You can deploy this model and start earning money today!

swadhindas324/
vit-convnext-mistral-UCM-with-4-captioning

Name: vit-convnext-mistral-UCM-with-4-captioning
Availability: InStock

transformers

safetensors

vision-encoder-decoder

generated_from_trainer

endpoints_compatible

Views

No views yet

vit-convnext-mistral-UCM-with-4-captioning

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

Loss: 0.4269
Accuracy: 73.77
Bleu-1: 0.8477
Bleu-2: 0.7877
Bleu-3: 0.7380
Bleu-4: 0.6933
Meteor: 0.8266
Rouge-l: 0.8108
Cider: 3.3994

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	0.6421	72.41	0.4181	0.2839	0.2084	0.1564	0.3172	0.3485	0.3577
No log	2.0	296	0.4644	72.0	0.2109	0.1479	0.0942	0.0551	0.1622	0.1858	0.1703
No log	3.0	444	0.4211	70.41	0.5729	0.4740	0.4042	0.3576	0.5119	0.5327	1.6305
No log	4.0	592	0.3564	74.13	0.8243	0.7607	0.7096	0.6649	0.7793	0.7776	3.1917
No log	5.0	740	0.3451	73.38	0.8146	0.7453	0.6897	0.6422	0.7902	0.7801	3.2392
No log	6.0	888	0.3513	73.52	0.8204	0.7622	0.7098	0.6625	0.8110	0.7933	3.2093
0.4504	7.0	1036	0.3390	74.22	0.8449	0.7847	0.7324	0.6854	0.8096	0.8007	3.3328
0.4504	8.0	1184	0.3446	74.17	0.8299	0.7680	0.7157	0.6688	0.7994	0.7880	3.3354
0.4504	9.0	1332	0.3568	74.44	0.8609	0.8123	0.7694	0.7302	0.8429	0.8301	3.5751
0.4504	10.0	1480	0.3538	74.4	0.8414	0.7755	0.7232	0.6766	0.8069	0.7972	3.3696
0.4504	11.0	1628	0.3666	73.81	0.8264	0.7602	0.7049	0.6548	0.8131	0.7920	3.1978
0.4504	12.0	1776	0.3617	74.22	0.8443	0.7904	0.7437	0.7005	0.8165	0.8099	3.3616
0.4504	13.0	1924	0.3904	73.82	0.8204	0.7608	0.7118	0.6696	0.7957	0.7820	3.3069
0.1647	14.0	2072	0.3910	74.4	0.8394	0.7791	0.7288	0.6826	0.8085	0.7897	3.2969
0.1647	15.0	2220	0.3890	74.79	0.8418	0.7793	0.7284	0.6817	0.8151	0.7969	3.4559
0.1647	16.0	2368	0.3939	74.37	0.8664	0.8148	0.7714	0.7306	0.8383	0.8315	3.5477
0.1647	17.0	2516	0.4030	74.34	0.8434	0.7886	0.7420	0.6985	0.8309	0.8138	3.4076
0.1647	18.0	2664	0.4140	73.99	0.8362	0.7768	0.7265	0.6797	0.8280	0.8066	3.3863
0.1647	19.0	2812	0.4168	74.42	0.8481	0.7841	0.7331	0.6878	0.8219	0.8092	3.3647
0.1647	20.0	2960	0.4184	75.11	0.8448	0.7830	0.7345	0.6910	0.8250	0.8146	3.3812
0.1405	21.0	3108	0.4119	73.74	0.8298	0.7727	0.7260	0.6834	0.8223	0.8062	3.3906
0.1405	22.0	3256	0.4180	74.26	0.8388	0.7783	0.7262	0.6770	0.8198	0.8033	3.3782
0.1405	23.0	3404	0.4294	74.22	0.8510	0.7894	0.7382	0.6895	0.8312	0.8171	3.4364
0.1405	24.0	3552	0.4362	74.45	0.8503	0.7914	0.7414	0.6954	0.8340	0.8133	3.4109
0.1405	25.0	3700	0.4429	75.05	0.8654	0.8061	0.7569	0.7113	0.8345	0.8164	3.5129
0.1405	26.0	3848	0.4269	73.77	0.8477	0.7877	0.7380	0.6933	0.8266	0.8108	3.3994

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

swadhindas324/vit-convnext-mistral-UCM-with-4-captioning

vit-convnext-mistral-UCM-with-4-captioning

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

swadhindas324/
vit-convnext-mistral-UCM-with-4-captioning