suicide-distilbert-original-8-5-v2

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

• Loss: 2.0057
• Accuracy: {'accuracy': 0.38}
• Precision: 0.3447
• Recall: 0.38
• Fscore: 0.3425

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: 8e-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: 13

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	Fscore
No log	1.0	10	1.6116	{'accuracy': 0.17}	0.0289	0.17	0.0494
No log	2.0	20	1.5254	{'accuracy': 0.37}	0.1990	0.37	0.2437
No log	3.0	30	1.4527	{'accuracy': 0.38}	0.3031	0.38	0.2628
No log	4.0	40	1.4323	{'accuracy': 0.39}	0.1913	0.39	0.2557
No log	5.0	50	1.4748	{'accuracy': 0.4}	0.2786	0.4	0.3192
No log	6.0	60	1.6159	{'accuracy': 0.37}	0.2911	0.37	0.2961
No log	7.0	70	1.5354	{'accuracy': 0.38}	0.3124	0.38	0.3301
No log	8.0	80	1.5825	{'accuracy': 0.38}	0.3247	0.38	0.3449
No log	9.0	90	1.6997	{'accuracy': 0.35}	0.3365	0.35	0.3297
No log	10.0	100	1.8153	{'accuracy': 0.36}	0.3228	0.36	0.3208
No log	11.0	110	1.9071	{'accuracy': 0.37}	0.3415	0.37	0.3333
No log	12.0	120	1.9984	{'accuracy': 0.38}	0.3313	0.38	0.3341
No log	13.0	130	2.0057	{'accuracy': 0.38}	0.3447	0.38	0.3425

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0