roberta-large-ner-ghtk-cs-add-2label-10-new-data-3090-14Sep-1

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2814
• Tk: {'precision': 0.8181818181818182, 'recall': 0.6982758620689655, 'f1': 0.7534883720930233, 'number': 116}
• A: {'precision': 0.92, 'recall': 0.9605568445475638, 'f1': 0.9398410896708287, 'number': 431}
• Gày: {'precision': 0.7209302325581395, 'recall': 0.9117647058823529, 'f1': 0.8051948051948051, 'number': 34}
• Gày trừu tượng: {'precision': 0.8959183673469387, 'recall': 0.8995901639344263, 'f1': 0.8977505112474438, 'number': 488}
• Iờ: {'precision': 0.6170212765957447, 'recall': 0.7631578947368421, 'f1': 0.6823529411764706, 'number': 38}
• Ã đơn: {'precision': 0.8542713567839196, 'recall': 0.8374384236453202, 'f1': 0.845771144278607, 'number': 203}
• Đt: {'precision': 0.9354838709677419, 'recall': 0.9908883826879271, 'f1': 0.9623893805309734, 'number': 878}
• Đt trừu tượng: {'precision': 0.7683823529411765, 'recall': 0.8969957081545065, 'f1': 0.8277227722772277, 'number': 233}
• Overall Precision: 0.8866
• Overall Recall: 0.9265
• Overall F1: 0.9061
• Overall Accuracy: 0.9580

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: 2.5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Tk	A	Gày	Gày trừu tượng	Iờ	Ã đơn	Đt	Đt trừu tượng	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
No log	1.0	274	0.1978	{'precision': 0.78, 'recall': 0.6724137931034483, 'f1': 0.7222222222222223, 'number': 116}	{'precision': 0.9051724137931034, 'recall': 0.974477958236659, 'f1': 0.9385474860335196, 'number': 431}	{'precision': 0.6808510638297872, 'recall': 0.9411764705882353, 'f1': 0.7901234567901235, 'number': 34}	{'precision': 0.8621359223300971, 'recall': 0.9098360655737705, 'f1': 0.8853439680957128, 'number': 488}	{'precision': 0.5833333333333334, 'recall': 0.9210526315789473, 'f1': 0.7142857142857143, 'number': 38}	{'precision': 0.8813559322033898, 'recall': 0.7684729064039408, 'f1': 0.8210526315789475, 'number': 203}	{'precision': 0.9145833333333333, 'recall': 1.0, 'f1': 0.955386289445049, 'number': 878}	{'precision': 0.6537313432835821, 'recall': 0.9399141630901288, 'f1': 0.7711267605633803, 'number': 233}	0.8510	0.9343	0.8907	0.9535
0.0773	2.0	548	0.1664	{'precision': 0.8695652173913043, 'recall': 0.6896551724137931, 'f1': 0.7692307692307693, 'number': 116}	{'precision': 0.9157667386609071, 'recall': 0.9837587006960556, 'f1': 0.9485458612975392, 'number': 431}	{'precision': 0.6744186046511628, 'recall': 0.8529411764705882, 'f1': 0.7532467532467532, 'number': 34}	{'precision': 0.8725490196078431, 'recall': 0.9118852459016393, 'f1': 0.8917835671342685, 'number': 488}	{'precision': 0.6170212765957447, 'recall': 0.7631578947368421, 'f1': 0.6823529411764706, 'number': 38}	{'precision': 0.7772727272727272, 'recall': 0.8423645320197044, 'f1': 0.8085106382978724, 'number': 203}	{'precision': 0.9166666666666666, 'recall': 0.989749430523918, 'f1': 0.9518072289156626, 'number': 878}	{'precision': 0.7482014388489209, 'recall': 0.8927038626609443, 'f1': 0.8140900195694717, 'number': 233}	0.8670	0.9314	0.8980	0.9549
0.0773	3.0	822	0.2053	{'precision': 0.7087378640776699, 'recall': 0.6293103448275862, 'f1': 0.6666666666666667, 'number': 116}	{'precision': 0.9298642533936652, 'recall': 0.9535962877030162, 'f1': 0.9415807560137456, 'number': 431}	{'precision': 0.7575757575757576, 'recall': 0.7352941176470589, 'f1': 0.746268656716418, 'number': 34}	{'precision': 0.8693069306930693, 'recall': 0.8995901639344263, 'f1': 0.8841893252769385, 'number': 488}	{'precision': 0.6285714285714286, 'recall': 0.5789473684210527, 'f1': 0.6027397260273972, 'number': 38}	{'precision': 0.7837837837837838, 'recall': 0.8571428571428571, 'f1': 0.8188235294117646, 'number': 203}	{'precision': 0.9345493562231759, 'recall': 0.9920273348519362, 'f1': 0.9624309392265193, 'number': 878}	{'precision': 0.75, 'recall': 0.8884120171673819, 'f1': 0.8133595284872298, 'number': 233}	0.8721	0.9178	0.8943	0.9548
0.0382	4.0	1096	0.1953	{'precision': 0.7384615384615385, 'recall': 0.8275862068965517, 'f1': 0.7804878048780489, 'number': 116}	{'precision': 0.9258426966292135, 'recall': 0.9559164733178654, 'f1': 0.9406392694063928, 'number': 431}	{'precision': 0.6956521739130435, 'recall': 0.9411764705882353, 'f1': 0.7999999999999999, 'number': 34}	{'precision': 0.8742632612966601, 'recall': 0.9118852459016393, 'f1': 0.8926780341023068, 'number': 488}	{'precision': 0.5769230769230769, 'recall': 0.7894736842105263, 'f1': 0.6666666666666666, 'number': 38}	{'precision': 0.8907103825136612, 'recall': 0.8029556650246306, 'f1': 0.844559585492228, 'number': 203}	{'precision': 0.940152339499456, 'recall': 0.9840546697038725, 'f1': 0.9616026711185309, 'number': 878}	{'precision': 0.8237704918032787, 'recall': 0.8626609442060086, 'f1': 0.8427672955974843, 'number': 233}	0.8873	0.9265	0.9064	0.9598
0.0382	5.0	1370	0.2185	{'precision': 0.7666666666666667, 'recall': 0.7931034482758621, 'f1': 0.7796610169491527, 'number': 116}	{'precision': 0.9230769230769231, 'recall': 0.974477958236659, 'f1': 0.9480812641083521, 'number': 431}	{'precision': 0.6956521739130435, 'recall': 0.9411764705882353, 'f1': 0.7999999999999999, 'number': 34}	{'precision': 0.8928571428571429, 'recall': 0.9221311475409836, 'f1': 0.9072580645161291, 'number': 488}	{'precision': 0.5454545454545454, 'recall': 0.7894736842105263, 'f1': 0.6451612903225806, 'number': 38}	{'precision': 0.8901098901098901, 'recall': 0.7980295566502463, 'f1': 0.8415584415584415, 'number': 203}	{'precision': 0.9613259668508287, 'recall': 0.9908883826879271, 'f1': 0.975883342680875, 'number': 878}	{'precision': 0.7491039426523297, 'recall': 0.8969957081545065, 'f1': 0.8164062499999999, 'number': 233}	0.8896	0.9356	0.9120	0.9602
0.0235	6.0	1644	0.2448	{'precision': 0.85, 'recall': 0.7327586206896551, 'f1': 0.787037037037037, 'number': 116}	{'precision': 0.9116379310344828, 'recall': 0.9814385150812065, 'f1': 0.9452513966480447, 'number': 431}	{'precision': 0.7073170731707317, 'recall': 0.8529411764705882, 'f1': 0.7733333333333334, 'number': 34}	{'precision': 0.897119341563786, 'recall': 0.8934426229508197, 'f1': 0.8952772073921971, 'number': 488}	{'precision': 0.6078431372549019, 'recall': 0.8157894736842105, 'f1': 0.6966292134831461, 'number': 38}	{'precision': 0.8260869565217391, 'recall': 0.8423645320197044, 'f1': 0.8341463414634146, 'number': 203}	{'precision': 0.9382448537378115, 'recall': 0.9863325740318907, 'f1': 0.9616879511382567, 'number': 878}	{'precision': 0.7832699619771863, 'recall': 0.8841201716738197, 'f1': 0.8306451612903226, 'number': 233}	0.8864	0.9281	0.9068	0.9570
0.0235	7.0	1918	0.2768	{'precision': 0.8877551020408163, 'recall': 0.75, 'f1': 0.8130841121495328, 'number': 116}	{'precision': 0.9229074889867841, 'recall': 0.9721577726218097, 'f1': 0.9468926553672317, 'number': 431}	{'precision': 0.7560975609756098, 'recall': 0.9117647058823529, 'f1': 0.8266666666666665, 'number': 34}	{'precision': 0.8862275449101796, 'recall': 0.9098360655737705, 'f1': 0.8978766430738119, 'number': 488}	{'precision': 0.6486486486486487, 'recall': 0.631578947368421, 'f1': 0.64, 'number': 38}	{'precision': 0.9028571428571428, 'recall': 0.7783251231527094, 'f1': 0.835978835978836, 'number': 203}	{'precision': 0.9564245810055866, 'recall': 0.9749430523917996, 'f1': 0.9655950366610265, 'number': 878}	{'precision': 0.819672131147541, 'recall': 0.8583690987124464, 'f1': 0.8385744234800838, 'number': 233}	0.9076	0.9166	0.9120	0.9602
0.0134	8.0	2192	0.2686	{'precision': 0.801980198019802, 'recall': 0.6982758620689655, 'f1': 0.7465437788018433, 'number': 116}	{'precision': 0.9263392857142857, 'recall': 0.962877030162413, 'f1': 0.944254835039818, 'number': 431}	{'precision': 0.7619047619047619, 'recall': 0.9411764705882353, 'f1': 0.8421052631578947, 'number': 34}	{'precision': 0.9088983050847458, 'recall': 0.8790983606557377, 'f1': 0.89375, 'number': 488}	{'precision': 0.6530612244897959, 'recall': 0.8421052631578947, 'f1': 0.735632183908046, 'number': 38}	{'precision': 0.8736842105263158, 'recall': 0.8177339901477833, 'f1': 0.8447837150127226, 'number': 203}	{'precision': 0.9314775160599572, 'recall': 0.9908883826879271, 'f1': 0.9602649006622518, 'number': 878}	{'precision': 0.796812749003984, 'recall': 0.8583690987124464, 'f1': 0.8264462809917356, 'number': 233}	0.8947	0.9190	0.9067	0.9591
0.0134	9.0	2466	0.2790	{'precision': 0.8181818181818182, 'recall': 0.6982758620689655, 'f1': 0.7534883720930233, 'number': 116}	{'precision': 0.9301801801801802, 'recall': 0.9582366589327146, 'f1': 0.9440000000000001, 'number': 431}	{'precision': 0.7209302325581395, 'recall': 0.9117647058823529, 'f1': 0.8051948051948051, 'number': 34}	{'precision': 0.9037656903765691, 'recall': 0.8852459016393442, 'f1': 0.8944099378881988, 'number': 488}	{'precision': 0.6444444444444445, 'recall': 0.7631578947368421, 'f1': 0.6987951807228916, 'number': 38}	{'precision': 0.8535353535353535, 'recall': 0.8325123152709359, 'f1': 0.8428927680798005, 'number': 203}	{'precision': 0.9395248380129589, 'recall': 0.9908883826879271, 'f1': 0.9645232815964523, 'number': 878}	{'precision': 0.7675276752767528, 'recall': 0.8927038626609443, 'f1': 0.8253968253968255, 'number': 233}	0.8918	0.9223	0.9068	0.9584
0.006	10.0	2740	0.2814	{'precision': 0.8181818181818182, 'recall': 0.6982758620689655, 'f1': 0.7534883720930233, 'number': 116}	{'precision': 0.92, 'recall': 0.9605568445475638, 'f1': 0.9398410896708287, 'number': 431}	{'precision': 0.7209302325581395, 'recall': 0.9117647058823529, 'f1': 0.8051948051948051, 'number': 34}	{'precision': 0.8959183673469387, 'recall': 0.8995901639344263, 'f1': 0.8977505112474438, 'number': 488}	{'precision': 0.6170212765957447, 'recall': 0.7631578947368421, 'f1': 0.6823529411764706, 'number': 38}	{'precision': 0.8542713567839196, 'recall': 0.8374384236453202, 'f1': 0.845771144278607, 'number': 203}	{'precision': 0.9354838709677419, 'recall': 0.9908883826879271, 'f1': 0.9623893805309734, 'number': 878}	{'precision': 0.7683823529411765, 'recall': 0.8969957081545065, 'f1': 0.8277227722772277, 'number': 233}	0.8866	0.9265	0.9061	0.9580

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1