Version_Test_ASAP_FineTuningBERT_AugV14_k10_task1_organization_k10_k10_fold4

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: 0.7820
• Qwk: 0.5794
• Mse: 0.7820
• Rmse: 0.8843

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	8.6701	0.0018	8.6701	2.9445
No log	2.0	14	4.1860	0.0079	4.1860	2.0460
No log	3.0	21	1.3297	0.0445	1.3297	1.1531
No log	4.0	28	0.8253	0.1390	0.8253	0.9085
No log	5.0	35	0.7852	0.2630	0.7852	0.8861
No log	6.0	42	0.7412	0.4863	0.7412	0.8610
No log	7.0	49	0.8901	0.4950	0.8901	0.9435
No log	8.0	56	0.8034	0.5385	0.8034	0.8963
No log	9.0	63	1.1706	0.4363	1.1706	1.0820
No log	10.0	70	0.6291	0.5785	0.6291	0.7931
No log	11.0	77	0.7019	0.5779	0.7019	0.8378
No log	12.0	84	1.0124	0.4603	1.0124	1.0062
No log	13.0	91	1.1666	0.4453	1.1666	1.0801
No log	14.0	98	0.8615	0.5627	0.8615	0.9282
No log	15.0	105	0.8066	0.5903	0.8066	0.8981
No log	16.0	112	0.7290	0.6039	0.7290	0.8538
No log	17.0	119	0.7209	0.6154	0.7209	0.8491
No log	18.0	126	0.7896	0.5691	0.7896	0.8886
No log	19.0	133	0.6203	0.6205	0.6203	0.7876
No log	20.0	140	0.6388	0.6105	0.6388	0.7992
No log	21.0	147	0.6444	0.6097	0.6444	0.8028
No log	22.0	154	0.6278	0.6232	0.6278	0.7924
No log	23.0	161	0.8842	0.5667	0.8842	0.9403
No log	24.0	168	0.6279	0.6311	0.6279	0.7924
No log	25.0	175	0.6641	0.6010	0.6641	0.8149
No log	26.0	182	0.6060	0.6127	0.6060	0.7785
No log	27.0	189	0.8539	0.5665	0.8539	0.9241
No log	28.0	196	0.6868	0.6108	0.6868	0.8287
No log	29.0	203	0.7885	0.5838	0.7885	0.8880
No log	30.0	210	0.7659	0.6084	0.7659	0.8752
No log	31.0	217	0.6400	0.6128	0.6400	0.8000
No log	32.0	224	0.7071	0.5945	0.7071	0.8409
No log	33.0	231	0.5634	0.6338	0.5634	0.7506
No log	34.0	238	0.9967	0.5014	0.9967	0.9983
No log	35.0	245	0.6658	0.6016	0.6658	0.8160
No log	36.0	252	0.7387	0.5848	0.7387	0.8595
No log	37.0	259	0.7656	0.5824	0.7656	0.8750
No log	38.0	266	0.6149	0.6002	0.6149	0.7841
No log	39.0	273	0.9827	0.4962	0.9827	0.9913
No log	40.0	280	0.8988	0.5114	0.8988	0.9481
No log	41.0	287	0.6664	0.6068	0.6664	0.8163
No log	42.0	294	0.7269	0.5977	0.7269	0.8526
No log	43.0	301	0.7173	0.5810	0.7173	0.8470
No log	44.0	308	0.6310	0.6178	0.6310	0.7943
No log	45.0	315	0.9993	0.5017	0.9993	0.9996
No log	46.0	322	0.7824	0.5933	0.7824	0.8846
No log	47.0	329	0.6323	0.6032	0.6323	0.7952
No log	48.0	336	0.7735	0.5514	0.7735	0.8795
No log	49.0	343	0.6039	0.6257	0.6039	0.7771
No log	50.0	350	0.7249	0.5987	0.7249	0.8514
No log	51.0	357	0.8585	0.5222	0.8585	0.9265
No log	52.0	364	0.6155	0.6190	0.6155	0.7846
No log	53.0	371	0.7820	0.5794	0.7820	0.8843

Framework versions

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