v0_mistral_lora

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: 0.5147
• Accuracy: 0.7633
• Precision: 0.6122
• Recall: 0.2917
• F1: 0.3952

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• total_eval_batch_size: 16
• 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
7.75	0.0027	5	5.3957	0.4137	0.2646	0.6810	0.3811
6.8129	0.0054	10	5.3507	0.4156	0.2644	0.6756	0.3800
5.0367	0.0081	15	5.2521	0.4196	0.2649	0.6698	0.3796
6.6579	0.0108	20	5.1170	0.4243	0.2645	0.6582	0.3774
6.4975	0.0136	25	4.9376	0.4326	0.2657	0.6465	0.3766
4.6778	0.0163	30	4.6965	0.4417	0.2660	0.6286	0.3738
3.8759	0.0190	35	4.4129	0.4533	0.2659	0.6031	0.3691
5.709	0.0217	40	4.0931	0.4687	0.2671	0.5758	0.3650
4.8813	0.0244	45	3.7454	0.4899	0.2677	0.5324	0.3562
4.8337	0.0271	50	3.4162	0.5163	0.2685	0.4783	0.3440
4.5265	0.0298	55	3.1400	0.5492	0.2729	0.4210	0.3312
2.8864	0.0325	60	2.9545	0.5766	0.2774	0.3723	0.3179
3.8508	0.0352	65	2.8438	0.6029	0.2844	0.3284	0.3048
4.345	0.0380	70	2.7800	0.6131	0.2867	0.3087	0.2973
2.9226	0.0407	75	2.7159	0.6159	0.2915	0.3136	0.3022
2.8788	0.0434	80	2.6496	0.6131	0.2907	0.3190	0.3042
3.7029	0.0461	85	2.6247	0.5910	0.2859	0.3624	0.3197
2.7038	0.0488	90	2.6103	0.5796	0.2846	0.3870	0.3280
3.2932	0.0515	95	2.6115	0.5673	0.2823	0.4098	0.3343
2.9678	0.0542	100	2.5788	0.5639	0.2814	0.4152	0.3354
2.4567	0.0569	105	2.4612	0.5872	0.2902	0.3852	0.3310
3.4606	0.0596	110	2.3713	0.6164	0.3031	0.3441	0.3223
2.752	0.0623	115	2.3224	0.6225	0.3079	0.3400	0.3232
2.8411	0.0651	120	2.2903	0.6127	0.3052	0.3611	0.3308
3.9967	0.0678	125	2.3376	0.5704	0.2880	0.4215	0.3422
3.7136	0.0705	130	2.4109	0.5419	0.2817	0.4698	0.3522
2.5731	0.0732	135	2.4106	0.5343	0.2829	0.4931	0.3595
2.6354	0.0759	140	2.1595	0.5901	0.2976	0.4018	0.3420
2.8646	0.0786	145	2.0589	0.6330	0.3115	0.3177	0.3146
2.4501	0.0813	150	1.9668	0.6111	0.3070	0.3714	0.3361
2.3214	0.0840	155	1.9614	0.5728	0.2938	0.4358	0.3510
2.2701	0.0867	160	1.8026	0.6006	0.2996	0.3785	0.3345
2.1174	0.0895	165	1.6617	0.6334	0.3079	0.3069	0.3074
1.7811	0.0922	170	1.5850	0.5776	0.2902	0.4103	0.3399
2.4461	0.0949	175	1.4067	0.6352	0.2948	0.2702	0.2820
1.6691	0.0976	180	1.3139	0.6350	0.2918	0.2640	0.2772
1.0397	0.1003	185	1.2387	0.6661	0.3014	0.1969	0.2382
1.431	0.1030	190	1.1442	0.5524	0.2891	0.4720	0.3586
1.2481	0.1057	195	0.9419	0.6773	0.3351	0.2210	0.2664
1.364	0.1084	200	1.0245	0.5193	0.2971	0.5955	0.3964
1.0323	0.1111	205	0.8623	0.7117	0.3631	0.1163	0.1762
2.0244	0.1139	210	0.7672	0.6892	0.3590	0.2192	0.2722
0.9657	0.1166	215	0.7330	0.6658	0.3449	0.2899	0.3150
1.5682	0.1193	220	1.2531	0.7348	0.4545	0.0022	0.0045
0.821	0.1220	225	0.7293	0.5499	0.3023	0.5338	0.3860
1.5009	0.1247	230	0.7776	0.7331	0.2857	0.0045	0.0088
0.7115	0.1274	235	0.6476	0.6518	0.3261	0.2940	0.3092
0.7846	0.1301	240	0.6325	0.7293	0.312	0.0174	0.0331
0.995	0.1328	245	0.6134	0.7079	0.3553	0.1253	0.1852
0.785	0.1355	250	0.6457	0.6424	0.3333	0.3490	0.3410
0.8269	0.1382	255	0.6189	0.6822	0.3377	0.2067	0.2565
0.9179	0.1410	260	0.7736	0.5244	0.3115	0.6559	0.4224
0.5934	0.1437	265	0.6379	0.7285	0.4146	0.0586	0.1027
0.56	0.1464	270	0.5986	0.7230	0.3603	0.0577	0.0995
0.6095	0.1491	275	0.5985	0.7150	0.3843	0.1248	0.1884
0.6656	0.1518	280	0.6124	0.7349	0.5	0.0103	0.0202
0.6999	0.1545	285	0.6019	0.7311	0.4558	0.0738	0.1271
0.6663	0.1572	290	0.6391	0.6892	0.3520	0.2049	0.2590
0.6746	0.1599	295	0.6216	0.7349	0.0	0.0	0.0
0.5564	0.1626	300	0.5942	0.7287	0.3976	0.0452	0.0812
0.7009	0.1654	305	0.5921	0.7242	0.3576	0.0506	0.0886
0.5978	0.1681	310	0.5935	0.7296	0.4157	0.0497	0.0887
0.6872	0.1708	315	0.6514	0.6526	0.3561	0.3843	0.3697
0.722	0.1735	320	0.6713	0.6195	0.3500	0.5078	0.4144
0.7311	0.1762	325	0.5976	0.7332	0.15	0.0013	0.0027
0.724	0.1789	330	0.6403	0.6738	0.3746	0.3441	0.3587
0.6807	0.1816	335	0.6316	0.6832	0.3792	0.3060	0.3387
0.751	0.1843	340	0.6013	0.7109	0.3855	0.1521	0.2182
0.6454	0.1870	345	0.5872	0.7258	0.2984	0.0255	0.0470
0.6811	0.1898	350	0.6126	0.7349	0.5	0.0009	0.0018
0.6908	0.1925	355	0.5956	0.7310	0.4413	0.0555	0.0986
0.6549	0.1952	360	0.6267	0.6993	0.3933	0.2474	0.3038
0.5877	0.1979	365	0.5867	0.7285	0.2923	0.0170	0.0321
0.6484	0.2006	370	0.5885	0.7321	0.3125	0.0089	0.0174
0.5318	0.2033	375	0.5884	0.7258	0.2941	0.0246	0.0454
0.5971	0.2060	380	0.5914	0.7211	0.3165	0.0447	0.0784
0.657	0.2087	385	0.6085	0.6996	0.3422	0.1445	0.2032
0.5199	0.2114	390	0.5827	0.7349	0.5	0.0004	0.0009
0.8601	0.2142	395	0.5832	0.7349	0.0	0.0	0.0
0.6302	0.2169	400	0.5969	0.7166	0.3881	0.1195	0.1827
0.5666	0.2196	405	0.5803	0.7349	0.0	0.0	0.0
0.6335	0.2223	410	0.6079	0.7349	0.0	0.0	0.0
0.6868	0.2250	415	0.5840	0.7315	0.3910	0.0233	0.0439
0.7763	0.2277	420	0.7961	0.3756	0.2893	0.9306	0.4414
0.7398	0.2304	425	0.6695	0.6145	0.3544	0.5526	0.4318
0.5726	0.2331	430	0.5898	0.7349	0.0	0.0	0.0
0.6005	0.2358	435	0.6024	0.7349	0.0	0.0	0.0
0.7129	0.2385	440	0.6004	0.7038	0.3901	0.2081	0.2714
0.7727	0.2413	445	0.6589	0.6331	0.3686	0.5383	0.4375
0.7756	0.2440	450	0.5859	0.7131	0.3451	0.0917	0.1449
0.7347	0.2467	455	0.5820	0.7331	0.2973	0.0049	0.0097
0.7084	0.2494	460	0.6002	0.7220	0.4231	0.1342	0.2038
0.5636	0.2521	465	0.5783	0.7347	0.4375	0.0031	0.0062
0.6612	0.2548	470	0.5767	0.7347	0.4375	0.0031	0.0062
0.5068	0.2575	475	0.5951	0.7276	0.4475	0.1181	0.1869
0.5444	0.2602	480	0.5758	0.7348	0.3333	0.0004	0.0009
0.6972	0.2629	485	0.5808	0.7349	0.0	0.0	0.0
0.728	0.2657	490	0.5867	0.7232	0.4216	0.1190	0.1856
0.6434	0.2684	495	0.6061	0.6967	0.4132	0.3427	0.3747
0.6407	0.2711	500	0.5749	0.7351	0.5102	0.0224	0.0429
0.6698	0.2738	505	0.5775	0.7328	0.4609	0.0474	0.0860
0.5178	0.2765	510	0.5805	0.7348	0.4971	0.0385	0.0714
0.7291	0.2792	515	0.5977	0.7349	0.0	0.0	0.0
0.6337	0.2819	520	0.5789	0.7344	0.375	0.0027	0.0053
0.7194	0.2846	525	0.5919	0.7330	0.4740	0.0653	0.1148
0.7127	0.2873	530	0.5956	0.7325	0.4746	0.0837	0.1423
0.6855	0.2901	535	0.5813	0.7341	0.4646	0.0206	0.0394
0.6432	0.2928	540	0.5908	0.7349	0.0	0.0	0.0
0.5179	0.2955	545	0.5805	0.7349	0.0	0.0	0.0
0.6875	0.2982	550	0.6134	0.7060	0.4197	0.2855	0.3398
0.7394	0.3009	555	0.6723	0.5901	0.3511	0.6443	0.4545
0.5555	0.3036	560	0.5891	0.7214	0.4120	0.1195	0.1852
1.0411	0.3063	565	0.5836	0.7349	0.0	0.0	0.0
0.6364	0.3090	570	0.5766	0.7313	0.2115	0.0049	0.0096
0.5456	0.3117	575	0.5835	0.7223	0.3450	0.0528	0.0916
0.6957	0.3144	580	0.5793	0.7302	0.2436	0.0085	0.0164
0.6393	0.3172	585	0.6096	0.7057	0.4155	0.2707	0.3278
0.6864	0.3199	590	0.5815	0.7309	0.1964	0.0049	0.0096
0.5028	0.3226	595	0.5850	0.7349	0.0	0.0	0.0
0.7812	0.3253	600	0.5805	0.7347	0.0	0.0	0.0
0.5293	0.3280	605	0.5790	0.7292	0.2143	0.0081	0.0155
0.6452	0.3307	610	0.5835	0.7222	0.2743	0.0291	0.0526
0.6424	0.3334	615	0.6071	0.6954	0.4021	0.3060	0.3476
0.6831	0.3361	620	0.6702	0.5913	0.3534	0.6532	0.4587
0.7074	0.3388	625	0.5925	0.6978	0.3790	0.2192	0.2778
0.7109	0.3416	630	0.5750	0.7347	0.0	0.0	0.0
0.5007	0.3443	635	0.5871	0.7349	0.0	0.0	0.0
0.7052	0.3470	640	0.5759	0.7348	0.0	0.0	0.0
0.617	0.3497	645	0.6011	0.7093	0.3784	0.1503	0.2152
0.6599	0.3524	650	0.6002	0.7099	0.3855	0.1588	0.2250
0.6019	0.3551	655	0.5735	0.7349	0.0	0.0	0.0
0.5231	0.3578	660	0.5879	0.7234	0.4139	0.1043	0.1665
0.6949	0.3605	665	0.5936	0.7055	0.3953	0.2094	0.2738
0.604	0.3632	670	0.5725	0.7346	0.4	0.0027	0.0053
0.4369	0.3660	675	0.5768	0.7349	0.0	0.0	0.0
0.5686	0.3687	680	0.5719	0.7346	0.44	0.0049	0.0097
0.6144	0.3714	685	0.5790	0.7278	0.4402	0.0989	0.1615
0.6037	0.3741	690	0.5738	0.7344	0.4915	0.0519	0.0939
0.6392	0.3768	695	0.5700	0.7344	0.4737	0.0161	0.0312
0.6035	0.3795	700	0.5762	0.7335	0.4766	0.0546	0.0980
0.6134	0.3822	705	0.5962	0.7109	0.4207	0.2398	0.3055
0.6669	0.3849	710	0.5736	0.7308	0.4411	0.0586	0.1035
0.6024	0.3876	715	0.6207	0.6733	0.3954	0.4389	0.4160
0.6747	0.3903	720	0.5924	0.7044	0.4134	0.2743	0.3297
0.5725	0.3931	725	0.5737	0.7236	0.4162	0.1056	0.1685
0.6164	0.3958	730	0.5943	0.6936	0.4037	0.3262	0.3608
0.7381	0.3985	735	0.6022	0.6873	0.4029	0.3723	0.3870
0.5391	0.4012	740	0.5710	0.7271	0.4218	0.0796	0.1340
0.73	0.4039	745	0.5698	0.7310	0.4444	0.0591	0.1043
0.6777	0.4066	750	0.6228	0.6726	0.4015	0.4787	0.4367
0.7137	0.4093	755	0.5796	0.7225	0.4383	0.1669	0.2417
0.6186	0.4120	760	0.5777	0.7349	0.0	0.0	0.0
0.6447	0.4147	765	0.5666	0.7346	0.4286	0.0040	0.0080
0.6349	0.4175	770	0.5957	0.7225	0.4545	0.2345	0.3093
0.6459	0.4202	775	0.5661	0.7351	0.5217	0.0107	0.0210
0.8066	0.4229	780	0.5823	0.7349	0.0	0.0	0.0
0.5664	0.4256	785	0.5658	0.7361	0.55	0.0246	0.0471
0.6653	0.4283	790	0.5876	0.7181	0.4511	0.2931	0.3553
0.5223	0.4310	795	0.5822	0.7214	0.4588	0.2841	0.3509
0.5611	0.4337	800	0.5653	0.7279	0.4322	0.0841	0.1408
0.6364	0.4364	805	0.5864	0.7335	0.1667	0.0013	0.0027
0.6732	0.4391	810	0.5649	0.7306	0.4712	0.1315	0.2057
0.7002	0.4419	815	0.6489	0.6373	0.3884	0.6407	0.4836
0.6093	0.4446	820	0.6097	0.6947	0.4274	0.4465	0.4368
0.5802	0.4473	825	0.5633	0.7332	0.4670	0.0443	0.0809
0.8647	0.4500	830	0.5811	0.7348	0.4286	0.0013	0.0027
0.4827	0.4527	835	0.5618	0.7360	0.5474	0.0233	0.0446
0.5555	0.4554	840	0.5599	0.7346	0.4943	0.0582	0.1041
0.549	0.4581	845	0.5606	0.7369	0.5205	0.0966	0.1630
0.6209	0.4608	850	0.5852	0.7274	0.4785	0.3132	0.3786
0.6519	0.4635	855	0.5641	0.7372	0.5140	0.1566	0.2401
0.6116	0.4663	860	0.5571	0.7357	0.5333	0.0251	0.0479
0.5691	0.4690	865	0.5557	0.7330	0.4890	0.1588	0.2398
0.6353	0.4717	870	0.5580	0.7291	0.4768	0.2255	0.3062
0.8314	0.4744	875	0.5808	0.7004	0.4368	0.4497	0.4431
0.6335	0.4771	880	0.5885	0.6900	0.4265	0.4922	0.4570
0.563	0.4798	885	0.5655	0.7139	0.4451	0.3213	0.3732
0.7697	0.4825	890	0.5632	0.7281	0.4329	0.0823	0.1383
0.6926	0.4852	895	0.5578	0.7280	0.4751	0.2479	0.3258
0.764	0.4879	900	0.6507	0.6195	0.3827	0.7101	0.4973
0.6447	0.4906	905	0.5921	0.7072	0.4503	0.4738	0.4617
0.7132	0.4934	910	0.5534	0.7392	0.5638	0.0711	0.1263
0.4559	0.4961	915	0.5515	0.7430	0.6	0.0913	0.1584
0.5774	0.4988	920	0.5580	0.7347	0.4992	0.2787	0.3577
0.5917	0.5015	925	0.5691	0.7246	0.4764	0.3937	0.4312
0.712	0.5042	930	0.5499	0.7421	0.5328	0.2219	0.3133
0.6302	0.5069	935	0.5451	0.7482	0.5930	0.1597	0.2517
0.7596	0.5096	940	0.5442	0.7502	0.6693	0.1141	0.1950
0.5878	0.5123	945	0.5502	0.7485	0.5697	0.2103	0.3072
0.6663	0.5150	950	0.5568	0.7387	0.5143	0.2582	0.3438
0.5847	0.5178	955	0.5429	0.7519	0.6486	0.1396	0.2297
0.6272	0.5205	960	0.5467	0.7478	0.7121	0.0819	0.1469
0.7481	0.5232	965	0.5529	0.7418	0.5265	0.2582	0.3464
0.6344	0.5259	970	0.5748	0.7216	0.4712	0.4098	0.4384
0.5883	0.5286	975	0.5421	0.7564	0.6472	0.1781	0.2793
0.5439	0.5313	980	0.5402	0.7564	0.6568	0.1696	0.2696
0.654	0.5340	985	0.5399	0.7538	0.7003	0.1244	0.2112
0.4815	0.5367	990	0.5418	0.7545	0.5922	0.2371	0.3387
0.6336	0.5394	995	0.5568	0.7332	0.4958	0.3682	0.4226
0.6301	0.5422	1000	0.5691	0.7131	0.4610	0.4872	0.4738
0.5931	0.5449	1005	0.5365	0.7538	0.6538	0.1512	0.2456
0.6604	0.5476	1010	0.5403	0.7542	0.7418	0.1119	0.1944
0.706	0.5503	1015	0.5394	0.7553	0.6041	0.2233	0.3260
0.6242	0.5530	1020	0.5473	0.7516	0.5670	0.2671	0.3631
0.591	0.5557	1025	0.5699	0.7302	0.4886	0.3839	0.4300
0.6172	0.5584	1030	0.5670	0.7266	0.4810	0.3964	0.4346
0.6831	0.5611	1035	0.5480	0.7433	0.5274	0.3056	0.3870
0.6925	0.5638	1040	0.5349	0.7553	0.6114	0.2112	0.3139
0.6452	0.5665	1045	0.5437	0.7434	0.5269	0.3154	0.3946
0.6023	0.5693	1050	0.5483	0.7361	0.5030	0.3740	0.4290
0.7421	0.5720	1055	0.5348	0.7507	0.5750	0.2282	0.3267
0.4162	0.5747	1060	0.5345	0.7523	0.6028	0.1928	0.2922
0.5154	0.5774	1065	0.5349	0.7531	0.6393	0.1570	0.2522
0.6058	0.5801	1070	0.5443	0.7461	0.5396	0.2868	0.3745
0.6614	0.5828	1075	0.5509	0.7367	0.5048	0.3557	0.4173
0.6042	0.5855	1080	0.5355	0.7509	0.5669	0.2559	0.3527
0.9067	0.5882	1085	0.5321	0.7545	0.5965	0.2282	0.3301
0.5541	0.5909	1090	0.5337	0.7557	0.5865	0.2653	0.3654
0.5755	0.5937	1095	0.5311	0.7587	0.6089	0.2515	0.3559
0.573	0.5964	1100	0.5487	0.7449	0.5284	0.3494	0.4207
0.6351	0.5991	1105	0.5691	0.7270	0.4833	0.4349	0.4578
0.6914	0.6018	1110	0.5571	0.7354	0.5011	0.3937	0.4410
0.6274	0.6045	1115	0.5681	0.7197	0.4706	0.4586	0.4645
0.641	0.6072	1120	0.5524	0.7402	0.5140	0.3687	0.4294
0.5991	0.6099	1125	0.5361	0.7555	0.5803	0.2814	0.3790
0.4889	0.6126	1130	0.5401	0.7529	0.5618	0.3092	0.3988
0.7734	0.6153	1135	0.5489	0.7446	0.5260	0.3714	0.4354
0.6568	0.6181	1140	0.5730	0.7151	0.4650	0.4971	0.4805
0.7067	0.6208	1145	0.5457	0.7437	0.5229	0.3785	0.4391
0.4641	0.6235	1150	0.5258	0.7580	0.6271	0.2152	0.3205
0.7844	0.6262	1155	0.5285	0.7604	0.6994	0.1687	0.2718
0.657	0.6289	1160	0.5262	0.7605	0.6742	0.1870	0.2928
0.5148	0.6316	1165	0.5272	0.7592	0.6248	0.2295	0.3357
0.5169	0.6343	1170	0.5436	0.7478	0.5396	0.3324	0.4114
0.6553	0.6370	1175	0.5340	0.7579	0.5931	0.2765	0.3772
0.799	0.6397	1180	0.5270	0.7621	0.6797	0.1937	0.3015
0.5979	0.6425	1185	0.5277	0.7616	0.6657	0.2022	0.3102
0.6531	0.6452	1190	0.5427	0.7517	0.5572	0.3096	0.3980
0.6177	0.6479	1195	0.5876	0.7043	0.4499	0.5181	0.4816
0.5962	0.6506	1200	0.5482	0.7448	0.5279	0.3508	0.4215
0.4873	0.6533	1205	0.5280	0.7604	0.7302	0.1526	0.2524
0.503	0.6560	1210	0.5403	0.7559	0.7810	0.1101	0.1929
0.5127	0.6587	1215	0.5239	0.7638	0.7061	0.1870	0.2957
0.5646	0.6614	1220	0.5393	0.7499	0.5448	0.3427	0.4208
0.595	0.6641	1225	0.5391	0.7500	0.5430	0.3588	0.4321
0.6213	0.6668	1230	0.5385	0.7488	0.5396	0.3566	0.4294
0.5927	0.6696	1235	0.5310	0.7526	0.5568	0.3266	0.4117
0.6592	0.6723	1240	0.5247	0.7570	0.5847	0.2872	0.3852
0.5777	0.6750	1245	0.5276	0.7548	0.5665	0.3204	0.4093
0.6144	0.6777	1250	0.5205	0.7611	0.6305	0.2389	0.3465
0.5397	0.6804	1255	0.5249	0.7572	0.5847	0.2904	0.3880
0.5756	0.6831	1260	0.5366	0.7445	0.5264	0.3620	0.4290
0.5533	0.6858	1265	0.5285	0.7527	0.5591	0.3172	0.4048
0.4767	0.6885	1270	0.5197	0.7611	0.6323	0.2362	0.3440
0.6095	0.6912	1275	0.5201	0.7648	0.6842	0.2094	0.3207
0.414	0.6940	1280	0.5194	0.7647	0.6790	0.2130	0.3243
0.4603	0.6967	1285	0.5194	0.7631	0.6730	0.2072	0.3168
0.6233	0.6994	1290	0.5199	0.7557	0.5841	0.2720	0.3712
0.6375	0.7021	1295	0.5513	0.7187	0.4718	0.5136	0.4919
0.5112	0.7048	1300	0.5662	0.7062	0.4571	0.5763	0.5098
0.5544	0.7075	1305	0.5450	0.7211	0.4753	0.4984	0.4866
0.4887	0.7102	1310	0.5201	0.7523	0.5650	0.2859	0.3797
0.6849	0.7129	1315	0.5208	0.7587	0.6467	0.1982	0.3034
0.4873	0.7156	1320	0.5187	0.7614	0.6628	0.2031	0.3110
0.5365	0.7184	1325	0.5179	0.7615	0.66	0.2067	0.3148
0.7564	0.7211	1330	0.5164	0.7619	0.6443	0.2277	0.3365
0.4961	0.7238	1335	0.5240	0.7545	0.5665	0.3145	0.4045
0.6191	0.7265	1340	0.5218	0.7586	0.5868	0.3025	0.3992
0.4835	0.7292	1345	0.5220	0.7586	0.5883	0.2980	0.3956
0.6704	0.7319	1350	0.5196	0.7612	0.6069	0.2819	0.3850
0.651	0.7346	1355	0.5226	0.7564	0.5772	0.3029	0.3973
0.6029	0.7373	1360	0.5241	0.7553	0.5708	0.3101	0.4019
0.4883	0.7400	1365	0.5182	0.7595	0.5981	0.2823	0.3836
0.5536	0.7427	1370	0.5153	0.7602	0.6129	0.2586	0.3638
0.6036	0.7455	1375	0.5170	0.7584	0.5950	0.2774	0.3784
0.5623	0.7482	1380	0.5280	0.7474	0.5342	0.3664	0.4347
0.5264	0.7509	1385	0.5186	0.7585	0.5884	0.2962	0.3940
0.5159	0.7536	1390	0.5151	0.7637	0.6758	0.2089	0.3192
0.5768	0.7563	1395	0.5147	0.7637	0.6695	0.2148	0.3252
0.6883	0.7590	1400	0.5205	0.7587	0.5857	0.3074	0.4032
0.5961	0.7617	1405	0.5417	0.7357	0.5018	0.4443	0.4713
0.5949	0.7644	1410	0.5480	0.7300	0.4902	0.4609	0.4751
0.5955	0.7671	1415	0.5405	0.7421	0.5170	0.4148	0.4603
0.6513	0.7699	1420	0.5261	0.7587	0.5789	0.3298	0.4202
0.4364	0.7726	1425	0.5160	0.7671	0.6696	0.2394	0.3527
0.6006	0.7753	1430	0.5158	0.7669	0.6705	0.2376	0.3508
0.4033	0.7780	1435	0.5160	0.7672	0.6542	0.2582	0.3702
0.5447	0.7807	1440	0.5185	0.7642	0.6193	0.2868	0.3920
0.5623	0.7834	1445	0.5260	0.7571	0.5695	0.3427	0.4279
0.5886	0.7861	1450	0.5294	0.7540	0.5542	0.3682	0.4425
0.6458	0.7888	1455	0.5331	0.7502	0.5397	0.3919	0.4541
0.7037	0.7915	1460	0.5344	0.7493	0.5359	0.4036	0.4604
0.5006	0.7943	1465	0.5379	0.7443	0.5222	0.4166	0.4634
0.6315	0.7970	1470	0.5267	0.7566	0.5648	0.3570	0.4375
0.7411	0.7997	1475	0.5182	0.7635	0.6134	0.2917	0.3954
0.5466	0.8024	1480	0.5145	0.7662	0.6634	0.2398	0.3523
0.4287	0.8051	1485	0.5148	0.7668	0.6850	0.2228	0.3363
0.4993	0.8078	1490	0.5140	0.7663	0.6741	0.2295	0.3425
0.6759	0.8105	1495	0.5134	0.7668	0.6671	0.2403	0.3533
0.6407	0.8132	1500	0.5137	0.7661	0.6447	0.2622	0.3728
0.5586	0.8159	1505	0.5136	0.7663	0.6399	0.2711	0.3809
0.6752	0.8187	1510	0.5143	0.7648	0.6257	0.2805	0.3874
0.681	0.8214	1515	0.5161	0.7638	0.6093	0.3043	0.4058
0.5568	0.8241	1520	0.5147	0.7637	0.6176	0.2855	0.3905
0.4895	0.8268	1525	0.5170	0.7628	0.6041	0.3051	0.4055
0.5304	0.8295	1530	0.5157	0.7633	0.6122	0.2917	0.3952
0.6346	0.8322	1535	0.5145	0.7661	0.6324	0.2810	0.3891
0.5449	0.8349	1540	0.5161	0.7641	0.6156	0.2931	0.3971
0.4459	0.8376	1545	0.5145	0.7657	0.6313	0.2796	0.3876
0.5313	0.8403	1550	0.5132	0.7666	0.6419	0.2702	0.3804
0.5503	0.8430	1555	0.5130	0.7661	0.6360	0.2752	0.3841
0.6352	0.8458	1560	0.5142	0.7630	0.6127	0.2881	0.3920
0.6018	0.8485	1565	0.5169	0.7602	0.5887	0.3163	0.4115
0.4977	0.8512	1570	0.5201	0.7567	0.5686	0.3414	0.4266
0.4957	0.8539	1575	0.5215	0.7561	0.5647	0.3494	0.4317
0.5012	0.8566	1580	0.5208	0.7570	0.5683	0.3463	0.4304
0.5376	0.8593	1585	0.5174	0.7596	0.5847	0.3213	0.4147
0.603	0.8620	1590	0.5142	0.7616	0.6013	0.2989	0.3993
0.5136	0.8647	1595	0.5126	0.7622	0.6112	0.2828	0.3867
0.5995	0.8674	1600	0.5119	0.7642	0.6315	0.2653	0.3737
0.5679	0.8702	1605	0.5114	0.7655	0.6421	0.2609	0.3710
0.4941	0.8729	1610	0.5122	0.7637	0.6262	0.2698	0.3771
0.6497	0.8756	1615	0.5138	0.7616	0.6035	0.2935	0.3949
0.6703	0.8783	1620	0.5170	0.7602	0.5874	0.3204	0.4146
0.6123	0.8810	1625	0.5195	0.7572	0.5706	0.3400	0.4261
0.6857	0.8837	1630	0.5191	0.7576	0.5731	0.3351	0.4229
0.631	0.8864	1635	0.5191	0.7571	0.5722	0.3315	0.4198
0.6355	0.8891	1640	0.5191	0.7584	0.5778	0.3289	0.4192
0.6009	0.8918	1645	0.5166	0.7621	0.5988	0.3105	0.4090
0.5264	0.8946	1650	0.5153	0.7618	0.6027	0.2980	0.3988
0.6552	0.8973	1655	0.5141	0.7623	0.6112	0.2841	0.3879
0.6215	0.9000	1660	0.5139	0.7631	0.6155	0.2837	0.3884
0.5159	0.9027	1665	0.5144	0.7629	0.6126	0.2872	0.3911
0.4092	0.9054	1670	0.5139	0.7631	0.6174	0.2801	0.3853
0.4887	0.9081	1675	0.5132	0.7634	0.6245	0.2694	0.3764
0.7156	0.9108	1680	0.5125	0.7647	0.6402	0.2564	0.3661
0.5593	0.9135	1685	0.5124	0.7655	0.6443	0.2577	0.3682
0.5466	0.9162	1690	0.5122	0.7662	0.6514	0.2541	0.3656
0.4649	0.9189	1695	0.5116	0.7663	0.6579	0.2470	0.3591
0.5319	0.9217	1700	0.5116	0.7669	0.6679	0.2403	0.3534
0.6049	0.9244	1705	0.5112	0.7666	0.6650	0.2407	0.3535
0.6349	0.9271	1710	0.5117	0.7663	0.6591	0.2456	0.3579
0.5973	0.9298	1715	0.5120	0.7663	0.6490	0.2582	0.3694
0.5477	0.9325	1720	0.5126	0.7659	0.6405	0.2662	0.3761
0.5352	0.9352	1725	0.5130	0.7649	0.6327	0.2698	0.3783
0.7681	0.9379	1730	0.5132	0.7644	0.6267	0.2756	0.3828
0.4676	0.9406	1735	0.5135	0.7637	0.6207	0.2796	0.3856
0.4645	0.9433	1740	0.5133	0.7630	0.6179	0.2779	0.3833
0.7623	0.9461	1745	0.5135	0.7634	0.6193	0.2787	0.3844
0.4886	0.9488	1750	0.5136	0.7634	0.6188	0.2796	0.3852
0.6107	0.9515	1755	0.5134	0.7637	0.6199	0.2810	0.3867
0.6393	0.9542	1760	0.5135	0.7636	0.6186	0.2823	0.3877
0.4865	0.9569	1765	0.5136	0.7635	0.6183	0.2819	0.3872
0.6028	0.9596	1770	0.5138	0.7636	0.6193	0.2810	0.3866
0.5836	0.9623	1775	0.5136	0.7641	0.6211	0.2823	0.3882
0.4832	0.9650	1780	0.5140	0.7634	0.6165	0.2841	0.3890
0.5918	0.9677	1785	0.5139	0.7629	0.6128	0.2868	0.3907
0.5778	0.9705	1790	0.5140	0.7629	0.6124	0.2877	0.3915
0.5671	0.9732	1795	0.5144	0.7638	0.6162	0.2895	0.3939
0.5434	0.9759	1800	0.5143	0.7631	0.6116	0.2917	0.3950
0.5667	0.9786	1805	0.5145	0.7636	0.6133	0.2931	0.3966
0.6422	0.9813	1810	0.5144	0.7633	0.6122	0.2917	0.3952
0.7449	0.9840	1815	0.5142	0.7630	0.6106	0.2926	0.3956
0.661	0.9867	1820	0.5144	0.7625	0.6094	0.2904	0.3933
0.467	0.9894	1825	0.5145	0.7631	0.6123	0.2904	0.3939
0.5339	0.9921	1830	0.5144	0.7636	0.6139	0.2917	0.3955
0.4899	0.9948	1835	0.5145	0.7627	0.6096	0.2913	0.3942
0.5254	0.9976	1840	0.5147	0.7633	0.6122	0.2917	0.3952

Framework versions

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