You can deploy this model and start earning money today!

swadhindas324/
vit-convnext-mistral-NWPU-with-7-captioning

Name: vit-convnext-mistral-NWPU-with-7-captioning
Availability: InStock

Views

No views yet

vit-convnext-mistral-NWPU-with-7-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
0.5083	1.0	2215	0.4745	82.94	0.5088	0.3469	0.2371	0.1589	0.4269	0.3797	0.1382
0.4019	2.0	4430	0.3612	84.61	0.8236	0.7161	0.6326	0.5660	0.7111	0.6998	1.5855
0.3316	3.0	6645	0.3255	85.05	0.8297	0.7324	0.6548	0.5922	0.7523	0.7364	1.7359
0.3001	4.0	8860	0.3138	85.48	0.8536	0.7674	0.6958	0.6367	0.7645	0.7536	1.7573
0.2817	5.0	11075	0.3113	85.66	0.8616	0.7743	0.7047	0.6478	0.7689	0.7605	1.8021
0.2665	6.0	13290	0.3118	85.54	0.8523	0.7641	0.6924	0.6340	0.7755	0.7594	1.8010
0.2602	7.0	15505	0.3170	86.15	0.8631	0.7782	0.7099	0.6536	0.7807	0.7665	1.8461
0.2492	8.0	17720	0.3210	86.0	0.8585	0.7733	0.7038	0.6470	0.7767	0.7639	1.7951
0.2384	9.0	19935	0.3251	86.06	0.8622	0.7757	0.7022	0.6420	0.7803	0.7696	1.8079
0.2288	10.0	22150	0.3346	86.09	0.8560	0.7680	0.6970	0.6396	0.7690	0.7586	1.8070
0.2190	11.0	24365	0.3373	86.24	0.8666	0.7800	0.7103	0.6529	0.7797	0.7684	1.8278
0.2094	12.0	26580	0.3489	86.16	0.8634	0.7754	0.7031	0.6442	0.7594	0.7555	1.7584
0.2151	13.0	28795	0.3528	86.29	0.8580	0.7705	0.6984	0.6392	0.7680	0.7573	1.7893
0.2041	14.0	31010	0.3634	86.25	0.8609	0.7726	0.6996	0.6399	0.7681	0.7589	1.7716