Version_concise_ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold2

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: 0.8303
• Qwk: 0.4868
• Mse: 0.8297
• Rmse: 0.9109

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	2	9.3481	0.0	9.3483	3.0575
No log	2.0	4	7.9430	0.0	7.9432	2.8184
No log	3.0	6	6.4297	0.0	6.4299	2.5357
No log	4.0	8	5.2472	0.0117	5.2475	2.2907
No log	5.0	10	4.2428	0.0	4.2430	2.0599
No log	6.0	12	3.4794	0.0	3.4797	1.8654
No log	7.0	14	2.6988	0.0	2.6991	1.6429
No log	8.0	16	2.1197	0.0703	2.1200	1.4560
No log	9.0	18	1.9120	0.0384	1.9124	1.3829
No log	10.0	20	1.5110	0.0107	1.5114	1.2294
No log	11.0	22	1.4265	0.0213	1.4270	1.1946
No log	12.0	24	1.1714	0.0	1.1719	1.0825
No log	13.0	26	1.1856	0.0	1.1862	1.0891
No log	14.0	28	0.9033	0.0399	0.9037	0.9507
No log	15.0	30	0.9177	0.2425	0.9180	0.9581
No log	16.0	32	0.7279	0.3720	0.7281	0.8533
No log	17.0	34	1.0334	-0.0926	1.0339	1.0168
No log	18.0	36	0.8170	0.2037	0.8173	0.9041
No log	19.0	38	1.3399	0.2230	1.3400	1.1576
No log	20.0	40	1.6036	0.1848	1.6039	1.2664
No log	21.0	42	0.6923	0.3811	0.6921	0.8319
No log	22.0	44	1.0683	-0.0312	1.0689	1.0339
No log	23.0	46	0.9522	0.0764	0.9527	0.9761
No log	24.0	48	0.6308	0.3460	0.6306	0.7941
No log	25.0	50	0.6579	0.3673	0.6576	0.8109
No log	26.0	52	0.6206	0.3796	0.6202	0.7875
No log	27.0	54	0.7016	0.3528	0.7015	0.8375
No log	28.0	56	0.6140	0.4792	0.6136	0.7834
No log	29.0	58	0.5970	0.5336	0.5966	0.7724
No log	30.0	60	0.8107	0.3111	0.8109	0.9005
No log	31.0	62	0.8294	0.3002	0.8295	0.9108
No log	32.0	64	0.6166	0.5815	0.6161	0.7849
No log	33.0	66	0.6254	0.5776	0.6249	0.7905
No log	34.0	68	0.7816	0.4265	0.7814	0.8840
No log	35.0	70	0.9633	0.2423	0.9637	0.9817
No log	36.0	72	0.9241	0.3392	0.9242	0.9613
No log	37.0	74	0.7563	0.5070	0.7558	0.8694
No log	38.0	76	0.8426	0.4486	0.8422	0.9177
No log	39.0	78	0.8088	0.5001	0.8083	0.8991
No log	40.0	80	0.8196	0.5160	0.8192	0.9051
No log	41.0	82	0.7739	0.5372	0.7733	0.8794
No log	42.0	84	0.8975	0.4119	0.8971	0.9472
No log	43.0	86	0.9952	0.3978	0.9948	0.9974
No log	44.0	88	0.8762	0.4926	0.8755	0.9357
No log	45.0	90	0.7937	0.5303	0.7930	0.8905
No log	46.0	92	0.8449	0.5272	0.8442	0.9188
No log	47.0	94	1.0401	0.4450	1.0395	1.0196
No log	48.0	96	0.9659	0.4810	0.9652	0.9824
No log	49.0	98	0.8894	0.4873	0.8887	0.9427
No log	50.0	100	0.9761	0.4685	0.9754	0.9876
No log	51.0	102	0.9562	0.4608	0.9557	0.9776
No log	52.0	104	0.8303	0.4868	0.8297	0.9109

Framework versions

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