timesformer-base-finetuned-k400-finetuned-yt_short_classification-sample_rate16

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: 0.2786
• Accuracy: 0.9220
• 0 Precision: 0.8978
• 0 Recall: 0.9432
• 0 F1-score: 0.9200
• 0 Support: 5796.0
• 1 Precision: 0.9460
• 1 Recall: 0.9026
• 1 F1-score: 0.9238
• 1 Support: 6389.0
• Accuracy F1-score: 0.9220
• Macro avg Precision: 0.9219
• Macro avg Recall: 0.9229
• Macro avg F1-score: 0.9219
• Macro avg Support: 12185.0
• Weighted avg Precision: 0.9231
• Weighted avg Recall: 0.9220
• Weighted avg F1-score: 0.9220
• Weighted avg Support: 12185.0

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: 8
• eval_batch_size: 8
• 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: 19800

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
0.6099	0.0501	991	0.4427	0.7965	0.8486	0.6963	0.7650	5796.0	0.7631	0.8873	0.8205	6389.0	0.7965	0.8059	0.7918	0.7927	12185.0	0.8038	0.7965	0.7941	12185.0
0.462	1.0501	1982	0.4645	0.7883	0.7250	0.8941	0.8007	5796.0	0.8781	0.6923	0.7742	6389.0	0.7883	0.8015	0.7932	0.7874	12185.0	0.8053	0.7883	0.7868	12185.0
0.3425	2.0501	2973	0.4453	0.8008	0.7376	0.9023	0.8117	5796.0	0.8889	0.7087	0.7886	6389.0	0.8008	0.8132	0.8055	0.8002	12185.0	0.8169	0.8008	0.7996	12185.0
0.4597	3.0501	3964	0.4212	0.8135	0.8965	0.6872	0.7780	5796.0	0.7658	0.9280	0.8391	6389.0	0.8135	0.8311	0.8076	0.8086	12185.0	0.8280	0.8135	0.8101	12185.0
0.34	4.0501	4955	0.3782	0.8435	0.8672	0.7923	0.8281	5796.0	0.8253	0.8900	0.8564	6389.0	0.8435	0.8462	0.8411	0.8422	12185.0	0.8452	0.8435	0.8429	12185.0
0.2322	5.0501	5946	0.3786	0.8507	0.8105	0.8956	0.8509	5796.0	0.8953	0.8100	0.8505	6389.0	0.8507	0.8529	0.8528	0.8507	12185.0	0.8550	0.8507	0.8507	12185.0
0.3278	6.0501	6937	0.5580	0.7881	0.6988	0.9746	0.8140	5796.0	0.9642	0.6189	0.7539	6389.0	0.7881	0.8315	0.7968	0.7839	12185.0	0.8379	0.7881	0.7825	12185.0
0.3531	7.0501	7928	0.4057	0.8516	0.7948	0.9275	0.8561	5796.0	0.9225	0.7828	0.8469	6389.0	0.8516	0.8587	0.8551	0.8515	12185.0	0.8618	0.8516	0.8513	12185.0
0.2513	8.0501	8919	0.3643	0.8574	0.8021	0.9296	0.8612	5796.0	0.9254	0.7920	0.8535	6389.0	0.8574	0.8638	0.8608	0.8573	12185.0	0.8668	0.8574	0.8572	12185.0
0.2592	9.0501	9910	0.2819	0.8968	0.8775	0.9099	0.8934	5796.0	0.9155	0.8848	0.8999	6389.0	0.8968	0.8965	0.8974	0.8967	12185.0	0.8974	0.8968	0.8968	12185.0
0.405	10.0501	10901	0.3755	0.8693	0.8229	0.9241	0.8705	5796.0	0.9225	0.8195	0.8680	6389.0	0.8693	0.8727	0.8718	0.8693	12185.0	0.8751	0.8693	0.8692	12185.0
0.1971	11.0501	11892	0.3913	0.8762	0.8102	0.9662	0.8813	5796.0	0.9628	0.7946	0.8707	6389.0	0.8762	0.8865	0.8804	0.8760	12185.0	0.8902	0.8762	0.8758	12185.0
0.3499	12.0501	12883	0.2850	0.8971	0.8939	0.8892	0.8915	5796.0	0.9000	0.9042	0.9021	6389.0	0.8971	0.8969	0.8967	0.8968	12185.0	0.8971	0.8971	0.8971	12185.0
0.1551	13.0501	13874	0.2965	0.9004	0.8876	0.9051	0.8963	5796.0	0.9124	0.8961	0.9041	6389.0	0.9004	0.9000	0.9006	0.9002	12185.0	0.9006	0.9004	0.9004	12185.0
0.1379	14.0501	14865	0.3175	0.9028	0.8661	0.9412	0.9021	5796.0	0.9421	0.8681	0.9036	6389.0	0.9028	0.9041	0.9046	0.9028	12185.0	0.9060	0.9028	0.9029	12185.0
0.1979	15.0501	15856	0.5168	0.8652	0.7884	0.9793	0.8736	5796.0	0.9759	0.7616	0.8556	6389.0	0.8652	0.8822	0.8705	0.8646	12185.0	0.8867	0.8652	0.8641	12185.0
0.043	16.0501	16847	0.3269	0.9093	0.8676	0.9551	0.9093	5796.0	0.9552	0.8677	0.9094	6389.0	0.9093	0.9114	0.9114	0.9093	12185.0	0.9135	0.9093	0.9093	12185.0
0.079	17.0501	17838	0.2941	0.9156	0.8929	0.9346	0.9133	5796.0	0.9381	0.8983	0.9177	6389.0	0.9156	0.9155	0.9164	0.9155	12185.0	0.9166	0.9156	0.9156	12185.0
0.2818	18.0501	18829	0.3127	0.9137	0.8751	0.9550	0.9133	5796.0	0.9555	0.8763	0.9142	6389.0	0.9137	0.9153	0.9157	0.9137	12185.0	0.9172	0.9137	0.9138	12185.0
0.0789	19.0490	19800	0.2786	0.9220	0.8978	0.9432	0.9200	5796.0	0.9460	0.9026	0.9238	6389.0	0.9220	0.9219	0.9229	0.9219	12185.0	0.9231	0.9220	0.9220	12185.0

Framework versions

• Transformers 4.46.3
• Pytorch 2.0.0+cu117
• Datasets 3.1.0
• Tokenizers 0.20.3