Version_Test_ASAP_FineTuningBERT_AugV14_k10_task1_organization_k10_k10_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: 0.5475
• Qwk: 0.5412
• Mse: 0.5475
• Rmse: 0.7399

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	7	6.2769	-0.0010	6.2769	2.5054
No log	2.0	14	3.2949	0.0	3.2949	1.8152
No log	3.0	21	1.3402	0.0316	1.3402	1.1577
No log	4.0	28	0.7525	0.1169	0.7525	0.8675
No log	5.0	35	0.9424	0.0689	0.9424	0.9708
No log	6.0	42	0.5171	0.4477	0.5171	0.7191
No log	7.0	49	0.5033	0.4620	0.5033	0.7095
No log	8.0	56	0.4756	0.5118	0.4756	0.6897
No log	9.0	63	0.4791	0.5044	0.4791	0.6922
No log	10.0	70	0.5121	0.5567	0.5121	0.7156
No log	11.0	77	0.8750	0.3946	0.8750	0.9354
No log	12.0	84	0.5732	0.5192	0.5732	0.7571
No log	13.0	91	0.6590	0.5295	0.6590	0.8118
No log	14.0	98	0.5113	0.5432	0.5113	0.7150
No log	15.0	105	0.6464	0.5021	0.6464	0.8040
No log	16.0	112	0.4853	0.5780	0.4853	0.6966
No log	17.0	119	0.6165	0.5465	0.6165	0.7851
No log	18.0	126	0.5927	0.5029	0.5927	0.7698
No log	19.0	133	0.7444	0.4677	0.7444	0.8628
No log	20.0	140	0.7202	0.5220	0.7202	0.8487
No log	21.0	147	0.6528	0.4862	0.6528	0.8080
No log	22.0	154	0.5971	0.5250	0.5971	0.7727
No log	23.0	161	0.6178	0.5447	0.6178	0.7860
No log	24.0	168	0.5620	0.5400	0.5620	0.7497
No log	25.0	175	0.5609	0.5334	0.5609	0.7489
No log	26.0	182	0.5293	0.5565	0.5293	0.7275
No log	27.0	189	0.5519	0.5387	0.5519	0.7429
No log	28.0	196	0.5604	0.5157	0.5604	0.7486
No log	29.0	203	0.5643	0.5668	0.5643	0.7512
No log	30.0	210	0.5627	0.5602	0.5627	0.7501
No log	31.0	217	0.5852	0.5535	0.5852	0.7650
No log	32.0	224	0.6176	0.5525	0.6176	0.7859
No log	33.0	231	0.5759	0.5799	0.5759	0.7589
No log	34.0	238	0.5550	0.5423	0.5550	0.7450
No log	35.0	245	0.5857	0.5522	0.5857	0.7653
No log	36.0	252	0.5577	0.5217	0.5577	0.7468
No log	37.0	259	0.5358	0.5701	0.5358	0.7320
No log	38.0	266	0.5959	0.5336	0.5959	0.7719
No log	39.0	273	0.5576	0.5472	0.5576	0.7467
No log	40.0	280	0.5265	0.5480	0.5265	0.7256
No log	41.0	287	0.7291	0.4986	0.7291	0.8539
No log	42.0	294	0.6184	0.5361	0.6184	0.7864
No log	43.0	301	0.5429	0.5488	0.5429	0.7368
No log	44.0	308	0.5375	0.5854	0.5375	0.7331
No log	45.0	315	0.5435	0.5193	0.5435	0.7372
No log	46.0	322	0.5452	0.5506	0.5452	0.7384
No log	47.0	329	0.5467	0.5527	0.5467	0.7394
No log	48.0	336	0.5557	0.5222	0.5557	0.7455
No log	49.0	343	0.5465	0.5334	0.5465	0.7392
No log	50.0	350	0.5537	0.5240	0.5537	0.7441
No log	51.0	357	0.5374	0.5713	0.5374	0.7330
No log	52.0	364	0.5366	0.5035	0.5366	0.7326
No log	53.0	371	0.5420	0.5193	0.5420	0.7362
No log	54.0	378	0.5166	0.5577	0.5166	0.7188
No log	55.0	385	0.5205	0.5569	0.5205	0.7214
No log	56.0	392	0.5336	0.5398	0.5336	0.7305
No log	57.0	399	0.5539	0.5279	0.5539	0.7443
No log	58.0	406	0.5689	0.5199	0.5689	0.7543
No log	59.0	413	0.5949	0.5184	0.5949	0.7713
No log	60.0	420	0.5280	0.5301	0.5280	0.7266
No log	61.0	427	0.5396	0.5463	0.5396	0.7345
No log	62.0	434	0.5438	0.5129	0.5438	0.7374
No log	63.0	441	0.5459	0.5209	0.5459	0.7388
No log	64.0	448	0.5475	0.5412	0.5475	0.7399

Framework versions

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