convnext-Mistral-SYDNEY-without-captioning

swadhindas324/convnext-Mistral-SYDNEY-without-captioning

convnext-Mistral-SYDNEY-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

1% of all-time downloads

All-time downloads

366

Public

Parameters

328M

9.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.3 GB · 100%

At a glance

Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Jul 15, 2026
Updated: Jul 15, 2026
SHA: 94c11eb3

Model card

From the Hugging Face model README

convnext-Mistral-SYDNEY-without-captioning

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

Loss: 0.9459
Accuracy: 68.81
Bleu-1: 0.7168
Bleu-2: 0.6146
Bleu-3: 0.5313
Bleu-4: 0.4543
Meteor: 0.6887
Rouge-l: 0.6507
Cider: 1.9765

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	3.9084	36.69	0.1665	0.0741	0.0170	0.0046	0.1389	0.2089	0.0274
No log	2.0	88	3.5424	47.43	0.1943	0.1121	0.0409	0.0094	0.1601	0.2109	0.0786
No log	3.0	132	1.4566	60.9	0.6464	0.5515	0.4688	0.3995	0.5554	0.5497	1.3515
No log	4.0	176	0.9469	64.89	0.7441	0.6529	0.5699	0.4942	0.6543	0.6503	1.9387
No log	5.0	220	0.7886	67.25	0.7828	0.7012	0.6175	0.5376	0.7258	0.7021	2.3285
No log	6.0	264	0.7919	67.48	0.7826	0.6961	0.6063	0.5248	0.7156	0.7056	2.2648
No log	7.0	308	0.7780	68.39	0.7971	0.7274	0.6588	0.5967	0.7577	0.7313	2.5490
No log	8.0	352	0.7723	63.78	0.8076	0.7410	0.6792	0.6249	0.7533	0.7255	2.5111
No log	9.0	396	0.8044	69.5	0.7899	0.7204	0.6630	0.6098	0.7387	0.7307	2.8213
No log	10.0	440	0.8435	68.36	0.7897	0.7119	0.6340	0.5622	0.7071	0.6911	2.3768
No log	11.0	484	0.8360	68.2	0.7820	0.6960	0.6150	0.5425	0.7195	0.6981	2.2970
No log	12.0	528	0.8246	68.0	0.7900	0.6851	0.6023	0.5304	0.7234	0.6810	2.2381
No log	13.0	572	0.8710	67.37	0.8043	0.7275	0.6612	0.6002	0.7338	0.7137	2.5321
No log	14.0	616	0.8840	65.62	0.7449	0.6562	0.5840	0.5210	0.6817	0.6543	2.3151
No log	15.0	660	0.8546	67.49	0.7737	0.6965	0.6248	0.5606	0.7120	0.6875	2.4416
No log	16.0	704	0.8597	67.69	0.8280	0.7411	0.6783	0.6263	0.7442	0.7132	2.5470
No log	17.0	748	0.9459	68.81	0.7168	0.6146	0.5313	0.4543	0.6887	0.6507	1.9765

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