self_iterative_v1_targeted_iteration_3

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.9097
• Accuracy Targeted: 0.7222
• F1 Macro Targeted: 0.6105
• F1 Weighted Targeted: 0.6847
• F1 Macro Total: 0.6105
• F1 Weighted Total: 0.6847

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: 6e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 1337
• 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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Targeted	F1 Macro Targeted	F1 Weighted Targeted	F1 Macro Total	F1 Weighted Total
0.7295	1.0	7573	2.8268	0.7156	0.5795	0.6645	0.5795	0.6645
0.5136	2.0	15146	2.7650	0.6978	0.6095	0.6755	0.6095	0.6755
0.4088	3.0	22719	3.6015	0.7178	0.5843	0.6680	0.5843	0.6680
0.2929	4.0	30292	4.0075	0.7067	0.5873	0.6662	0.5873	0.6662
0.152	5.0	37865	3.9097	0.7222	0.6105	0.6847	0.6105	0.6847
0.1324	6.0	45438	4.3839	0.6978	0.5958	0.6680	0.5958	0.6680
0.1184	7.0	53011	4.0303	0.7089	0.5834	0.6647	0.5834	0.6647
0.0751	8.0	60584	4.1326	0.7111	0.6015	0.6758	0.6015	0.6758
0.0358	9.0	68157	4.2129	0.72	0.6061	0.6814	0.6061	0.6814
0.0815	10.0	75730	4.5400	0.6956	0.5965	0.6676	0.5965	0.6676

Framework versions

• Transformers 4.50.2
• Pytorch 2.6.0+cu124
• Datasets 3.0.1
• Tokenizers 0.21.1