You can deploy this model and start earning money today!

swadhindas324/
vit-resnet-mistral-UCM-with-all-captioning

Name: vit-resnet-mistral-UCM-with-all-captioning
Availability: InStock

transformers

safetensors

vision-encoder-decoder

generated_from_trainer

endpoints_compatible

Views

No views yet

vit-resnet-mistral-UCM-with-all-captioning

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

Loss: 0.4433
Accuracy: 75.85
Bleu-1: 0.856
Bleu-2: 0.7986
Bleu-3: 0.7519
Bleu-4: 0.7081
Meteor: 0.8220
Rouge-l: 0.8172
Cider: 3.5494

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	0.6535	72.44	0.4122	0.2818	0.2051	0.1519	0.3152	0.3481	0.3395
No log	2.0	296	0.4715	71.82	0.2959	0.1985	0.1264	0.0810	0.2092	0.2410	0.2590
No log	3.0	444	0.4170	70.81	0.6443	0.5634	0.5067	0.4654	0.5964	0.6071	2.1635
No log	4.0	592	0.3568	73.94	0.8182	0.7510	0.6967	0.6468	0.7836	0.7725	3.1108
No log	5.0	740	0.3441	73.69	0.8322	0.7715	0.7210	0.6751	0.8011	0.7912	3.2036
No log	6.0	888	0.3483	73.61	0.8319	0.7807	0.7339	0.6911	0.8301	0.8152	3.3627
0.4515	7.0	1036	0.3488	74.56	0.8574	0.8037	0.7603	0.7211	0.8338	0.8147	3.5405
0.4515	8.0	1184	0.3497	74.4	0.8476	0.7974	0.7532	0.7115	0.8288	0.8195	3.5229
0.4515	9.0	1332	0.3594	74.72	0.8589	0.8084	0.7641	0.7249	0.8208	0.8164	3.4768
0.4515	10.0	1480	0.3555	74.29	0.8419	0.7834	0.7348	0.6920	0.8236	0.8138	3.3339
0.4515	11.0	1628	0.3554	74.36	0.8284	0.7662	0.7144	0.6647	0.8226	0.8012	3.3010
0.4515	12.0	1776	0.3648	73.6	0.8491	0.7934	0.7469	0.7038	0.8125	0.8120	3.4218
0.4515	13.0	1924	0.3775	73.6	0.8284	0.7651	0.7156	0.6700	0.8091	0.7964	3.3573
0.1649	14.0	2072	0.3816	74.94	0.8587	0.8022	0.7525	0.7041	0.8376	0.8224	3.4485
0.1649	15.0	2220	0.3855	75.01	0.8422	0.7853	0.7385	0.6957	0.8115	0.8013	3.4637
0.1649	16.0	2368	0.3995	74.38	0.8325	0.7737	0.7236	0.6763	0.8135	0.7980	3.3184
0.1649	17.0	2516	0.4062	74.88	0.8646	0.8096	0.7623	0.7196	0.8454	0.8243	3.5141
0.1649	18.0	2664	0.4146	75.11	0.8612	0.8087	0.7635	0.7237	0.8372	0.8278	3.5472
0.1649	19.0	2812	0.4105	74.8	0.8548	0.7958	0.7453	0.6966	0.8251	0.8138	3.4701
0.1649	20.0	2960	0.4122	74.06	0.8459	0.7878	0.7378	0.6924	0.8276	0.8102	3.4003
0.1404	21.0	3108	0.4200	73.55	0.8361	0.7699	0.7161	0.6649	0.8175	0.8040	3.3310
0.1404	22.0	3256	0.4242	74.99	0.8549	0.7999	0.7507	0.7060	0.8329	0.8233	3.5677
0.1404	23.0	3404	0.4304	73.99	0.8516	0.7953	0.7471	0.7004	0.8129	0.8076	3.3200
0.1404	24.0	3552	0.4328	74.8	0.8493	0.7954	0.7489	0.7062	0.8293	0.8158	3.4241
0.1404	25.0	3700	0.4354	74.95	0.8422	0.7877	0.7408	0.6983	0.8206	0.8043	3.3908
0.1404	26.0	3848	0.4230	74.62	0.8548	0.7984	0.7521	0.7112	0.8362	0.8197	3.5196
0.1404	27.0	3996	0.4267	74.96	0.8410	0.7855	0.7373	0.6922	0.8086	0.7982	3.3668
0.1324	28.0	4144	0.4433	75.85	0.856	0.7986	0.7519	0.7081	0.8220	0.8172	3.5494

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

swadhindas324/vit-resnet-mistral-UCM-with-all-captioning

vit-resnet-mistral-UCM-with-all-captioning

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

swadhindas324/
vit-resnet-mistral-UCM-with-all-captioning