VesleAnne

This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.9711

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
5.3015	0.22	50	4.6180
4.4575	0.44	100	4.1929
4.1257	0.66	150	3.7698
3.8209	0.88	200	3.6617
3.55	1.11	250	3.3673
3.2001	1.33	300	3.1787
3.0574	1.55	350	2.9297
3.0092	1.77	400	2.6812
2.6884	1.99	450	3.1342
2.1791	2.21	500	2.8536
2.0669	2.43	550	2.4897
1.8517	2.65	600	2.5249
1.8483	2.88	650	2.2894
1.5113	3.1	700	2.1788
1.4535	3.32	750	2.0870
1.3109	3.54	800	2.5402
1.3217	3.76	850	2.1795
1.2264	3.98	900	2.2207
1.1269	4.2	950	2.7403
0.9924	4.42	1000	2.7255
1.0717	4.65	1050	3.0009
0.9322	4.87	1100	3.1246
0.9571	5.09	1150	3.4044
1.0463	5.31	1200	3.4533
0.8581	5.53	1250	3.0303
0.642	5.75	1300	3.6659
0.7991	5.97	1350	3.0716
0.4301	6.19	1400	3.3405
0.6194	6.42	1450	3.3413
0.7542	6.64	1500	3.2337
0.7794	6.86	1550	3.9620
0.8369	7.08	1600	3.2489
0.3225	7.3	1650	3.4928
0.4733	7.52	1700	3.3744
0.5242	7.74	1750	3.6537
0.3053	7.96	1800	3.9220
0.3376	8.19	1850	3.7916
0.6053	8.41	1900	3.3018
0.4441	8.63	1950	3.3969
0.3911	8.85	2000	3.3319
0.2184	9.07	2050	3.7348
0.2243	9.29	2100	3.6821
0.2049	9.51	2150	3.9148
0.1885	9.73	2200	4.1785
0.349	9.96	2250	3.9408
0.2324	10.18	2300	4.1387
0.2395	10.4	2350	4.0347
0.2178	10.62	2400	3.9753
0.1087	10.84	2450	4.4449
0.1677	11.06	2500	4.0552
0.1727	11.28	2550	3.9994
0.1876	11.5	2600	4.0458
0.165	11.73	2650	4.0139
0.1279	11.95	2700	4.2826
0.1795	12.17	2750	4.2433
0.1207	12.39	2800	4.3634
0.1421	12.61	2850	4.2781
0.1055	12.83	2900	4.3014
0.1568	13.05	2950	4.0862
0.0823	13.27	3000	4.4141
0.1443	13.5	3050	4.4451
0.0259	13.72	3100	4.6366
0.166	13.94	3150	4.4636
0.0451	14.16	3200	4.5297
0.0459	14.38	3250	4.6649
0.097	14.6	3300	4.6214
0.1233	14.82	3350	4.6148
0.1131	15.04	3400	4.4825
0.0897	15.27	3450	4.6712
0.0251	15.49	3500	4.9292
0.0814	15.71	3550	5.0073
0.0398	15.93	3600	4.9904
0.0165	16.15	3650	4.8615
0.0219	16.37	3700	5.0948
0.0606	16.59	3750	5.0635
0.1226	16.81	3800	5.0042
0.0577	17.04	3850	4.8606
0.0822	17.26	3900	4.8630
0.0288	17.48	3950	4.8891
0.0722	17.7	4000	4.8209
0.0339	17.92	4050	4.8838
0.0687	18.14	4100	4.9312
0.0083	18.36	4150	4.9128
0.02	18.58	4200	4.9771
0.0402	18.81	4250	4.9897
0.0274	19.03	4300	5.0073
0.0159	19.25	4350	5.0235
0.0363	19.47	4400	4.9699
0.0205	19.69	4450	4.9734
0.0213	19.91	4500	4.9711

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1