best_model-yelp_polarity-64-42

This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6069
• Accuracy: 0.9375

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	4	0.7342	0.9219
No log	2.0	8	0.7290	0.9219
0.5102	3.0	12	0.7270	0.9219
0.5102	4.0	16	0.7253	0.9219
0.4089	5.0	20	0.7208	0.9219
0.4089	6.0	24	0.7191	0.9219
0.4089	7.0	28	0.7271	0.9297
0.3981	8.0	32	0.7192	0.9297
0.3981	9.0	36	0.7009	0.9219
0.1982	10.0	40	0.6963	0.9141
0.1982	11.0	44	0.6904	0.9219
0.1982	12.0	48	0.6924	0.9219
0.2128	13.0	52	0.6921	0.9297
0.2128	14.0	56	0.6866	0.9219
0.0935	15.0	60	0.6841	0.9219
0.0935	16.0	64	0.6494	0.9219
0.0935	17.0	68	0.6201	0.9219
0.0365	18.0	72	0.6122	0.9219
0.0365	19.0	76	0.6047	0.9219
0.026	20.0	80	0.5870	0.9219
0.026	21.0	84	0.5739	0.9219
0.026	22.0	88	0.5737	0.9219
0.0139	23.0	92	0.5677	0.9219
0.0139	24.0	96	0.5579	0.9219
0.0149	25.0	100	0.5468	0.9219
0.0149	26.0	104	0.5277	0.9219
0.0149	27.0	108	0.5168	0.9219
0.0085	28.0	112	0.5036	0.9141
0.0085	29.0	116	0.4960	0.9141
0.0	30.0	120	0.4941	0.9219
0.0	31.0	124	0.4956	0.9297
0.0	32.0	128	0.4987	0.9297
0.0	33.0	132	0.5018	0.9297
0.0	34.0	136	0.5053	0.9297
0.0	35.0	140	0.5081	0.9297
0.0	36.0	144	0.5107	0.9297
0.0	37.0	148	0.5125	0.9297
0.0	38.0	152	0.5135	0.9297
0.0	39.0	156	0.5146	0.9297
0.0	40.0	160	0.5157	0.9297
0.0	41.0	164	0.5168	0.9297
0.0	42.0	168	0.5182	0.9297
0.0	43.0	172	0.5197	0.9297
0.0	44.0	176	0.5209	0.9297
0.0	45.0	180	0.5224	0.9297
0.0	46.0	184	0.5240	0.9297
0.0	47.0	188	0.5257	0.9297
0.0	48.0	192	0.5272	0.9297
0.0	49.0	196	0.5286	0.9297
0.0	50.0	200	0.5300	0.9297
0.0	51.0	204	0.5313	0.9297
0.0	52.0	208	0.5329	0.9297
0.0	53.0	212	0.5343	0.9297
0.0	54.0	216	0.5355	0.9297
0.0	55.0	220	0.5369	0.9297
0.0	56.0	224	0.5382	0.9297
0.0	57.0	228	0.5395	0.9297
0.0	58.0	232	0.5407	0.9297
0.0	59.0	236	0.5419	0.9297
0.0	60.0	240	0.5431	0.9297
0.0	61.0	244	0.5444	0.9297
0.0	62.0	248	0.5455	0.9297
0.0	63.0	252	0.5466	0.9297
0.0	64.0	256	0.5478	0.9297
0.0	65.0	260	0.5489	0.9297
0.0	66.0	264	0.5501	0.9297
0.0	67.0	268	0.5513	0.9297
0.0	68.0	272	0.5524	0.9297
0.0	69.0	276	0.5535	0.9297
0.0	70.0	280	0.5548	0.9297
0.0	71.0	284	0.5559	0.9297
0.0	72.0	288	0.5570	0.9297
0.0	73.0	292	0.5581	0.9297
0.0	74.0	296	0.5592	0.9297
0.0	75.0	300	0.5601	0.9297
0.0	76.0	304	0.5610	0.9297
0.0	77.0	308	0.5620	0.9297
0.0	78.0	312	0.5630	0.9297
0.0	79.0	316	0.5640	0.9297
0.0	80.0	320	0.5648	0.9297
0.0	81.0	324	0.5658	0.9297
0.0	82.0	328	0.5667	0.9297
0.0	83.0	332	0.5675	0.9297
0.0	84.0	336	0.5684	0.9297
0.0	85.0	340	0.5693	0.9297
0.0	86.0	344	0.5701	0.9297
0.0	87.0	348	0.5710	0.9297
0.0	88.0	352	0.5719	0.9297
0.0	89.0	356	0.5728	0.9297
0.0	90.0	360	0.5736	0.9297
0.0	91.0	364	0.5745	0.9297
0.0	92.0	368	0.5754	0.9297
0.0	93.0	372	0.5762	0.9297
0.0	94.0	376	0.5771	0.9297
0.0	95.0	380	0.5779	0.9297
0.0	96.0	384	0.5788	0.9297
0.0	97.0	388	0.5796	0.9297
0.0	98.0	392	0.5804	0.9297
0.0	99.0	396	0.5812	0.9297
0.0	100.0	400	0.5820	0.9297
0.0	101.0	404	0.5828	0.9297
0.0	102.0	408	0.5836	0.9297
0.0	103.0	412	0.5843	0.9297
0.0	104.0	416	0.5851	0.9297
0.0	105.0	420	0.5859	0.9297
0.0	106.0	424	0.5866	0.9297
0.0	107.0	428	0.5874	0.9297
0.0	108.0	432	0.5881	0.9297
0.0	109.0	436	0.5889	0.9297
0.0	110.0	440	0.5896	0.9297
0.0	111.0	444	0.5902	0.9297
0.0	112.0	448	0.5910	0.9375
0.0	113.0	452	0.5916	0.9375
0.0	114.0	456	0.5924	0.9375
0.0	115.0	460	0.5931	0.9375
0.0	116.0	464	0.5938	0.9375
0.0	117.0	468	0.5945	0.9375
0.0	118.0	472	0.5952	0.9375
0.0	119.0	476	0.5958	0.9375
0.0	120.0	480	0.5964	0.9375
0.0	121.0	484	0.5971	0.9375
0.0	122.0	488	0.5978	0.9375
0.0	123.0	492	0.5985	0.9375
0.0	124.0	496	0.5991	0.9375
0.0	125.0	500	0.5997	0.9375
0.0	126.0	504	0.6004	0.9375
0.0	127.0	508	0.6009	0.9375
0.0	128.0	512	0.6015	0.9375
0.0	129.0	516	0.6020	0.9375
0.0	130.0	520	0.6025	0.9375
0.0	131.0	524	0.6029	0.9375
0.0	132.0	528	0.6034	0.9375
0.0	133.0	532	0.6038	0.9375
0.0	134.0	536	0.6042	0.9375
0.0	135.0	540	0.6045	0.9375
0.0	136.0	544	0.6048	0.9375
0.0	137.0	548	0.6051	0.9375
0.0	138.0	552	0.6054	0.9375
0.0	139.0	556	0.6056	0.9375
0.0	140.0	560	0.6058	0.9375
0.0	141.0	564	0.6061	0.9375
0.0	142.0	568	0.6062	0.9375
0.0	143.0	572	0.6064	0.9375
0.0	144.0	576	0.6065	0.9375
0.0	145.0	580	0.6066	0.9375
0.0	146.0	584	0.6067	0.9375
0.0	147.0	588	0.6068	0.9375
0.0	148.0	592	0.6068	0.9375
0.0	149.0	596	0.6069	0.9375
0.0	150.0	600	0.6069	0.9375

Framework versions

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