Version_concise_ASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_fold2

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: 1.1353
• Qwk: 0.4321
• Mse: 1.1341
• Rmse: 1.0649

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	9.2333	0.0	9.2336	3.0387
No log	2.0	8	6.3422	0.0087	6.3426	2.5185
No log	3.0	12	3.8708	0.0039	3.8711	1.9675
No log	4.0	16	2.3283	0.1027	2.3287	1.5260
No log	5.0	20	1.7155	0.0501	1.7159	1.3099
No log	6.0	24	1.2847	0.0280	1.2851	1.1336
No log	7.0	28	0.9823	0.0174	0.9826	0.9913
No log	8.0	32	0.8225	0.3053	0.8227	0.9070
No log	9.0	36	0.8666	0.3290	0.8667	0.9310
No log	10.0	40	0.8367	0.3964	0.8366	0.9146
No log	11.0	44	0.7933	0.4297	0.7930	0.8905
No log	12.0	48	0.9072	0.4201	0.9068	0.9522
No log	13.0	52	0.8809	0.4290	0.8803	0.9382
No log	14.0	56	0.6916	0.4783	0.6910	0.8312
No log	15.0	60	0.8238	0.4405	0.8228	0.9071
No log	16.0	64	0.8148	0.4654	0.8138	0.9021
No log	17.0	68	0.8538	0.4760	0.8527	0.9234
No log	18.0	72	0.9999	0.4405	0.9986	0.9993
No log	19.0	76	1.0019	0.4554	1.0006	1.0003
No log	20.0	80	1.1618	0.3745	1.1605	1.0773
No log	21.0	84	1.0175	0.4589	1.0164	1.0081
No log	22.0	88	1.1290	0.4834	1.1278	1.0620
No log	23.0	92	1.1970	0.3870	1.1955	1.0934
No log	24.0	96	1.1282	0.4673	1.1269	1.0616
No log	25.0	100	1.1480	0.3714	1.1468	1.0709
No log	26.0	104	1.1077	0.4603	1.1065	1.0519
No log	27.0	108	1.0251	0.4551	1.0237	1.0118
No log	28.0	112	1.1306	0.3928	1.1293	1.0627
No log	29.0	116	1.1263	0.4838	1.1248	1.0605
No log	30.0	120	1.2243	0.3904	1.2227	1.1057
No log	31.0	124	1.2559	0.4217	1.2544	1.1200
No log	32.0	128	1.1514	0.4071	1.1498	1.0723
No log	33.0	132	1.3955	0.3949	1.3941	1.1807
No log	34.0	136	1.3437	0.4097	1.3420	1.1585
No log	35.0	140	1.2856	0.4333	1.2840	1.1331
No log	36.0	144	1.2304	0.4319	1.2289	1.1086
No log	37.0	148	1.2883	0.4315	1.2868	1.1344
No log	38.0	152	1.1758	0.4253	1.1743	1.0836
No log	39.0	156	1.1739	0.4278	1.1722	1.0827
No log	40.0	160	1.2062	0.3665	1.2049	1.0977
No log	41.0	164	1.4454	0.3883	1.4445	1.2019
No log	42.0	168	1.2265	0.3824	1.2252	1.1069
No log	43.0	172	1.3218	0.3864	1.3204	1.1491
No log	44.0	176	1.5018	0.3722	1.5005	1.2249
No log	45.0	180	1.2620	0.4116	1.2605	1.1227
No log	46.0	184	1.2455	0.4269	1.2440	1.1154
No log	47.0	188	1.0308	0.3738	1.0298	1.0148
No log	48.0	192	1.1424	0.4214	1.1413	1.0683
No log	49.0	196	1.1353	0.4321	1.1341	1.0649

Framework versions

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