Modelpublic

genki10/Version_Test_ASAP_FineTuningBERT_AugV14_k5_task1_organization_k5_k5_fold4

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes1downloads

Model Card

VersionTestASAPFineTuningBERTAugV14k5task1organizationk5k5fold4

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: 0.6453
—Qwk: 0.6137
—Mse: 0.6453
—Rmse: 0.8033

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
—trainbatchsize: 64
—evalbatchsize: 64
—seed: 42
—optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	4	6.5522	0.0018	6.5522	2.5597
No log	2.0	8	3.8429	0.0118	3.8429	1.9603
No log	3.0	12	2.3726	0.0725	2.3726	1.5403
No log	4.0	16	1.1503	0.0316	1.1503	1.0725
No log	5.0	20	0.8362	0.2069	0.8362	0.9144
No log	6.0	24	0.8330	0.0840	0.8330	0.9127
No log	7.0	28	0.7226	0.1986	0.7226	0.8501
No log	8.0	32	0.5366	0.4420	0.5366	0.7325
No log	9.0	36	0.4952	0.6240	0.4952	0.7037
No log	10.0	40	0.5231	0.6141	0.5231	0.7233
No log	11.0	44	0.5175	0.6368	0.5175	0.7194
No log	12.0	48	0.7652	0.4889	0.7652	0.8747
No log	13.0	52	0.6165	0.5830	0.6165	0.7852
No log	14.0	56	0.4907	0.6291	0.4907	0.7005
No log	15.0	60	0.5052	0.6328	0.5052	0.7107
No log	16.0	64	0.5566	0.6141	0.5566	0.7461
No log	17.0	68	0.4707	0.6425	0.4707	0.6861
No log	18.0	72	0.5250	0.6099	0.5250	0.7246
No log	19.0	76	0.5387	0.6306	0.5387	0.7340
No log	20.0	80	0.6385	0.6187	0.6385	0.7990
No log	21.0	84	0.6432	0.6275	0.6432	0.8020
No log	22.0	88	0.8777	0.5814	0.8777	0.9368
No log	23.0	92	0.5681	0.6380	0.5681	0.7537
No log	24.0	96	0.9545	0.5664	0.9545	0.9770
No log	25.0	100	0.5826	0.6219	0.5826	0.7633
No log	26.0	104	0.5740	0.6295	0.5740	0.7576
No log	27.0	108	0.5885	0.6400	0.5885	0.7671
No log	28.0	112	0.6930	0.6080	0.6930	0.8325
No log	29.0	116	0.6283	0.6250	0.6283	0.7926
No log	30.0	120	0.5776	0.6224	0.5776	0.7600
No log	31.0	124	0.8047	0.5785	0.8047	0.8970
No log	32.0	128	0.6438	0.6211	0.6438	0.8024
No log	33.0	132	0.5827	0.6424	0.5827	0.7634
No log	34.0	136	0.6854	0.6169	0.6854	0.8279
No log	35.0	140	0.4960	0.6500	0.4960	0.7043
No log	36.0	144	0.6011	0.6120	0.6011	0.7753
No log	37.0	148	0.5562	0.6397	0.5562	0.7458
No log	38.0	152	0.5399	0.6326	0.5399	0.7348
No log	39.0	156	0.7702	0.5921	0.7702	0.8776
No log	40.0	160	0.7656	0.5840	0.7656	0.8750
No log	41.0	164	0.5599	0.6287	0.5599	0.7483
No log	42.0	168	0.6474	0.5962	0.6474	0.8046
No log	43.0	172	0.6162	0.6069	0.6162	0.7850
No log	44.0	176	0.5839	0.6319	0.5839	0.7641
No log	45.0	180	0.5293	0.6482	0.5293	0.7275
No log	46.0	184	0.8159	0.5828	0.8159	0.9033
No log	47.0	188	0.5011	0.6551	0.5011	0.7079
No log	48.0	192	0.8205	0.5852	0.8205	0.9058
No log	49.0	196	0.5616	0.6378	0.5616	0.7494
No log	50.0	200	0.5987	0.6099	0.5987	0.7737
No log	51.0	204	0.5673	0.6358	0.5673	0.7532
No log	52.0	208	0.6135	0.6383	0.6135	0.7833
No log	53.0	212	0.6894	0.5964	0.6894	0.8303
No log	54.0	216	0.5766	0.6212	0.5766	0.7593
No log	55.0	220	0.6159	0.6171	0.6159	0.7848
No log	56.0	224	0.5991	0.6060	0.5991	0.7740
No log	57.0	228	0.5809	0.6267	0.5809	0.7622
No log	58.0	232	0.5718	0.6308	0.5718	0.7562
No log	59.0	236	0.5960	0.6294	0.5960	0.7720
No log	60.0	240	0.5309	0.6442	0.5309	0.7286
No log	61.0	244	0.5871	0.6307	0.5871	0.7662
No log	62.0	248	0.6439	0.6184	0.6439	0.8024
No log	63.0	252	0.6192	0.6188	0.6192	0.7869
No log	64.0	256	0.6727	0.6064	0.6727	0.8202
No log	65.0	260	0.5856	0.6337	0.5856	0.7652
No log	66.0	264	0.5808	0.6324	0.5808	0.7621
No log	67.0	268	0.6453	0.6137	0.6453	0.8033

Framework versions

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