distilbert-base-uncased-finetuned-dob

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0001

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: 128
• eval_batch_size: 128
• 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
0.5564	1.0	10	0.3900
0.3348	2.0	20	0.1773
0.1584	3.0	30	0.0763
0.0758	4.0	40	0.0294
0.0322	5.0	50	0.0055
0.0075	6.0	60	0.0023
0.0035	7.0	70	0.0015
0.0021	8.0	80	0.0011
0.0013	9.0	90	0.0009
0.0011	10.0	100	0.0008
0.0009	11.0	110	0.0008
0.0009	12.0	120	0.0007
0.0008	13.0	130	0.0006
0.0008	14.0	140	0.0006
0.0007	15.0	150	0.0006
0.0007	16.0	160	0.0005
0.0006	17.0	170	0.0005
0.0006	18.0	180	0.0005
0.0005	19.0	190	0.0004
0.0005	20.0	200	0.0004
0.0005	21.0	210	0.0004
0.0005	22.0	220	0.0004
0.0005	23.0	230	0.0004
0.0004	24.0	240	0.0004
0.0004	25.0	250	0.0003
0.0004	26.0	260	0.0003
0.0004	27.0	270	0.0003
0.0004	28.0	280	0.0003
0.0003	29.0	290	0.0003
0.0003	30.0	300	0.0003
0.0003	31.0	310	0.0003
0.0004	32.0	320	0.0003
0.0003	33.0	330	0.0003
0.0003	34.0	340	0.0003
0.0003	35.0	350	0.0003
0.0003	36.0	360	0.0003
0.0003	37.0	370	0.0002
0.0003	38.0	380	0.0002
0.0003	39.0	390	0.0002
0.0003	40.0	400	0.0002
0.0003	41.0	410	0.0002
0.0003	42.0	420	0.0002
0.0002	43.0	430	0.0002
0.0002	44.0	440	0.0002
0.0002	45.0	450	0.0002
0.0002	46.0	460	0.0002
0.0002	47.0	470	0.0002
0.0002	48.0	480	0.0002
0.0002	49.0	490	0.0002
0.0002	50.0	500	0.0002
0.0002	51.0	510	0.0002
0.0002	52.0	520	0.0002
0.0002	53.0	530	0.0002
0.0002	54.0	540	0.0002
0.0002	55.0	550	0.0002
0.0002	56.0	560	0.0002
0.0002	57.0	570	0.0002
0.0002	58.0	580	0.0002
0.0002	59.0	590	0.0002
0.0002	60.0	600	0.0002
0.0002	61.0	610	0.0002
0.0002	62.0	620	0.0002
0.0002	63.0	630	0.0002
0.0002	64.0	640	0.0002
0.0002	65.0	650	0.0002
0.0002	66.0	660	0.0002
0.0002	67.0	670	0.0002
0.0002	68.0	680	0.0002
0.0002	69.0	690	0.0002
0.0002	70.0	700	0.0002
0.0002	71.0	710	0.0002
0.0002	72.0	720	0.0002
0.0002	73.0	730	0.0002
0.0002	74.0	740	0.0002
0.0001	75.0	750	0.0002
0.0002	76.0	760	0.0002
0.0002	77.0	770	0.0002
0.0001	78.0	780	0.0002
0.0002	79.0	790	0.0002
0.0002	80.0	800	0.0002
0.0001	81.0	810	0.0002
0.0002	82.0	820	0.0002
0.0001	83.0	830	0.0001
0.0001	84.0	840	0.0001
0.0001	85.0	850	0.0001
0.0001	86.0	860	0.0001
0.0001	87.0	870	0.0001
0.0001	88.0	880	0.0001
0.0001	89.0	890	0.0001
0.0001	90.0	900	0.0001
0.0001	91.0	910	0.0001
0.0001	92.0	920	0.0001
0.0001	93.0	930	0.0001
0.0001	94.0	940	0.0001
0.0001	95.0	950	0.0001
0.0001	96.0	960	0.0001
0.0001	97.0	970	0.0001
0.0001	98.0	980	0.0001
0.0001	99.0	990	0.0001
0.0001	100.0	1000	0.0001

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.0