vit-convnext-mistral-UCM-with-7-captioning

swadhindas324/vit-convnext-mistral-UCM-with-7-captioning

vit-convnext-mistral-UCM-with-7-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

128

Public

Parameters

436M

10.5 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: Jul 2, 2026
Updated: Jul 2, 2026
SHA: d85a7394

Model card

From the Hugging Face model README

vit-convnext-mistral-UCM-with-7-captioning

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

Loss: 0.3999
Accuracy: 74.24
Bleu-1: 0.8516
Bleu-2: 0.7966
Bleu-3: 0.7503
Bleu-4: 0.7068
Meteor: 0.8386
Rouge-l: 0.8222
Cider: 3.5380

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	148	0.6484	72.33	0.4163	0.2846	0.2094	0.1568	0.3218	0.3495	0.3547
No log	2.0	296	0.4700	71.95	0.2299	0.1572	0.0969	0.0569	0.1776	0.2027	0.2084
No log	3.0	444	0.4302	70.48	0.6147	0.5243	0.4584	0.4116	0.5593	0.5731	1.8693
No log	4.0	592	0.3586	73.48	0.8141	0.7455	0.6894	0.6408	0.7721	0.7639	3.0535
No log	5.0	740	0.3448	73.73	0.8245	0.7591	0.7056	0.6604	0.7992	0.7874	3.2681
No log	6.0	888	0.3506	73.61	0.8219	0.7649	0.7137	0.6662	0.8099	0.7968	3.2637
0.4543	7.0	1036	0.3448	74.89	0.8640	0.8095	0.7616	0.7163	0.8403	0.8239	3.4456
0.4543	8.0	1184	0.3494	74.61	0.8484	0.7957	0.7501	0.7077	0.8207	0.8148	3.5181
0.4543	9.0	1332	0.3554	74.86	0.8573	0.8049	0.7578	0.7137	0.8245	0.8171	3.4658
0.4543	10.0	1480	0.3650	74.48	0.8432	0.7793	0.7278	0.6810	0.8064	0.7971	3.3423
0.4543	11.0	1628	0.3697	74.26	0.8413	0.7834	0.7322	0.6857	0.8377	0.8187	3.5078
0.4543	12.0	1776	0.3592	73.47	0.8308	0.7719	0.7201	0.6727	0.8155	0.8075	3.3047
0.4543	13.0	1924	0.3769	74.21	0.8352	0.7752	0.7261	0.6831	0.8198	0.8058	3.3604
0.1652	14.0	2072	0.3875	74.57	0.8249	0.7673	0.7180	0.6698	0.8049	0.7910	3.2726
0.1652	15.0	2220	0.3928	74.5	0.8404	0.7820	0.7311	0.6833	0.8207	0.8081	3.3728
0.1652	16.0	2368	0.3908	74.94	0.8572	0.8047	0.7593	0.7197	0.8264	0.8204	3.4894
0.1652	17.0	2516	0.3999	74.24	0.8516	0.7966	0.7503	0.7068	0.8386	0.8222	3.5380

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 2, 2026
Updated: Jul 2, 2026