unt_faqs_model

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

• Loss: 6.1017

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	12	5.4252
No log	2.0	24	4.4929
No log	3.0	36	3.8593
No log	4.0	48	3.1898
No log	5.0	60	3.2708
No log	6.0	72	3.2766
No log	7.0	84	3.6022
No log	8.0	96	3.8336
No log	9.0	108	4.0215
No log	10.0	120	4.1909
No log	11.0	132	4.4297
No log	12.0	144	4.3085
No log	13.0	156	4.4102
No log	14.0	168	4.4956
No log	15.0	180	4.8586
No log	16.0	192	4.8999
No log	17.0	204	4.6935
No log	18.0	216	4.5933
No log	19.0	228	4.5490
No log	20.0	240	4.7068
No log	21.0	252	4.7150
No log	22.0	264	4.9225
No log	23.0	276	4.7852
No log	24.0	288	4.8968
No log	25.0	300	4.9657
No log	26.0	312	5.0764
No log	27.0	324	5.0940
No log	28.0	336	5.1408
No log	29.0	348	5.3001
No log	30.0	360	5.1304
No log	31.0	372	5.4316
No log	32.0	384	5.3884
No log	33.0	396	5.4434
No log	34.0	408	5.3642
No log	35.0	420	5.5924
No log	36.0	432	5.2098
No log	37.0	444	5.3167
No log	38.0	456	5.2808
No log	39.0	468	5.3687
No log	40.0	480	5.4625
No log	41.0	492	5.4122
0.6438	42.0	504	5.4850
0.6438	43.0	516	5.4797
0.6438	44.0	528	5.8061
0.6438	45.0	540	5.8501
0.6438	46.0	552	5.6079
0.6438	47.0	564	5.6625
0.6438	48.0	576	5.7005
0.6438	49.0	588	5.6703
0.6438	50.0	600	5.5704
0.6438	51.0	612	5.7556
0.6438	52.0	624	5.6541
0.6438	53.0	636	5.7571
0.6438	54.0	648	5.8092
0.6438	55.0	660	5.8529
0.6438	56.0	672	5.7974
0.6438	57.0	684	6.0617
0.6438	58.0	696	5.8630
0.6438	59.0	708	5.8652
0.6438	60.0	720	5.9569
0.6438	61.0	732	6.0163
0.6438	62.0	744	5.8635
0.6438	63.0	756	6.1112
0.6438	64.0	768	5.9750
0.6438	65.0	780	5.7267
0.6438	66.0	792	5.9968
0.6438	67.0	804	5.9974
0.6438	68.0	816	5.9145
0.6438	69.0	828	5.8521
0.6438	70.0	840	5.9012
0.6438	71.0	852	5.9272
0.6438	72.0	864	5.9137
0.6438	73.0	876	5.9371
0.6438	74.0	888	5.9811
0.6438	75.0	900	6.0054
0.6438	76.0	912	6.0101
0.6438	77.0	924	6.0301
0.6438	78.0	936	5.9783
0.6438	79.0	948	5.9784
0.6438	80.0	960	6.0630
0.6438	81.0	972	6.1151
0.6438	82.0	984	6.0869
0.6438	83.0	996	6.0823
0.0228	84.0	1008	6.0805
0.0228	85.0	1020	6.0722
0.0228	86.0	1032	6.0623
0.0228	87.0	1044	6.0561
0.0228	88.0	1056	6.0367
0.0228	89.0	1068	6.0342
0.0228	90.0	1080	6.0461
0.0228	91.0	1092	6.0646
0.0228	92.0	1104	6.0780
0.0228	93.0	1116	6.0926
0.0228	94.0	1128	6.0963
0.0228	95.0	1140	6.1009
0.0228	96.0	1152	6.1044
0.0228	97.0	1164	6.1015
0.0228	98.0	1176	6.1014
0.0228	99.0	1188	6.1021
0.0228	100.0	1200	6.1017

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.1+cpu
• Datasets 2.12.0
• Tokenizers 0.13.2