roberta-base-finetuned-ner

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

• Loss: 1.1738
• Precision: 0.6666
• Recall: 0.7036
• F1: 0.6846
• Accuracy: 0.6664

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.19	50	1.3378	0.2046	0.2159	0.2101	0.2062
No log	0.37	100	1.3271	0.2419	0.2553	0.2484	0.2431
No log	0.56	150	1.3164	0.2741	0.2893	0.2815	0.2753
No log	0.75	200	1.3061	0.3090	0.3261	0.3173	0.3100
No log	0.93	250	1.2965	0.3373	0.3560	0.3464	0.3381
No log	1.12	300	1.2872	0.3726	0.3932	0.3826	0.3734
No log	1.31	350	1.2783	0.4027	0.4251	0.4136	0.4034
No log	1.49	400	1.2697	0.4327	0.4567	0.4444	0.4333
No log	1.68	450	1.2613	0.4565	0.4818	0.4688	0.4569
1.2812	1.87	500	1.2537	0.4768	0.5032	0.4897	0.4774
1.2812	2.05	550	1.2464	0.4971	0.5247	0.5105	0.4975
1.2812	2.24	600	1.2394	0.5185	0.5472	0.5324	0.5189
1.2812	2.43	650	1.2328	0.5341	0.5637	0.5485	0.5345
1.2812	2.61	700	1.2266	0.5480	0.5784	0.5628	0.5484
1.2812	2.8	750	1.2208	0.5630	0.5942	0.5782	0.5634
1.2812	2.99	800	1.2153	0.5771	0.6091	0.5927	0.5773
1.2812	3.17	850	1.2100	0.5903	0.6230	0.6062	0.5905
1.2812	3.36	900	1.2051	0.5993	0.6325	0.6155	0.5995
1.2812	3.54	950	1.2008	0.6128	0.6468	0.6294	0.6128
1.2012	3.73	1000	1.1967	0.6202	0.6546	0.6370	0.6200
1.2012	3.92	1050	1.1931	0.6264	0.6611	0.6433	0.6262
1.2012	4.1	1100	1.1896	0.6352	0.6704	0.6523	0.6350
1.2012	4.29	1150	1.1865	0.6426	0.6782	0.6599	0.6424
1.2012	4.48	1200	1.1838	0.6467	0.6825	0.6641	0.6465
1.2012	4.66	1250	1.1814	0.6529	0.6890	0.6705	0.6526
1.2012	4.85	1300	1.1794	0.6568	0.6932	0.6745	0.6565
1.2012	5.04	1350	1.1777	0.6598	0.6964	0.6776	0.6596
1.2012	5.22	1400	1.1763	0.6617	0.6984	0.6795	0.6615
1.2012	5.41	1450	1.1752	0.6635	0.7003	0.6814	0.6633
1.1618	5.6	1500	1.1744	0.6652	0.7020	0.6831	0.6650
1.1618	5.78	1550	1.1740	0.6660	0.7029	0.6839	0.6658
1.1618	5.97	1600	1.1738	0.6666	0.7036	0.6846	0.6664

Framework versions

• Transformers 4.36.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2