mdeberta-v3-base-finetuned-green-classification-new

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6027
• Accuracy: 0.8927
• F1 Macro: 0.8743
• Accuracy Balanced: 0.8750
• F1 Micro: 0.8927
• Precision Macro: 0.8736
• Recall Macro: 0.8750
• Precision Micro: 0.8927
• Recall Micro: 0.8927

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: 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_ratio: 0.06
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Accuracy Balanced	F1 Micro	Precision Macro	Recall Macro	Precision Micro	Recall Micro
0.4492	0.3053	500	0.5885	0.8289	0.7932	0.7853	0.8289	0.8034	0.7853	0.8289	0.8289
0.2917	0.6105	1000	0.4281	0.8523	0.8369	0.8615	0.8523	0.8252	0.8615	0.8523	0.8523
0.248	0.9158	1500	0.4235	0.8795	0.8584	0.8580	0.8795	0.8588	0.8580	0.8795	0.8795
0.181	1.2210	2000	0.6807	0.8487	0.8034	0.7794	0.8487	0.8558	0.7794	0.8487	0.8487
0.1562	1.5263	2500	0.5073	0.8823	0.8631	0.8664	0.8823	0.8601	0.8664	0.8823	0.8823
0.1696	1.8315	3000	0.8349	0.8257	0.7588	0.7313	0.8257	0.8563	0.7313	0.8257	0.8257
0.14	2.1368	3500	0.5772	0.8827	0.8567	0.8435	0.8827	0.8748	0.8435	0.8827	0.8827
0.0941	2.4420	4000	0.6805	0.8823	0.8603	0.8563	0.8823	0.8647	0.8563	0.8823	0.8823
0.0923	2.7473	4500	0.5840	0.8889	0.8679	0.8634	0.8889	0.8730	0.8634	0.8889	0.8889
0.0905	3.0525	5000	0.5933	0.8925	0.8721	0.8671	0.8925	0.8777	0.8671	0.8925	0.8925
0.0555	3.3578	5500	0.6134	0.8919	0.8702	0.8623	0.8919	0.8798	0.8623	0.8919	0.8919
0.0639	3.6630	6000	0.6264	0.8903	0.8681	0.8595	0.8903	0.8785	0.8595	0.8903	0.8903
0.0631	3.9683	6500	0.6027	0.8927	0.8743	0.8750	0.8927	0.8736	0.8750	0.8927	0.8927

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1