README.md

metadata

library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: my-polarization-model
    results: []

my-polarization-model

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6961
• Accuracy: 0.3752
• F1: 0.2200
• Precision: 0.6991
• Recall: 0.3752

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: 1e-07
• train_batch_size: 30
• eval_batch_size: 30
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.7122	1.0	86	0.7156	0.3643	0.1946	0.1327	0.3643
0.7114	2.0	172	0.7133	0.3643	0.1946	0.1327	0.3643
0.7121	3.0	258	0.7112	0.3643	0.1946	0.1327	0.3643
0.709	4.0	344	0.7093	0.3643	0.1946	0.1327	0.3643
0.7079	5.0	430	0.7074	0.3643	0.1946	0.1327	0.3643
0.7036	6.0	516	0.7058	0.3643	0.1946	0.1327	0.3643
0.7026	7.0	602	0.7044	0.3643	0.1946	0.1327	0.3643
0.7031	8.0	688	0.7032	0.3643	0.1946	0.1327	0.3643
0.7024	9.0	774	0.7020	0.3643	0.1946	0.1327	0.3643
0.7018	10.0	860	0.7009	0.3643	0.1946	0.1327	0.3643
0.7029	11.0	946	0.7000	0.3643	0.1946	0.1327	0.3643
0.6942	12.0	1032	0.6991	0.3643	0.1946	0.1327	0.3643
0.693	13.0	1118	0.6983	0.3659	0.1979	0.7686	0.3659
0.6957	14.0	1204	0.6977	0.3659	0.1979	0.7686	0.3659
0.6966	15.0	1290	0.6971	0.3659	0.1979	0.7686	0.3659
0.6963	16.0	1376	0.6967	0.3690	0.2045	0.7690	0.3690
0.6937	17.0	1462	0.6964	0.3721	0.2136	0.6785	0.3721
0.6924	18.0	1548	0.6961	0.3752	0.2200	0.6991	0.3752
0.6951	19.0	1634	0.6960	0.3752	0.2200	0.6991	0.3752
0.6937	20.0	1720	0.6959	0.3752	0.2200	0.6991	0.3752

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.4.1
• Tokenizers 0.22.1