Version3_ASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_fold3

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: 0.7043
• Qwk: 0.5771
• Mse: 0.7049
• Rmse: 0.8396

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	9.2142	0.0	9.2126	3.0352
No log	2.0	8	6.8108	0.0	6.8093	2.6095
No log	3.0	12	4.1226	0.0038	4.1213	2.0301
No log	4.0	16	3.2069	0.0010	3.2059	1.7905
No log	5.0	20	1.7597	0.0202	1.7589	1.3262
No log	6.0	24	1.2773	0.0355	1.2768	1.1300
No log	7.0	28	1.0465	-0.1076	1.0459	1.0227
No log	8.0	32	1.2588	0.0811	1.2585	1.1218
No log	9.0	36	1.0964	0.0958	1.0961	1.0470
No log	10.0	40	0.6781	0.3474	0.6780	0.8234
No log	11.0	44	0.7543	0.4044	0.7543	0.8685
No log	12.0	48	0.5909	0.5376	0.5910	0.7688
No log	13.0	52	0.7128	0.5493	0.7131	0.8445
No log	14.0	56	0.5488	0.5621	0.5492	0.7411
No log	15.0	60	0.5546	0.5882	0.5550	0.7450
No log	16.0	64	0.8963	0.5249	0.8971	0.9471
No log	17.0	68	0.6389	0.6195	0.6395	0.7997
No log	18.0	72	0.7927	0.5940	0.7935	0.8908
No log	19.0	76	0.9394	0.5331	0.9403	0.9697
No log	20.0	80	0.7548	0.5775	0.7553	0.8691
No log	21.0	84	0.9783	0.5267	0.9791	0.9895
No log	22.0	88	0.8373	0.5792	0.8379	0.9154
No log	23.0	92	0.8537	0.5573	0.8545	0.9244
No log	24.0	96	0.7848	0.5595	0.7854	0.8862
No log	25.0	100	0.7843	0.5877	0.7848	0.8859
No log	26.0	104	0.8265	0.5412	0.8273	0.9095
No log	27.0	108	0.9620	0.5508	0.9627	0.9812
No log	28.0	112	0.7898	0.5259	0.7906	0.8892
No log	29.0	116	0.7855	0.5842	0.7863	0.8867
No log	30.0	120	0.7657	0.5341	0.7665	0.8755
No log	31.0	124	0.7680	0.5777	0.7687	0.8768
No log	32.0	128	0.6835	0.5931	0.6841	0.8271
No log	33.0	132	0.7560	0.5326	0.7567	0.8699
No log	34.0	136	0.7747	0.5718	0.7753	0.8805
No log	35.0	140	0.7159	0.5806	0.7165	0.8465
No log	36.0	144	0.6999	0.5727	0.7004	0.8369
No log	37.0	148	0.7043	0.5771	0.7049	0.8396

Framework versions

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