ASAP_FineTuningBERT_AugV6_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: 0.8595
• Qwk: 0.5380
• Mse: 0.8595
• Rmse: 0.9271

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	8.8811	0.0	8.8811	2.9801
No log	2.0	4	7.5509	0.0	7.5508	2.7479
No log	3.0	6	6.7460	0.0	6.7460	2.5973
No log	4.0	8	5.8761	0.0189	5.8761	2.4241
5.8082	5.0	10	5.0292	0.0115	5.0292	2.2426
5.8082	6.0	12	4.2521	0.0039	4.2521	2.0621
5.8082	7.0	14	3.4523	0.0	3.4523	1.8580
5.8082	8.0	16	2.7183	0.0	2.7183	1.6487
5.8082	9.0	18	2.1572	0.1179	2.1572	1.4687
2.8732	10.0	20	1.6519	0.0316	1.6519	1.2853
2.8732	11.0	22	1.3935	0.0316	1.3935	1.1805
2.8732	12.0	24	1.1961	0.0316	1.1961	1.0937
2.8732	13.0	26	1.2001	0.0548	1.2001	1.0955
2.8732	14.0	28	1.1480	0.0419	1.1480	1.0714
1.934	15.0	30	0.9577	0.0484	0.9577	0.9786
1.934	16.0	32	1.1208	0.1546	1.1208	1.0587
1.934	17.0	34	0.8860	0.3149	0.8860	0.9413
1.934	18.0	36	0.8460	0.2726	0.8460	0.9198
1.934	19.0	38	0.7177	0.5162	0.7177	0.8472
1.6002	20.0	40	0.8215	0.4362	0.8215	0.9063
1.6002	21.0	42	0.6332	0.5232	0.6332	0.7957
1.6002	22.0	44	0.5953	0.4460	0.5953	0.7716
1.6002	23.0	46	0.5623	0.4928	0.5623	0.7499
1.6002	24.0	48	0.5517	0.4862	0.5517	0.7427
1.1161	25.0	50	0.5247	0.4726	0.5247	0.7244
1.1161	26.0	52	0.5182	0.4952	0.5182	0.7199
1.1161	27.0	54	0.5120	0.5051	0.5120	0.7156
1.1161	28.0	56	0.5656	0.4304	0.5656	0.7521
1.1161	29.0	58	0.5800	0.4419	0.5800	0.7616
0.5588	30.0	60	0.5492	0.5333	0.5492	0.7411
0.5588	31.0	62	0.5972	0.5278	0.5972	0.7728
0.5588	32.0	64	0.6732	0.4767	0.6732	0.8205
0.5588	33.0	66	0.6075	0.5525	0.6075	0.7794
0.5588	34.0	68	0.6221	0.5457	0.6221	0.7887
0.4149	35.0	70	0.7169	0.4849	0.7169	0.8467
0.4149	36.0	72	0.6383	0.5455	0.6383	0.7989
0.4149	37.0	74	0.6091	0.5355	0.6091	0.7805
0.4149	38.0	76	0.8084	0.4734	0.8084	0.8991
0.4149	39.0	78	0.7538	0.5089	0.7538	0.8682
0.2595	40.0	80	0.6563	0.5224	0.6563	0.8101
0.2595	41.0	82	0.7760	0.5040	0.7760	0.8809
0.2595	42.0	84	0.8608	0.4670	0.8608	0.9278
0.2595	43.0	86	0.7309	0.5248	0.7309	0.8549
0.2595	44.0	88	0.8292	0.4972	0.8292	0.9106
0.2026	45.0	90	0.8060	0.5158	0.8060	0.8978
0.2026	46.0	92	0.6862	0.5223	0.6862	0.8284
0.2026	47.0	94	0.8269	0.5007	0.8269	0.9093
0.2026	48.0	96	0.9000	0.4917	0.9000	0.9487
0.2026	49.0	98	0.7245	0.5331	0.7245	0.8512
0.19	50.0	100	0.7499	0.5267	0.7499	0.8660
0.19	51.0	102	0.8634	0.5171	0.8634	0.9292
0.19	52.0	104	0.8279	0.5273	0.8279	0.9099
0.19	53.0	106	0.9419	0.4743	0.9419	0.9705
0.19	54.0	108	0.8147	0.5287	0.8147	0.9026
0.1459	55.0	110	0.8340	0.5323	0.8340	0.9132
0.1459	56.0	112	0.8910	0.5088	0.8910	0.9439
0.1459	57.0	114	0.6827	0.5812	0.6827	0.8263
0.1459	58.0	116	0.7232	0.5540	0.7232	0.8504
0.1459	59.0	118	0.9747	0.4552	0.9747	0.9873
0.1274	60.0	120	0.8289	0.5072	0.8289	0.9104
0.1274	61.0	122	0.7750	0.5510	0.7750	0.8803
0.1274	62.0	124	0.9056	0.5208	0.9056	0.9516
0.1274	63.0	126	0.8874	0.5281	0.8874	0.9420
0.1274	64.0	128	0.8058	0.5508	0.8058	0.8977
0.1211	65.0	130	0.9572	0.4733	0.9572	0.9784
0.1211	66.0	132	1.0216	0.4710	1.0216	1.0107
0.1211	67.0	134	0.8105	0.5473	0.8105	0.9003
0.1211	68.0	136	0.7906	0.5297	0.7906	0.8891
0.1211	69.0	138	0.9597	0.4630	0.9597	0.9796
0.1076	70.0	140	0.9511	0.4874	0.9511	0.9753
0.1076	71.0	142	0.8808	0.5019	0.8808	0.9385
0.1076	72.0	144	0.8929	0.5080	0.8929	0.9449
0.1076	73.0	146	0.8058	0.5373	0.8058	0.8977
0.1076	74.0	148	0.8397	0.4927	0.8397	0.9164
0.0921	75.0	150	0.9614	0.4835	0.9614	0.9805
0.0921	76.0	152	0.9351	0.5030	0.9351	0.9670
0.0921	77.0	154	0.7886	0.5672	0.7886	0.8880
0.0921	78.0	156	0.7448	0.5707	0.7448	0.8630
0.0921	79.0	158	0.8472	0.5045	0.8472	0.9204
0.0963	80.0	160	1.0165	0.4606	1.0165	1.0082
0.0963	81.0	162	0.9800	0.4620	0.9800	0.9899
0.0963	82.0	164	0.8314	0.5186	0.8314	0.9118
0.0963	83.0	166	0.8019	0.5433	0.8019	0.8955
0.0963	84.0	168	0.8823	0.5142	0.8823	0.9393
0.0853	85.0	170	0.9447	0.4925	0.9447	0.9719
0.0853	86.0	172	0.9500	0.4914	0.9500	0.9747
0.0853	87.0	174	0.9537	0.4910	0.9537	0.9766
0.0853	88.0	176	0.9749	0.4938	0.9749	0.9874
0.0853	89.0	178	0.9619	0.5029	0.9619	0.9807
0.0775	90.0	180	0.9105	0.5171	0.9105	0.9542
0.0775	91.0	182	0.8746	0.5349	0.8746	0.9352
0.0775	92.0	184	0.9135	0.5192	0.9135	0.9558
0.0775	93.0	186	0.9801	0.4974	0.9801	0.9900
0.0775	94.0	188	0.9754	0.4789	0.9754	0.9876
0.077	95.0	190	0.9309	0.4985	0.9309	0.9648
0.077	96.0	192	0.8736	0.5179	0.8736	0.9347
0.077	97.0	194	0.8469	0.5280	0.8469	0.9203
0.077	98.0	196	0.8428	0.5422	0.8428	0.9180
0.077	99.0	198	0.8519	0.5420	0.8519	0.9230
0.0743	100.0	200	0.8595	0.5380	0.8595	0.9271

Framework versions

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