trained_FM_plus_minus_finetuned-finetuned

xixi1031/trained_FM_plus_minus_finetuned-finetuned

trained_FM_plus_minus_finetuned-finetuned is a machine learning model from xixi1031. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

9% of all-time downloads

All-time downloads

Public

Parameters

86.2M

34.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors345 MB · 100%

At a glance

Model type: videomae
Access: Public
Created: Aug 7, 2024
Updated: Aug 9, 2024
SHA: deccc376

Model card

From the Hugging Face model README

trained_FM_plus_minus_finetuned-finetuned

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0008
Accuracy: 1.0

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 6750

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0201	0.0201	136	0.4265	0.8900
0.0655	1.0201	272	0.0014	1.0
0.0262	2.0201	408	1.2800	0.8034
0.045	3.0201	544	0.5063	0.9224
0.0027	4.0201	680	0.6001	0.9056
0.0475	5.0201	816	0.4429	0.9056
0.0512	6.0201	952	0.0526	0.9702
0.0005	7.0201	1088	0.8258	0.8978
0.001	8.0201	1224	0.9702	0.8978
0.0364	9.0201	1360	0.8333	0.8978
0.0335	10.0201	1496	0.4587	0.8978
0.0433	11.0201	1632	0.3666	0.9120
0.0015	12.0201	1768	0.8214	0.8978
0.0212	13.0201	1904	0.4954	0.9030
0.024	14.0201	2040	0.5142	0.9043
0.0029	15.0201	2176	0.7126	0.9030
0.039	16.0201	2312	0.9752	0.8978
0.0284	17.0201	2448	0.8832	0.8978
0.0007	18.0201	2584	1.0282	0.8978
0.0004	19.0201	2720	0.0305	0.9819
0.0293	20.0201	2856	0.7992	0.9017
0.0002	21.0201	2992	0.3760	0.9508
0.0006	22.0201	3128	0.3892	0.9107
0.0005	23.0201	3264	0.5964	0.9030
0.0338	24.0201	3400	0.1783	0.9431
0.0006	25.0201	3536	0.1233	0.9521
0.0135	26.0201	3672	0.4995	0.8978
0.0005	27.0201	3808	0.8097	0.8978
0.0446	28.0201	3944	0.9635	0.8978
0.001	29.0201	4080	0.8746	0.8978
0.0252	30.0201	4216	0.9896	0.8978
0.0002	31.0201	4352	0.9572	0.8978
0.0204	32.0201	4488	0.9263	0.8978
0.0365	33.0201	4624	0.1628	0.9379
0.0037	34.0201	4760	0.3472	0.9030
0.0004	35.0201	4896	0.0515	0.9702
0.0371	36.0201	5032	0.8920	0.8978
0.0002	37.0201	5168	0.5903	0.8978
0.0004	38.0201	5304	0.7191	0.8978
0.0004	39.0201	5440	0.7647	0.8978
0.0002	40.0201	5576	0.8480	0.8978
0.0001	41.0201	5712	0.9607	0.8978
0.0003	42.0201	5848	0.9465	0.8978
0.0002	43.0201	5984	0.9669	0.8978
0.0002	44.0201	6120	0.9628	0.8978
0.0003	45.0201	6256	0.9807	0.8978
0.0	46.0201	6392	0.9692	0.8978
0.0257	47.0201	6528	0.9883	0.8978
0.0001	48.0201	6664	0.9766	0.8978
0.0001	49.0127	6750	0.9790	0.8978

Framework versions

Transformers 4.42.3
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Type: videomae
Created: Aug 7, 2024
Updated: Aug 9, 2024