You can deploy this model and start earning money today!

swadhindas324/
vit-Mistral-NWPU-without-captioning

Name: vit-Mistral-NWPU-without-captioning
Availability: InStock

Views

No views yet

vit-Mistral-NWPU-without-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
0.9097	1.0	2215	0.8610	84.07	0.5661	0.3844	0.2671	0.1868	0.4415	0.4062	0.2157
0.6998	2.0	4430	0.6533	84.67	0.8198	0.7149	0.6330	0.5669	0.7297	0.7119	1.6370
0.6128	3.0	6645	0.6157	85.14	0.8347	0.7392	0.6628	0.6008	0.7528	0.7402	1.7231
0.5677	4.0	8860	0.6001	85.14	0.8538	0.7643	0.6896	0.6282	0.7645	0.7493	1.7262
0.5351	5.0	11075	0.5989	85.81	0.8689	0.7848	0.7144	0.6563	0.7775	0.7691	1.8229
0.5060	6.0	13290	0.6045	85.49	0.8513	0.7622	0.6900	0.6320	0.7822	0.7630	1.8044
0.4953	7.0	15505	0.6160	86.02	0.8611	0.7744	0.7052	0.6488	0.7788	0.7633	1.8221
0.4740	8.0	17720	0.6297	86.07	0.8572	0.7699	0.7002	0.6437	0.7729	0.7626	1.8127
0.4537	9.0	19935	0.6375	86.09	0.8633	0.7783	0.7080	0.6501	0.7846	0.7717	1.8135
0.4347	10.0	22150	0.6517	86.02	0.8572	0.7717	0.7024	0.6463	0.7736	0.7633	1.8241
0.4172	11.0	24365	0.6642	86.23	0.8603	0.7714	0.6993	0.6405	0.7826	0.7665	1.8206
0.4003	12.0	26580	0.6892	86.03	0.8520	0.7608	0.6883	0.6307	0.7597	0.7481	1.7471
0.4129	13.0	28795	0.6939	86.34	0.8600	0.7723	0.7006	0.6424	0.7719	0.7608	1.7873
0.3938	14.0	31010	0.7111	86.09	0.8519	0.7630	0.6905	0.6315	0.7619	0.7514	1.7323