test-model

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: 5.7326

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.5222	0.2212	50	3.3167
0.3741	0.4425	100	3.5175
0.5087	0.6637	150	3.8062
0.7125	0.8850	200	4.1227
0.4148	1.1062	250	4.1049
0.3261	1.3274	300	3.8527
0.3721	1.5487	350	4.1329
0.3444	1.7699	400	4.0143
0.7134	1.9912	450	3.9609
0.2702	2.2124	500	4.3720
0.4396	2.4336	550	4.0561
0.4176	2.6549	600	3.8587
0.3063	2.8761	650	3.7568
0.2262	3.0973	700	4.1540
0.2206	3.3186	750	4.4668
0.3822	3.5398	800	4.1496
0.2665	3.7611	850	4.0747
0.3072	3.9823	900	4.8918
0.2284	4.2035	950	4.1878
0.1628	4.4248	1000	4.7544
0.1525	4.6460	1050	4.5190
0.2555	4.8673	1100	4.3845
0.3933	5.0885	1150	4.0418
0.0484	5.3097	1200	4.6753
0.3433	5.5310	1250	4.1875
0.2453	5.7522	1300	4.1922
0.0677	5.9735	1350	4.7340
0.1835	6.1947	1400	4.6262
0.2394	6.4159	1450	4.4393
0.1599	6.6372	1500	5.3708
0.2705	6.8584	1550	3.9829
0.2067	7.0796	1600	4.3178
0.2859	7.3009	1650	3.7816
0.1232	7.5221	1700	4.1798
0.1811	7.7434	1750	4.3196
0.1274	7.9646	1800	4.6113
0.1361	8.1858	1850	4.2228
0.1533	8.4071	1900	3.8230
0.1179	8.6283	1950	4.0259
0.1265	8.8496	2000	4.8971
0.2258	9.0708	2050	4.7136
0.0998	9.2920	2100	4.8828
0.1154	9.5133	2150	4.2313
0.1426	9.7345	2200	3.8275
0.0924	9.9558	2250	4.2277
0.0889	10.1770	2300	4.0426
0.0495	10.3982	2350	4.2849
0.0538	10.6195	2400	4.6157
0.0318	10.8407	2450	5.0160
0.0957	11.0619	2500	5.1147
0.0417	11.2832	2550	4.8833
0.0244	11.5044	2600	5.1067
0.0799	11.7257	2650	4.8877
0.0365	11.9469	2700	5.0193
0.0901	12.1681	2750	4.7789
0.0088	12.3894	2800	4.7324
0.0498	12.6106	2850	4.6903
0.0809	12.8319	2900	4.4701
0.035	13.0531	2950	4.6233
0.0486	13.2743	3000	4.8579
0.0231	13.4956	3050	4.9399
0.0677	13.7168	3100	4.8829
0.028	13.9381	3150	5.1337
0.0243	14.1593	3200	5.3634
0.0248	14.3805	3250	5.4940
0.0422	14.6018	3300	5.6946
0.0654	14.8230	3350	5.3121
0.0134	15.0442	3400	5.3630
0.0405	15.2655	3450	5.3444
0.0213	15.4867	3500	5.3298
0.0125	15.7080	3550	5.3672
0.0623	15.9292	3600	5.3024
0.0032	16.1504	3650	5.2147
0.0149	16.3717	3700	5.3809
0.0248	16.5929	3750	5.4913
0.03	16.8142	3800	5.3860
0.0007	17.0354	3850	5.3717
0.0032	17.2566	3900	5.5140
0.0029	17.4779	3950	5.4480
0.0055	17.6991	4000	5.4522
0.0349	17.9204	4050	5.5724
0.0007	18.1416	4100	5.6047
0.0006	18.3628	4150	5.6135
0.0007	18.5841	4200	5.6239
0.0077	18.8053	4250	5.6692
0.009	19.0265	4300	5.6640
0.009	19.2478	4350	5.6822
0.0007	19.4690	4400	5.7342
0.0073	19.6903	4450	5.7320
0.015	19.9115	4500	5.7326

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3