EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-08-23_text_vision_enc_9_10_11_12_ramp

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: 1.3988
Accuracy: 0.78
Exit 0 Accuracy: 0.0775
Exit 1 Accuracy: 0.0925
Exit 2 Accuracy: 0.775
Exit 3 Accuracy: 0.7775
Exit 4 Accuracy: 0.78
Exit 5 Accuracy: 0.78

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	Exit 5 Accuracy
No log	0.96	16	2.6732	0.1725	0.085	0.0875	0.0625	0.0625	0.0625	0.025
No log	1.98	33	2.4561	0.2675	0.075	0.09	0.0625	0.0625	0.0625	0.14
No log	3.0	50	2.2694	0.3275	0.0825	0.09	0.0625	0.0625	0.0625	0.225
No log	3.96	66	2.0390	0.4075	0.0775	0.09	0.0625	0.0625	0.0625	0.31
No log	4.98	83	1.7550	0.5525	0.08	0.09	0.0625	0.0625	0.0625	0.4125
No log	6.0	100	1.5468	0.605	0.08	0.09	0.0625	0.0625	0.0625	0.46
No log	6.96	116	1.3226	0.6475	0.08	0.0875	0.0625	0.0625	0.0625	0.5725
No log	7.98	133	1.2189	0.6625	0.0775	0.0875	0.0625	0.0625	0.0625	0.5725
No log	9.0	150	1.0980	0.71	0.0775	0.0875	0.0625	0.0625	0.0625	0.6175
No log	9.96	166	1.0513	0.7125	0.0775	0.0875	0.0625	0.0625	0.0625	0.6675
No log	10.98	183	1.0210	0.7175	0.0775	0.0875	0.0625	0.0625	0.0625	0.665
No log	12.0	200	0.9739	0.7325	0.08	0.0875	0.0625	0.0625	0.0625	0.69
No log	12.96	216	0.9843	0.735	0.08	0.0875	0.0625	0.0625	0.075	0.6925
No log	13.98	233	0.9552	0.7375	0.0775	0.0875	0.0625	0.0775	0.09	0.725
No log	15.0	250	0.9733	0.7425	0.0775	0.0875	0.065	0.1	0.1225	0.735
No log	15.96	266	1.0124	0.7425	0.075	0.09	0.0825	0.1575	0.2025	0.7275
No log	16.98	283	1.0410	0.74	0.0775	0.09	0.1125	0.1675	0.33	0.735
No log	18.0	300	1.0557	0.7575	0.0775	0.09	0.12	0.215	0.6875	0.7475
No log	18.96	316	1.0908	0.7525	0.075	0.09	0.175	0.3075	0.72	0.745
No log	19.98	333	1.0982	0.755	0.075	0.09	0.245	0.385	0.7475	0.7525
No log	21.0	350	1.1223	0.7475	0.08	0.09	0.2975	0.6975	0.7525	0.7625
No log	21.96	366	1.1636	0.745	0.0775	0.09	0.51	0.73	0.7525	0.75
No log	22.98	383	1.1899	0.755	0.0775	0.09	0.5825	0.7525	0.76	0.7525
No log	24.0	400	1.2495	0.7475	0.0775	0.09	0.65	0.735	0.75	0.745
No log	24.96	416	1.2234	0.7675	0.0825	0.09	0.705	0.7525	0.77	0.7675
No log	25.98	433	1.3483	0.75	0.08	0.09	0.735	0.7375	0.7475	0.75
No log	27.0	450	1.2518	0.7775	0.0775	0.09	0.76	0.7675	0.7775	0.78
No log	27.96	466	1.2421	0.78	0.0775	0.09	0.775	0.7725	0.7775	0.78
No log	28.98	483	1.3018	0.7775	0.075	0.09	0.7675	0.775	0.7825	0.7775
1.4084	30.0	500	1.2753	0.785	0.0925	0.09	0.775	0.7775	0.78	0.785
1.4084	30.96	516	1.3205	0.78	0.0775	0.09	0.7725	0.78	0.7775	0.78
1.4084	31.98	533	1.3406	0.775	0.08	0.09	0.765	0.77	0.775	0.775
1.4084	33.0	550	1.3088	0.7725	0.0775	0.09	0.7825	0.78	0.775	0.7725
1.4084	33.96	566	1.3133	0.7775	0.08	0.0925	0.775	0.78	0.78	0.7775
1.4084	34.98	583	1.3377	0.785	0.075	0.0925	0.7825	0.7775	0.78	0.785
1.4084	36.0	600	1.3352	0.78	0.0775	0.0925	0.7775	0.7775	0.7775	0.78
1.4084	36.96	616	1.3348	0.7775	0.0775	0.0925	0.7775	0.775	0.775	0.7775
1.4084	37.98	633	1.3719	0.7775	0.08	0.0925	0.7775	0.7775	0.7775	0.7775
1.4084	39.0	650	1.3702	0.7775	0.0775	0.0925	0.7775	0.775	0.775	0.78
1.4084	39.96	666	1.3670	0.78	0.085	0.0925	0.78	0.775	0.7775	0.78
1.4084	40.98	683	1.3672	0.78	0.075	0.0925	0.7825	0.78	0.78	0.78
1.4084	42.0	700	1.3799	0.7825	0.08	0.0925	0.7825	0.7775	0.78	0.785
1.4084	42.96	716	1.3860	0.78	0.0775	0.0925	0.78	0.775	0.775	0.7775
1.4084	43.98	733	1.3926	0.78	0.0775	0.0925	0.775	0.7775	0.775	0.7775
1.4084	45.0	750	1.3853	0.7775	0.0775	0.0925	0.7775	0.775	0.7775	0.78
1.4084	45.96	766	1.3883	0.78	0.0825	0.0925	0.775	0.7775	0.78	0.78
1.4084	46.98	783	1.3877	0.78	0.08	0.0925	0.7775	0.775	0.78	0.78
1.4084	48.0	800	1.3859	0.78	0.0775	0.0925	0.7775	0.7775	0.7825	0.78
1.4084	48.96	816	1.3878	0.78	0.0775	0.0925	0.7775	0.775	0.78	0.78
1.4084	49.98	833	1.3851	0.78	0.0775	0.0925	0.78	0.775	0.78	0.78
1.4084	51.0	850	1.3872	0.78	0.0775	0.0925	0.775	0.7775	0.78	0.78
1.4084	51.96	866	1.3914	0.78	0.0775	0.0925	0.775	0.775	0.78	0.78
1.4084	52.98	883	1.3955	0.78	0.0775	0.0925	0.775	0.7775	0.78	0.78
1.4084	54.0	900	1.3955	0.78	0.0775	0.0925	0.775	0.7775	0.78	0.78
1.4084	54.96	916	1.3979	0.78	0.0775	0.0925	0.775	0.7775	0.78	0.78
1.4084	55.98	933	1.3987	0.78	0.0775	0.0925	0.775	0.7775	0.78	0.78
1.4084	57.0	950	1.3988	0.78	0.0775	0.0925	0.775	0.7775	0.78	0.78
1.4084	57.6	960	1.3988	0.78	0.0775	0.0925	0.775	0.7775	0.78	0.78

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_2023-08-23_text_vision_enc_9_10_11_12_ramp

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

NSDT 3DConvert

UnrealSynth

DreamTexture.js