Version_weird_ASAP_FineTuningBERT_AugV12_k15_task1_organization_k15_k15_fold0

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: 0.5373
• Qwk: 0.6588
• Mse: 0.5373
• Rmse: 0.7330

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	8.1828	0.0	8.1828	2.8606
No log	2.0	6	6.8597	0.0	6.8597	2.6191
No log	3.0	9	5.5617	0.0112	5.5617	2.3583
No log	4.0	12	4.3490	0.0039	4.3490	2.0854
No log	5.0	15	3.1646	0.0	3.1646	1.7789
No log	6.0	18	2.1376	0.0689	2.1376	1.4620
No log	7.0	21	1.4538	0.0316	1.4538	1.2057
No log	8.0	24	1.0235	0.0212	1.0235	1.0117
No log	9.0	27	0.8177	0.1742	0.8177	0.9043
No log	10.0	30	0.7601	0.0968	0.7601	0.8719
No log	11.0	33	0.8499	0.0689	0.8499	0.9219
No log	12.0	36	1.0047	0.0521	1.0047	1.0023
No log	13.0	39	1.0503	0.3391	1.0503	1.0248
No log	14.0	42	1.1579	0.2812	1.1579	1.0761
No log	15.0	45	0.9515	0.4071	0.9515	0.9754
No log	16.0	48	0.6790	0.5275	0.6790	0.8240
No log	17.0	51	0.6746	0.5808	0.6746	0.8214
No log	18.0	54	0.5768	0.6447	0.5768	0.7595
No log	19.0	57	0.5450	0.6695	0.5450	0.7382
No log	20.0	60	0.5238	0.6634	0.5238	0.7237
No log	21.0	63	0.7143	0.5976	0.7143	0.8452
No log	22.0	66	0.4357	0.6163	0.4357	0.6601
No log	23.0	69	1.8064	0.3904	1.8064	1.3440
No log	24.0	72	0.5467	0.5985	0.5467	0.7394
No log	25.0	75	0.5931	0.6127	0.5931	0.7701
No log	26.0	78	1.1661	0.4857	1.1661	1.0799
No log	27.0	81	0.4817	0.6465	0.4817	0.6941
No log	28.0	84	0.6248	0.6407	0.6248	0.7904
No log	29.0	87	0.6360	0.5801	0.6360	0.7975
No log	30.0	90	0.5151	0.6248	0.5151	0.7177
No log	31.0	93	0.4918	0.6499	0.4918	0.7013
No log	32.0	96	0.5364	0.6660	0.5364	0.7324
No log	33.0	99	0.4716	0.6403	0.4716	0.6867
No log	34.0	102	0.6455	0.5838	0.6455	0.8034
No log	35.0	105	0.4375	0.6290	0.4375	0.6614
No log	36.0	108	0.6254	0.6110	0.6254	0.7908
No log	37.0	111	0.4787	0.6529	0.4787	0.6918
No log	38.0	114	0.5030	0.6655	0.5030	0.7092
No log	39.0	117	0.5373	0.6588	0.5373	0.7330

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0