fineweb-edu-kr-scorer_gte-multilingual-base

This model is a fine-tuned version of Alibaba-NLP/gte-multilingual-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3162
• Precision: 0.6234
• Recall: 0.5137
• F1 Macro: 0.5517
• Accuracy: 0.6470

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: 0.0003
• train_batch_size: 256
• eval_batch_size: 128
• seed: 0
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1 Macro	Accuracy
No log	0	0	2.1114	0.1594	0.2001	0.0641	0.1899
0.3586	0.6325	1000	0.3604	0.4876	0.3912	0.4206	0.6117
0.3356	1.2650	2000	0.3510	0.6037	0.4682	0.5063	0.6294
0.3323	1.8975	3000	0.3287	0.6414	0.4737	0.5189	0.6419
0.3132	2.5300	4000	0.3243	0.6440	0.4738	0.5193	0.6421
0.309	3.1626	5000	0.3211	0.6374	0.4991	0.5431	0.6469
0.3083	3.7951	6000	0.3175	0.6532	0.4733	0.5182	0.6492
0.3066	4.4276	7000	0.3180	0.6379	0.5025	0.5442	0.6405
0.2958	5.0601	8000	0.3214	0.5228	0.4301	0.4615	0.6421
0.2941	5.6926	9000	0.3129	0.6410	0.5031	0.5462	0.6477
0.2887	6.3251	10000	0.3163	0.5242	0.4315	0.4633	0.6431
0.2853	6.9576	11000	0.3106	0.6449	0.4953	0.5396	0.6529
0.2753	7.5901	12000	0.3118	0.5321	0.4272	0.4622	0.6501
0.2697	8.2226	13000	0.3143	0.6339	0.5115	0.5524	0.6530
0.2725	8.8552	14000	0.3115	0.6403	0.5012	0.5454	0.6530
0.2672	9.4877	15000	0.3123	0.6398	0.5082	0.5513	0.6482
0.2583	10.1202	16000	0.3117	0.6440	0.5033	0.5458	0.6520
0.264	10.7527	17000	0.3126	0.6287	0.5195	0.5581	0.6484
0.2555	11.3852	18000	0.3148	0.6257	0.5224	0.5594	0.6471
0.256	12.0177	19000	0.3119	0.6352	0.5152	0.5558	0.6498
0.2503	12.6502	20000	0.3135	0.5226	0.4359	0.4674	0.6506
0.2451	13.2827	21000	0.3140	0.6412	0.5041	0.5472	0.6511
0.2497	13.9152	22000	0.3156	0.6331	0.5148	0.5541	0.6433
0.2432	14.5478	23000	0.3176	0.6230	0.5161	0.5529	0.6424
0.2353	15.1803	24000	0.3161	0.6286	0.5091	0.5491	0.6494
0.2334	15.8128	25000	0.3174	0.5174	0.4315	0.4618	0.6420
0.2352	16.4453	26000	0.3157	0.6255	0.5203	0.5578	0.6475
0.2293	17.0778	27000	0.3163	0.6281	0.5086	0.5478	0.6484
0.2297	17.7103	28000	0.3158	0.6258	0.5169	0.5554	0.6478
0.2319	18.3428	29000	0.3162	0.6260	0.5146	0.5531	0.6450
0.2335	18.9753	30000	0.3161	0.6222	0.5175	0.5547	0.6461
0.2262	19.6078	31000	0.3162	0.6234	0.5137	0.5517	0.6470

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0