sciqqa_noaugs_masked_qwen_lora

This model is a fine-tuned version of Daewon0808/prm800k_qwen_fulltune on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2775
• Prm accuracy: 0.8968
• Prm precision: 0.9896
• Prm recall: 0.8879
• Prm specificty: 0.9474
• Prm npv: 0.6
• Prm f1: 0.9360
• Prm f1 neg: 0.7347
• Prm f1 auc: 0.9176
• Prm f1 auc (fixed): 0.9358

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 4
• seed: 908932403
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Prm accuracy	Prm precision	Prm recall	Prm specificty	Prm npv	Prm f1	Prm f1 neg	Prm f1 auc	Prm f1 auc (fixed)
No log	0	0	0.6081	0.6905	0.9146	0.7009	0.6316	0.2727	0.7937	0.3810	0.6663	0.6702
0.6385	0.0038	5	0.6078	0.6825	0.9136	0.6916	0.6316	0.2667	0.7872	0.375	0.6616	0.6712
0.4928	0.0076	10	0.6039	0.6825	0.9036	0.7009	0.5789	0.2558	0.7895	0.3548	0.6399	0.6717
0.546	0.0113	15	0.5826	0.7222	0.9091	0.7477	0.5789	0.2895	0.8205	0.3860	0.6633	0.6709
0.4919	0.0151	20	0.5109	0.7857	0.9082	0.8318	0.5263	0.3571	0.8683	0.4255	0.6790	0.6800
0.498	0.0189	25	0.4043	0.8175	0.8559	0.9439	0.1053	0.25	0.8978	0.1481	0.5246	0.6874
0.3579	0.0227	30	0.4042	0.8333	0.8468	0.9813	0.0	0.0	0.9091	0.0	0.4907	0.7056
0.3826	0.0264	35	0.3958	0.8333	0.8468	0.9813	0.0	0.0	0.9091	0.0	0.4907	0.7241
0.3989	0.0302	40	0.3753	0.8254	0.8455	0.9720	0.0	0.0	0.9043	0.0	0.4860	0.7221
0.3773	0.0340	45	0.3845	0.8175	0.8684	0.9252	0.2105	0.3333	0.8959	0.2581	0.5679	0.7245
0.394	0.0378	50	0.3924	0.8333	0.8839	0.9252	0.3158	0.4286	0.9041	0.3636	0.6205	0.7275
0.4451	0.0415	55	0.3828	0.8333	0.8839	0.9252	0.3158	0.4286	0.9041	0.3636	0.6205	0.7403
0.3329	0.0453	60	0.3694	0.8413	0.8655	0.9626	0.1579	0.4286	0.9115	0.2308	0.5603	0.7523
0.2341	0.0491	65	0.3743	0.8254	0.8512	0.9626	0.0526	0.2	0.9035	0.0833	0.5076	0.7607
0.598	0.0529	70	0.3698	0.8333	0.8583	0.9626	0.1053	0.3333	0.9075	0.16	0.5339	0.7725
0.3966	0.0566	75	0.3723	0.8333	0.8772	0.9346	0.2632	0.4167	0.9050	0.3226	0.5989	0.7681
0.2968	0.0604	80	0.3801	0.8175	0.8889	0.8972	0.3684	0.3889	0.8930	0.3784	0.6328	0.7661
0.3936	0.0642	85	0.3565	0.8254	0.8571	0.9533	0.1053	0.2857	0.9027	0.1538	0.5293	0.7720
0.6123	0.0680	90	0.3608	0.8175	0.8443	0.9626	0.0	0.0	0.8996	0.0	0.4813	0.7774
0.2802	0.0718	95	0.3490	0.8254	0.8512	0.9626	0.0526	0.2	0.9035	0.0833	0.5076	0.7725
0.3323	0.0755	100	0.3514	0.8254	0.8632	0.9439	0.1579	0.3333	0.9018	0.2143	0.5509	0.7787
0.3634	0.0793	105	0.3479	0.8413	0.8718	0.9533	0.2105	0.4444	0.9107	0.2857	0.5819	0.7890
0.4573	0.0831	110	0.3547	0.8175	0.875	0.9159	0.2632	0.3571	0.8950	0.3030	0.5895	0.7949
0.3029	0.0869	115	0.3677	0.8016	0.8727	0.8972	0.2632	0.3125	0.8848	0.2857	0.5802	0.7924
0.4164	0.0906	120	0.3717	0.8333	0.8772	0.9346	0.2632	0.4167	0.9050	0.3226	0.5989	0.7791
0.1918	0.0944	125	0.3705	0.8254	0.8632	0.9439	0.1579	0.3333	0.9018	0.2143	0.5509	0.7809
0.3394	0.0982	130	0.3652	0.8175	0.875	0.9159	0.2632	0.3571	0.8950	0.3030	0.5895	0.7897
0.4407	0.1020	135	0.3553	0.8333	0.8772	0.9346	0.2632	0.4167	0.9050	0.3226	0.5989	0.7959
0.3097	0.1057	140	0.3518	0.8254	0.8632	0.9439	0.1579	0.3333	0.9018	0.2143	0.5509	0.8008
0.2729	0.1095	145	0.3570	0.8254	0.8761	0.9252	0.2632	0.3846	0.9	0.3125	0.5942	0.8005
0.3682	0.1133	150	0.3600	0.8175	0.8818	0.9065	0.3158	0.375	0.8940	0.3429	0.6112	0.8057
0.2771	0.1171	155	0.3457	0.8333	0.8707	0.9439	0.2105	0.4	0.9058	0.2759	0.5772	0.8084
0.3597	0.1208	160	0.3620	0.7937	0.8649	0.8972	0.2105	0.2667	0.8807	0.2353	0.5539	0.7996
0.294	0.1246	165	0.3559	0.8175	0.8684	0.9252	0.2105	0.3333	0.8959	0.2581	0.5679	0.7971
0.4535	0.1284	170	0.3571	0.8095	0.8547	0.9346	0.1053	0.2222	0.8929	0.1429	0.5199	0.7988
0.3241	0.1322	175	0.3865	0.8254	0.8972	0.8972	0.4211	0.4211	0.8972	0.4211	0.6591	0.7892
0.2695	0.1360	180	0.3794	0.8254	0.9048	0.8879	0.4737	0.4286	0.8962	0.45	0.6808	0.7993
0.3834	0.1397	185	0.3515	0.8095	0.8547	0.9346	0.1053	0.2222	0.8929	0.1429	0.5199	0.8182
0.3114	0.1435	190	0.3326	0.8333	0.8772	0.9346	0.2632	0.4167	0.9050	0.3226	0.5989	0.8276
0.2343	0.1473	195	0.3423	0.8333	0.9057	0.8972	0.4737	0.45	0.9014	0.4615	0.6854	0.8298
0.3194	0.1511	200	0.3364	0.8254	0.8696	0.9346	0.2105	0.3636	0.9009	0.2667	0.5726	0.8325
0.2724	0.1548	205	0.3598	0.8175	0.8684	0.9252	0.2105	0.3333	0.8959	0.2581	0.5679	0.8320
0.2524	0.1586	210	0.3650	0.8254	0.8761	0.9252	0.2632	0.3846	0.9	0.3125	0.5942	0.8313
0.2784	0.1624	215	0.3719	0.8413	0.8850	0.9346	0.3158	0.4615	0.9091	0.375	0.6252	0.8310
0.2646	0.1662	220	0.3638	0.8254	0.8632	0.9439	0.1579	0.3333	0.9018	0.2143	0.5509	0.8318
0.2213	0.1699	225	0.3436	0.8413	0.8783	0.9439	0.2632	0.4545	0.9099	0.3333	0.6035	0.8323
0.3227	0.1737	230	0.3316	0.8254	0.8696	0.9346	0.2105	0.3636	0.9009	0.2667	0.5726	0.8360
0.4916	0.1775	235	0.3277	0.8333	0.8772	0.9346	0.2632	0.4167	0.9050	0.3226	0.5989	0.8347
0.231	0.1813	240	0.3417	0.8492	0.9	0.9252	0.4211	0.5	0.9124	0.4571	0.6731	0.8328
0.2534	0.1850	245	0.3519	0.8413	0.8919	0.9252	0.3684	0.4667	0.9083	0.4118	0.6468	0.8379
0.1744	0.1888	250	0.3645	0.8175	0.8684	0.9252	0.2105	0.3333	0.8959	0.2581	0.5679	0.8325
0.1956	0.1926	255	0.3743	0.8254	0.8829	0.9159	0.3158	0.4	0.8991	0.3529	0.6158	0.8384
0.2433	0.1964	260	0.3851	0.8333	0.8909	0.9159	0.3684	0.4375	0.9032	0.4	0.6422	0.8392
0.1635	0.2002	265	0.3914	0.8333	0.8909	0.9159	0.3684	0.4375	0.9032	0.4	0.6422	0.8394
0.2518	0.2039	270	0.3686	0.8333	0.8839	0.9252	0.3158	0.4286	0.9041	0.3636	0.6205	0.8337
0.1965	0.2077	275	0.3608	0.8333	0.8909	0.9159	0.3684	0.4375	0.9032	0.4	0.6422	0.8328
0.1828	0.2115	280	0.3587	0.8175	0.8818	0.9065	0.3158	0.375	0.8940	0.3429	0.6112	0.8357
0.1828	0.2153	285	0.3682	0.8333	0.8981	0.9065	0.4211	0.4444	0.9023	0.4324	0.6638	0.8369
0.3494	0.2190	290	0.3765	0.8413	0.8991	0.9159	0.4211	0.4706	0.9074	0.4444	0.6685	0.8426
0.1442	0.2228	295	0.3848	0.8254	0.8899	0.9065	0.3684	0.4118	0.8981	0.3889	0.6375	0.8500
0.48	0.2266	300	0.3995	0.8492	0.9231	0.8972	0.5789	0.5	0.9100	0.5366	0.7381	0.8480
0.273	0.2304	305	0.4264	0.8413	0.9394	0.8692	0.6842	0.4815	0.9029	0.5652	0.7767	0.8424
0.2761	0.2341	310	0.3866	0.8333	0.9057	0.8972	0.4737	0.45	0.9014	0.4615	0.6854	0.8510
0.275	0.2379	315	0.3683	0.8333	0.8981	0.9065	0.4211	0.4444	0.9023	0.4324	0.6638	0.8465
0.1085	0.2417	320	0.3759	0.8333	0.9057	0.8972	0.4737	0.45	0.9014	0.4615	0.6854	0.8460
0.1563	0.2455	325	0.4183	0.8333	0.9216	0.8785	0.5789	0.4583	0.8995	0.5116	0.7287	0.8500
0.1716	0.2492	330	0.4099	0.8333	0.9216	0.8785	0.5789	0.4583	0.8995	0.5116	0.7287	0.8571
0.2344	0.2530	335	0.3944	0.8254	0.9126	0.8785	0.5263	0.4348	0.8952	0.4762	0.7024	0.8645
0.2226	0.2568	340	0.3944	0.8333	0.93	0.8692	0.6316	0.4615	0.8986	0.5333	0.7504	0.8652
0.1149	0.2606	345	0.3895	0.8333	0.93	0.8692	0.6316	0.4615	0.8986	0.5333	0.7504	0.8679
0.3667	0.2644	350	0.3767	0.8254	0.9293	0.8598	0.6316	0.4444	0.8932	0.5217	0.7457	0.8697
0.2327	0.2681	355	0.3481	0.8492	0.9490	0.8692	0.7368	0.5	0.9073	0.5957	0.8030	0.8765
0.2695	0.2719	360	0.3490	0.8571	0.9495	0.8785	0.7368	0.5185	0.9126	0.6087	0.8077	0.8810
0.1497	0.2757	365	0.3314	0.8571	0.9495	0.8785	0.7368	0.5185	0.9126	0.6087	0.8077	0.8854
0.1042	0.2795	370	0.3265	0.8571	0.9320	0.8972	0.6316	0.5217	0.9143	0.5714	0.7644	0.8888
0.2562	0.2832	375	0.3505	0.8492	0.94	0.8785	0.6842	0.5	0.9082	0.5778	0.7814	0.8824
0.1686	0.2870	380	0.3760	0.8413	0.9485	0.8598	0.7368	0.4828	0.9020	0.5833	0.7983	0.8780
0.2691	0.2908	385	0.3779	0.8492	0.9583	0.8598	0.7895	0.5	0.9064	0.6122	0.8246	0.8775
0.0963	0.2946	390	0.3801	0.8571	0.9588	0.8692	0.7895	0.5172	0.9118	0.625	0.8293	0.8721
0.2267	0.2983	395	0.3910	0.8333	0.9388	0.8598	0.6842	0.4643	0.8976	0.5532	0.7720	0.8682
0.1731	0.3021	400	0.4036	0.8175	0.9375	0.8411	0.6842	0.4333	0.8867	0.5306	0.7627	0.8672
0.1307	0.3059	405	0.4109	0.8254	0.9474	0.8411	0.7368	0.4516	0.8911	0.56	0.7890	0.8687
0.1398	0.3097	410	0.3803	0.8333	0.9216	0.8785	0.5789	0.4583	0.8995	0.5116	0.7287	0.8733
0.1262	0.3134	415	0.3765	0.8333	0.9135	0.8879	0.5263	0.4545	0.9005	0.4878	0.7071	0.8721
0.278	0.3172	420	0.3719	0.8413	0.9223	0.8879	0.5789	0.4783	0.9048	0.5238	0.7334	0.8669
0.3012	0.3210	425	0.3763	0.8333	0.93	0.8692	0.6316	0.4615	0.8986	0.5333	0.7504	0.8682
0.0863	0.3248	430	0.3632	0.8254	0.9293	0.8598	0.6316	0.4444	0.8932	0.5217	0.7457	0.8728
0.157	0.3285	435	0.3599	0.8175	0.9118	0.8692	0.5263	0.4167	0.8900	0.4651	0.6977	0.8746
0.0816	0.3323	440	0.3503	0.8413	0.9223	0.8879	0.5789	0.4783	0.9048	0.5238	0.7334	0.8783
0.1013	0.3361	445	0.3357	0.8254	0.9208	0.8692	0.5789	0.44	0.8942	0.5	0.7241	0.8795
0.1326	0.3399	450	0.3567	0.8413	0.9485	0.8598	0.7368	0.4828	0.9020	0.5833	0.7983	0.8726
0.1505	0.3437	455	0.3640	0.8492	0.9583	0.8598	0.7895	0.5	0.9064	0.6122	0.8246	0.8706
0.1813	0.3474	460	0.3410	0.8730	0.9505	0.8972	0.7368	0.56	0.9231	0.6364	0.8170	0.8788
0.1044	0.3512	465	0.3238	0.8651	0.9412	0.8972	0.6842	0.5417	0.9187	0.6047	0.7907	0.8893
0.067	0.3550	470	0.3305	0.8571	0.9406	0.8879	0.6842	0.52	0.9135	0.5909	0.7860	0.8957
0.0945	0.3588	475	0.3576	0.8413	0.9579	0.8505	0.7895	0.4839	0.9010	0.6	0.8200	0.8923
0.0482	0.3625	480	0.3570	0.8413	0.9579	0.8505	0.7895	0.4839	0.9010	0.6	0.8200	0.8915
0.0886	0.3663	485	0.3367	0.8413	0.9579	0.8505	0.7895	0.4839	0.9010	0.6	0.8200	0.8896
0.1636	0.3701	490	0.3469	0.8571	0.9684	0.8598	0.8421	0.5161	0.9109	0.64	0.8510	0.8898
0.1143	0.3739	495	0.3598	0.8571	0.9684	0.8598	0.8421	0.5161	0.9109	0.64	0.8510	0.8879
0.1518	0.3776	500	0.3407	0.8651	0.9688	0.8692	0.8421	0.5333	0.9163	0.6531	0.8556	0.8896
0.3155	0.3814	505	0.3007	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.8947
0.4684	0.3852	510	0.2919	0.8730	0.9505	0.8972	0.7368	0.56	0.9231	0.6364	0.8170	0.8913
0.0565	0.3890	515	0.3044	0.8651	0.95	0.8879	0.7368	0.5385	0.9179	0.6222	0.8123	0.8920
0.1134	0.3927	520	0.3411	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.8918
0.1935	0.3965	525	0.3482	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.8945
0.1482	0.4003	530	0.3368	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.8994
0.1269	0.4041	535	0.3155	0.8651	0.95	0.8879	0.7368	0.5385	0.9179	0.6222	0.8123	0.8984
0.0869	0.4079	540	0.3132	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.8974
0.0613	0.4116	545	0.3115	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.9033
0.0776	0.4154	550	0.3160	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.9070
0.1956	0.4192	555	0.3147	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.9063
0.1022	0.4230	560	0.3114	0.8810	0.96	0.8972	0.7895	0.5769	0.9275	0.6667	0.8433	0.9043
0.153	0.4267	565	0.3079	0.8571	0.9406	0.8879	0.6842	0.52	0.9135	0.5909	0.7860	0.9075
0.0976	0.4305	570	0.3143	0.8571	0.9495	0.8785	0.7368	0.5185	0.9126	0.6087	0.8077	0.9088
0.1728	0.4343	575	0.3130	0.8571	0.9495	0.8785	0.7368	0.5185	0.9126	0.6087	0.8077	0.9073
0.0927	0.4381	580	0.3185	0.8571	0.9495	0.8785	0.7368	0.5185	0.9126	0.6087	0.8077	0.9065
0.2111	0.4418	585	0.3186	0.8571	0.9588	0.8692	0.7895	0.5172	0.9118	0.625	0.8293	0.9147
0.2632	0.4456	590	0.3516	0.8651	0.9787	0.8598	0.8947	0.5312	0.9154	0.6667	0.8773	0.9169
0.0907	0.4494	595	0.3562	0.8571	0.9684	0.8598	0.8421	0.5161	0.9109	0.64	0.8510	0.9159
0.2318	0.4532	600	0.3217	0.8651	0.9592	0.8785	0.7895	0.5357	0.9171	0.6383	0.8340	0.9159
0.0327	0.4569	605	0.3137	0.8810	0.96	0.8972	0.7895	0.5769	0.9275	0.6667	0.8433	0.9124
0.2628	0.4607	610	0.3008	0.8810	0.96	0.8972	0.7895	0.5769	0.9275	0.6667	0.8433	0.9139
0.2209	0.4645	615	0.2882	0.8810	0.96	0.8972	0.7895	0.5769	0.9275	0.6667	0.8433	0.9139
0.087	0.4683	620	0.2999	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9137
0.1212	0.4721	625	0.3059	0.8810	0.9694	0.8879	0.8421	0.5714	0.9268	0.6809	0.8650	0.9134
0.0392	0.4758	630	0.3034	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9110
0.0534	0.4796	635	0.2982	0.8968	0.9608	0.9159	0.7895	0.625	0.9378	0.6977	0.8527	0.9122
0.2347	0.4834	640	0.2935	0.8810	0.9423	0.9159	0.6842	0.5909	0.9289	0.6341	0.8000	0.9120
0.1026	0.4872	645	0.2889	0.8810	0.9423	0.9159	0.6842	0.5909	0.9289	0.6341	0.8000	0.9080
0.1179	0.4909	650	0.2885	0.8889	0.9515	0.9159	0.7368	0.6087	0.9333	0.6667	0.8264	0.9063
0.0637	0.4947	655	0.2891	0.8730	0.9505	0.8972	0.7368	0.56	0.9231	0.6364	0.8170	0.9043
0.2306	0.4985	660	0.2921	0.8730	0.9505	0.8972	0.7368	0.56	0.9231	0.6364	0.8170	0.9011
0.0569	0.5023	665	0.3070	0.8810	0.96	0.8972	0.7895	0.5769	0.9275	0.6667	0.8433	0.8984
0.0969	0.5060	670	0.3124	0.8810	0.9694	0.8879	0.8421	0.5714	0.9268	0.6809	0.8650	0.8994
0.0859	0.5098	675	0.3053	0.8810	0.96	0.8972	0.7895	0.5769	0.9275	0.6667	0.8433	0.8994
0.1873	0.5136	680	0.3143	0.8810	0.96	0.8972	0.7895	0.5769	0.9275	0.6667	0.8433	0.9001
0.1293	0.5174	685	0.3350	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.9001
0.2524	0.5211	690	0.3780	0.8571	0.9588	0.8692	0.7895	0.5172	0.9118	0.625	0.8293	0.9041
0.073	0.5249	695	0.4126	0.8333	0.9674	0.8318	0.8421	0.4706	0.8945	0.6038	0.8369	0.9065
0.0514	0.5287	700	0.3931	0.8333	0.9574	0.8411	0.7895	0.4688	0.8955	0.5882	0.8153	0.9068
0.1408	0.5325	705	0.3500	0.8413	0.9579	0.8505	0.7895	0.4839	0.9010	0.6	0.8200	0.9092
0.0275	0.5363	710	0.3177	0.8651	0.9592	0.8785	0.7895	0.5357	0.9171	0.6383	0.8340	0.9092
0.1079	0.5400	715	0.3097	0.8889	0.9604	0.9065	0.7895	0.6	0.9327	0.6818	0.8480	0.9100
0.1745	0.5438	720	0.3008	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.9115
0.0713	0.5476	725	0.2943	0.8651	0.9592	0.8785	0.7895	0.5357	0.9171	0.6383	0.8340	0.9100
0.3159	0.5514	730	0.2942	0.8571	0.9588	0.8692	0.7895	0.5172	0.9118	0.625	0.8293	0.9097
0.1935	0.5551	735	0.3000	0.8651	0.9688	0.8692	0.8421	0.5333	0.9163	0.6531	0.8556	0.9110
0.172	0.5589	740	0.2824	0.8651	0.9688	0.8692	0.8421	0.5333	0.9163	0.6531	0.8556	0.9097
0.0745	0.5627	745	0.2831	0.8651	0.9688	0.8692	0.8421	0.5333	0.9163	0.6531	0.8556	0.9097
0.0462	0.5665	750	0.2744	0.8651	0.9688	0.8692	0.8421	0.5333	0.9163	0.6531	0.8556	0.9139
0.1097	0.5702	755	0.2682	0.8651	0.95	0.8879	0.7368	0.5385	0.9179	0.6222	0.8123	0.9164
0.0354	0.5740	760	0.2701	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.9176
0.084	0.5778	765	0.2666	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.9174
0.1478	0.5816	770	0.2712	0.8730	0.9596	0.8879	0.7895	0.5556	0.9223	0.6522	0.8387	0.9169
0.1632	0.5853	775	0.2733	0.8651	0.9592	0.8785	0.7895	0.5357	0.9171	0.6383	0.8340	0.9206
0.1185	0.5891	780	0.2815	0.8810	0.9792	0.8785	0.8947	0.5667	0.9261	0.6939	0.8866	0.9223
0.0871	0.5929	785	0.2901	0.8730	0.9789	0.8692	0.8947	0.5484	0.9208	0.68	0.8819	0.9198
0.1045	0.5967	790	0.2900	0.8651	0.9688	0.8692	0.8421	0.5333	0.9163	0.6531	0.8556	0.9225
0.1288	0.6005	795	0.2755	0.8730	0.9691	0.8785	0.8421	0.5517	0.9216	0.6667	0.8603	0.9208
0.176	0.6042	800	0.2572	0.8810	0.9694	0.8879	0.8421	0.5714	0.9268	0.6809	0.8650	0.9191
0.0711	0.6080	805	0.2534	0.8810	0.9694	0.8879	0.8421	0.5714	0.9268	0.6809	0.8650	0.9203
0.0778	0.6118	810	0.2548	0.8810	0.9694	0.8879	0.8421	0.5714	0.9268	0.6809	0.8650	0.9201
0.1253	0.6156	815	0.2572	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9203
0.0736	0.6193	820	0.2660	0.8810	0.9694	0.8879	0.8421	0.5714	0.9268	0.6809	0.8650	0.9193
0.1462	0.6231	825	0.2706	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9191
0.0322	0.6269	830	0.2798	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9201
0.1017	0.6307	835	0.2861	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9220
0.1343	0.6344	840	0.2805	0.8968	0.97	0.9065	0.8421	0.6154	0.9372	0.7111	0.8743	0.9233
0.1605	0.6382	845	0.2796	0.8968	0.97	0.9065	0.8421	0.6154	0.9372	0.7111	0.8743	0.9223
0.0955	0.6420	850	0.2813	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9223
0.1326	0.6458	855	0.2887	0.8730	0.9691	0.8785	0.8421	0.5517	0.9216	0.6667	0.8603	0.9238
0.1332	0.6495	860	0.2834	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9233
0.1101	0.6533	865	0.2776	0.8968	0.97	0.9065	0.8421	0.6154	0.9372	0.7111	0.8743	0.9250
0.1003	0.6571	870	0.2579	0.8968	0.97	0.9065	0.8421	0.6154	0.9372	0.7111	0.8743	0.9270
0.2752	0.6609	875	0.2433	0.8968	0.97	0.9065	0.8421	0.6154	0.9372	0.7111	0.8743	0.9277
0.1615	0.6647	880	0.2415	0.8889	0.9604	0.9065	0.7895	0.6	0.9327	0.6818	0.8480	0.9297
0.1292	0.6684	885	0.2431	0.8889	0.9604	0.9065	0.7895	0.6	0.9327	0.6818	0.8480	0.9272
0.2202	0.6722	890	0.2423	0.8889	0.9604	0.9065	0.7895	0.6	0.9327	0.6818	0.8480	0.9242
0.0293	0.6760	895	0.2340	0.8968	0.97	0.9065	0.8421	0.6154	0.9372	0.7111	0.8743	0.9267
0.0622	0.6798	900	0.2452	0.9048	0.9798	0.9065	0.8947	0.6296	0.9417	0.7391	0.9006	0.9287
0.0972	0.6835	905	0.2549	0.8968	0.9796	0.8972	0.8947	0.6071	0.9366	0.7234	0.8960	0.9302
0.0657	0.6873	910	0.2641	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9297
0.059	0.6911	915	0.2764	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9324
0.0267	0.6949	920	0.2913	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9306
0.115	0.6986	925	0.2999	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9331
0.1118	0.7024	930	0.3030	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9353
0.1306	0.7062	935	0.2844	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9351
0.0938	0.7100	940	0.2677	0.9127	0.9898	0.9065	0.9474	0.6429	0.9463	0.7660	0.9270	0.9375
0.1011	0.7137	945	0.2698	0.9127	0.9898	0.9065	0.9474	0.6429	0.9463	0.7660	0.9270	0.9378
0.0306	0.7175	950	0.2727	0.9127	0.9898	0.9065	0.9474	0.6429	0.9463	0.7660	0.9270	0.9383
0.2848	0.7213	955	0.2827	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9390
0.0458	0.7251	960	0.2826	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9378
0.135	0.7289	965	0.2807	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9370
0.2891	0.7326	970	0.2704	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9365
0.1518	0.7364	975	0.2526	0.9127	0.9898	0.9065	0.9474	0.6429	0.9463	0.7660	0.9270	0.9353
0.0747	0.7402	980	0.2464	0.9127	0.9898	0.9065	0.9474	0.6429	0.9463	0.7660	0.9270	0.9341
0.1213	0.7440	985	0.2451	0.9127	0.9898	0.9065	0.9474	0.6429	0.9463	0.7660	0.9270	0.9331
0.0319	0.7477	990	0.2451	0.9127	0.9898	0.9065	0.9474	0.6429	0.9463	0.7660	0.9270	0.9331
0.0346	0.7515	995	0.2448	0.9127	0.9898	0.9065	0.9474	0.6429	0.9463	0.7660	0.9270	0.9329
0.0656	0.7553	1000	0.2458	0.9048	0.9798	0.9065	0.8947	0.6296	0.9417	0.7391	0.9006	0.9331
0.1061	0.7591	1005	0.2492	0.9048	0.9798	0.9065	0.8947	0.6296	0.9417	0.7391	0.9006	0.9336
0.0346	0.7628	1010	0.2515	0.9048	0.9798	0.9065	0.8947	0.6296	0.9417	0.7391	0.9006	0.9329
0.0292	0.7666	1015	0.2466	0.9048	0.9798	0.9065	0.8947	0.6296	0.9417	0.7391	0.9006	0.9343
0.0713	0.7704	1020	0.2472	0.9048	0.9798	0.9065	0.8947	0.6296	0.9417	0.7391	0.9006	0.9343
0.1907	0.7742	1025	0.2473	0.8968	0.97	0.9065	0.8421	0.6154	0.9372	0.7111	0.8743	0.9341
0.035	0.7779	1030	0.2523	0.8968	0.97	0.9065	0.8421	0.6154	0.9372	0.7111	0.8743	0.9346
0.0634	0.7817	1035	0.2544	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9336
0.046	0.7855	1040	0.2571	0.8968	0.97	0.9065	0.8421	0.6154	0.9372	0.7111	0.8743	0.9336
0.1029	0.7893	1045	0.2609	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9326
0.0225	0.7931	1050	0.2679	0.8889	0.9697	0.8972	0.8421	0.5926	0.9320	0.6957	0.8697	0.9331
0.0589	0.7968	1055	0.2713	0.8968	0.9796	0.8972	0.8947	0.6071	0.9366	0.7234	0.8960	0.9338
0.0316	0.8006	1060	0.2742	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9338
0.0329	0.8044	1065	0.2732	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9316
0.0358	0.8082	1070	0.2710	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9331
0.1176	0.8119	1075	0.2711	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9329
0.0965	0.8157	1080	0.2709	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9336
0.1119	0.8195	1085	0.2726	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9336
0.0547	0.8233	1090	0.2757	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9326
0.0804	0.8270	1095	0.2790	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9336
0.0996	0.8308	1100	0.2756	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9324
0.0618	0.8346	1105	0.2741	0.8968	0.9796	0.8972	0.8947	0.6071	0.9366	0.7234	0.8960	0.9341
0.1504	0.8384	1110	0.2753	0.8889	0.9794	0.8879	0.8947	0.5862	0.9314	0.7083	0.8913	0.9336
0.063	0.8421	1115	0.2771	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9324
0.0467	0.8459	1120	0.2826	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9331
0.0246	0.8497	1125	0.2803	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9336
0.04	0.8535	1130	0.2778	0.8889	0.9794	0.8879	0.8947	0.5862	0.9314	0.7083	0.8913	0.9329
0.1134	0.8573	1135	0.2786	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9336
0.1396	0.8610	1140	0.2799	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9341
0.1252	0.8648	1145	0.2807	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9348
0.0448	0.8686	1150	0.2852	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9331
0.0655	0.8724	1155	0.2867	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9341
0.0286	0.8761	1160	0.2842	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9348
0.0217	0.8799	1165	0.2850	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9346
0.0161	0.8837	1170	0.2820	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9346
0.1203	0.8875	1175	0.2814	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9346
0.0881	0.8912	1180	0.2805	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9356
0.1188	0.8950	1185	0.2788	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9351
0.0502	0.8988	1190	0.2774	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9358
0.065	0.9026	1195	0.2776	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9363
0.0777	0.9063	1200	0.2786	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9365
0.0944	0.9101	1205	0.2794	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9370
0.0688	0.9139	1210	0.2797	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9375
0.0273	0.9177	1215	0.2807	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9365
0.1101	0.9215	1220	0.2808	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9365
0.2071	0.9252	1225	0.2815	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9365
0.0514	0.9290	1230	0.2793	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9365
0.1012	0.9328	1235	0.2797	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9356
0.1001	0.9366	1240	0.2771	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9361
0.1153	0.9403	1245	0.2777	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9353
0.1082	0.9441	1250	0.2783	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9363
0.0705	0.9479	1255	0.2780	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9365
0.1329	0.9517	1260	0.2778	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9368
0.024	0.9554	1265	0.2790	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9365
0.023	0.9592	1270	0.2775	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9370
0.1096	0.9630	1275	0.2768	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9370
0.0278	0.9668	1280	0.2771	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9368
0.0833	0.9705	1285	0.2788	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9363
0.0705	0.9743	1290	0.2781	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9363
0.1616	0.9781	1295	0.2767	0.8889	0.9895	0.8785	0.9474	0.5806	0.9307	0.72	0.9129	0.9361
0.0467	0.9819	1300	0.2759	0.9048	0.9897	0.8972	0.9474	0.6207	0.9412	0.75	0.9223	0.9370
0.1176	0.9856	1305	0.2762	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9375
0.2117	0.9894	1310	0.2766	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9365
0.1356	0.9932	1315	0.2770	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9368
0.2054	0.9970	1320	0.2775	0.8968	0.9896	0.8879	0.9474	0.6	0.9360	0.7347	0.9176	0.9358

Framework versions

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