Version_weird_ASAP_FineTuningBERT_AugV12_k4_task1_organization_k4_k4_fold2

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8096
• Qwk: 0.5449
• Mse: 0.8089
• Rmse: 0.8994

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• 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	9.8119	0.0035	9.8121	3.1324
No log	2.0	4	7.7136	0.0	7.7137	2.7774
No log	3.0	6	7.4225	0.0	7.4227	2.7245
No log	4.0	8	6.0393	0.0085	6.0396	2.4576
No log	5.0	10	4.3830	0.0088	4.3833	2.0936
No log	6.0	12	3.4275	0.0025	3.4279	1.8515
No log	7.0	14	2.9811	0.0	2.9815	1.7267
No log	8.0	16	2.2043	0.1314	2.2047	1.4848
No log	9.0	18	1.7804	0.0992	1.7808	1.3345
No log	10.0	20	1.4447	0.0241	1.4451	1.2021
No log	11.0	22	1.1592	0.0068	1.1596	1.0769
No log	12.0	24	0.9305	0.0068	0.9309	0.9648
No log	13.0	26	0.8838	0.1865	0.8842	0.9403
No log	14.0	28	0.7555	0.2642	0.7559	0.8694
No log	15.0	30	0.7292	0.1856	0.7295	0.8541
No log	16.0	32	0.6874	0.2355	0.6875	0.8291
No log	17.0	34	0.7789	0.1404	0.7788	0.8825
No log	18.0	36	0.6813	0.2142	0.6810	0.8252
No log	19.0	38	0.6311	0.4258	0.6305	0.7940
No log	20.0	40	0.5868	0.4241	0.5864	0.7658
No log	21.0	42	0.6200	0.4964	0.6194	0.7870
No log	22.0	44	0.7243	0.5119	0.7233	0.8505
No log	23.0	46	0.6938	0.5108	0.6928	0.8324
No log	24.0	48	0.9110	0.5013	0.9095	0.9537
No log	25.0	50	0.8775	0.5228	0.8760	0.9360
No log	26.0	52	0.7849	0.5310	0.7842	0.8855
No log	27.0	54	0.9147	0.5291	0.9132	0.9556
No log	28.0	56	1.1528	0.4674	1.1508	1.0727
No log	29.0	58	0.9715	0.5304	0.9705	0.9852
No log	30.0	60	1.4414	0.3410	1.4415	1.2006
No log	31.0	62	1.0300	0.4138	1.0301	1.0149
No log	32.0	64	1.0087	0.4442	1.0074	1.0037
No log	33.0	66	1.3121	0.4235	1.3106	1.1448
No log	34.0	68	0.7740	0.4976	0.7736	0.8795
No log	35.0	70	0.7672	0.5308	0.7670	0.8758
No log	36.0	72	0.7501	0.5495	0.7494	0.8657
No log	37.0	74	0.8123	0.5208	0.8125	0.9014
No log	38.0	76	0.7560	0.5563	0.7560	0.8695
No log	39.0	78	0.8329	0.5534	0.8321	0.9122
No log	40.0	80	0.6849	0.5938	0.6845	0.8274
No log	41.0	82	0.6846	0.5887	0.6841	0.8271
No log	42.0	84	0.8798	0.5287	0.8789	0.9375
No log	43.0	86	0.6962	0.5836	0.6957	0.8341
No log	44.0	88	0.9164	0.5205	0.9155	0.9568
No log	45.0	90	0.8172	0.5433	0.8164	0.9036
No log	46.0	92	0.7212	0.5777	0.7211	0.8492
No log	47.0	94	0.7516	0.5786	0.7513	0.8668
No log	48.0	96	0.8582	0.5455	0.8575	0.9260
No log	49.0	98	0.8162	0.5689	0.8155	0.9031
No log	50.0	100	0.7090	0.5907	0.7087	0.8418
No log	51.0	102	0.6770	0.5797	0.6766	0.8226
No log	52.0	104	0.7588	0.5649	0.7581	0.8707
No log	53.0	106	0.7399	0.5748	0.7393	0.8599
No log	54.0	108	0.8031	0.5653	0.8025	0.8958
No log	55.0	110	0.7655	0.5637	0.7654	0.8749
No log	56.0	112	0.7318	0.5651	0.7316	0.8553
No log	57.0	114	0.8559	0.5230	0.8552	0.9248
No log	58.0	116	0.8085	0.5435	0.8078	0.8988
No log	59.0	118	0.7159	0.5758	0.7156	0.8459
No log	60.0	120	0.8096	0.5449	0.8089	0.8994

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0