EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-10_txt_vis_concat_9_10_11_12_gate

This model is a fine-tuned version of microsoft/layoutlmv3-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8876
Accuracy: 0.7975
Exit 0 Accuracy: 0.0625
Exit 1 Accuracy: 0.0625
Exit 2 Accuracy: 0.0625
Exit 3 Accuracy: 0.0625
Exit 4 Accuracy: 0.0625

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: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 24
total_train_batch_size: 48
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 60

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Exit 0 Accuracy	Exit 1 Accuracy	Exit 2 Accuracy	Exit 3 Accuracy	Exit 4 Accuracy
No log	0.96	16	2.6594	0.17	0.065	0.0625	0.0625	0.0625	0.05
No log	1.98	33	2.5171	0.2475	0.0725	0.0625	0.0625	0.0625	0.0725
No log	3.0	50	2.3322	0.31	0.065	0.0625	0.0625	0.0625	0.0775
No log	3.96	66	2.1362	0.37	0.0625	0.0625	0.0625	0.0625	0.0625
No log	4.98	83	1.8938	0.5225	0.0625	0.0625	0.0625	0.0625	0.07
No log	6.0	100	1.6266	0.6425	0.0625	0.0625	0.0625	0.0625	0.065
No log	6.96	116	1.3983	0.6775	0.0625	0.0625	0.0625	0.0625	0.0775
No log	7.98	133	1.2573	0.7175	0.0625	0.0625	0.0625	0.0625	0.065
No log	9.0	150	1.1421	0.7425	0.0625	0.0625	0.0625	0.0625	0.0825
No log	9.96	166	1.0503	0.765	0.0625	0.0625	0.0625	0.0625	0.065
No log	10.98	183	0.9980	0.7725	0.0625	0.0625	0.0625	0.0625	0.065
No log	12.0	200	0.9884	0.7475	0.0625	0.0625	0.0625	0.0625	0.075
No log	12.96	216	0.9560	0.76	0.0625	0.0625	0.0625	0.0625	0.0675
No log	13.98	233	0.9037	0.785	0.0625	0.0625	0.0625	0.0625	0.065
No log	15.0	250	0.9221	0.7825	0.0625	0.0625	0.0625	0.0625	0.0625
No log	15.96	266	0.9096	0.775	0.0625	0.0625	0.0625	0.0625	0.0675
No log	16.98	283	0.9004	0.7775	0.0625	0.0625	0.0625	0.0625	0.0675
No log	18.0	300	0.9163	0.7825	0.0625	0.0625	0.0625	0.0625	0.065
No log	18.96	316	0.8849	0.7825	0.0625	0.0625	0.0625	0.0625	0.065
No log	19.98	333	0.8734	0.795	0.0625	0.0625	0.0625	0.0625	0.07
No log	21.0	350	0.8764	0.7925	0.0625	0.0625	0.0625	0.0625	0.065
No log	21.96	366	0.8937	0.775	0.0625	0.0625	0.0625	0.0625	0.065
No log	22.98	383	0.8677	0.795	0.0625	0.0625	0.0625	0.0625	0.065
No log	24.0	400	0.8877	0.785	0.0625	0.0625	0.0625	0.0625	0.0675
No log	24.96	416	0.8833	0.7825	0.0625	0.0625	0.0625	0.0625	0.065
No log	25.98	433	0.8721	0.7875	0.0625	0.0625	0.0625	0.0625	0.0675
No log	27.0	450	0.8774	0.79	0.0625	0.0625	0.0625	0.0625	0.065
No log	27.96	466	0.8845	0.7925	0.0625	0.0625	0.0625	0.0625	0.0675
No log	28.98	483	0.8844	0.79	0.0625	0.0625	0.0625	0.0625	0.07
0.5662	30.0	500	0.8830	0.7875	0.0625	0.0625	0.0625	0.0625	0.065
0.5662	30.96	516	0.8860	0.7925	0.0625	0.0625	0.0625	0.0625	0.065
0.5662	31.98	533	0.8786	0.795	0.0625	0.0625	0.0625	0.0625	0.065
0.5662	33.0	550	0.8877	0.7925	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	33.96	566	0.8878	0.7875	0.0625	0.0625	0.0625	0.0625	0.065
0.5662	34.98	583	0.8792	0.7925	0.0625	0.0625	0.0625	0.0625	0.065
0.5662	36.0	600	0.8824	0.785	0.0625	0.0625	0.0625	0.0625	0.065
0.5662	36.96	616	0.8836	0.79	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	37.98	633	0.8752	0.7975	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	39.0	650	0.8826	0.7975	0.0625	0.0625	0.0625	0.0625	0.065
0.5662	39.96	666	0.8881	0.7975	0.0625	0.0625	0.0625	0.0625	0.065
0.5662	40.98	683	0.8860	0.79	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	42.0	700	0.8825	0.7975	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	42.96	716	0.8868	0.795	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	43.98	733	0.8873	0.8	0.0625	0.0625	0.0625	0.0625	0.06
0.5662	45.0	750	0.8905	0.795	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	45.96	766	0.8873	0.795	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	46.98	783	0.8883	0.7975	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	48.0	800	0.8896	0.795	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	48.96	816	0.8873	0.795	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	49.98	833	0.8851	0.795	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	51.0	850	0.8845	0.8	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	51.96	866	0.8861	0.7975	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	52.98	883	0.8867	0.7975	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	54.0	900	0.8887	0.8	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	54.96	916	0.8874	0.8	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	55.98	933	0.8867	0.7975	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	57.0	950	0.8875	0.7975	0.0625	0.0625	0.0625	0.0625	0.0625
0.5662	57.6	960	0.8876	0.7975	0.0625	0.0625	0.0625	0.0625	0.0625

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3

EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-10_txt_vis_concat_9_10_11_12_gate

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

NSDT 3DConvert

UnrealSynth

DreamTexture.js