bert_baseline_language_task3_fold1

This model is a fine-tuned version of google-bert/bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3495
• Qwk: 0.7465
• Mse: 0.3495

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse
No log	0.0308	2	0.9241	0.0973	0.9241
No log	0.0615	4	0.7692	0.0172	0.7692
No log	0.0923	6	0.6906	0.0	0.6906
No log	0.1231	8	0.6645	0.0	0.6645
No log	0.1538	10	0.6742	0.0	0.6742
No log	0.1846	12	0.6600	0.0097	0.6600
No log	0.2154	14	0.6105	0.1283	0.6105
No log	0.2462	16	0.5742	0.0989	0.5742
No log	0.2769	18	0.5379	0.2188	0.5379
No log	0.3077	20	0.5496	0.3968	0.5496
No log	0.3385	22	0.5728	0.4810	0.5728
No log	0.3692	24	0.4980	0.5887	0.4980
No log	0.4	26	0.4483	0.5874	0.4483
No log	0.4308	28	0.4423	0.5669	0.4423
No log	0.4615	30	0.4260	0.5824	0.4260
No log	0.4923	32	0.4285	0.6024	0.4285
No log	0.5231	34	0.4691	0.6564	0.4691
No log	0.5538	36	0.4531	0.6363	0.4531
No log	0.5846	38	0.4242	0.5254	0.4242
No log	0.6154	40	0.4281	0.3450	0.4281
No log	0.6462	42	0.4759	0.3197	0.4759
No log	0.6769	44	0.5171	0.3390	0.5171
No log	0.7077	46	0.4740	0.3374	0.4740
No log	0.7385	48	0.4149	0.3145	0.4149
No log	0.7692	50	0.4579	0.6005	0.4579
No log	0.8	52	0.5321	0.6699	0.5321
No log	0.8308	54	0.5278	0.6732	0.5278
No log	0.8615	56	0.4365	0.6723	0.4365
No log	0.8923	58	0.3708	0.5577	0.3708
No log	0.9231	60	0.3647	0.4893	0.3647
No log	0.9538	62	0.3586	0.5214	0.3586
No log	0.9846	64	0.3454	0.5466	0.3454
No log	1.0154	66	0.3349	0.6349	0.3349
No log	1.0462	68	0.3784	0.6895	0.3784
No log	1.0769	70	0.3880	0.6963	0.3880
No log	1.1077	72	0.3685	0.6724	0.3685
No log	1.1385	74	0.3318	0.6633	0.3318
No log	1.1692	76	0.3129	0.5935	0.3129
No log	1.2	78	0.3051	0.6429	0.3051
No log	1.2308	80	0.3128	0.6913	0.3128
No log	1.2615	82	0.4495	0.7299	0.4495
No log	1.2923	84	0.6028	0.7010	0.6028
No log	1.3231	86	0.4935	0.7148	0.4935
No log	1.3538	88	0.3399	0.6230	0.3399
No log	1.3846	90	0.3273	0.5044	0.3273
No log	1.4154	92	0.3266	0.4930	0.3266
No log	1.4462	94	0.3575	0.6291	0.3575
No log	1.4769	96	0.4728	0.7079	0.4728
No log	1.5077	98	0.5130	0.7288	0.5130
No log	1.5385	100	0.4588	0.7313	0.4588
No log	1.5692	102	0.3353	0.7112	0.3353
No log	1.6	104	0.2876	0.5570	0.2876
No log	1.6308	106	0.3135	0.4982	0.3135
No log	1.6615	108	0.2884	0.5642	0.2884
No log	1.6923	110	0.3044	0.7035	0.3044
No log	1.7231	112	0.3390	0.7189	0.3390
No log	1.7538	114	0.3387	0.7189	0.3387
No log	1.7846	116	0.3060	0.7181	0.3060
No log	1.8154	118	0.2881	0.6756	0.2881
No log	1.8462	120	0.2881	0.6663	0.2881
No log	1.8769	122	0.3084	0.6906	0.3084
No log	1.9077	124	0.3555	0.7381	0.3555
No log	1.9385	126	0.3414	0.7463	0.3414
No log	1.9692	128	0.2947	0.6779	0.2947
No log	2.0	130	0.2831	0.5537	0.2831
No log	2.0308	132	0.2853	0.5515	0.2853
No log	2.0615	134	0.2808	0.6274	0.2808
No log	2.0923	136	0.2888	0.6663	0.2888
No log	2.1231	138	0.2990	0.6887	0.2990
No log	2.1538	140	0.3005	0.6804	0.3005
No log	2.1846	142	0.2969	0.6593	0.2969
No log	2.2154	144	0.3092	0.6859	0.3092
No log	2.2462	146	0.3575	0.7172	0.3575
No log	2.2769	148	0.5047	0.7428	0.5047
No log	2.3077	150	0.5975	0.7277	0.5975
No log	2.3385	152	0.5210	0.7478	0.5210
No log	2.3692	154	0.3886	0.7241	0.3886
No log	2.4	156	0.3019	0.6758	0.3019
No log	2.4308	158	0.2917	0.6260	0.2917
No log	2.4615	160	0.3031	0.6687	0.3031
No log	2.4923	162	0.3197	0.6870	0.3197
No log	2.5231	164	0.3623	0.7384	0.3623
No log	2.5538	166	0.3509	0.7409	0.3509
No log	2.5846	168	0.3104	0.7006	0.3104
No log	2.6154	170	0.2990	0.6717	0.2990
No log	2.6462	172	0.3004	0.6883	0.3004
No log	2.6769	174	0.3242	0.7166	0.3242
No log	2.7077	176	0.3344	0.7123	0.3344
No log	2.7385	178	0.3443	0.7146	0.3443
No log	2.7692	180	0.3725	0.7165	0.3725
No log	2.8	182	0.3582	0.7229	0.3582
No log	2.8308	184	0.3007	0.6950	0.3007
No log	2.8615	186	0.2832	0.6327	0.2832
No log	2.8923	188	0.2833	0.6634	0.2833
No log	2.9231	190	0.3170	0.7161	0.3170
No log	2.9538	192	0.3658	0.7354	0.3658
No log	2.9846	194	0.4421	0.7460	0.4421
No log	3.0154	196	0.4628	0.7556	0.4628
No log	3.0462	198	0.4077	0.7401	0.4077
No log	3.0769	200	0.3241	0.7265	0.3241
No log	3.1077	202	0.2805	0.6529	0.2805
No log	3.1385	204	0.2775	0.6296	0.2775
No log	3.1692	206	0.2868	0.6576	0.2868
No log	3.2	208	0.3327	0.7343	0.3327
No log	3.2308	210	0.3808	0.7450	0.3808
No log	3.2615	212	0.3902	0.7446	0.3902
No log	3.2923	214	0.3556	0.7431	0.3556
No log	3.3231	216	0.3444	0.7378	0.3444
No log	3.3538	218	0.3067	0.7044	0.3067
No log	3.3846	220	0.2869	0.6498	0.2869
No log	3.4154	222	0.2910	0.6745	0.2910
No log	3.4462	224	0.3184	0.7196	0.3184
No log	3.4769	226	0.3408	0.7263	0.3408
No log	3.5077	228	0.3229	0.7265	0.3229
No log	3.5385	230	0.3237	0.7234	0.3237
No log	3.5692	232	0.3386	0.7248	0.3386
No log	3.6	234	0.3175	0.7088	0.3175
No log	3.6308	236	0.3032	0.6863	0.3032
No log	3.6615	238	0.3059	0.6853	0.3059
No log	3.6923	240	0.3283	0.7173	0.3283
No log	3.7231	242	0.3330	0.7226	0.3330
No log	3.7538	244	0.3505	0.7378	0.3505
No log	3.7846	246	0.3617	0.7467	0.3617
No log	3.8154	248	0.3791	0.7474	0.3791
No log	3.8462	250	0.3584	0.7476	0.3584
No log	3.8769	252	0.3236	0.7291	0.3236
No log	3.9077	254	0.3140	0.7169	0.3140
No log	3.9385	256	0.3216	0.7300	0.3216
No log	3.9692	258	0.3348	0.7316	0.3348
No log	4.0	260	0.3488	0.7524	0.3488
No log	4.0308	262	0.3508	0.7556	0.3508
No log	4.0615	264	0.3401	0.7409	0.3401
No log	4.0923	266	0.3341	0.7408	0.3341
No log	4.1231	268	0.3301	0.7397	0.3301
No log	4.1538	270	0.3245	0.7386	0.3245
No log	4.1846	272	0.3197	0.7314	0.3197
No log	4.2154	274	0.3080	0.7152	0.3080
No log	4.2462	276	0.2973	0.6889	0.2973
No log	4.2769	278	0.2955	0.6828	0.2955
No log	4.3077	280	0.3032	0.7075	0.3032
No log	4.3385	282	0.3200	0.7297	0.3200
No log	4.3692	284	0.3547	0.7527	0.3547
No log	4.4	286	0.3780	0.7524	0.3780
No log	4.4308	288	0.3775	0.7532	0.3775
No log	4.4615	290	0.3563	0.7478	0.3563
No log	4.4923	292	0.3411	0.7414	0.3411
No log	4.5231	294	0.3259	0.7389	0.3259
No log	4.5538	296	0.3079	0.7092	0.3079
No log	4.5846	298	0.2988	0.6886	0.2988
No log	4.6154	300	0.2977	0.6884	0.2977
No log	4.6462	302	0.3039	0.6961	0.3039
No log	4.6769	304	0.3155	0.7221	0.3155
No log	4.7077	306	0.3336	0.7411	0.3336
No log	4.7385	308	0.3505	0.7475	0.3505
No log	4.7692	310	0.3624	0.7538	0.3624
No log	4.8	312	0.3655	0.7510	0.3655
No log	4.8308	314	0.3611	0.7510	0.3611
No log	4.8615	316	0.3557	0.7507	0.3557
No log	4.8923	318	0.3523	0.7467	0.3523
No log	4.9231	320	0.3497	0.7465	0.3497
No log	4.9538	322	0.3499	0.7465	0.3499
No log	4.9846	324	0.3495	0.7465	0.3495

Framework versions

• Transformers 4.42.3
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1