learning_rate: 5e-06
train_batch_size: 8
eval_batch_size: 8
seed: 0
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: 0.01
num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss
3.1118	0.0811	3	3.2024
3.0902	0.1622	6	3.2023
2.9193	0.2432	9	3.1908
3.0231	0.3243	12	3.1700
3.0429	0.4054	15	3.1323
2.9739	0.4865	18	3.0926
2.9118	0.5676	21	3.0477
2.8564	0.6486	24	2.9984
2.9689	0.7297	27	2.9489
2.8155	0.8108	30	2.8946
2.8495	0.8919	33	2.8411
2.7311	0.9730	36	2.7843
2.6327	1.0541	39	2.7375
2.6728	1.1351	42	2.6747
2.5236	1.2162	45	2.6151
2.5009	1.2973	48	2.5595
2.4129	1.3784	51	2.5030
2.3506	1.4595	54	2.4369
2.3542	1.5405	57	2.3803
2.237	1.6216	60	2.3189
2.3302	1.7027	63	2.2589
2.1679	1.7838	66	2.2005
2.1406	1.8649	69	2.1355
2.0373	1.9459	72	2.0689
1.9979	2.0270	75	2.0098
2.0711	2.1081	78	1.9351
1.8819	2.1892	81	1.8753
1.7832	2.2703	84	1.8243
1.7165	2.3514	87	1.7668
1.6765	2.4324	90	1.7111
1.6243	2.5135	93	1.6613
1.6819	2.5946	96	1.6154
1.6006	2.6757	99	1.5679
1.4845	2.7568	102	1.5229
1.4014	2.8378	105	1.4728
1.452	2.9189	108	1.4313
1.3642	3.0	111	1.3985
1.3571	3.0811	114	1.3647
1.4434	3.1622	117	1.3416
1.3829	3.2432	120	1.3206
1.3319	3.3243	123	1.3000
1.2262	3.4054	126	1.2851
1.2693	3.4865	129	1.2711
1.264	3.5676	132	1.2588
1.1851	3.6486	135	1.2470
1.2656	3.7297	138	1.2380
1.205	3.8108	141	1.2244
1.2115	3.8919	144	1.2109
1.1366	3.9730	147	1.1997
1.1794	4.0541	150	1.1929
1.171	4.1351	153	1.1805
1.0875	4.2162	156	1.1714
1.1192	4.2973	159	1.1619
1.1082	4.3784	162	1.1548
1.0923	4.4595	165	1.1465
1.1731	4.5405	168	1.1397
1.2138	4.6216	171	1.1315
1.2322	4.7027	174	1.1223
1.0893	4.7838	177	1.1179
1.1414	4.8649	180	1.1116
1.0242	4.9459	183	1.1058
1.0929	5.0270	186	1.0982
1.0967	5.1081	189	1.0916
1.0666	5.1892	192	1.0866
1.1382	5.2703	195	1.0851
1.0709	5.3514	198	1.0781
1.0904	5.4324	201	1.0742
1.0521	5.5135	204	1.0699
0.9745	5.5946	207	1.0641
1.1268	5.6757	210	1.0624
1.0437	5.7568	213	1.0588
1.0124	5.8378	216	1.0578
1.0217	5.9189	219	1.0511
1.0656	6.0	222	1.0475
1.0841	6.0811	225	1.0454
1.1352	6.1622	228	1.0440
1.0402	6.2432	231	1.0407
1.0042	6.3243	234	1.0326
0.9738	6.4054	237	1.0295
0.9671	6.4865	240	1.0292
1.0515	6.5676	243	1.0282
0.9551	6.6486	246	1.0246
1.0084	6.7297	249	1.0210
0.9964	6.8108	252	1.0188
0.966	6.8919	255	1.0146
1.0284	6.9730	258	1.0113
1.0367	7.0541	261	1.0103
0.9015	7.1351	264	1.0056
0.9097	7.2162	267	1.0043
0.9598	7.2973	270	0.9998
1.1724	7.3784	273	0.9980
0.9607	7.4595	276	0.9947
0.9749	7.5405	279	0.9960
0.9704	7.6216	282	0.9924
0.9855	7.7027	285	0.9899
0.9368	7.7838	288	0.9853
0.9812	7.8649	291	0.9856
0.9809	7.9459	294	0.9809
0.9337	8.0270	297	0.9824
0.8848	8.1081	300	0.9759
0.876	8.1892	303	0.9751
0.97	8.2703	306	0.9734
1.1309	8.3514	309	0.9726
0.9012	8.4324	312	0.9709
1.0355	8.5135	315	0.9681
0.9047	8.5946	318	0.9663
0.9417	8.6757	321	0.9622
0.9266	8.7568	324	0.9613
0.8873	8.8378	327	0.9625
0.9364	8.9189	330	0.9598
0.9885	9.0	333	0.9539
0.91	9.0811	336	0.9538
1.0834	9.1622	339	0.9522
0.8694	9.2432	342	0.9502
1.0554	9.3243	345	0.9498
0.9123	9.4054	348	0.9484
0.9542	9.4865	351	0.9449
0.9287	9.5676	354	0.9417
0.8435	9.6486	357	0.9406
0.8419	9.7297	360	0.9374
0.8265	9.8108	363	0.9351
0.8677	9.8919	366	0.9343
0.9989	9.9730	369	0.9341
0.8331	10.0541	372	0.9329
0.8823	10.1351	375	0.9312
0.9312	10.2162	378	0.9299
0.8736	10.2973	381	0.9279
1.0039	10.3784	384	0.9259
0.8728	10.4595	387	0.9249
0.9946	10.5405	390	0.9216
0.8747	10.6216	393	0.9196
0.9043	10.7027	396	0.9183
0.8777	10.7838	399	0.9163
0.8023	10.8649	402	0.9160
0.9002	10.9459	405	0.9128
0.8568	11.0270	408	0.9146
0.9145	11.1081	411	0.9124
0.896	11.1892	414	0.9101
0.8151	11.2703	417	0.9067
0.8352	11.3514	420	0.9060
1.0484	11.4324	423	0.9044
0.8623	11.5135	426	0.9041
0.8942	11.5946	429	0.9022
0.8789	11.6757	432	0.9008
0.9077	11.7568	435	0.9000
0.8	11.8378	438	0.8999
0.8116	11.9189	441	0.8985
0.8382	12.0	444	0.8970
0.8267	12.0811	447	0.8962
0.9168	12.1622	450	0.8947
0.7878	12.2432	453	0.8949
0.8829	12.3243	456	0.8926
0.8465	12.4054	459	0.8935
0.882	12.4865	462	0.8914
0.8265	12.5676	465	0.8896
0.8846	12.6486	468	0.8891
0.7943	12.7297	471	0.8899
0.8846	12.8108	474	0.8883
0.8177	12.8919	477	0.8852
0.8807	12.9730	480	0.8840
0.893	13.0541	483	0.8822
0.7497	13.1351	486	0.8799
0.8803	13.2162	489	0.8785
0.917	13.2973	492	0.8797
0.8162	13.3784	495	0.8783
0.9659	13.4595	498	0.8799
0.8163	13.5405	501	0.8790
0.8139	13.6216	504	0.8753
0.7451	13.7027	507	0.8737
0.7726	13.7838	510	0.8738
0.821	13.8649	513	0.8714
0.8782	13.9459	516	0.8689
0.8563	14.0270	519	0.8700
0.8645	14.1081	522	0.8671
0.9223	14.1892	525	0.8676
0.8396	14.2703	528	0.8682
0.8224	14.3514	531	0.8679
0.7793	14.4324	534	0.8690
0.7911	14.5135	537	0.8650
0.7706	14.5946	540	0.8634
0.7983	14.6757	543	0.8606
0.7409	14.7568	546	0.8611
0.8634	14.8378	549	0.8594
0.8631	14.9189	552	0.8594
0.7624	15.0	555	0.8582
0.8568	15.0811	558	0.8568
0.8833	15.1622	561	0.8542
0.7804	15.2432	564	0.8514
0.9113	15.3243	567	0.8526
0.72	15.4054	570	0.8511
0.8631	15.4865	573	0.8498
0.6486	15.5676	576	0.8507
0.7745	15.6486	579	0.8507
0.8591	15.7297	582	0.8519
0.8479	15.8108	585	0.8515
0.7879	15.8919	588	0.8486
0.7829	15.9730	591	0.8483
0.7271	16.0541	594	0.8451
0.7425	16.1351	597	0.8464
0.7692	16.2162	600	0.8436
0.7492	16.2973	603	0.8459
0.7085	16.3784	606	0.8440
0.7351	16.4595	609	0.8429
0.8593	16.5405	612	0.8412
0.8999	16.6216	615	0.8400
0.8136	16.7027	618	0.8417
0.8415	16.7838	621	0.8393
0.849	16.8649	624	0.8400
0.798	16.9459	627	0.8409
0.7581	17.0270	630	0.8393
0.7244	17.1081	633	0.8376
0.7221	17.1892	636	0.8379
0.8085	17.2703	639	0.8363
0.7364	17.3514	642	0.8357
0.7684	17.4324	645	0.8385
0.7323	17.5135	648	0.8330
0.8999	17.5946	651	0.8334
0.7243	17.6757	654	0.8323
0.741	17.7568	657	0.8300
0.7529	17.8378	660	0.8290
0.9129	17.9189	663	0.8313
0.8043	18.0	666	0.8282
0.838	18.0811	669	0.8294
0.8133	18.1622	672	0.8294
0.708	18.2432	675	0.8283
0.8017	18.3243	678	0.8289
0.9087	18.4054	681	0.8256
0.6983	18.4865	684	0.8260
0.7684	18.5676	687	0.8251
0.6372	18.6486	690	0.8241
0.7369	18.7297	693	0.8261
0.819	18.8108	696	0.8231
0.6806	18.8919	699	0.8244
0.8233	18.9730	702	0.8237
0.7614	19.0541	705	0.8234
0.7862	19.1351	708	0.8212
0.6605	19.2162	711	0.8195
0.8229	19.2973	714	0.8194
0.731	19.3784	717	0.8193
0.783	19.4595	720	0.8187
0.6495	19.5405	723	0.8185
0.8034	19.6216	726	0.8173
0.7064	19.7027	729	0.8177
0.7276	19.7838	732	0.8156
0.8778	19.8649	735	0.8143
0.7399	19.9459	738	0.8126
0.7399	20.0270	741	0.8139
0.7912	20.1081	744	0.8153
0.8063	20.1892	747	0.8120
0.671	20.2703	750	0.8105
0.6342	20.3514	753	0.8113
0.8271	20.4324	756	0.8097
0.6755	20.5135	759	0.8099
0.762	20.5946	762	0.8084
0.9197	20.6757	765	0.8079
0.7844	20.7568	768	0.8094
0.6502	20.8378	771	0.8096
0.6877	20.9189	774	0.8078
0.7705	21.0	777	0.8074
0.6842	21.0811	780	0.8067
0.6799	21.1622	783	0.8066
0.7344	21.2432	786	0.8039
0.6554	21.3243	789	0.8051
0.7007	21.4054	792	0.8051
0.6292	21.4865	795	0.8040
0.7404	21.5676	798	0.8031
0.7976	21.6486	801	0.8030
1.0023	21.7297	804	0.8045
0.6626	21.8108	807	0.8042
0.8212	21.8919	810	0.8019
0.6982	21.9730	813	0.8029
0.7221	22.0541	816	0.8007
0.8042	22.1351	819	0.8013
0.775	22.2162	822	0.7999
0.7614	22.2973	825	0.7971
0.7132	22.3784	828	0.7972
0.647	22.4595	831	0.8001
0.692	22.5405	834	0.7968
0.7775	22.6216	837	0.7976
0.7764	22.7027	840	0.7980
0.6962	22.7838	843	0.7990
0.649	22.8649	846	0.7941
0.7853	22.9459	849	0.7940
0.6808	23.0270	852	0.7959
0.7018	23.1081	855	0.7948
0.6743	23.1892	858	0.7949
0.7512	23.2703	861	0.7926
0.7136	23.3514	864	0.7922
0.6847	23.4324	867	0.7943
0.7309	23.5135	870	0.7910
0.9269	23.5946	873	0.7903
0.7629	23.6757	876	0.7923
0.6551	23.7568	879	0.7896
0.7346	23.8378	882	0.7920
0.7469	23.9189	885	0.7921
0.6343	24.0	888	0.7925
0.7232	24.0811	891	0.7905
0.714	24.1622	894	0.7885
0.6603	24.2432	897	0.7885
0.6798	24.3243	900	0.7892
0.7163	24.4054	903	0.7889
0.8428	24.4865	906	0.7871
0.8125	24.5676	909	0.7875
0.7566	24.6486	912	0.7895
0.7167	24.7297	915	0.7874
0.65	24.8108	918	0.7861
0.6817	24.8919	921	0.7860
0.6185	24.9730	924	0.7879
0.7745	25.0541	927	0.7900
0.8923	25.1351	930	0.7871
0.7395	25.2162	933	0.7834
0.7361	25.2973	936	0.7842
0.676	25.3784	939	0.7835
0.7359	25.4595	942	0.7846
0.6533	25.5405	945	0.7829
0.6989	25.6216	948	0.7848
0.8168	25.7027	951	0.7837
0.6519	25.7838	954	0.7826
0.6951	25.8649	957	0.7840
0.5833	25.9459	960	0.7823
0.617	26.0270	963	0.7812
0.6778	26.1081	966	0.7829
0.6571	26.1892	969	0.7818
0.7921	26.2703	972	0.7811
0.6962	26.3514	975	0.7807
0.8437	26.4324	978	0.7814
0.6147	26.5135	981	0.7813
0.7263	26.5946	984	0.7803
0.6618	26.6757	987	0.7809
0.7502	26.7568	990	0.7835
0.6094	26.8378	993	0.7813
0.6506	26.9189	996	0.7800
0.7927	27.0	999	0.7807
0.8217	27.0811	1002	0.7816
0.5989	27.1622	1005	0.7786
0.7204	27.2432	1008	0.7782
0.6906	27.3243	1011	0.7785
0.7592	27.4054	1014	0.7777
0.8692	27.4865	1017	0.7778
0.587	27.5676	1020	0.7781
0.7139	27.6486	1023	0.7781
0.6367	27.7297	1026	0.7774
0.6502	27.8108	1029	0.7779
0.6956	27.8919	1032	0.7770
0.7137	27.9730	1035	0.7784
0.7062	28.0541	1038	0.7775
0.6568	28.1351	1041	0.7782
0.7612	28.2162	1044	0.7766
0.7177	28.2973	1047	0.7765
0.6537	28.3784	1050	0.7776
0.6742	28.4595	1053	0.7773
0.724	28.5405	1056	0.7778
0.8277	28.6216	1059	0.7763
0.609	28.7027	1062	0.7767
0.5459	28.7838	1065	0.7781
0.8179	28.8649	1068	0.7769
0.6419	28.9459	1071	0.7754
0.6947	29.0270	1074	0.7745
0.71	29.1081	1077	0.7751
0.5664	29.1892	1080	0.7747
0.7678	29.2703	1083	0.7741
0.7829	29.3514	1086	0.7732
0.7294	29.4324	1089	0.7729
0.679	29.5135	1092	0.7752
0.6838	29.5946	1095	0.7739
0.6918	29.6757	1098	0.7731
0.6563	29.7568	1101	0.7727
0.6946	29.8378	1104	0.7742
0.6884	29.9189	1107	0.7729
0.6851	30.0	1110	0.7744
0.5865	30.0811	1113	0.7744
0.6906	30.1622	1116	0.7746
0.6716	30.2432	1119	0.7751
0.7492	30.3243	1122	0.7736
0.6608	30.4054	1125	0.7709
0.6577	30.4865	1128	0.7710
0.7475	30.5676	1131	0.7722
0.7643	30.6486	1134	0.7694
0.8186	30.7297	1137	0.7711
0.7465	30.8108	1140	0.7724
0.6621	30.8919	1143	0.7728
0.579	30.9730	1146	0.7713
0.6014	31.0541	1149	0.7707
0.7663	31.1351	1152	0.7697
0.6609	31.2162	1155	0.7719
0.7984	31.2973	1158	0.7715
0.7166	31.3784	1161	0.7715
0.7276	31.4595	1164	0.7712
0.6179	31.5405	1167	0.7681
0.621	31.6216	1170	0.7707
0.743	31.7027	1173	0.7711
0.6733	31.7838	1176	0.7706
0.6066	31.8649	1179	0.7716
0.6787	31.9459	1182	0.7713
0.812	32.0270	1185	0.7708
0.7022	32.1081	1188	0.7695
0.6709	32.1892	1191	0.7721
0.5536	32.2703	1194	0.7716
0.7462	32.3514	1197	0.7693
0.7817	32.4324	1200	0.7686
0.7624	32.5135	1203	0.7719
0.6346	32.5946	1206	0.7696
0.6284	32.6757	1209	0.7717
0.654	32.7568	1212	0.7708
0.6406	32.8378	1215	0.7707
0.752	32.9189	1218	0.7690
0.5956	33.0	1221	0.7713
0.6772	33.0811	1224	0.7701
0.5034	33.1622	1227	0.7693
0.6292	33.2432	1230	0.7687
0.7374	33.3243	1233	0.7693
0.5385	33.4054	1236	0.7678
0.7198	33.4865	1239	0.7686
0.7642	33.5676	1242	0.7695
0.6984	33.6486	1245	0.7682
0.776	33.7297	1248	0.7694
0.7073	33.8108	1251	0.7700
0.8016	33.8919	1254	0.7683
0.7812	33.9730	1257	0.7662
0.578	34.0541	1260	0.7681
0.7074	34.1351	1263	0.7679
0.6142	34.2162	1266	0.7669
0.6469	34.2973	1269	0.7675
0.7334	34.3784	1272	0.7669
0.7086	34.4595	1275	0.7675
0.6302	34.5405	1278	0.7684
0.6576	34.6216	1281	0.7687
0.7496	34.7027	1284	0.7667
0.7836	34.7838	1287	0.7671
0.6405	34.8649	1290	0.7679
0.6088	34.9459	1293	0.7681
0.7511	35.0270	1296	0.7697
0.7591	35.1081	1299	0.7680
0.6207	35.1892	1302	0.7689
0.651	35.2703	1305	0.7660
0.6758	35.3514	1308	0.7694
0.7277	35.4324	1311	0.7680
0.7118	35.5135	1314	0.7663
0.706	35.5946	1317	0.7669
0.6595	35.6757	1320	0.7678
0.7253	35.7568	1323	0.7688
0.582	35.8378	1326	0.7694
0.7094	35.9189	1329	0.7684
0.7042	36.0	1332	0.7686
0.6486	36.0811	1335	0.7664
0.6691	36.1622	1338	0.7678
0.7937	36.2432	1341	0.7672
0.6343	36.3243	1344	0.7670
0.76	36.4054	1347	0.7674
0.5929	36.4865	1350	0.7690
0.6485	36.5676	1353	0.7674
0.7451	36.6486	1356	0.7663
0.6367	36.7297	1359	0.7691
0.6192	36.8108	1362	0.7656
0.7042	36.8919	1365	0.7682
0.6886	36.9730	1368	0.7682
0.8111	37.0541	1371	0.7690
0.6443	37.1351	1374	0.7690
0.6387	37.2162	1377	0.7679
0.7861	37.2973	1380	0.7668
0.6397	37.3784	1383	0.7670
0.6467	37.4595	1386	0.7688
0.6977	37.5405	1389	0.7699
0.7833	37.6216	1392	0.7672
0.6164	37.7027	1395	0.7675
0.7457	37.7838	1398	0.7690
0.6477	37.8649	1401	0.7681
0.7251	37.9459	1404	0.7674
0.5642	38.0270	1407	0.7672
0.786	38.1081	1410	0.7660
0.7014	38.1892	1413	0.7683
0.7747	38.2703	1416	0.7659
0.631	38.3514	1419	0.7675
0.6787	38.4324	1422	0.7671
0.6388	38.5135	1425	0.7684
0.5745	38.5946	1428	0.7666
0.6253	38.6757	1431	0.7668
0.6611	38.7568	1434	0.7688
0.6129	38.8378	1437	0.7666
0.7588	38.9189	1440	0.7670
0.7615	39.0	1443	0.7664
0.7449	39.0811	1446	0.7674
0.7012	39.1622	1449	0.7666
0.788	39.2432	1452	0.7676
0.5958	39.3243	1455	0.7666
0.675	39.4054	1458	0.7670
0.6761	39.4865	1461	0.7676
0.7046	39.5676	1464	0.7669
0.6198	39.6486	1467	0.7673
0.6646	39.7297	1470	0.7670
0.6161	39.8108	1473	0.7677
0.7152	39.8919	1476	0.7676
0.7365	39.9730	1479	0.7671

Framework versions

PEFT 0.13.2
Transformers 4.46.0
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0

sujithatz/quen_2.5_qlora

quen_2.5_qlora

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

sujithatz/
quen_2.5_qlora