receipt-core-model

This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7190

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• 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: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
3.0009	1.0	29	1.1423
0.3485	2.0	58	1.1296
0.1717	3.0	87	1.1880
0.1204	4.0	116	1.2580
0.0912	5.0	145	1.2250
0.0801	6.0	174	1.3189
0.0677	7.0	203	1.2968
0.058	8.0	232	1.3284
0.0517	9.0	261	1.3641
0.0441	10.0	290	1.3873
0.0404	11.0	319	1.4239
0.0353	12.0	348	1.4632
0.0324	13.0	377	1.4464
0.0282	14.0	406	1.4695
0.0248	15.0	435	1.4713
0.0234	16.0	464	1.4474
0.0228	17.0	493	1.4191
0.0198	18.0	522	1.4753
0.0203	19.0	551	1.5000
0.0159	20.0	580	1.5167
0.0163	21.0	609	1.4873
0.0177	22.0	638	1.5335
0.0153	23.0	667	1.4642
0.0127	24.0	696	1.4740
0.0118	25.0	725	1.4890
0.0097	26.0	754	1.5592
0.0087	27.0	783	1.5312
0.008	28.0	812	1.5255
0.0083	29.0	841	1.5413
0.0082	30.0	870	1.5408
0.007	31.0	899	1.5491
0.006	32.0	928	1.5660
0.0062	33.0	957	1.5685
0.0053	34.0	986	1.5968
0.0044	35.0	1015	1.5778
0.0046	36.0	1044	1.5743
0.0041	37.0	1073	1.6028
0.0049	38.0	1102	1.5782
0.004	39.0	1131	1.5704
0.004	40.0	1160	1.5804
0.0034	41.0	1189	1.5837
0.0037	42.0	1218	1.5838
0.0037	43.0	1247	1.6018
0.0024	44.0	1276	1.5922
0.0025	45.0	1305	1.5824
0.0036	46.0	1334	1.5884
0.0042	47.0	1363	1.5972
0.0025	48.0	1392	1.5946
0.0023	49.0	1421	1.5923
0.0038	50.0	1450	1.6010
0.0027	51.0	1479	1.5831
0.0053	52.0	1508	1.6958
0.0034	53.0	1537	1.6677
0.003	54.0	1566	1.6849
0.0023	55.0	1595	1.6919
0.0027	56.0	1624	1.6944
0.0023	57.0	1653	1.6739
0.0024	58.0	1682	1.6647
0.0018	59.0	1711	1.6915
0.0016	60.0	1740	1.6705
0.0021	61.0	1769	1.6920
0.002	62.0	1798	1.6965
0.002	63.0	1827	1.6271
0.0017	64.0	1856	1.6795
0.0019	65.0	1885	1.6736
0.0016	66.0	1914	1.7282
0.0025	67.0	1943	1.7446
0.0018	68.0	1972	1.7058
0.0025	69.0	2001	1.6667
0.0022	70.0	2030	1.6680
0.0024	71.0	2059	1.6693
0.0016	72.0	2088	1.6961
0.0026	73.0	2117	1.6914
0.0013	74.0	2146	1.6961
0.0013	75.0	2175	1.6985
0.0008	76.0	2204	1.7127
0.001	77.0	2233	1.7117
0.0016	78.0	2262	1.6930
0.0022	79.0	2291	1.7050
0.001	80.0	2320	1.7253
0.001	81.0	2349	1.7169
0.0016	82.0	2378	1.7116
0.0012	83.0	2407	1.7689
0.0008	84.0	2436	1.8345
0.0012	85.0	2465	1.8240
0.0007	86.0	2494	1.7860
0.0008	87.0	2523	1.7905
0.0007	88.0	2552	1.7736
0.001	89.0	2581	1.7675
0.0029	90.0	2610	1.8951
0.0021	91.0	2639	1.7821
0.0023	92.0	2668	1.8104
0.0018	93.0	2697	1.7326
0.0014	94.0	2726	1.7357
0.0012	95.0	2755	1.7611
0.001	96.0	2784	1.6929
0.0014	97.0	2813	1.7353
0.0011	98.0	2842	1.7296
0.0013	99.0	2871	1.6806
0.0019	100.0	2900	1.7465
0.0012	101.0	2929	1.7528
0.0015	102.0	2958	1.7190

Framework versions

• Transformers 4.48.1
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0