |
| 0.1346 | 5.0 | 1320 | 0.6624 | 0.8028 |
| 0.1116 | 6.0 | 1584 | 0.6961 | 0.8016 |
| 0.094 | 7.0 | 1848 | 0.7631 | 0.8085 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1