vit-resnet-mistral-SYDNEY-with-5-captioning

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

vit-resnet-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

2% of all-time downloads

All-time downloads

Public

Parameters

298M

6 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: Jun 30, 2026
Updated: Jun 30, 2026
SHA: 27901e79

Model card

From the Hugging Face model README

vit-resnet-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: 0.4824
Accuracy: 68.23
Bleu-1: 0.7905
Bleu-2: 0.7259
Bleu-3: 0.6670
Bleu-4: 0.6113
Meteor: 0.7557
Rouge-l: 0.7248
Cider: 2.7760

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	0.9248	65.31	0.5252	0.4047	0.3219	0.2509	0.4382	0.4531	0.8224
No log	2.0	88	0.5305	61.37	0.5480	0.4380	0.3590	0.2933	0.4270	0.4606	0.7265
No log	3.0	132	0.4505	66.45	0.6632	0.5628	0.4784	0.4085	0.5755	0.5936	1.5557
No log	4.0	176	0.4265	66.92	0.7869	0.6881	0.5975	0.5105	0.6974	0.6710	2.2781
No log	5.0	220	0.4119	66.7	0.7966	0.7167	0.6315	0.5425	0.7147	0.6772	2.2084
No log	6.0	264	0.4041	67.98	0.8172	0.7314	0.6448	0.5634	0.7418	0.7349	2.4565
No log	7.0	308	0.4058	69.2	0.8005	0.7295	0.6554	0.5859	0.7515	0.7337	2.5251
No log	8.0	352	0.3919	66.7	0.8214	0.7557	0.7029	0.6575	0.7924	0.7575	2.9292
No log	9.0	396	0.4144	67.86	0.8078	0.7302	0.6626	0.6043	0.7681	0.7409	2.6383
No log	10.0	440	0.4445	66.67	0.8124	0.7344	0.6658	0.6047	0.7447	0.7167	2.5420
No log	11.0	484	0.4195	68.09	0.7942	0.7295	0.6724	0.6213	0.7592	0.7297	2.7331
No log	12.0	528	0.4351	69.07	0.8196	0.7448	0.6801	0.6221	0.7974	0.7655	2.7519
No log	13.0	572	0.4621	66.83	0.8059	0.7297	0.6517	0.5748	0.7272	0.7033	2.5973
No log	14.0	616	0.4553	67.78	0.7918	0.7114	0.6353	0.5636	0.7381	0.7181	2.5373
No log	15.0	660	0.4535	68.71	0.8161	0.7376	0.6688	0.6035	0.7763	0.7380	2.4278
No log	16.0	704	0.4663	68.31	0.8076	0.7398	0.6790	0.6250	0.7596	0.7356	2.6741
No log	17.0	748	0.4821	68.69	0.8127	0.7348	0.6572	0.5891	0.7648	0.7345	2.4772
No log	18.0	792	0.4684	68.88	0.8336	0.7614	0.6887	0.6177	0.7711	0.7497	2.6446
No log	19.0	836	0.4446	67.71	0.7819	0.7106	0.6568	0.6108	0.7361	0.6974	2.5762
No log	20.0	880	0.4839	69.17	0.8285	0.7545	0.6865	0.6265	0.7800	0.7549	2.7620
No log	21.0	924	0.4976	67.43	0.8100	0.7374	0.6731	0.6146	0.7653	0.7354	2.6819
No log	22.0	968	0.4824	68.23	0.7905	0.7259	0.6670	0.6113	0.7557	0.7248	2.7760

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