qwen3_4_20250810_1830

prl90777/qwen3_4_20250810_1830

qwen3_4_20250810_1830 is a machine learning model from prl90777. 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 peft. The card lists the license as apache-2.0.

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

Downloads · 30 days

26% of all-time downloads

All-time downloads

Public

Repo size

410 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors133 MB · 89%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Aug 10, 2025
Updated: Aug 11, 2025
SHA: 18ad8d9c

Base models

Qwen/Qwen3-4B

Model card

From the Hugging Face model README

qwen3_4_20250810_1830

This model is a fine-tuned version of Qwen/Qwen3-4B on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3527
Map@3: 0.9402

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: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
optimizer: Use OptimizerNames.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	Map@3
17.833	0.0598	20	1.5907	0.6585
10.8612	0.1196	40	1.0722	0.7894
7.8304	0.1794	60	0.9041	0.8111
6.5089	0.2392	80	0.7447	0.8618
5.8982	0.2990	100	0.8053	0.8353
5.731	0.3587	120	0.6625	0.8693
5.0727	0.4185	140	0.5880	0.8846
4.5931	0.4783	160	0.6262	0.8838
4.7836	0.5381	180	0.6134	0.8885
4.4168	0.5979	200	0.5579	0.8916
4.1757	0.6577	220	0.5146	0.8965
4.3021	0.7175	240	0.6313	0.8833
4.6016	0.7773	260	0.4597	0.9115
3.7059	0.8371	280	0.5034	0.9067
3.9725	0.8969	300	0.4700	0.9133
3.914	0.9567	320	0.4651	0.9122
3.7313	1.0149	340	0.4505	0.9136
2.9634	1.0747	360	0.4426	0.9149
2.6522	1.1345	380	0.4350	0.9170
3.2828	1.1943	400	0.4200	0.9143
2.4674	1.2541	420	0.4215	0.9216
2.7299	1.3139	440	0.4072	0.9242
2.8582	1.3737	460	0.3967	0.9253
2.5655	1.4335	480	0.4050	0.9231
2.5789	1.4933	500	0.3962	0.9259
2.6098	1.5531	520	0.3773	0.9266
2.432	1.6129	540	0.3689	0.9304
2.6076	1.6726	560	0.3542	0.9342
2.3517	1.7324	580	0.3527	0.9325
2.5449	1.7922	600	0.3853	0.9287
2.7974	1.8520	620	0.3393	0.9350
2.3339	1.9118	640	0.3370	0.9353
2.1641	1.9716	660	0.3473	0.9360
2.3347	2.0299	680	0.3355	0.9348
1.5164	2.0897	700	0.3569	0.9346
1.3422	2.1495	720	0.3643	0.9365
1.4261	2.2093	740	0.3514	0.9385
1.2539	2.2691	760	0.3639	0.9388
1.2392	2.3288	780	0.3515	0.9373
1.3577	2.3886	800	0.3409	0.9389
1.4255	2.4484	820	0.3588	0.9375
1.1825	2.5082	840	0.3485	0.9381
1.0949	2.5680	860	0.3546	0.9393
0.9391	2.6278	880	0.3649	0.9386
1.4165	2.6876	900	0.3568	0.9394
0.9286	2.7474	920	0.3540	0.9391
1.0405	2.8072	940	0.3531	0.9399
1.1154	2.8670	960	0.3526	0.9401
0.9436	2.9268	980	0.3532	0.9398
1.3439	2.9865	1000	0.3527	0.9402

Framework versions

PEFT 0.17.0
Transformers 4.55.0
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.4

Library: peft
License: apache-2.0
Created: Aug 10, 2025
Updated: Aug 11, 2025