vit-convnext-mistral-SYDNEY-with-5-captioning

swadhindas324/vit-convnext-mistral-SYDNEY-with-5-captioning

vit-convnext-mistral-SYDNEY-with-5-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

9% of all-time downloads

All-time downloads

Public

Parameters

436M

8.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.7 GB · 100%

At a glance

Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Jun 30, 2026
Updated: Jun 30, 2026
SHA: 15e92705

Model card

From the Hugging Face model README

vit-convnext-mistral-SYDNEY-with-5-captioning

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

Loss: 0.4719
Accuracy: 68.21
Bleu-1: 0.7905
Bleu-2: 0.7035
Bleu-3: 0.6310
Bleu-4: 0.5672
Meteor: 0.7413
Rouge-l: 0.7145
Cider: 2.3571

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
No log	1.0	44	0.9231	65.32	0.5321	0.4141	0.3308	0.2599	0.4420	0.4645	0.8607
No log	2.0	88	0.5206	62.06	0.5480	0.4380	0.3590	0.2933	0.4270	0.4606	0.7265
No log	3.0	132	0.4501	66.88	0.6550	0.5569	0.4760	0.4080	0.5652	0.5865	1.5449
No log	4.0	176	0.4289	66.03	0.7800	0.6844	0.5940	0.5075	0.6888	0.6565	2.2382
No log	5.0	220	0.4063	66.68	0.8039	0.7220	0.6396	0.5539	0.7174	0.6700	2.2843
No log	6.0	264	0.4053	67.94	0.7943	0.7016	0.6106	0.5328	0.7177	0.7072	2.2472
No log	7.0	308	0.4070	68.2	0.7921	0.7222	0.6500	0.5816	0.7561	0.7275	2.5189
No log	8.0	352	0.3946	67.96	0.8289	0.7701	0.7190	0.6734	0.8083	0.7632	3.0012
No log	9.0	396	0.4050	67.86	0.8058	0.7287	0.6538	0.5832	0.7576	0.7293	2.6116
No log	10.0	440	0.4304	67.27	0.7947	0.7100	0.6407	0.5773	0.7316	0.6914	2.4231
No log	11.0	484	0.4440	68.12	0.8112	0.7383	0.6818	0.6291	0.7517	0.7218	2.6168
No log	12.0	528	0.4337	69.79	0.8084	0.7268	0.6489	0.5771	0.7550	0.7274	2.6067
No log	13.0	572	0.4419	67.34	0.8273	0.7591	0.6888	0.6163	0.7518	0.7097	2.7129
No log	14.0	616	0.4395	66.85	0.7781	0.7111	0.6506	0.5909	0.7469	0.7038	2.5782
No log	15.0	660	0.4486	69.08	0.8051	0.7316	0.6648	0.5980	0.7567	0.7150	2.5019
No log	16.0	704	0.4660	68.37	0.7925	0.7300	0.6733	0.6231	0.7683	0.7312	2.5630
No log	17.0	748	0.4564	68.81	0.8090	0.7402	0.6781	0.6210	0.7820	0.7488	2.6836
No log	18.0	792	0.4719	68.21	0.7905	0.7035	0.6310	0.5672	0.7413	0.7145	2.3571

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: Jun 30, 2026
Updated: Jun 30, 2026