You can deploy this model and start earning money today!

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

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

Views

No views yet

vit-convnext-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
0.9122	1.0	2215	0.8667	83.86	0.5366	0.3703	0.2570	0.1708	0.4284	0.3912	0.1648
0.7089	2.0	4430	0.6574	84.78	0.8246	0.7189	0.6369	0.5708	0.7175	0.7070	1.6290
0.6161	3.0	6645	0.6180	85.23	0.8339	0.7374	0.6603	0.5981	0.7455	0.7356	1.7258
0.5698	4.0	8860	0.6043	85.57	0.8570	0.7725	0.7025	0.6440	0.7680	0.7580	1.7768
0.5369	5.0	11075	0.5999	85.87	0.8673	0.7807	0.7098	0.6516	0.7699	0.7637	1.8073
0.5081	6.0	13290	0.6047	85.64	0.8548	0.7630	0.6894	0.6298	0.7757	0.7585	1.7978
0.4975	7.0	15505	0.6180	86.17	0.8629	0.7747	0.7038	0.6461	0.7750	0.7614	1.8191
0.4766	8.0	17720	0.6260	86.25	0.8664	0.7803	0.7113	0.6553	0.7673	0.7630	1.8373
0.4555	9.0	19935	0.6379	86.24	0.8767	0.7942	0.7236	0.6648	0.7883	0.7798	1.8496
0.4370	10.0	22150	0.6511	86.36	0.8709	0.7865	0.7177	0.6614	0.7709	0.7657	1.8616
0.4185	11.0	24365	0.6634	86.34	0.8708	0.7868	0.7175	0.6607	0.7801	0.7700	1.8337
0.4016	12.0	26580	0.6841	86.37	0.8661	0.7794	0.7086	0.6514	0.7584	0.7580	1.7835
0.4142	13.0	28795	0.6944	86.59	0.8619	0.7739	0.7001	0.6396	0.7525	0.7496	1.8005
0.3941	14.0	31010	0.7094	86.38	0.8668	0.7792	0.7076	0.6494	0.7630	0.7578	1.7849