Version_concise_ASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_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: 0.8049
• Qwk: 0.4890
• Mse: 0.8059
• Rmse: 0.8977

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	4	10.4084	0.0	10.4062	3.2259
No log	2.0	8	7.2285	0.0	7.2270	2.6883
No log	3.0	12	3.7588	0.0137	3.7578	1.9385
No log	4.0	16	2.2177	0.1520	2.2170	1.4890
No log	5.0	20	1.3261	0.0266	1.3254	1.1512
No log	6.0	24	0.9468	0.0535	0.9465	0.9729
No log	7.0	28	2.2473	0.1576	2.2468	1.4989
No log	8.0	32	1.7879	0.1676	1.7875	1.3370
No log	9.0	36	0.8554	0.2787	0.8553	0.9248
No log	10.0	40	1.1573	0.2254	1.1573	1.0758
No log	11.0	44	0.7502	0.4458	0.7503	0.8662
No log	12.0	48	1.6908	0.2336	1.6912	1.3005
No log	13.0	52	1.5579	0.2761	1.5583	1.2483
No log	14.0	56	0.5757	0.4869	0.5762	0.7591
No log	15.0	60	0.9721	0.3730	0.9728	0.9863
No log	16.0	64	0.5872	0.5466	0.5882	0.7669
No log	17.0	68	0.6144	0.5580	0.6156	0.7846
No log	18.0	72	0.8037	0.5061	0.8048	0.8971
No log	19.0	76	0.7493	0.5220	0.7502	0.8662
No log	20.0	80	0.8208	0.4970	0.8218	0.9066
No log	21.0	84	0.7606	0.5427	0.7618	0.8728
No log	22.0	88	0.9268	0.4634	0.9279	0.9633
No log	23.0	92	0.7481	0.5301	0.7492	0.8656
No log	24.0	96	1.1137	0.4053	1.1149	1.0559
No log	25.0	100	1.0607	0.4350	1.0619	1.0305
No log	26.0	104	0.9132	0.4943	0.9144	0.9562
No log	27.0	108	1.0272	0.4531	1.0283	1.0140
No log	28.0	112	1.0483	0.4520	1.0495	1.0245
No log	29.0	116	0.7777	0.5350	0.7788	0.8825
No log	30.0	120	1.0714	0.4099	1.0723	1.0355
No log	31.0	124	0.7234	0.5320	0.7244	0.8511
No log	32.0	128	1.0526	0.3898	1.0536	1.0264
No log	33.0	132	0.7696	0.5145	0.7705	0.8778
No log	34.0	136	0.9328	0.4471	0.9338	0.9663
No log	35.0	140	0.7858	0.5028	0.7868	0.8870
No log	36.0	144	0.8130	0.4934	0.8139	0.9022
No log	37.0	148	0.8049	0.4890	0.8059	0.8977

Framework versions

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