model-mental-health-classification-3e-5

This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8045
• Accuracy: 0.5667

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	68	1.5103	0.4375
No log	2.0	136	1.2891	0.5542
No log	3.0	204	1.2470	0.5542
No log	4.0	272	1.2915	0.5542
No log	5.0	340	1.4760	0.55
No log	6.0	408	1.5205	0.5458
No log	7.0	476	1.7233	0.525
0.7743	8.0	544	1.8045	0.5667
0.7743	9.0	612	1.9940	0.5458
0.7743	10.0	680	2.0559	0.5458
0.7743	11.0	748	2.1883	0.5667
0.7743	12.0	816	2.2989	0.5625
0.7743	13.0	884	2.3148	0.5583
0.7743	14.0	952	2.3263	0.5625
0.0226	15.0	1020	2.3321	0.5625

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1