token_classification_test

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: 0.2859
• Precision: 0.9187
• Recall: 0.9095
• F1: 0.9140
• Accuracy: 0.9308

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	47	1.2700	0.6758	0.5896	0.6298	0.7121
No log	2.0	94	0.6468	0.8315	0.7864	0.8083	0.8461
No log	3.0	141	0.4607	0.8709	0.8422	0.8563	0.8845
No log	4.0	188	0.3841	0.8924	0.8686	0.8804	0.9047
No log	5.0	235	0.3380	0.9060	0.8905	0.8982	0.9180
No log	6.0	282	0.3164	0.9096	0.8934	0.9014	0.9213
No log	7.0	329	0.3072	0.9090	0.9001	0.9045	0.9227
No log	8.0	376	0.2997	0.9156	0.9009	0.9082	0.9258
No log	9.0	423	0.2940	0.9141	0.9058	0.9099	0.9269
No log	10.0	470	0.2904	0.9199	0.9076	0.9137	0.9312
0.5334	11.0	517	0.2894	0.9210	0.9093	0.9151	0.9314
0.5334	12.0	564	0.2884	0.9173	0.9081	0.9127	0.9295
0.5334	13.0	611	0.2862	0.9184	0.9089	0.9136	0.9305
0.5334	14.0	658	0.2859	0.9196	0.9103	0.9149	0.9310
0.5334	15.0	705	0.2859	0.9187	0.9095	0.9140	0.9308

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.3
• Tokenizers 0.13.3