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	10.9648	-0.0065	10.9648	3.3113
No log	2.0	2	10.0365	-0.0003	10.0365	3.1680
No log	3.0	3	8.6676	0.0	8.6676	2.9441
No log	4.0	4	7.8365	0.0	7.8365	2.7994
No log	5.0	5	6.9569	0.0	6.9569	2.6376
No log	6.0	6	6.2335	0.0138	6.2335	2.4967
No log	7.0	7	5.6318	0.0396	5.6318	2.3731
No log	8.0	8	5.0640	0.0177	5.0640	2.2503
No log	9.0	9	4.6737	0.0115	4.6737	2.1619
No log	10.0	10	4.2384	0.0115	4.2384	2.0587
No log	11.0	11	3.7287	0.0115	3.7287	1.9310
No log	12.0	12	3.3192	0.0115	3.3192	1.8219
No log	13.0	13	2.9648	0.0039	2.9648	1.7219
No log	14.0	14	2.6661	0.0039	2.6661	1.6328
No log	15.0	15	2.5076	0.0452	2.5076	1.5836
No log	16.0	16	2.2650	0.0591	2.2650	1.5050
No log	17.0	17	2.0267	0.0601	2.0267	1.4236
No log	18.0	18	1.8464	0.0548	1.8464	1.3588
No log	19.0	19	1.6731	0.0419	1.6731	1.2935
No log	20.0	20	1.5331	0.0316	1.5331	1.2382
No log	21.0	21	1.4092	0.0316	1.4092	1.1871
No log	22.0	22	1.2901	0.0316	1.2901	1.1358
No log	23.0	23	1.1682	0.0316	1.1682	1.0808
No log	24.0	24	1.0753	0.0316	1.0753	1.0370
No log	25.0	25	0.9896	0.0316	0.9896	0.9948
No log	26.0	26	0.9259	0.0316	0.9259	0.9622
No log	27.0	27	0.8399	0.1938	0.8399	0.9165
No log	28.0	28	0.7826	0.4124	0.7826	0.8846
No log	29.0	29	0.7320	0.4223	0.7320	0.8556
No log	30.0	30	0.6954	0.3629	0.6954	0.8339
No log	31.0	31	0.6432	0.4172	0.6432	0.8020
No log	32.0	32	0.6044	0.4411	0.6044	0.7774
No log	33.0	33	0.5802	0.4302	0.5802	0.7617
No log	34.0	34	0.5483	0.4491	0.5483	0.7405
No log	35.0	35	0.5515	0.3749	0.5515	0.7427
No log	36.0	36	0.5148	0.4522	0.5148	0.7175
No log	37.0	37	0.5367	0.5311	0.5367	0.7326
No log	38.0	38	0.5093	0.5272	0.5093	0.7136
No log	39.0	39	0.4938	0.4627	0.4938	0.7027
No log	40.0	40	0.4823	0.5143	0.4823	0.6945
No log	41.0	41	0.4973	0.5520	0.4973	0.7052
No log	42.0	42	0.5028	0.5571	0.5028	0.7091
No log	43.0	43	0.4698	0.5443	0.4698	0.6854
No log	44.0	44	0.4748	0.6127	0.4748	0.6891
No log	45.0	45	0.4764	0.6233	0.4764	0.6902
No log	46.0	46	0.4909	0.6085	0.4909	0.7006
No log	47.0	47	0.4890	0.6371	0.4890	0.6993
No log	48.0	48	0.4990	0.6115	0.4990	0.7064
No log	49.0	49	0.5142	0.6163	0.5142	0.7171
No log	50.0	50	0.5221	0.6107	0.5221	0.7226
No log	51.0	51	0.5516	0.6055	0.5516	0.7427
No log	52.0	52	0.5288	0.6003	0.5288	0.7272
No log	53.0	53	0.5595	0.5537	0.5595	0.7480
No log	54.0	54	0.5518	0.5636	0.5518	0.7429
No log	55.0	55	0.5484	0.5923	0.5484	0.7405
No log	56.0	56	0.5824	0.5742	0.5824	0.7631
No log	57.0	57	0.5559	0.5725	0.5559	0.7456
No log	58.0	58	0.5516	0.5863	0.5516	0.7427
No log	59.0	59	0.5473	0.6135	0.5473	0.7398
No log	60.0	60	0.5641	0.5852	0.5641	0.7511
No log	61.0	61	0.5504	0.6135	0.5504	0.7419
No log	62.0	62	0.5499	0.6073	0.5499	0.7415
No log	63.0	63	0.5611	0.6011	0.5611	0.7491
No log	64.0	64	0.6399	0.6016	0.6399	0.7999
No log	65.0	65	0.6566	0.5920	0.6566	0.8103
No log	66.0	66	0.5942	0.5951	0.5942	0.7708
No log	67.0	67	0.5413	0.6026	0.5413	0.7357
No log	68.0	68	0.5443	0.5897	0.5443	0.7378
No log	69.0	69	0.5362	0.5874	0.5362	0.7323
No log	70.0	70	0.5362	0.5953	0.5362	0.7322
No log	71.0	71	0.5947	0.5856	0.5947	0.7712
No log	72.0	72	0.6267	0.5858	0.6267	0.7917
No log	73.0	73	0.5982	0.5832	0.5982	0.7735
No log	74.0	74	0.5423	0.6010	0.5423	0.7364
No log	75.0	75	0.5255	0.6006	0.5255	0.7249
No log	76.0	76	0.5258	0.5962	0.5258	0.7252
No log	77.0	77	0.5295	0.5973	0.5295	0.7277

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo50_k1_k1_fold0

BERT_V8_sp10_lw20_ex100_lo50_k1_k1_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k1_k1_fold0