README.md

metadata

license: mit
base_model: surrey-nlp/roberta-base-finetuned-abbr
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: roberta-base-finetuned-abbr-finetuned-ner
    results: []

roberta-base-finetuned-abbr-finetuned-ner

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

• Loss: 0.6069
• Precision: 0.7971
• Recall: 0.8633
• F1: 0.8289
• Accuracy: 0.7973

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-06
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.37	100	0.7456	0.7807	0.8460	0.8120	0.7807
No log	0.75	200	0.7377	0.7807	0.8460	0.8120	0.7807
No log	1.12	300	0.7192	0.7807	0.8460	0.8120	0.7807
No log	1.49	400	0.7027	0.7808	0.8461	0.8122	0.7808
0.8312	1.87	500	0.6920	0.7817	0.8471	0.8131	0.7817
0.8312	2.24	600	0.6785	0.7813	0.8466	0.8126	0.7813
0.8312	2.61	700	0.6826	0.7826	0.8480	0.8140	0.7826
0.8312	2.99	800	0.6590	0.7855	0.8511	0.8170	0.7855
0.8312	3.36	900	0.6499	0.7904	0.8564	0.8221	0.7904
0.755	3.73	1000	0.6440	0.7933	0.8596	0.8251	0.7933
0.755	4.1	1100	0.6378	0.7941	0.8605	0.8260	0.7943
0.755	4.48	1200	0.6291	0.7950	0.8615	0.8269	0.7951
0.755	4.85	1300	0.6269	0.7927	0.8588	0.8244	0.7927
0.755	5.22	1400	0.6202	0.7949	0.8613	0.8267	0.7950
0.7217	5.6	1500	0.6154	0.7962	0.8627	0.8281	0.7963
0.7217	5.97	1600	0.6126	0.7964	0.8627	0.8282	0.7966
0.7217	6.34	1700	0.6099	0.7960	0.8624	0.8279	0.7960
0.7217	6.72	1800	0.6094	0.7926	0.8580	0.8240	0.7933
0.7217	7.09	1900	0.6087	0.7964	0.8629	0.8283	0.7966
0.6873	7.46	2000	0.6069	0.7971	0.8633	0.8289	0.7973
0.6873	7.84	2100	0.6048	0.7968	0.8629	0.8285	0.7970
0.6873	8.21	2200	0.6017	0.7974	0.8630	0.8289	0.7973
0.6873	8.58	2300	0.6025	0.7941	0.8591	0.8253	0.7951
0.6873	8.96	2400	0.5981	0.7964	0.8616	0.8277	0.7964
0.6731	9.33	2500	0.5993	0.7968	0.8622	0.8282	0.7969

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2