amazonPolarity_XLNET_5E

This model is a fine-tuned version of xlnet-base-cased on the amazon_polarity dataset. It achieves the following results on the evaluation set:

Loss: 0.4490
Accuracy: 0.9267

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: 3e-05
train_batch_size: 8
eval_batch_size: 8
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	Accuracy
0.6238	0.01	50	0.3703	0.86
0.3149	0.03	100	0.3715	0.9
0.3849	0.04	150	0.4125	0.8867
0.4051	0.05	200	0.4958	0.8933
0.3345	0.07	250	0.4258	0.9067
0.439	0.08	300	0.2650	0.9067
0.2248	0.09	350	0.3314	0.9267
0.2849	0.11	400	0.3097	0.8933
0.3468	0.12	450	0.3060	0.9067
0.3216	0.13	500	0.3826	0.9067
0.3462	0.15	550	0.2207	0.94
0.3632	0.16	600	0.1864	0.94
0.2483	0.17	650	0.3069	0.9267
0.3709	0.19	700	0.2859	0.9333
0.2953	0.2	750	0.3010	0.9333
0.3222	0.21	800	0.2668	0.9133
0.3142	0.23	850	0.3545	0.8667
0.2637	0.24	900	0.1922	0.9467
0.3929	0.25	950	0.2712	0.92
0.2918	0.27	1000	0.2516	0.9333
0.2269	0.28	1050	0.4227	0.8933
0.239	0.29	1100	0.3639	0.9133
0.2439	0.31	1150	0.3430	0.9133
0.2417	0.32	1200	0.2920	0.94
0.3223	0.33	1250	0.3426	0.9067
0.2775	0.35	1300	0.3752	0.8867
0.2733	0.36	1350	0.3015	0.9333
0.3737	0.37	1400	0.2875	0.9267
0.2907	0.39	1450	0.4926	0.8933
0.316	0.4	1500	0.2948	0.9333
0.2472	0.41	1550	0.4003	0.8933
0.2607	0.43	1600	0.3608	0.92
0.2848	0.44	1650	0.3332	0.9133
0.2708	0.45	1700	0.3424	0.92
0.3721	0.47	1750	0.2384	0.9267
0.2925	0.48	1800	0.4472	0.88
0.3619	0.49	1850	0.3824	0.9
0.1994	0.51	1900	0.4160	0.9133
0.3586	0.52	1950	0.3198	0.8867
0.2455	0.53	2000	0.3119	0.92
0.2683	0.55	2050	0.4262	0.8867
0.2983	0.56	2100	0.3552	0.9067
0.2973	0.57	2150	0.2966	0.8933
0.2299	0.59	2200	0.2972	0.92
0.295	0.6	2250	0.3122	0.9067
0.2716	0.61	2300	0.2556	0.9267
0.2842	0.63	2350	0.3317	0.92
0.2723	0.64	2400	0.4409	0.8933
0.2492	0.65	2450	0.3871	0.88
0.2297	0.67	2500	0.3526	0.9133
0.2125	0.68	2550	0.4597	0.9067
0.3003	0.69	2600	0.3374	0.8933
0.2622	0.71	2650	0.3492	0.9267
0.2436	0.72	2700	0.3438	0.9267
0.2599	0.73	2750	0.3725	0.9133
0.2759	0.75	2800	0.3260	0.9333
0.1841	0.76	2850	0.4218	0.9067
0.252	0.77	2900	0.2730	0.92
0.248	0.79	2950	0.3628	0.92
0.2356	0.8	3000	0.4012	0.9067
0.191	0.81	3050	0.3500	0.9267
0.2351	0.83	3100	0.4038	0.9133
0.2758	0.84	3150	0.3361	0.9067
0.2952	0.85	3200	0.2301	0.9267
0.2137	0.87	3250	0.3837	0.9133
0.2386	0.88	3300	0.2739	0.94
0.2786	0.89	3350	0.2820	0.9333
0.2284	0.91	3400	0.2557	0.9333
0.2546	0.92	3450	0.2744	0.9267
0.2514	0.93	3500	0.2908	0.94
0.3052	0.95	3550	0.2362	0.9333
0.2366	0.96	3600	0.3047	0.9333
0.2147	0.97	3650	0.3375	0.9333
0.3347	0.99	3700	0.2669	0.9267
0.3076	1.0	3750	0.2453	0.94
0.1685	1.01	3800	0.4117	0.9133
0.1954	1.03	3850	0.3074	0.9333
0.2512	1.04	3900	0.3942	0.9133
0.1365	1.05	3950	0.3211	0.92
0.1985	1.07	4000	0.4188	0.9133
0.1585	1.08	4050	0.4177	0.9133
0.1798	1.09	4100	0.3298	0.9333
0.1458	1.11	4150	0.5283	0.9
0.1831	1.12	4200	0.3884	0.92
0.1452	1.13	4250	0.4130	0.9133
0.1679	1.15	4300	0.3678	0.9267
0.1688	1.16	4350	0.3268	0.9333
0.1175	1.17	4400	0.4722	0.92
0.1661	1.19	4450	0.3899	0.9133
0.1688	1.2	4500	0.4050	0.9133
0.228	1.21	4550	0.4608	0.9
0.1946	1.23	4600	0.5080	0.9
0.1849	1.24	4650	0.4340	0.9067
0.1365	1.25	4700	0.4592	0.9133
0.2432	1.27	4750	0.3683	0.92
0.1679	1.28	4800	0.4604	0.9
0.2107	1.29	4850	0.3952	0.9
0.1499	1.31	4900	0.4275	0.92
0.1504	1.32	4950	0.3370	0.9333
0.1013	1.33	5000	0.3723	0.92
0.1303	1.35	5050	0.2925	0.9333
0.1205	1.36	5100	0.3452	0.9267
0.1427	1.37	5150	0.3080	0.94
0.1518	1.39	5200	0.3190	0.94
0.1885	1.4	5250	0.2726	0.9467
0.1264	1.41	5300	0.3466	0.9333
0.1939	1.43	5350	0.3957	0.9133
0.1939	1.44	5400	0.4007	0.9
0.1239	1.45	5450	0.2924	0.9333
0.1588	1.47	5500	0.2687	0.9333
0.1516	1.48	5550	0.3668	0.92
0.1623	1.49	5600	0.3141	0.94
0.2632	1.51	5650	0.2714	0.9333
0.1674	1.52	5700	0.3188	0.94
0.1854	1.53	5750	0.2818	0.9267
0.1282	1.55	5800	0.2918	0.9333
0.228	1.56	5850	0.2802	0.9133
0.2349	1.57	5900	0.1803	0.9467
0.1608	1.59	5950	0.3112	0.92
0.1493	1.6	6000	0.3018	0.9267
0.2182	1.61	6050	0.3419	0.9333
0.2408	1.63	6100	0.2887	0.9267
0.1872	1.64	6150	0.2408	0.9267
0.1246	1.65	6200	0.3752	0.9
0.2098	1.67	6250	0.2622	0.9333
0.1916	1.68	6300	0.2245	0.9467
0.2069	1.69	6350	0.2151	0.9467
0.1446	1.71	6400	0.2186	0.9533
0.1528	1.72	6450	0.1863	0.9533
0.1352	1.73	6500	0.2660	0.9467
0.2398	1.75	6550	0.1912	0.9533
0.1485	1.76	6600	0.2492	0.9467
0.2006	1.77	6650	0.2495	0.9267
0.2036	1.79	6700	0.3885	0.9067
0.1725	1.8	6750	0.2359	0.9533
0.1864	1.81	6800	0.2271	0.9533
0.1465	1.83	6850	0.2669	0.9333
0.197	1.84	6900	0.2290	0.96
0.1382	1.85	6950	0.2322	0.9467
0.1206	1.87	7000	0.3117	0.9333
0.157	1.88	7050	0.2163	0.9533
0.1686	1.89	7100	0.2239	0.9533
0.1953	1.91	7150	0.3064	0.9333
0.1638	1.92	7200	0.2821	0.9533
0.1605	1.93	7250	0.2413	0.9467
0.1736	1.95	7300	0.2430	0.94
0.2372	1.96	7350	0.2306	0.94
0.1549	1.97	7400	0.2730	0.94
0.1824	1.99	7450	0.3443	0.94
0.2263	2.0	7500	0.2695	0.9267
0.088	2.01	7550	0.2305	0.96
0.0376	2.03	7600	0.3380	0.94
0.072	2.04	7650	0.3349	0.9467
0.0491	2.05	7700	0.3397	0.94
0.0509	2.07	7750	0.3496	0.9467
0.1033	2.08	7800	0.3364	0.94
0.0549	2.09	7850	0.3520	0.94
0.0627	2.11	7900	0.4510	0.9267
0.0283	2.12	7950	0.3733	0.94
0.1215	2.13	8000	0.3892	0.9267
0.0856	2.15	8050	0.3114	0.9533
0.0945	2.16	8100	0.3626	0.9333
0.0901	2.17	8150	0.3116	0.94
0.0688	2.19	8200	0.3515	0.9267
0.1286	2.2	8250	0.3255	0.9333
0.1043	2.21	8300	0.4395	0.9133
0.1199	2.23	8350	0.3307	0.94
0.0608	2.24	8400	0.2992	0.9533
0.0827	2.25	8450	0.3500	0.94
0.047	2.27	8500	0.3982	0.94
0.1154	2.28	8550	0.3851	0.94
0.1158	2.29	8600	0.3820	0.9133
0.1053	2.31	8650	0.4414	0.92
0.1336	2.32	8700	0.3680	0.92
0.0853	2.33	8750	0.3732	0.9333
0.0496	2.35	8800	0.3450	0.94
0.0552	2.36	8850	0.4310	0.9267
0.1054	2.37	8900	0.4174	0.92
0.0951	2.39	8950	0.3815	0.9333
0.1235	2.4	9000	0.4119	0.9267
0.1094	2.41	9050	0.4282	0.9133
0.0897	2.43	9100	0.4766	0.9133
0.0925	2.44	9150	0.3303	0.94
0.1487	2.45	9200	0.2948	0.94
0.0963	2.47	9250	0.2911	0.94
0.0836	2.48	9300	0.3379	0.94
0.1594	2.49	9350	0.3841	0.9267
0.0846	2.51	9400	0.4128	0.9267
0.0984	2.52	9450	0.4131	0.9333
0.1042	2.53	9500	0.4048	0.9267
0.0633	2.55	9550	0.3776	0.94
0.1266	2.56	9600	0.3247	0.9333
0.1084	2.57	9650	0.3174	0.9467
0.0714	2.59	9700	0.3597	0.94
0.0826	2.6	9750	0.3261	0.9467
0.1527	2.61	9800	0.2531	0.9533
0.0506	2.63	9850	0.2994	0.9533
0.1043	2.64	9900	0.3345	0.9467
0.0229	2.65	9950	0.4318	0.9333
0.1247	2.67	10000	0.2951	0.9533
0.1285	2.68	10050	0.3036	0.9533
0.081	2.69	10100	0.3541	0.94
0.0829	2.71	10150	0.3757	0.9467
0.0702	2.72	10200	0.3307	0.9533
0.07	2.73	10250	0.3638	0.94
0.1563	2.75	10300	0.3283	0.94
0.1223	2.76	10350	0.3441	0.92
0.0954	2.77	10400	0.3049	0.94
0.0438	2.79	10450	0.3675	0.9467
0.0796	2.8	10500	0.3364	0.94
0.0803	2.81	10550	0.2970	0.94
0.0324	2.83	10600	0.3941	0.9267
0.083	2.84	10650	0.3439	0.94
0.1263	2.85	10700	0.3759	0.9267
0.1044	2.87	10750	1.0700	0.58
0.1182	2.88	10800	0.4409	0.9333
0.126	2.89	10850	0.6467	0.5933
0.094	2.91	10900	0.3741	0.9333
0.1405	2.92	10950	0.3458	0.9267
0.1024	2.93	11000	0.2946	0.9333
0.0812	2.95	11050	0.2850	0.9333
0.1132	2.96	11100	0.3093	0.9267
0.0775	2.97	11150	0.3938	0.9067
0.1179	2.99	11200	0.3528	0.9267
0.1413	3.0	11250	0.2984	0.9333
0.0528	3.01	11300	0.3387	0.9333
0.0214	3.03	11350	0.4108	0.92
0.0408	3.04	11400	0.4174	0.9267
0.0808	3.05	11450	0.4283	0.9267
0.0535	3.07	11500	0.3719	0.9333
0.0344	3.08	11550	0.4382	0.9333
0.0364	3.09	11600	0.4195	0.9333
0.0524	3.11	11650	0.4607	0.92
0.0682	3.12	11700	0.4503	0.92
0.0554	3.13	11750	0.4563	0.92
0.0401	3.15	11800	0.4668	0.9133
0.0782	3.16	11850	0.4468	0.9133
0.0605	3.17	11900	0.4239	0.92
0.0599	3.19	11950	0.4019	0.92
0.0364	3.2	12000	0.3988	0.9267
0.0357	3.21	12050	0.4168	0.9267
0.072	3.23	12100	0.3889	0.9333
0.0931	3.24	12150	0.3368	0.9333
0.0724	3.25	12200	0.3209	0.9333
0.0653	3.27	12250	0.3615	0.9333
0.0173	3.28	12300	0.3946	0.9333
0.0537	3.29	12350	0.3876	0.9333
0.0373	3.31	12400	0.4079	0.9267
0.0322	3.32	12450	0.3553	0.94
0.0585	3.33	12500	0.4276	0.92
0.0315	3.35	12550	0.4092	0.9267
0.0317	3.36	12600	0.4107	0.9267
0.082	3.37	12650	0.4170	0.9267
0.1101	3.39	12700	0.3801	0.9333
0.0392	3.4	12750	0.3802	0.9333
0.0382	3.41	12800	0.4194	0.9267
0.048	3.43	12850	0.3794	0.9333
0.0896	3.44	12900	0.3961	0.9267
0.0966	3.45	12950	0.3982	0.92
0.0165	3.47	13000	0.3819	0.92
0.0701	3.48	13050	0.3440	0.94
0.0104	3.49	13100	0.4132	0.9267
0.0991	3.51	13150	0.3477	0.9333
0.0554	3.52	13200	0.3255	0.94
0.0476	3.53	13250	0.4343	0.92
0.0213	3.55	13300	0.4601	0.92
0.0465	3.56	13350	0.4141	0.9267
0.1246	3.57	13400	0.3473	0.94
0.1112	3.59	13450	0.3679	0.92
0.0323	3.6	13500	0.3508	0.9267
0.0423	3.61	13550	0.3475	0.94
0.0498	3.63	13600	0.4095	0.92
0.0531	3.64	13650	0.3544	0.9333
0.0365	3.65	13700	0.4403	0.9133
0.058	3.67	13750	0.4284	0.9133
0.0191	3.68	13800	0.4466	0.92
0.0838	3.69	13850	0.5128	0.9067
0.1561	3.71	13900	0.3588	0.9267
0.0464	3.72	13950	0.3867	0.92
0.037	3.73	14000	0.3961	0.92
0.0288	3.75	14050	0.4274	0.92
0.0928	3.76	14100	0.3524	0.94
0.0696	3.77	14150	0.3555	0.9333
0.0318	3.79	14200	0.3457	0.9467
0.0417	3.8	14250	0.3412	0.94
0.0283	3.81	14300	0.3845	0.9333
0.058	3.83	14350	0.3765	0.9333
0.0589	3.84	14400	0.4085	0.9267
0.0432	3.85	14450	0.4103	0.9267
0.0365	3.87	14500	0.4000	0.9267
0.0858	3.88	14550	0.3905	0.9267
0.0494	3.89	14600	0.3739	0.9267
0.0503	3.91	14650	0.3203	0.94
0.0349	3.92	14700	0.3268	0.9467
0.0328	3.93	14750	0.3259	0.9467
0.0347	3.95	14800	0.3588	0.94
0.0233	3.96	14850	0.3456	0.9467
0.0602	3.97	14900	0.3819	0.94
0.0766	3.99	14950	0.3813	0.9333
0.0562	4.0	15000	0.3669	0.9333
0.0163	4.01	15050	0.4176	0.92
0.007	4.03	15100	0.3694	0.9333
0.0005	4.04	15150	0.3915	0.9333
0.021	4.05	15200	0.4334	0.9333
0.0823	4.07	15250	0.4155	0.9333
0.0509	4.08	15300	0.4056	0.9333
0.0381	4.09	15350	0.3729	0.94
0.045	4.11	15400	0.3940	0.9333
0.0379	4.12	15450	0.4276	0.9267
0.0661	4.13	15500	0.3797	0.94
0.0522	4.15	15550	0.4029	0.9333
0.0189	4.16	15600	0.4424	0.9267
0.0191	4.17	15650	0.4711	0.92
0.031	4.19	15700	0.4344	0.9333
0.0837	4.2	15750	0.3703	0.94
0.0397	4.21	15800	0.3976	0.9333
0.034	4.23	15850	0.4021	0.9333
0.0199	4.24	15900	0.4015	0.9333
0.0315	4.25	15950	0.3652	0.94
0.076	4.27	16000	0.3421	0.94
0.0478	4.28	16050	0.3122	0.9533
0.0203	4.29	16100	0.3436	0.9467
0.0706	4.31	16150	0.3544	0.94
0.0086	4.32	16200	0.3730	0.94
0.05	4.33	16250	0.3761	0.94
0.048	4.35	16300	0.3583	0.94
0.0715	4.36	16350	0.3459	0.94
0.0316	4.37	16400	0.3355	0.94
0.0356	4.39	16450	0.3278	0.9467
0.0176	4.4	16500	0.3177	0.9467
0.0817	4.41	16550	0.3705	0.9333
0.0414	4.43	16600	0.3919	0.9333
0.0198	4.44	16650	0.3435	0.9467
0.0203	4.45	16700	0.3708	0.94
0.0391	4.47	16750	0.3615	0.94
0.0132	4.48	16800	0.3827	0.94
0.0385	4.49	16850	0.3837	0.94
0.0366	4.51	16900	0.3633	0.94
0.0779	4.52	16950	0.3403	0.9467
0.0168	4.53	17000	0.4592	0.92
0.0517	4.55	17050	0.4063	0.9333
0.0138	4.56	17100	0.4335	0.9267
0.0123	4.57	17150	0.3777	0.9333
0.0324	4.59	17200	0.4657	0.92
0.0202	4.6	17250	0.4791	0.92
0.001	4.61	17300	0.4761	0.92
0.0364	4.63	17350	0.4663	0.92
0.0154	4.64	17400	0.4611	0.92
0.0184	4.65	17450	0.4616	0.92
0.0004	4.67	17500	0.4650	0.92
0.0192	4.68	17550	0.4649	0.92
0.0185	4.69	17600	0.4654	0.92
0.0196	4.71	17650	0.4643	0.92
0.0386	4.72	17700	0.4660	0.92
0.0236	4.73	17750	0.4499	0.9267
0.0383	4.75	17800	0.4479	0.9267
0.0398	4.76	17850	0.4483	0.9267
0.0004	4.77	17900	0.4541	0.9267
0.023	4.79	17950	0.4387	0.9267
0.0361	4.8	18000	0.4409	0.9267
0.0409	4.81	18050	0.4384	0.9267
0.0004	4.83	18100	0.4376	0.9267
0.0171	4.84	18150	0.4421	0.9267
0.0589	4.85	18200	0.4373	0.9267
0.0004	4.87	18250	0.4492	0.9267
0.0142	4.88	18300	0.4585	0.9267
0.0561	4.89	18350	0.4681	0.9267
0.0204	4.91	18400	0.4608	0.9267
0.0248	4.92	18450	0.4641	0.9267
0.0404	4.93	18500	0.4567	0.9267
0.0608	4.95	18550	0.4518	0.9267
0.0412	4.96	18600	0.4510	0.9267
0.0183	4.97	18650	0.4522	0.9267
0.0567	4.99	18700	0.4492	0.9267
0.0173	5.0	18750	0.4490	0.9267

Framework versions

Transformers 4.24.0
Pytorch 1.13.0
Datasets 2.6.1
Tokenizers 0.13.1

Etelis/amazonPolarity_XLNET_5E

amazonPolarity_XLNET_5E

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Seed this model