BERT_V8_sp10_lw20_ex200_lo50_k5_k5_fold1

genki10/BERT_V8_sp10_lw20_ex200_lo50_k5_k5_fold1

BERT_V8_sp10_lw20_ex200_lo50_k5_k5_fold1 is a text classification model from genki10. Use it when you need a label for a piece of text. 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

0% of all-time downloads

All-time downloads

Public

Repo size

16.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin876 MB · 100%

At a glance

Task: Text Classification
Library: transformers
License: apache-2.0
Model type: bert
Access: Public
Created: Apr 17, 2025
Updated: Apr 17, 2025
SHA: 0143f512

Try a prompt

Base models

Model card

From the Hugging Face model README

BERT_V8_sp10_lw20_ex200_lo50_k5_k5_fold1

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

Loss: 0.6259
Qwk: 0.4761
Mse: 0.6243
Rmse: 0.7901

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-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	3	10.1387	0.0	10.1363	3.1838
No log	2.0	6	8.1001	0.0	8.0976	2.8456
No log	3.0	9	5.5299	0.0391	5.5276	2.3511
No log	4.0	12	3.1730	0.0	3.1712	1.7808
No log	5.0	15	1.9022	0.1410	1.9005	1.3786
No log	6.0	18	1.2029	0.0315	1.2014	1.0961
No log	7.0	21	0.9224	0.0973	0.9211	0.9597
No log	8.0	24	0.8755	0.1225	0.8744	0.9351
No log	9.0	27	0.7800	0.1347	0.7790	0.8826
No log	10.0	30	0.6465	0.3258	0.6456	0.8035
No log	11.0	33	0.6166	0.4947	0.6156	0.7846
No log	12.0	36	0.5464	0.4297	0.5456	0.7387
No log	13.0	39	0.6838	0.5029	0.6826	0.8262
No log	14.0	42	0.5494	0.5918	0.5487	0.7407
No log	15.0	45	0.5114	0.5507	0.5103	0.7144
No log	16.0	48	1.0454	0.3506	1.0437	1.0216
No log	17.0	51	0.5214	0.5415	0.5205	0.7214
No log	18.0	54	0.6422	0.4819	0.6407	0.8004
No log	19.0	57	0.6164	0.4897	0.6149	0.7841
No log	20.0	60	0.5502	0.5744	0.5492	0.7411
No log	21.0	63	0.5511	0.5406	0.5497	0.7414
No log	22.0	66	0.5566	0.5642	0.5552	0.7451
No log	23.0	69	0.5718	0.5557	0.5703	0.7552
No log	24.0	72	0.5502	0.5877	0.5488	0.7408
No log	25.0	75	0.6996	0.4958	0.6978	0.8353
No log	26.0	78	0.6305	0.5521	0.6295	0.7934
No log	27.0	81	0.5356	0.5804	0.5344	0.7310
No log	28.0	84	0.6656	0.5149	0.6640	0.8149
No log	29.0	87	0.5512	0.5674	0.5499	0.7415
No log	30.0	90	0.5929	0.5194	0.5914	0.7690
No log	31.0	93	0.5671	0.5644	0.5661	0.7524
No log	32.0	96	0.7343	0.4891	0.7327	0.8560
No log	33.0	99	0.7206	0.4905	0.7190	0.8480
No log	34.0	102	0.6488	0.5613	0.6479	0.8049
No log	35.0	105	0.5364	0.5874	0.5353	0.7316
No log	36.0	108	0.6364	0.5325	0.6349	0.7968
No log	37.0	111	0.5458	0.5637	0.5445	0.7379
No log	38.0	114	0.6272	0.5174	0.6257	0.7910
No log	39.0	117	0.5850	0.5327	0.5835	0.7639
No log	40.0	120	0.5892	0.5240	0.5881	0.7669
No log	41.0	123	0.6380	0.4830	0.6364	0.7978
No log	42.0	126	0.6103	0.5082	0.6088	0.7802
No log	43.0	129	0.5529	0.5423	0.5517	0.7428
No log	44.0	132	0.6259	0.4761	0.6243	0.7901

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

Task: Text Classification
Library: transformers
Type: bert
License: apache-2.0
Created: Apr 17, 2025
Updated: Apr 17, 2025