results_combined

Sushant0809/results_combined

results_combined is a token classification model from Sushant0809. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.

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

Downloads · 30 days

31% of all-time downloads

All-time downloads

Public

Parameters

109M

59.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.3 GB · 100%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: bert
Access: Public
Created: Jun 27, 2024
Updated: Jun 29, 2024
SHA: 303cd4a7

Try a prompt

Base models

Model card

From the Hugging Face model README

results_combined

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

Loss: 0.2039
Treatment: 0.9157
Chronic: 0.9092
Cancer: 0.8980
Allergy: 0.8158
Other: 0.9494
Weighted Avg: 0.9319

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: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Treatment	Chronic	Cancer	Allergy	Other	Weighted Avg
1.135	0.0995	100	0.6244	0.7117	0.6706	0.3658	0.0	0.8549	0.7592
0.4722	0.1990	200	0.3545	0.8356	0.8459	0.8056	0.0028	0.9165	0.8731
0.3368	0.2985	300	0.2911	0.8738	0.8737	0.8562	0.2790	0.9343	0.9012
0.2799	0.3980	400	0.2997	0.8723	0.8693	0.8567	0.7510	0.9370	0.9070
0.2941	0.4975	500	0.2878	0.8890	0.8689	0.8471	0.7100	0.9334	0.9069
0.2748	0.5970	600	0.2684	0.8851	0.8869	0.8659	0.7757	0.9380	0.9136
0.2466	0.6965	700	0.2525	0.9038	0.8782	0.8850	0.7934	0.9368	0.9164
0.2508	0.7960	800	0.2542	0.8955	0.8937	0.8714	0.6529	0.9409	0.9174
0.2392	0.8955	900	0.2189	0.9059	0.9008	0.8874	0.8157	0.9453	0.9257
0.237	0.9950	1000	0.2188	0.9014	0.8982	0.8807	0.8073	0.9459	0.9244
0.1843	1.0945	1100	0.2202	0.9077	0.9022	0.8825	0.8169	0.9465	0.9267
0.1766	1.1940	1200	0.2287	0.9148	0.9051	0.8759	0.8095	0.9468	0.9282
0.1667	1.2935	1300	0.2220	0.9091	0.9031	0.8878	0.7717	0.9483	0.9280
0.1868	1.3930	1400	0.2170	0.9140	0.9031	0.8932	0.8192	0.9473	0.9292
0.172	1.4925	1500	0.2151	0.9171	0.9070	0.8959	0.8113	0.9495	0.9317
0.1592	1.5920	1600	0.2082	0.9149	0.9060	0.8966	0.8097	0.9483	0.9305
0.1546	1.6915	1700	0.2039	0.9157	0.9092	0.8980	0.8158	0.9494	0.9319
0.1667	1.7910	1800	0.2041	0.9148	0.9100	0.9025	0.8128	0.9500	0.9325
0.1425	1.8905	1900	0.2093	0.9168	0.9099	0.8996	0.8125	0.9496	0.9325
0.1609	1.9900	2000	0.2059	0.9166	0.9110	0.8996	0.8125	0.9497	0.9327

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.19.1

Task: Token Classification
Library: transformers
Type: bert
License: apache-2.0
Created: Jun 27, 2024
Updated: Jun 29, 2024