Version_weird_ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold1

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: 1.1309
• Qwk: 0.5189
• Mse: 1.1305
• Rmse: 1.0632

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	1	12.5740	-0.0003	12.5713	3.5456
No log	2.0	2	10.8014	0.0088	10.7983	3.2861
No log	3.0	3	10.0333	0.0041	10.0308	3.1671
No log	4.0	4	9.0135	0.0	9.0110	3.0018
No log	5.0	5	7.8288	0.0	7.8265	2.7976
No log	6.0	6	6.8564	0.0	6.8543	2.6181
No log	7.0	7	6.0657	-0.0038	6.0636	2.4624
No log	8.0	8	5.2253	0.0150	5.2232	2.2854
No log	9.0	9	4.3913	0.0040	4.3894	2.0951
No log	10.0	10	3.9496	0.0040	3.9476	1.9869
No log	11.0	11	3.5993	0.0	3.5973	1.8967
No log	12.0	12	3.1575	0.0	3.1556	1.7764
No log	13.0	13	2.7309	0.0	2.7290	1.6520
No log	14.0	14	2.4330	-0.0248	2.4312	1.5592
No log	15.0	15	2.0834	0.0426	2.0817	1.4428
No log	16.0	16	1.7675	0.0418	1.7659	1.3289
No log	17.0	17	1.6028	0.0315	1.6013	1.2654
No log	18.0	18	1.4872	0.0211	1.4857	1.2189
No log	19.0	19	1.3808	0.0106	1.3793	1.1744
No log	20.0	20	1.2609	0.0	1.2594	1.1222
No log	21.0	21	1.1246	0.0	1.1232	1.0598
No log	22.0	22	1.0317	0.0	1.0303	1.0151
No log	23.0	23	0.9622	0.0	0.9609	0.9802
No log	24.0	24	0.8966	0.2075	0.8953	0.9462
No log	25.0	25	0.8800	0.2097	0.8788	0.9374
No log	26.0	26	0.8632	0.2104	0.8620	0.9284
No log	27.0	27	0.7932	0.2525	0.7921	0.8900
No log	28.0	28	0.7208	0.3412	0.7197	0.8483
No log	29.0	29	0.6937	0.3181	0.6926	0.8322
No log	30.0	30	0.7237	0.2705	0.7227	0.8501
No log	31.0	31	0.6996	0.2960	0.6986	0.8358
No log	32.0	32	0.6294	0.3766	0.6284	0.7927
No log	33.0	33	0.5427	0.4519	0.5418	0.7361
No log	34.0	34	0.4997	0.5094	0.4988	0.7063
No log	35.0	35	0.5241	0.4893	0.5233	0.7234
No log	36.0	36	0.5243	0.4948	0.5235	0.7235
No log	37.0	37	0.5915	0.4691	0.5907	0.7686
No log	38.0	38	0.5673	0.4962	0.5665	0.7527
No log	39.0	39	0.5203	0.6145	0.5196	0.7208
No log	40.0	40	0.5670	0.6093	0.5663	0.7526
No log	41.0	41	0.6641	0.5452	0.6634	0.8145
No log	42.0	42	0.7402	0.5215	0.7395	0.8599
No log	43.0	43	0.7829	0.5248	0.7823	0.8845
No log	44.0	44	0.7472	0.5472	0.7466	0.8640
No log	45.0	45	0.7368	0.5631	0.7362	0.8580
No log	46.0	46	0.8122	0.5450	0.8116	0.9009
No log	47.0	47	0.7932	0.5644	0.7927	0.8903
No log	48.0	48	0.7381	0.5918	0.7376	0.8588
No log	49.0	49	0.8549	0.5576	0.8544	0.9243
No log	50.0	50	0.9385	0.5304	0.9380	0.9685
No log	51.0	51	0.8605	0.5666	0.8601	0.9274
No log	52.0	52	0.8364	0.5718	0.8360	0.9143
No log	53.0	53	1.0331	0.5290	1.0327	1.0162
No log	54.0	54	0.9910	0.5409	0.9906	0.9953
No log	55.0	55	1.0710	0.5255	1.0707	1.0347
No log	56.0	56	0.9077	0.5777	0.9074	0.9526
No log	57.0	57	0.9744	0.5590	0.9741	0.9869
No log	58.0	58	1.1406	0.5228	1.1402	1.0678
No log	59.0	59	1.1309	0.5189	1.1305	1.0632

Framework versions

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