ASAP_FineTuningBERT_AugV7_k1_task1_organization_fold3

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: 0.5828
• Qwk: 0.6059
• Mse: 0.5825
• Rmse: 0.7632

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	11.8525	-0.0270	11.8514	3.4426
No log	2.0	4	9.1453	0.0	9.1446	3.0240
No log	3.0	6	7.2312	0.0	7.2307	2.6890
No log	4.0	8	5.9342	0.0411	5.9338	2.4359
7.392	5.0	10	4.5855	0.0114	4.5855	2.1414
7.392	6.0	12	3.5682	0.0	3.5683	1.8890
7.392	7.0	14	3.1861	0.0	3.1862	1.7850
7.392	8.0	16	2.2573	0.1203	2.2576	1.5025
7.392	9.0	18	1.9039	0.0524	1.9044	1.3800
2.9294	10.0	20	1.5598	0.0302	1.5604	1.2491
2.9294	11.0	22	1.3056	0.0302	1.3063	1.1429
2.9294	12.0	24	1.3064	0.0365	1.3070	1.1432
2.9294	13.0	26	1.0493	0.0302	1.0501	1.0247
2.9294	14.0	28	0.9377	0.0722	0.9385	0.9688
2.0871	15.0	30	0.9088	0.1987	0.9095	0.9537
2.0871	16.0	32	1.3048	0.1271	1.3054	1.1425
2.0871	17.0	34	1.0895	0.1736	1.0900	1.0440
2.0871	18.0	36	0.7533	0.3890	0.7538	0.8682
2.0871	19.0	38	0.6948	0.4308	0.6952	0.8338
1.5255	20.0	40	0.6495	0.4420	0.6499	0.8062
1.5255	21.0	42	0.7141	0.4259	0.7144	0.8452
1.5255	22.0	44	0.6258	0.4325	0.6261	0.7913
1.5255	23.0	46	0.6095	0.4323	0.6097	0.7808
1.5255	24.0	48	0.6422	0.4258	0.6426	0.8016
0.9142	25.0	50	0.5927	0.4618	0.5929	0.7700
0.9142	26.0	52	0.5603	0.4910	0.5603	0.7486
0.9142	27.0	54	0.5251	0.5415	0.5251	0.7246
0.9142	28.0	56	0.8716	0.4636	0.8718	0.9337
0.9142	29.0	58	0.8944	0.4655	0.8946	0.9458
0.5981	30.0	60	0.5109	0.6189	0.5107	0.7146
0.5981	31.0	62	0.5379	0.6101	0.5376	0.7332
0.5981	32.0	64	0.6153	0.5439	0.6152	0.7844
0.5981	33.0	66	0.7007	0.5123	0.7008	0.8371
0.5981	34.0	68	0.5701	0.5686	0.5699	0.7549
0.3103	35.0	70	0.5948	0.5644	0.5945	0.7710
0.3103	36.0	72	0.6321	0.5566	0.6320	0.7950
0.3103	37.0	74	0.6252	0.5688	0.6250	0.7906
0.3103	38.0	76	0.5912	0.5818	0.5910	0.7688
0.3103	39.0	78	0.6025	0.5985	0.6023	0.7761
0.233	40.0	80	0.7199	0.5321	0.7200	0.8485
0.233	41.0	82	0.6779	0.5479	0.6779	0.8234
0.233	42.0	84	0.6082	0.5936	0.6078	0.7796
0.233	43.0	86	0.5989	0.5981	0.5985	0.7736
0.233	44.0	88	0.5727	0.6225	0.5725	0.7567
0.1694	45.0	90	0.6822	0.5642	0.6822	0.8260
0.1694	46.0	92	0.5860	0.6191	0.5857	0.7653
0.1694	47.0	94	0.6343	0.5968	0.6338	0.7961
0.1694	48.0	96	0.6177	0.5943	0.6173	0.7857
0.1694	49.0	98	0.6358	0.5795	0.6355	0.7972
0.1235	50.0	100	0.6385	0.5749	0.6382	0.7988
0.1235	51.0	102	0.6317	0.5840	0.6313	0.7945
0.1235	52.0	104	0.6299	0.5907	0.6293	0.7933
0.1235	53.0	106	0.5855	0.6120	0.5851	0.7649
0.1235	54.0	108	0.6421	0.5603	0.6420	0.8013
0.1206	55.0	110	0.6112	0.5663	0.6111	0.7817
0.1206	56.0	112	0.5475	0.6173	0.5472	0.7397
0.1206	57.0	114	0.5721	0.5787	0.5720	0.7563
0.1206	58.0	116	0.5814	0.5851	0.5812	0.7623
0.1206	59.0	118	0.6170	0.5971	0.6165	0.7852
0.1149	60.0	120	0.6294	0.5959	0.6290	0.7931
0.1149	61.0	122	0.6045	0.5592	0.6042	0.7773
0.1149	62.0	124	0.5876	0.5823	0.5874	0.7664
0.1149	63.0	126	0.5668	0.5883	0.5665	0.7526
0.1149	64.0	128	0.5842	0.5808	0.5841	0.7643
0.082	65.0	130	0.5803	0.5866	0.5802	0.7617
0.082	66.0	132	0.5879	0.5853	0.5877	0.7666
0.082	67.0	134	0.6166	0.5665	0.6165	0.7852
0.082	68.0	136	0.6288	0.5663	0.6286	0.7928
0.082	69.0	138	0.6698	0.5737	0.6694	0.8182
0.0675	70.0	140	0.6724	0.5737	0.6719	0.8197
0.0675	71.0	142	0.6155	0.5973	0.6152	0.7843
0.0675	72.0	144	0.6295	0.5873	0.6294	0.7934
0.0675	73.0	146	0.6324	0.5788	0.6323	0.7952
0.0675	74.0	148	0.5995	0.5960	0.5993	0.7741
0.0778	75.0	150	0.6050	0.6093	0.6046	0.7776
0.0778	76.0	152	0.5932	0.5941	0.5929	0.7700
0.0778	77.0	154	0.6043	0.5754	0.6042	0.7773
0.0778	78.0	156	0.6151	0.5655	0.6151	0.7843
0.0778	79.0	158	0.5844	0.5926	0.5843	0.7644
0.0699	80.0	160	0.5827	0.6062	0.5824	0.7631
0.0699	81.0	162	0.5891	0.5895	0.5888	0.7673
0.0699	82.0	164	0.5807	0.5890	0.5805	0.7619
0.0699	83.0	166	0.5890	0.5854	0.5888	0.7673
0.0699	84.0	168	0.5915	0.5880	0.5912	0.7689
0.0642	85.0	170	0.5930	0.6033	0.5926	0.7698
0.0642	86.0	172	0.5926	0.6009	0.5922	0.7696
0.0642	87.0	174	0.5925	0.6021	0.5922	0.7695
0.0642	88.0	176	0.5878	0.5897	0.5875	0.7665
0.0642	89.0	178	0.5816	0.5941	0.5814	0.7625
0.0647	90.0	180	0.5830	0.5881	0.5828	0.7634
0.0647	91.0	182	0.5847	0.5873	0.5844	0.7645
0.0647	92.0	184	0.5871	0.5880	0.5868	0.7660
0.0647	93.0	186	0.5893	0.5917	0.5890	0.7675
0.0647	94.0	188	0.5952	0.5973	0.5948	0.7712
0.0608	95.0	190	0.5981	0.6038	0.5978	0.7732
0.0608	96.0	192	0.5942	0.6072	0.5938	0.7706
0.0608	97.0	194	0.5884	0.6076	0.5881	0.7669
0.0608	98.0	196	0.5850	0.6076	0.5847	0.7647
0.0608	99.0	198	0.5834	0.6044	0.5831	0.7636
0.0498	100.0	200	0.5828	0.6059	0.5825	0.7632

Framework versions

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