Version_weird_ASAP_FineTuningBERT_AugV12_k6_task1_organization_k6_k6_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: 0.5022
• Qwk: 0.6631
• Mse: 0.5022
• Rmse: 0.7086

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	2	9.0378	0.0	9.0378	3.0063
No log	2.0	4	7.6163	0.0	7.6163	2.7598
No log	3.0	6	6.8514	0.0	6.8514	2.6175
No log	4.0	8	5.8736	0.0176	5.8736	2.4236
No log	5.0	10	5.0356	0.0115	5.0356	2.2440
No log	6.0	12	4.3284	0.0077	4.3283	2.0805
No log	7.0	14	3.5191	0.0	3.5191	1.8759
No log	8.0	16	2.8177	0.0	2.8177	1.6786
No log	9.0	18	2.1729	0.0627	2.1729	1.4741
No log	10.0	20	1.6977	0.0316	1.6977	1.3030
No log	11.0	22	1.3287	0.0316	1.3287	1.1527
No log	12.0	24	1.0797	0.0212	1.0797	1.0391
No log	13.0	26	0.8893	0.0369	0.8893	0.9430
No log	14.0	28	0.7897	0.1890	0.7897	0.8887
No log	15.0	30	0.7172	0.2213	0.7172	0.8469
No log	16.0	32	0.7048	0.1601	0.7048	0.8395
No log	17.0	34	0.7532	0.1502	0.7532	0.8678
No log	18.0	36	0.6644	0.2309	0.6644	0.8151
No log	19.0	38	0.7882	0.2266	0.7882	0.8878
No log	20.0	40	0.5153	0.4030	0.5153	0.7179
No log	21.0	42	0.6083	0.5140	0.6083	0.7799
No log	22.0	44	0.5563	0.5369	0.5563	0.7458
No log	23.0	46	0.4657	0.6174	0.4657	0.6825
No log	24.0	48	0.8299	0.5097	0.8299	0.9110
No log	25.0	50	0.5265	0.6185	0.5265	0.7256
No log	26.0	52	0.5755	0.6341	0.5755	0.7586
No log	27.0	54	0.8338	0.5727	0.8338	0.9131
No log	28.0	56	0.8532	0.5793	0.8532	0.9237
No log	29.0	58	0.5393	0.6841	0.5393	0.7344
No log	30.0	60	0.6050	0.6644	0.6050	0.7778
No log	31.0	62	0.5241	0.6607	0.5241	0.7240
No log	32.0	64	0.4276	0.6692	0.4276	0.6539
No log	33.0	66	0.7041	0.5911	0.7041	0.8391
No log	34.0	68	0.5886	0.6291	0.5886	0.7672
No log	35.0	70	0.4463	0.6543	0.4463	0.6681
No log	36.0	72	0.4846	0.6587	0.4846	0.6962
No log	37.0	74	0.4471	0.6396	0.4471	0.6687
No log	38.0	76	0.4474	0.6426	0.4474	0.6689
No log	39.0	78	0.4680	0.6536	0.4680	0.6841
No log	40.0	80	0.4849	0.6515	0.4849	0.6963
No log	41.0	82	0.5514	0.6520	0.5514	0.7425
No log	42.0	84	0.5064	0.6539	0.5064	0.7116
No log	43.0	86	0.4408	0.6397	0.4408	0.6640
No log	44.0	88	0.5347	0.6456	0.5347	0.7312
No log	45.0	90	0.5150	0.6450	0.5150	0.7176
No log	46.0	92	0.4678	0.6528	0.4678	0.6840
No log	47.0	94	0.5120	0.6413	0.5120	0.7155
No log	48.0	96	0.4972	0.6530	0.4972	0.7051
No log	49.0	98	0.5022	0.6631	0.5022	0.7086

Framework versions

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