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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	11.3441	0.0161	11.3412	3.3677
No log	2.0	4	9.7102	0.0050	9.7076	3.1157
No log	3.0	6	6.8275	0.0	6.8251	2.6125
No log	4.0	8	5.5903	0.0340	5.5881	2.3639
No log	5.0	10	4.2110	0.0040	4.2090	2.0516
No log	6.0	12	3.5167	0.0	3.5148	1.8748
No log	7.0	14	2.5669	0.0	2.5651	1.6016
No log	8.0	16	2.0324	0.0501	2.0307	1.4250
No log	9.0	18	1.6402	0.0315	1.6386	1.2801
No log	10.0	20	1.4098	0.0106	1.4083	1.1867
No log	11.0	22	1.1603	0.0	1.1589	1.0765
No log	12.0	24	1.0392	0.0	1.0379	1.0188
No log	13.0	26	1.3072	0.0211	1.3058	1.1427
No log	14.0	28	1.3383	0.0315	1.3368	1.1562
No log	15.0	30	1.0563	0.0315	1.0550	1.0271
No log	16.0	32	1.2400	0.0583	1.2387	1.1129
No log	17.0	34	1.2609	0.0901	1.2596	1.1223
No log	18.0	36	0.9545	0.2045	0.9535	0.9765
No log	19.0	38	0.8711	0.2222	0.8702	0.9328
No log	20.0	40	1.2856	0.1985	1.2847	1.1335
No log	21.0	42	1.2153	0.2522	1.2147	1.1022
No log	22.0	44	0.8330	0.3830	0.8326	0.9125
No log	23.0	46	0.8249	0.3953	0.8247	0.9081
No log	24.0	48	0.7854	0.4128	0.7852	0.8861
No log	25.0	50	0.7289	0.4175	0.7286	0.8536
No log	26.0	52	0.8654	0.3408	0.8651	0.9301
No log	27.0	54	0.9309	0.3230	0.9306	0.9647
No log	28.0	56	1.0994	0.3311	1.0992	1.0484
No log	29.0	58	1.2102	0.3266	1.2101	1.1000
No log	30.0	60	0.8799	0.4500	0.8797	0.9379
No log	31.0	62	1.0011	0.4109	1.0009	1.0004
No log	32.0	64	1.6441	0.2348	1.6437	1.2821
No log	33.0	66	0.8590	0.4123	0.8587	0.9266
No log	34.0	68	0.8436	0.4994	0.8434	0.9184
No log	35.0	70	0.8282	0.4212	0.8281	0.9100
No log	36.0	72	1.4347	0.2619	1.4344	1.1977
No log	37.0	74	1.0105	0.3792	1.0104	1.0052
No log	38.0	76	0.7464	0.5444	0.7464	0.8639
No log	39.0	78	0.6750	0.5389	0.6749	0.8215
No log	40.0	80	1.4614	0.3174	1.4612	1.2088
No log	41.0	82	2.0257	0.2129	2.0255	1.4232
No log	42.0	84	1.1607	0.3589	1.1607	1.0774
No log	43.0	86	0.8777	0.5140	0.8779	0.9370
No log	44.0	88	0.8544	0.4734	0.8546	0.9244
No log	45.0	90	1.1360	0.3522	1.1359	1.0658
No log	46.0	92	1.1019	0.3650	1.1018	1.0497
No log	47.0	94	0.7570	0.4826	0.7570	0.8701
No log	48.0	96	0.7251	0.4723	0.7250	0.8515
No log	49.0	98	0.7089	0.4741	0.7088	0.8419
No log	50.0	100	0.8099	0.4358	0.8098	0.8999
No log	51.0	102	1.1817	0.3259	1.1816	1.0870
No log	52.0	104	1.0498	0.3698	1.0497	1.0245
No log	53.0	106	0.8286	0.4406	0.8285	0.9102

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Trial3BERT_AugV8_k1_task1_organization_sp020_lw070_fold1

Trial3BERT_AugV8_k1_task1_organization_sp020_lw070_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Trial3BERT_AugV8_k1_task1_organization_sp020_lw070_fold1