ASAP_changed_semanticV2_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_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: 1.5344
• Qwk: 0.2067
• Mse: 1.5340
• Rmse: 1.2386

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	3	9.4692	0.0122	9.4664	3.0768
No log	2.0	6	6.2496	0.0	6.2473	2.4995
No log	3.0	9	6.0149	0.0	6.0126	2.4521
No log	4.0	12	5.6838	-0.0226	5.6815	2.3836
No log	5.0	15	4.9629	0.0	4.9608	2.2273
No log	6.0	18	4.0504	0.0	4.0484	2.0121
No log	7.0	21	3.1681	0.0	3.1663	1.7794
No log	8.0	24	2.4806	-0.0098	2.4788	1.5744
No log	9.0	27	1.7185	0.0759	1.7169	1.3103
No log	10.0	30	1.9276	0.1020	1.9261	1.3878
No log	11.0	33	1.7058	0.1265	1.7043	1.3055
No log	12.0	36	1.2975	0.1336	1.2962	1.1385
No log	13.0	39	1.3069	0.1583	1.3056	1.1426
No log	14.0	42	1.8048	0.1604	1.8031	1.3428
No log	15.0	45	1.4076	0.1619	1.4066	1.1860
No log	16.0	48	1.2596	0.1907	1.2589	1.1220
No log	17.0	51	2.1787	0.0420	2.1777	1.4757
No log	18.0	54	1.1582	0.2207	1.1578	1.0760
No log	19.0	57	2.2147	0.0271	2.2128	1.4876
No log	20.0	60	1.3756	0.1451	1.3746	1.1724
No log	21.0	63	2.4749	-0.0009	2.4729	1.5726
No log	22.0	66	1.4056	0.1434	1.4056	1.1856
No log	23.0	69	2.4642	0.0191	2.4631	1.5694
No log	24.0	72	1.4835	0.1212	1.4832	1.2179
No log	25.0	75	1.0007	0.3274	1.0003	1.0002
No log	26.0	78	2.3566	0.0381	2.3555	1.5348
No log	27.0	81	2.5559	0.0191	2.5547	1.5984
No log	28.0	84	0.9948	0.3234	0.9947	0.9973
No log	29.0	87	1.2580	0.2137	1.2581	1.1217
No log	30.0	90	2.2387	0.0691	2.2382	1.4961
No log	31.0	93	1.5816	0.1722	1.5819	1.2577
No log	32.0	96	2.3899	0.0544	2.3889	1.5456
No log	33.0	99	1.4769	0.1988	1.4766	1.2152
No log	34.0	102	1.8285	0.1078	1.8274	1.3518
No log	35.0	105	1.5025	0.1974	1.5019	1.2255
No log	36.0	108	2.3155	0.0569	2.3140	1.5212
No log	37.0	111	1.6967	0.1443	1.6961	1.3023
No log	38.0	114	1.6967	0.1132	1.6958	1.3022
No log	39.0	117	1.3597	0.1908	1.3589	1.1657
No log	40.0	120	1.6503	0.1253	1.6492	1.2842
No log	41.0	123	1.4586	0.1968	1.4579	1.2074
No log	42.0	126	1.8088	0.1189	1.8079	1.3446
No log	43.0	129	1.3314	0.2274	1.3308	1.1536
No log	44.0	132	1.5394	0.1512	1.5385	1.2403
No log	45.0	135	1.5344	0.2067	1.5340	1.2386

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0