multi_task_model_content_freeze_encoder_2048_8

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: 0.8441
• Accuracy: 0.6952
• F1: 0.4707

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 64
• 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
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.3077	1.0	330	1.1435	0.5855	0.2698
1.127	2.0	660	1.0268	0.6204	0.3367
1.0532	3.0	990	0.9587	0.6595	0.4240
1.0091	4.0	1320	0.9028	0.6829	0.4461
0.9842	5.0	1650	0.8887	0.6783	0.4405
0.9671	6.0	1980	0.8665	0.6897	0.4568
0.955	7.0	2310	0.8712	0.6887	0.4619
0.9468	8.0	2640	0.8543	0.6885	0.4584
0.936	9.0	2970	0.8436	0.6975	0.4721
0.9376	10.0	3300	0.8441	0.6952	0.4707

Framework versions

• Transformers 4.57.1
• Pytorch 2.6.0+cu124
• Datasets 4.4.1
• Tokenizers 0.22.1