results_1027_easy

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: 1.5176

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
3.7763	0.0389	10	4.5283
3.8936	0.0779	20	4.4799
4.4563	0.1168	30	4.3501
4.7589	0.1557	40	4.0769
5.071	0.1946	50	3.6929
3.2634	0.2336	60	3.3487
2.8326	0.2725	70	3.0637
2.819	0.3114	80	2.8154
2.6421	0.3504	90	2.5662
2.3516	0.3893	100	2.3786
2.7655	0.4282	110	2.3151
2.097	0.4672	120	2.1992
1.9609	0.5061	130	2.1322
1.8021	0.5450	140	2.0846
1.6522	0.5839	150	2.0758
2.6338	0.6229	160	2.0508
1.8254	0.6618	170	1.9887
1.7601	0.7007	180	1.9707
1.6096	0.7397	190	1.9472
1.4924	0.7786	200	1.9573
2.5712	0.8175	210	1.9522
1.6991	0.8564	220	1.9024
1.6546	0.8954	230	1.8793
1.5023	0.9343	240	1.8753
1.4243	0.9732	250	1.8831
2.0387	1.0122	260	1.8509
2.1742	1.0511	270	1.8497
1.6214	1.0900	280	1.8301
1.5333	1.1290	290	1.8235
1.4649	1.1679	300	1.8228
1.6879	1.2068	310	1.8274
2.2073	1.2457	320	1.8120
1.5935	1.2847	330	1.7940
1.514	1.3236	340	1.7872
1.3913	1.3625	350	1.7860
1.6293	1.4015	360	1.7919
2.115	1.4404	370	1.7775
1.5845	1.4793	380	1.7729
1.4547	1.5182	390	1.7540
1.3436	1.5572	400	1.7591
1.6404	1.5961	410	1.7705
2.1136	1.6350	420	1.7545
1.5435	1.6740	430	1.7411
1.4524	1.7129	440	1.7353
1.3298	1.7518	450	1.7408
1.6466	1.7908	460	1.7537
2.0529	1.8297	470	1.7372
1.5272	1.8686	480	1.7231
1.4131	1.9075	490	1.7233
1.3182	1.9465	500	1.7230
1.4042	1.9854	510	1.7303
2.0085	2.0243	520	1.7065
1.6983	2.0633	530	1.7059
1.4279	2.1022	540	1.7026
1.3527	2.1411	550	1.7021
1.2341	2.1800	560	1.7234
1.9291	2.2190	570	1.7160
1.7796	2.2579	580	1.7010
1.4267	2.2968	590	1.6932
1.3393	2.3358	600	1.6907
1.2142	2.3747	610	1.7022
1.9125	2.4136	620	1.6990
1.8458	2.4526	630	1.6864
1.4531	2.4915	640	1.6796
1.3657	2.5304	650	1.6782
1.2651	2.5693	660	1.6826
1.9316	2.6083	670	1.6875
1.6314	2.6472	680	1.6757
1.4485	2.6861	690	1.6691
1.309	2.7251	700	1.6664
1.209	2.7640	710	1.6777
1.8986	2.8029	720	1.6775
1.8361	2.8418	730	1.6669
1.4449	2.8808	740	1.6572
1.2946	2.9197	750	1.6591
1.2103	2.9586	760	1.6680
1.4037	2.9976	770	1.6621
2.1818	3.0365	780	1.6511
1.4904	3.0754	790	1.6450
1.3461	3.1144	800	1.6488
1.2472	3.1533	810	1.6551
1.1493	3.1922	820	1.6697
2.2146	3.2311	830	1.6583
1.403	3.2701	840	1.6433
1.3514	3.3090	850	1.6436
1.2089	3.3479	860	1.6471
1.1023	3.3869	870	1.6645
2.2152	3.4258	880	1.6598
1.5242	3.4647	890	1.6477
1.3203	3.5036	900	1.6369
1.2507	3.5426	910	1.6402
1.1166	3.5815	920	1.6616
2.2196	3.6204	930	1.6440
1.4112	3.6594	940	1.6346
1.3503	3.6983	950	1.6256
1.2029	3.7372	960	1.6336
1.1152	3.7762	970	1.6468
2.1977	3.8151	980	1.6385
1.5103	3.8540	990	1.6287
1.362	3.8929	1000	1.6246
1.2141	3.9319	1010	1.6220
1.1004	3.9708	1020	1.6423
1.6619	4.0097	1030	1.6203
1.9806	4.0487	1040	1.6170
1.3531	4.0876	1050	1.6129
1.281	4.1265	1060	1.6145
1.1584	4.1655	1070	1.6254
1.3343	4.2044	1080	1.6362
1.9491	4.2433	1090	1.6206
1.3445	4.2822	1100	1.6129
1.2577	4.3212	1110	1.6119
1.1242	4.3601	1120	1.6255
1.3583	4.3990	1130	1.6395
2.0065	4.4380	1140	1.6209
1.3461	4.4769	1150	1.6104
1.2333	4.5158	1160	1.6055
1.1523	4.5547	1170	1.6114
1.3992	4.5937	1180	1.6308
2.0767	4.6326	1190	1.6160
1.3482	4.6715	1200	1.6039
1.2425	4.7105	1210	1.6042
1.1431	4.7494	1220	1.6075
1.3811	4.7883	1230	1.6289
1.9523	4.8273	1240	1.6105
1.3783	4.8662	1250	1.5982
1.2572	4.9051	1260	1.5952
1.1646	4.9440	1270	1.5982
1.1906	4.9830	1280	1.6090
1.7989	5.0219	1290	1.5914
1.7403	5.0608	1300	1.5873
1.2874	5.0998	1310	1.5850
1.1733	5.1387	1320	1.5948
1.0615	5.1776	1330	1.6029
1.6934	5.2165	1340	1.6018
1.6591	5.2555	1350	1.5912
1.2596	5.2944	1360	1.5863
1.1479	5.3333	1370	1.5888
1.0699	5.3723	1380	1.5977
1.7117	5.4112	1390	1.6021
1.6833	5.4501	1400	1.5841
1.288	5.4891	1410	1.5820
1.2	5.5280	1420	1.5814
1.0931	5.5669	1430	1.5936
1.715	5.6058	1440	1.5990
1.6323	5.6448	1450	1.5816
1.2706	5.6837	1460	1.5785
1.1385	5.7226	1470	1.5805
1.0803	5.7616	1480	1.5904
1.6976	5.8005	1490	1.5994
1.6462	5.8394	1500	1.5772
1.3095	5.8783	1510	1.5740
1.1689	5.9173	1520	1.5726
1.071	5.9562	1530	1.5818
1.1859	5.9951	1540	1.5829
2.0191	6.0341	1550	1.5715
1.4098	6.0730	1560	1.5694
1.2502	6.1119	1570	1.5730
1.0788	6.1509	1580	1.5807
0.988	6.1898	1590	1.6018
2.0501	6.2287	1600	1.5809
1.3556	6.2676	1610	1.5715
1.2059	6.3066	1620	1.5718
1.0579	6.3455	1630	1.5743
0.971	6.3844	1640	1.5913
2.0085	6.4234	1650	1.5908
1.4356	6.4623	1660	1.5711
1.2325	6.5012	1670	1.5663
1.111	6.5401	1680	1.5682
0.9896	6.5791	1690	1.5832
2.0567	6.6180	1700	1.5820
1.3979	6.6569	1710	1.5675
1.2178	6.6959	1720	1.5624
1.0477	6.7348	1730	1.5670
0.9771	6.7737	1740	1.5721
2.0197	6.8127	1750	1.5751
1.258	6.8516	1760	1.5606
1.2167	6.8905	1770	1.5588
1.0911	6.9294	1780	1.5622
1.0111	6.9684	1790	1.5690
1.4849	7.0073	1800	1.5580
1.9573	7.0462	1810	1.5582
1.2576	7.0852	1820	1.5510
1.1611	7.1241	1830	1.5627
1.0478	7.1630	1840	1.5702
1.1798	7.2019	1850	1.5827
1.9795	7.2409	1860	1.5587
1.2165	7.2798	1870	1.5507
1.1532	7.3187	1880	1.5570
1.0266	7.3577	1890	1.5631
1.1541	7.3966	1900	1.5813
1.9844	7.4355	1910	1.5687
1.272	7.4745	1920	1.5524
1.15	7.5134	1930	1.5564
1.0207	7.5523	1940	1.5631
1.1958	7.5912	1950	1.5714
1.8459	7.6302	1960	1.5598
1.2237	7.6691	1970	1.5502
1.0912	7.7080	1980	1.5576
1.0293	7.7470	1990	1.5605
1.1759	7.7859	2000	1.5748
1.9501	7.8248	2010	1.5619
1.278	7.8637	2020	1.5485
1.1444	7.9027	2030	1.5470
0.9825	7.9416	2040	1.5567
1.1099	7.9805	2050	1.5713
1.6283	8.0195	2060	1.5478
1.5212	8.0584	2070	1.5439
1.1641	8.0973	2080	1.5414
1.0507	8.1363	2090	1.5554
0.9638	8.1752	2100	1.5691
1.5681	8.2141	2110	1.5728
1.6317	8.2530	2120	1.5490
1.1769	8.2920	2130	1.5427
1.0881	8.3309	2140	1.5535
0.9701	8.3698	2150	1.5607
1.5534	8.4088	2160	1.5754
1.7206	8.4477	2170	1.5547
1.2126	8.4866	2180	1.5407
1.063	8.5255	2190	1.5540
0.972	8.5645	2200	1.5613
1.5243	8.6034	2210	1.5667
1.6769	8.6423	2220	1.5481
1.2002	8.6813	2230	1.5378
1.0425	8.7202	2240	1.5443
0.9598	8.7591	2250	1.5548
1.5318	8.7981	2260	1.5622
1.6112	8.8370	2270	1.5435
1.2198	8.8759	2280	1.5350
1.0364	8.9148	2290	1.5446
0.9443	8.9538	2300	1.5562
1.1055	8.9927	2310	1.5467
1.9621	9.0316	2320	1.5375
1.3497	9.0706	2330	1.5358
1.1692	9.1095	2340	1.5320
0.9726	9.1484	2350	1.5516
0.9062	9.1873	2360	1.5673
1.8685	9.2263	2370	1.5527
1.376	9.2652	2380	1.5364
1.1297	9.3041	2390	1.5330
0.9794	9.3431	2400	1.5479
0.8959	9.3820	2410	1.5624
1.9017	9.4209	2420	1.5572
1.3083	9.4599	2430	1.5361
1.1149	9.4988	2440	1.5312
0.9902	9.5377	2450	1.5475
0.9252	9.5766	2460	1.5582
1.8811	9.6156	2470	1.5605
1.3395	9.6545	2480	1.5356
1.1577	9.6934	2490	1.5291
0.9977	9.7324	2500	1.5435
0.8878	9.7713	2510	1.5561
1.8883	9.8102	2520	1.5541
1.2806	9.8491	2530	1.5316
1.1298	9.8881	2540	1.5272
0.9948	9.9270	2550	1.5390
0.8918	9.9659	2560	1.5530
1.2933	10.0049	2570	1.5386
1.9556	10.0438	2580	1.5349
1.1961	10.0827	2590	1.5291
1.098	10.1217	2600	1.5311
0.943	10.1606	2610	1.5481
1.0277	10.1995	2620	1.5648
1.9568	10.2384	2630	1.5436
1.1865	10.2774	2640	1.5299
1.0858	10.3163	2650	1.5292
0.9243	10.3552	2660	1.5482
1.0187	10.3942	2670	1.5573
2.0017	10.4331	2680	1.5513
1.2038	10.4720	2690	1.5293
1.0947	10.5109	2700	1.5263
0.9356	10.5499	2710	1.5422
1.0083	10.5888	2720	1.5570
1.9654	10.6277	2730	1.5480
1.1638	10.6667	2740	1.5290
1.0585	10.7056	2750	1.5248
0.9363	10.7445	2760	1.5409
1.0313	10.7835	2770	1.5523
1.897	10.8224	2780	1.5488
1.1019	10.8613	2790	1.5276
1.0441	10.9002	2800	1.5242
0.9135	10.9392	2810	1.5403
0.9778	10.9781	2820	1.5515
1.5447	11.0170	2830	1.5332
1.6157	11.0560	2840	1.5295
1.1112	11.0949	2850	1.5248
0.9669	11.1338	2860	1.5301
0.8877	11.1727	2870	1.5445
1.4297	11.2117	2880	1.5561
1.5628	11.2506	2890	1.5340
1.1499	11.2895	2900	1.5247
0.9486	11.3285	2910	1.5303
0.8866	11.3674	2920	1.5451
1.3927	11.4063	2930	1.5516
1.5893	11.4453	2940	1.5372
1.1348	11.4842	2950	1.5259
0.9893	11.5231	2960	1.5259
0.8922	11.5620	2970	1.5432
1.3919	11.6010	2980	1.5495
1.5819	11.6399	2990	1.5356
1.1188	11.6788	3000	1.5227
1.034	11.7178	3010	1.5211
0.8827	11.7567	3020	1.5371
1.4279	11.7956	3030	1.5479
1.6805	11.8345	3040	1.5390
1.171	11.8735	3050	1.5218
1.0276	11.9124	3060	1.5209
0.9081	11.9513	3070	1.5341
1.1048	11.9903	3080	1.5415
1.8218	12.0292	3090	1.5286
1.3226	12.0681	3100	1.5233
1.0733	12.1071	3110	1.5216
0.9257	12.1460	3120	1.5272
0.8751	12.1849	3130	1.5413
1.7518	12.2238	3140	1.5455
1.2875	12.2628	3150	1.5270
1.1092	12.3017	3160	1.5211
0.9707	12.3406	3170	1.5254
0.8338	12.3796	3180	1.5412
1.7599	12.4185	3190	1.5457
1.3328	12.4574	3200	1.5311
1.0805	12.4964	3210	1.5219
0.9024	12.5353	3220	1.5267
0.837	12.5742	3230	1.5429
1.7753	12.6131	3240	1.5473
1.3426	12.6521	3250	1.5309
1.0846	12.6910	3260	1.5202
0.9351	12.7299	3270	1.5223
0.8488	12.7689	3280	1.5328
1.7821	12.8078	3290	1.5418
1.3392	12.8467	3300	1.5286
1.1127	12.8856	3310	1.5166
0.9486	12.9246	3320	1.5209
0.8417	12.9635	3330	1.5322
1.1718	13.0024	3340	1.5309
1.9716	13.0414	3350	1.5266
1.1337	13.0803	3360	1.5236
1.0718	13.1192	3370	1.5188
0.8822	13.1582	3380	1.5261
0.9183	13.1971	3390	1.5378
1.9565	13.2360	3400	1.5338
1.1241	13.2749	3410	1.5208
1.0213	13.3139	3420	1.5165
0.8995	13.3528	3430	1.5246
0.8652	13.3917	3440	1.5373
1.9183	13.4307	3450	1.5405
1.1156	13.4696	3460	1.5241
1.0254	13.5085	3470	1.5173
0.8632	13.5474	3480	1.5216
0.9004	13.5864	3490	1.5332
2.0236	13.6253	3500	1.5368
1.1511	13.6642	3510	1.5245
1.0503	13.7032	3520	1.5171
0.9045	13.7421	3530	1.5191
0.8821	13.7810	3540	1.5287
1.9734	13.8200	3550	1.5321
1.1315	13.8589	3560	1.5213
1.0325	13.8978	3570	1.5165
0.8575	13.9367	3580	1.5207
0.8822	13.9757	3590	1.5289
1.447	14.0146	3600	1.5233
1.6728	14.0535	3610	1.5217
1.1381	14.0925	3620	1.5187
0.9491	14.1314	3630	1.5173
0.8364	14.1703	3640	1.5241
1.2993	14.2092	3650	1.5325
1.6248	14.2482	3660	1.5288
1.122	14.2871	3670	1.5192
1.005	14.3260	3680	1.5164
0.8747	14.3650	3690	1.5229
1.3121	14.4039	3700	1.5298
1.634	14.4428	3710	1.5287
1.066	14.4818	3720	1.5195
0.9698	14.5207	3730	1.5160
0.8493	14.5596	3740	1.5213
1.3017	14.5985	3750	1.5302
1.5936	14.6375	3760	1.5277
1.0953	14.6764	3770	1.5197
0.9469	14.7153	3780	1.5156
0.8458	14.7543	3790	1.5186
1.3036	14.7932	3800	1.5267
1.574	14.8321	3810	1.5260
1.1098	14.8710	3820	1.5192
0.9657	14.9100	3830	1.5146
0.8517	14.9489	3840	1.5178
1.0223	14.9878	3850	1.5236
1.6899	15.0268	3860	1.5228
1.3283	15.0657	3870	1.5222
1.0927	15.1046	3880	1.5195
0.9177	15.1436	3890	1.5172
0.8073	15.1825	3900	1.5216
1.6583	15.2214	3910	1.5260
1.2776	15.2603	3920	1.5231
1.0238	15.2993	3930	1.5184
0.9063	15.3382	3940	1.5168
0.7996	15.3771	3950	1.5199
1.6785	15.4161	3960	1.5251
1.4315	15.4550	3970	1.5234
1.0864	15.4939	3980	1.5170
0.9408	15.5328	3990	1.5146
0.8287	15.5718	4000	1.5177
1.6559	15.6107	4010	1.5214
1.2785	15.6496	4020	1.5206
1.068	15.6886	4030	1.5159
0.915	15.7275	4040	1.5143
0.8228	15.7664	4050	1.5177
1.6733	15.8054	4060	1.5228
1.4009	15.8443	4070	1.5221
1.0602	15.8832	4080	1.5167
0.8688	15.9221	4090	1.5146
0.8254	15.9611	4100	1.5166
1.0349	16.0	4110	1.5195
2.0188	16.0389	4120	1.5204
1.1284	16.0779	4130	1.5197
1.0365	16.1168	4140	1.5169
0.8305	16.1557	4150	1.5169
0.7805	16.1946	4160	1.5203
1.9277	16.2336	4170	1.5228
1.0915	16.2725	4180	1.5212
1.0079	16.3114	4190	1.5182
0.8584	16.3504	4200	1.5172
0.7641	16.3893	4210	1.5192
2.0658	16.4282	4220	1.5209
1.1286	16.4672	4230	1.5202
1.0207	16.5061	4240	1.5169
0.8381	16.5450	4250	1.5162
0.7626	16.5839	4260	1.5182
1.9724	16.6229	4270	1.5203
1.1349	16.6618	4280	1.5192
0.9713	16.7007	4290	1.5165
0.8707	16.7397	4300	1.5155
0.7885	16.7786	4310	1.5171
2.0034	16.8175	4320	1.5186
1.1205	16.8564	4330	1.5184
1.0324	16.8954	4340	1.5167
0.8949	16.9343	4350	1.5154
0.7844	16.9732	4360	1.5169
1.4873	17.0122	4370	1.5183
1.7198	17.0511	4380	1.5189
1.126	17.0900	4390	1.5182
0.9643	17.1290	4400	1.5165
0.8349	17.1679	4410	1.5165
1.1926	17.2068	4420	1.5182
1.6662	17.2457	4430	1.5193
1.0947	17.2847	4440	1.5185
0.9806	17.3236	4450	1.5167
0.8168	17.3625	4460	1.5164
1.1892	17.4015	4470	1.5178
1.6756	17.4404	4480	1.5186
1.0762	17.4793	4490	1.5182
0.9869	17.5182	4500	1.5174
0.8504	17.5572	4510	1.5173
1.203	17.5961	4520	1.5183
1.6836	17.6350	4530	1.5187
1.0487	17.6740	4540	1.5181
0.9546	17.7129	4550	1.5170
0.8789	17.7518	4560	1.5168
1.2027	17.7908	4570	1.5172
1.6092	17.8297	4580	1.5177
1.0803	17.8686	4590	1.5174
0.9246	17.9075	4600	1.5169
0.7924	17.9465	4610	1.5170
0.9566	17.9854	4620	1.5179
1.602	18.0243	4630	1.5183
1.3736	18.0633	4640	1.5184
1.0586	18.1022	4650	1.5179
0.8991	18.1411	4660	1.5173
0.7958	18.1800	4670	1.5175
1.6093	18.2190	4680	1.5180
1.3001	18.2579	4690	1.5182
1.023	18.2968	4700	1.5178
0.9075	18.3358	4710	1.5173
0.7954	18.3747	4720	1.5174
1.5904	18.4136	4730	1.5179
1.3829	18.4526	4740	1.5181
1.0583	18.4915	4750	1.5179
0.869	18.5304	4760	1.5174
0.8325	18.5693	4770	1.5174
1.5891	18.6083	4780	1.5176
1.4293	18.6472	4790	1.5177
1.0682	18.6861	4800	1.5175
0.942	18.7251	4810	1.5173
0.8241	18.7640	4820	1.5172
1.5807	18.8029	4830	1.5174
1.4419	18.8418	4840	1.5175
1.0941	18.8808	4850	1.5174
0.875	18.9197	4860	1.5173
0.8072	18.9586	4870	1.5174
0.9517	18.9976	4880	1.5176
1.8926	19.0365	4890	1.5177
1.0971	19.0754	4900	1.5177
0.9934	19.1144	4910	1.5175
0.8713	19.1533	4920	1.5175
0.7732	19.1922	4930	1.5175
1.9746	19.2311	4940	1.5176
1.1707	19.2701	4950	1.5176
1.0383	19.3090	4960	1.5175
0.8454	19.3479	4970	1.5175
0.787	19.3869	4980	1.5176
1.9232	19.4258	4990	1.5176
1.0839	19.4647	5000	1.5176
1.009	19.5036	5010	1.5176
0.8278	19.5426	5020	1.5176
0.7563	19.5815	5030	1.5176
1.9536	19.6204	5040	1.5176
1.1281	19.6594	5050	1.5176
0.9934	19.6983	5060	1.5176
0.8663	19.7372	5070	1.5176
0.7888	19.7762	5080	1.5176
1.9462	19.8151	5090	1.5176
1.2184	19.8540	5100	1.5176
1.0388	19.8929	5110	1.5176
0.8607	19.9319	5120	1.5176

Framework versions

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