roberta-base-finetuned-depression

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

  • Loss: 0.7662
  • Precision: 0.8912
  • Recall: 0.9136
  • F1: 0.9018
  • Accuracy: 0.9104

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: 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: 20

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 469 0.5219 0.8220 0.7921 0.8000 0.8603
0.602 2.0 938 0.6344 0.9039 0.8257 0.8538 0.8753
0.3573 3.0 1407 0.4821 0.8818 0.8902 0.8859 0.8870
0.2511 4.0 1876 0.6265 0.8511 0.8965 0.8676 0.8934
0.1614 5.0 2345 0.5439 0.8908 0.8992 0.8919 0.9041
0.1107 6.0 2814 0.6237 0.8838 0.8990 0.8886 0.9009
0.0756 7.0 3283 0.6915 0.8930 0.9062 0.8988 0.9083
0.057 8.0 3752 0.6572 0.8736 0.9107 0.8905 0.9062
0.0664 9.0 4221 0.8022 0.8692 0.8987 0.8804 0.8977
0.0392 10.0 4690 0.7953 0.8931 0.8847 0.8844 0.8977
0.0472 11.0 5159 0.7757 0.8951 0.8886 0.8885 0.8998
0.0375 12.0 5628 0.7821 0.8881 0.9029 0.8939 0.9072
0.0292 13.0 6097 0.8124 0.8793 0.8982 0.8870 0.9009
0.0373 14.0 6566 0.9106 0.8774 0.8818 0.8735 0.8934
0.0227 15.0 7035 0.8325 0.8876 0.8855 0.8825 0.8966
0.0249 16.0 7504 0.7662 0.8912 0.9136 0.9018 0.9104
0.0249 17.0 7973 0.8383 0.8804 0.8905 0.8833 0.8955
0.0245 18.0 8442 0.8073 0.8844 0.9000 0.8907 0.9030
0.0188 19.0 8911 0.8137 0.8850 0.9012 0.8917 0.9041
0.0203 20.0 9380 0.8234 0.8850 0.8993 0.8905 0.9030

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
7
Safetensors
Model size
125M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for welsachy/roberta-base-finetuned-depression

Finetuned
(1631)
this model