ASAP_FineTuningBERT_AugV5_k4_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: 1.5071
• Qwk: 0.2737
• Mse: 1.5071
• Rmse: 1.2277

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	0.6667	2	9.0690	0.0	9.0690	3.0115
No log	1.3333	4	7.6655	0.0	7.6655	2.7687
No log	2.0	6	6.9385	0.0	6.9385	2.6341
No log	2.6667	8	6.0508	0.0216	6.0508	2.4598
4.8555	3.3333	10	5.2284	0.0115	5.2284	2.2866
4.8555	4.0	12	4.4262	0.0039	4.4262	2.1039
4.8555	4.6667	14	3.6383	0.0	3.6383	1.9074
4.8555	5.3333	16	2.9057	0.0	2.9057	1.7046
4.8555	6.0	18	2.2491	0.0850	2.2491	1.4997
2.4087	6.6667	20	1.7801	0.0382	1.7801	1.3342
2.4087	7.3333	22	1.6431	0.0316	1.6431	1.2818
2.4087	8.0	24	1.9085	0.0590	1.9085	1.3815
2.4087	8.6667	26	1.5951	0.0316	1.5951	1.2630
2.4087	9.3333	28	1.4231	0.0316	1.4231	1.1929
1.7827	10.0	30	1.9661	0.1238	1.9661	1.4022
1.7827	10.6667	32	2.7146	0.0632	2.7146	1.6476
1.7827	11.3333	34	2.1531	0.1716	2.1531	1.4674
1.7827	12.0	36	1.3052	0.0447	1.3052	1.1425
1.7827	12.6667	38	1.5152	0.0897	1.5152	1.2309
1.6996	13.3333	40	2.6726	0.0813	2.6726	1.6348
1.6996	14.0	42	3.0227	0.0204	3.0227	1.7386
1.6996	14.6667	44	2.4825	0.1137	2.4825	1.5756
1.6996	15.3333	46	1.3449	0.1105	1.3449	1.1597
1.6996	16.0	48	1.1689	0.1455	1.1689	1.0812
1.6541	16.6667	50	2.0098	0.1216	2.0098	1.4177
1.6541	17.3333	52	3.0336	0.0531	3.0336	1.7417
1.6541	18.0	54	2.7094	0.0770	2.7094	1.6460
1.6541	18.6667	56	1.7147	0.1591	1.7147	1.3095
1.6541	19.3333	58	1.0701	0.2860	1.0701	1.0344
1.2336	20.0	60	1.4950	0.2379	1.4950	1.2227
1.2336	20.6667	62	2.5290	0.0772	2.5290	1.5903
1.2336	21.3333	64	2.2908	0.1012	2.2908	1.5135
1.2336	22.0	66	1.2765	0.2635	1.2765	1.1298
1.2336	22.6667	68	1.3651	0.2296	1.3651	1.1684
0.7782	23.3333	70	2.4047	0.0862	2.4047	1.5507
0.7782	24.0	72	2.3177	0.0877	2.3177	1.5224
0.7782	24.6667	74	1.3631	0.2396	1.3631	1.1675
0.7782	25.3333	76	1.5247	0.2292	1.5247	1.2348
0.7782	26.0	78	2.1085	0.1342	2.1085	1.4521
0.4341	26.6667	80	1.5375	0.2178	1.5375	1.2400
0.4341	27.3333	82	2.0030	0.1508	2.0030	1.4153
0.4341	28.0	84	2.4371	0.0926	2.4371	1.5611
0.4341	28.6667	86	1.7195	0.1510	1.7195	1.3113
0.4341	29.3333	88	2.0927	0.1406	2.0927	1.4466
0.2682	30.0	90	2.3033	0.1303	2.3033	1.5177
0.2682	30.6667	92	1.6060	0.2287	1.6060	1.2673
0.2682	31.3333	94	1.7280	0.2321	1.7280	1.3145
0.2682	32.0	96	2.6927	0.1152	2.6927	1.6410
0.2682	32.6667	98	2.2621	0.1746	2.2621	1.5040
0.2247	33.3333	100	1.4874	0.2915	1.4874	1.2196
0.2247	34.0	102	1.7766	0.2448	1.7766	1.3329
0.2247	34.6667	104	2.0857	0.1835	2.0857	1.4442
0.2247	35.3333	106	1.5131	0.2845	1.5131	1.2301
0.2247	36.0	108	1.5584	0.2823	1.5584	1.2484
0.179	36.6667	110	2.0858	0.1764	2.0858	1.4442
0.179	37.3333	112	1.6165	0.2539	1.6165	1.2714
0.179	38.0	114	1.7275	0.2420	1.7275	1.3144
0.179	38.6667	116	1.8210	0.2189	1.8210	1.3495
0.179	39.3333	118	2.1455	0.1717	2.1455	1.4648
0.1493	40.0	120	1.5247	0.3030	1.5247	1.2348
0.1493	40.6667	122	1.4957	0.3053	1.4957	1.2230
0.1493	41.3333	124	1.9484	0.2143	1.9484	1.3959
0.1493	42.0	126	1.7468	0.2608	1.7468	1.3217
0.1493	42.6667	128	1.7644	0.2763	1.7644	1.3283
0.128	43.3333	130	2.1228	0.2025	2.1228	1.4570
0.128	44.0	132	2.0809	0.2131	2.0809	1.4425
0.128	44.6667	134	2.2372	0.1715	2.2372	1.4957
0.128	45.3333	136	1.8516	0.2445	1.8516	1.3607
0.128	46.0	138	1.9335	0.2216	1.9335	1.3905
0.0991	46.6667	140	2.2975	0.1611	2.2975	1.5158
0.0991	47.3333	142	1.7128	0.2617	1.7128	1.3087
0.0991	48.0	144	1.6409	0.2690	1.6409	1.2810
0.0991	48.6667	146	1.8524	0.2364	1.8524	1.3610
0.0991	49.3333	148	1.8970	0.2238	1.8970	1.3773
0.0988	50.0	150	1.6201	0.2905	1.6201	1.2728
0.0988	50.6667	152	1.8059	0.2372	1.8059	1.3439
0.0988	51.3333	154	1.6158	0.2931	1.6158	1.2711
0.0988	52.0	156	1.5329	0.3033	1.5329	1.2381
0.0988	52.6667	158	1.8816	0.2325	1.8816	1.3717
0.0809	53.3333	160	1.7108	0.2688	1.7108	1.3080
0.0809	54.0	162	1.5249	0.3058	1.5249	1.2349
0.0809	54.6667	164	1.2596	0.3303	1.2596	1.1223
0.0809	55.3333	166	1.5501	0.3147	1.5501	1.2450
0.0809	56.0	168	1.8061	0.2478	1.8061	1.3439
0.1067	56.6667	170	1.5341	0.3177	1.5341	1.2386
0.1067	57.3333	172	1.4945	0.3148	1.4945	1.2225
0.1067	58.0	174	1.7990	0.2476	1.7990	1.3413
0.1067	58.6667	176	1.9050	0.2270	1.9050	1.3802
0.1067	59.3333	178	1.5962	0.2778	1.5962	1.2634
0.0705	60.0	180	1.5447	0.2851	1.5447	1.2429
0.0705	60.6667	182	1.6104	0.2698	1.6104	1.2690
0.0705	61.3333	184	1.5860	0.2676	1.5860	1.2594
0.0705	62.0	186	1.5977	0.2762	1.5977	1.2640
0.0705	62.6667	188	1.6779	0.2657	1.6779	1.2954
0.0724	63.3333	190	1.5805	0.2859	1.5805	1.2572
0.0724	64.0	192	1.7477	0.2570	1.7477	1.3220
0.0724	64.6667	194	1.9430	0.2082	1.9430	1.3939
0.0724	65.3333	196	1.7571	0.2393	1.7571	1.3256
0.0724	66.0	198	1.4695	0.2877	1.4695	1.2122
0.0661	66.6667	200	1.5108	0.2836	1.5108	1.2291
0.0661	67.3333	202	1.7107	0.2425	1.7107	1.3080
0.0661	68.0	204	1.6595	0.2548	1.6595	1.2882
0.0661	68.6667	206	1.4383	0.3037	1.4383	1.1993
0.0661	69.3333	208	1.5355	0.2625	1.5355	1.2392
0.0656	70.0	210	1.5483	0.2572	1.5483	1.2443
0.0656	70.6667	212	1.4197	0.2974	1.4197	1.1915
0.0656	71.3333	214	1.5078	0.2761	1.5078	1.2279
0.0656	72.0	216	1.8226	0.2203	1.8226	1.3500
0.0656	72.6667	218	1.9100	0.1970	1.9100	1.3820
0.0644	73.3333	220	1.6416	0.2402	1.6416	1.2813
0.0644	74.0	222	1.3359	0.3017	1.3359	1.1558
0.0644	74.6667	224	1.3737	0.2873	1.3737	1.1721
0.0644	75.3333	226	1.6761	0.2401	1.6761	1.2947
0.0644	76.0	228	1.8035	0.2212	1.8035	1.3430
0.0667	76.6667	230	1.6203	0.2620	1.6203	1.2729
0.0667	77.3333	232	1.4950	0.2906	1.4950	1.2227
0.0667	78.0	234	1.4850	0.2752	1.4850	1.2186
0.0667	78.6667	236	1.5552	0.2664	1.5552	1.2471
0.0667	79.3333	238	1.6526	0.2427	1.6526	1.2855
0.0582	80.0	240	1.6030	0.2569	1.6030	1.2661
0.0582	80.6667	242	1.7156	0.2399	1.7156	1.3098
0.0582	81.3333	244	1.8537	0.2230	1.8537	1.3615
0.0582	82.0	246	1.7407	0.2480	1.7407	1.3194
0.0582	82.6667	248	1.6288	0.2702	1.6288	1.2762
0.0576	83.3333	250	1.5769	0.2701	1.5769	1.2558
0.0576	84.0	252	1.5610	0.2758	1.5610	1.2494
0.0576	84.6667	254	1.4504	0.2799	1.4504	1.2043
0.0576	85.3333	256	1.4638	0.2866	1.4638	1.2099
0.0576	86.0	258	1.6333	0.2668	1.6333	1.2780
0.0584	86.6667	260	1.7992	0.2286	1.7992	1.3413
0.0584	87.3333	262	1.7825	0.2280	1.7825	1.3351
0.0584	88.0	264	1.6282	0.2605	1.6282	1.2760
0.0584	88.6667	266	1.5496	0.2681	1.5496	1.2448
0.0584	89.3333	268	1.5631	0.2589	1.5631	1.2502
0.0511	90.0	270	1.6483	0.2604	1.6483	1.2839
0.0511	90.6667	272	1.6868	0.2581	1.6868	1.2988
0.0511	91.3333	274	1.6328	0.2638	1.6328	1.2778
0.0511	92.0	276	1.5796	0.2766	1.5796	1.2568
0.0511	92.6667	278	1.5551	0.2791	1.5551	1.2470
0.0501	93.3333	280	1.5712	0.2766	1.5712	1.2535
0.0501	94.0	282	1.5738	0.2749	1.5738	1.2545
0.0501	94.6667	284	1.5536	0.2704	1.5536	1.2464
0.0501	95.3333	286	1.5227	0.2643	1.5227	1.2340
0.0501	96.0	288	1.5199	0.2684	1.5199	1.2329
0.0497	96.6667	290	1.5281	0.2695	1.5281	1.2362
0.0497	97.3333	292	1.5431	0.2651	1.5431	1.2422
0.0497	98.0	294	1.5367	0.2655	1.5367	1.2396
0.0497	98.6667	296	1.5256	0.2695	1.5256	1.2352
0.0497	99.3333	298	1.5134	0.2737	1.5134	1.2302
0.0512	100.0	300	1.5071	0.2737	1.5071	1.2277

Framework versions

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