XML-roBERTA-large-ner-ftit_2_big6

This model is a fine-tuned version of Zamza/XLM-roberta-large-ftit-emb-lr01 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 9.7425
• Precision Type: 0.4824
• Recall Type: 0.6945
• F1 Type: 0.5693
• Accuracy Type: 0.6945
• Precision Class: 0.5575
• Recall Class: 0.7467
• F1 Class: 0.6384
• Accuracy Class: 0.7467
• Precision Rel: 0.9192
• Recall Rel: 0.9587
• F1 Rel: 0.9385
• Accuracy Rel: 0.9587

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 22
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision Type	Recall Type	F1 Type	Accuracy Type	Precision Class	Recall Class	F1 Class	Accuracy Class	Precision Rel	Recall Rel	F1 Rel	Accuracy Rel
10.8548	0.4361	1000	10.8543	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.8102	0.8722	2000	10.8097	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.7626	1.3083	3000	10.7626	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.7216	1.7444	4000	10.7222	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.6778	2.1805	5000	10.6786	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.6371	2.6167	6000	10.6360	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.5934	3.0528	7000	10.5932	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.5549	3.4889	8000	10.5541	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.5181	3.9250	9000	10.5161	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.4797	4.3611	10000	10.4804	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.4421	4.7972	11000	10.4429	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.4057	5.2333	12000	10.4049	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.3732	5.6694	13000	10.3732	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.3387	6.1055	14000	10.3362	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.3056	6.5416	15000	10.3045	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.2734	6.9778	16000	10.2730	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.2444	7.4139	17000	10.2438	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.2134	7.8500	18000	10.2132	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.1825	8.2861	19000	10.1846	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.1561	8.7222	20000	10.1568	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.1278	9.1583	21000	10.1289	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.1036	9.5944	22000	10.1009	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.0787	10.0305	23000	10.0782	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.0547	10.4666	24000	10.0517	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.0286	10.9027	25000	10.0295	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
10.0054	11.3389	26000	10.0078	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.9881	11.7750	27000	9.9886	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.9615	12.2111	28000	9.9647	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.9451	12.6472	29000	9.9452	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.9293	13.0833	30000	9.9296	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.9143	13.5194	31000	9.9111	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.8922	13.9555	32000	9.8931	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.8758	14.3916	33000	9.8750	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.8616	14.8277	34000	9.8626	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.8466	15.2638	35000	9.8466	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.8328	15.7000	36000	9.8345	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.819	16.1361	37000	9.8224	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.8067	16.5722	38000	9.8100	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7976	17.0083	39000	9.7985	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7872	17.4444	40000	9.7893	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7759	17.8805	41000	9.7797	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7748	18.3166	42000	9.7753	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7657	18.7527	43000	9.7666	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7604	19.1888	44000	9.7602	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7561	19.6249	45000	9.7553	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7465	20.0611	46000	9.7509	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7475	20.4972	47000	9.7480	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7459	20.9333	48000	9.7454	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.742	21.3694	49000	9.7425	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587
9.7417	21.8055	50000	9.7425	0.4824	0.6945	0.5693	0.6945	0.5575	0.7467	0.6384	0.7467	0.9192	0.9587	0.9385	0.9587

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1