ModelPublicadoExterno

Timesformer Base Finetuned K400 Snapdata Classification Sample Rate16 Freeze Last2blocks

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: 0.6734 Accuracy: 0.6421 0 Precision: 0.6913 0...

Fuentehuggingface.co/Kartikeya/timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks/tree/4b274113c5d8dd82fd504302e8527e7d6a3630ff

TipoOtherModelo basefacebook/timesformer-base-finetuned-k400VersiónRevision 4b27411Bcalidad

Fuente del modelo

Tipo: Other
Tamaño del archivo: 463 MB
Modelo base: facebook/timesformer-base-finetuned-k400
Versión: vRevision 4b27411
Actualizado: 2 oct 2026
Descargas: 3
Fuente: Hugging Face

Descripción de la fuente

timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks

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: 0.6734
Accuracy: 0.6421
0 Precision: 0.6913
0 Recall: 0.4116
0 F1-score: 0.5160
0 Support: 2002.0
1 Precision: 0.6234
1 Recall: 0.8412
1 F1-score: 0.7161
1 Support: 2318.0
Accuracy F1-score: 0.6421
Macro avg Precision: 0.6573
Macro avg Recall: 0.6264
Macro avg F1-score: 0.6160
Macro avg Support: 4320.0
Weighted avg Precision: 0.6549
Weighted avg Recall: 0.6421
Weighted avg F1-score: 0.6234
Weighted avg Support: 4320.0

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: 8e-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: cosine
lr_scheduler_warmup_ratio: 0.1
training_steps: 62000
label_smoothing_factor: 0.1

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
0.725	0.0002	10	0.7611	0.4905	0.4552	0.5045	0.4786	2002.0	0.5278	0.4784	0.5019	2318.0	0.4905	0.4915	0.4915	0.4902	4320.0	0.4942	0.4905	0.4911	4320.0
0.74	0.0003	20	0.7609	0.4914	0.4560	0.5045	0.4790	2002.0	0.5287	0.4802	0.5033	2318.0	0.4914	0.4924	0.4923	0.4911	4320.0	0.4950	0.4914	0.4920	4320.0
0.7386	0.0005	30	0.7607	0.4919	0.4564	0.5040	0.4790	2002.0	0.5292	0.4814	0.5042	2318.0	0.4919	0.4928	0.4927	0.4916	4320.0	0.4954	0.4919	0.4925	4320.0
0.8112	0.0006	40	0.7605	0.4921	0.4565	0.5030	0.4786	2002.0	0.5293	0.4827	0.5050	2318.0	0.4921	0.4929	0.4929	0.4918	4320.0	0.4956	0.4921	0.4928	4320.0
0.8034	0.0008	50	0.7601	0.4914	0.4555	0.4990	0.4763	2002.0	0.5284	0.4849	0.5057	2318.0	0.4914	0.4920	0.4920	0.4910	4320.0	0.4947	0.4914	0.4921	4320.0
0.784	0.0010	60	0.7596	0.4919	0.4557	0.4955	0.4748	2002.0	0.5287	0.4888	0.5080	2318.0	0.4919	0.4922	0.4921	0.4914	4320.0	0.4949	0.4919	0.4926	4320.0
0.8148	0.0011	70	0.7589	0.4928	0.4562	0.4915	0.4732	2002.0	0.5294	0.4940	0.5110	2318.0	0.4928	0.4928	0.4927	0.4921	4320.0	0.4954	0.4928	0.4935	4320.0
0.8031	0.0013	80	0.7580	0.4944	0.4575	0.4895	0.4730	2002.0	0.5308	0.4987	0.5142	2318.0	0.4944	0.4941	0.4941	0.4936	4320.0	0.4968	0.4944	0.4951	4320.0
0.8194	0.0015	90	0.7571	0.4949	0.4575	0.4840	0.4704	2002.0	0.5309	0.5043	0.5173	2318.0	0.4949	0.4942	0.4942	0.4938	4320.0	0.4969	0.4949	0.4955	4320.0
0.7805	0.0016	100	0.7561	0.4961	0.4583	0.4805	0.4692	2002.0	0.5317	0.5095	0.5204	2318.0	0.4961	0.4950	0.4950	0.4948	4320.0	0.4977	0.4961	0.4966	4320.0
0.7331	0.0018	110	0.7550	0.4961	0.4578	0.4745	0.4660	2002.0	0.5314	0.5147	0.5229	2318.0	0.4961	0.4946	0.4946	0.4945	4320.0	0.4973	0.4961	0.4965	4320.0
0.7107	0.0019	120	0.7542	0.4986	0.4602	0.4740	0.4670	2002.0	0.5337	0.5198	0.5267	2318.0	0.4986	0.4969	0.4969	0.4968	4320.0	0.4996	0.4986	0.4990	4320.0
0.8021	0.0021	130	0.7530	0.4979	0.4589	0.4660	0.4625	2002.0	0.5326	0.5255	0.5290	2318.0	0.4979	0.4958	0.4957	0.4957	4320.0	0.4984	0.4979	0.4982	4320.0
0.7522	0.0023	140	0.7515	0.5007	0.4610	0.4580	0.4595	2002.0	0.5345	0.5375	0.5360	2318.0	0.5007	0.4978	0.4978	0.4978	4320.0	0.5005	0.5007	0.5006	4320.0
0.7187	0.0024	150	0.7501	0.5037	0.4640	0.4575	0.4608	2002.0	0.5371	0.5436	0.5403	2318.0	0.5037	0.5006	0.5006	0.5005	4320.0	0.5032	0.5037	0.5034	4320.0
0.8722	0.0026	160	0.7483	0.5030	0.4627	0.4496	0.4560	2002.0	0.536	0.5492	0.5425	2318.0	0.5030	0.4994	0.4994	0.4993	4320.0	0.5020	0.5030	0.5024	4320.0
0.841	0.0027	170	0.7466	0.5060	0.4660	0.4520	0.4589	2002.0	0.5387	0.5526	0.5456	2318.0	0.5060	0.5024	0.5023	0.5022	4320.0	0.5050	0.5060	0.5054	4320.0
0.7659	0.0029	180	0.7455	0.5069	0.4668	0.4496	0.4580	2002.0	0.5393	0.5565	0.5478	2318.0	0.5069	0.5031	0.5030	0.5029	4320.0	0.5057	0.5069	0.5062	4320.0
0.7639	0.0031	190	0.7442	0.5090	0.4689	0.4476	0.4580	2002.0	0.5409	0.5621	0.5513	2318.0	0.5090	0.5049	0.5048	0.5046	4320.0	0.5075	0.5090	0.5080	4320.0
0.7889	0.0032	200	0.7433	0.5104	0.4706	0.4510	0.4606	2002.0	0.5423	0.5617	0.5518	2318.0	0.5104	0.5064	0.5064	0.5062	4320.0	0.5090	0.5104	0.5095	4320.0
0.738	0.0034	210	0.7423	0.5111	0.4713	0.4505	0.4607	2002.0	0.5428	0.5634	0.5529	2318.0	0.5111	0.5070	0.5070	0.5068	4320.0	0.5097	0.5111	0.5102	4320.0
0.7325	0.0035	220	0.7416	0.5127	0.4731	0.4530	0.4629	2002.0	0.5443	0.5643	0.5541	2318.0	0.5127	0.5087	0.5087	0.5085	4320.0	0.5113	0.5127	0.5118	4320.0
0.7353	0.0037	230	0.7408	0.5130	0.4738	0.4615	0.4676	2002.0	0.5451	0.5574	0.5512	2318.0	0.5130	0.5095	0.5095	0.5094	4320.0	0.5121	0.5130	0.5125	4320.0
0.789	0.0039	240	0.7407	0.5137	0.4754	0.4770	0.4762	2002.0	0.5469	0.5453	0.5461	2318.0	0.5137	0.5112	0.5112	0.5112	4320.0	0.5138	0.5137	0.5137	4320.0
0.71	0.0040	250	0.7394	0.5155	0.4772	0.4765	0.4769	2002.0	0.5485	0.5492	0.5488	2318.0	0.5155	0.5129	0.5129	0.5129	4320.0	0.5155	0.5155	0.5155	4320.0
0.7802	0.0042	260	0.7378	0.5178	0.4793	0.4685	0.4739	2002.0	0.5497	0.5604	0.5550	2318.0	0.5178	0.5145	0.5145	0.5144	4320.0	0.5171	0.5178	0.5174	4320.0
0.7368	0.0044	270	0.7365	0.5190	0.4804...

Fuentes

1 fuente

Hugging FacePrincipalVersión 4b274113c5d8dd82fd504302e8527e7d6a3630ff

huggingface.co/Kartikeya/timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks/tree/4b274113c5d8dd82fd504302e8527e7d6a3630ff

Verificado 21 ago

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 463 MB · SHA-256 3b6ee7e59dd7…bf97 · Hugging Face

Download file

Extractos de fuentes

2 extractos

Readme21 agohuggingface.co/Kartikeya/timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks

--- library_name: transformers license: cc-by-nc-4.0 base_model: facebook/timesformer-base-finetuned-k400 tags: - generated_from_trainer metrics: - accuracy model-index: - name: timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks results: [] ---  # timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6734 - Accuracy: 0.6421 - 0 Precision: 0.6913 - 0 Recall: 0.4116 - 0 F1-score: 0.5160 - 0 Support: 2002.0 - 1 Precision: 0.6234 - 1 Recall: 0.8412 - 1 F1-score: 0.7161 - 1 Support: 2318.0 - Accuracy F1-score: 0.6421 - Macro avg Precision: 0.6573 - Macro avg Recall: 0.6264 - Macro avg F1-score: 0.6160 - Macro avg Support: 4320.0 - Weighted avg Precision: 0.6549 - Weighted avg Recall: 0.6421 - Weighted avg F1-score: 0.6234 - Weighted avg Support: 4320.0 ## 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: 8e-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: cosine - lr_scheduler_warmup_ratio: 0.1 - training_steps: 62000 - label_smoothing_factor: 0.1 ### 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 | |:-------------:|:------:|:----:|:---------------:|:--------:|:-----------:|:--------:|:----------:|:---------:|:-----------:|:--------:|:----------:|:---------:|:--------...

Note21 agohuggingface.co/Kartikeya/timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Kartikeya/timesformer-base-finetuned-k400-snapdata_classification-sample_rate16_freeze_last2blocks