Version_weird_ASAP_FineTuningBERT_AugV12_k10_task1_organization_k10_k10_fold1

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: 0.6475
• Qwk: 0.6652
• Mse: 0.6475
• Rmse: 0.8047

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	9.6083	-0.0002	9.6058	3.0993
No log	2.0	6	8.0111	0.0	8.0085	2.8299
No log	3.0	9	5.4888	0.0809	5.4863	2.3423
No log	4.0	12	4.1409	0.0079	4.1391	2.0345
No log	5.0	15	2.8160	0.0039	2.8144	1.6776
No log	6.0	18	2.2988	0.0615	2.2974	1.5157
No log	7.0	21	1.3564	0.0379	1.3547	1.1639
No log	8.0	24	0.9580	0.0211	0.9568	0.9781
No log	9.0	27	0.8299	0.2991	0.8287	0.9103
No log	10.0	30	0.8182	0.2004	0.8170	0.9039
No log	11.0	33	0.9664	0.0518	0.9656	0.9826
No log	12.0	36	1.1885	0.0518	1.1878	1.0899
No log	13.0	39	1.1777	0.2136	1.1770	1.0849
No log	14.0	42	1.4462	0.2041	1.4456	1.2023
No log	15.0	45	1.6508	0.1842	1.6504	1.2847
No log	16.0	48	1.3021	0.2878	1.3017	1.1409
No log	17.0	51	0.5746	0.5210	0.5740	0.7576
No log	18.0	54	0.5238	0.6246	0.5234	0.7235
No log	19.0	57	0.5707	0.6328	0.5701	0.7550
No log	20.0	60	0.5307	0.6832	0.5303	0.7282
No log	21.0	63	0.8465	0.5857	0.8466	0.9201
No log	22.0	66	0.5977	0.6546	0.5975	0.7730
No log	23.0	69	1.1312	0.5423	1.1316	1.0638
No log	24.0	72	0.4941	0.6694	0.4935	0.7025
No log	25.0	75	1.1737	0.5348	1.1741	1.0836
No log	26.0	78	0.7234	0.6185	0.7233	0.8505
No log	27.0	81	0.4611	0.6385	0.4606	0.6787
No log	28.0	84	1.2329	0.4690	1.2330	1.1104
No log	29.0	87	1.0975	0.4722	1.0974	1.0476
No log	30.0	90	0.5840	0.6440	0.5836	0.7639
No log	31.0	93	1.0243	0.5290	1.0243	1.0121
No log	32.0	96	1.0641	0.5304	1.0642	1.0316
No log	33.0	99	0.5146	0.6898	0.5145	0.7173
No log	34.0	102	0.8386	0.6015	0.8386	0.9158
No log	35.0	105	0.8392	0.5672	0.8391	0.9160
No log	36.0	108	0.9739	0.5580	0.9740	0.9869
No log	37.0	111	0.5356	0.6860	0.5355	0.7318
No log	38.0	114	0.5371	0.6770	0.5370	0.7328
No log	39.0	117	0.7163	0.6179	0.7162	0.8463
No log	40.0	120	0.7616	0.6122	0.7616	0.8727
No log	41.0	123	0.7926	0.5995	0.7925	0.8902
No log	42.0	126	0.9804	0.5385	0.9802	0.9901
No log	43.0	129	0.5345	0.6661	0.5343	0.7310
No log	44.0	132	0.5595	0.6769	0.5594	0.7479
No log	45.0	135	1.2601	0.4849	1.2600	1.1225
No log	46.0	138	1.0409	0.5092	1.0407	1.0201
No log	47.0	141	0.8094	0.5863	0.8093	0.8996
No log	48.0	144	0.8497	0.5943	0.8497	0.9218
No log	49.0	147	0.7667	0.6032	0.7667	0.8756
No log	50.0	150	0.9751	0.5092	0.9749	0.9873
No log	51.0	153	0.9236	0.5337	0.9235	0.9610
No log	52.0	156	0.7785	0.6075	0.7784	0.8823
No log	53.0	159	0.6475	0.6652	0.6475	0.8047

Framework versions

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