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	13.4435	0.0	13.4413	3.6662
No log	2.0	4	11.1099	0.0124	11.1079	3.3329
No log	3.0	6	9.4524	0.0	9.4506	3.0742
No log	4.0	8	7.2670	0.0	7.2657	2.6955
No log	5.0	10	5.8754	0.0125	5.8742	2.4237
No log	6.0	12	5.0481	0.0164	5.0468	2.2465
No log	7.0	14	4.0560	0.0062	4.0548	2.0136
No log	8.0	16	3.0537	0.0038	3.0528	1.7472
No log	9.0	18	2.4950	0.0674	2.4944	1.5794
No log	10.0	20	1.9970	0.1425	1.9964	1.4130
No log	11.0	22	1.7097	0.0355	1.7089	1.3073
No log	12.0	24	1.2866	0.0401	1.2862	1.1341
No log	13.0	26	1.5289	0.0488	1.5282	1.2362
No log	14.0	28	1.3353	0.0401	1.3347	1.1553
No log	15.0	30	1.1315	0.0202	1.1309	1.0635
No log	16.0	32	0.8726	0.2854	0.8722	0.9339
No log	17.0	34	0.7447	0.2695	0.7446	0.8629
No log	18.0	36	0.7980	0.1944	0.7979	0.8933
No log	19.0	38	0.7600	0.2322	0.7600	0.8718
No log	20.0	40	0.7647	0.3685	0.7645	0.8744
No log	21.0	42	0.8768	0.2506	0.8767	0.9363
No log	22.0	44	1.0126	0.1168	1.0125	1.0062
No log	23.0	46	1.1182	0.1303	1.1182	1.0574
No log	24.0	48	0.9367	0.3194	0.9368	0.9679
No log	25.0	50	0.7528	0.4410	0.7530	0.8677
No log	26.0	52	0.7203	0.4412	0.7205	0.8488
No log	27.0	54	0.6565	0.4525	0.6568	0.8105
No log	28.0	56	0.6503	0.4734	0.6507	0.8066
No log	29.0	58	0.7472	0.4418	0.7477	0.8647
No log	30.0	60	0.8776	0.3434	0.8783	0.9372
No log	31.0	62	0.8014	0.3879	0.8021	0.8956
No log	32.0	64	0.6409	0.4487	0.6414	0.8009
No log	33.0	66	0.6385	0.4476	0.6390	0.7994
No log	34.0	68	0.7523	0.4055	0.7532	0.8679
No log	35.0	70	0.9221	0.3630	0.9233	0.9609
No log	36.0	72	0.9427	0.3658	0.9441	0.9717
No log	37.0	74	0.7990	0.4342	0.8002	0.8945
No log	38.0	76	0.6981	0.4636	0.6989	0.8360
No log	39.0	78	0.6560	0.4786	0.6568	0.8104
No log	40.0	80	0.6962	0.4429	0.6971	0.8349
No log	41.0	82	0.7318	0.4287	0.7327	0.8560
No log	42.0	84	0.7321	0.3954	0.7330	0.8561
No log	43.0	86	0.6801	0.4193	0.6809	0.8252
No log	44.0	88	0.6866	0.4656	0.6874	0.8291
No log	45.0	90	0.6388	0.5451	0.6396	0.7997
No log	46.0	92	0.6235	0.5375	0.6245	0.7902
No log	47.0	94	0.6985	0.5094	0.6997	0.8365
No log	48.0	96	0.6793	0.5432	0.6805	0.8249
No log	49.0	98	0.6825	0.5411	0.6836	0.8268
No log	50.0	100	0.6951	0.5634	0.6960	0.8343
No log	51.0	102	0.6669	0.5466	0.6678	0.8172
No log	52.0	104	0.6884	0.5306	0.6894	0.8303
No log	53.0	106	0.6938	0.5298	0.6947	0.8335
No log	54.0	108	0.6769	0.5356	0.6777	0.8232
No log	55.0	110	0.6925	0.5440	0.6933	0.8326
No log	56.0	112	0.7394	0.4979	0.7400	0.8602
No log	57.0	114	0.7525	0.4858	0.7531	0.8678
No log	58.0	116	0.6933	0.5329	0.6940	0.8331
No log	59.0	118	0.7025	0.5153	0.7034	0.8387
No log	60.0	120	0.7473	0.4814	0.7483	0.8650
No log	61.0	122	0.7308	0.4976	0.7318	0.8555
No log	62.0	124	0.6718	0.5396	0.6727	0.8202
No log	63.0	126	0.6545	0.5710	0.6553	0.8095
No log	64.0	128	0.6936	0.5523	0.6944	0.8333
No log	65.0	130	0.7139	0.5424	0.7147	0.8454
No log	66.0	132	0.7509	0.5070	0.7516	0.8670
No log	67.0	134	0.7615	0.5034	0.7623	0.8731
No log	68.0	136	0.7364	0.4924	0.7372	0.8586
No log	69.0	138	0.7270	0.4928	0.7279	0.8532
No log	70.0	140	0.7224	0.5131	0.7233	0.8505
No log	71.0	142	0.7304	0.5145	0.7314	0.8552
No log	72.0	144	0.7067	0.5338	0.7077	0.8412
No log	73.0	146	0.7014	0.5581	0.7023	0.8380
No log	74.0	148	0.7165	0.5578	0.7174	0.8470
No log	75.0	150	0.7373	0.5304	0.7383	0.8592
No log	76.0	152	0.7633	0.5112	0.7643	0.8742
No log	77.0	154	0.7588	0.5222	0.7598	0.8717
No log	78.0	156	0.7650	0.5203	0.7659	0.8751
No log	79.0	158	0.7733	0.5229	0.7741	0.8798
No log	80.0	160	0.7526	0.5274	0.7535	0.8680
No log	81.0	162	0.7414	0.5370	0.7423	0.8616
No log	82.0	164	0.7241	0.5421	0.7251	0.8515
No log	83.0	166	0.7277	0.5309	0.7287	0.8536
No log	84.0	168	0.7254	0.5305	0.7264	0.8523
No log	85.0	170	0.7143	0.5418	0.7152	0.8457
No log	86.0	172	0.7123	0.5357	0.7132	0.8445
No log	87.0	174	0.7070	0.5338	0.7078	0.8413
No log	88.0	176	0.7146	0.5195	0.7154	0.8458
No log	89.0	178	0.7151	0.5163	0.7159	0.8461
No log	90.0	180	0.7112	0.5256	0.7121	0.8438
No log	91.0	182	0.7112	0.5297	0.7121	0.8439
No log	92.0	184	0.7101	0.5297	0.7109	0.8432
No log	93.0	186	0.7098	0.5282	0.7106	0.8430

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold3

BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold3