README.md

metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: distilbert_finetune_own_data_model
    results: []

distilbert_finetune_own_data_model

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: 0.0053
• Precision: 1.0
• Recall: 1.0
• F1: 1.0
• Accuracy: 1.0

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	3	0.8131	1.0	0.25	0.4	0.76
No log	2.0	6	0.6099	1.0	0.25	0.4	0.76
No log	3.0	9	0.4666	1.0	0.25	0.4	0.76
No log	4.0	12	0.3527	1.0	0.625	0.7692	0.88
No log	5.0	15	0.2583	1.0	0.875	0.9333	0.96
No log	6.0	18	0.1838	1.0	1.0	1.0	1.0
No log	7.0	21	0.1230	1.0	1.0	1.0	1.0
No log	8.0	24	0.0776	1.0	1.0	1.0	1.0
No log	9.0	27	0.0543	1.0	1.0	1.0	1.0
No log	10.0	30	0.0427	1.0	1.0	1.0	1.0
No log	11.0	33	0.0378	1.0	1.0	1.0	1.0
No log	12.0	36	0.0345	1.0	1.0	1.0	1.0
No log	13.0	39	0.0323	1.0	1.0	1.0	1.0
No log	14.0	42	0.0280	1.0	1.0	1.0	1.0
No log	15.0	45	0.0228	1.0	1.0	1.0	1.0
No log	16.0	48	0.0180	1.0	1.0	1.0	1.0
No log	17.0	51	0.0141	1.0	1.0	1.0	1.0
No log	18.0	54	0.0117	1.0	1.0	1.0	1.0
No log	19.0	57	0.0104	1.0	1.0	1.0	1.0
No log	20.0	60	0.0094	1.0	1.0	1.0	1.0
No log	21.0	63	0.0086	1.0	1.0	1.0	1.0
No log	22.0	66	0.0079	1.0	1.0	1.0	1.0
No log	23.0	69	0.0074	1.0	1.0	1.0	1.0
No log	24.0	72	0.0069	1.0	1.0	1.0	1.0
No log	25.0	75	0.0063	1.0	1.0	1.0	1.0
No log	26.0	78	0.0059	1.0	1.0	1.0	1.0
No log	27.0	81	0.0056	1.0	1.0	1.0	1.0
No log	28.0	84	0.0054	1.0	1.0	1.0	1.0
No log	29.0	87	0.0053	1.0	1.0	1.0	1.0
No log	30.0	90	0.0053	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2