distilbert-base-uncased-ner_cv

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: 0.8548
• Precision: 0.3327
• Recall: 0.2358
• F1: 0.2760
• Accuracy: 0.7815

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: 1e-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
• lr_scheduler_warmup_steps: 20
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	5.0	30	1.0790	0.0	0.0	0.0	0.7537
No log	10.0	60	0.9589	0.3208	0.1207	0.1754	0.7677
No log	15.0	90	0.8975	0.3363	0.1591	0.2160	0.7773
No log	20.0	120	0.8675	0.3354	0.2259	0.2699	0.7786
No log	25.0	150	0.8568	0.3333	0.2443	0.2820	0.7811
No log	30.0	180	0.8548	0.3327	0.2358	0.2760	0.7815

Framework versions

• Transformers 4.21.1
• Pytorch 1.8.1+cu111
• Datasets 1.6.2
• Tokenizers 0.12.1