mental_classification

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

  • Loss: 0.6424
  • Accuracy: 0.8623

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 14

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.356 1.4046 184 1.6835 0.5908
1.2119 2.8092 368 1.1011 0.7648
0.6548 4.2137 552 0.8192 0.8241
0.3782 5.6183 736 0.6968 0.8375
0.1931 7.0229 920 0.6587 0.8528
0.1127 8.4275 1104 0.6390 0.8566
0.081 9.8321 1288 0.6382 0.8566
0.0532 11.2366 1472 0.6433 0.8623
0.0416 12.6412 1656 0.6424 0.8623

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
36
Safetensors
Model size
67M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for akbarsigit/mental_classification

Finetuned
(7860)
this model