bge-m3-edu-scorer-lr3e5-bs32

This model is a fine-tuned version of BAAI/bge-m3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2380
• Precision: 0.4817
• Recall: 0.345
• F1 Macro: 0.3403
• Accuracy: 0.3709

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: 0
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1 Macro	Accuracy
No log	0	0	3.4165	0.0891	0.1668	0.0874	0.3526
0.9463	0.3368	1000	0.9205	0.3220	0.2806	0.2541	0.4234
0.8023	0.6736	2000	0.7874	0.4037	0.3211	0.3133	0.47
0.7599	1.0104	3000	0.7541	0.4143	0.3319	0.3267	0.478
0.7508	1.3473	4000	0.7518	0.4155	0.3353	0.3289	0.4884
0.7342	1.6841	5000	0.7402	0.3963	0.3310	0.3233	0.4746
0.7122	2.0209	6000	0.7442	0.4105	0.3344	0.3293	0.4966
0.7719	2.3577	7000	0.7282	0.4580	0.3494	0.3499	0.4808
0.7346	2.6945	8000	0.7177	0.4993	0.3573	0.3601	0.4962
0.6964	3.0313	9000	0.7203	0.4079	0.3454	0.3390	0.4908
0.6999	3.3681	10000	0.7195	0.4250	0.3444	0.3422	0.5068
0.7036	3.7050	11000	0.7054	0.4842	0.3565	0.3589	0.503
0.6953	4.0418	12000	0.7028	0.4887	0.3560	0.3592	0.4856
0.6808	4.3786	13000	0.7103	0.4289	0.3594	0.3599	0.4778
0.7021	4.7154	14000	0.6918	0.4628	0.3604	0.3622	0.4928
0.6476	5.0522	15000	0.6884	0.4275	0.3634	0.3631	0.5062
0.6674	5.3890	16000	0.6767	0.4543	0.3651	0.3684	0.5084
0.6683	5.7258	17000	0.6924	0.5046	0.3600	0.3638	0.519
0.6491	6.0626	18000	0.6814	0.4656	0.3624	0.3666	0.506
0.6824	6.3995	19000	0.6724	0.4554	0.3656	0.3697	0.5026
0.6366	6.7363	20000	0.6712	0.4314	0.3670	0.3684	0.5062
0.6594	7.0731	21000	0.6686	0.4503	0.3679	0.3716	0.5068
0.6605	7.4099	22000	0.6669	0.4441	0.3711	0.3720	0.506
0.6448	7.7467	23000	0.6716	0.4306	0.3676	0.3687	0.4992
0.6108	8.0835	24000	0.6646	0.4573	0.3683	0.3728	0.5184
0.6202	8.4203	25000	0.6623	0.4336	0.3691	0.3715	0.518
0.6483	8.7572	26000	0.6623	0.4434	0.3696	0.3735	0.5142
0.667	9.0940	27000	0.6569	0.4491	0.3724	0.3752	0.5166
0.6241	9.4308	28000	0.6572	0.4368	0.3705	0.3735	0.516
0.5817	9.7676	29000	0.6552	0.4473	0.3739	0.3782	0.5242
0.6129	10.1044	30000	0.6603	0.4585	0.3717	0.3764	0.5218
0.6051	10.4412	31000	0.6565	0.4783	0.3725	0.3796	0.5272
0.5914	10.7780	32000	0.6514	0.4484	0.3741	0.3769	0.517
0.6089	11.1149	33000	0.6570	0.4449	0.3729	0.3773	0.5054
0.5907	11.4517	34000	0.6520	0.4652	0.3696	0.3740	0.5206
0.6165	11.7885	35000	0.6501	0.4627	0.3807	0.3867	0.5248
0.5896	12.1253	36000	0.6513	0.4351	0.3735	0.3758	0.5116
0.5681	12.4621	37000	0.6480	0.4492	0.3749	0.3806	0.5216
0.6265	12.7989	38000	0.6498	0.4651	0.3755	0.3816	0.5246
0.5862	13.1357	39000	0.6449	0.4551	0.3732	0.3784	0.5256
0.6074	13.4725	40000	0.6480	0.4525	0.3765	0.3804	0.5136
0.5815	13.8094	41000	0.6495	0.4510	0.3761	0.3808	0.5312
0.5591	14.1462	42000	0.6450	0.4608	0.3757	0.3808	0.5176
0.5616	14.4830	43000	0.6444	0.4613	0.3802	0.3854	0.525
0.5735	14.8198	44000	0.6467	0.4756	0.3707	0.3776	0.5266
0.5891	15.1566	45000	0.6450	0.4537	0.3764	0.3808	0.525
0.571	15.4934	46000	0.6431	0.4581	0.3783	0.3846	0.5264
0.5853	15.8302	47000	0.6412	0.4751	0.3804	0.3858	0.5242
0.5796	16.1671	48000	0.6464	0.4628	0.3810	0.3866	0.528
0.5912	16.5039	49000	0.6443	0.4560	0.3816	0.3869	0.5242
0.5302	16.8407	50000	0.6412	0.4610	0.3800	0.3858	0.5292
0.5752	17.1775	51000	0.6400	0.4521	0.3793	0.3845	0.5254
0.5771	17.5143	52000	0.6412	0.4678	0.3818	0.3873	0.535
0.5383	17.8511	53000	0.6393	0.4582	0.3778	0.3838	0.5196
0.5373	18.1879	54000	0.6393	0.4571	0.3787	0.3845	0.5234
0.565	18.5248	55000	0.6390	0.4535	0.3766	0.3821	0.5214
0.5498	18.8616	56000	0.6394	0.4596	0.3770	0.3823	0.5282
0.5643	19.1984	57000	0.6384	0.4572	0.3777	0.3830	0.5238
0.5697	19.5352	58000	0.6390	0.4558	0.3766	0.3819	0.5244
0.547	19.8720	59000	0.6394	0.4573	0.3787	0.3843	0.524

Framework versions

• Transformers 4.53.2
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.21.2