best_model-sst-2-32-42

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2575
• Accuracy: 0.8281

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	2	1.2950	0.8281
No log	2.0	4	1.2965	0.8281
No log	3.0	6	1.2971	0.8281
No log	4.0	8	1.2972	0.8281
0.3346	5.0	10	1.2994	0.8281
0.3346	6.0	12	1.3037	0.8281
0.3346	7.0	14	1.3082	0.8281
0.3346	8.0	16	1.3140	0.8281
0.3346	9.0	18	1.3212	0.8281
0.2586	10.0	20	1.3285	0.8281
0.2586	11.0	22	1.3346	0.8281
0.2586	12.0	24	1.3404	0.8281
0.2586	13.0	26	1.3443	0.8281
0.2586	14.0	28	1.3499	0.8281
0.2171	15.0	30	1.3534	0.8281
0.2171	16.0	32	1.3551	0.8281
0.2171	17.0	34	1.3544	0.8281
0.2171	18.0	36	1.3531	0.8281
0.2171	19.0	38	1.3516	0.8281
0.1549	20.0	40	1.3494	0.8281
0.1549	21.0	42	1.3471	0.8281
0.1549	22.0	44	1.3446	0.8281
0.1549	23.0	46	1.3414	0.8281
0.1549	24.0	48	1.3351	0.8281
0.0613	25.0	50	1.3277	0.8281
0.0613	26.0	52	1.3201	0.8281
0.0613	27.0	54	1.3110	0.8281
0.0613	28.0	56	1.2974	0.8281
0.0613	29.0	58	1.2847	0.8281
0.0094	30.0	60	1.2767	0.8281
0.0094	31.0	62	1.2697	0.8281
0.0094	32.0	64	1.2638	0.8281
0.0094	33.0	66	1.2625	0.8281
0.0094	34.0	68	1.2633	0.8281
0.0004	35.0	70	1.2642	0.8281
0.0004	36.0	72	1.2757	0.8281
0.0004	37.0	74	1.2783	0.8281
0.0004	38.0	76	1.2813	0.8281
0.0004	39.0	78	1.2892	0.8281
0.0074	40.0	80	1.2990	0.8281
0.0074	41.0	82	1.3111	0.8281
0.0074	42.0	84	1.3233	0.8281
0.0074	43.0	86	1.3317	0.8281
0.0074	44.0	88	1.3371	0.8281
0.0004	45.0	90	1.3410	0.8281
0.0004	46.0	92	1.3436	0.8281
0.0004	47.0	94	1.3456	0.8281
0.0004	48.0	96	1.3471	0.8281
0.0004	49.0	98	1.3489	0.8281
0.0005	50.0	100	1.3488	0.8281
0.0005	51.0	102	1.3429	0.8281
0.0005	52.0	104	1.3365	0.8281
0.0005	53.0	106	1.3305	0.8281
0.0005	54.0	108	1.3247	0.8281
0.0003	55.0	110	1.3195	0.8281
0.0003	56.0	112	1.3151	0.8281
0.0003	57.0	114	1.2921	0.8281
0.0003	58.0	116	1.2717	0.8281
0.0003	59.0	118	1.2551	0.8281
0.0166	60.0	120	1.2421	0.8281
0.0166	61.0	122	1.2590	0.8281
0.0166	62.0	124	1.2739	0.8281
0.0166	63.0	126	1.2861	0.8281
0.0166	64.0	128	1.2958	0.8281
0.0003	65.0	130	1.3039	0.8281
0.0003	66.0	132	1.3103	0.8281
0.0003	67.0	134	1.3126	0.8281
0.0003	68.0	136	1.3125	0.8281
0.0003	69.0	138	1.3125	0.8281
0.0002	70.0	140	1.3128	0.8281
0.0002	71.0	142	1.3131	0.8281
0.0002	72.0	144	1.3135	0.8281
0.0002	73.0	146	1.3141	0.8281
0.0002	74.0	148	1.3147	0.8281
0.0004	75.0	150	1.3289	0.8281
0.0004	76.0	152	1.3274	0.8281
0.0004	77.0	154	1.3260	0.8281
0.0004	78.0	156	1.3251	0.8281
0.0004	79.0	158	1.3523	0.8281
0.0008	80.0	160	1.3691	0.8281
0.0008	81.0	162	1.3789	0.8281
0.0008	82.0	164	1.3844	0.8281
0.0008	83.0	166	1.3873	0.8281
0.0008	84.0	168	1.3885	0.8281
0.0002	85.0	170	1.3889	0.8281
0.0002	86.0	172	1.3889	0.8281
0.0002	87.0	174	1.3888	0.8281
0.0002	88.0	176	1.3888	0.8281
0.0002	89.0	178	1.3890	0.8281
0.0002	90.0	180	1.3893	0.8281
0.0002	91.0	182	1.3898	0.8281
0.0002	92.0	184	1.3905	0.8281
0.0002	93.0	186	1.3913	0.8281
0.0002	94.0	188	1.3927	0.8281
0.0002	95.0	190	1.3938	0.8281
0.0002	96.0	192	1.3947	0.8281
0.0002	97.0	194	1.3954	0.8281
0.0002	98.0	196	1.3960	0.8281
0.0002	99.0	198	1.3967	0.8281
0.0002	100.0	200	1.3975	0.8281
0.0002	101.0	202	1.3984	0.8281
0.0002	102.0	204	1.3993	0.8281
0.0002	103.0	206	1.4001	0.8281
0.0002	104.0	208	1.4008	0.8281
0.0001	105.0	210	1.4014	0.8281
0.0001	106.0	212	1.4020	0.8281
0.0001	107.0	214	1.4026	0.8281
0.0001	108.0	216	1.4030	0.8281
0.0001	109.0	218	1.4035	0.8281
0.0001	110.0	220	1.4040	0.8281
0.0001	111.0	222	1.4046	0.8281
0.0001	112.0	224	1.4051	0.8281
0.0001	113.0	226	1.4057	0.8281
0.0001	114.0	228	1.4064	0.8281
0.0001	115.0	230	1.4071	0.8281
0.0001	116.0	232	1.4078	0.8281
0.0001	117.0	234	1.4085	0.8281
0.0001	118.0	236	1.4092	0.8281
0.0001	119.0	238	1.4099	0.8281
0.0001	120.0	240	1.4106	0.8281
0.0001	121.0	242	1.4108	0.8281
0.0001	122.0	244	1.4081	0.8281
0.0001	123.0	246	1.4055	0.8281
0.0001	124.0	248	1.4032	0.8281
0.0001	125.0	250	1.4011	0.8281
0.0001	126.0	252	1.3995	0.8281
0.0001	127.0	254	1.3982	0.8281
0.0001	128.0	256	1.3973	0.8281
0.0001	129.0	258	1.3967	0.8281
0.0001	130.0	260	1.3963	0.8281
0.0001	131.0	262	1.3962	0.8281
0.0001	132.0	264	1.3962	0.8281
0.0001	133.0	266	1.3965	0.8281
0.0001	134.0	268	1.3970	0.8281
0.0001	135.0	270	1.3989	0.8281
0.0001	136.0	272	1.4012	0.8281
0.0001	137.0	274	1.4035	0.8281
0.0001	138.0	276	1.4052	0.8281
0.0001	139.0	278	1.4064	0.8281
0.0002	140.0	280	1.3703	0.8281
0.0002	141.0	282	1.2995	0.8438
0.0002	142.0	284	1.2572	0.8281
0.0002	143.0	286	1.2224	0.8281
0.0002	144.0	288	1.2120	0.8438
0.0001	145.0	290	1.2242	0.8281
0.0001	146.0	292	1.2377	0.8281
0.0001	147.0	294	1.2477	0.8281
0.0001	148.0	296	1.2542	0.8281
0.0001	149.0	298	1.2575	0.8281
0.0002	150.0	300	1.2575	0.8281

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.4.0
• Tokenizers 0.13.3