You can deploy this model and start earning money today!

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

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

transformers

safetensors

vision-encoder-decoder

generated_from_trainer

endpoints_compatible

Views

No views yet

vit-resnet-mistral-UCM-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: 0.3964
Accuracy: 75.21
Bleu-1: 0.8472
Bleu-2: 0.7926
Bleu-3: 0.7468
Bleu-4: 0.7045
Meteor: 0.8371
Rouge-l: 0.8234
Cider: 3.5900

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	0.6536	71.59	0.3841	0.2527	0.1789	0.1282	0.2946	0.3238	0.2676
No log	2.0	296	0.4646	72.14	0.2825	0.1969	0.1307	0.0869	0.2141	0.2374	0.3272
No log	3.0	444	0.4161	70.0	0.6260	0.5455	0.4852	0.4410	0.5859	0.5848	1.9913
No log	4.0	592	0.3540	73.91	0.8091	0.7401	0.6845	0.6358	0.7695	0.7560	3.0698
No log	5.0	740	0.3459	73.75	0.8234	0.7621	0.7140	0.6727	0.8001	0.7888	3.2917
No log	6.0	888	0.3447	73.57	0.8331	0.7803	0.7323	0.6874	0.8344	0.8143	3.4044
0.4486	7.0	1036	0.3400	74.32	0.8602	0.8071	0.7620	0.7216	0.8360	0.8235	3.5290
0.4486	8.0	1184	0.3425	74.06	0.8348	0.7758	0.7249	0.6791	0.8089	0.8007	3.3918
0.4486	9.0	1332	0.3470	74.32	0.8516	0.7963	0.7487	0.7070	0.8344	0.8219	3.4696
0.4486	10.0	1480	0.3501	74.32	0.8386	0.7726	0.7171	0.6676	0.8182	0.8023	3.3117
0.4486	11.0	1628	0.3587	73.99	0.8450	0.7876	0.7384	0.6935	0.8349	0.8171	3.4853
0.4486	12.0	1776	0.3551	73.86	0.8648	0.8071	0.7584	0.7154	0.8378	0.8310	3.5645
0.4486	13.0	1924	0.3828	73.71	0.8463	0.7893	0.7405	0.6968	0.8347	0.8149	3.4868
0.1647	14.0	2072	0.3740	75.4	0.8587	0.8074	0.7626	0.7196	0.8478	0.8277	3.5439
0.1647	15.0	2220	0.3750	75.05	0.8371	0.7747	0.7221	0.6721	0.8214	0.8054	3.4475
0.1647	16.0	2368	0.3844	75.08	0.8558	0.7999	0.7514	0.7069	0.8273	0.8139	3.5475
0.1647	17.0	2516	0.3985	73.9	0.8177	0.7584	0.7107	0.6662	0.8163	0.7931	3.2645
0.1647	18.0	2664	0.4044	73.66	0.8472	0.7866	0.7353	0.6866	0.8334	0.8126	3.4793
0.1647	19.0	2812	0.3926	74.69	0.8592	0.8081	0.7650	0.7234	0.8356	0.8207	3.5878
0.1647	20.0	2960	0.4025	75.34	0.8449	0.7903	0.7465	0.7077	0.8208	0.8143	3.5759
0.1397	21.0	3108	0.3946	73.86	0.8403	0.7899	0.7477	0.7107	0.8376	0.8231	3.5964
0.1397	22.0	3256	0.3964	75.21	0.8472	0.7926	0.7468	0.7045	0.8371	0.8234	3.5900

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-4-tag-supressed-captioning

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