Modelpublic

CodeIsAbstract/HybridModelScratch_lightn_Conti

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes5downloads

Model Card

HybridModelScratchlightnConti

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 3.2749
—Accuracy: 0.3848

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: 0.001
—trainbatchsize: 120
—evalbatchsize: 16
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: cosine
—lrschedulerwarmup_steps: 150
—training_steps: 50000

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
4.5799	0.02	1000	0.2697	4.5051
4.1703	0.04	2000	0.3056	4.1036
4.0044	0.06	3000	0.3195	3.9451
3.8638	0.08	4000	0.3281	3.8499
3.7991	0.1	5000	0.3350	3.7702
3.6996	0.12	6000	0.3414	3.7112
3.6319	0.14	7000	0.3448	3.6666
3.6062	0.16	8000	0.3476	3.6405
3.6643	0.18	9000	0.3498	3.6175
3.5992	0.2	10000	0.3535	3.5797
3.5671	0.22	11000	0.3559	3.5543
3.5230	0.24	12000	0.3578	3.5308
3.5930	0.26	13000	0.3593	3.5190
3.5475	0.28	14000	0.3616	3.4961
3.5220	0.3	15000	0.3633	3.4778
3.5050	0.32	16000	0.3644	3.4654
3.4776	0.34	17000	0.3666	3.4458
3.4829	0.36	18000	0.3674	3.4346
3.4483	0.38	19000	0.3694	3.4189
3.4418	0.4	20000	0.3704	3.4063
3.4183	0.42	21000	0.3720	3.3956
3.3858	0.44	22000	0.3725	3.3870
3.3654	0.46	23000	0.3728	3.3824
3.3943	0.48	24000	0.3734	3.3756
3.3957	0.5	25000	0.3757	3.3548
3.3787	0.52	26000	0.3769	3.3452
3.3605	0.54	27000	0.3777	3.3393
3.3707	0.56	28000	0.3787	3.3302
3.3508	0.58	29000	0.3793	3.3221
3.3566	0.6	30000	0.3802	3.3148
3.3441	0.62	31000	0.3809	3.3054
3.3268	0.64	32000	0.3814	3.3028
3.0620	0.02	33000	3.3109	0.3804
3.0159	0.04	34000	3.3074	0.3810
3.0230	0.06	35000	3.3025	0.3815
3.0335	0.08	36000	3.2988	0.3821
3.0098	0.1	37000	3.2959	0.3826
3.0096	0.12	38000	3.2932	0.3826
2.9760	0.14	39000	3.2904	0.3831
2.9701	0.16	40000	3.2869	0.3832
2.9654	0.18	41000	3.2847	0.3837
2.9752	0.2	42000	3.2823	0.3839
2.9480	0.22	43000	3.2810	0.3840
2.9637	0.24	44000	3.2790	0.3842
2.9721	0.26	45000	3.2772	0.3843
2.9694	0.28	46000	3.2765	0.3847
2.9577	0.3	47000	3.2756	0.3847
2.9573	0.32	48000	3.2751	0.3847
2.9537	0.34	49000	3.2749	0.3848
2.9677	0.36	50000	3.2749	0.3848

Framework versions

—Transformers 5.13.0
—Pytorch 2.8.0+cu128
—Datasets 5.0.0
—Tokenizers 0.22.2