Hugging Face's logo

thrunlab
/
t5-3b_rte_sp0_ar0

Text Classification
Transformers
Safetensors
t5
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
t5-3b_rte_sp0_ar0 / README.md
lukeleeai's picture
lukeleeai
End of training
6647bd5
preview code
|
raw
history blame
3.53 kB
metadata
license: apache-2.0
base_model: t5-3b
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: t5-3b_rte_sp0_ar0
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: glue
          type: glue
          config: rte
          split: validation
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8995983935742972

t5-3b_rte_sp0_ar0

This model is a fine-tuned version of t5-3b on the glue dataset. It achieves the following results on the evaluation set:

  • Loss: 2.4886
  • Accuracy: 0.8996

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: 8
  • eval_batch_size: 16
  • seed: 1
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 20
  • training_steps: 750

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.7116 0.18 25 0.7078 0.4838
0.615 0.36 50 0.4571 0.8484
0.501 0.53 75 0.4176 0.8484
0.337 0.71 100 0.4462 0.8809
0.4199 0.89 125 0.4309 0.7942
0.2477 1.07 150 0.4325 0.8881
0.2253 1.25 175 0.4596 0.8845
0.214 1.42 200 0.9106 0.8736
0.2577 1.6 225 0.3652 0.9025
0.1966 1.78 250 0.3645 0.9097
0.2278 1.96 275 0.3337 0.9206
0.1221 2.14 300 1.2373 0.8881
0.3576 2.31 325 2.0514 0.8809
0.6186 2.49 350 3.9886 0.8809
1.0915 2.67 375 3.3403 0.8845
0.321 2.85 400 4.6906 0.8989
0.3969 3.02 425 1.2608 0.8736
0.026 3.2 450 4.4563 0.8809
0.0695 3.38 475 4.6858 0.8917
0.7626 3.56 500 4.7502 0.8917
0.2675 3.74 525 5.0576 0.9025
0.82 3.91 550 3.6297 0.9025
0.0011 4.09 575 5.7629 0.8989
0.3 4.27 600 2.3117 0.9097
0.0544 4.45 625 1.5657 0.9097
0.2907 4.63 650 2.6475 0.9025
0.2868 4.8 675 2.6720 0.8989
0.3191 4.98 700 2.8372 0.8773
0.0382 5.16 725 6.0565 0.9025
0.0297 5.34 750 4.1639 0.8736

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0