bert_baseline_prompt_adherence_task3_fold0

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: 0.2935
• Qwk: 0.6969
• Mse: 0.2933

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	1.4854	0.0	1.4830
No log	0.0615	4	1.1545	0.0	1.1527
No log	0.0923	6	1.0353	0.1047	1.0337
No log	0.1231	8	0.8265	0.0080	0.8256
No log	0.1538	10	0.7134	0.0080	0.7131
No log	0.1846	12	0.7006	0.0080	0.7006
No log	0.2154	14	0.6698	0.0160	0.6697
No log	0.2462	16	0.6591	0.0261	0.6587
No log	0.2769	18	0.6070	0.0608	0.6065
No log	0.3077	20	0.5114	0.3209	0.5113
No log	0.3385	22	0.5089	0.5441	0.5090
No log	0.3692	24	0.4664	0.5828	0.4664
No log	0.4	26	0.4133	0.5528	0.4130
No log	0.4308	28	0.3954	0.5784	0.3950
No log	0.4615	30	0.4077	0.4964	0.4068
No log	0.4923	32	0.4400	0.4461	0.4389
No log	0.5231	34	0.3693	0.5871	0.3685
No log	0.5538	36	0.4165	0.6417	0.4162
No log	0.5846	38	0.4393	0.6482	0.4390
No log	0.6154	40	0.3674	0.6179	0.3668
No log	0.6462	42	0.4456	0.3881	0.4447
No log	0.6769	44	0.5274	0.3133	0.5263
No log	0.7077	46	0.4872	0.3225	0.4863
No log	0.7385	48	0.4269	0.3624	0.4263
No log	0.7692	50	0.4285	0.4215	0.4281
No log	0.8	52	0.4577	0.6590	0.4574
No log	0.8308	54	0.4957	0.6612	0.4955
No log	0.8615	56	0.4681	0.6717	0.4679
No log	0.8923	58	0.3478	0.6613	0.3475
No log	0.9231	60	0.3521	0.5242	0.3515
No log	0.9538	62	0.4063	0.4490	0.4055
No log	0.9846	64	0.3644	0.5015	0.3637
No log	1.0154	66	0.3224	0.6241	0.3220
No log	1.0462	68	0.3547	0.6701	0.3545
No log	1.0769	70	0.3713	0.6762	0.3711
No log	1.1077	72	0.3302	0.6574	0.3299
No log	1.1385	74	0.3111	0.6304	0.3107
No log	1.1692	76	0.3082	0.6457	0.3078
No log	1.2	78	0.3058	0.6367	0.3054
No log	1.2308	80	0.3031	0.6176	0.3026
No log	1.2615	82	0.3044	0.6173	0.3039
No log	1.2923	84	0.2976	0.6220	0.2971
No log	1.3231	86	0.3050	0.6457	0.3047
No log	1.3538	88	0.3121	0.6704	0.3118
No log	1.3846	90	0.2957	0.6403	0.2953
No log	1.4154	92	0.2961	0.6064	0.2957
No log	1.4462	94	0.2995	0.5934	0.2991
No log	1.4769	96	0.2915	0.6499	0.2912
No log	1.5077	98	0.3321	0.6978	0.3319
No log	1.5385	100	0.4077	0.7087	0.4078
No log	1.5692	102	0.3793	0.7102	0.3793
No log	1.6	104	0.3049	0.6918	0.3048
No log	1.6308	106	0.2953	0.6376	0.2950
No log	1.6615	108	0.3054	0.6513	0.3052
No log	1.6923	110	0.3162	0.6674	0.3160
No log	1.7231	112	0.3023	0.6294	0.3020
No log	1.7538	114	0.3041	0.6641	0.3038
No log	1.7846	116	0.3123	0.6912	0.3120
No log	1.8154	118	0.3106	0.6878	0.3103
No log	1.8462	120	0.3049	0.6864	0.3046
No log	1.8769	122	0.3027	0.6772	0.3024
No log	1.9077	124	0.2932	0.6741	0.2928
No log	1.9385	126	0.3010	0.6824	0.3006
No log	1.9692	128	0.3298	0.6837	0.3295
No log	2.0	130	0.3293	0.6857	0.3290
No log	2.0308	132	0.3017	0.6529	0.3013
No log	2.0615	134	0.3023	0.5797	0.3017
No log	2.0923	136	0.3035	0.5761	0.3029
No log	2.1231	138	0.2916	0.6173	0.2912
No log	2.1538	140	0.3012	0.6787	0.3009
No log	2.1846	142	0.2960	0.6767	0.2957
No log	2.2154	144	0.2858	0.6631	0.2855
No log	2.2462	146	0.2807	0.6614	0.2804
No log	2.2769	148	0.2860	0.6577	0.2857
No log	2.3077	150	0.2929	0.6777	0.2927
No log	2.3385	152	0.2800	0.6558	0.2797
No log	2.3692	154	0.2830	0.6594	0.2828
No log	2.4	156	0.2810	0.6588	0.2808
No log	2.4308	158	0.2975	0.6841	0.2974
No log	2.4615	160	0.3103	0.6994	0.3102
No log	2.4923	162	0.2931	0.6883	0.2930
No log	2.5231	164	0.2755	0.6602	0.2753
No log	2.5538	166	0.2733	0.6434	0.2731
No log	2.5846	168	0.2833	0.6803	0.2831
No log	2.6154	170	0.3004	0.7083	0.3003
No log	2.6462	172	0.3652	0.7356	0.3652
No log	2.6769	174	0.4676	0.7614	0.4677
No log	2.7077	176	0.4272	0.7588	0.4272
No log	2.7385	178	0.3219	0.7219	0.3218
No log	2.7692	180	0.2715	0.6607	0.2712
No log	2.8	182	0.2737	0.6189	0.2733
No log	2.8308	184	0.2726	0.6522	0.2723
No log	2.8615	186	0.3011	0.7039	0.3009
No log	2.8923	188	0.3333	0.7262	0.3332
No log	2.9231	190	0.3351	0.7226	0.3350
No log	2.9538	192	0.2959	0.6960	0.2957
No log	2.9846	194	0.2766	0.6285	0.2762
No log	3.0154	196	0.2932	0.5847	0.2927
No log	3.0462	198	0.2860	0.5958	0.2855
No log	3.0769	200	0.2763	0.6459	0.2759
No log	3.1077	202	0.2817	0.6746	0.2814
No log	3.1385	204	0.2909	0.6957	0.2906
No log	3.1692	206	0.2919	0.6968	0.2916
No log	3.2	208	0.2818	0.6554	0.2815
No log	3.2308	210	0.2849	0.6224	0.2845
No log	3.2615	212	0.2951	0.5993	0.2946
No log	3.2923	214	0.2859	0.6233	0.2855
No log	3.3231	216	0.2858	0.6721	0.2855
No log	3.3538	218	0.3363	0.7036	0.3361
No log	3.3846	220	0.4129	0.7291	0.4128
No log	3.4154	222	0.4321	0.7289	0.4320
No log	3.4462	224	0.3973	0.7335	0.3972
No log	3.4769	226	0.3306	0.7122	0.3304
No log	3.5077	228	0.2865	0.6763	0.2862
No log	3.5385	230	0.2814	0.6373	0.2810
No log	3.5692	232	0.2811	0.6373	0.2808
No log	3.6	234	0.2820	0.6554	0.2816
No log	3.6308	236	0.2812	0.6459	0.2809
No log	3.6615	238	0.2822	0.6583	0.2819
No log	3.6923	240	0.2855	0.6661	0.2852
No log	3.7231	242	0.2927	0.6832	0.2924
No log	3.7538	244	0.2929	0.6807	0.2926
No log	3.7846	246	0.2926	0.6807	0.2924
No log	3.8154	248	0.2922	0.6812	0.2919
No log	3.8462	250	0.2938	0.6842	0.2935
No log	3.8769	252	0.2859	0.6709	0.2857
No log	3.9077	254	0.2817	0.6562	0.2815
No log	3.9385	256	0.2816	0.6372	0.2814
No log	3.9692	258	0.2824	0.6621	0.2821
No log	4.0	260	0.2910	0.6803	0.2908
No log	4.0308	262	0.3234	0.7267	0.3232
No log	4.0615	264	0.3467	0.7501	0.3465
No log	4.0923	266	0.3459	0.7528	0.3457
No log	4.1231	268	0.3338	0.7411	0.3336
No log	4.1538	270	0.3105	0.7108	0.3103
No log	4.1846	272	0.2960	0.6983	0.2958
No log	4.2154	274	0.2861	0.6827	0.2859
No log	4.2462	276	0.2789	0.6555	0.2787
No log	4.2769	278	0.2773	0.6550	0.2771
No log	4.3077	280	0.2781	0.6514	0.2779
No log	4.3385	282	0.2856	0.6833	0.2854
No log	4.3692	284	0.3094	0.7113	0.3093
No log	4.4	286	0.3352	0.7320	0.3350
No log	4.4308	288	0.3420	0.7373	0.3418
No log	4.4615	290	0.3342	0.7338	0.3340
No log	4.4923	292	0.3181	0.7229	0.3179
No log	4.5231	294	0.3053	0.7026	0.3052
No log	4.5538	296	0.3018	0.6940	0.3016
No log	4.5846	298	0.3028	0.6951	0.3026
No log	4.6154	300	0.2999	0.6951	0.2997
No log	4.6462	302	0.2983	0.6969	0.2981
No log	4.6769	304	0.2955	0.6969	0.2953
No log	4.7077	306	0.2960	0.6969	0.2958
No log	4.7385	308	0.2976	0.6969	0.2974
No log	4.7692	310	0.2946	0.6969	0.2945
No log	4.8	312	0.2913	0.6951	0.2911
No log	4.8308	314	0.2903	0.6940	0.2901
No log	4.8615	316	0.2897	0.6940	0.2895
No log	4.8923	318	0.2910	0.6940	0.2908
No log	4.9231	320	0.2927	0.6969	0.2925
No log	4.9538	322	0.2931	0.6969	0.2929
No log	4.9846	324	0.2935	0.6969	0.2933

Framework versions

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