Loss: 0.6097
Answer: {'precision': 0.43703703703703706, 'recall': 0.6413043478260869, 'f1': 0.5198237885462555, 'number': 92}
Header: {'precision': 0.2894736842105263, 'recall': 0.34375, 'f1': 0.3142857142857143, 'number': 32}
Overall Precision: 0.4046
Overall Recall: 0.5645
Overall F1: 0.4714
Overall Accuracy: 0.8656

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: 3e-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
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Answer	Header	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
1.4561	1.0	2	1.0789	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32}	0.0	0.0	0.0	0.8182
0.7649	2.0	4	0.9219	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32}	0.0	0.0	0.0	0.8182
0.5601	3.0	6	0.8338	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32}	0.0	0.0	0.0	0.8182
0.4611	4.0	8	0.7533	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32}	0.0	0.0	0.0	0.8182
0.3306	5.0	10	0.6861	{'precision': 0.75, 'recall': 0.03260869565217391, 'f1': 0.06249999999999999, 'number': 92}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32}	0.75	0.0242	0.0469	0.8207
0.3001	6.0	12	0.6509	{'precision': 0.43243243243243246, 'recall': 0.5217391304347826, 'f1': 0.47290640394088673, 'number': 92}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 32}	0.4324	0.3871	0.4085	0.8592
0.3436	7.0	14	0.6713	{'precision': 0.33689839572192515, 'recall': 0.6847826086956522, 'f1': 0.45161290322580644, 'number': 92}	{'precision': 0.14285714285714285, 'recall': 0.03125, 'f1': 0.05128205128205128, 'number': 32}	0.3299	0.5161	0.4025	0.8284
0.3624	8.0	16	0.6454	{'precision': 0.3516483516483517, 'recall': 0.6956521739130435, 'f1': 0.46715328467153283, 'number': 92}	{'precision': 0.4, 'recall': 0.0625, 'f1': 0.10810810810810811, 'number': 32}	0.3529	0.5323	0.4244	0.8387
0.4258	9.0	18	0.6192	{'precision': 0.3668639053254438, 'recall': 0.6739130434782609, 'f1': 0.475095785440613, 'number': 92}	{'precision': 0.5555555555555556, 'recall': 0.15625, 'f1': 0.24390243902439024, 'number': 32}	0.3764	0.5403	0.4437	0.8528
0.2221	10.0	20	0.6282	{'precision': 0.36942675159235666, 'recall': 0.6304347826086957, 'f1': 0.465863453815261, 'number': 92}	{'precision': 0.3181818181818182, 'recall': 0.21875, 'f1': 0.25925925925925924, 'number': 32}	0.3631	0.5242	0.4290	0.8476
0.2069	11.0	22	0.6241	{'precision': 0.40559440559440557, 'recall': 0.6304347826086957, 'f1': 0.4936170212765958, 'number': 92}	{'precision': 0.34375, 'recall': 0.34375, 'f1': 0.34375, 'number': 32}	0.3943	0.5565	0.4615	0.8592
0.2035	12.0	24	0.6218	{'precision': 0.4084507042253521, 'recall': 0.6304347826086957, 'f1': 0.49572649572649574, 'number': 92}	{'precision': 0.3125, 'recall': 0.3125, 'f1': 0.3125, 'number': 32}	0.3908	0.5484	0.4564	0.8604
0.1729	13.0	26	0.6175	{'precision': 0.41843971631205673, 'recall': 0.6413043478260869, 'f1': 0.5064377682403434, 'number': 92}	{'precision': 0.3125, 'recall': 0.3125, 'f1': 0.3125, 'number': 32}	0.3988	0.5565	0.4646	0.8643
0.1759	14.0	28	0.6127	{'precision': 0.427536231884058, 'recall': 0.6413043478260869, 'f1': 0.5130434782608696, 'number': 92}	{'precision': 0.3142857142857143, 'recall': 0.34375, 'f1': 0.3283582089552239, 'number': 32}	0.4046	0.5645	0.4714	0.8656
0.2299	15.0	30	0.6097	{'precision': 0.43703703703703706, 'recall': 0.6413043478260869, 'f1': 0.5198237885462555, 'number': 92}	{'precision': 0.2894736842105263, 'recall': 0.34375, 'f1': 0.3142857142857143, 'number': 32}	0.4046	0.5645	0.4714	0.8656

Framework versions

Transformers 4.39.0
Pytorch 2.2.1
Datasets 2.18.0
Tokenizers 0.15.2

ethangclark/layoutlm-funsd

layoutlm-funsd

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ethangclark/
layoutlm-funsd