Modelpublic

swadhindas324/vit-resnet-mistral-RSICD-with-4-captioning

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes4downloads

Model Card

vit-resnet-mistral-RSICD-with-4-captioning

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: 0.8500
—Accuracy: 81.62
—Bleu-1: 0.6071
—Bleu-2: 0.4705
—Bleu-3: 0.3769
—Bleu-4: 0.3091
—Meteor: 0.5647
—Rouge-l: 0.5326
—Cider: 1.6445

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
—trainbatchsize: 64
—evalbatchsize: 64
—seed: 50
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—lrschedulerwarmup_steps: 0.1
—num_epochs: 128
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Meteor	Rouge-l	Cider
No log	1.0	768	0.6892	80.02	0.4668	0.3027	0.2115	0.1537	0.4085	0.3975	0.4800
0.9621	2.0	1536	0.6626	80.02	0.5474	0.3969	0.3025	0.2374	0.5225	0.4851	0.9514
0.4685	3.0	2304	0.6257	81.47	0.6952	0.5703	0.4770	0.4035	0.6808	0.6318	2.1988
0.3468	4.0	3072	0.6766	81.6	0.6792	0.5494	0.4553	0.3820	0.6611	0.6149	2.0585
0.3468	5.0	3840	0.7356	80.72	0.6386	0.5060	0.4140	0.3467	0.6189	0.5652	1.8487
0.2398	6.0	4608	0.7806	81.96	0.6455	0.5102	0.4175	0.3493	0.6118	0.5801	1.8529
0.1895	7.0	5376	0.8330	81.52	0.6266	0.4938	0.4000	0.3314	0.6079	0.5600	1.7289
0.1664	8.0	6144	0.8500	81.62	0.6071	0.4705	0.3769	0.3091	0.5647	0.5326	1.6445

Framework versions

—Transformers 5.12.1
—Pytorch 2.12.1+cu130
—Datasets 5.0.0
—Tokenizers 0.22.2