Edit model card

MontelClassifier

This model is a fine-tuned version of Redhotchilipoppy/montelnewsspeaker on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6256
  • Accuracy: 0.7296

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: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 116 1.4596 0.5880
No log 2.0 232 1.1372 0.7039
No log 3.0 348 1.0803 0.6910
No log 4.0 464 1.1075 0.7253
1.2586 5.0 580 1.1247 0.7253
1.2586 6.0 696 1.2004 0.7253
1.2586 7.0 812 1.2889 0.7253
1.2586 8.0 928 1.3423 0.7253
0.3598 9.0 1044 1.5117 0.7425
0.3598 10.0 1160 1.4968 0.7425
0.3598 11.0 1276 1.4889 0.7253
0.3598 12.0 1392 1.5606 0.7296
0.0958 13.0 1508 1.6033 0.7339
0.0958 14.0 1624 1.6221 0.7339
0.0958 15.0 1740 1.6256 0.7296

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.15.0
Downloads last month
2
Safetensors
Model size
81.9M params
Tensor type
F32
·

Finetuned from