vit-convnext-mistral-NWPU-with-8-captioning

swadhindas324/vit-convnext-mistral-NWPU-with-8-captioning

vit-convnext-mistral-NWPU-with-8-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

8% of all-time downloads

All-time downloads

147

Public

Parameters

439M

14 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.8 GB · 100%

At a glance

Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Jul 4, 2026
Updated: Jul 4, 2026
SHA: 82476d8d

Model card

From the Hugging Face model README

vit-convnext-mistral-NWPU-with-8-captioning

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

Loss: 0.3627
Accuracy: 86.14
Bleu-1: 0.8559
Bleu-2: 0.7656
Bleu-3: 0.6926
Bleu-4: 0.6335
Meteor: 0.7655
Rouge-l: 0.7523
Cider: 1.7459

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
0.5094	1.0	2215	0.4768	83.03	0.5109	0.3483	0.2381	0.1584	0.4230	0.3778	0.1350
0.4062	2.0	4430	0.3635	84.67	0.8211	0.7131	0.6300	0.5637	0.7108	0.7004	1.5919
0.3331	3.0	6645	0.3266	85.09	0.8316	0.7336	0.6562	0.5940	0.7494	0.7351	1.7243
0.3012	4.0	8860	0.3148	85.49	0.8565	0.7705	0.6989	0.6396	0.7682	0.7558	1.7616
0.2827	5.0	11075	0.3114	85.61	0.8614	0.7732	0.7024	0.6444	0.7692	0.7607	1.7920
0.2676	6.0	13290	0.3126	85.55	0.8530	0.7647	0.6933	0.6352	0.7811	0.7639	1.8152
0.2611	7.0	15505	0.3162	86.13	0.8615	0.7752	0.7052	0.6485	0.7783	0.7632	1.8229
0.2505	8.0	17720	0.3205	86.17	0.8634	0.7785	0.7091	0.6527	0.7755	0.7658	1.8210
0.2399	9.0	19935	0.3252	86.09	0.8652	0.7806	0.7088	0.6495	0.7842	0.7736	1.8123
0.2301	10.0	22150	0.3329	86.1	0.8604	0.7731	0.7032	0.6464	0.7709	0.7608	1.8229
0.2201	11.0	24365	0.3391	86.11	0.8587	0.7713	0.7005	0.6431	0.7767	0.7625	1.8000
0.2109	12.0	26580	0.3498	86.01	0.8513	0.7617	0.6898	0.6316	0.7663	0.7545	1.7468
0.2158	13.0	28795	0.3545	86.3	0.8560	0.7671	0.6934	0.6334	0.7680	0.7560	1.7767
0.2045	14.0	31010	0.3627	86.14	0.8559	0.7656	0.6926	0.6335	0.7655	0.7523	1.7459

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 4, 2026
Updated: Jul 4, 2026