Version_weird_ASAP_FineTuningBERT_AugV12_k10_task1_organization_k10_k10_fold4

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: 0.9002
• Qwk: 0.6066
• Mse: 0.9002
• Rmse: 0.9488

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	7.8056	0.0037	7.8056	2.7938
No log	2.0	6	5.8481	0.0213	5.8481	2.4183
No log	3.0	9	4.2144	0.0156	4.2144	2.0529
No log	4.0	12	2.7847	0.0118	2.7847	1.6687
No log	5.0	15	2.0015	0.1082	2.0015	1.4147
No log	6.0	18	1.3584	0.0420	1.3584	1.1655
No log	7.0	21	1.0811	0.0316	1.0811	1.0398
No log	8.0	24	0.9124	0.0530	0.9124	0.9552
No log	9.0	27	0.8243	0.1118	0.8243	0.9079
No log	10.0	30	0.9123	0.0747	0.9123	0.9552
No log	11.0	33	1.2739	0.0454	1.2739	1.1287
No log	12.0	36	1.4335	0.1759	1.4335	1.1973
No log	13.0	39	1.8193	0.1162	1.8193	1.3488
No log	14.0	42	1.8561	0.1435	1.8561	1.3624
No log	15.0	45	0.9841	0.3761	0.9841	0.9920
No log	16.0	48	0.7313	0.5326	0.7313	0.8552
No log	17.0	51	0.7339	0.5702	0.7339	0.8567
No log	18.0	54	0.5834	0.5840	0.5834	0.7638
No log	19.0	57	0.6078	0.5890	0.6078	0.7796
No log	20.0	60	0.7324	0.6326	0.7324	0.8558
No log	21.0	63	0.5792	0.6737	0.5792	0.7611
No log	22.0	66	1.4680	0.4653	1.4680	1.2116
No log	23.0	69	0.6729	0.6499	0.6729	0.8203
No log	24.0	72	1.4444	0.4875	1.4444	1.2018
No log	25.0	75	1.5153	0.4856	1.5153	1.2310
No log	26.0	78	0.6709	0.6385	0.6709	0.8191
No log	27.0	81	1.4818	0.4740	1.4818	1.2173
No log	28.0	84	1.2698	0.5007	1.2698	1.1268
No log	29.0	87	0.5879	0.6431	0.5879	0.7667
No log	30.0	90	0.6411	0.6549	0.6411	0.8007
No log	31.0	93	1.3267	0.5113	1.3267	1.1518
No log	32.0	96	0.8309	0.6278	0.8309	0.9115
No log	33.0	99	0.8959	0.5986	0.8959	0.9465
No log	34.0	102	1.2955	0.4868	1.2955	1.1382
No log	35.0	105	0.5478	0.6556	0.5478	0.7401
No log	36.0	108	0.5421	0.6591	0.5421	0.7363
No log	37.0	111	0.9267	0.5830	0.9267	0.9627
No log	38.0	114	1.6690	0.4389	1.6690	1.2919
No log	39.0	117	0.8910	0.5954	0.8910	0.9439
No log	40.0	120	0.8903	0.5997	0.8903	0.9436
No log	41.0	123	0.9002	0.6066	0.9002	0.9488

Framework versions

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