README.md

metadata

library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: vit_focus
    results: []

vit_focus

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

• Loss: 0.0599
• Mse: 0.1695
• Mae: 0.3672

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae
No log	1.0	2	0.1236	0.2098	0.4114
No log	2.0	4	0.1196	0.2083	0.4100
No log	3.0	6	0.1133	0.2058	0.4075
No log	4.0	8	0.1060	0.2028	0.4042
No log	5.0	10	0.1033	0.2020	0.4024
No log	6.0	12	0.0938	0.1972	0.3968
No log	7.0	14	0.1082	0.2021	0.4018
No log	8.0	16	0.0798	0.1897	0.3890
No log	9.0	18	0.1011	0.1983	0.3964
No log	10.0	20	0.0874	0.1913	0.3888
No log	11.0	22	0.0687	0.1811	0.3799
No log	12.0	24	0.0812	0.1892	0.3876
No log	13.0	26	0.0704	0.1831	0.3812
No log	14.0	28	0.0579	0.1744	0.3713
No log	15.0	30	0.0678	0.1791	0.3762
No log	16.0	32	0.0881	0.1883	0.3863
No log	17.0	34	0.0960	0.1896	0.3880
No log	18.0	36	0.0696	0.1776	0.3753
No log	19.0	38	0.0576	0.1716	0.3692
No log	20.0	40	0.0585	0.1720	0.3697
No log	21.0	42	0.0710	0.1792	0.3773
No log	22.0	44	0.0815	0.1843	0.3829
No log	23.0	46	0.0686	0.1737	0.3710
No log	24.0	48	0.0674	0.1734	0.3704
0.118	25.0	50	0.0707	0.1776	0.3757
0.118	26.0	52	0.0753	0.1817	0.3804
0.118	27.0	54	0.0708	0.1787	0.3771
0.118	28.0	56	0.0637	0.1721	0.3699
0.118	29.0	58	0.0599	0.1695	0.3672
0.118	30.0	60	0.0627	0.1731	0.3711
0.118	31.0	62	0.0693	0.1786	0.3770
0.118	32.0	64	0.0738	0.1799	0.3781
0.118	33.0	66	0.0730	0.1773	0.3752
0.118	34.0	68	0.0684	0.1735	0.3711
0.118	35.0	70	0.0642	0.1702	0.3673
0.118	36.0	72	0.0641	0.1721	0.3694
0.118	37.0	74	0.0687	0.1758	0.3737
0.118	38.0	76	0.0739	0.1788	0.3772
0.118	39.0	78	0.0706	0.1765	0.3748
0.118	40.0	80	0.0665	0.1726	0.3704
0.118	41.0	82	0.0642	0.1703	0.3677
0.118	42.0	84	0.0659	0.1719	0.3695
0.118	43.0	86	0.0682	0.1743	0.3721
0.118	44.0	88	0.0723	0.1776	0.3759
0.118	45.0	90	0.0730	0.1778	0.3761
0.118	46.0	92	0.0738	0.1775	0.3757
0.118	47.0	94	0.0743	0.1770	0.3751
0.118	48.0	96	0.0743	0.1766	0.3747
0.118	49.0	98	0.0737	0.1764	0.3746
0.0449	50.0	100	0.0729	0.1760	0.3741

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0
• Datasets 3.5.1
• Tokenizers 0.21.1