test4

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

• Loss: 0.3100
• Precision: 0.5949
• Recall: 0.6424
• F1: 0.6177
• Accuracy: 0.9580

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: 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	Precision	Recall	F1	Accuracy
No log	1.0	418	0.2052	0.2415	0.2465	0.2440	0.9423
0.3341	2.0	836	0.1816	0.4286	0.4792	0.4525	0.9513
0.1296	3.0	1254	0.2039	0.4589	0.5035	0.4801	0.9526
0.0727	4.0	1672	0.2130	0.5237	0.5764	0.5488	0.9566
0.0553	5.0	2090	0.2290	0.5171	0.5764	0.5452	0.9551
0.0412	6.0	2508	0.2351	0.5390	0.5521	0.5455	0.9555
0.0412	7.0	2926	0.2431	0.5280	0.5903	0.5574	0.9542
0.0321	8.0	3344	0.2490	0.5825	0.625	0.6030	0.9570
0.0249	9.0	3762	0.2679	0.5764	0.5764	0.5764	0.9573
0.0192	10.0	4180	0.2574	0.5506	0.6042	0.5762	0.9558
0.0206	11.0	4598	0.2857	0.5498	0.5938	0.5710	0.9559
0.0147	12.0	5016	0.2638	0.5548	0.5972	0.5753	0.9550
0.0147	13.0	5434	0.2771	0.5677	0.5972	0.5821	0.9577
0.0129	14.0	5852	0.3016	0.5761	0.6181	0.5963	0.9549
0.0118	15.0	6270	0.3055	0.5587	0.6111	0.5837	0.9570
0.0099	16.0	6688	0.2937	0.5682	0.6076	0.5872	0.9564
0.0099	17.0	7106	0.3075	0.5313	0.6181	0.5714	0.9531
0.0085	18.0	7524	0.3079	0.6026	0.6424	0.6218	0.9580
0.0085	19.0	7942	0.3082	0.5833	0.6319	0.6067	0.9572
0.0074	20.0	8360	0.3100	0.5949	0.6424	0.6177	0.9580

Framework versions

• Transformers 4.23.1
• Pytorch 1.12.1+cu113
• Datasets 2.6.1
• Tokenizers 0.13.1