vit-resnet-mistral-SYDNEY-with-3-captioning

swadhindas324/vit-resnet-mistral-SYDNEY-with-3-captioning

vit-resnet-mistral-SYDNEY-with-3-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

7.2 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: c4929be4

Model card

From the Hugging Face model README

vit-resnet-mistral-SYDNEY-with-3-captioning

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

Loss: 0.5269
Accuracy: 68.02
Bleu-1: 0.8074
Bleu-2: 0.7349
Bleu-3: 0.6646
Bleu-4: 0.6020
Meteor: 0.7862
Rouge-l: 0.7598
Cider: 2.6581

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	0.9244	65.26	0.5296	0.4113	0.3278	0.2564	0.4434	0.4580	0.8508
No log	2.0	88	0.5200	61.75	0.5480	0.4380	0.3590	0.2933	0.4270	0.4606	0.7265
No log	3.0	132	0.4348	66.37	0.6624	0.5612	0.4773	0.4076	0.5768	0.5940	1.5570
No log	4.0	176	0.4120	66.43	0.7949	0.6974	0.6040	0.5115	0.7103	0.6757	2.3639
No log	5.0	220	0.3946	66.85	0.7953	0.7135	0.6310	0.5458	0.7069	0.6669	2.2607
No log	6.0	264	0.3993	68.74	0.8028	0.7101	0.6200	0.5355	0.7145	0.7151	2.3702
No log	7.0	308	0.3904	68.78	0.8026	0.7343	0.6674	0.6066	0.7750	0.7418	2.7676
No log	8.0	352	0.3794	67.55	0.8152	0.7553	0.7051	0.6584	0.8004	0.7528	3.0471
No log	9.0	396	0.3971	69.37	0.8160	0.7418	0.6752	0.6152	0.7714	0.7466	2.5937
No log	10.0	440	0.4194	68.29	0.8218	0.7503	0.6840	0.6201	0.7487	0.7156	2.6796
No log	11.0	484	0.4391	68.53	0.8041	0.7324	0.6656	0.6037	0.7730	0.7339	2.5695
No log	12.0	528	0.4405	69.25	0.7750	0.6772	0.5944	0.5240	0.7151	0.6930	2.2449
No log	13.0	572	0.4355	68.07	0.8078	0.7305	0.6518	0.5786	0.7426	0.7227	2.5123
No log	14.0	616	0.4476	68.79	0.7945	0.7252	0.6570	0.5931	0.7643	0.7263	2.7031
No log	15.0	660	0.4524	67.96	0.7896	0.7089	0.6423	0.5804	0.7542	0.7013	2.3879
No log	16.0	704	0.4639	70.23	0.8157	0.7511	0.6912	0.6367	0.7799	0.7572	2.5914
No log	17.0	748	0.4630	67.49	0.7967	0.7270	0.6583	0.5894	0.7624	0.7246	2.4560
No log	18.0	792	0.4759	69.07	0.8289	0.7570	0.6928	0.6313	0.7719	0.7488	2.7776
No log	19.0	836	0.4637	67.91	0.8189	0.7525	0.6949	0.6416	0.7872	0.7426	2.7667
No log	20.0	880	0.4855	69.05	0.8084	0.7399	0.6751	0.6128	0.7752	0.7404	2.6369
No log	21.0	924	0.4763	68.28	0.7786	0.7104	0.6531	0.6045	0.7798	0.7341	2.6364
No log	22.0	968	0.4705	69.02	0.8065	0.7351	0.6735	0.6161	0.7714	0.7364	2.7665
No log	23.0	1012	0.5032	68.39	0.7794	0.7079	0.6394	0.5760	0.7420	0.7255	2.5956
0.2689	24.0	1056	0.5234	69.45	0.8423	0.7776	0.7159	0.6579	0.7911	0.7698	2.7425
0.2689	25.0	1100	0.4776	68.49	0.8245	0.7628	0.7145	0.6694	0.7993	0.7527	2.9163
0.2689	26.0	1144	0.5117	69.01	0.8190	0.7441	0.6729	0.6090	0.7817	0.7512	2.6523
0.2689	27.0	1188	0.5173	69.44	0.7753	0.6895	0.6186	0.5577	0.7205	0.6969	2.4088
0.2689	28.0	1232	0.5215	69.71	0.7958	0.7307	0.6703	0.6181	0.7756	0.7479	2.7830
0.2689	29.0	1276	0.5321	68.38	0.7979	0.7111	0.6358	0.5674	0.7541	0.7215	2.4415
0.2689	30.0	1320	0.5227	69.07	0.7822	0.7061	0.6380	0.5741	0.7536	0.7201	2.4727
0.2689	31.0	1364	0.5517	68.04	0.7860	0.7113	0.6383	0.5712	0.7473	0.7219	2.4661
0.2689	32.0	1408	0.5093	69.14	0.7840	0.7132	0.6521	0.5977	0.7578	0.7296	2.7266
0.2689	33.0	1452	0.5072	68.37	0.7928	0.7078	0.6335	0.5663	0.7540	0.7238	2.4756
0.2689	34.0	1496	0.5269	68.02	0.8074	0.7349	0.6646	0.6020	0.7862	0.7598	2.6581

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