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	1	11.3923	0.0041	11.3922	3.3752
No log	2.0	2	10.5849	0.0036	10.5850	3.2535
No log	3.0	3	10.2653	0.0	10.2655	3.2040
No log	4.0	4	9.8254	0.0	9.8256	3.1346
No log	5.0	5	9.3087	0.0	9.3089	3.0510
No log	6.0	6	8.7275	0.0	8.7277	2.9543
No log	7.0	7	8.0909	0.0	8.0911	2.8445
No log	8.0	8	7.4986	0.0	7.4989	2.7384
No log	9.0	9	7.0539	0.0	7.0543	2.6560
No log	10.0	10	6.4326	0.0	6.4330	2.5363
No log	11.0	11	5.9820	0.0351	5.9823	2.4459
No log	12.0	12	5.5683	0.0352	5.5685	2.3598
No log	13.0	13	5.0791	0.0165	5.0795	2.2538
No log	14.0	14	4.6873	0.0155	4.6877	2.1651
No log	15.0	15	4.1939	0.0039	4.1943	2.0480
No log	16.0	16	3.6997	0.0	3.7000	1.9236
No log	17.0	17	3.3596	0.0	3.3600	1.8330
No log	18.0	18	3.0593	0.0	3.0597	1.7492
No log	19.0	19	2.7474	0.0	2.7478	1.6576
No log	20.0	20	2.4055	0.1325	2.4059	1.5511
No log	21.0	21	2.1703	0.1306	2.1707	1.4733
No log	22.0	22	1.9929	0.1041	1.9933	1.4118
No log	23.0	23	1.7485	0.0703	1.7489	1.3225
No log	24.0	24	1.5352	0.0551	1.5356	1.2392
No log	25.0	25	1.4333	0.0577	1.4336	1.1973
No log	26.0	26	1.3450	0.0513	1.3453	1.1599
No log	27.0	27	1.1471	0.0384	1.1474	1.0712
No log	28.0	28	1.0442	0.0384	1.0446	1.0221
No log	29.0	29	0.9758	0.0384	0.9761	0.9880
No log	30.0	30	0.9527	0.0261	0.9530	0.9762
No log	31.0	31	0.8261	0.2751	0.8264	0.9090
No log	32.0	32	0.8020	0.3160	0.8023	0.8957
No log	33.0	33	0.7392	0.4204	0.7395	0.8599
No log	34.0	34	0.6693	0.4557	0.6694	0.8182
No log	35.0	35	0.6490	0.4511	0.6491	0.8057
No log	36.0	36	0.6156	0.4326	0.6157	0.7846
No log	37.0	37	0.7141	0.3170	0.7143	0.8452
No log	38.0	38	0.7354	0.3006	0.7357	0.8577
No log	39.0	39	0.6333	0.3821	0.6335	0.7959
No log	40.0	40	0.5530	0.4716	0.5529	0.7436
No log	41.0	41	0.5518	0.4728	0.5517	0.7428
No log	42.0	42	0.5341	0.4943	0.5340	0.7308
No log	43.0	43	0.5764	0.4730	0.5765	0.7593
No log	44.0	44	0.5959	0.4606	0.5960	0.7720
No log	45.0	45	0.5723	0.4975	0.5723	0.7565
No log	46.0	46	0.5488	0.5010	0.5487	0.7407
No log	47.0	47	0.5591	0.4861	0.5588	0.7476
No log	48.0	48	0.5666	0.4803	0.5663	0.7526
No log	49.0	49	0.6384	0.4553	0.6384	0.7990
No log	50.0	50	0.6674	0.4507	0.6675	0.8170
No log	51.0	51	0.6208	0.4685	0.6206	0.7878
No log	52.0	52	0.5866	0.4842	0.5863	0.7657
No log	53.0	53	0.5831	0.5396	0.5828	0.7634
No log	54.0	54	0.5799	0.5547	0.5796	0.7613
No log	55.0	55	0.5986	0.5394	0.5985	0.7736
No log	56.0	56	0.5902	0.5603	0.5901	0.7682
No log	57.0	57	0.5720	0.5826	0.5718	0.7562
No log	58.0	58	0.5468	0.5759	0.5465	0.7393
No log	59.0	59	0.5479	0.5837	0.5476	0.7400
No log	60.0	60	0.5762	0.5889	0.5759	0.7589
No log	61.0	61	0.6753	0.5058	0.6752	0.8217
No log	62.0	62	0.7400	0.4085	0.7400	0.8603
No log	63.0	63	0.7344	0.4301	0.7344	0.8570
No log	64.0	64	0.6695	0.5331	0.6694	0.8181
No log	65.0	65	0.6621	0.5495	0.6620	0.8136
No log	66.0	66	0.6515	0.5626	0.6513	0.8070
No log	67.0	67	0.6700	0.5500	0.6699	0.8185
No log	68.0	68	0.6641	0.5613	0.6640	0.8149
No log	69.0	69	0.6770	0.5633	0.6768	0.8227
No log	70.0	70	0.7236	0.4990	0.7236	0.8506
No log	71.0	71	0.7955	0.3927	0.7957	0.8920
No log	72.0	72	0.8147	0.3754	0.8149	0.9027
No log	73.0	73	0.7931	0.4011	0.7933	0.8906
No log	74.0	74	0.7445	0.4821	0.7445	0.8628
No log	75.0	75	0.6913	0.5748	0.6911	0.8313
No log	76.0	76	0.6773	0.5754	0.6770	0.8228
No log	77.0	77	0.6856	0.5652	0.6853	0.8278
No log	78.0	78	0.7118	0.5368	0.7116	0.8436
No log	79.0	79	0.7528	0.4628	0.7528	0.8676
No log	80.0	80	0.7766	0.4130	0.7768	0.8813
No log	81.0	81	0.7806	0.4156	0.7807	0.8836
No log	82.0	82	0.7680	0.4375	0.7681	0.8764
No log	83.0	83	0.7540	0.4811	0.7540	0.8684
No log	84.0	84	0.7576	0.5066	0.7575	0.8704
No log	85.0	85	0.7809	0.4898	0.7809	0.8837
No log	86.0	86	0.8122	0.4469	0.8122	0.9012
No log	87.0	87	0.8478	0.4123	0.8479	0.9208
No log	88.0	88	0.8647	0.4097	0.8648	0.9299
No log	89.0	89	0.8670	0.4393	0.8670	0.9311
No log	90.0	90	0.8778	0.4358	0.8778	0.9369

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo100_k1_k1_fold2

BERT_V8_sp10_lw20_ex200_lo100_k1_k1_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo100_k1_k1_fold2