learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use adamw_torch 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: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Academicdiscipline F1	Ambiguouslydefinedconcept F1	Discoursephenomenon F1	Languagerelatedterm F1	Languageresourceinformation F1	Lexicalphenomenon F1	Morphologicalphenomenon F1	Morphosyntacticphenomenon F1	New Tag F1	Otherlinguisticterm F1	Phonologicalphenomenon F1	Semanticphenomenon F1	Syntacticphenomenon F1	Topnode Dummy F1	Unclassifiedlinguisticconcept F1
No log	1.0	238	0.2144	0.5229	0.3946	0.4497	0.9428	0.0	0.0	0.0	0.6371	0.1948	0.0	0.3467	0.5773	0.4131	0.2583	0.6915	0.0	0.2875	0.0669	0.0
No log	2.0	476	0.1441	0.6669	0.6837	0.6752	0.9592	0.0	0.5630	0.2222	0.7148	0.7052	0.5858	0.6909	0.7704	0.7018	0.6263	0.8058	0.4787	0.6517	0.4617	0.7415
0.532	3.0	714	0.1160	0.7430	0.7150	0.7287	0.9656	0.0	0.7015	0.3030	0.7716	0.7016	0.6667	0.7681	0.8105	0.7683	0.6609	0.8500	0.6074	0.6975	0.5533	0.6949
0.532	4.0	952	0.1087	0.7241	0.7898	0.7555	0.9676	0.4	0.7750	0.3579	0.7882	0.7439	0.7187	0.7852	0.8353	0.7882	0.7112	0.8726	0.6344	0.6991	0.6311	0.6926
0.0978	5.0	1190	0.1033	0.7632	0.7924	0.7775	0.9704	0.4516	0.8387	0.3514	0.7895	0.7426	0.7345	0.8205	0.8599	0.8064	0.7297	0.8814	0.6422	0.7452	0.6374	0.7650
0.0978	6.0	1428	0.1047	0.7549	0.8139	0.7833	0.9707	0.8	0.8462	0.45	0.8052	0.7549	0.7518	0.8080	0.8465	0.8166	0.7399	0.8878	0.6632	0.7391	0.6632	0.7753
0.051	7.0	1666	0.1130	0.7384	0.8308	0.7819	0.9698	0.7692	0.8462	0.4250	0.7952	0.7846	0.7080	0.8272	0.8689	0.8032	0.7411	0.8912	0.6329	0.7379	0.6551	0.7946
0.051	8.0	1904	0.1145	0.7767	0.8161	0.7959	0.9726	0.8	0.8272	0.5238	0.8167	0.7773	0.7579	0.8233	0.8634	0.8176	0.7545	0.9002	0.6719	0.7683	0.6711	0.8018
0.0302	9.0	2142	0.1195	0.7833	0.8091	0.7960	0.9726	0.8	0.8302	0.4944	0.8140	0.7755	0.7605	0.8227	0.8658	0.8184	0.7600	0.8947	0.6582	0.7675	0.6738	0.7739
0.0302	10.0	2380	0.1219	0.7842	0.8141	0.7989	0.9728	0.8	0.8428	0.4884	0.825	0.7568	0.7579	0.8222	0.8664	0.8188	0.7643	0.9007	0.6523	0.7621	0.6846	0.7807

Framework versions

Transformers 4.57.6
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.22.2

c-ho/2026-07-29-xlmr-large-baseline

2026-07-29-xlmr-large-baseline

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

c-ho/
2026-07-29-xlmr-large-baseline