learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.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	9.0409	0.0	9.0383	3.0064
No log	2.0	8	5.2843	0.0427	5.2822	2.2983
No log	3.0	12	3.2013	0.0	3.1995	1.7887
No log	4.0	16	1.6364	0.0379	1.6348	1.2786
No log	5.0	20	1.0361	0.0	1.0348	1.0172
No log	6.0	24	0.9238	0.1360	0.9227	0.9606
No log	7.0	28	1.0000	0.0518	0.9988	0.9994
No log	8.0	32	1.0497	0.0272	1.0486	1.0240
No log	9.0	36	0.7997	0.2097	0.7988	0.8937
No log	10.0	40	0.7763	0.2455	0.7754	0.8806
No log	11.0	44	0.7272	0.3721	0.7265	0.8524
No log	12.0	48	0.6733	0.3897	0.6725	0.8201
No log	13.0	52	0.6055	0.4736	0.6049	0.7778
No log	14.0	56	1.1583	0.2389	1.1573	1.0758
No log	15.0	60	0.7312	0.4149	0.7306	0.8547
No log	16.0	64	1.1504	0.2931	1.1495	1.0722
No log	17.0	68	0.7963	0.3668	0.7954	0.8919
No log	18.0	72	1.0468	0.2583	1.0457	1.0226
No log	19.0	76	0.8196	0.3452	0.8188	0.9049
No log	20.0	80	1.0236	0.2861	1.0225	1.0112
No log	21.0	84	0.7506	0.4122	0.7497	0.8659
No log	22.0	88	0.7704	0.3877	0.7696	0.8773
No log	23.0	92	1.1167	0.2332	1.1155	1.0562
No log	24.0	96	0.7725	0.3585	0.7716	0.8784
No log	25.0	100	0.9348	0.2730	0.9335	0.9662
No log	26.0	104	0.7742	0.3754	0.7733	0.8794
No log	27.0	108	1.0246	0.2594	1.0233	1.0116
No log	28.0	112	0.6947	0.4586	0.6940	0.8331
No log	29.0	116	0.9885	0.2553	0.9874	0.9937
No log	30.0	120	0.8002	0.3213	0.7994	0.8941
No log	31.0	124	0.9075	0.2471	0.9064	0.9520
No log	32.0	128	0.8110	0.2942	0.8102	0.9001
No log	33.0	132	0.9615	0.2422	0.9605	0.9801
No log	34.0	136	0.8525	0.3187	0.8517	0.9228
No log	35.0	140	0.8445	0.3351	0.8436	0.9185
No log	36.0	144	0.8999	0.2804	0.8988	0.9480
No log	37.0	148	0.8078	0.3388	0.8069	0.8983
No log	38.0	152	0.9023	0.2638	0.9012	0.9493
No log	39.0	156	0.9435	0.2126	0.9423	0.9707
No log	40.0	160	0.8441	0.3175	0.8432	0.9183
No log	41.0	164	0.9542	0.2382	0.9531	0.9763
No log	42.0	168	0.8508	0.2485	0.8499	0.9219
No log	43.0	172	1.0069	0.2179	1.0059	1.0029

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo50_k7_k7_fold1

BERT_V8_sp10_lw40_ex50_lo50_k7_k7_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo50_k7_k7_fold1