You can deploy this model and start earning money today!

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

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

transformers

safetensors

vision-encoder-decoder

generated_from_trainer

endpoints_compatible

Views

No views yet

vit-convnext-mistral-SYDNEY-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: 0.4817
Accuracy: 68.94
Bleu-1: 0.7853
Bleu-2: 0.7091
Bleu-3: 0.6419
Bleu-4: 0.5821
Meteor: 0.7662
Rouge-l: 0.7244
Cider: 2.6920

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	0.9232	65.25	0.5333	0.4166	0.3342	0.2634	0.4432	0.4633	0.8705
No log	2.0	88	0.5180	62.11	0.5480	0.4380	0.3590	0.2933	0.4270	0.4606	0.7265
No log	3.0	132	0.4452	67.0	0.6559	0.5568	0.4762	0.4083	0.5623	0.5855	1.5443
No log	4.0	176	0.4240	66.68	0.7845	0.6895	0.5991	0.5117	0.6917	0.6621	2.3176
No log	5.0	220	0.4053	66.9	0.7977	0.7149	0.6305	0.5426	0.7173	0.6752	2.2180
No log	6.0	264	0.4059	68.15	0.7904	0.6923	0.5990	0.5167	0.7127	0.7010	2.1525
No log	7.0	308	0.4053	67.44	0.7822	0.7012	0.6216	0.5490	0.7382	0.7094	2.2948
No log	8.0	352	0.3871	67.54	0.8181	0.7541	0.6946	0.6435	0.7986	0.7555	2.9078
No log	9.0	396	0.4107	68.05	0.8122	0.7364	0.6730	0.6167	0.7489	0.7236	2.6662
No log	10.0	440	0.4334	67.7	0.8013	0.7099	0.6363	0.5682	0.7392	0.7056	2.4897
No log	11.0	484	0.4355	68.46	0.8223	0.7499	0.6813	0.6212	0.7683	0.7384	2.6141
No log	12.0	528	0.4309	69.66	0.7744	0.6872	0.6142	0.5511	0.7193	0.6898	2.4418
No log	13.0	572	0.4254	67.19	0.8037	0.7389	0.6822	0.6283	0.7751	0.7381	2.7802
No log	14.0	616	0.4403	68.65	0.8070	0.7321	0.6690	0.6089	0.7412	0.7171	2.6453
No log	15.0	660	0.4583	67.17	0.7982	0.7241	0.6500	0.5700	0.7382	0.6833	2.4793
No log	16.0	704	0.4492	67.96	0.8120	0.7466	0.6919	0.6386	0.7815	0.7229	2.7784
No log	17.0	748	0.4668	68.33	0.8293	0.7704	0.7199	0.6768	0.7972	0.7635	3.0215
No log	18.0	792	0.4754	68.8	0.7958	0.7129	0.6355	0.5637	0.7420	0.7191	2.4416
No log	19.0	836	0.4553	67.85	0.7982	0.7232	0.6620	0.6105	0.7609	0.7257	2.5225
No log	20.0	880	0.4749	68.9	0.8154	0.7576	0.7077	0.6609	0.7913	0.7446	2.9853
No log	21.0	924	0.4817	68.55	0.7721	0.6914	0.6271	0.5710	0.7414	0.7026	2.4508
No log	22.0	968	0.4736	69.21	0.8105	0.7537	0.7018	0.6550	0.7838	0.7584	2.9625
No log	23.0	1012	0.5061	67.56	0.8218	0.7625	0.7108	0.6609	0.7706	0.7389	2.9007
0.2727	24.0	1056	0.4840	67.64	0.7929	0.7335	0.6740	0.6200	0.7800	0.7440	2.8012
0.2727	25.0	1100	0.5053	70.11	0.7834	0.7022	0.6343	0.5724	0.7535	0.7241	2.5048
0.2727	26.0	1144	0.5140	67.52	0.8018	0.7288	0.6688	0.6181	0.7714	0.7266	2.5976
0.2727	27.0	1188	0.4817	68.94	0.7853	0.7091	0.6419	0.5821	0.7662	0.7244	2.6920

Framework versions

Transformers 5.12.1
Pytorch 2.12.1+cu130
Datasets 5.0.0
Tokenizers 0.22.2

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

vit-convnext-mistral-SYDNEY-with-4-captioning

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

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