GSM8K-Binary_Llama-3.2-1B-kcrbohqy

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: 1.5026
• Model Preparation Time: 0.0059
• Mdl: 5365.4215
• Accumulated Loss: 3719.0268
• Correct Preds: 1963.0
• Total Preds: 2475.0
• Accuracy: 0.7931
• Correct Gen Preds: 1691.0
• Gen Accuracy: 0.6832
• Correct Gen Preds 34192: 871.0
• Correct Preds 34192: 1035.0
• Total Labels 34192: 1196.0
• Accuracy 34192: 0.8654
• Gen Accuracy 34192: 0.7283
• Correct Gen Preds 41568: 814.0
• Correct Preds 41568: 928.0
• Total Labels 41568: 1267.0
• Accuracy 41568: 0.7324
• Gen Accuracy 41568: 0.6425

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: constant
• lr_scheduler_warmup_ratio: 0.001
• 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	0.0059	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
1.0257	1.0	47	0.6155	0.0059	2197.8915	1523.4623	1717.0	2475.0	0.6937	8.0	0.0032	0.0	1150.0	1196.0	0.9615	0.0	0.0	567.0	1267.0	0.4475	0.0
0.2829	2.0	94	0.5306	0.0059	1894.7016	1313.3071	1908.0	2475.0	0.7709	7.0	0.0028	0.0	989.0	1196.0	0.8269	0.0	0.0	919.0	1267.0	0.7253	0.0
0.0289	3.0	141	0.5964	0.0059	2129.4510	1476.0229	1931.0	2475.0	0.7802	7.0	0.0028	0.0	886.0	1196.0	0.7408	0.0	0.0	1045.0	1267.0	0.8248	0.0
0.2101	4.0	188	1.0279	0.0059	3670.3209	2544.0726	1902.0	2475.0	0.7685	689.0	0.2784	293.0	1091.0	1196.0	0.9122	0.2450	388.0	811.0	1267.0	0.6401	0.3062
0.7687	5.0	235	0.9640	0.0059	3442.2378	2385.9775	1948.0	2475.0	0.7871	446.0	0.1802	132.0	1004.0	1196.0	0.8395	0.1104	307.0	944.0	1267.0	0.7451	0.2423
0.0001	6.0	282	1.8360	0.0059	6555.6511	4544.0311	1870.0	2475.0	0.7556	1150.0	0.4646	673.0	1110.0	1196.0	0.9281	0.5627	470.0	760.0	1267.0	0.5998	0.3710
0.0114	7.0	329	1.5026	0.0059	5365.4215	3719.0268	1963.0	2475.0	0.7931	1691.0	0.6832	871.0	1035.0	1196.0	0.8654	0.7283	814.0	928.0	1267.0	0.7324	0.6425
0.0001	8.0	376	1.7366	0.0059	6200.7876	4298.0585	1937.0	2475.0	0.7826	1561.0	0.6307	686.0	938.0	1196.0	0.7843	0.5736	867.0	999.0	1267.0	0.7885	0.6843
0.0	9.0	423	1.9428	0.0059	6937.0874	4808.4226	1919.0	2475.0	0.7754	1722.0	0.6958	823.0	959.0	1196.0	0.8018	0.6881	890.0	960.0	1267.0	0.7577	0.7024
0.0	10.0	470	1.9499	0.0059	6962.3264	4825.9169	1923.0	2475.0	0.7770	1742.0	0.7038	785.0	911.0	1196.0	0.7617	0.6564	948.0	1012.0	1267.0	0.7987	0.7482
0.0	11.0	517	1.9904	0.0059	7107.2016	4926.3368	1928.0	2475.0	0.7790	1741.0	0.7034	869.0	1000.0	1196.0	0.8361	0.7266	863.0	928.0	1267.0	0.7324	0.6811
0.0	12.0	564	1.9920	0.0059	7112.9400	4930.3143	1931.0	2475.0	0.7802	1740.0	0.7030	871.0	1003.0	1196.0	0.8386	0.7283	860.0	928.0	1267.0	0.7324	0.6788
0.0	13.0	611	1.9893	0.0059	7103.2337	4923.5864	1931.0	2475.0	0.7802	1749.0	0.7067	872.0	1000.0	1196.0	0.8361	0.7291	869.0	931.0	1267.0	0.7348	0.6859
0.0	14.0	658	1.9887	0.0059	7100.8464	4921.9317	1930.0	2475.0	0.7798	1755.0	0.7091	874.0	1000.0	1196.0	0.8361	0.7308	872.0	930.0	1267.0	0.7340	0.6882
0.0	15.0	705	1.9885	0.0059	7100.2310	4921.5051	1933.0	2475.0	0.7810	1750.0	0.7071	873.0	1000.0	1196.0	0.8361	0.7299	868.0	933.0	1267.0	0.7364	0.6851
0.0	16.0	752	1.9883	0.0059	7099.4041	4920.9320	1931.0	2475.0	0.7802	1755.0	0.7091	876.0	999.0	1196.0	0.8353	0.7324	870.0	932.0	1267.0	0.7356	0.6867
0.0	17.0	799	1.9886	0.0059	7100.6278	4921.7802	1931.0	2475.0	0.7802	1755.0	0.7091	873.0	999.0	1196.0	0.8353	0.7299	874.0	932.0	1267.0	0.7356	0.6898
0.0	18.0	846	1.9860	0.0059	7091.2435	4915.2755	1934.0	2475.0	0.7814	1759.0	0.7107	877.0	999.0	1196.0	0.8353	0.7333	873.0	935.0	1267.0	0.7380	0.6890

Framework versions

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