GSM8K-Binary_Llama-3.2-1B-f5e1gp29

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: 1.3710
• Model Preparation Time: 0.0058
• Mdl: 4895.4536
• Accumulated Loss: 3393.2699
• Correct Preds: 1979.0
• Total Preds: 2475.0
• Accuracy: 0.7996
• Correct Gen Preds: 1881.0
• Gen Accuracy: 0.76
• Correct Gen Preds 34192: 895.0
• Correct Preds 34192: 956.0
• Total Labels 34192: 1196.0
• Accuracy 34192: 0.7993
• Gen Accuracy 34192: 0.7483
• Correct Gen Preds 41568: 979.0
• Correct Preds 41568: 1023.0
• Total Labels 41568: 1267.0
• Accuracy 41568: 0.8074
• Gen Accuracy 41568: 0.7727

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	0.0058	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
0.3983	1.0	49	0.5710	0.0058	2038.7089	1413.1253	1846.0	2475.0	0.7459	8.0	0.0032	0.0	1068.0	1196.0	0.8930	0.0	0.0	778.0	1267.0	0.6140	0.0
0.7238	2.0	98	0.5804	0.0058	2072.3256	1436.4266	1842.0	2475.0	0.7442	54.0	0.0218	0.0	695.0	1196.0	0.5811	0.0	46.0	1147.0	1267.0	0.9053	0.0363
0.2749	3.0	147	0.6253	0.0058	2232.6603	1547.5622	1858.0	2475.0	0.7507	64.0	0.0259	0.0	701.0	1196.0	0.5861	0.0	56.0	1157.0	1267.0	0.9132	0.0442
0.597	4.0	196	0.8394	0.0058	2997.3738	2077.6212	1911.0	2475.0	0.7721	212.0	0.0857	95.0	1127.0	1196.0	0.9423	0.0794	109.0	784.0	1267.0	0.6188	0.0860
0.0501	5.0	245	0.8325	0.0058	2972.4858	2060.3702	1947.0	2475.0	0.7867	902.0	0.3644	211.0	870.0	1196.0	0.7274	0.1764	682.0	1077.0	1267.0	0.8500	0.5383
0.4066	6.0	294	1.4218	0.0058	5076.7544	3518.9380	1962.0	2475.0	0.7927	1696.0	0.6853	936.0	1062.0	1196.0	0.8880	0.7826	750.0	900.0	1267.0	0.7103	0.5919
0.9865	7.0	343	1.2377	0.0058	4419.2414	3063.1847	1900.0	2475.0	0.7677	1592.0	0.6432	600.0	778.0	1196.0	0.6505	0.5017	983.0	1122.0	1267.0	0.8856	0.7758
0.0072	8.0	392	1.3710	0.0058	4895.4536	3393.2699	1979.0	2475.0	0.7996	1881.0	0.76	895.0	956.0	1196.0	0.7993	0.7483	979.0	1023.0	1267.0	0.8074	0.7727
0.0	9.0	441	1.6015	0.0058	5718.5637	3963.8063	1971.0	2475.0	0.7964	1898.0	0.7669	958.0	999.0	1196.0	0.8353	0.8010	932.0	972.0	1267.0	0.7672	0.7356
0.0007	10.0	490	1.7766	0.0058	6343.6664	4397.0945	1967.0	2475.0	0.7947	1930.0	0.7798	998.0	1022.0	1196.0	0.8545	0.8344	924.0	945.0	1267.0	0.7459	0.7293
0.0	11.0	539	1.8418	0.0058	6576.5420	4558.5115	1960.0	2475.0	0.7919	1930.0	0.7798	1013.0	1034.0	1196.0	0.8645	0.8470	909.0	926.0	1267.0	0.7309	0.7174
0.0	12.0	588	1.8374	0.0058	6560.5850	4547.4510	1960.0	2475.0	0.7919	1926.0	0.7782	1009.0	1033.0	1196.0	0.8637	0.8436	909.0	927.0	1267.0	0.7316	0.7174
0.0	13.0	637	1.8365	0.0058	6557.4102	4545.2504	1958.0	2475.0	0.7911	1928.0	0.7790	1010.0	1031.0	1196.0	0.8620	0.8445	910.0	927.0	1267.0	0.7316	0.7182
0.0	14.0	686	1.8354	0.0058	6553.5613	4542.5825	1958.0	2475.0	0.7911	1932.0	0.7806	1011.0	1030.0	1196.0	0.8612	0.8453	913.0	928.0	1267.0	0.7324	0.7206
0.0	15.0	735	1.8357	0.0058	6554.7112	4543.3796	1964.0	2475.0	0.7935	1934.0	0.7814	1010.0	1031.0	1196.0	0.8620	0.8445	916.0	933.0	1267.0	0.7364	0.7230
0.4056	16.0	784	1.8367	0.0058	6558.1779	4545.7825	1963.0	2475.0	0.7931	1938.0	0.7830	1011.0	1030.0	1196.0	0.8612	0.8453	919.0	933.0	1267.0	0.7364	0.7253
0.0	17.0	833	1.8323	0.0058	6542.6779	4535.0388	1963.0	2475.0	0.7931	1935.0	0.7818	1012.0	1030.0	1196.0	0.8612	0.8462	915.0	933.0	1267.0	0.7364	0.7222
0.0	18.0	882	1.8342	0.0058	6549.3643	4539.6734	1964.0	2475.0	0.7935	1939.0	0.7834	1012.0	1030.0	1196.0	0.8612	0.8462	919.0	934.0	1267.0	0.7372	0.7253

Framework versions

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