Hugging Face's logo

shirzady1934
/
roberta-base-riddle-finetuned_new

Multiple Choice
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
roberta-base-riddle-finetuned_new / README.md
shirzady1934's picture
shirzady1934
End of training
a9bc9c4 verified
preview code
|
raw
history blame
3.17 kB
metadata
license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: roberta-base-riddle-finetuned_new
    results: []

roberta-base-riddle-finetuned_new

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3450
  • Accuracy: 0.875

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: 0.0005
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 12 1.3014 0.6000
No log 2.0 24 1.0521 0.5
No log 3.0 36 0.9390 0.6500
No log 4.0 48 0.9100 0.5250
No log 5.0 60 0.8639 0.7000
No log 6.0 72 0.7679 0.75
No log 7.0 84 0.6577 0.75
No log 8.0 96 0.6747 0.7250
No log 9.0 108 0.5993 0.8250
No log 10.0 120 0.5482 0.8000
No log 11.0 132 0.4691 0.9250
No log 12.0 144 0.7105 0.7750
No log 13.0 156 0.4716 0.9250
No log 14.0 168 0.4583 0.8000
No log 15.0 180 0.3940 0.8500
No log 16.0 192 0.3841 0.875
No log 17.0 204 0.3450 0.875
No log 18.0 216 0.3995 0.8500
No log 19.0 228 0.4778 0.8250
No log 20.0 240 0.4217 0.8500
No log 21.0 252 0.3841 0.875
No log 22.0 264 0.3971 0.875
No log 23.0 276 0.4158 0.8250
No log 24.0 288 0.3915 0.8500
No log 25.0 300 0.4234 0.8250
No log 26.0 312 0.3857 0.8500
No log 27.0 324 0.4306 0.8250
No log 28.0 336 0.4166 0.8250
No log 29.0 348 0.4101 0.8500
No log 30.0 360 0.4044 0.8500

Framework versions

  • Transformers 4.37.2
  • Pytorch 1.13.1+cu117
  • Datasets 2.16.1
  • Tokenizers 0.15.0