You can deploy this model and start earning money today!

swadhindas324/
vit-resnet-mistral-UCM-with-4-captioning

Name: vit-resnet-mistral-UCM-with-4-captioning
Availability: InStock

Views

No views yet

vit-resnet-mistral-UCM-with-4-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
No log	1.0	148	0.6541	72.15	0.4098	0.2781	0.2017	0.1494	0.3125	0.3445	0.3271
No log	2.0	296	0.4641	72.1	0.2927	0.2072	0.1412	0.0992	0.2246	0.2495	0.3782
No log	3.0	444	0.4152	69.47	0.6191	0.5374	0.4747	0.4284	0.5770	0.5799	1.8770
No log	4.0	592	0.3534	72.5	0.8028	0.7310	0.6748	0.6250	0.7647	0.7532	3.0486
No log	5.0	740	0.3411	73.71	0.8299	0.7717	0.7266	0.6873	0.8096	0.7979	3.3644
No log	6.0	888	0.3437	73.56	0.8308	0.7821	0.7374	0.6979	0.8242	0.8085	3.3850
0.4482	7.0	1036	0.3365	74.17	0.8571	0.8081	0.7680	0.7304	0.8374	0.8300	3.5829
0.4482	8.0	1184	0.3422	74.1	0.8321	0.7750	0.7276	0.6854	0.8055	0.7977	3.3997
0.4482	9.0	1332	0.3544	73.72	0.8528	0.7996	0.7521	0.7083	0.8346	0.8195	3.5114
0.4482	10.0	1480	0.3530	74.4	0.8296	0.7755	0.7312	0.6918	0.8015	0.7982	3.4191
0.4482	11.0	1628	0.3684	74.4	0.8279	0.7716	0.7262	0.6834	0.8091	0.8016	3.4273
0.4482	12.0	1776	0.3584	74.04	0.8456	0.7930	0.7479	0.7068	0.8102	0.8031	3.4203
0.4482	13.0	1924	0.3771	73.47	0.8459	0.7907	0.7429	0.6996	0.8322	0.8201	3.5223
0.1645	14.0	2072	0.3798	75.2	0.8488	0.7914	0.7425	0.6988	0.8106	0.7986	3.3265
0.1645	15.0	2220	0.3792	75.64	0.8432	0.7869	0.7375	0.6923	0.8167	0.8142	3.5419
0.1645	16.0	2368	0.3777	74.13	0.8588	0.8084	0.7634	0.7243	0.8192	0.8175	3.5993
0.1645	17.0	2516	0.3861	75.0	0.8587	0.8078	0.7634	0.7195	0.8423	0.8230	3.5857