GSM8K-Binary_Llama-3.2-1B-ivxh9bjy

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7423
• Model Preparation Time: 0.0054
• Mdl: 2650.3578
• Accumulated Loss: 1837.0880
• Correct Preds: 1688.0
• Total Preds: 2475.0
• Accuracy: 0.6820
• Correct Gen Preds: 7.0
• Gen Accuracy: 0.0028
• Correct Gen Preds 34192: 0.0
• Correct Preds 34192: 783.0
• Total Labels 34192: 1196.0
• Accuracy 34192: 0.6547
• Gen Accuracy 34192: 0.0
• Correct Gen Preds 41568: 0.0
• Correct Preds 41568: 905.0
• Total Labels 41568: 1267.0
• Accuracy 41568: 0.7143
• Gen Accuracy 41568: 0.0

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: 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	0.0054	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
1.8926	1.0	3	0.7529	0.0054	2688.4400	1863.4846	1326.0	2475.0	0.5358	28.0	0.0113	10.0	888.0	1196.0	0.7425	0.0084	10.0	438.0	1267.0	0.3457	0.0079
0.8692	2.0	6	1.1837	0.0054	4226.7103	2929.7323	1267.0	2475.0	0.5119	156.0	0.0630	0.0	0.0	1196.0	0.0	0.0	148.0	1267.0	1267.0	1.0	0.1168
1.9719	3.0	9	0.7201	0.0054	2571.1173	1782.1627	1463.0	2475.0	0.5911	10.0	0.0040	0.0	1128.0	1196.0	0.9431	0.0	2.0	335.0	1267.0	0.2644	0.0016
0.5314	4.0	12	0.7689	0.0054	2745.5918	1903.0992	1349.0	2475.0	0.5451	20.0	0.0081	0.0	104.0	1196.0	0.0870	0.0	12.0	1245.0	1267.0	0.9826	0.0095
0.5337	5.0	15	0.8571	0.0054	3060.3610	2121.2806	1424.0	2475.0	0.5754	7.0	0.0028	0.0	1151.0	1196.0	0.9624	0.0	0.0	273.0	1267.0	0.2155	0.0
0.9397	6.0	18	0.8323	0.0054	2971.7447	2059.8565	1552.0	2475.0	0.6271	8.0	0.0032	0.0	401.0	1196.0	0.3353	0.0	0.0	1151.0	1267.0	0.9084	0.0
0.1934	7.0	21	0.7423	0.0054	2650.3578	1837.0880	1688.0	2475.0	0.6820	7.0	0.0028	0.0	783.0	1196.0	0.6547	0.0	0.0	905.0	1267.0	0.7143	0.0
0.9493	8.0	24	1.3176	0.0054	4704.6623	3261.0234	1640.0	2475.0	0.6626	278.0	0.1123	169.0	939.0	1196.0	0.7851	0.1413	102.0	701.0	1267.0	0.5533	0.0805
0.3022	9.0	27	1.3117	0.0054	4683.8108	3246.5703	1515.0	2475.0	0.6121	772.0	0.3119	126.0	429.0	1196.0	0.3587	0.1054	638.0	1086.0	1267.0	0.8571	0.5036
0.4787	10.0	30	1.0910	0.0054	3895.7073	2700.2985	1628.0	2475.0	0.6578	823.0	0.3325	274.0	718.0	1196.0	0.6003	0.2291	541.0	910.0	1267.0	0.7182	0.4270
0.0038	11.0	33	2.0771	0.0054	7416.5828	5140.7834	1584.0	2475.0	0.64	1201.0	0.4853	468.0	681.0	1196.0	0.5694	0.3913	726.0	903.0	1267.0	0.7127	0.5730
0.0043	12.0	36	2.2125	0.0054	7900.0977	5475.9304	1585.0	2475.0	0.6404	1442.0	0.5826	603.0	662.0	1196.0	0.5535	0.5042	832.0	923.0	1267.0	0.7285	0.6567
0.0001	13.0	39	2.2169	0.0054	7915.9312	5486.9054	1621.0	2475.0	0.6549	1458.0	0.5891	751.0	818.0	1196.0	0.6839	0.6279	700.0	803.0	1267.0	0.6338	0.5525
0.4529	14.0	42	2.5412	0.0054	9073.8672	6289.5255	1607.0	2475.0	0.6493	1464.0	0.5915	614.0	677.0	1196.0	0.5661	0.5134	843.0	930.0	1267.0	0.7340	0.6654
0.4524	15.0	45	2.9305	0.0054	10463.8496	7252.9878	1610.0	2475.0	0.6505	1474.0	0.5956	683.0	741.0	1196.0	0.6196	0.5711	784.0	869.0	1267.0	0.6859	0.6188
0.9048	16.0	48	3.2752	0.0054	11694.7828	8106.2057	1621.0	2475.0	0.6549	1480.0	0.5980	788.0	854.0	1196.0	0.7140	0.6589	685.0	767.0	1267.0	0.6054	0.5406
0.0	17.0	51	3.5192	0.0054	12565.8354	8709.9734	1616.0	2475.0	0.6529	1475.0	0.5960	827.0	897.0	1196.0	0.75	0.6915	641.0	719.0	1267.0	0.5675	0.5059
0.4524	18.0	54	3.6613	0.0054	13073.4132	9061.7995	1603.0	2475.0	0.6477	1468.0	0.5931	847.0	915.0	1196.0	0.7651	0.7082	614.0	688.0	1267.0	0.5430	0.4846
0.4524	19.0	57	3.7335	0.0054	13331.1999	9240.4837	1605.0	2475.0	0.6485	1470.0	0.5939	857.0	927.0	1196.0	0.7751	0.7166	606.0	678.0	1267.0	0.5351	0.4783
0.0	20.0	60	3.7780	0.0054	13489.9545	9350.5239	1598.0	2475.0	0.6457	1479.0	0.5976	868.0	928.0	1196.0	0.7759	0.7258	604.0	670.0	1267.0	0.5288	0.4767
0.0	21.0	63	3.7912	0.0054	13537.2531	9383.3089	1604.0	2475.0	0.6481	1484.0	0.5996	871.0	933.0	1196.0	0.7801	0.7283	606.0	671.0	1267.0	0.5296	0.4783
0.4524	22.0	66	3.7968	0.0054	13557.2370	9397.1606	1605.0	2475.0	0.6485	1480.0	0.5980	871.0	931.0	1196.0	0.7784	0.7283	602.0	674.0	1267.0	0.5320	0.4751
0.9048	23.0	69	3.8063	0.0054	13591.2194	9420.7154	1607.0	2475.0	0.6493	1484.0	0.5996	871.0	933.0	1196.0	0.7801	0.7283	606.0	674.0	1267.0	0.5320	0.4783
0.4524	24.0	72	3.8033	0.0054	13580.3724	9413.1968	1607.0	2475.0	0.6493	1489.0	0.6016	871.0	930.0	1196.0	0.7776	0.7283	611.0	677.0	1267.0	0.5343	0.4822
0.4524	25.0	75	3.8088	0.0054	13599.9088	9426.7384	1606.0	2475.0	0.6489	1492.0	0.6028	872.0	928.0	1196.0	0.7759	0.7291	613.0	678.0	1267.0	0.5351	0.4838
0.9048	26.0	78	3.8077	0.0054	13595.8914	9423.9538	1608.0	2475.0	0.6497	1494.0	0.6036	871.0	928.0	1196.0	0.7759	0.7283	616.0	680.0	1267.0	0.5367	0.4862
0.4524	27.0	81	3.8064	0.0054	13591.4585	9420.8811	1609.0	2475.0	0.6501	1493.0	0.6032	869.0	928.0	1196.0	0.7759	0.7266	617.0	681.0	1267.0	0.5375	0.4870
0.0	28.0	84	3.8025	0.0054	13577.4399	9411.1642	1608.0	2475.0	0.6497	1495.0	0.6040	870.0	928.0	1196.0	0.7759	0.7274	618.0	680.0	1267.0	0.5367	0.4878
0.0	29.0	87	3.8055	0.0054	13588.0611	9418.5263	1615.0	2475.0	0.6525	1496.0	0.6044	869.0	931.0	1196.0	0.7784	0.7266	620.0	684.0	1267.0	0.5399	0.4893
0.0	30.0	90	3.8028	0.0054	13578.4494	9411.8640	1607.0	2475.0	0.6493	1499.0	0.6057	868.0	925.0	1196.0	0.7734	0.7258	624.0	682.0	1267.0	0.5383	0.4925
0.4524	31.0	93	3.8007	0.0054	13571.0659	9406.7461	1610.0	2475.0	0.6505	1497.0	0.6048	866.0	924.0	1196.0	0.7726	0.7241	624.0	686.0	1267.0	0.5414	0.4925
0.4524	32.0	96	3.8028	0.0054	13578.6452	9411.9996	1610.0	2475.0	0.6505	1498.0	0.6053	862.0	923.0	1196.0	0.7717	0.7207	629.0	687.0	1267.0	0.5422	0.4964
0.4524	33.0	99	3.8003	0.0054	13569.6111	9405.7377	1610.0	2475.0	0.6505	1503.0	0.6073	869.0	925.0	1196.0	0.7734	0.7266	627.0	685.0	1267.0	0.5406	0.4949
0.4524	34.0	102	3.7994	0.0054	13566.5818	9403.6379	1611.0	2475.0	0.6509	1501.0	0.6065	866.0	924.0	1196.0	0.7726	0.7241	628.0	687.0	1267.0	0.5422	0.4957
0.0	35.0	105	3.7990	0.0054	13565.1272	9402.6297	1610.0	2475.0	0.6505	1501.0	0.6065	864.0	920.0	1196.0	0.7692	0.7224	630.0	690.0	1267.0	0.5446	0.4972
0.4524	36.0	108	3.8014	0.0054	13573.4117	9408.3720	1610.0	2475.0	0.6505	1499.0	0.6057	866.0	921.0	1196.0	0.7701	0.7241	626.0	689.0	1267.0	0.5438	0.4941
0.4524	37.0	111	3.7985	0.0054	13563.0986	9401.2236	1608.0	2475.0	0.6497	1503.0	0.6073	864.0	920.0	1196.0	0.7692	0.7224	632.0	688.0	1267.0	0.5430	0.4988

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1