GSM8K-Binary_Llama-3.2-1B-qjearsjc

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: 1.3357
• Model Preparation Time: 0.0056
• Mdl: 4769.2624
• Accumulated Loss: 3305.8008
• Correct Preds: 1535.0
• Total Preds: 2475.0
• Accuracy: 0.6202
• Correct Gen Preds: 462.0
• Gen Accuracy: 0.1867
• Correct Gen Preds 34192: 259.0
• Correct Preds 34192: 766.0
• Total Labels 34192: 1196.0
• Accuracy 34192: 0.6405
• Gen Accuracy 34192: 0.2166
• Correct Gen Preds 41568: 195.0
• Correct Preds 41568: 769.0
• Total Labels 41568: 1267.0
• Accuracy 41568: 0.6069
• Gen Accuracy 41568: 0.1539

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	0.0056	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
2.159	1.0	2	2.4593	0.0056	8781.1889	6086.6563	1266.0	2475.0	0.5115	1271.0	0.5135	0.0	0.0	1196.0	0.0	0.0	1263.0	1266.0	1267.0	0.9992	0.9968
0.9326	2.0	4	2.9664	0.0056	10591.9006	7341.7460	1196.0	2475.0	0.4832	8.0	0.0032	0.0	1196.0	1196.0	1.0	0.0	0.0	0.0	1267.0	0.0	0.0
0.934	3.0	6	0.8287	0.0056	2959.1705	2051.1407	1223.0	2475.0	0.4941	7.0	0.0028	0.0	1144.0	1196.0	0.9565	0.0	0.0	79.0	1267.0	0.0624	0.0
1.266	4.0	8	0.8432	0.0056	3010.6868	2086.8491	1266.0	2475.0	0.5115	8.0	0.0032	0.0	3.0	1196.0	0.0025	0.0	0.0	1263.0	1267.0	0.9968	0.0
1.1255	5.0	10	0.7617	0.0056	2719.6432	1885.1130	1292.0	2475.0	0.5220	8.0	0.0032	0.0	1120.0	1196.0	0.9365	0.0	0.0	172.0	1267.0	0.1358	0.0
0.5485	6.0	12	0.7261	0.0056	2592.7188	1797.1357	1434.0	2475.0	0.5794	8.0	0.0032	0.0	576.0	1196.0	0.4816	0.0	0.0	858.0	1267.0	0.6772	0.0
0.774	7.0	14	0.7111	0.0056	2538.9261	1759.8495	1522.0	2475.0	0.6149	8.0	0.0032	0.0	731.0	1196.0	0.6112	0.0	0.0	791.0	1267.0	0.6243	0.0
0.7172	8.0	16	0.8789	0.0056	3138.2628	2175.2780	1486.0	2475.0	0.6004	8.0	0.0032	0.0	587.0	1196.0	0.4908	0.0	0.0	899.0	1267.0	0.7096	0.0
0.0124	9.0	18	1.0022	0.0056	3578.4299	2480.3786	1519.0	2475.0	0.6137	58.0	0.0234	31.0	607.0	1196.0	0.5075	0.0259	19.0	912.0	1267.0	0.7198	0.0150
0.5132	10.0	20	1.3357	0.0056	4769.2624	3305.8008	1535.0	2475.0	0.6202	462.0	0.1867	259.0	766.0	1196.0	0.6405	0.2166	195.0	769.0	1267.0	0.6069	0.1539
0.5116	11.0	22	1.7177	0.0056	6133.3370	4251.3052	1510.0	2475.0	0.6101	958.0	0.3871	432.0	726.0	1196.0	0.6070	0.3612	517.0	784.0	1267.0	0.6188	0.4081
0.5115	12.0	24	2.0096	0.0056	7175.7009	4973.8169	1505.0	2475.0	0.6081	1186.0	0.4792	510.0	694.0	1196.0	0.5803	0.4264	667.0	811.0	1267.0	0.6401	0.5264
0.0	13.0	26	2.2179	0.0056	7919.3806	5489.2963	1481.0	2475.0	0.5984	1283.0	0.5184	546.0	662.0	1196.0	0.5535	0.4565	728.0	819.0	1267.0	0.6464	0.5746
0.0	14.0	28	2.3460	0.0056	8376.7131	5806.2950	1486.0	2475.0	0.6004	1339.0	0.5410	565.0	649.0	1196.0	0.5426	0.4724	765.0	837.0	1267.0	0.6606	0.6038
0.0	15.0	30	2.4274	0.0056	8667.6229	6007.9384	1483.0	2475.0	0.5992	1361.0	0.5499	574.0	643.0	1196.0	0.5376	0.4799	778.0	840.0	1267.0	0.6630	0.6140
0.5114	16.0	32	2.4736	0.0056	8832.2736	6122.0655	1480.0	2475.0	0.5980	1385.0	0.5596	586.0	643.0	1196.0	0.5376	0.4900	790.0	837.0	1267.0	0.6606	0.6235
0.0	17.0	34	2.4918	0.0056	8897.3192	6167.1517	1479.0	2475.0	0.5976	1396.0	0.5640	596.0	646.0	1196.0	0.5401	0.4983	791.0	833.0	1267.0	0.6575	0.6243
0.5114	18.0	36	2.5053	0.0056	8945.5765	6200.6011	1476.0	2475.0	0.5964	1399.0	0.5653	600.0	647.0	1196.0	0.5410	0.5017	790.0	829.0	1267.0	0.6543	0.6235
0.0	19.0	38	2.5135	0.0056	8975.0189	6221.0090	1479.0	2475.0	0.5976	1404.0	0.5673	606.0	651.0	1196.0	0.5443	0.5067	789.0	828.0	1267.0	0.6535	0.6227
0.5114	20.0	40	2.5146	0.0056	8978.6771	6223.5447	1481.0	2475.0	0.5984	1410.0	0.5697	613.0	658.0	1196.0	0.5502	0.5125	788.0	823.0	1267.0	0.6496	0.6219
0.5114	21.0	42	2.5164	0.0056	8985.2387	6228.0929	1481.0	2475.0	0.5984	1414.0	0.5713	619.0	662.0	1196.0	0.5535	0.5176	786.0	819.0	1267.0	0.6464	0.6204
0.0	22.0	44	2.5151	0.0056	8980.5739	6224.8595	1485.0	2475.0	0.6	1419.0	0.5733	625.0	665.0	1196.0	0.5560	0.5226	785.0	820.0	1267.0	0.6472	0.6196
0.0	23.0	46	2.5157	0.0056	8982.8389	6226.4294	1478.0	2475.0	0.5972	1415.0	0.5717	623.0	663.0	1196.0	0.5543	0.5209	783.0	815.0	1267.0	0.6433	0.6180
0.0	24.0	48	2.5154	0.0056	8981.6130	6225.5797	1489.0	2475.0	0.6016	1421.0	0.5741	629.0	670.0	1196.0	0.5602	0.5259	783.0	819.0	1267.0	0.6464	0.6180
0.0	25.0	50	2.5149	0.0056	8979.8291	6224.3432	1483.0	2475.0	0.5992	1418.0	0.5729	625.0	668.0	1196.0	0.5585	0.5226	784.0	815.0	1267.0	0.6433	0.6188
0.5114	26.0	52	2.5138	0.0056	8975.9674	6221.6665	1485.0	2475.0	0.6	1422.0	0.5745	631.0	672.0	1196.0	0.5619	0.5276	782.0	813.0	1267.0	0.6417	0.6172
0.5114	27.0	54	2.5126	0.0056	8971.6565	6218.6784	1480.0	2475.0	0.5980	1419.0	0.5733	630.0	667.0	1196.0	0.5577	0.5268	780.0	813.0	1267.0	0.6417	0.6156
0.0	28.0	56	2.5118	0.0056	8968.9510	6216.8031	1487.0	2475.0	0.6008	1424.0	0.5754	630.0	672.0	1196.0	0.5619	0.5268	785.0	815.0	1267.0	0.6433	0.6196
0.5114	29.0	58	2.5114	0.0056	8967.4311	6215.7496	1486.0	2475.0	0.6004	1424.0	0.5754	636.0	675.0	1196.0	0.5644	0.5318	779.0	811.0	1267.0	0.6401	0.6148
0.5114	30.0	60	2.5107	0.0056	8965.0040	6214.0673	1490.0	2475.0	0.6020	1425.0	0.5758	635.0	675.0	1196.0	0.5644	0.5309	781.0	815.0	1267.0	0.6433	0.6164
0.5114	31.0	62	2.5092	0.0056	8959.3649	6210.1585	1491.0	2475.0	0.6024	1427.0	0.5766	636.0	677.0	1196.0	0.5661	0.5318	782.0	814.0	1267.0	0.6425	0.6172
0.5114	32.0	64	2.5104	0.0056	8963.9824	6213.3591	1485.0	2475.0	0.6	1425.0	0.5758	635.0	674.0	1196.0	0.5635	0.5309	781.0	811.0	1267.0	0.6401	0.6164
0.5114	33.0	66	2.5094	0.0056	8960.2537	6210.7746	1487.0	2475.0	0.6008	1428.0	0.5770	639.0	676.0	1196.0	0.5652	0.5343	780.0	811.0	1267.0	0.6401	0.6156
0.0	34.0	68	2.5074	0.0056	8953.1812	6205.8723	1488.0	2475.0	0.6012	1425.0	0.5758	633.0	676.0	1196.0	0.5652	0.5293	783.0	812.0	1267.0	0.6409	0.6180
0.5114	35.0	70	2.5108	0.0056	8965.1034	6214.1362	1489.0	2475.0	0.6016	1427.0	0.5766	636.0	675.0	1196.0	0.5644	0.5318	782.0	814.0	1267.0	0.6425	0.6172
0.0	36.0	72	2.5116	0.0056	8968.2043	6216.2855	1490.0	2475.0	0.6020	1426.0	0.5762	637.0	677.0	1196.0	0.5661	0.5326	780.0	813.0	1267.0	0.6417	0.6156
0.0	37.0	74	2.5119	0.0056	8969.1267	6216.9249	1490.0	2475.0	0.6020	1426.0	0.5762	635.0	677.0	1196.0	0.5661	0.5309	782.0	813.0	1267.0	0.6417	0.6172
0.0	38.0	76	2.5082	0.0056	8955.9512	6207.7924	1490.0	2475.0	0.6020	1429.0	0.5774	639.0	677.0	1196.0	0.5661	0.5343	781.0	813.0	1267.0	0.6417	0.6164
0.0	39.0	78	2.5092	0.0056	8959.5687	6210.2998	1485.0	2475.0	0.6	1423.0	0.5749	633.0	674.0	1196.0	0.5635	0.5293	781.0	811.0	1267.0	0.6401	0.6164
0.0	40.0	80	2.5072	0.0056	8952.5199	6205.4140	1491.0	2475.0	0.6024	1426.0	0.5762	638.0	677.0	1196.0	0.5661	0.5334	779.0	814.0	1267.0	0.6425	0.6148

Framework versions

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