Hartunka's picture
End of training
cb3a6b9 verified
metadata
language:
  - en
base_model: Hartunka/tiny_bert_rand_50_v1
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: tiny_bert_rand_50_v1_rte
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE RTE
          type: glue
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5595667870036101

tiny_bert_rand_50_v1_rte

This model is a fine-tuned version of Hartunka/tiny_bert_rand_50_v1 on the GLUE RTE dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6857
  • Accuracy: 0.5596

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
0.6992 1.0 10 0.6892 0.5632
0.6919 2.0 20 0.6865 0.5379
0.6803 3.0 30 0.6857 0.5596
0.6477 4.0 40 0.7186 0.5560
0.5941 5.0 50 0.7787 0.5523
0.5146 6.0 60 0.8585 0.5415
0.3902 7.0 70 1.0804 0.5162
0.2783 8.0 80 1.2461 0.5271

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.6.0+cu124
  • Datasets 3.5.0
  • Tokenizers 0.19.1