Version_concise_ASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_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: 1.0307
• Qwk: 0.4300
• Mse: 1.0307
• Rmse: 1.0152

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	4	7.4588	0.0018	7.4588	2.7311
No log	2.0	8	5.6748	0.0147	5.6748	2.3822
No log	3.0	12	3.1219	0.0040	3.1219	1.7669
No log	4.0	16	2.0769	0.0443	2.0769	1.4412
No log	5.0	20	1.3324	0.0420	1.3324	1.1543
No log	6.0	24	1.1297	0.0420	1.1297	1.0629
No log	7.0	28	0.9878	0.0893	0.9878	0.9939
No log	8.0	32	0.8485	0.3041	0.8485	0.9212
No log	9.0	36	1.2866	0.2224	1.2866	1.1343
No log	10.0	40	0.7212	0.4504	0.7212	0.8493
No log	11.0	44	0.7540	0.3932	0.7540	0.8683
No log	12.0	48	1.4693	0.2655	1.4693	1.2122
No log	13.0	52	0.8152	0.3987	0.8152	0.9029
No log	14.0	56	0.6546	0.5020	0.6546	0.8091
No log	15.0	60	1.1949	0.3535	1.1949	1.0931
No log	16.0	64	0.6309	0.4675	0.6309	0.7943
No log	17.0	68	0.7855	0.4193	0.7855	0.8863
No log	18.0	72	0.9035	0.4336	0.9035	0.9505
No log	19.0	76	0.6346	0.5751	0.6346	0.7966
No log	20.0	80	1.5135	0.3608	1.5135	1.2303
No log	21.0	84	0.7148	0.5558	0.7148	0.8455
No log	22.0	88	1.4888	0.3392	1.4888	1.2202
No log	23.0	92	0.7341	0.5106	0.7341	0.8568
No log	24.0	96	0.7437	0.5145	0.7437	0.8624
No log	25.0	100	1.1277	0.3793	1.1277	1.0619
No log	26.0	104	0.6928	0.5499	0.6928	0.8323
No log	27.0	108	1.2308	0.3657	1.2308	1.1094
No log	28.0	112	0.6680	0.5682	0.6680	0.8173
No log	29.0	116	1.2037	0.3691	1.2037	1.0971
No log	30.0	120	0.6844	0.5727	0.6844	0.8273
No log	31.0	124	1.5364	0.2895	1.5364	1.2395
No log	32.0	128	1.0686	0.4135	1.0686	1.0337
No log	33.0	132	0.6534	0.5681	0.6534	0.8084
No log	34.0	136	1.1260	0.3803	1.1260	1.0611
No log	35.0	140	0.6955	0.5569	0.6955	0.8340
No log	36.0	144	1.0050	0.4228	1.0050	1.0025
No log	37.0	148	0.7496	0.5306	0.7496	0.8658
No log	38.0	152	0.8950	0.4803	0.8950	0.9461
No log	39.0	156	1.0307	0.4300	1.0307	1.0152

Framework versions

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