facebook-xlm-roberta-large-finetuned-ner-vlsp2021-3090-15June-2

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1066
• Atetime: {'precision': 0.8667972575905974, 'recall': 0.8832335329341318, 'f1': 0.874938210578349, 'number': 1002}
• Ddress: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 29}
• Erson: {'precision': 0.9608050847457628, 'recall': 0.9552395997893628, 'f1': 0.9580142593081595, 'number': 1899}
• Ersontype: {'precision': 0.7647058823529411, 'recall': 0.7412280701754386, 'f1': 0.7527839643652561, 'number': 684}
• Honenumber: {'precision': 0.8181818181818182, 'recall': 1.0, 'f1': 0.9, 'number': 9}
• Iscellaneous: {'precision': 0.5471698113207547, 'recall': 0.5471698113207547, 'f1': 0.5471698113207547, 'number': 159}
• Mail: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 51}
• Ocation: {'precision': 0.8797276853252648, 'recall': 0.8939277478862413, 'f1': 0.8867708730461304, 'number': 1301}
• P: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11}
• Rl: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 15}
• Roduct: {'precision': 0.7075163398692811, 'recall': 0.6928, 'f1': 0.7000808407437348, 'number': 625}
• Overall Precision: 0.8654
• Overall Recall: 0.8650
• Overall F1: 0.8652
• Overall Accuracy: 0.9804

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Atetime	Ddress	Erson	Ersontype	Honenumber	Iscellaneous	Mail	Ocation	P	Rl	Roduct	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0937	1.0	3263	0.0795	{'precision': 0.8605108055009824, 'recall': 0.874251497005988, 'f1': 0.8673267326732673, 'number': 1002}	{'precision': 0.5277777777777778, 'recall': 0.6551724137931034, 'f1': 0.5846153846153845, 'number': 29}	{'precision': 0.9568460309003729, 'recall': 0.9457609268035808, 'f1': 0.9512711864406779, 'number': 1899}	{'precision': 0.7157584683357879, 'recall': 0.7105263157894737, 'f1': 0.7131327953044755, 'number': 684}	{'precision': 0.8181818181818182, 'recall': 1.0, 'f1': 0.9, 'number': 9}	{'precision': 0.5068493150684932, 'recall': 0.46540880503144655, 'f1': 0.4852459016393443, 'number': 159}	{'precision': 0.8421052631578947, 'recall': 0.9411764705882353, 'f1': 0.8888888888888888, 'number': 51}	{'precision': 0.8387799564270153, 'recall': 0.8877786318216756, 'f1': 0.8625840179238238, 'number': 1301}	{'precision': 0.7, 'recall': 0.6363636363636364, 'f1': 0.6666666666666666, 'number': 11}	{'precision': 0.42857142857142855, 'recall': 0.6, 'f1': 0.5, 'number': 15}	{'precision': 0.5705426356589147, 'recall': 0.5888, 'f1': 0.5795275590551181, 'number': 625}	0.8247	0.8379	0.8312	0.9776
0.0607	2.0	6526	0.0845	{'precision': 0.8528265107212476, 'recall': 0.873253493013972, 'f1': 0.8629191321499013, 'number': 1002}	{'precision': 0.6842105263157895, 'recall': 0.896551724137931, 'f1': 0.7761194029850746, 'number': 29}	{'precision': 0.9515534491837809, 'recall': 0.9515534491837809, 'f1': 0.9515534491837809, 'number': 1899}	{'precision': 0.8087649402390438, 'recall': 0.5935672514619883, 'f1': 0.684654300168634, 'number': 684}	{'precision': 0.8, 'recall': 0.8888888888888888, 'f1': 0.8421052631578948, 'number': 9}	{'precision': 0.5735294117647058, 'recall': 0.49056603773584906, 'f1': 0.5288135593220338, 'number': 159}	{'precision': 1.0, 'recall': 0.9411764705882353, 'f1': 0.9696969696969697, 'number': 51}	{'precision': 0.847970479704797, 'recall': 0.8831667947732513, 'f1': 0.8652108433734941, 'number': 1301}	{'precision': 0.7777777777777778, 'recall': 0.6363636363636364, 'f1': 0.7000000000000001, 'number': 11}	{'precision': 0.7647058823529411, 'recall': 0.8666666666666667, 'f1': 0.8125, 'number': 15}	{'precision': 0.59, 'recall': 0.5664, 'f1': 0.5779591836734693, 'number': 625}	0.8459	0.8247	0.8352	0.9780
0.0399	3.0	9789	0.0881	{'precision': 0.8660714285714286, 'recall': 0.8712574850299402, 'f1': 0.8686567164179105, 'number': 1002}	{'precision': 0.9, 'recall': 0.9310344827586207, 'f1': 0.9152542372881356, 'number': 29}	{'precision': 0.9576943416181914, 'recall': 0.9536598209583992, 'f1': 0.9556728232189974, 'number': 1899}	{'precision': 0.7612179487179487, 'recall': 0.6944444444444444, 'f1': 0.7262996941896024, 'number': 684}	{'precision': 0.9, 'recall': 1.0, 'f1': 0.9473684210526316, 'number': 9}	{'precision': 0.4723618090452261, 'recall': 0.5911949685534591, 'f1': 0.5251396648044693, 'number': 159}	{'precision': 1.0, 'recall': 0.9411764705882353, 'f1': 0.9696969696969697, 'number': 51}	{'precision': 0.8602230483271376, 'recall': 0.889315910837817, 'f1': 0.8745275888133032, 'number': 1301}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11}	{'precision': 0.5789473684210527, 'recall': 0.7333333333333333, 'f1': 0.6470588235294117, 'number': 15}	{'precision': 0.7083333333333334, 'recall': 0.68, 'f1': 0.6938775510204083, 'number': 625}	0.8541	0.8541	0.8541	0.9795
0.0253	4.0	13052	0.0961	{'precision': 0.8686567164179104, 'recall': 0.8712574850299402, 'f1': 0.8699551569506726, 'number': 1002}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 29}	{'precision': 0.9528054535920294, 'recall': 0.9568193786203265, 'f1': 0.9548081975827641, 'number': 1899}	{'precision': 0.7784911717495987, 'recall': 0.7090643274853801, 'f1': 0.7421576128538638, 'number': 684}	{'precision': 0.8181818181818182, 'recall': 1.0, 'f1': 0.9, 'number': 9}	{'precision': 0.4712041884816754, 'recall': 0.5660377358490566, 'f1': 0.5142857142857142, 'number': 159}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 51}	{'precision': 0.8851963746223565, 'recall': 0.9008455034588778, 'f1': 0.8929523809523809, 'number': 1301}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11}	{'precision': 0.875, 'recall': 0.9333333333333333, 'f1': 0.9032258064516129, 'number': 15}	{'precision': 0.6703125, 'recall': 0.6864, 'f1': 0.6782608695652174, 'number': 625}	0.8574	0.8608	0.8591	0.9799
0.0161	5.0	16315	0.1066	{'precision': 0.8667972575905974, 'recall': 0.8832335329341318, 'f1': 0.874938210578349, 'number': 1002}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 29}	{'precision': 0.9608050847457628, 'recall': 0.9552395997893628, 'f1': 0.9580142593081595, 'number': 1899}	{'precision': 0.7647058823529411, 'recall': 0.7412280701754386, 'f1': 0.7527839643652561, 'number': 684}	{'precision': 0.8181818181818182, 'recall': 1.0, 'f1': 0.9, 'number': 9}	{'precision': 0.5471698113207547, 'recall': 0.5471698113207547, 'f1': 0.5471698113207547, 'number': 159}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 51}	{'precision': 0.8797276853252648, 'recall': 0.8939277478862413, 'f1': 0.8867708730461304, 'number': 1301}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 11}	{'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 15}	{'precision': 0.7075163398692811, 'recall': 0.6928, 'f1': 0.7000808407437348, 'number': 625}	0.8654	0.8650	0.8652	0.9804

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1