metadata

license: cc-by-nc-4.0
base_model: Zamoranesis/mental_bert
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: mental_bert_classifier
    results: []

mental_bert_classifier

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

Loss: 0.3709
F1 Class 0: 0.8475
F1 Class 1: 0.9157
F1 Class 2: 0.7692
F1 Class 3: 0.8764
F1 Class 4: 0.8772
F1: 0.8572

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: 0.0005
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 100
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Class 0	F1 Class 1	F1 Class 2	F1 Class 3	F1 Class 4	F1
1.3938	6.25	100	1.0235	0.7458	0.8000	0.6957	0.8315	0.8197	0.7785
0.7425	12.5	200	0.6302	0.7667	0.875	0.7755	0.8478	0.8475	0.8225
0.5225	18.75	300	0.5192	0.8276	0.9268	0.7843	0.8667	0.8475	0.8506
0.4433	25.0	400	0.4599	0.8276	0.9157	0.7692	0.8636	0.8475	0.8447
0.3862	31.25	500	0.4208	0.8475	0.9157	0.7692	0.8636	0.8621	0.8516
0.3702	37.5	600	0.3987	0.8475	0.9157	0.7692	0.8764	0.8772	0.8572
0.3437	43.75	700	0.3872	0.8475	0.9157	0.7692	0.8764	0.8772	0.8572
0.337	50.0	800	0.3759	0.8475	0.9157	0.7692	0.8764	0.8772	0.8572
0.3253	56.25	900	0.3727	0.8475	0.9157	0.7692	0.8764	0.8772	0.8572
0.3236	62.5	1000	0.3709	0.8475	0.9157	0.7692	0.8764	0.8772	0.8572

Framework versions

Transformers 4.33.3
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3