Modelpublic

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

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes3downloads

Model Card

vit-convnext-mistral-RSICD-with-all-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: 0.9457
—Accuracy: 83.3
—Bleu-1: 0.7206
—Bleu-2: 0.5985
—Bleu-3: 0.5032
—Bleu-4: 0.4285
—Meteor: 0.6909
—Rouge-l: 0.6497
—Cider: 2.3592

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	0.6918	80.82	0.4668	0.3027	0.2115	0.1537	0.4085	0.3975	0.4800
0.9613	2.0	1536	0.6654	79.71	0.5529	0.3979	0.2983	0.2293	0.5204	0.4831	0.8729
0.4780	3.0	2304	0.6192	82.27	0.7396	0.6219	0.5283	0.4503	0.6811	0.6570	2.3965
0.3591	4.0	3072	0.6623	84.14	0.7501	0.6341	0.5467	0.4782	0.6538	0.6502	2.4749
0.3591	5.0	3840	0.7271	83.42	0.7515	0.6349	0.5447	0.4745	0.6772	0.6595	2.5529
0.2512	6.0	4608	0.7516	83.98	0.7486	0.6314	0.5404	0.4672	0.6669	0.6535	2.4837
0.1983	7.0	5376	0.8064	84.2	0.7431	0.6226	0.5301	0.4570	0.6838	0.6606	2.5097
0.1730	8.0	6144	0.8239	84.31	0.7464	0.6249	0.5327	0.4616	0.6873	0.6606	2.5639
0.1730	9.0	6912	0.8647	84.05	0.7409	0.6211	0.5280	0.4544	0.6862	0.6597	2.5088
0.1534	10.0	7680	0.8776	84.11	0.7358	0.6144	0.5225	0.4514	0.6954	0.6589	2.4861
0.1468	11.0	8448	0.9117	83.81	0.7241	0.6020	0.5082	0.4351	0.6807	0.6469	2.4261
0.1438	12.0	9216	0.9457	83.3	0.7206	0.5985	0.5032	0.4285	0.6909	0.6497	2.3592

Framework versions

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