You can deploy this model and start earning money today!

swadhindas324/
vit-convnext-mistral-NWPU-with-11-captioning

Name: vit-convnext-mistral-NWPU-with-11-captioning
Availability: InStock

Views

No views yet

vit-convnext-mistral-NWPU-with-11-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
0.5110	1.0	2215	0.4782	83.14	0.5100	0.3496	0.2383	0.1566	0.4237	0.3777	0.1339
0.4064	2.0	4430	0.3640	85.01	0.8289	0.7244	0.6423	0.5757	0.7165	0.7080	1.6284
0.3337	3.0	6645	0.3270	85.23	0.8375	0.7400	0.6618	0.5981	0.7455	0.7350	1.7436
0.3015	4.0	8860	0.3152	85.71	0.8654	0.7811	0.7106	0.6513	0.7672	0.7591	1.7834
0.2827	5.0	11075	0.3127	85.79	0.8683	0.7812	0.7104	0.6522	0.7623	0.7620	1.8072
0.2672	6.0	13290	0.3130	85.95	0.8677	0.7813	0.7111	0.6535	0.7729	0.7648	1.8534
0.2604	7.0	15505	0.3193	86.49	0.8769	0.7938	0.7265	0.6708	0.7714	0.7689	1.8770
0.2492	8.0	17720	0.3229	86.54	0.8759	0.7938	0.7263	0.6701	0.7675	0.7709	1.8670
0.2384	9.0	19935	0.3257	86.64	0.8775	0.7926	0.7200	0.6599	0.7687	0.7687	1.8299
0.2285	10.0	22150	0.3345	86.66	0.8739	0.7895	0.7208	0.6644	0.7609	0.7633	1.8533
0.2184	11.0	24365	0.3393	86.9	0.8867	0.8045	0.7355	0.6785	0.7697	0.7729	1.8873
0.2085	12.0	26580	0.3504	86.66	0.8703	0.7848	0.7145	0.6573	0.7522	0.7581	1.8106
0.2143	13.0	28795	0.3554	87.12	0.8784	0.7945	0.7239	0.6647	0.7567	0.7622	1.8520
0.2030	14.0	31010	0.3652	86.96	0.8802	0.7949	0.7238	0.6646	0.7454	0.7560	1.8150
0.1916	15.0	33225	0.3736	86.92	0.8770	0.7887	0.7158	0.6561	0.7386	0.7495	1.7932
0.1811	16.0	35440	0.3834	87.16	0.8870	0.8028	0.7322	0.6744	0.7565	0.7647	1.8544