vit-resnet-Mistral-SYDNEY-without-captioning

swadhindas324/vit-resnet-Mistral-SYDNEY-without-captioning

vit-resnet-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

0% of all-time downloads

All-time downloads

1.3K

Public

Parameters

298M

10.7 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: Jul 15, 2026
Updated: Jul 15, 2026
SHA: 31072c5b

Model card

From the Hugging Face model README

vit-resnet-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: 0.9681
Accuracy: 68.56
Bleu-1: 0.7787
Bleu-2: 0.6903
Bleu-3: 0.6233
Bleu-4: 0.5656
Meteor: 0.7394
Rouge-l: 0.7063
Cider: 2.5903

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	1.2399	65.66	0.5451	0.4295	0.3473	0.2766	0.4585	0.4791	0.9797
No log	2.0	88	0.6969	65.82	0.6036	0.5017	0.4237	0.3578	0.5013	0.5334	1.2560
No log	3.0	132	0.6610	65.95	0.7412	0.6458	0.5571	0.4783	0.6493	0.6311	1.9577
No log	4.0	176	0.6637	67.35	0.7964	0.7029	0.6165	0.5383	0.6982	0.7003	2.3030
No log	5.0	220	0.6533	65.87	0.7936	0.7178	0.6409	0.5624	0.7263	0.6811	2.2026
No log	6.0	264	0.6650	67.88	0.7823	0.6955	0.6124	0.5354	0.7148	0.7078	2.2586
No log	7.0	308	0.6896	68.74	0.8037	0.7353	0.6764	0.6235	0.7548	0.7334	2.8266
No log	8.0	352	0.6931	67.62	0.8123	0.7431	0.6788	0.6195	0.7761	0.7464	2.5703
No log	9.0	396	0.7316	67.76	0.8005	0.7303	0.6694	0.6142	0.7620	0.7289	2.7284
No log	10.0	440	0.7723	67.37	0.7628	0.6685	0.5936	0.5358	0.7176	0.6802	2.4814
No log	11.0	484	0.8144	68.96	0.7903	0.7165	0.6529	0.5939	0.7570	0.7239	2.6379
No log	12.0	528	0.7906	70.1	0.8121	0.7361	0.6756	0.6247	0.7681	0.7363	2.7043
No log	13.0	572	0.7732	67.49	0.8060	0.7216	0.6483	0.5773	0.7581	0.7081	2.3343
No log	14.0	616	0.8243	67.94	0.8134	0.7444	0.6825	0.6227	0.7592	0.7328	2.9149
No log	15.0	660	0.8511	68.97	0.7843	0.6943	0.6193	0.5493	0.7380	0.7003	2.2574
No log	16.0	704	0.8239	68.68	0.7696	0.6909	0.6316	0.5803	0.7657	0.7183	2.5587
No log	17.0	748	0.8697	66.65	0.7676	0.6834	0.6163	0.5566	0.7302	0.6859	2.4938
No log	18.0	792	0.8184	67.96	0.8038	0.7454	0.6919	0.6427	0.7787	0.7466	2.9091
No log	19.0	836	0.8239	68.03	0.7946	0.7197	0.6581	0.6038	0.7662	0.7319	2.4666
No log	20.0	880	0.8709	68.8	0.8224	0.7584	0.7059	0.6595	0.7853	0.7607	2.9884
No log	21.0	924	0.9301	67.21	0.7949	0.7182	0.6512	0.5894	0.7742	0.7350	2.5431
No log	22.0	968	0.9047	68.6	0.7876	0.7035	0.6323	0.5646	0.7367	0.7062	2.2402
No log	23.0	1012	0.9427	67.56	0.8077	0.7354	0.6659	0.5967	0.7613	0.7160	2.6634
0.4198	24.0	1056	0.9053	69.09	0.8264	0.7600	0.6962	0.6345	0.7690	0.7507	2.6222
0.4198	25.0	1100	0.9894	68.78	0.7924	0.7097	0.6359	0.5683	0.7548	0.7203	2.4229
0.4198	26.0	1144	0.9599	68.56	0.7929	0.7130	0.6433	0.5793	0.7636	0.7267	2.5887
0.4198	27.0	1188	0.9524	69.19	0.7798	0.6941	0.6227	0.5612	0.7377	0.7159	2.5883
0.4198	28.0	1232	0.9933	69.11	0.8	0.7339	0.6721	0.6115	0.7779	0.7306	2.7312
0.4198	29.0	1276	0.9040	68.07	0.7725	0.6910	0.6281	0.5736	0.7156	0.6912	2.5760
0.4198	30.0	1320	0.9681	68.56	0.7787	0.6903	0.6233	0.5656	0.7394	0.7063	2.5903

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