GSM8K-Binary_Llama-3.2-1B-kyohy420

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: 1.7333
• Model Preparation Time: 0.0057
• Mdl: 6189.0935
• Accumulated Loss: 4289.9527
• Correct Preds: 1966.0
• Total Preds: 2475.0
• Accuracy: 0.7943
• Correct Gen Preds: 1919.0
• Gen Accuracy: 0.7754
• Correct Gen Preds 34192: 1033.0
• Correct Preds 34192: 1051.0
• Total Labels 34192: 1196.0
• Accuracy 34192: 0.8788
• Gen Accuracy 34192: 0.8637
• Correct Gen Preds 41568: 879.0
• Correct Preds 41568: 915.0
• Total Labels 41568: 1267.0
• Accuracy 41568: 0.7222
• Gen Accuracy 41568: 0.6938

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	0.0057	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
0.5871	1.0	41	0.5846	0.0057	2087.4184	1446.8881	1815.0	2475.0	0.7333	8.0	0.0032	0.0	796.0	1196.0	0.6656	0.0	0.0	1019.0	1267.0	0.8043	0.0
0.3259	2.0	82	0.5427	0.0057	1937.7495	1343.1456	1911.0	2475.0	0.7721	8.0	0.0032	1.0	957.0	1196.0	0.8002	0.0008	0.0	954.0	1267.0	0.7530	0.0
0.1383	3.0	123	0.6677	0.0057	2384.2568	1652.6409	1892.0	2475.0	0.7644	87.0	0.0352	19.0	845.0	1196.0	0.7065	0.0159	60.0	1047.0	1267.0	0.8264	0.0474
0.5615	4.0	164	0.9346	0.0057	3337.0389	2313.0591	1909.0	2475.0	0.7713	1042.0	0.4210	614.0	1035.0	1196.0	0.8654	0.5134	420.0	874.0	1267.0	0.6898	0.3315
0.0373	5.0	205	0.9718	0.0057	3470.0702	2405.2694	1938.0	2475.0	0.7830	1048.0	0.4234	528.0	975.0	1196.0	0.8152	0.4415	514.0	963.0	1267.0	0.7601	0.4057
0.0417	6.0	246	1.2990	0.0057	4638.2735	3215.0062	1895.0	2475.0	0.7657	1372.0	0.5543	553.0	873.0	1196.0	0.7299	0.4624	812.0	1022.0	1267.0	0.8066	0.6409
0.006	7.0	287	1.6147	0.0057	5765.6029	3996.4114	1942.0	2475.0	0.7846	1793.0	0.7244	962.0	1013.0	1196.0	0.8470	0.8043	823.0	929.0	1267.0	0.7332	0.6496
0.0	8.0	328	1.6999	0.0057	6069.9536	4207.3712	1965.0	2475.0	0.7939	1893.0	0.7648	1030.0	1052.0	1196.0	0.8796	0.8612	856.0	913.0	1267.0	0.7206	0.6756
0.0	9.0	369	1.7440	0.0057	6227.1358	4316.3216	1964.0	2475.0	0.7935	1913.0	0.7729	1037.0	1053.0	1196.0	0.8804	0.8671	869.0	911.0	1267.0	0.7190	0.6859
0.0	10.0	410	1.7394	0.0057	6210.7145	4304.9393	1963.0	2475.0	0.7931	1915.0	0.7737	1035.0	1052.0	1196.0	0.8796	0.8654	873.0	911.0	1267.0	0.7190	0.6890
0.0	11.0	451	1.7371	0.0057	6202.5019	4299.2467	1963.0	2475.0	0.7931	1914.0	0.7733	1033.0	1050.0	1196.0	0.8779	0.8637	874.0	913.0	1267.0	0.7206	0.6898
0.0	12.0	492	1.7354	0.0057	6196.6385	4295.1825	1964.0	2475.0	0.7935	1915.0	0.7737	1034.0	1051.0	1196.0	0.8788	0.8645	874.0	913.0	1267.0	0.7206	0.6898
0.0	13.0	533	1.7333	0.0057	6189.0935	4289.9527	1966.0	2475.0	0.7943	1919.0	0.7754	1033.0	1051.0	1196.0	0.8788	0.8637	879.0	915.0	1267.0	0.7222	0.6938
0.0	14.0	574	1.7293	0.0057	6174.5892	4279.8991	1962.0	2475.0	0.7927	1917.0	0.7745	1031.0	1047.0	1196.0	0.8754	0.8620	879.0	915.0	1267.0	0.7222	0.6938
0.0	15.0	615	1.7313	0.0057	6182.0153	4285.0465	1962.0	2475.0	0.7927	1919.0	0.7754	1030.0	1047.0	1196.0	0.8754	0.8612	882.0	915.0	1267.0	0.7222	0.6961
0.0	16.0	656	1.7293	0.0057	6174.8938	4280.1102	1964.0	2475.0	0.7935	1919.0	0.7754	1031.0	1048.0	1196.0	0.8763	0.8620	881.0	916.0	1267.0	0.7230	0.6953
0.0	17.0	697	1.7291	0.0057	6174.0165	4279.5021	1964.0	2475.0	0.7935	1920.0	0.7758	1032.0	1049.0	1196.0	0.8771	0.8629	881.0	915.0	1267.0	0.7222	0.6953
0.0	18.0	738	1.7284	0.0057	6171.6047	4277.8304	1964.0	2475.0	0.7935	1920.0	0.7758	1031.0	1048.0	1196.0	0.8763	0.8620	882.0	916.0	1267.0	0.7230	0.6961
0.0	19.0	779	1.7288	0.0057	6172.8248	4278.6761	1965.0	2475.0	0.7939	1922.0	0.7766	1030.0	1047.0	1196.0	0.8754	0.8612	885.0	918.0	1267.0	0.7245	0.6985
0.0	20.0	820	1.7275	0.0057	6168.3684	4275.5871	1963.0	2475.0	0.7931	1919.0	0.7754	1030.0	1047.0	1196.0	0.8754	0.8612	882.0	916.0	1267.0	0.7230	0.6961
0.0	21.0	861	1.7275	0.0057	6168.3839	4275.5979	1964.0	2475.0	0.7935	1923.0	0.7770	1031.0	1047.0	1196.0	0.8754	0.8620	885.0	917.0	1267.0	0.7238	0.6985
0.0	22.0	902	1.7271	0.0057	6166.9583	4274.6097	1964.0	2475.0	0.7935	1924.0	0.7774	1033.0	1047.0	1196.0	0.8754	0.8637	884.0	917.0	1267.0	0.7238	0.6977
0.4356	23.0	943	1.7266	0.0057	6165.0094	4273.2589	1966.0	2475.0	0.7943	1923.0	0.7770	1030.0	1047.0	1196.0	0.8754	0.8612	886.0	919.0	1267.0	0.7253	0.6993
0.8713	24.0	984	1.7272	0.0057	6167.4313	4274.9376	1965.0	2475.0	0.7939	1926.0	0.7782	1032.0	1047.0	1196.0	0.8754	0.8629	887.0	918.0	1267.0	0.7245	0.7001
0.4356	25.0	1025	1.7285	0.0057	6171.7803	4277.9521	1963.0	2475.0	0.7931	1921.0	0.7762	1030.0	1047.0	1196.0	0.8754	0.8612	884.0	916.0	1267.0	0.7230	0.6977

Framework versions

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