results

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

• Loss: 1.0623

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: 0.001
• train_batch_size: 16
• eval_batch_size: 16
• 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
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.7744	1.0	1500	0.7233
0.7218	2.0	3000	0.7428
0.6669	3.0	4500	0.6779
0.636	4.0	6000	0.6808
0.6135	5.0	7500	0.6543
0.5883	6.0	9000	0.6726
0.5606	7.0	10500	0.6569
0.5241	8.0	12000	0.6778
0.5001	9.0	13500	0.7105
0.469	10.0	15000	0.6990
0.4412	11.0	16500	0.6955
0.4026	12.0	18000	0.7050
0.3648	13.0	19500	0.7286
0.3203	14.0	21000	0.7616
0.2927	15.0	22500	0.7478
0.2477	16.0	24000	0.8421
0.22	17.0	25500	0.8972
0.1897	18.0	27000	0.9615
0.1543	19.0	28500	1.0105
0.1387	20.0	30000	1.0623

Framework versions

• PEFT 0.17.1
• Transformers 4.57.0
• Pytorch 2.8.0+cu126
• Datasets 4.1.1
• Tokenizers 0.22.1