Intoxicated_Classification

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7660
• Accuracy: 0.6971
• F1 Macro: 0.6962
• F1 Weighted: 0.6990
• Precision Macro: 0.7040
• Precision Weighted: 0.7216
• Recall Macro: 0.7094
• Recall Weighted: 0.6971

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 OptimizerNames.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: 6980

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted	Precision Macro	Precision Weighted	Recall Macro	Recall Weighted
0.3101	0.1	698	1.1498	0.6133	0.6127	0.6100	0.6448	0.6663	0.6396	0.6133
0.0223	1.1	1396	2.0621	0.6154	0.6114	0.6046	0.6727	0.6992	0.6528	0.6154
0.071	2.1	2094	1.1017	0.6650	0.6649	0.6641	0.6905	0.7124	0.6884	0.6650
0.1562	3.1	2792	0.9922	0.7803	0.7713	0.7792	0.7746	0.7791	0.7691	0.7803
0.1505	4.1	3490	0.6705	0.8203	0.8157	0.8208	0.8143	0.8217	0.8176	0.8203
0.0634	5.1	4188	2.0951	0.6155	0.6122	0.6059	0.6687	0.6945	0.6515	0.6155
0.0002	6.1	4886	2.2097	0.6473	0.6472	0.6483	0.6627	0.6818	0.6645	0.6473
0.0366	7.1	5584	1.7946	0.6842	0.6837	0.6858	0.6947	0.7133	0.6988	0.6842
0.0002	8.1	6282	1.8526	0.6838	0.6832	0.6856	0.6926	0.7107	0.6972	0.6838
0.0004	9.1	6980	1.7660	0.6971	0.6962	0.6990	0.7040	0.7216	0.7094	0.6971

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.1
• Tokenizers 0.21.1