lge_tests_prelim

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

• Loss: 0.2067
• Accuracy: 0.75

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: 0.0002
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0	0	2.6254	0.0
2.6109	0.0064	100	2.6078	0.0
2.5713	0.0128	200	2.5687	0.0
2.5492	0.0192	300	2.5395	0.0
2.5191	0.0256	400	2.5052	0.0
2.4652	0.0320	500	2.4670	0.0
2.435	0.0384	600	2.4292	0.0
2.4039	0.0448	700	2.3940	0.0
2.3781	0.0512	800	2.3642	0.0
2.35	0.0576	900	2.3376	0.0
2.3129	0.0640	1000	2.3098	0.0
2.2849	0.0704	1100	2.2799	0.0
2.2505	0.0768	1200	2.2264	0.0
2.2202	0.0832	1300	2.1897	0.0
2.1454	0.0896	1400	2.1558	0.0
2.1293	0.0960	1500	2.1155	0.0
2.0727	0.1024	1600	2.0485	0.0
2.0048	0.1088	1700	1.9935	0.0
2.0274	0.1152	1800	1.9687	0.0
1.953	0.1216	1900	1.9447	0.0
1.8883	0.1280	2000	1.8772	0.0
1.8263	0.1344	2100	1.8623	0.0
1.7997	0.1408	2200	1.8072	0.005
1.7646	0.1472	2300	1.7725	0.0
1.7121	0.1536	2400	1.7096	0.0
1.6922	0.1600	2500	1.6917	0.015
1.6736	0.1664	2600	1.6496	0.0
1.6291	0.1728	2700	1.6183	0.035
1.5893	0.1792	2800	1.5810	0.005
1.5395	0.1856	2900	1.5429	0.035
1.5109	0.1920	3000	1.5153	0.075
1.4911	0.1984	3100	1.4899	0.07
1.4687	0.2048	3200	1.4783	0.065
1.4461	0.2112	3300	1.4396	0.075
1.3921	0.2176	3400	1.4007	0.075
1.3629	0.2240	3500	1.3684	0.1
1.3245	0.2304	3600	1.3432	0.075
1.3085	0.2368	3700	1.3058	0.195
1.3496	0.2432	3800	1.2990	0.055
1.2774	0.2496	3900	1.2640	0.095
1.2665	0.2560	4000	1.2677	0.06
1.1992	0.2625	4100	1.2062	0.215
1.2042	0.2689	4200	1.1900	0.21
1.1635	0.2753	4300	1.1518	0.26
1.1682	0.2817	4400	1.1399	0.18
1.1194	0.2881	4500	1.1299	0.225
1.1014	0.2945	4600	1.0991	0.225
1.0721	0.3009	4700	1.0832	0.215
1.052	0.3073	4800	1.0435	0.325
1.0626	0.3137	4900	1.0431	0.285
1.0336	0.3201	5000	1.0169	0.275
1.0364	0.3265	5100	1.0671	0.075
0.9757	0.3329	5200	0.9752	0.375
0.9877	0.3393	5300	0.9627	0.325
0.9792	0.3457	5400	0.9401	0.345
0.9266	0.3521	5500	0.9213	0.365
0.9113	0.3585	5600	0.8966	0.415
0.8876	0.3649	5700	0.8923	0.275
0.8558	0.3713	5800	0.8789	0.28
0.8659	0.3777	5900	0.8660	0.3
0.8328	0.3841	6000	0.8422	0.375
0.8317	0.3905	6100	0.8459	0.28
0.8277	0.3969	6200	0.8762	0.155
0.7851	0.4033	6300	0.7940	0.4
0.7875	0.4097	6400	0.7926	0.36
0.8502	0.4161	6500	0.7876	0.375
0.7762	0.4225	6600	0.8018	0.295
0.8015	0.4289	6700	0.7519	0.365
0.7489	0.4353	6800	0.7534	0.36
0.7517	0.4417	6900	0.7896	0.2
0.7989	0.4481	7000	0.7280	0.36
0.6945	0.4545	7100	0.7047	0.37
0.6574	0.4609	7200	0.6533	0.54
0.7302	0.4673	7300	0.7296	0.26
0.688	0.4737	7400	0.6556	0.395
0.6391	0.4801	7500	0.6475	0.415
0.6368	0.4865	7600	0.6306	0.355
0.6125	0.4929	7700	0.6164	0.395
0.5952	0.4993	7800	0.6018	0.42
0.5939	0.5057	7900	0.6027	0.365
0.5922	0.5121	8000	0.5569	0.545
0.5471	0.5185	8100	0.5585	0.38
0.5395	0.5249	8200	0.5676	0.42
0.5494	0.5313	8300	0.5726	0.345
0.5166	0.5377	8400	0.5164	0.49
0.5454	0.5441	8500	0.5302	0.455
0.5121	0.5505	8600	0.4883	0.54
0.5356	0.5569	8700	0.4843	0.515
0.4726	0.5633	8800	0.4832	0.465
0.472	0.5697	8900	0.5029	0.45
0.4606	0.5761	9000	0.4561	0.55
0.4735	0.5825	9100	0.4549	0.52
0.4721	0.5889	9200	0.4391	0.55
0.4607	0.5953	9300	0.4354	0.495
0.4426	0.6017	9400	0.4215	0.57
0.4074	0.6081	9500	0.4147	0.55
0.3937	0.6145	9600	0.3986	0.575
0.4057	0.6209	9700	0.3876	0.605
0.4043	0.6273	9800	0.3881	0.565
0.3691	0.6337	9900	0.3787	0.59
0.3728	0.6401	10000	0.3860	0.5
0.3425	0.6465	10100	0.3778	0.52
0.4213	0.6529	10200	0.4044	0.47
0.3457	0.6593	10300	0.3736	0.535
0.3617	0.6657	10400	0.3520	0.545
0.3519	0.6721	10500	0.3561	0.57
0.3314	0.6785	10600	0.3393	0.6
0.3375	0.6849	10700	0.3368	0.61
0.3132	0.6913	10800	0.3140	0.67
0.2988	0.6977	10900	0.3258	0.56
0.3196	0.7041	11000	0.3215	0.555
0.3012	0.7105	11100	0.2978	0.625
0.2984	0.7169	11200	0.3184	0.53
0.2854	0.7233	11300	0.2925	0.625
0.3007	0.7297	11400	0.3168	0.53
0.2954	0.7361	11500	0.2840	0.675
0.2899	0.7425	11600	0.2734	0.72
0.3006	0.7489	11700	0.2771	0.62
0.2949	0.7553	11800	0.2746	0.68
0.2557	0.7617	11900	0.2814	0.665
0.2523	0.7681	12000	0.2641	0.685
0.3054	0.7745	12100	0.2987	0.53
0.2678	0.7809	12200	0.2528	0.7
0.2506	0.7874	12300	0.2647	0.6
0.2438	0.7938	12400	0.2464	0.695
0.2442	0.8002	12500	0.2424	0.725
0.2717	0.8066	12600	0.2565	0.66
0.2423	0.8130	12700	0.2455	0.68
0.2391	0.8194	12800	0.2422	0.68
0.2348	0.8258	12900	0.2366	0.7
0.2267	0.8322	13000	0.2376	0.69
0.2277	0.8386	13100	0.2295	0.71
0.2094	0.8450	13200	0.2281	0.71
0.2433	0.8514	13300	0.2349	0.705
0.2364	0.8578	13400	0.2224	0.74
0.2148	0.8642	13500	0.2257	0.695
0.2102	0.8706	13600	0.2260	0.695
0.2252	0.8770	13700	0.2234	0.71
0.2031	0.8834	13800	0.2185	0.725
0.2133	0.8898	13900	0.2198	0.74
0.2204	0.8962	14000	0.2129	0.745
0.2215	0.9026	14100	0.2151	0.755
0.1938	0.9090	14200	0.2142	0.73
0.2088	0.9154	14300	0.2135	0.73
0.202	0.9218	14400	0.2138	0.71
0.202	0.9282	14500	0.2096	0.75
0.2003	0.9346	14600	0.2104	0.745
0.1985	0.9410	14700	0.2106	0.725
0.2097	0.9474	14800	0.2071	0.745
0.2058	0.9538	14900	0.2070	0.775
0.2163	0.9602	15000	0.2080	0.755
0.2123	0.9666	15100	0.2067	0.755
0.2151	0.9730	15200	0.2082	0.74
0.1888	0.9794	15300	0.2069	0.75
0.2026	0.9858	15400	0.2069	0.75
0.1918	0.9922	15500	0.2065	0.75
0.1987	0.9986	15600	0.2067	0.75

Framework versions

• Transformers 4.46.0
• Pytorch 2.5.1
• Datasets 3.1.0
• Tokenizers 0.20.1