Modelpublic

swadhindas324/vit-convnext-mistral-RSICD-with-6-captioning

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes3downloads

Model Card

vit-convnext-mistral-RSICD-with-6-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: 0.8395
—Accuracy: 82.47
—Bleu-1: 0.6648
—Bleu-2: 0.5372
—Bleu-3: 0.4453
—Bleu-4: 0.3753
—Meteor: 0.6335
—Rouge-l: 0.5980
—Cider: 2.0474

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	0.6909	80.86	0.4668	0.3027	0.2115	0.1537	0.4085	0.3975	0.4800
0.9606	2.0	1536	0.6627	79.67	0.5547	0.3996	0.2987	0.2291	0.5223	0.4799	0.8587
0.4759	3.0	2304	0.6243	81.36	0.6953	0.5695	0.4731	0.3970	0.6717	0.6292	2.1478
0.3616	4.0	3072	0.6703	82.11	0.6832	0.5634	0.4753	0.4061	0.6632	0.6252	2.1751
0.3616	5.0	3840	0.7356	81.01	0.6608	0.5326	0.4411	0.3723	0.6484	0.6009	2.0336
0.2488	6.0	4608	0.7569	82.9	0.6904	0.5601	0.4677	0.3972	0.6448	0.6184	2.1698
0.1939	7.0	5376	0.8128	82.5	0.6730	0.5457	0.4532	0.3850	0.6437	0.6046	2.1525
0.1694	8.0	6144	0.8395	82.47	0.6648	0.5372	0.4453	0.3753	0.6335	0.5980	2.0474

Framework versions

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