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-mdeberta_data-univner_en44
    results: []

scenario-non-kd-po-ner-full-mdeberta_data-univner_en44

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: 0.1418
Precision: 0.8347
Recall: 0.8416
F1: 0.8381
Accuracy: 0.9853

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
0.0023	1.2755	500	0.1132	0.8279	0.8364	0.8321	0.9857
0.0022	2.5510	1000	0.1035	0.8234	0.8540	0.8384	0.9858
0.0021	3.8265	1500	0.0987	0.8228	0.8509	0.8366	0.9851
0.0013	5.1020	2000	0.1237	0.7955	0.8458	0.8199	0.9839
0.0008	6.3776	2500	0.1278	0.8173	0.8292	0.8232	0.9845
0.0007	7.6531	3000	0.1257	0.8257	0.8437	0.8346	0.9848
0.0006	8.9286	3500	0.1257	0.8466	0.8282	0.8373	0.9855
0.0011	10.2041	4000	0.1250	0.8141	0.8251	0.8195	0.9843
0.0007	11.4796	4500	0.1240	0.8206	0.8240	0.8223	0.9840
0.0004	12.7551	5000	0.1297	0.8192	0.8395	0.8292	0.9847
0.0008	14.0306	5500	0.1342	0.8270	0.8116	0.8192	0.9844
0.0004	15.3061	6000	0.1295	0.8147	0.8240	0.8194	0.9843
0.0004	16.5816	6500	0.1374	0.8118	0.8437	0.8274	0.9839
0.0003	17.8571	7000	0.1416	0.8092	0.8209	0.8150	0.9837
0.0003	19.1327	7500	0.1264	0.8249	0.8489	0.8367	0.9852
0.0002	20.4082	8000	0.1323	0.8262	0.8416	0.8338	0.9854
0.0003	21.6837	8500	0.1341	0.8239	0.8427	0.8332	0.9854
0.0001	22.9592	9000	0.1400	0.8251	0.8499	0.8373	0.9852
0.0002	24.2347	9500	0.1342	0.8219	0.8406	0.8311	0.9849
0.0002	25.5102	10000	0.1355	0.8352	0.8447	0.8399	0.9855
0.0001	26.7857	10500	0.1454	0.8254	0.8416	0.8334	0.9846
0.0001	28.0612	11000	0.1448	0.8254	0.8416	0.8334	0.9849
0.0001	29.3367	11500	0.1418	0.8347	0.8416	0.8381	0.9853

Framework versions

Transformers 4.44.2
Pytorch 2.1.1+cu121
Datasets 2.14.5
Tokenizers 0.19.1