Modelpublic

cuadron11/suicide-distilbert-original-5-5

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes5downloads

Model Card

suicide-distilbert-original-5-5

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: 2.3097
—Accuracy: {'accuracy': 0.33}
—Precision: 0.2925
—Recall: 0.33
—Fscore: 0.3091

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: 4.5e-05
—trainbatchsize: 32
—evalbatchsize: 32
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	Fscore
No log	1.0	10	1.6028	{'accuracy': 0.31}	0.0961	0.31	0.1467
No log	2.0	20	1.5911	{'accuracy': 0.31}	0.0961	0.31	0.1467
No log	3.0	30	1.5529	{'accuracy': 0.31}	0.0971	0.31	0.1478
No log	4.0	40	1.5191	{'accuracy': 0.32}	0.1532	0.32	0.2072
No log	5.0	50	1.4784	{'accuracy': 0.35}	0.1829	0.35	0.2343
No log	6.0	60	1.4951	{'accuracy': 0.39}	0.3290	0.39	0.2927
No log	7.0	70	1.5486	{'accuracy': 0.35}	0.2532	0.35	0.2676
No log	8.0	80	1.5740	{'accuracy': 0.38}	0.3537	0.38	0.3242
No log	9.0	90	1.6350	{'accuracy': 0.37}	0.3219	0.37	0.3439
No log	10.0	100	1.7061	{'accuracy': 0.38}	0.3253	0.38	0.3401
No log	11.0	110	1.7335	{'accuracy': 0.37}	0.3214	0.37	0.3430
No log	12.0	120	1.8224	{'accuracy': 0.39}	0.3332	0.39	0.3558
No log	13.0	130	1.8892	{'accuracy': 0.37}	0.3207	0.37	0.3414
No log	14.0	140	2.0359	{'accuracy': 0.34}	0.3092	0.34	0.3232
No log	15.0	150	2.0748	{'accuracy': 0.36}	0.4394	0.36	0.3411
No log	16.0	160	2.2032	{'accuracy': 0.37}	0.3182	0.37	0.3367
No log	17.0	170	2.2481	{'accuracy': 0.34}	0.2971	0.34	0.3141
No log	18.0	180	2.2278	{'accuracy': 0.34}	0.2957	0.34	0.3157
No log	19.0	190	2.2986	{'accuracy': 0.32}	0.2828	0.32	0.2981
No log	20.0	200	2.3097	{'accuracy': 0.33}	0.2925	0.33	0.3091

Framework versions

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