2_task_v2_sports_movies

This model is a fine-tuned version of RonTon05/model_content_V2_test on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.5897
• F1 Task1: 0.9978
• F1 Task2: 0.4244
• Acc Task1: 0.9985
• Acc Task2: 0.4533
• F1: 0.7111

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: 0.0003
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 348
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Task1	F1 Task2	Acc Task1	Acc Task2	F1
2.3783	1.0	116	2.1904	0.9978	0.1017	0.9985	0.2387	0.5498
2.1670	2.0	232	2.1006	0.9978	0.1741	0.9985	0.2828	0.5860
2.0689	3.0	348	1.9326	0.9978	0.2666	0.9985	0.3276	0.6322
1.9503	4.0	464	1.8881	0.9978	0.2554	0.9985	0.3406	0.6266
1.8918	5.0	580	1.8318	0.9978	0.3163	0.9985	0.3759	0.6571
1.8410	6.0	696	1.7996	0.9978	0.3435	0.9985	0.4149	0.6707
1.7993	7.0	812	1.6977	0.9978	0.3640	0.9985	0.4126	0.6809
1.7554	8.0	928	1.6767	0.9978	0.3900	0.9985	0.4230	0.6939
1.7368	9.0	1044	1.6585	0.9978	0.3834	0.9985	0.4157	0.6906
1.7082	10.0	1160	1.6302	0.9978	0.3846	0.9985	0.4111	0.6912
1.6917	11.0	1276	1.6157	0.9978	0.4201	0.9985	0.4510	0.7090
1.6658	12.0	1392	1.5944	0.9978	0.4225	0.9985	0.4571	0.7102
1.6686	13.0	1508	1.5929	0.9978	0.4225	0.9985	0.4548	0.7101
1.6499	14.0	1624	1.5921	0.9978	0.4195	0.9985	0.4502	0.7086
1.6509	15.0	1740	1.5897	0.9978	0.4244	0.9985	0.4533	0.7111

Framework versions

• Transformers 5.14.1
• Pytorch 2.11.0+cu128
• Datasets 5.0.0
• Tokenizers 0.22.2