flaird-modernbert-large-attention-multitask

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

• Loss: 0.0231
• Roc-auc: 1.0
• Brier: 0.995
• C@1: 0.994
• F1: 0.997
• F05u: 0.999
• Mean: 0.997

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: 2e-05
• train_batch_size: 128
• eval_batch_size: 128
• 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: cosine
• lr_scheduler_warmup_steps: 0.06
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Roc-auc	Brier	C@1	F1	F05u	Mean
0.0903	0.1000	3968	0.0801	0.997	0.984	0.979	0.989	0.995	0.989
0.0603	0.2000	7936	0.0585	0.999	0.985	0.979	0.989	0.995	0.99
0.0516	0.3001	11904	0.0460	0.999	0.992	0.989	0.994	0.997	0.994
0.0433	0.4001	15872	0.0385	0.999	0.989	0.985	0.992	0.997	0.992
0.0369	0.5001	19840	0.0335	1.0	0.994	0.991	0.995	0.998	0.996
0.0301	0.6001	23808	0.0291	1.0	0.993	0.991	0.995	0.998	0.995
0.0294	0.7001	27776	0.0267	1.0	0.996	0.994	0.997	0.999	0.997
0.0254	0.8002	31744	0.0244	1.0	0.994	0.993	0.996	0.998	0.996
0.0239	0.9002	35712	0.0233	1.0	0.995	0.994	0.997	0.999	0.997
0.0228	1.0	39672	0.0231	1.0	0.995	0.994	0.997	0.999	0.997

Framework versions

• Transformers 5.16.1
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.23.1