vit-resnet-Mistral-NWPU-without-captioning

swadhindas324/vit-resnet-Mistral-NWPU-without-captioning

vit-resnet-Mistral-NWPU-without-captioning is a machine learning model from swadhindas324. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

2% of all-time downloads

All-time downloads

220

Public

Parameters

300M

8.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.2 GB · 100%

At a glance

Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Jul 15, 2026
Updated: Jul 15, 2026
SHA: b90e5784

Model card

From the Hugging Face model README

vit-resnet-Mistral-NWPU-without-captioning

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

Loss: 0.7079
Accuracy: 85.94
Bleu-1: 0.8500
Bleu-2: 0.7618
Bleu-3: 0.6909
Bleu-4: 0.6332
Meteor: 0.7684
Rouge-l: 0.7556
Cider: 1.7413

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
train_batch_size: 64
eval_batch_size: 64
seed: 50
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 128
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Meteor	Rouge-l	Cider
0.9127	1.0	2215	0.8689	84.17	0.5549	0.3816	0.2652	0.1805	0.4389	0.4025	0.1819
0.7059	2.0	4430	0.6550	84.6	0.8223	0.7142	0.6290	0.5610	0.7258	0.7089	1.6245
0.6142	3.0	6645	0.6157	84.96	0.8269	0.7306	0.6527	0.5890	0.7483	0.7348	1.7100
0.5684	4.0	8860	0.6006	85.37	0.8558	0.7709	0.6993	0.6397	0.7713	0.7578	1.7633
0.5357	5.0	11075	0.5992	85.66	0.8645	0.7792	0.7089	0.6509	0.7724	0.7640	1.8052
0.5069	6.0	13290	0.6032	85.47	0.8506	0.7615	0.6890	0.6302	0.7823	0.7607	1.8042
0.4967	7.0	15505	0.6158	86.07	0.8582	0.7719	0.7019	0.6447	0.7765	0.7602	1.8124
0.4756	8.0	17720	0.6284	86.13	0.8635	0.7792	0.7112	0.6557	0.7826	0.7700	1.8368
0.4550	9.0	19935	0.6379	86.19	0.8629	0.7776	0.7054	0.6459	0.7841	0.7717	1.8001
0.4365	10.0	22150	0.6479	86.1	0.8595	0.7737	0.7043	0.6483	0.7751	0.7624	1.8366
0.4186	11.0	24365	0.6591	86.2	0.8599	0.7736	0.7035	0.6467	0.7816	0.7676	1.8304
0.4027	12.0	26580	0.6891	85.95	0.8482	0.7565	0.6829	0.6235	0.7663	0.7507	1.7277
0.4155	13.0	28795	0.6964	86.23	0.8496	0.7584	0.6846	0.6247	0.7578	0.7448	1.7463
0.3958	14.0	31010	0.7079	85.94	0.8500	0.7618	0.6909	0.6332	0.7684	0.7556	1.7413

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

Library: transformers
Type: vision-encoder-decoder
Created: Jul 15, 2026
Updated: Jul 15, 2026