metadata

base_model: haryoaw/scenario-TCR-NER_data-univner_en
library_name: transformers
license: mit
metrics:
  - precision
  - recall
  - f1
  - accuracy
tags:
  - generated_from_trainer
model-index:
  - name: scenario-non-kd-po-ner-full_data-univner_full44
    results: []

scenario-non-kd-po-ner-full_data-univner_full44

This model is a fine-tuned version of haryoaw/scenario-TCR-NER_data-univner_en on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1413
Precision: 0.7900
Recall: 0.8023
F1: 0.7961
Accuracy: 0.9836

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: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 44
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0035	1.2755	500	0.1065	0.7916	0.8023	0.7969	0.9842
0.0036	2.5510	1000	0.1246	0.7914	0.7619	0.7764	0.9821
0.0027	3.8265	1500	0.1191	0.7819	0.8054	0.7935	0.9837
0.002	5.1020	2000	0.1324	0.7907	0.7940	0.7924	0.9831
0.0023	6.3776	2500	0.1197	0.7826	0.8085	0.7953	0.9836
0.0017	7.6531	3000	0.1390	0.7673	0.8054	0.7859	0.9819
0.0012	8.9286	3500	0.1371	0.7827	0.7609	0.7717	0.9815
0.0013	10.2041	4000	0.1459	0.7426	0.8002	0.7703	0.9809
0.0017	11.4796	4500	0.1345	0.7771	0.7723	0.7747	0.9819
0.0011	12.7551	5000	0.1327	0.7824	0.7930	0.7877	0.9831
0.001	14.0306	5500	0.1422	0.7591	0.7961	0.7772	0.9813
0.0009	15.3061	6000	0.1383	0.7715	0.7899	0.7806	0.9819
0.0006	16.5816	6500	0.1360	0.7827	0.8054	0.7939	0.9831
0.0006	17.8571	7000	0.1429	0.7889	0.7930	0.7909	0.9834
0.0006	19.1327	7500	0.1409	0.7933	0.7826	0.7879	0.9827
0.0005	20.4082	8000	0.1415	0.7886	0.7992	0.7938	0.9835
0.0005	21.6837	8500	0.1361	0.7913	0.7930	0.7921	0.9832
0.0004	22.9592	9000	0.1393	0.8069	0.8002	0.8035	0.9839
0.0004	24.2347	9500	0.1376	0.7784	0.8147	0.7962	0.9835
0.0003	25.5102	10000	0.1421	0.7862	0.7919	0.7891	0.9833
0.0002	26.7857	10500	0.1417	0.7882	0.8054	0.7967	0.9834
0.0002	28.0612	11000	0.1399	0.7900	0.7981	0.7940	0.9835
0.0001	29.3367	11500	0.1413	0.7900	0.8023	0.7961	0.9836

Framework versions

Transformers 4.44.2
Pytorch 2.1.1+cu121
Datasets 2.14.5
Tokenizers 0.19.1