layoutlm-base-uncased-finetuned-invoices-3

This model is a fine-tuned version of riteshbehera857/layoutlm-base-uncased-finetuned-invoices-2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0163
• B-adress: {'precision': 0.9780666125101544, 'recall': 0.9868852459016394, 'f1': 0.9824561403508772, 'number': 1220}
• B-name: {'precision': 0.9794117647058823, 'recall': 0.9881305637982196, 'f1': 0.983751846381093, 'number': 337}
• Gst no: {'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}
• Invoice no: {'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}
• Order date: {'precision': 0.9841269841269841, 'recall': 0.96875, 'f1': 0.9763779527559054, 'number': 128}
• Order id: {'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}
• S-adress: {'precision': 0.9955223880597015, 'recall': 0.9970104633781763, 'f1': 0.9962658700522778, 'number': 2007}
• S-name: {'precision': 0.9937629937629938, 'recall': 0.9958333333333333, 'f1': 0.9947970863683663, 'number': 480}
• Total gross: {'precision': 0.9090909090909091, 'recall': 1.0, 'f1': 0.9523809523809523, 'number': 50}
• Total net: {'precision': 0.984251968503937, 'recall': 0.9920634920634921, 'f1': 0.9881422924901185, 'number': 126}
• Overall Precision: 0.9871
• Overall Recall: 0.9913
• Overall F1: 0.9892
• Overall Accuracy: 0.9964

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	B-adress	B-name	Gst no	Invoice no	Order date	Order id	S-adress	S-name	Total gross	Total net	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0175	1.0	19	0.0149	{'precision': 0.9780130293159609, 'recall': 0.9844262295081967, 'f1': 0.9812091503267973, 'number': 1220}	{'precision': 0.9793510324483776, 'recall': 0.9851632047477745, 'f1': 0.9822485207100592, 'number': 337}	{'precision': 1.0, 'recall': 0.9841269841269841, 'f1': 0.9919999999999999, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9841269841269841, 'recall': 0.96875, 'f1': 0.9763779527559054, 'number': 128}	{'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}	{'precision': 0.9940387481371088, 'recall': 0.9970104633781763, 'f1': 0.9955223880597015, 'number': 2007}	{'precision': 0.9958333333333333, 'recall': 0.9958333333333333, 'f1': 0.9958333333333333, 'number': 480}	{'precision': 0.9090909090909091, 'recall': 1.0, 'f1': 0.9523809523809523, 'number': 50}	{'precision': 0.946969696969697, 'recall': 0.9920634920634921, 'f1': 0.9689922480620156, 'number': 126}	0.9856	0.9911	0.9884	0.9961
0.0131	2.0	38	0.0163	{'precision': 0.9780666125101544, 'recall': 0.9868852459016394, 'f1': 0.9824561403508772, 'number': 1220}	{'precision': 0.9794117647058823, 'recall': 0.9881305637982196, 'f1': 0.983751846381093, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9841269841269841, 'recall': 0.96875, 'f1': 0.9763779527559054, 'number': 128}	{'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}	{'precision': 0.9955223880597015, 'recall': 0.9970104633781763, 'f1': 0.9962658700522778, 'number': 2007}	{'precision': 0.9937629937629938, 'recall': 0.9958333333333333, 'f1': 0.9947970863683663, 'number': 480}	{'precision': 0.9090909090909091, 'recall': 1.0, 'f1': 0.9523809523809523, 'number': 50}	{'precision': 0.984251968503937, 'recall': 0.9920634920634921, 'f1': 0.9881422924901185, 'number': 126}	0.9871	0.9913	0.9892	0.9964
0.0111	3.0	57	0.0180	{'precision': 0.9826732673267327, 'recall': 0.9762295081967213, 'f1': 0.9794407894736842, 'number': 1220}	{'precision': 0.9736842105263158, 'recall': 0.9881305637982196, 'f1': 0.9808541973490427, 'number': 337}	{'precision': 1.0, 'recall': 0.9682539682539683, 'f1': 0.9838709677419354, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9841269841269841, 'recall': 0.96875, 'f1': 0.9763779527559054, 'number': 128}	{'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}	{'precision': 0.9955223880597015, 'recall': 0.9970104633781763, 'f1': 0.9962658700522778, 'number': 2007}	{'precision': 0.9937106918238994, 'recall': 0.9875, 'f1': 0.9905956112852665, 'number': 480}	{'precision': 0.8928571428571429, 'recall': 1.0, 'f1': 0.9433962264150945, 'number': 50}	{'precision': 0.984, 'recall': 0.9761904761904762, 'f1': 0.9800796812749003, 'number': 126}	0.9877	0.9875	0.9876	0.9960
0.0096	4.0	76	0.0202	{'precision': 0.9811165845648604, 'recall': 0.9795081967213115, 'f1': 0.9803117309269893, 'number': 1220}	{'precision': 0.9851632047477745, 'recall': 0.9851632047477745, 'f1': 0.9851632047477745, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9841269841269841, 'recall': 0.96875, 'f1': 0.9763779527559054, 'number': 128}	{'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}	{'precision': 0.9964912280701754, 'recall': 0.9905331340308918, 'f1': 0.993503248375812, 'number': 2007}	{'precision': 0.9676113360323887, 'recall': 0.9958333333333333, 'f1': 0.9815195071868584, 'number': 480}	{'precision': 0.8620689655172413, 'recall': 1.0, 'f1': 0.9259259259259259, 'number': 50}	{'precision': 1.0, 'recall': 0.9444444444444444, 'f1': 0.9714285714285714, 'number': 126}	0.9858	0.9851	0.9854	0.9957
0.0086	5.0	95	0.0188	{'precision': 0.9787408013082584, 'recall': 0.9811475409836066, 'f1': 0.9799426934097422, 'number': 1220}	{'precision': 0.9852507374631269, 'recall': 0.9910979228486647, 'f1': 0.9881656804733727, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9763779527559056, 'recall': 0.96875, 'f1': 0.9725490196078432, 'number': 128}	{'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}	{'precision': 0.9960179193628671, 'recall': 0.9970104633781763, 'f1': 0.9965139442231075, 'number': 2007}	{'precision': 0.9937238493723849, 'recall': 0.9895833333333334, 'f1': 0.9916492693110648, 'number': 480}	{'precision': 0.847457627118644, 'recall': 1.0, 'f1': 0.9174311926605504, 'number': 50}	{'precision': 0.9761904761904762, 'recall': 0.9761904761904762, 'f1': 0.9761904761904762, 'number': 126}	0.9867	0.9890	0.9878	0.9960
0.0102	6.0	114	0.0185	{'precision': 0.9827302631578947, 'recall': 0.9795081967213115, 'f1': 0.9811165845648604, 'number': 1220}	{'precision': 0.9794721407624634, 'recall': 0.9910979228486647, 'f1': 0.9852507374631269, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9763779527559056, 'recall': 0.96875, 'f1': 0.9725490196078432, 'number': 128}	{'precision': 0.9624060150375939, 'recall': 0.9846153846153847, 'f1': 0.973384030418251, 'number': 130}	{'precision': 0.9955223880597015, 'recall': 0.9970104633781763, 'f1': 0.9962658700522778, 'number': 2007}	{'precision': 0.9937369519832986, 'recall': 0.9916666666666667, 'f1': 0.9927007299270073, 'number': 480}	{'precision': 0.9259259259259259, 'recall': 1.0, 'f1': 0.9615384615384615, 'number': 50}	{'precision': 0.9920634920634921, 'recall': 0.9920634920634921, 'f1': 0.9920634920634921, 'number': 126}	0.9879	0.9892	0.9885	0.9963
0.0084	7.0	133	0.0201	{'precision': 0.9747762408462164, 'recall': 0.9819672131147541, 'f1': 0.9783585136790527, 'number': 1220}	{'precision': 0.9794721407624634, 'recall': 0.9910979228486647, 'f1': 0.9852507374631269, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9622641509433962, 'recall': 0.9714285714285714, 'f1': 0.9668246445497629, 'number': 105}	{'precision': 0.9841269841269841, 'recall': 0.96875, 'f1': 0.9763779527559054, 'number': 128}	{'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}	{'precision': 0.9955223880597015, 'recall': 0.9970104633781763, 'f1': 0.9962658700522778, 'number': 2007}	{'precision': 0.9937238493723849, 'recall': 0.9895833333333334, 'f1': 0.9916492693110648, 'number': 480}	{'precision': 0.9259259259259259, 'recall': 1.0, 'f1': 0.9615384615384615, 'number': 50}	{'precision': 0.9920634920634921, 'recall': 0.9920634920634921, 'f1': 0.9920634920634921, 'number': 126}	0.9867	0.9892	0.9879	0.9960
0.0078	8.0	152	0.0201	{'precision': 0.9819672131147541, 'recall': 0.9819672131147541, 'f1': 0.9819672131147541, 'number': 1220}	{'precision': 0.9794721407624634, 'recall': 0.9910979228486647, 'f1': 0.9852507374631269, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.96875, 'recall': 0.96875, 'f1': 0.96875, 'number': 128}	{'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}	{'precision': 0.9950273495773247, 'recall': 0.9970104633781763, 'f1': 0.9960179193628671, 'number': 2007}	{'precision': 0.9937629937629938, 'recall': 0.9958333333333333, 'f1': 0.9947970863683663, 'number': 480}	{'precision': 0.8928571428571429, 'recall': 1.0, 'f1': 0.9433962264150945, 'number': 50}	{'precision': 0.9919354838709677, 'recall': 0.9761904761904762, 'f1': 0.9840000000000001, 'number': 126}	0.9875	0.9898	0.9887	0.9963
0.0064	9.0	171	0.0206	{'precision': 0.9804081632653061, 'recall': 0.9844262295081967, 'f1': 0.9824130879345603, 'number': 1220}	{'precision': 0.9794721407624634, 'recall': 0.9910979228486647, 'f1': 0.9852507374631269, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9763779527559056, 'recall': 0.96875, 'f1': 0.9725490196078432, 'number': 128}	{'precision': 0.9770992366412213, 'recall': 0.9846153846153847, 'f1': 0.9808429118773947, 'number': 130}	{'precision': 0.9955223880597015, 'recall': 0.9970104633781763, 'f1': 0.9962658700522778, 'number': 2007}	{'precision': 0.9937629937629938, 'recall': 0.9958333333333333, 'f1': 0.9947970863683663, 'number': 480}	{'precision': 0.8928571428571429, 'recall': 1.0, 'f1': 0.9433962264150945, 'number': 50}	{'precision': 0.9919354838709677, 'recall': 0.9761904761904762, 'f1': 0.9840000000000001, 'number': 126}	0.9873	0.9904	0.9889	0.9964
0.0062	10.0	190	0.0213	{'precision': 0.9795751633986928, 'recall': 0.9827868852459016, 'f1': 0.9811783960720132, 'number': 1220}	{'precision': 0.9794721407624634, 'recall': 0.9910979228486647, 'f1': 0.9852507374631269, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9763779527559056, 'recall': 0.96875, 'f1': 0.9725490196078432, 'number': 128}	{'precision': 0.9696969696969697, 'recall': 0.9846153846153847, 'f1': 0.9770992366412214, 'number': 130}	{'precision': 0.9955223880597015, 'recall': 0.9970104633781763, 'f1': 0.9962658700522778, 'number': 2007}	{'precision': 0.9937238493723849, 'recall': 0.9895833333333334, 'f1': 0.9916492693110648, 'number': 480}	{'precision': 0.8928571428571429, 'recall': 1.0, 'f1': 0.9433962264150945, 'number': 50}	{'precision': 0.9919354838709677, 'recall': 0.9761904761904762, 'f1': 0.9840000000000001, 'number': 126}	0.9869	0.9894	0.9881	0.9962
0.0056	11.0	209	0.0218	{'precision': 0.9819227608874281, 'recall': 0.9795081967213115, 'f1': 0.9807139926138695, 'number': 1220}	{'precision': 0.9766081871345029, 'recall': 0.9910979228486647, 'f1': 0.9837997054491899, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9763779527559056, 'recall': 0.96875, 'f1': 0.9725490196078432, 'number': 128}	{'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}	{'precision': 0.9965122072745392, 'recall': 0.9965122072745392, 'f1': 0.9965122072745392, 'number': 2007}	{'precision': 0.9937238493723849, 'recall': 0.9895833333333334, 'f1': 0.9916492693110648, 'number': 480}	{'precision': 0.8928571428571429, 'recall': 1.0, 'f1': 0.9433962264150945, 'number': 50}	{'precision': 0.9919354838709677, 'recall': 0.9761904761904762, 'f1': 0.9840000000000001, 'number': 126}	0.9881	0.9883	0.9882	0.9962
0.0052	12.0	228	0.0217	{'precision': 0.980440097799511, 'recall': 0.9860655737704918, 'f1': 0.98324478953821, 'number': 1220}	{'precision': 0.9794721407624634, 'recall': 0.9910979228486647, 'f1': 0.9852507374631269, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9763779527559056, 'recall': 0.96875, 'f1': 0.9725490196078432, 'number': 128}	{'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}	{'precision': 0.9955201592832255, 'recall': 0.9965122072745392, 'f1': 0.9960159362549801, 'number': 2007}	{'precision': 0.9937238493723849, 'recall': 0.9895833333333334, 'f1': 0.9916492693110648, 'number': 480}	{'precision': 0.8928571428571429, 'recall': 1.0, 'f1': 0.9433962264150945, 'number': 50}	{'precision': 0.9919354838709677, 'recall': 0.9761904761904762, 'f1': 0.9840000000000001, 'number': 126}	0.9875	0.9900	0.9888	0.9964
0.0049	13.0	247	0.0225	{'precision': 0.9812091503267973, 'recall': 0.9844262295081967, 'f1': 0.9828150572831423, 'number': 1220}	{'precision': 0.9766081871345029, 'recall': 0.9910979228486647, 'f1': 0.9837997054491899, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9763779527559056, 'recall': 0.96875, 'f1': 0.9725490196078432, 'number': 128}	{'precision': 0.9846153846153847, 'recall': 0.9846153846153847, 'f1': 0.9846153846153847, 'number': 130}	{'precision': 0.9965104685942173, 'recall': 0.9960139511709019, 'f1': 0.9962621480189384, 'number': 2007}	{'precision': 0.9937238493723849, 'recall': 0.9895833333333334, 'f1': 0.9916492693110648, 'number': 480}	{'precision': 0.9259259259259259, 'recall': 1.0, 'f1': 0.9615384615384615, 'number': 50}	{'precision': 0.9920634920634921, 'recall': 0.9920634920634921, 'f1': 0.9920634920634921, 'number': 126}	0.9883	0.9898	0.9891	0.9965
0.0052	14.0	266	0.0224	{'precision': 0.9811937857726901, 'recall': 0.9836065573770492, 'f1': 0.98239869013508, 'number': 1220}	{'precision': 0.9766081871345029, 'recall': 0.9910979228486647, 'f1': 0.9837997054491899, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9763779527559056, 'recall': 0.96875, 'f1': 0.9725490196078432, 'number': 128}	{'precision': 0.9770992366412213, 'recall': 0.9846153846153847, 'f1': 0.9808429118773947, 'number': 130}	{'precision': 0.9955201592832255, 'recall': 0.9965122072745392, 'f1': 0.9960159362549801, 'number': 2007}	{'precision': 0.9937238493723849, 'recall': 0.9895833333333334, 'f1': 0.9916492693110648, 'number': 480}	{'precision': 0.9090909090909091, 'recall': 1.0, 'f1': 0.9523809523809523, 'number': 50}	{'precision': 0.992, 'recall': 0.9841269841269841, 'f1': 0.9880478087649401, 'number': 126}	0.9875	0.9896	0.9885	0.9964
0.0046	15.0	285	0.0224	{'precision': 0.9811629811629812, 'recall': 0.9819672131147541, 'f1': 0.9815649324047521, 'number': 1220}	{'precision': 0.9766081871345029, 'recall': 0.9910979228486647, 'f1': 0.9837997054491899, 'number': 337}	{'precision': 1.0, 'recall': 0.9603174603174603, 'f1': 0.9797570850202428, 'number': 126}	{'precision': 0.9629629629629629, 'recall': 0.9904761904761905, 'f1': 0.9765258215962442, 'number': 105}	{'precision': 0.9763779527559056, 'recall': 0.96875, 'f1': 0.9725490196078432, 'number': 128}	{'precision': 0.9770992366412213, 'recall': 0.9846153846153847, 'f1': 0.9808429118773947, 'number': 130}	{'precision': 0.9955201592832255, 'recall': 0.9965122072745392, 'f1': 0.9960159362549801, 'number': 2007}	{'precision': 0.9937238493723849, 'recall': 0.9895833333333334, 'f1': 0.9916492693110648, 'number': 480}	{'precision': 0.9090909090909091, 'recall': 1.0, 'f1': 0.9523809523809523, 'number': 50}	{'precision': 0.992, 'recall': 0.9841269841269841, 'f1': 0.9880478087649401, 'number': 126}	0.9875	0.9892	0.9883	0.9963

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1