scenario-TCR-NER_data-univner_full

haryoaw/scenario-TCR-NER_data-univner_full

scenario-TCR-NER_data-univner_full is a machine learning model from haryoaw. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

21% of all-time downloads

All-time downloads

Public

Repo size

8.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.1 GB · 98%

At a glance

License: mit
Model type: xlm-roberta
Access: Public
Created: Sep 12, 2024
Updated: Sep 12, 2024
SHA: bdd2712b

Base models

Model card

From the Hugging Face model README

scenario-TCR-NER_data-univner_full

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0917
Precision: 0.8470
Recall: 0.8570
F1: 0.8520
Accuracy: 0.9843

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: 42
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
0.1399	0.29	500	0.0671	0.7708	0.8429	0.8052	0.9803
0.0523	0.58	1000	0.0719	0.7863	0.8642	0.8234	0.9800
0.0457	0.87	1500	0.0565	0.8288	0.8583	0.8433	0.9835
0.037	1.16	2000	0.0606	0.8269	0.8680	0.8470	0.9835
0.0295	1.46	2500	0.0609	0.8393	0.8681	0.8535	0.9848
0.0289	1.75	3000	0.0597	0.8414	0.8700	0.8554	0.9845
0.0285	2.04	3500	0.0627	0.8236	0.8768	0.8493	0.9842
0.0197	2.33	4000	0.0649	0.8356	0.8641	0.8496	0.9833
0.0196	2.62	4500	0.0678	0.8387	0.8619	0.8501	0.9837
0.0198	2.91	5000	0.0677	0.8458	0.8616	0.8536	0.9840
0.0158	3.2	5500	0.0695	0.8437	0.8670	0.8552	0.9848
0.0147	3.49	6000	0.0728	0.8300	0.8707	0.8499	0.9841
0.0141	3.78	6500	0.0753	0.8360	0.8651	0.8503	0.9839
0.0137	4.07	7000	0.0748	0.8399	0.8697	0.8546	0.9843
0.0095	4.37	7500	0.0775	0.8406	0.8727	0.8564	0.9839
0.0107	4.66	8000	0.0805	0.8451	0.8738	0.8592	0.9845
0.0112	4.95	8500	0.0808	0.8501	0.8660	0.8580	0.9848
0.0076	5.24	9000	0.0864	0.8485	0.8616	0.8550	0.9840
0.0083	5.53	9500	0.0846	0.8500	0.8600	0.8550	0.9845
0.0094	5.82	10000	0.0791	0.8467	0.8663	0.8564	0.9844
0.0074	6.11	10500	0.0931	0.8514	0.8629	0.8571	0.9846
0.0065	6.4	11000	0.0967	0.8507	0.8534	0.8521	0.9840
0.0073	6.69	11500	0.0914	0.8446	0.8687	0.8565	0.9840
0.0063	6.98	12000	0.0923	0.8552	0.8579	0.8565	0.9845
0.0052	7.28	12500	0.0963	0.8539	0.8619	0.8579	0.9844
0.0061	7.57	13000	0.0917	0.8470	0.8570	0.8520	0.9843

Framework versions

Transformers 4.33.3
Pytorch 2.1.1+cu121
Datasets 2.14.5
Tokenizers 0.13.3

Type: xlm-roberta
License: mit
Created: Sep 12, 2024
Updated: Sep 12, 2024