results_1024_hard

SangMoone/results_1024_hard

results_1024_hard is a machine learning model from SangMoone. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as gemma.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

33% of all-time downloads

All-time downloads

Public

Repo size

53.4 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.json34.4 MB · 64%

At a glance

Library: peft
License: gemma
Access: Public
Created: Oct 24, 2024
Updated: Oct 24, 2024
SHA: 71c170ce

Base models

google/gemma-2b-it

Model card

From the Hugging Face model README

results_1024_hard

This model is a fine-tuned version of google/gemma-2b-it on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.7783

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: 3
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 24
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 20
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.5619	0.0390	10	3.6739
3.5429	0.0780	20	3.6357
3.5082	0.1170	30	3.5419
3.5337	0.1560	40	3.3450
3.4677	0.1950	50	3.0606
2.9464	0.2340	60	2.8547
2.7669	0.2730	70	2.6702
2.6965	0.3120	80	2.5309
2.5909	0.3510	90	2.4184
2.4393	0.3901	100	2.3441
2.4496	0.4291	110	2.3040
2.4013	0.4681	120	2.2693
2.3979	0.5071	130	2.2463
2.3603	0.5461	140	2.2143
2.221	0.5851	150	2.1913
2.3495	0.6241	160	2.1816
2.3647	0.6631	170	2.1766
2.3218	0.7021	180	2.1577
2.3126	0.7411	190	2.1344
2.1452	0.7801	200	2.1263
2.3334	0.8191	210	2.1238
2.2701	0.8581	220	2.1139
2.2801	0.8971	230	2.1050
2.2627	0.9361	240	2.0848
2.0111	0.9751	250	2.0796
2.2442	1.0141	260	2.0675
2.2478	1.0531	270	2.0694
2.282	1.0922	280	2.0713
2.2581	1.1312	290	2.0573
2.1635	1.1702	300	2.0495
2.004	1.2092	310	2.0506
2.191	1.2482	320	2.0578
2.1744	1.2872	330	2.0493
2.1702	1.3262	340	2.0327
2.1859	1.3652	350	2.0240
1.9934	1.4042	360	2.0287
2.2299	1.4432	370	2.0442
2.1927	1.4822	380	2.0247
2.1494	1.5212	390	2.0049
2.1116	1.5602	400	2.0000
1.9836	1.5992	410	2.0000
2.1745	1.6382	420	2.0106
2.1316	1.6772	430	2.0039
2.1532	1.7162	440	1.9822
2.0582	1.7552	450	1.9795
1.9695	1.7942	460	1.9824
2.1855	1.8333	470	2.0026
2.176	1.8723	480	1.9842
2.1188	1.9113	490	1.9598
2.0718	1.9503	500	1.9515
1.8728	1.9893	510	1.9540
2.0879	2.0283	520	1.9532
2.119	2.0673	530	1.9605
2.1424	2.1063	540	1.9559
2.0755	2.1453	550	1.9306
1.9815	2.1843	560	1.9407
1.952	2.2233	570	1.9472
2.1086	2.2623	580	1.9460
2.1537	2.3013	590	1.9390
2.0626	2.3403	600	1.9184
1.9718	2.3793	610	1.9251
1.9661	2.4183	620	1.9346
2.0937	2.4573	630	1.9418
2.1033	2.4963	640	1.9311
1.9948	2.5353	650	1.9051
1.9327	2.5744	660	1.9142
1.9565	2.6134	670	1.9182
2.0608	2.6524	680	1.9238
2.0804	2.6914	690	1.9166
2.0171	2.7304	700	1.8911
1.9227	2.7694	710	1.8917
1.8928	2.8084	720	1.8967
2.1007	2.8474	730	1.9101
2.0644	2.8864	740	1.8979
2.0158	2.9254	750	1.8790
1.8893	2.9644	760	1.8889
1.8667	3.0034	770	1.8789
2.0376	3.0424	780	1.8826
2.0067	3.0814	790	1.8921
2.0115	3.1204	800	1.8781
1.9622	3.1594	810	1.8691
1.6909	3.1984	820	1.8865
2.0386	3.2374	830	1.8937
2.0207	3.2765	840	1.8961
2.0297	3.3155	850	1.8736
1.9413	3.3545	860	1.8623
1.7372	3.3935	870	1.8927
2.0537	3.4325	880	1.8809
2.0477	3.4715	890	1.8878
2.0275	3.5105	900	1.8757
1.9251	3.5495	910	1.8551
1.7597	3.5885	920	1.8677
2.0448	3.6275	930	1.8671
2.0844	3.6665	940	1.8749
2.0147	3.7055	950	1.8612
1.9194	3.7445	960	1.8494
1.7378	3.7835	970	1.8554
2.029	3.8225	980	1.8591
2.0434	3.8615	990	1.8658
1.9697	3.9005	1000	1.8546
1.9241	3.9395	1010	1.8430
1.7295	3.9785	1020	1.8510
2.0073	4.0176	1030	1.8400
1.9937	4.0566	1040	1.8487
2.0309	4.0956	1050	1.8506
1.9177	4.1346	1060	1.8354
1.868	4.1736	1070	1.8401
1.7374	4.2126	1080	1.8390
2.0335	4.2516	1090	1.8501
1.9698	4.2906	1100	1.8499
1.896	4.3296	1110	1.8350
1.8848	4.3686	1120	1.8367
1.7259	4.4076	1130	1.8355
1.9634	4.4466	1140	1.8485
1.9683	4.4856	1150	1.8451
1.9561	4.5246	1160	1.8269
1.8939	4.5636	1170	1.8320
1.748	4.6026	1180	1.8308
1.98	4.6416	1190	1.8427
1.9592	4.6806	1200	1.8391
1.9849	4.7196	1210	1.8259
1.8567	4.7587	1220	1.8243
1.7734	4.7977	1230	1.8267
2.0098	4.8367	1240	1.8420
1.9283	4.8757	1250	1.8364
1.9114	4.9147	1260	1.8182
1.83	4.9537	1270	1.8210
1.6698	4.9927	1280	1.8231
1.8952	5.0317	1290	1.8315
1.97	5.0707	1300	1.8474
1.895	5.1097	1310	1.8373
1.8165	5.1487	1320	1.8196
1.7256	5.1877	1330	1.8280
1.8193	5.2267	1340	1.8230
1.9184	5.2657	1350	1.8317
1.9165	5.3047	1360	1.8342
1.9257	5.3437	1370	1.8116
1.7266	5.3827	1380	1.8229
1.819	5.4217	1390	1.8162
1.9576	5.4608	1400	1.8311
1.9448	5.4998	1410	1.8251
1.8438	5.5388	1420	1.8083
1.7266	5.5778	1430	1.8173
1.8128	5.6168	1440	1.8113
1.9558	5.6558	1450	1.8206
1.9478	5.6948	1460	1.8177
1.8407	5.7338	1470	1.8036
1.7654	5.7728	1480	1.8194
1.8663	5.8118	1490	1.8082
1.9504	5.8508	1500	1.8202
1.9463	5.8898	1510	1.8196
1.7968	5.9288	1520	1.8029
1.7647	5.9678	1530	1.8152
1.7266	6.0068	1540	1.8015
1.9003	6.0458	1550	1.8100
1.9034	6.0848	1560	1.8137
1.8396	6.1238	1570	1.8103
1.7832	6.1628	1580	1.8055
1.6215	6.2019	1590	1.8197
1.9618	6.2409	1600	1.8072
1.897	6.2799	1610	1.8152
1.8719	6.3189	1620	1.8071
1.8327	6.3579	1630	1.8009
1.6011	6.3969	1640	1.8202
1.9512	6.4359	1650	1.8061
1.8925	6.4749	1660	1.8183
1.8759	6.5139	1670	1.8104
1.7985	6.5529	1680	1.7971
1.6509	6.5919	1690	1.8161
1.9336	6.6309	1700	1.7963
1.9162	6.6699	1710	1.8053
1.8663	6.7089	1720	1.8038
1.8258	6.7479	1730	1.7938
1.59	6.7869	1740	1.8156
1.9273	6.8259	1750	1.7902
1.8987	6.8649	1760	1.8011
1.8492	6.9039	1770	1.8008
1.7775	6.9430	1780	1.7896
1.5814	6.9820	1790	1.8116
1.8407	7.0210	1800	1.7896
1.8887	7.0600	1810	1.7979
1.9142	7.0990	1820	1.8057
1.7626	7.1380	1830	1.7939
1.7565	7.1770	1840	1.7964
1.6147	7.2160	1850	1.7995
1.8237	7.2550	1860	1.7914
1.8857	7.2940	1870	1.7981
1.8479	7.3330	1880	1.7916
1.7318	7.3720	1890	1.7945
1.6457	7.4110	1900	1.7967
1.8955	7.4500	1910	1.7870
1.9229	7.4890	1920	1.7929
1.8029	7.5280	1930	1.7899
1.7959	7.5670	1940	1.7871
1.6022	7.6060	1950	1.8001
1.9062	7.6451	1960	1.7833
1.9102	7.6841	1970	1.7858
1.8149	7.7231	1980	1.7854
1.7492	7.7621	1990	1.7861
1.6135	7.8011	2000	1.7939
1.8301	7.8401	2010	1.7817
1.8828	7.8791	2020	1.7844
1.754	7.9181	2030	1.7823
1.7694	7.9571	2040	1.7831
1.6105	7.9961	2050	1.7867
1.8275	8.0351	2060	1.7847
1.7555	8.0741	2070	1.7868
1.8719	8.1131	2080	1.7861
1.7381	8.1521	2090	1.7837
1.6302	8.1911	2100	1.8011
1.7826	8.2301	2110	1.7855
1.8958	8.2691	2120	1.7826
1.852	8.3081	2130	1.7842
1.748	8.3471	2140	1.7819
1.5133	8.3862	2150	1.7930
1.8326	8.4252	2160	1.7814
1.8598	8.4642	2170	1.7784
1.8627	8.5032	2180	1.7821
1.7473	8.5422	2190	1.7797
1.642	8.5812	2200	1.7848
1.8286	8.6202	2210	1.7777
1.7744	8.6592	2220	1.7803
1.825	8.6982	2230	1.7779
1.7296	8.7372	2240	1.7785
1.5304	8.7762	2250	1.7871
1.747	8.8152	2260	1.7760
1.8467	8.8542	2270	1.7778
1.8316	8.8932	2280	1.7769
1.7574	8.9322	2290	1.7732
1.6203	8.9712	2300	1.7821
1.742	9.0102	2310	1.7773
1.7971	9.0492	2320	1.7799
1.8526	9.0882	2330	1.7805
1.7679	9.1273	2340	1.7821
1.6806	9.1663	2350	1.7809
1.4834	9.2053	2360	1.7905
1.829	9.2443	2370	1.7772
1.8293	9.2833	2380	1.7783
1.7669	9.3223	2390	1.7767
1.7476	9.3613	2400	1.7753
1.5542	9.4003	2410	1.7906
1.8146	9.4393	2420	1.7747
1.805	9.4783	2430	1.7772
1.7651	9.5173	2440	1.7778
1.7134	9.5563	2450	1.7757
1.5159	9.5953	2460	1.7883
1.8303	9.6343	2470	1.7727
1.833	9.6733	2480	1.7777
1.8066	9.7123	2490	1.7735
1.7443	9.7513	2500	1.7769
1.5211	9.7903	2510	1.7894
1.8166	9.8294	2520	1.7726
1.8283	9.8684	2530	1.7754
1.8072	9.9074	2540	1.7718
1.704	9.9464	2550	1.7751
1.5475	9.9854	2560	1.7846
1.7583	10.0244	2570	1.7745
1.7812	10.0634	2580	1.7760
1.7514	10.1024	2590	1.7782
1.6958	10.1414	2600	1.7743
1.6448	10.1804	2610	1.7814
1.6535	10.2194	2620	1.7832
1.863	10.2584	2630	1.7734
1.7768	10.2974	2640	1.7782
1.7197	10.3364	2650	1.7740
1.7241	10.3754	2660	1.7787
1.5929	10.4144	2670	1.7812
1.8043	10.4534	2680	1.7727
1.8393	10.4924	2690	1.7775
1.7536	10.5314	2700	1.7729
1.6587	10.5705	2710	1.7802
1.593	10.6095	2720	1.7824
1.8398	10.6485	2730	1.7725
1.8289	10.6875	2740	1.7765
1.7409	10.7265	2750	1.7738
1.6725	10.7655	2760	1.7778
1.6102	10.8045	2770	1.7810
1.7391	10.8435	2780	1.7710
1.751	10.8825	2790	1.7737
1.6602	10.9215	2800	1.7726
1.6149	10.9605	2810	1.7780
1.5124	10.9995	2820	1.7788
1.8017	11.0385	2830	1.7731
1.7256	11.0775	2840	1.7764
1.7597	11.1165	2850	1.7756
1.6996	11.1555	2860	1.7732
1.4229	11.1945	2870	1.7867
1.7985	11.2335	2880	1.7743
1.7496	11.2725	2890	1.7755
1.8179	11.3116	2900	1.7767
1.6852	11.3506	2910	1.7729
1.4504	11.3896	2920	1.7864
1.7277	11.4286	2930	1.7751
1.786	11.4676	2940	1.7730
1.7619	11.5066	2950	1.7744
1.6852	11.5456	2960	1.7718
1.4457	11.5846	2970	1.7845
1.8336	11.6236	2980	1.7750
1.7752	11.6626	2990	1.7715
1.7486	11.7016	3000	1.7731
1.6407	11.7406	3010	1.7728
1.5157	11.7796	3020	1.7797
1.7665	11.8186	3030	1.7730
1.7849	11.8576	3040	1.7724
1.7888	11.8966	3050	1.7738
1.7117	11.9356	3060	1.7703
1.4887	11.9746	3070	1.7802
1.7605	12.0137	3080	1.7763
1.7601	12.0527	3090	1.7729
1.7629	12.0917	3100	1.7772
1.7879	12.1307	3110	1.7705
1.618	12.1697	3120	1.7783
1.4831	12.2087	3130	1.7898
1.7599	12.2477	3140	1.7718
1.7936	12.2867	3150	1.7757
1.686	12.3257	3160	1.7778
1.6687	12.3647	3170	1.7751
1.5258	12.4037	3180	1.7826
1.7463	12.4427	3190	1.7747
1.7613	12.4817	3200	1.7738
1.7218	12.5207	3210	1.7730
1.6481	12.5597	3220	1.7736
1.4752	12.5987	3230	1.7842
1.7901	12.6377	3240	1.7730
1.8045	12.6767	3250	1.7727
1.7731	12.7157	3260	1.7709
1.6888	12.7548	3270	1.7727
1.4489	12.7938	3280	1.7822
1.8051	12.8328	3290	1.7712
1.7413	12.8718	3300	1.7720
1.6658	12.9108	3310	1.7744
1.6568	12.9498	3320	1.7724
1.4916	12.9888	3330	1.7812
1.6604	13.0278	3340	1.7756
1.78	13.0668	3350	1.7741
1.7498	13.1058	3360	1.7770
1.6802	13.1448	3370	1.7746
1.5932	13.1838	3380	1.7772
1.5691	13.2228	3390	1.7824
1.7558	13.2618	3400	1.7726
1.8435	13.3008	3410	1.7734
1.6418	13.3398	3420	1.7744
1.5933	13.3788	3430	1.7780
1.558	13.4178	3440	1.7791
1.8047	13.4569	3450	1.7728
1.7587	13.4959	3460	1.7743
1.696	13.5349	3470	1.7741
1.5533	13.5739	3480	1.7765
1.5472	13.6129	3490	1.7795
1.6872	13.6519	3500	1.7737
1.7398	13.6909	3510	1.7726
1.6902	13.7299	3520	1.7737
1.6542	13.7689	3530	1.7751
1.5921	13.8079	3540	1.7773
1.7336	13.8469	3550	1.7737
1.7588	13.8859	3560	1.7747
1.6348	13.9249	3570	1.7732
1.5502	13.9639	3580	1.7781
1.522	14.0029	3590	1.7787
1.7596	14.0419	3600	1.7735
1.7118	14.0809	3610	1.7747
1.7507	14.1199	3620	1.7761
1.6661	14.1589	3630	1.7746
1.4149	14.1980	3640	1.7810
1.7937	14.2370	3650	1.7781
1.7723	14.2760	3660	1.7736
1.7098	14.3150	3670	1.7756
1.6265	14.3540	3680	1.7776
1.4276	14.3930	3690	1.7821
1.7301	14.4320	3700	1.7783
1.7402	14.4710	3710	1.7753
1.7258	14.5100	3720	1.7756
1.6407	14.5490	3730	1.7758
1.3929	14.5880	3740	1.7812
1.7925	14.6270	3750	1.7786
1.7348	14.6660	3760	1.7742
1.7815	14.7050	3770	1.7743
1.667	14.7440	3780	1.7730
1.4567	14.7830	3790	1.7781
1.7649	14.8220	3800	1.7790
1.7334	14.8610	3810	1.7747
1.6922	14.9000	3820	1.7735
1.6162	14.9391	3830	1.7742
1.38	14.9781	3840	1.7789
1.6846	15.0171	3850	1.7780
1.6927	15.0561	3860	1.7749
1.8049	15.0951	3870	1.7742
1.7247	15.1341	3880	1.7747
1.6067	15.1731	3890	1.7761
1.4859	15.2121	3900	1.7805
1.7554	15.2511	3910	1.7764
1.7054	15.2901	3920	1.7766
1.7034	15.3291	3930	1.7772
1.6364	15.3681	3940	1.7760
1.4598	15.4071	3950	1.7795
1.7259	15.4461	3960	1.7781
1.7547	15.4851	3970	1.7758
1.6734	15.5241	3980	1.7763
1.6257	15.5631	3990	1.7770
1.4633	15.6021	4000	1.7799
1.6762	15.6412	4010	1.7782
1.7339	15.6802	4020	1.7761
1.6549	15.7192	4030	1.7761
1.5622	15.7582	4040	1.7783
1.4879	15.7972	4050	1.7822
1.7163	15.8362	4060	1.7783
1.8122	15.8752	4070	1.7755
1.7154	15.9142	4080	1.7750
1.6695	15.9532	4090	1.7748
1.4664	15.9922	4100	1.7783
1.6513	16.0312	4110	1.7775
1.7294	16.0702	4120	1.7773
1.7467	16.1092	4130	1.7765
1.5965	16.1482	4140	1.7756
1.5172	16.1872	4150	1.7774
1.6064	16.2262	4160	1.7789
1.7203	16.2652	4170	1.7783
1.7374	16.3042	4180	1.7768
1.6223	16.3432	4190	1.7752
1.5243	16.3823	4200	1.7757
1.603	16.4213	4210	1.7788
1.7494	16.4603	4220	1.7788
1.7415	16.4993	4230	1.7771
1.6295	16.5383	4240	1.7754
1.5225	16.5773	4250	1.7768
1.5805	16.6163	4260	1.7790
1.7568	16.6553	4270	1.7786
1.7337	16.6943	4280	1.7765
1.6712	16.7333	4290	1.7748
1.5539	16.7723	4300	1.7760
1.5777	16.8113	4310	1.7779
1.7397	16.8503	4320	1.7771
1.7327	16.8893	4330	1.7764
1.6784	16.9283	4340	1.7764
1.5556	16.9673	4350	1.7773
1.5201	17.0063	4360	1.7795
1.7309	17.0453	4370	1.7793
1.724	17.0843	4380	1.7782
1.739	17.1234	4390	1.7773
1.5871	17.1624	4400	1.7764
1.4126	17.2014	4410	1.7781
1.7192	17.2404	4420	1.7789
1.6981	17.2794	4430	1.7782
1.7179	17.3184	4440	1.7779
1.6096	17.3574	4450	1.7776
1.375	17.3964	4460	1.7789
1.6688	17.4354	4470	1.7793
1.6978	17.4744	4480	1.7786
1.7511	17.5134	4490	1.7780
1.6402	17.5524	4500	1.7772
1.4435	17.5914	4510	1.7775
1.7534	17.6304	4520	1.7780
1.7607	17.6694	4530	1.7778
1.771	17.7084	4540	1.7771
1.6721	17.7474	4550	1.7764
1.3991	17.7864	4560	1.7769
1.7386	17.8255	4570	1.7776
1.7345	17.8645	4580	1.7781
1.6783	17.9035	4590	1.7781
1.5988	17.9425	4600	1.7777
1.4249	17.9815	4610	1.7779
1.697	18.0205	4620	1.7782
1.7454	18.0595	4630	1.7782
1.7218	18.0985	4640	1.7779
1.6152	18.1375	4650	1.7775
1.6062	18.1765	4660	1.7772
1.4834	18.2155	4670	1.7777
1.711	18.2545	4680	1.7779
1.7126	18.2935	4690	1.7778
1.7342	18.3325	4700	1.7773
1.6363	18.3715	4710	1.7768
1.4322	18.4105	4720	1.7773
1.7839	18.4495	4730	1.7775
1.7095	18.4885	4740	1.7776
1.6805	18.5275	4750	1.7775
1.5983	18.5666	4760	1.7776
1.4826	18.6056	4770	1.7780
1.7331	18.6446	4780	1.7783
1.7222	18.6836	4790	1.7782
1.6478	18.7226	4800	1.7780
1.616	18.7616	4810	1.7779
1.5055	18.8006	4820	1.7781
1.7357	18.8396	4830	1.7782
1.7558	18.8786	4840	1.7782
1.6319	18.9176	4850	1.7782
1.596	18.9566	4860	1.7782
1.4068	18.9956	4870	1.7784
1.729	19.0346	4880	1.7784
1.7094	19.0736	4890	1.7784
1.744	19.1126	4900	1.7784
1.6065	19.1516	4910	1.7784
1.4862	19.1906	4920	1.7784
1.6656	19.2296	4930	1.7784
1.7731	19.2686	4940	1.7784
1.7516	19.3077	4950	1.7784
1.6241	19.3467	4960	1.7783
1.479	19.3857	4970	1.7783
1.6246	19.4247	4980	1.7783
1.7093	19.4637	4990	1.7783
1.7031	19.5027	5000	1.7783
1.6452	19.5417	5010	1.7783
1.4704	19.5807	5020	1.7783
1.6488	19.6197	5030	1.7783
1.7266	19.6587	5040	1.7783
1.7535	19.6977	5050	1.7783
1.586	19.7367	5060	1.7783
1.4617	19.7757	5070	1.7783
1.5699	19.8147	5080	1.7783
1.6759	19.8537	5090	1.7783
1.7787	19.8927	5100	1.7783
1.6833	19.9317	5110	1.7783
1.4781	19.9707	5120	1.7783

Framework versions

PEFT 0.12.0
Transformers 4.45.0
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.20.1

Library: peft
License: gemma
Created: Oct 24, 2024
Updated: Oct 24, 2024