EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-05_txt_vis_enc_4_5_6_7_11_12_rmp

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: 1.7887
Accuracy: 0.7325
Exit 0 Accuracy: 0.0575
Exit 1 Accuracy: 0.6525
Exit 2 Accuracy: 0.7075
Exit 3 Accuracy: 0.7075
Exit 4 Accuracy: 0.7075
Exit 5 Accuracy: 0.7325
Exit 6 Accuracy: 0.7375

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	Exit 6 Accuracy
No log	0.96	16	2.6685	0.1775	0.08	0.065	0.0625	0.0625	0.0625	0.0625	0.1
No log	1.98	33	2.5182	0.2375	0.07	0.0675	0.0625	0.0625	0.0625	0.0625	0.155
No log	3.0	50	2.3044	0.36	0.0725	0.1075	0.0625	0.0625	0.0625	0.0625	0.225
No log	3.96	66	2.0763	0.415	0.07	0.1075	0.0625	0.0625	0.0625	0.0625	0.255
No log	4.98	83	1.8495	0.5325	0.07	0.1025	0.0625	0.065	0.0625	0.0625	0.3175
No log	6.0	100	1.5493	0.615	0.08	0.1125	0.0625	0.0675	0.0775	0.0625	0.4275
No log	6.96	116	1.3915	0.6275	0.075	0.1125	0.0625	0.065	0.115	0.0625	0.49
No log	7.98	133	1.1837	0.695	0.0725	0.1125	0.0625	0.09	0.12	0.0625	0.58
No log	9.0	150	1.0780	0.715	0.0725	0.1125	0.0675	0.105	0.1625	0.0625	0.6425
No log	9.96	166	0.9851	0.75	0.075	0.1125	0.085	0.1275	0.1825	0.0625	0.67
No log	10.98	183	0.9633	0.7175	0.0775	0.1125	0.1025	0.155	0.2075	0.0625	0.685
No log	12.0	200	0.9930	0.7225	0.08	0.105	0.12	0.2175	0.2275	0.0625	0.7125
No log	12.96	216	0.9389	0.75	0.08	0.1075	0.12	0.3075	0.3225	0.0675	0.73
No log	13.98	233	0.9902	0.735	0.08	0.095	0.1475	0.3675	0.3925	0.0975	0.715
No log	15.0	250	0.9248	0.765	0.08	0.0875	0.1725	0.425	0.445	0.115	0.7625
No log	15.96	266	0.9750	0.7425	0.0825	0.08	0.2425	0.49	0.55	0.1175	0.7325
No log	16.98	283	0.9921	0.7425	0.0775	0.0775	0.2775	0.5225	0.56	0.1375	0.73
No log	18.0	300	0.9683	0.7775	0.08	0.075	0.355	0.555	0.6075	0.2375	0.78
No log	18.96	316	1.0880	0.73	0.0825	0.095	0.4225	0.56	0.6325	0.47	0.735
No log	19.98	333	1.1014	0.7575	0.0775	0.105	0.5125	0.5925	0.68	0.715	0.7525
No log	21.0	350	1.1023	0.7575	0.0775	0.1175	0.5475	0.6125	0.69	0.7375	0.7475
No log	21.96	366	1.1588	0.755	0.0725	0.125	0.5875	0.6275	0.685	0.735	0.75
No log	22.98	383	1.1741	0.76	0.08	0.13	0.59	0.655	0.6875	0.75	0.755
No log	24.0	400	1.2203	0.7575	0.08	0.14	0.6075	0.6625	0.6925	0.7525	0.76
No log	24.96	416	1.2219	0.7525	0.075	0.1525	0.63	0.675	0.705	0.7575	0.755
No log	25.98	433	1.2819	0.7575	0.0725	0.17	0.625	0.675	0.7	0.7575	0.76
No log	27.0	450	1.3932	0.7425	0.06	0.185	0.6425	0.6725	0.68	0.7475	0.74
No log	27.96	466	1.3149	0.76	0.055	0.1925	0.655	0.695	0.6925	0.755	0.76
No log	28.98	483	1.3421	0.7625	0.0575	0.2275	0.65	0.6975	0.6875	0.76	0.76
1.4389	30.0	500	1.3388	0.76	0.055	0.2625	0.68	0.7175	0.705	0.765	0.76
1.4389	30.96	516	1.4119	0.735	0.055	0.2975	0.675	0.715	0.7125	0.735	0.735
1.4389	31.98	533	1.4079	0.7525	0.0525	0.3575	0.695	0.71	0.715	0.7575	0.7475
1.4389	33.0	550	1.4316	0.76	0.0525	0.3975	0.7	0.72	0.7225	0.7575	0.76
1.4389	33.96	566	1.4783	0.7525	0.05	0.4325	0.6975	0.7175	0.705	0.745	0.755
1.4389	34.98	583	1.4989	0.755	0.05	0.465	0.7075	0.72	0.7125	0.7475	0.7575
1.4389	36.0	600	1.5397	0.75	0.0525	0.4875	0.7075	0.725	0.715	0.745	0.7525
1.4389	36.96	616	1.5462	0.7475	0.05	0.5	0.7025	0.72	0.715	0.745	0.7425
1.4389	37.98	633	1.6063	0.74	0.0575	0.53	0.695	0.715	0.6975	0.7375	0.7375
1.4389	39.0	650	1.6784	0.7225	0.0525	0.535	0.7025	0.715	0.715	0.725	0.7225
1.4389	39.96	666	1.6285	0.735	0.055	0.5325	0.71	0.7225	0.715	0.7325	0.7325
1.4389	40.98	683	1.6233	0.7375	0.0525	0.55	0.705	0.7125	0.7	0.7325	0.735
1.4389	42.0	700	1.6116	0.7375	0.0525	0.5575	0.7025	0.7275	0.7175	0.7425	0.74
1.4389	42.96	716	1.7073	0.735	0.0525	0.5575	0.7025	0.7125	0.7075	0.73	0.7375
1.4389	43.98	733	1.7029	0.73	0.055	0.565	0.7025	0.715	0.71	0.7325	0.73
1.4389	45.0	750	1.7378	0.7375	0.055	0.595	0.6925	0.7075	0.6975	0.73	0.735
1.4389	45.96	766	1.7340	0.735	0.0525	0.6	0.7	0.7125	0.695	0.735	0.735
1.4389	46.98	783	1.7457	0.725	0.0525	0.615	0.7	0.71	0.71	0.725	0.7275
1.4389	48.0	800	1.7585	0.735	0.055	0.625	0.7075	0.71	0.7025	0.7375	0.7325
1.4389	48.96	816	1.7471	0.73	0.055	0.6325	0.7	0.7175	0.705	0.73	0.73
1.4389	49.98	833	1.7883	0.7275	0.055	0.6375	0.7075	0.7075	0.7075	0.7275	0.7325
1.4389	51.0	850	1.7675	0.7375	0.0575	0.65	0.7075	0.7125	0.705	0.7375	0.74
1.4389	51.96	866	1.7772	0.7325	0.0525	0.6475	0.7075	0.715	0.7075	0.725	0.73
1.4389	52.98	883	1.7676	0.735	0.0575	0.6475	0.7075	0.715	0.7	0.73	0.735
1.4389	54.0	900	1.7960	0.73	0.0575	0.65	0.7125	0.7125	0.71	0.7225	0.7325
1.4389	54.96	916	1.7900	0.7375	0.0575	0.65	0.71	0.7075	0.71	0.735	0.7425
1.4389	55.98	933	1.7869	0.7275	0.0575	0.6525	0.7025	0.7175	0.705	0.7275	0.73
1.4389	57.0	950	1.7876	0.7325	0.0575	0.6525	0.7075	0.7075	0.71	0.7325	0.735
1.4389	57.6	960	1.7887	0.7325	0.0575	0.6525	0.7075	0.7075	0.7075	0.7325	0.7375

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_2023-09-05_txt_vis_enc_4_5_6_7_11_12_rmp

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

NSDT 3DConvert

UnrealSynth

DreamTexture.js