v0_mistral_lora_batch8

This model is a fine-tuned version of peiyi9979/math-shepherd-mistral-7b-prm on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4561
• Accuracy: 0.7885
• Precision: 0.6945
• Recall: 0.3611
• F1: 0.4751

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: 2.5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 32
• optimizer: Use 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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.7133	0.0054	5	0.7176	0.4580	0.2666	0.5969	0.3686
0.7149	0.0109	10	0.7167	0.4631	0.2680	0.5924	0.3691
0.7031	0.0163	15	0.7145	0.4672	0.2680	0.5834	0.3673
0.6996	0.0217	20	0.7116	0.4730	0.2673	0.5673	0.3634
0.7065	0.0271	25	0.7079	0.4838	0.2694	0.5535	0.3624
0.7025	0.0326	30	0.7021	0.4982	0.2718	0.5320	0.3598
0.6965	0.0380	35	0.6945	0.5206	0.2736	0.4886	0.3508
0.6836	0.0434	40	0.6843	0.5449	0.2737	0.4336	0.3356
0.6657	0.0488	45	0.6727	0.5748	0.2765	0.3736	0.3178
0.6456	0.0543	50	0.6597	0.6089	0.2795	0.3011	0.2899
0.633	0.0597	55	0.6458	0.6456	0.2900	0.2327	0.2582
0.6917	0.0651	60	0.6316	0.6768	0.3080	0.1758	0.2239
0.6715	0.0705	65	0.6190	0.6965	0.3081	0.1163	0.1689
0.6556	0.0760	70	0.6091	0.7096	0.3204	0.0850	0.1344
0.6629	0.0814	75	0.6018	0.7165	0.3235	0.0635	0.1062
0.5698	0.0868	80	0.5964	0.7227	0.3541	0.0559	0.0966
0.573	0.0922	85	0.5919	0.7259	0.3652	0.0461	0.0818
0.6451	0.0977	90	0.5885	0.7267	0.3519	0.0367	0.0665
0.5387	0.1031	95	0.5859	0.7299	0.3807	0.0300	0.0556
0.5793	0.1085	100	0.5844	0.7305	0.3806	0.0264	0.0494
0.6536	0.1139	105	0.5823	0.7302	0.3851	0.0300	0.0556
0.6614	0.1194	110	0.5821	0.7295	0.3789	0.0322	0.0594
0.5592	0.1248	115	0.5822	0.7290	0.375	0.0336	0.0616
0.557	0.1302	120	0.5811	0.7292	0.3824	0.0349	0.0640
0.5654	0.1356	125	0.5798	0.7298	0.3897	0.0340	0.0626
0.5963	0.1411	130	0.5809	0.7292	0.3929	0.0394	0.0716
0.6295	0.1465	135	0.5791	0.7302	0.4010	0.0362	0.0665
0.6703	0.1519	140	0.5744	0.7325	0.4107	0.0206	0.0392
0.5978	0.1574	145	0.5730	0.7334	0.3934	0.0107	0.0209
0.5869	0.1628	150	0.5721	0.7336	0.4127	0.0116	0.0226
0.6086	0.1682	155	0.5725	0.7336	0.4382	0.0174	0.0336
0.6421	0.1736	160	0.5787	0.7308	0.4314	0.0492	0.0884
0.6386	0.1791	165	0.5776	0.7292	0.4259	0.0617	0.1079
0.7036	0.1845	170	0.5709	0.7306	0.4348	0.0537	0.0956
0.5139	0.1899	175	0.5675	0.7309	0.4267	0.0443	0.0803
0.5911	0.1953	180	0.5658	0.7321	0.4375	0.0376	0.0692
0.5792	0.2008	185	0.5663	0.7317	0.4462	0.0501	0.0901
0.5127	0.2062	190	0.5657	0.7318	0.4522	0.0550	0.0981
0.5224	0.2116	195	0.5669	0.7328	0.4664	0.0559	0.0999
0.6026	0.2170	200	0.5621	0.7359	0.5260	0.0362	0.0678
0.605	0.2225	205	0.5614	0.7367	0.5664	0.0286	0.0545
0.66	0.2279	210	0.5631	0.7335	0.4773	0.0564	0.1008
0.6215	0.2333	215	0.5653	0.7322	0.4681	0.0756	0.1302
0.5474	0.2387	220	0.5681	0.7322	0.4744	0.0953	0.1587
0.5773	0.2442	225	0.5654	0.7330	0.4825	0.0984	0.1635
0.5398	0.2496	230	0.5696	0.7308	0.4711	0.1275	0.2007
0.5985	0.2550	235	0.5659	0.7308	0.4684	0.1159	0.1858
0.5055	0.2604	240	0.5582	0.7344	0.4949	0.0877	0.1490
0.5527	0.2659	245	0.5544	0.7373	0.5365	0.0658	0.1172
0.566	0.2713	250	0.5544	0.7379	0.5510	0.0604	0.1089
0.4956	0.2767	255	0.5616	0.7373	0.5278	0.0850	0.1464
0.5447	0.2821	260	0.5653	0.7336	0.4891	0.1105	0.1803
0.6067	0.2876	265	0.5538	0.7376	0.5356	0.0774	0.1353
0.4665	0.2930	270	0.5530	0.7385	0.5765	0.0506	0.0930
0.5816	0.2984	275	0.5496	0.7407	0.5836	0.0765	0.1353
0.6179	0.3039	280	0.5518	0.7389	0.5379	0.1078	0.1796
0.5686	0.3093	285	0.5473	0.7402	0.5768	0.0756	0.1337
0.5387	0.3147	290	0.5513	0.7417	0.6887	0.0465	0.0872
0.4715	0.3201	295	0.5444	0.7455	0.6240	0.1002	0.1727
0.6593	0.3256	300	0.5505	0.7458	0.5868	0.1391	0.2250
0.5704	0.3310	305	0.5408	0.7475	0.6506	0.1025	0.1770
0.6698	0.3364	310	0.5380	0.7453	0.6549	0.0832	0.1477
0.5405	0.3418	315	0.5380	0.7484	0.6344	0.1204	0.2023
0.6369	0.3473	320	0.5373	0.7504	0.6202	0.1512	0.2432
0.6279	0.3527	325	0.5393	0.7510	0.5988	0.1843	0.2819
0.5781	0.3581	330	0.5343	0.7517	0.6511	0.1369	0.2262
0.7693	0.3635	335	0.5317	0.7547	0.6993	0.1311	0.2208
0.5138	0.3690	340	0.5335	0.7551	0.6345	0.1794	0.2797
0.5736	0.3744	345	0.5425	0.7490	0.5600	0.2483	0.3441
0.6249	0.3798	350	0.5425	0.7499	0.5589	0.2676	0.3619
0.6678	0.3852	355	0.5348	0.7547	0.6048	0.2157	0.3179
0.5652	0.3907	360	0.5298	0.7561	0.6525	0.1714	0.2714
0.5489	0.3961	365	0.5289	0.7554	0.6248	0.1937	0.2958
0.5557	0.4015	370	0.5274	0.7572	0.6331	0.2	0.3040
0.5696	0.4069	375	0.5254	0.7598	0.6411	0.2134	0.3202
0.5106	0.4124	380	0.5243	0.7591	0.6409	0.2076	0.3136
0.6313	0.4178	385	0.5234	0.7612	0.6642	0.2009	0.3085
0.6376	0.4232	390	0.5263	0.7574	0.5962	0.2635	0.3655
0.4679	0.4286	395	0.5300	0.7564	0.5845	0.2801	0.3787
0.4335	0.4341	400	0.5216	0.7619	0.6652	0.2054	0.3138
0.5813	0.4395	405	0.5229	0.7621	0.6850	0.1897	0.2971
0.6103	0.4449	410	0.5303	0.7519	0.5630	0.2859	0.3792
0.5488	0.4504	415	0.5399	0.7466	0.5370	0.3213	0.4020
0.5357	0.4558	420	0.5172	0.7627	0.6762	0.2009	0.3098
0.5744	0.4612	425	0.5160	0.7629	0.7489	0.1588	0.2621
0.5674	0.4666	430	0.5140	0.7655	0.7279	0.1843	0.2942
0.4955	0.4721	435	0.5179	0.7638	0.6521	0.2340	0.3444
0.6084	0.4775	440	0.5138	0.7654	0.6561	0.2416	0.3532
0.4945	0.4829	445	0.5154	0.7644	0.6210	0.2859	0.3915
0.577	0.4883	450	0.5144	0.7643	0.6097	0.3083	0.4095
0.6142	0.4938	455	0.5122	0.7667	0.6304	0.2899	0.3972
0.5128	0.4992	460	0.5069	0.7679	0.6868	0.2286	0.3431
0.465	0.5046	465	0.5046	0.7693	0.7042	0.2237	0.3396
0.5021	0.5100	470	0.5053	0.7681	0.6695	0.2474	0.3613
0.3761	0.5155	475	0.5041	0.7693	0.6908	0.2349	0.3506
0.6094	0.5209	480	0.5039	0.7699	0.7462	0.2	0.3155
0.4426	0.5263	485	0.5031	0.7701	0.7155	0.2206	0.3372
0.5076	0.5317	490	0.5025	0.7676	0.6429	0.2779	0.3880
0.4563	0.5372	495	0.5084	0.7618	0.5953	0.3172	0.4139
0.4412	0.5426	500	0.5009	0.7711	0.6767	0.2613	0.3770
0.5029	0.5480	505	0.5019	0.7694	0.6448	0.2899	0.4
0.4427	0.5534	510	0.5151	0.7595	0.5726	0.3651	0.4459
0.6357	0.5589	515	0.5075	0.7614	0.5881	0.3329	0.4251
0.5216	0.5643	520	0.5055	0.7652	0.6069	0.3239	0.4224
0.4494	0.5697	525	0.5046	0.7704	0.7221	0.2174	0.3343
0.4227	0.5751	530	0.5006	0.7712	0.6880	0.2506	0.3673
0.5916	0.5806	535	0.5206	0.7504	0.5433	0.3673	0.4383
0.4983	0.5860	540	0.5124	0.7586	0.5719	0.3557	0.4386
0.5794	0.5914	545	0.5025	0.7688	0.6897	0.2327	0.3479
0.7319	0.5969	550	0.4989	0.7659	0.6283	0.2859	0.3930
0.4717	0.6023	555	0.5048	0.7597	0.5743	0.3615	0.4437
0.5232	0.6077	560	0.4963	0.7671	0.6215	0.3101	0.4137
0.7354	0.6131	565	0.4977	0.7711	0.6835	0.2541	0.3705
0.5752	0.6186	570	0.4981	0.7663	0.6061	0.3387	0.4346
0.6172	0.6240	575	0.4993	0.7637	0.5903	0.3553	0.4436
0.5781	0.6294	580	0.4976	0.7633	0.5841	0.3714	0.4540
0.4338	0.6348	585	0.4931	0.7686	0.6199	0.3284	0.4294
0.405	0.6403	590	0.4968	0.7748	0.7176	0.2479	0.3685
0.563	0.6457	595	0.4934	0.7723	0.6528	0.3011	0.4121
0.4531	0.6511	600	0.5103	0.7635	0.5830	0.3785	0.4590
0.4971	0.6565	605	0.4953	0.7736	0.6698	0.2877	0.4025
0.6782	0.6620	610	0.4928	0.7749	0.7370	0.2345	0.3557
0.4925	0.6674	615	0.4928	0.7722	0.6784	0.2671	0.3833
0.6392	0.6728	620	0.4885	0.7716	0.6588	0.2868	0.3996
0.4689	0.6782	625	0.4860	0.7732	0.6746	0.2792	0.3949
0.4968	0.6837	630	0.4869	0.7697	0.6360	0.3065	0.4136
0.5046	0.6891	635	0.4859	0.7723	0.6537	0.2998	0.4110
0.5538	0.6945	640	0.4875	0.7724	0.6447	0.3150	0.4232
0.4675	0.6999	645	0.4857	0.7740	0.6551	0.3119	0.4226
0.4654	0.7054	650	0.4853	0.7756	0.7174	0.2532	0.3743
0.5262	0.7108	655	0.4873	0.7681	0.6104	0.3463	0.4419
0.4566	0.7162	660	0.4969	0.7584	0.5610	0.4076	0.4721
0.5038	0.7216	665	0.4823	0.7761	0.6828	0.2899	0.4070
0.5881	0.7271	670	0.4838	0.7768	0.6904	0.2864	0.4048
0.5963	0.7325	675	0.4846	0.7745	0.6532	0.3186	0.4283
0.6296	0.7379	680	0.4844	0.7752	0.6537	0.3235	0.4328
0.4304	0.7434	685	0.4849	0.7810	0.7440	0.2653	0.3912
0.426	0.7488	690	0.4835	0.7797	0.7086	0.2872	0.4088
0.6854	0.7542	695	0.4858	0.7758	0.6570	0.3230	0.4331
0.4642	0.7596	700	0.4828	0.7786	0.6720	0.3217	0.4351
0.4785	0.7651	705	0.4799	0.7778	0.6750	0.3123	0.4270
0.5718	0.7705	710	0.4796	0.7765	0.6571	0.3284	0.4379
0.4136	0.7759	715	0.4801	0.7757	0.6610	0.3159	0.4275
0.4833	0.7813	720	0.4851	0.7718	0.6239	0.3503	0.4487
0.4986	0.7868	725	0.5012	0.7624	0.5729	0.4081	0.4766
0.4768	0.7922	730	0.4935	0.7716	0.6186	0.3606	0.4556
0.4468	0.7976	735	0.4880	0.7749	0.7785	0.2107	0.3317
0.6234	0.8030	740	0.4887	0.7750	0.7894	0.2063	0.3271
0.509	0.8085	745	0.4901	0.7716	0.6235	0.3490	0.4475
0.5037	0.8139	750	0.5225	0.7470	0.5244	0.4908	0.5070
0.5635	0.8193	755	0.4976	0.7641	0.5753	0.4206	0.4859
0.4618	0.8247	760	0.4773	0.7835	0.7253	0.2953	0.4197
0.557	0.8302	765	0.4790	0.7832	0.7822	0.2523	0.3816
0.55	0.8356	770	0.4788	0.7821	0.7192	0.2922	0.4155
0.4587	0.8410	775	0.4845	0.7708	0.6091	0.3785	0.4669
0.5118	0.8464	780	0.4801	0.7744	0.6243	0.3740	0.4678
0.4716	0.8519	785	0.4808	0.7726	0.6144	0.3821	0.4712
0.5481	0.8573	790	0.4849	0.7644	0.5787	0.4094	0.4796
0.5619	0.8627	795	0.4804	0.7708	0.6086	0.3799	0.4678
0.5896	0.8681	800	0.4780	0.7762	0.6436	0.3490	0.4526
0.4955	0.8736	805	0.4870	0.7694	0.5978	0.3978	0.4777
0.5305	0.8790	810	0.4838	0.7719	0.6121	0.3812	0.4698
0.4659	0.8844	815	0.4762	0.7808	0.6770	0.3311	0.4447
0.5003	0.8899	820	0.4778	0.7797	0.6567	0.3544	0.4603
0.527	0.8953	825	0.4766	0.7822	0.7752	0.2515	0.3797
0.4833	0.9007	830	0.4757	0.7824	0.7646	0.2586	0.3865
0.3969	0.9061	835	0.4739	0.7826	0.7094	0.3047	0.4263
0.4587	0.9116	840	0.4738	0.7829	0.7199	0.2966	0.4202
0.4181	0.9170	845	0.4743	0.7807	0.7019	0.3002	0.4206
0.4802	0.9224	850	0.4797	0.7736	0.6349	0.3432	0.4455
0.4451	0.9278	855	0.4773	0.7777	0.6574	0.3374	0.4459
0.4468	0.9333	860	0.4758	0.7783	0.6664	0.3280	0.4396
0.4387	0.9387	865	0.4762	0.7786	0.7175	0.2716	0.3940
0.4369	0.9441	870	0.4723	0.7781	0.6695	0.3217	0.4346
0.4826	0.9495	875	0.4768	0.7706	0.6061	0.3848	0.4707
0.545	0.9550	880	0.4735	0.7755	0.6299	0.3709	0.4669
0.5462	0.9604	885	0.4804	0.7698	0.5957	0.4094	0.4853
0.5456	0.9658	890	0.4861	0.7660	0.5807	0.4219	0.4887
0.5797	0.9712	895	0.4827	0.7676	0.5869	0.4170	0.4876
0.4881	0.9767	900	0.4730	0.7778	0.6628	0.3298	0.4404
0.5739	0.9821	905	0.4744	0.7821	0.7772	0.2497	0.3779
0.5551	0.9875	910	0.4738	0.7813	0.7137	0.2922	0.4146
0.3974	0.9929	915	0.4782	0.7750	0.6404	0.3450	0.4484
0.4537	0.9984	920	0.4724	0.7800	0.6820	0.3186	0.4343
0.5169	1.0038	925	0.4728	0.7803	0.6826	0.3204	0.4361
0.501	1.0092	930	0.4760	0.7752	0.6378	0.3521	0.4537
0.5022	1.0147	935	0.4770	0.7742	0.6255	0.3691	0.4643
0.4872	1.0201	940	0.4774	0.7738	0.6228	0.3723	0.4660
0.4887	1.0255	945	0.4716	0.7794	0.6697	0.3311	0.4431
0.7189	1.0309	950	0.4695	0.7829	0.7346	0.2837	0.4093
0.5526	1.0364	955	0.4738	0.7771	0.6498	0.3454	0.4511
0.5607	1.0418	960	0.4783	0.7736	0.6254	0.3638	0.4600
0.4735	1.0472	965	0.4890	0.7656	0.5812	0.4148	0.4841
0.4889	1.0526	970	0.4883	0.7663	0.5817	0.4219	0.4891
0.5013	1.0581	975	0.4712	0.7767	0.6621	0.3217	0.4330
0.5881	1.0635	980	0.4696	0.7782	0.6760	0.3136	0.4285
0.5009	1.0689	985	0.4707	0.7769	0.6536	0.3369	0.4446
0.5022	1.0743	990	0.4730	0.7764	0.6476	0.3436	0.4490
0.5214	1.0798	995	0.4717	0.7776	0.6528	0.3441	0.4506
0.4922	1.0852	1000	0.4668	0.7826	0.7295	0.2859	0.4108
0.4946	1.0906	1005	0.4671	0.7819	0.7050	0.3047	0.4255
0.4006	1.0960	1010	0.4723	0.7746	0.6175	0.3937	0.4809
0.471	1.1015	1015	0.4879	0.7582	0.5498	0.4841	0.5149
0.4273	1.1069	1020	0.4704	0.7754	0.6159	0.4054	0.4889
0.4815	1.1123	1025	0.4720	0.7818	0.7400	0.2725	0.3983
0.4919	1.1177	1030	0.4684	0.7819	0.7084	0.3011	0.4226
0.4011	1.1232	1035	0.4710	0.7774	0.6330	0.3812	0.4758
0.4243	1.1286	1040	0.4727	0.7778	0.6363	0.3781	0.4743
0.4581	1.1340	1045	0.4685	0.7797	0.6655	0.3400	0.4501
0.445	1.1394	1050	0.4648	0.7847	0.7530	0.2796	0.4078
0.496	1.1449	1055	0.4655	0.7837	0.7729	0.2604	0.3896
0.4797	1.1503	1060	0.4686	0.7806	0.6768	0.3298	0.4434
0.4825	1.1557	1065	0.4855	0.7680	0.5899	0.4094	0.4834
0.4453	1.1612	1070	0.4709	0.7782	0.6468	0.3597	0.4623
0.6114	1.1666	1075	0.4660	0.7838	0.7150	0.3065	0.4291
0.4965	1.1720	1080	0.4654	0.7852	0.7482	0.2859	0.4137
0.4957	1.1774	1085	0.4679	0.7815	0.6631	0.3575	0.4645
0.5131	1.1829	1090	0.4799	0.7673	0.5798	0.4438	0.5028
0.459	1.1883	1095	0.4781	0.7681	0.5809	0.4497	0.5069
0.414	1.1937	1100	0.4680	0.7783	0.6360	0.3830	0.4781
0.4745	1.1991	1105	0.4653	0.7828	0.7117	0.3038	0.4258
0.4272	1.2046	1110	0.4657	0.7846	0.7325	0.2953	0.4209
0.5231	1.2100	1115	0.4672	0.7837	0.7021	0.3195	0.4391
0.4883	1.2154	1120	0.4720	0.7786	0.6506	0.3557	0.4599
0.4738	1.2208	1125	0.4705	0.7788	0.6516	0.3557	0.4602
0.5561	1.2263	1130	0.4656	0.7822	0.6721	0.3485	0.4590
0.5488	1.2317	1135	0.4657	0.7806	0.6587	0.3575	0.4635
0.4728	1.2371	1140	0.4702	0.7755	0.6246	0.3834	0.4752
0.4644	1.2425	1145	0.4666	0.7802	0.6705	0.3360	0.4477
0.4159	1.2480	1150	0.4658	0.7838	0.7336	0.2895	0.4151
0.5057	1.2534	1155	0.4640	0.7840	0.7138	0.3092	0.4315
0.5188	1.2588	1160	0.4701	0.7791	0.6470	0.3673	0.4686
0.561	1.2642	1165	0.4762	0.7743	0.6086	0.4161	0.4943
0.4715	1.2697	1170	0.4809	0.7714	0.5879	0.4609	0.5167
0.432	1.2751	1175	0.4706	0.7774	0.6155	0.4268	0.5041
0.4911	1.2805	1180	0.4625	0.7867	0.6866	0.3597	0.4721
0.5408	1.2859	1185	0.4623	0.7859	0.6913	0.3477	0.4626
0.3171	1.2914	1190	0.4632	0.7832	0.6527	0.3893	0.4877
0.4122	1.2968	1195	0.4626	0.7840	0.6583	0.3852	0.4860
0.5293	1.3022	1200	0.4605	0.7854	0.6827	0.3562	0.4681
0.4583	1.3077	1205	0.4653	0.7789	0.6226	0.4215	0.5027
0.4013	1.3131	1210	0.4689	0.7749	0.5999	0.4528	0.5161
0.5588	1.3185	1215	0.4661	0.7801	0.6241	0.4286	0.5082
0.5086	1.3239	1220	0.4614	0.7854	0.6699	0.3758	0.4815
0.404	1.3294	1225	0.4614	0.7846	0.6667	0.3749	0.4800
0.5662	1.3348	1230	0.4645	0.7818	0.6341	0.4179	0.5038
0.4344	1.3402	1235	0.4666	0.7781	0.6155	0.4340	0.5091
0.4496	1.3456	1240	0.4616	0.7837	0.6526	0.3933	0.4908
0.4512	1.3511	1245	0.4620	0.7841	0.6564	0.3897	0.4891
0.4258	1.3565	1250	0.4625	0.7828	0.6517	0.3884	0.4867
0.4792	1.3619	1255	0.4600	0.7854	0.6898	0.3463	0.4611
0.4307	1.3673	1260	0.4601	0.7859	0.6962	0.3414	0.4581
0.5315	1.3728	1265	0.4591	0.7876	0.7106	0.3351	0.4555
0.5734	1.3782	1270	0.4588	0.7879	0.7155	0.3320	0.4535
0.4071	1.3836	1275	0.4601	0.7876	0.7056	0.3409	0.4597
0.503	1.3890	1280	0.4617	0.7861	0.6765	0.3705	0.4788
0.4997	1.3945	1285	0.4654	0.7820	0.6387	0.4089	0.4986
0.453	1.3999	1290	0.4753	0.7706	0.5849	0.4640	0.5175
0.4052	1.4053	1295	0.4738	0.7723	0.5918	0.4541	0.5139
0.3826	1.4107	1300	0.4645	0.7812	0.6360	0.4081	0.4971
0.432	1.4162	1305	0.4590	0.7893	0.6927	0.3691	0.4816
0.5126	1.4216	1310	0.4578	0.7898	0.7076	0.3530	0.4710
0.5268	1.4270	1315	0.4601	0.7866	0.6685	0.3870	0.4902
0.3992	1.4324	1320	0.4614	0.7852	0.6547	0.4013	0.4976
0.5153	1.4379	1325	0.4578	0.7872	0.6899	0.3584	0.4717
0.5084	1.4433	1330	0.4571	0.7869	0.7272	0.3136	0.4383
0.5292	1.4487	1335	0.4570	0.7866	0.7198	0.3195	0.4425
0.5776	1.4542	1340	0.4630	0.7850	0.6675	0.3763	0.4813
0.4558	1.4596	1345	0.4689	0.7808	0.6367	0.4031	0.4937
0.4301	1.4650	1350	0.4697	0.7786	0.6233	0.4161	0.4991
0.5145	1.4704	1355	0.4675	0.7805	0.6330	0.4089	0.4969
0.4087	1.4759	1360	0.4634	0.7850	0.6616	0.3866	0.4880
0.5818	1.4813	1365	0.4625	0.7853	0.6604	0.3915	0.4916
0.4387	1.4867	1370	0.4632	0.7850	0.6551	0.3987	0.4957
0.5374	1.4921	1375	0.4628	0.7857	0.6609	0.3933	0.4931
0.5327	1.4976	1380	0.4646	0.7842	0.6505	0.4022	0.4971
0.4564	1.5030	1385	0.4629	0.7850	0.6594	0.3906	0.4906
0.4669	1.5084	1390	0.4581	0.7883	0.7016	0.3503	0.4673
0.4227	1.5138	1395	0.4573	0.7895	0.7386	0.3186	0.4451
0.5092	1.5193	1400	0.4569	0.7889	0.7362	0.3172	0.4434
0.4983	1.5247	1405	0.4574	0.7884	0.7106	0.3405	0.4604
0.415	1.5301	1410	0.4582	0.7882	0.7013	0.3499	0.4669
0.4053	1.5355	1415	0.4574	0.7891	0.7110	0.3445	0.4641
0.4361	1.5410	1420	0.4568	0.7898	0.7303	0.3284	0.4531
0.4592	1.5464	1425	0.4562	0.7891	0.7278	0.3266	0.4509
0.5448	1.5518	1430	0.4570	0.7895	0.7142	0.3432	0.4636
0.4261	1.5572	1435	0.4574	0.7888	0.7106	0.3427	0.4624
0.4477	1.5627	1440	0.4575	0.7890	0.7107	0.3441	0.4637
0.5436	1.5681	1445	0.4573	0.7893	0.7155	0.3409	0.4618
0.4306	1.5735	1450	0.4573	0.7891	0.7110	0.3445	0.4641
0.4283	1.5789	1455	0.4586	0.7899	0.7028	0.3597	0.4759
0.472	1.5844	1460	0.4607	0.7873	0.6740	0.3830	0.4884
0.3639	1.5898	1465	0.4600	0.7882	0.6783	0.3821	0.4888
0.3948	1.5952	1470	0.4583	0.7882	0.6857	0.3709	0.4814
0.5209	1.6007	1475	0.4578	0.7886	0.6918	0.3655	0.4783
0.444	1.6061	1480	0.4578	0.7893	0.6947	0.3664	0.4798
0.4128	1.6115	1485	0.4573	0.7888	0.6960	0.3606	0.4751
0.4807	1.6169	1490	0.4569	0.7889	0.7059	0.3490	0.4671
0.4298	1.6224	1495	0.4567	0.7891	0.7079	0.3481	0.4667
0.5	1.6278	1500	0.4560	0.7895	0.7099	0.3481	0.4671
0.3869	1.6332	1505	0.4562	0.7888	0.7060	0.3481	0.4663
0.4452	1.6386	1510	0.4563	0.7890	0.7184	0.3356	0.4575
0.5222	1.6441	1515	0.4558	0.7896	0.7258	0.3315	0.4552
0.4767	1.6495	1520	0.4560	0.7882	0.7243	0.3244	0.4481
0.5223	1.6549	1525	0.4559	0.7884	0.7230	0.3271	0.4504
0.5075	1.6603	1530	0.4556	0.7882	0.7177	0.3311	0.4532
0.4564	1.6658	1535	0.4558	0.7889	0.7185	0.3347	0.4567
0.4615	1.6712	1540	0.4554	0.7886	0.7167	0.3351	0.4567
0.4659	1.6766	1545	0.4556	0.7879	0.7118	0.3360	0.4565
0.5568	1.6820	1550	0.4554	0.7884	0.7170	0.3333	0.4551
0.3962	1.6875	1555	0.4552	0.7882	0.7169	0.3320	0.4538
0.4666	1.6929	1560	0.4552	0.7877	0.7171	0.3289	0.4509
0.496	1.6983	1565	0.4552	0.7889	0.7185	0.3347	0.4567
0.5433	1.7037	1570	0.4549	0.7888	0.7208	0.3315	0.4542
0.4571	1.7092	1575	0.4550	0.7885	0.7233	0.3275	0.4509
0.4439	1.7146	1580	0.4548	0.7889	0.7343	0.3190	0.4448
0.4559	1.7200	1585	0.4545	0.7895	0.7421	0.3154	0.4427
0.4633	1.7254	1590	0.4550	0.7888	0.7395	0.3136	0.4405
0.5376	1.7309	1595	0.4550	0.7889	0.7324	0.3208	0.4462
0.4961	1.7363	1600	0.4553	0.7885	0.7169	0.3342	0.4559
0.4855	1.7417	1605	0.4559	0.7890	0.7084	0.3468	0.4656
0.4406	1.7472	1610	0.4566	0.7889	0.6994	0.3570	0.4727
0.509	1.7526	1615	0.4569	0.7879	0.6952	0.3562	0.4710
0.3787	1.7580	1620	0.4572	0.7884	0.6963	0.3579	0.4728
0.4324	1.7634	1625	0.4561	0.7876	0.6972	0.3512	0.4671
0.5501	1.7689	1630	0.4563	0.7882	0.7010	0.3503	0.4672
0.4358	1.7743	1635	0.4558	0.7889	0.7089	0.3454	0.4645
0.5515	1.7797	1640	0.4556	0.7879	0.7060	0.3427	0.4614
0.4532	1.7851	1645	0.4556	0.7877	0.7058	0.3414	0.4602
0.4381	1.7906	1650	0.4554	0.7883	0.7049	0.3463	0.4644
0.4129	1.7960	1655	0.4554	0.7883	0.7053	0.3459	0.4641
0.434	1.8014	1660	0.4549	0.7886	0.7068	0.3463	0.4649
0.4347	1.8068	1665	0.4553	0.7888	0.7067	0.3472	0.4656
0.5182	1.8123	1670	0.4555	0.7885	0.7040	0.3490	0.4666
0.5414	1.8177	1675	0.4556	0.7886	0.7010	0.3535	0.4700
0.5232	1.8231	1680	0.4559	0.7889	0.7022	0.3535	0.4702
0.4845	1.8285	1685	0.4563	0.7882	0.6937	0.3597	0.4738
0.525	1.8340	1690	0.4563	0.7873	0.6889	0.3606	0.4734
0.4395	1.8394	1695	0.4567	0.7884	0.6922	0.3633	0.4765
0.567	1.8448	1700	0.4570	0.7883	0.6872	0.3696	0.4807
0.5039	1.8502	1705	0.4573	0.7884	0.6856	0.3727	0.4829
0.4758	1.8557	1710	0.4575	0.7882	0.6818	0.3767	0.4853
0.4654	1.8611	1715	0.4580	0.7886	0.6828	0.3785	0.4870
0.4603	1.8665	1720	0.4578	0.7880	0.6824	0.3749	0.4840
0.4068	1.8719	1725	0.4578	0.7872	0.6774	0.3767	0.4842
0.5461	1.8774	1730	0.4581	0.7877	0.6787	0.3781	0.4856
0.6282	1.8828	1735	0.4576	0.7879	0.6810	0.3763	0.4847
0.5704	1.8882	1740	0.4575	0.7875	0.6799	0.3745	0.4830
0.5337	1.8937	1745	0.4576	0.7873	0.6811	0.3718	0.4810
0.413	1.8991	1750	0.4572	0.7876	0.6829	0.3709	0.4807
0.466	1.9045	1755	0.4569	0.7878	0.6855	0.3687	0.4795
0.4467	1.9099	1760	0.4564	0.7883	0.6897	0.3660	0.4782
0.4427	1.9154	1765	0.4565	0.7882	0.6898	0.3651	0.4775
0.4436	1.9208	1770	0.4561	0.7884	0.6922	0.3633	0.4765
0.5262	1.9262	1775	0.4565	0.7882	0.6907	0.3638	0.4766
0.409	1.9316	1780	0.4563	0.7883	0.6920	0.3629	0.4761
0.5116	1.9371	1785	0.4563	0.7885	0.6932	0.3629	0.4764
0.4718	1.9425	1790	0.4561	0.7882	0.6920	0.3620	0.4753
0.4289	1.9479	1795	0.4563	0.7882	0.6924	0.3615	0.4750
0.4745	1.9533	1800	0.4562	0.7884	0.6939	0.3611	0.4750
0.4312	1.9588	1805	0.4561	0.7888	0.6940	0.3633	0.4769
0.47	1.9642	1810	0.4563	0.7886	0.6944	0.3620	0.4759
0.5307	1.9696	1815	0.4560	0.7879	0.6925	0.3597	0.4735
0.5403	1.9750	1820	0.4560	0.7895	0.6976	0.3633	0.4778
0.4265	1.9805	1825	0.4563	0.7879	0.6922	0.3602	0.4738
0.5254	1.9859	1830	0.4559	0.7888	0.6947	0.3624	0.4763
0.4676	1.9913	1835	0.4560	0.7880	0.6924	0.3606	0.4743
0.4489	1.9967	1840	0.4561	0.7885	0.6945	0.3611	0.4751

Framework versions

• PEFT 0.12.0
• Transformers 4.46.0
• Pytorch 2.4.0+cu118
• Datasets 3.0.0
• Tokenizers 0.20.1