mental-longformer-base-4096-pr – AI Model by rendchevi | AlphaNeural AI

You can deploy this model and start earning money today!

rendchevi/
mental-longformer-base-4096-pr

like

0

text-classification

generated_from_trainer

AIMH/mental-longformer-base-4096

endpoints_compatible

Views

No views yet

mental-longformer-base-4096-pr

This model is a fine-tuned version of AIMH/mental-longformer-base-4096 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.9954
F1 Macro: 0.6043
Precision: 0.6255
Recall: 0.6059
Accuracy: 0.7596

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: 16
eval_batch_size: 32
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_ratio: 0.1
num_epochs: 20
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Macro	Precision	Recall	Accuracy
No log	1.0	240	1.9792	0.3899	0.4216	0.4264	0.6217
No log	2.0	480	0.8616	0.5735	0.5906	0.6019	0.7399
1.8862	3.0	720	0.8725	0.5853	0.5995	0.6155	0.7320
1.8862	4.0	960	0.8129	0.6137	0.6030	0.6326	0.7534
0.8633	5.0	1200	0.8869	0.6056	0.6206	0.6181	0.7622
0.8633	6.0	1440	0.9954	0.6043	0.6255	0.6059	0.7596

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu128
Datasets 4.4.1
Tokenizers 0.22.1