combined-finetuned

TakalaWang/combined-finetuned

combined-finetuned is a machine learning model from TakalaWang. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

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

Downloads · 30 days

Access

Public

Updated Apr 16, 2025

Parameters

204M

1.6 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors816 MB · 100%

At a glance

Library: transformers
Access: Public
Created: Apr 16, 2025
Updated: Apr 16, 2025
SHA: 802e316f

Model card

From the Hugging Face model README

combined-finetuned

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7790
Accuracy: 0.6966

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: 0.001
train_batch_size: 4
eval_batch_size: 4
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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6898	0.0556	10	1.9771	0.1348
1.8961	0.1111	20	1.8402	0.2472
1.8259	0.1667	30	1.7101	0.3146
1.3534	0.2222	40	1.5978	0.3371
1.4887	0.2778	50	1.5017	0.3371
1.4251	0.3333	60	1.4178	0.3371
1.4539	0.3889	70	1.3337	0.3483
1.2221	0.4444	80	1.2563	0.3708
1.2487	0.5	90	1.1889	0.4157
1.1406	0.5556	100	1.1331	0.4607
1.0978	0.6111	110	1.0826	0.4944
1.068	0.6667	120	1.0459	0.5393
0.9636	0.7222	130	1.0139	0.6292
0.9899	0.7778	140	0.9942	0.6180
0.9764	0.8333	150	0.9711	0.6629
1.0178	0.8889	160	0.9448	0.6517
0.8486	0.9444	170	0.9202	0.6629
0.923	1.0	180	0.8977	0.6067
1.0081	1.0556	190	0.8822	0.6180
0.9016	1.1111	200	0.8715	0.6292
0.8923	1.1667	210	0.8647	0.6292
0.8144	1.2222	220	0.8550	0.6180
0.8705	1.2778	230	0.8464	0.6629
0.8513	1.3333	240	0.8390	0.6629
0.7723	1.3889	250	0.8327	0.6742
0.8737	1.4444	260	0.8282	0.6629
0.752	1.5	270	0.8257	0.6180
0.8057	1.5556	280	0.8208	0.6180
0.8247	1.6111	290	0.8156	0.6404
0.8664	1.6667	300	0.8096	0.6629
0.8615	1.7222	310	0.8044	0.6854
0.6972	1.7778	320	0.8010	0.6742
0.8843	1.8333	330	0.7969	0.6517
0.6894	1.8889	340	0.7941	0.6404
0.7269	1.9444	350	0.7922	0.6517
0.7956	2.0	360	0.7920	0.6854
0.7205	2.0556	370	0.7912	0.6966
0.7218	2.1111	380	0.7903	0.6966
0.9249	2.1667	390	0.7880	0.6966
0.8235	2.2222	400	0.7864	0.6854
0.8147	2.2778	410	0.7857	0.6966
0.8336	2.3333	420	0.7845	0.6854
0.7546	2.3889	430	0.7835	0.6966
0.6565	2.4444	440	0.7829	0.6966
0.7907	2.5	450	0.7817	0.6966
0.7389	2.5556	460	0.7808	0.6966
0.7064	2.6111	470	0.7805	0.6966
0.8611	2.6667	480	0.7804	0.6966
0.8771	2.7222	490	0.7802	0.6966
0.8697	2.7778	500	0.7797	0.6966
0.7718	2.8333	510	0.7795	0.6966
0.7465	2.8889	520	0.7793	0.6966
0.7693	2.9444	530	0.7791	0.6966
0.7886	3.0	540	0.7790	0.6966

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.3.2
Tokenizers 0.21.0

Library: transformers
Created: Apr 16, 2025
Updated: Apr 16, 2025