You can deploy this model and start earning money today!

swadhindas324/
vit-resnet-mistral-SYDNEY-with-4-tag-supressed-captioning

Name: vit-resnet-mistral-SYDNEY-with-4-tag-supressed-captioning
Availability: InStock

transformers

safetensors

vision-encoder-decoder

generated_from_trainer

endpoints_compatible

Views

No views yet

vit-resnet-mistral-SYDNEY-with-4-tag-supressed-captioning

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

Loss: 0.5243
Accuracy: 68.47
Bleu-1: 0.7971
Bleu-2: 0.7259
Bleu-3: 0.6664
Bleu-4: 0.6148
Meteor: 0.7807
Rouge-l: 0.7446
Cider: 2.7384

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	0.9281	65.6	0.5645	0.4525	0.3706	0.3002	0.4727	0.4947	1.0436
No log	2.0	88	0.5268	61.77	0.5480	0.4380	0.3590	0.2933	0.4270	0.4606	0.7265
No log	3.0	132	0.4461	66.64	0.6619	0.5603	0.4762	0.4067	0.5743	0.5932	1.5562
No log	4.0	176	0.4230	66.5	0.8011	0.7075	0.6170	0.5298	0.7017	0.6710	2.3529
No log	5.0	220	0.4093	66.14	0.7990	0.7203	0.6373	0.5487	0.7212	0.6760	2.2260
No log	6.0	264	0.4075	68.49	0.8093	0.7125	0.6207	0.5363	0.7386	0.7252	2.3150
No log	7.0	308	0.4093	68.92	0.8093	0.7450	0.6817	0.6237	0.7573	0.7376	2.5883
No log	8.0	352	0.3996	67.76	0.8123	0.7455	0.6915	0.6447	0.7790	0.7418	2.8487
No log	9.0	396	0.4150	68.43	0.8197	0.7463	0.6845	0.6269	0.7480	0.7335	2.6748
No log	10.0	440	0.4327	66.59	0.7829	0.7061	0.6424	0.5845	0.7173	0.6920	2.5101
No log	11.0	484	0.4332	68.2	0.8247	0.7468	0.6811	0.6190	0.7865	0.7454	2.6026
No log	12.0	528	0.4355	68.46	0.8024	0.7364	0.6774	0.6260	0.7705	0.7362	2.8168
No log	13.0	572	0.4227	67.6	0.8034	0.7313	0.6566	0.5852	0.7527	0.7215	2.4428
No log	14.0	616	0.4416	68.12	0.7995	0.7240	0.6548	0.5877	0.7578	0.7271	2.5960
No log	15.0	660	0.4817	68.8	0.7863	0.6952	0.6200	0.5504	0.7352	0.7024	2.2065
No log	16.0	704	0.4594	68.71	0.8187	0.7518	0.6915	0.6318	0.7695	0.7353	2.6452
No log	17.0	748	0.4680	68.56	0.8207	0.7366	0.6702	0.6128	0.7572	0.7243	2.6157
No log	18.0	792	0.4807	67.8	0.8057	0.7262	0.6492	0.5745	0.7569	0.7174	2.4850
No log	19.0	836	0.4581	67.69	0.8164	0.7437	0.6795	0.6191	0.7599	0.7202	2.6759
No log	20.0	880	0.4899	70.23	0.8177	0.7454	0.6794	0.6180	0.7699	0.7499	2.6067
No log	21.0	924	0.4802	68.71	0.8106	0.7471	0.6917	0.6414	0.7846	0.7569	2.7053
No log	22.0	968	0.4740	68.76	0.8103	0.7413	0.6836	0.6289	0.7792	0.7484	2.6759
No log	23.0	1012	0.5066	68.49	0.7868	0.7136	0.6485	0.5830	0.7390	0.6961	2.4752
0.2732	24.0	1056	0.4799	68.96	0.8381	0.7843	0.7323	0.6839	0.8165	0.7912	3.0334
0.2732	25.0	1100	0.4920	68.69	0.8104	0.7505	0.6976	0.6476	0.7946	0.7518	2.8785
0.2732	26.0	1144	0.5119	67.68	0.8288	0.7579	0.6910	0.6289	0.7812	0.7560	2.7113
0.2732	27.0	1188	0.4996	69.44	0.7957	0.7178	0.6570	0.6022	0.7565	0.7266	2.7614
0.2732	28.0	1232	0.5136	70.1	0.8196	0.7581	0.6982	0.6401	0.8040	0.7599	2.7475
0.2732	29.0	1276	0.5055	68.83	0.8456	0.7734	0.7109	0.6559	0.7827	0.7505	2.6982
0.2732	30.0	1320	0.5120	68.51	0.8281	0.7684	0.7156	0.6673	0.8004	0.7630	2.9220
0.2732	31.0	1364	0.5256	69.33	0.8437	0.7782	0.7188	0.6644	0.7914	0.7721	2.7471
0.2732	32.0	1408	0.5336	68.65	0.8103	0.7456	0.6851	0.6286	0.7890	0.7491	2.8766
0.2732	33.0	1452	0.5516	68.87	0.8147	0.7474	0.6879	0.6322	0.7686	0.7406	2.7614
0.2732	34.0	1496	0.5243	68.47	0.7971	0.7259	0.6664	0.6148	0.7807	0.7446	2.7384

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

swadhindas324/vit-resnet-mistral-SYDNEY-with-4-tag-supressed-captioning

vit-resnet-mistral-SYDNEY-with-4-tag-supressed-captioning

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

swadhindas324/
vit-resnet-mistral-SYDNEY-with-4-tag-supressed-captioning