results

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: 0.3095
• Macro F1: 0.8317
• Macro Precision: 0.8609
• Macro Recall: 0.8061
• Macro Support: None

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: 64
• eval_batch_size: 64
• seed: 42
• 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: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Macro F1	Macro Precision	Macro Recall	Macro Support
No log	1.0	86	0.5550	0.1427	0.1109	0.2	None
0.6112	2.0	172	0.4244	0.5106	0.7966	0.4864	None
0.4482	3.0	258	0.3317	0.7370	0.7756	0.7129	None
0.3083	4.0	344	0.3029	0.7749	0.8252	0.7414	None
0.2015	5.0	430	0.2997	0.7893	0.8241	0.7742	None
0.1252	6.0	516	0.2980	0.8110	0.8430	0.7882	None
0.0736	7.0	602	0.3023	0.8148	0.8565	0.7811	None
0.0736	8.0	688	0.3091	0.8279	0.8448	0.8135	None
0.0384	9.0	774	0.3087	0.8313	0.8613	0.8062	None
0.0216	10.0	860	0.3095	0.8317	0.8609	0.8061	None

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1