learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Mdl	Accumulated Loss	Correct Preds	Total Preds	Accuracy	Correct Gen Preds	Gen Accuracy	Correct Gen Preds 34192	Correct Preds 34192	Total Labels 34192	Accuracy 34192	Gen Accuracy 34192	Correct Gen Preds 41568	Correct Preds 41568	Total Labels 41568	Accuracy 41568	Gen Accuracy 41568
No log	0	0	1.4656	0.0065	5233.1723	3627.3586	1196.0	2475.0	0.4832	1204.0	0.4865	1196.0	1196.0	1196.0	1.0	1.0	0.0	0.0	1267.0	0.0	0.0
1.3409	1.0	1	1.4656	0.0065	5233.1723	3627.3586	1196.0	2475.0	0.4832	1204.0	0.4865	1196.0	1196.0	1196.0	1.0	1.0	0.0	0.0	1267.0	0.0	0.0
1.3409	2.0	2	5.0471	0.0065	18021.6093	12491.6277	1267.0	2475.0	0.5119	1274.0	0.5147	0.0	0.0	1196.0	0.0	0.0	1266.0	1267.0	1267.0	1.0	0.9992
5.223	3.0	3	1.2264	0.0065	4379.2036	3035.4327	1267.0	2475.0	0.5119	7.0	0.0028	0.0	0.0	1196.0	0.0	0.0	0.0	1267.0	1267.0	1.0	0.0
1.1318	4.0	4	1.7383	0.0065	6206.9539	4302.3326	1196.0	2475.0	0.4832	7.0	0.0028	0.0	1196.0	1196.0	1.0	0.0	0.0	0.0	1267.0	0.0	0.0
1.7411	5.0	5	0.9508	0.0065	3394.8693	2353.1441	1195.0	2475.0	0.4828	7.0	0.0028	0.0	1195.0	1196.0	0.9992	0.0	0.0	0.0	1267.0	0.0	0.0
0.8262	6.0	6	0.7805	0.0065	2786.9443	1931.7626	1291.0	2475.0	0.5216	7.0	0.0028	0.0	63.0	1196.0	0.0527	0.0	0.0	1228.0	1267.0	0.9692	0.0
0.6271	7.0	7	0.8670	0.0065	3095.6900	2145.7688	1197.0	2475.0	0.4836	7.0	0.0028	0.0	1196.0	1196.0	1.0	0.0	0.0	1.0	1267.0	0.0008	0.0
0.7505	8.0	8	0.9428	0.0065	3366.3062	2333.3457	1273.0	2475.0	0.5143	7.0	0.0028	0.0	8.0	1196.0	0.0067	0.0	0.0	1265.0	1267.0	0.9984	0.0
0.8724	9.0	9	0.7376	0.0065	2633.8765	1825.6641	1398.0	2475.0	0.5648	7.0	0.0028	0.0	663.0	1196.0	0.5543	0.0	0.0	735.0	1267.0	0.5801	0.0
0.4126	10.0	10	0.7465	0.0065	2665.3371	1847.4709	1446.0	2475.0	0.5842	7.0	0.0028	0.0	909.0	1196.0	0.7600	0.0	0.0	537.0	1267.0	0.4238	0.0
0.3209	11.0	11	0.7370	0.0065	2631.4060	1823.9516	1450.0	2475.0	0.5859	7.0	0.0028	0.0	639.0	1196.0	0.5343	0.0	0.0	811.0	1267.0	0.6401	0.0
0.1643	12.0	12	0.8454	0.0065	3018.5818	2092.3215	1456.0	2475.0	0.5883	7.0	0.0028	0.0	1116.0	1196.0	0.9331	0.0	0.0	340.0	1267.0	0.2684	0.0
0.1099	13.0	13	0.7445	0.0065	2658.3002	1842.5933	1543.0	2475.0	0.6234	7.0	0.0028	0.0	704.0	1196.0	0.5886	0.0	0.0	839.0	1267.0	0.6622	0.0
0.028	14.0	14	0.8177	0.0065	2919.8840	2023.9093	1534.0	2475.0	0.6198	9.0	0.0036	2.0	683.0	1196.0	0.5711	0.0017	0.0	851.0	1267.0	0.6717	0.0
0.0052	15.0	15	1.1057	0.0065	3948.0509	2736.5803	1552.0	2475.0	0.6271	31.0	0.0125	18.0	985.0	1196.0	0.8236	0.0151	6.0	567.0	1267.0	0.4475	0.0047
0.0017	16.0	16	1.2464	0.0065	4450.4039	3084.7849	1532.0	2475.0	0.6190	122.0	0.0493	69.0	1010.0	1196.0	0.8445	0.0577	46.0	522.0	1267.0	0.4120	0.0363
0.0003	17.0	17	1.3048	0.0065	4658.8358	3229.2589	1543.0	2475.0	0.6234	254.0	0.1026	142.0	1010.0	1196.0	0.8445	0.1187	105.0	533.0	1267.0	0.4207	0.0829
0.0001	18.0	18	1.3088	0.0065	4673.4608	3239.3962	1566.0	2475.0	0.6327	380.0	0.1535	208.0	991.0	1196.0	0.8286	0.1739	165.0	575.0	1267.0	0.4538	0.1302
0.0001	19.0	19	1.2930	0.0065	4617.0495	3200.2948	1570.0	2475.0	0.6343	510.0	0.2061	276.0	963.0	1196.0	0.8052	0.2308	227.0	607.0	1267.0	0.4791	0.1792
0.0	20.0	20	1.2726	0.0065	4543.9424	3149.6209	1586.0	2475.0	0.6408	631.0	0.2549	326.0	931.0	1196.0	0.7784	0.2726	297.0	655.0	1267.0	0.5170	0.2344
0.0	21.0	21	1.2595	0.0065	4497.1054	3117.1559	1595.0	2475.0	0.6444	735.0	0.2970	369.0	907.0	1196.0	0.7584	0.3085	358.0	688.0	1267.0	0.5430	0.2826
0.0	22.0	22	1.2521	0.0065	4470.9109	3098.9993	1587.0	2475.0	0.6412	815.0	0.3293	397.0	880.0	1196.0	0.7358	0.3319	410.0	707.0	1267.0	0.5580	0.3236
0.0	23.0	23	1.2502	0.0065	4463.9021	3094.1411	1586.0	2475.0	0.6408	881.0	0.3560	417.0	860.0	1196.0	0.7191	0.3487	456.0	726.0	1267.0	0.5730	0.3599
0.0	24.0	24	1.2464	0.0065	4450.5497	3084.8860	1581.0	2475.0	0.6388	926.0	0.3741	431.0	839.0	1196.0	0.7015	0.3604	487.0	742.0	1267.0	0.5856	0.3844
0.0	25.0	25	1.2471	0.0065	4452.8832	3086.5034	1578.0	2475.0	0.6376	964.0	0.3895	442.0	825.0	1196.0	0.6898	0.3696	514.0	753.0	1267.0	0.5943	0.4057
0.0	26.0	26	1.2496	0.0065	4461.9980	3092.8213	1576.0	2475.0	0.6368	998.0	0.4032	453.0	811.0	1196.0	0.6781	0.3788	537.0	765.0	1267.0	0.6038	0.4238
0.0	27.0	27	1.2537	0.0065	4476.6965	3103.0095	1580.0	2475.0	0.6384	1022.0	0.4129	458.0	808.0	1196.0	0.6756	0.3829	556.0	772.0	1267.0	0.6093	0.4388
0.0	28.0	28	1.2551	0.0065	4481.5542	3106.3767	1584.0	2475.0	0.64	1038.0	0.4194	459.0	802.0	1196.0	0.6706	0.3838	571.0	782.0	1267.0	0.6172	0.4507
0.0	29.0	29	1.2594	0.0065	4496.7748	3116.9268	1575.0	2475.0	0.6364	1060.0	0.4283	471.0	793.0	1196.0	0.6630	0.3938	581.0	782.0	1267.0	0.6172	0.4586
0.0	30.0	30	1.2634	0.0065	4511.2109	3126.9331	1578.0	2475.0	0.6376	1058.0	0.4275	467.0	789.0	1196.0	0.6597	0.3905	583.0	789.0	1267.0	0.6227	0.4601
0.0	31.0	31	1.2628	0.0065	4508.9851	3125.3903	1580.0	2475.0	0.6384	1068.0	0.4315	472.0	786.0	1196.0	0.6572	0.3946	588.0	794.0	1267.0	0.6267	0.4641
0.0	32.0	32	1.2654	0.0065	4518.4607	3131.9583	1575.0	2475.0	0.6364	1077.0	0.4352	473.0	784.0	1196.0	0.6555	0.3955	596.0	791.0	1267.0	0.6243	0.4704
0.0	33.0	33	1.2681	0.0065	4527.8199	3138.4456	1577.0	2475.0	0.6372	1086.0	0.4388	476.0	781.0	1196.0	0.6530	0.3980	602.0	796.0	1267.0	0.6283	0.4751
0.0	34.0	34	1.2686	0.0065	4529.5938	3139.6752	1571.0	2475.0	0.6347	1095.0	0.4424	482.0	775.0	1196.0	0.6480	0.4030	605.0	796.0	1267.0	0.6283	0.4775
0.0	35.0	35	1.2707	0.0065	4537.3934	3145.0814	1576.0	2475.0	0.6368	1090.0	0.4404	478.0	778.0	1196.0	0.6505	0.3997	604.0	798.0	1267.0	0.6298	0.4767
0.0	36.0	36	1.2720	0.0065	4541.9417	3148.2341	1572.0	2475.0	0.6352	1094.0	0.4420	478.0	774.0	1196.0	0.6472	0.3997	608.0	798.0	1267.0	0.6298	0.4799
0.0	37.0	37	1.2745	0.0065	4550.8572	3154.4138	1573.0	2475.0	0.6356	1100.0	0.4444	481.0	774.0	1196.0	0.6472	0.4022	611.0	799.0	1267.0	0.6306	0.4822
0.0	38.0	38	1.2769	0.0065	4559.2224	3160.2121	1566.0	2475.0	0.6327	1098.0	0.4436	481.0	770.0	1196.0	0.6438	0.4022	609.0	796.0	1267.0	0.6283	0.4807
0.0	39.0	39	1.2769	0.0065	4559.3229	3160.2818	1570.0	2475.0	0.6343	1096.0	0.4428	481.0	772.0	1196.0	0.6455	0.4022	607.0	798.0	1267.0	0.6298	0.4791
0.0	40.0	40	1.2790	0.0065	4566.8061	3165.4687	1565.0	2475.0	0.6323	1093.0	0.4416	480.0	769.0	1196.0	0.6430	0.4013	605.0	796.0	1267.0	0.6283	0.4775
0.0	41.0	41	1.2781	0.0065	4563.7781	3163.3700	1574.0	2475.0	0.6360	1104.0	0.4461	485.0	775.0	1196.0	0.6480	0.4055	611.0	799.0	1267.0	0.6306	0.4822
0.0	42.0	42	1.2805	0.0065	4572.1858	3169.1977	1569.0	2475.0	0.6339	1095.0	0.4424	478.0	775.0	1196.0	0.6480	0.3997	609.0	794.0	1267.0	0.6267	0.4807
0.0	43.0	43	1.2805	0.0065	4572.3049	3169.2803	1573.0	2475.0	0.6356	1101.0	0.4448	485.0	774.0	1196.0	0.6472	0.4055	608.0	799.0	1267.0	0.6306	0.4799
0.0	44.0	44	1.2802	0.0065	4571.2266	3168.5328	1570.0	2475.0	0.6343	1100.0	0.4444	484.0	774.0	1196.0	0.6472	0.4047	608.0	796.0	1267.0	0.6283	0.4799
0.0	45.0	45	1.2801	0.0065	4570.7812	3168.2241	1569.0	2475.0	0.6339	1097.0	0.4432	481.0	770.0	1196.0	0.6438	0.4022	608.0	799.0	1267.0	0.6306	0.4799
0.0	46.0	46	1.2812	0.0065	4574.7385	3170.9671	1568.0	2475.0	0.6335	1094.0	0.4420	478.0	771.0	1196.0	0.6446	0.3997	608.0	797.0	1267.0	0.6290	0.4799
0.0	47.0	47	1.2830	0.0065	4581.2375	3175.4718	1567.0	2475.0	0.6331	1104.0	0.4461	485.0	768.0	1196.0	0.6421	0.4055	611.0	799.0	1267.0	0.6306	0.4822
0.0	48.0	48	1.2809	0.0065	4573.6493	3170.2121	1575.0	2475.0	0.6364	1100.0	0.4444	485.0	776.0	1196.0	0.6488	0.4055	607.0	799.0	1267.0	0.6306	0.4791
0.0	49.0	49	1.2822	0.0065	4578.3301	3173.4566	1575.0	2475.0	0.6364	1104.0	0.4461	485.0	776.0	1196.0	0.6488	0.4055	611.0	799.0	1267.0	0.6306	0.4822
0.0	50.0	50	1.2832	0.0065	4581.9667	3175.9773	1570.0	2475.0	0.6343	1103.0	0.4457	482.0	770.0	1196.0	0.6438	0.4030	613.0	800.0	1267.0	0.6314	0.4838
0.0	51.0	51	1.2823	0.0065	4578.8190	3173.7955	1567.0	2475.0	0.6331	1095.0	0.4424	477.0	771.0	1196.0	0.6446	0.3988	610.0	796.0	1267.0	0.6283	0.4815

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

donoway/GSM8K-Binary_Llama-3.2-1B-sgk3topm

GSM8K-Binary_Llama-3.2-1B-sgk3topm

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

donoway/
GSM8K-Binary_Llama-3.2-1B-sgk3topm