ASAP_FineTuningBERT_AugV7_k2_task1_organization_fold0

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: 0.5630
• Qwk: 0.5803
• Mse: 0.5630
• Rmse: 0.7504

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	9.1752	0.0	9.1752	3.0291
No log	2.0	4	7.7179	0.0	7.7179	2.7781
No log	3.0	6	6.8858	0.0	6.8858	2.6241
No log	4.0	8	6.1315	-0.0034	6.1315	2.4762
5.9923	5.0	10	5.2786	0.0115	5.2786	2.2975
5.9923	6.0	12	4.4534	0.0039	4.4534	2.1103
5.9923	7.0	14	3.7854	0.0039	3.7854	1.9456
5.9923	8.0	16	2.9801	0.0	2.9801	1.7263
5.9923	9.0	18	2.3411	0.1127	2.3411	1.5301
3.1484	10.0	20	1.8749	0.0601	1.8749	1.3693
3.1484	11.0	22	1.4206	0.0316	1.4206	1.1919
3.1484	12.0	24	1.2357	0.0316	1.2357	1.1116
3.1484	13.0	26	1.4653	0.0700	1.4653	1.2105
3.1484	14.0	28	0.9406	0.0484	0.9406	0.9699
2.062	15.0	30	0.8993	0.0530	0.8993	0.9483
2.062	16.0	32	1.4590	0.1524	1.4590	1.2079
2.062	17.0	34	1.0014	0.2377	1.0014	1.0007
2.062	18.0	36	0.7699	0.4697	0.7699	0.8775
2.062	19.0	38	0.9935	0.3626	0.9935	0.9967
1.5859	20.0	40	0.7458	0.4449	0.7458	0.8636
1.5859	21.0	42	0.6769	0.4011	0.6769	0.8227
1.5859	22.0	44	0.7657	0.4345	0.7657	0.8750
1.5859	23.0	46	0.6978	0.4723	0.6978	0.8353
1.5859	24.0	48	0.6172	0.4147	0.6172	0.7856
0.9959	25.0	50	0.6037	0.4515	0.6037	0.7770
0.9959	26.0	52	0.6360	0.4537	0.6360	0.7975
0.9959	27.0	54	0.6490	0.4523	0.6490	0.8056
0.9959	28.0	56	0.6340	0.4692	0.6340	0.7963
0.9959	29.0	58	0.6109	0.5223	0.6109	0.7816
0.4734	30.0	60	0.5788	0.5219	0.5788	0.7608
0.4734	31.0	62	0.7643	0.4324	0.7643	0.8742
0.4734	32.0	64	0.5653	0.5389	0.5653	0.7519
0.4734	33.0	66	0.5844	0.5341	0.5844	0.7644
0.4734	34.0	68	0.6616	0.5387	0.6616	0.8134
0.2995	35.0	70	0.6560	0.5457	0.6560	0.8100
0.2995	36.0	72	0.6433	0.5320	0.6433	0.8021
0.2995	37.0	74	0.6235	0.5664	0.6235	0.7896
0.2995	38.0	76	0.5793	0.5605	0.5793	0.7611
0.2995	39.0	78	0.5552	0.5829	0.5552	0.7451
0.1962	40.0	80	0.5893	0.5811	0.5893	0.7677
0.1962	41.0	82	0.5787	0.5850	0.5787	0.7607
0.1962	42.0	84	0.5814	0.5789	0.5814	0.7625
0.1962	43.0	86	0.6176	0.5599	0.6176	0.7859
0.1962	44.0	88	0.5806	0.5707	0.5806	0.7620
0.1293	45.0	90	0.5913	0.5737	0.5913	0.7690
0.1293	46.0	92	0.5811	0.5711	0.5811	0.7623
0.1293	47.0	94	0.5857	0.5676	0.5857	0.7653
0.1293	48.0	96	0.5799	0.5570	0.5799	0.7615
0.1293	49.0	98	0.5957	0.5817	0.5957	0.7718
0.0899	50.0	100	0.6516	0.5508	0.6516	0.8072
0.0899	51.0	102	0.6040	0.5803	0.6040	0.7772
0.0899	52.0	104	0.5839	0.5830	0.5839	0.7641
0.0899	53.0	106	0.5882	0.5931	0.5882	0.7669
0.0899	54.0	108	0.5953	0.5780	0.5953	0.7715
0.0853	55.0	110	0.5937	0.5876	0.5937	0.7705
0.0853	56.0	112	0.5938	0.5770	0.5938	0.7706
0.0853	57.0	114	0.5731	0.5932	0.5731	0.7570
0.0853	58.0	116	0.5726	0.5946	0.5726	0.7567
0.0853	59.0	118	0.5926	0.5703	0.5926	0.7698
0.0816	60.0	120	0.5899	0.5649	0.5899	0.7680
0.0816	61.0	122	0.5942	0.5779	0.5942	0.7708
0.0816	62.0	124	0.5630	0.5943	0.5630	0.7504
0.0816	63.0	126	0.5727	0.5863	0.5727	0.7568
0.0816	64.0	128	0.5878	0.5854	0.5878	0.7667
0.072	65.0	130	0.6183	0.5980	0.6183	0.7863
0.072	66.0	132	0.6039	0.5825	0.6039	0.7771
0.072	67.0	134	0.5995	0.5758	0.5995	0.7743
0.072	68.0	136	0.5879	0.5888	0.5879	0.7667
0.072	69.0	138	0.6164	0.5916	0.6164	0.7851
0.0661	70.0	140	0.5828	0.5969	0.5828	0.7634
0.0661	71.0	142	0.5668	0.5760	0.5668	0.7529
0.0661	72.0	144	0.5635	0.5885	0.5635	0.7507
0.0661	73.0	146	0.5611	0.5800	0.5611	0.7491
0.0661	74.0	148	0.5949	0.5873	0.5949	0.7713
0.0565	75.0	150	0.5878	0.5838	0.5878	0.7667
0.0565	76.0	152	0.5828	0.5813	0.5828	0.7634
0.0565	77.0	154	0.5665	0.5827	0.5665	0.7527
0.0565	78.0	156	0.5617	0.5932	0.5617	0.7494
0.0565	79.0	158	0.5565	0.5794	0.5565	0.7460
0.0632	80.0	160	0.5684	0.5876	0.5684	0.7539
0.0632	81.0	162	0.5733	0.5919	0.5733	0.7572
0.0632	82.0	164	0.5764	0.5887	0.5764	0.7592
0.0632	83.0	166	0.5692	0.5912	0.5692	0.7544
0.0632	84.0	168	0.5628	0.5868	0.5628	0.7502
0.0509	85.0	170	0.5602	0.5850	0.5602	0.7485
0.0509	86.0	172	0.5550	0.5828	0.5550	0.7450
0.0509	87.0	174	0.5508	0.5878	0.5508	0.7422
0.0509	88.0	176	0.5533	0.5919	0.5533	0.7439
0.0509	89.0	178	0.5558	0.5865	0.5558	0.7455
0.0511	90.0	180	0.5617	0.5887	0.5617	0.7495
0.0511	91.0	182	0.5668	0.5908	0.5668	0.7528
0.0511	92.0	184	0.5680	0.5864	0.5680	0.7537
0.0511	93.0	186	0.5669	0.5862	0.5669	0.7529
0.0511	94.0	188	0.5652	0.5847	0.5652	0.7518
0.0457	95.0	190	0.5626	0.5720	0.5626	0.7500
0.0457	96.0	192	0.5623	0.5803	0.5623	0.7499
0.0457	97.0	194	0.5642	0.5860	0.5642	0.7512
0.0457	98.0	196	0.5645	0.5836	0.5645	0.7513
0.0457	99.0	198	0.5636	0.5821	0.5636	0.7507
0.0489	100.0	200	0.5630	0.5803	0.5630	0.7504

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1