You can deploy this model and start earning money today!

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

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

Views

No views yet

vit-resnet-mistral-NWPU-with-8-tag-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
0.5095	1.0	2215	0.4772	83.2	0.5044	0.3522	0.2430	0.1591	0.4162	0.3738	0.1391
0.4055	2.0	4430	0.3620	84.56	0.8103	0.7002	0.6156	0.5483	0.7083	0.6925	1.5592
0.3318	3.0	6645	0.3262	85.09	0.8295	0.7312	0.6527	0.5893	0.7417	0.7287	1.6976
0.3005	4.0	8860	0.3146	85.47	0.8537	0.7679	0.6958	0.6362	0.7685	0.7542	1.7593
0.2822	5.0	11075	0.3112	85.69	0.8627	0.7768	0.7071	0.6502	0.7730	0.7620	1.7980
0.2672	6.0	13290	0.3124	85.5	0.8503	0.7609	0.6885	0.6301	0.7814	0.7628	1.8072
0.2608	7.0	15505	0.3168	85.99	0.8543	0.7654	0.6938	0.6353	0.7770	0.7587	1.8000
0.2499	8.0	17720	0.3212	86.19	0.8598	0.7762	0.7087	0.6532	0.7760	0.7669	1.8265
0.2395	9.0	19935	0.3238	86.09	0.8685	0.7838	0.7116	0.6518	0.7836	0.7742	1.8243
0.2295	10.0	22150	0.3326	86.04	0.8595	0.7743	0.7055	0.6496	0.7756	0.7634	1.8297
0.2202	11.0	24365	0.3381	86.26	0.8626	0.7750	0.7041	0.6461	0.7747	0.7630	1.8018
0.2106	12.0	26580	0.3508	86.04	0.8536	0.7637	0.6918	0.6337	0.7627	0.7523	1.7460
0.2159	13.0	28795	0.3534	86.24	0.8552	0.7666	0.6936	0.6343	0.7712	0.7557	1.7708
0.2050	14.0	31010	0.3616	86.03	0.8566	0.7677	0.6952	0.6367	0.7744	0.7596	1.7657