README.md

metadata

library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: mdeberta-v3-base-name-classifier-v2
    results: []

mdeberta-v3-base-name-classifier-v2

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

• Loss: 0.0269
• Accuracy: 0.9927
• Precision: 0.9966
• Recall: 0.9906
• F1: 0.9936

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-05
• train_batch_size: 128
• eval_batch_size: 128
• 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
• lr_scheduler_warmup_steps: 2000
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.0495	0.0411	2000	0.0448	0.9881	0.9963	0.9826	0.9894
0.0433	0.0821	4000	0.0427	0.9906	0.9955	0.9879	0.9917
0.0385	0.1232	6000	0.0397	0.9900	0.9973	0.9851	0.9912
0.0315	0.1642	8000	0.0328	0.9913	0.9961	0.9885	0.9923
0.0326	0.2053	10000	0.0317	0.9914	0.9944	0.9905	0.9924
0.0331	0.2464	12000	0.0317	0.9917	0.9965	0.9888	0.9926
0.0383	0.2874	14000	0.0302	0.9919	0.9947	0.9909	0.9928
0.0299	0.3285	16000	0.0296	0.9919	0.9953	0.9904	0.9929
0.0299	0.3696	18000	0.0294	0.9921	0.9959	0.9901	0.9930
0.0322	0.4106	20000	0.0297	0.9921	0.9970	0.9890	0.9930
0.0323	0.4517	22000	0.0288	0.9922	0.9959	0.9903	0.9931
0.0309	0.4927	24000	0.0292	0.9921	0.9972	0.9889	0.9930
0.0325	0.5338	26000	0.0284	0.9921	0.9949	0.9912	0.9930
0.0292	0.5749	28000	0.0279	0.9923	0.9961	0.9903	0.9932
0.0265	0.6159	30000	0.0289	0.9923	0.9953	0.9911	0.9932
0.0291	0.6570	32000	0.0279	0.9924	0.9963	0.9903	0.9933
0.0307	0.6981	34000	0.0276	0.9926	0.9965	0.9904	0.9934
0.0286	0.7391	36000	0.0273	0.9926	0.9967	0.9903	0.9935
0.0287	0.7802	38000	0.0269	0.9927	0.9970	0.9901	0.9935
0.0284	0.8212	40000	0.0278	0.9925	0.9958	0.9910	0.9934
0.0258	0.8623	42000	0.0274	0.9927	0.9965	0.9905	0.9935
0.0245	0.9034	44000	0.0273	0.9927	0.9967	0.9904	0.9935
0.0324	0.9444	46000	0.0269	0.9927	0.9964	0.9907	0.9935
0.0311	0.9855	48000	0.0269	0.9927	0.9966	0.9906	0.9936

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.0+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1