distilbert-base-cased-logdetective-extraction-retrained

This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.3047

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	9	5.4981
No log	2.0	18	4.7485
No log	3.0	27	4.2960
No log	4.0	36	4.0269
No log	5.0	45	3.0733
No log	6.0	54	2.9759
No log	7.0	63	2.5961
No log	8.0	72	2.3365
No log	9.0	81	2.4470
No log	10.0	90	2.3994
No log	11.0	99	2.3914
No log	12.0	108	2.3324
No log	13.0	117	2.2978
No log	14.0	126	2.2797
No log	15.0	135	2.2886
No log	16.0	144	2.2969
No log	17.0	153	2.3091
No log	18.0	162	2.2597
No log	19.0	171	2.3080
No log	20.0	180	2.3047

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1