You can deploy this model and start earning money today!

Kartikeya/
timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32

Name: timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32
Availability: InStock

generated_from_trainer

facebook/timesformer-base-finetuned-k400

finetune

cc-by-nc-4.0

endpoints_compatible

Views

No views yet

timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32

This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9266
Accuracy: 0.6862
0 Precision: 0.6305
0 Recall: 0.7881
0 F1-score: 0.7005
0 Support: 1024.0
1 Precision: 0.7639
1 Recall: 0.5974
1 F1-score: 0.6705
1 Support: 1175.0
Accuracy F1-score: 0.6862
Macro avg Precision: 0.6972
Macro avg Recall: 0.6928
Macro avg F1-score: 0.6855
Macro avg Support: 2199.0
Weighted avg Precision: 0.7018
Weighted avg Recall: 0.6862
Weighted avg F1-score: 0.6845
Weighted avg Support: 2199.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 31000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	0 Precision	0 Recall	0 F1-score	0 Support	1 Precision	1 Recall	1 F1-score	1 Support	Accuracy F1-score	Macro avg Precision	Macro avg Recall	Macro avg F1-score	Macro avg Support	Weighted avg Precision	Weighted avg Recall	Weighted avg F1-score	Weighted avg Support
0.664	0.0200	621	0.6462	0.6271	0.5733	0.7793	0.6606	1024.0	0.7200	0.4945	0.5863	1175.0	0.6271	0.6466	0.6369	0.6234	2199.0	0.6516	0.6271	0.6209	2199.0
0.5917	1.0200	1242	0.6000	0.6885	0.6680	0.6582	0.6631	1024.0	0.7059	0.7149	0.7104	1175.0	0.6885	0.6869	0.6865	0.6867	2199.0	0.6882	0.6885	0.6883	2199.0
0.5387	2.0200	1863	0.5982	0.6758	0.6474	0.6670	0.6570	1024.0	0.7019	0.6834	0.6925	1175.0	0.6758	0.6747	0.6752	0.6748	2199.0	0.6765	0.6758	0.6760	2199.0
0.5298	3.0200	2484	0.5978	0.6894	0.7155	0.5527	0.6237	1024.0	0.6747	0.8085	0.7356	1175.0	0.6894	0.6951	0.6806	0.6796	2199.0	0.6937	0.6894	0.6835	2199.0
0.472	4.0200	3105	0.6734	0.6457	0.5886	0.7949	0.6764	1024.0	0.7426	0.5157	0.6087	1175.0	0.6457	0.6656	0.6553	0.6425	2199.0	0.6709	0.6457	0.6402	2199.0
0.4621	5.0200	3726	0.6309	0.6903	0.6862	0.6172	0.6499	1024.0	0.6933	0.7540	0.7224	1175.0	0.6903	0.6897	0.6856	0.6861	2199.0	0.6900	0.6903	0.6886	2199.0
0.4311	6.0200	4347	0.6399	0.7058	0.6682	0.7314	0.6984	1024.0	0.7449	0.6834	0.7128	1175.0	0.7058	0.7065	0.7074	0.7056	2199.0	0.7092	0.7058	0.7061	2199.0
0.3747	7.0200	4968	0.7701	0.6735	0.6957	0.5312	0.6024	1024.0	0.6613	0.7974	0.7230	1175.0	0.6735	0.6785	0.6643	0.6627	2199.0	0.6773	0.6735	0.6669	2199.0
0.3247	8.0200	5589	0.7543	0.7003	0.6605	0.7334	0.6950	1024.0	0.7429	0.6715	0.7054	1175.0	0.7003	0.7017	0.7024	0.7002	2199.0	0.7046	0.7003	0.7006	2199.0
0.3022	9.0200	6210	0.9266	0.6862	0.6305	0.7881	0.7005	1024.0	0.7639	0.5974	0.6705	1175.0	0.6862	0.6972	0.6928	0.6855	2199.0	0.7018	0.6862	0.6845	2199.0

Framework versions

Transformers 4.46.3
Pytorch 2.0.0+cu117
Datasets 3.1.0
Tokenizers 0.20.3

Kartikeya/timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32

timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Kartikeya/
timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate32