ASAP_FineTuningBERT_AugV8_k2_task1_organization_k2_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: 0.8707
• Qwk: 0.3856
• Mse: 0.8707
• Rmse: 0.9331

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	9.1562	0.0055	9.1562	3.0259
No log	2.0	4	8.2018	0.0018	8.2018	2.8639
No log	3.0	6	7.0604	0.0	7.0604	2.6571
No log	4.0	8	5.9040	0.0133	5.9040	2.4298
No log	5.0	10	4.8670	0.0079	4.8670	2.2061
No log	6.0	12	3.9948	0.0040	3.9948	1.9987
No log	7.0	14	3.3136	0.0040	3.3136	1.8203
No log	8.0	16	2.6843	0.0040	2.6843	1.6384
No log	9.0	18	2.1148	0.0965	2.1148	1.4542
No log	10.0	20	1.7039	0.0420	1.7039	1.3053
No log	11.0	22	1.3880	0.0420	1.3880	1.1781
No log	12.0	24	1.3416	0.0420	1.3416	1.1583
No log	13.0	26	1.0438	0.0420	1.0438	1.0216
No log	14.0	28	1.5433	0.1465	1.5433	1.2423
No log	15.0	30	1.0895	0.1110	1.0895	1.0438
No log	16.0	32	0.9257	0.2865	0.9257	0.9621
No log	17.0	34	1.4243	0.2040	1.4243	1.1934
No log	18.0	36	0.8176	0.4163	0.8176	0.9042
No log	19.0	38	1.1406	0.3061	1.1406	1.0680
No log	20.0	40	1.1534	0.3201	1.1534	1.0740
No log	21.0	42	0.8710	0.3876	0.8710	0.9333
No log	22.0	44	1.2162	0.2326	1.2162	1.1028
No log	23.0	46	0.8118	0.3930	0.8118	0.9010
No log	24.0	48	1.1061	0.3022	1.1061	1.0517
No log	25.0	50	1.0337	0.3465	1.0337	1.0167
No log	26.0	52	0.6291	0.4662	0.6291	0.7931
No log	27.0	54	1.0230	0.3792	1.0230	1.0114
No log	28.0	56	0.8564	0.4161	0.8564	0.9254
No log	29.0	58	0.6712	0.4669	0.6712	0.8193
No log	30.0	60	0.8744	0.3648	0.8744	0.9351
No log	31.0	62	0.8814	0.3983	0.8814	0.9388
No log	32.0	64	0.5998	0.5257	0.5998	0.7745
No log	33.0	66	0.6548	0.5443	0.6548	0.8092
No log	34.0	68	1.1177	0.3339	1.1177	1.0572
No log	35.0	70	0.9153	0.3896	0.9153	0.9567
No log	36.0	72	0.8065	0.4688	0.8065	0.8980
No log	37.0	74	1.1134	0.3143	1.1134	1.0552
No log	38.0	76	1.1732	0.2948	1.1732	1.0831
No log	39.0	78	0.8321	0.4171	0.8321	0.9122
No log	40.0	80	0.9266	0.3884	0.9266	0.9626
No log	41.0	82	0.9125	0.3606	0.9125	0.9552
No log	42.0	84	0.7919	0.4285	0.7919	0.8899
No log	43.0	86	0.8707	0.3856	0.8707	0.9331

Framework versions

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