You can deploy this model and start earning money today!

swadhindas324/
vit-resnet-mistral-NWPU-with-8-loss-supressed-captioning

Name: vit-resnet-mistral-NWPU-with-8-loss-supressed-captioning
Availability: InStock

Views

No views yet

vit-resnet-mistral-NWPU-with-8-loss-supressed-captioning

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

More information needed

More information needed

More information needed

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 Loss	Epoch	Step	Validation Loss	Accuracy	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Meteor	Rouge-l	Cider
0.9125	1.0	2215	0.8700	83.9	0.5527	0.3777	0.2615	0.1786	0.4388	0.4015	0.1724
0.7063	2.0	4430	0.6551	84.86	0.8295	0.7253	0.6432	0.5775	0.7278	0.7152	1.6655
0.6141	3.0	6645	0.6163	85.13	0.8301	0.7330	0.6549	0.5918	0.7481	0.7353	1.7171
0.5686	4.0	8860	0.6017	85.49	0.8609	0.7769	0.7065	0.6477	0.7718	0.7604	1.7921
0.5364	5.0	11075	0.5999	85.71	0.8647	0.7804	0.7110	0.6540	0.7719	0.7653	1.8137
0.5077	6.0	13290	0.6022	85.62	0.8545	0.7675	0.6963	0.6383	0.7799	0.7630	1.8127
0.4971	7.0	15505	0.6174	86.16	0.8622	0.7733	0.7012	0.6423	0.7763	0.7615	1.8195
0.4761	8.0	17720	0.6287	86.09	0.8618	0.7768	0.7086	0.6527	0.7743	0.7636	1.8237
0.4554	9.0	19935	0.6336	86.24	0.8698	0.7871	0.7171	0.6590	0.7863	0.7759	1.8337
0.4373	10.0	22150	0.6478	86.28	0.8655	0.7826	0.7139	0.6574	0.7736	0.7678	1.8611
0.4186	11.0	24365	0.6572	86.3	0.8670	0.7777	0.7055	0.6464	0.7757	0.7625	1.8094
0.4019	12.0	26580	0.6814	86.31	0.8640	0.7766	0.7062	0.6489	0.7643	0.7599	1.7831
0.4145	13.0	28795	0.6949	86.49	0.8605	0.7722	0.7004	0.6416	0.7636	0.7569	1.7895
0.3941	14.0	31010	0.7050	86.38	0.8648	0.7777	0.7052	0.6461	0.7632	0.7568	1.7818