BoolQ_Llama-3.2-1B-4lp9g5r3

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: 1.5927
• Model Preparation Time: 0.0058
• Mdl: 7513.6957
• Accumulated Loss: 5208.0970
• Correct Preds: 2609.0
• Total Preds: 3270.0
• Accuracy: 0.7979
• Correct Gen Preds: 2610.0
• Gen Accuracy: 0.7982
• Correct Gen Preds 9642: 1661.0
• Correct Preds 9642: 1668.0
• Total Labels 9642: 2026.0
• Accuracy 9642: 0.8233
• Gen Accuracy 9642: 0.8198
• Correct Gen Preds 2822: 940.0
• Correct Preds 2822: 941.0
• Total Labels 2822: 1231.0
• Accuracy 2822: 0.7644
• Gen Accuracy 2822: 0.7636

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: 120
• 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 9642	Correct Preds 9642	Total Labels 9642	Accuracy 9642	Gen Accuracy 9642	Correct Gen Preds 2822	Correct Preds 2822	Total Labels 2822	Accuracy 2822	Gen Accuracy 2822
No log	0	0	0.7080	0.0058	3339.8933	2315.0376	2032.0	3270.0	0.6214	2040.0	0.6239	2007.0	2008.0	2026.0	0.9911	0.9906	24.0	24.0	1231.0	0.0195	0.0195
0.5297	1.0	54	0.5655	0.0058	2667.8169	1849.1897	2391.0	3270.0	0.7312	2397.0	0.7330	1482.0	1483.0	2026.0	0.7320	0.7315	906.0	908.0	1231.0	0.7376	0.7360
0.429	2.0	108	0.6555	0.0058	3092.6188	2143.6400	2562.0	3270.0	0.7835	2524.0	0.7719	1836.0	1856.0	2026.0	0.9161	0.9062	680.0	706.0	1231.0	0.5735	0.5524
0.1091	3.0	162	0.9086	0.0058	4286.2025	2970.9692	2566.0	3270.0	0.7847	2517.0	0.7697	1682.0	1729.0	2026.0	0.8534	0.8302	827.0	837.0	1231.0	0.6799	0.6718
0.3827	4.0	216	1.0952	0.0058	5166.9108	3581.4297	2592.0	3270.0	0.7927	2498.0	0.7639	1556.0	1643.0	2026.0	0.8110	0.7680	933.0	949.0	1231.0	0.7709	0.7579
0.0001	5.0	270	1.4491	0.0058	6836.4286	4738.6512	2590.0	3270.0	0.7920	2589.0	0.7917	1644.0	1653.0	2026.0	0.8159	0.8115	936.0	937.0	1231.0	0.7612	0.7604
0.0006	6.0	324	1.6538	0.0058	7802.1499	5408.0382	2602.0	3270.0	0.7957	2605.0	0.7966	1797.0	1801.0	2026.0	0.8889	0.8870	799.0	801.0	1231.0	0.6507	0.6491
0.0001	7.0	378	1.5927	0.0058	7513.6957	5208.0970	2609.0	3270.0	0.7979	2610.0	0.7982	1661.0	1668.0	2026.0	0.8233	0.8198	940.0	941.0	1231.0	0.7644	0.7636
0.0	8.0	432	1.6183	0.0058	7634.6804	5291.9572	2601.0	3270.0	0.7954	2603.0	0.7960	1657.0	1663.0	2026.0	0.8208	0.8179	937.0	938.0	1231.0	0.7620	0.7612
0.0	9.0	486	1.6373	0.0058	7724.0835	5353.9267	2602.0	3270.0	0.7957	2605.0	0.7966	1659.0	1664.0	2026.0	0.8213	0.8189	938.0	938.0	1231.0	0.7620	0.7620
0.0	10.0	540	1.6487	0.0058	7777.7540	5391.1283	2603.0	3270.0	0.7960	2607.0	0.7972	1660.0	1665.0	2026.0	0.8218	0.8193	938.0	938.0	1231.0	0.7620	0.7620
0.0	11.0	594	1.6598	0.0058	7830.1323	5427.4341	2603.0	3270.0	0.7960	2607.0	0.7972	1659.0	1664.0	2026.0	0.8213	0.8189	939.0	939.0	1231.0	0.7628	0.7628
0.0	12.0	648	1.6698	0.0058	7877.2390	5460.0860	2604.0	3270.0	0.7963	2607.0	0.7972	1661.0	1667.0	2026.0	0.8228	0.8198	937.0	937.0	1231.0	0.7612	0.7612
0.0	13.0	702	1.6788	0.0058	7920.0781	5489.7798	2603.0	3270.0	0.7960	2606.0	0.7969	1660.0	1666.0	2026.0	0.8223	0.8193	937.0	937.0	1231.0	0.7612	0.7612
0.0	14.0	756	1.6880	0.0058	7963.3426	5519.7685	2604.0	3270.0	0.7963	2607.0	0.7972	1660.0	1666.0	2026.0	0.8223	0.8193	938.0	938.0	1231.0	0.7620	0.7620
0.0	15.0	810	1.6918	0.0058	7981.2343	5532.1700	2603.0	3270.0	0.7960	2607.0	0.7972	1660.0	1665.0	2026.0	0.8218	0.8193	938.0	938.0	1231.0	0.7620	0.7620
0.0	16.0	864	1.6997	0.0058	8018.5627	5558.0441	2606.0	3270.0	0.7969	2610.0	0.7982	1663.0	1668.0	2026.0	0.8233	0.8208	938.0	938.0	1231.0	0.7620	0.7620
0.0	17.0	918	1.7052	0.0058	8044.3508	5575.9191	2601.0	3270.0	0.7954	2605.0	0.7966	1659.0	1664.0	2026.0	0.8213	0.8189	937.0	937.0	1231.0	0.7612	0.7612
0.0	18.0	972	1.7084	0.0058	8059.3827	5586.3384	2602.0	3270.0	0.7957	2606.0	0.7969	1660.0	1665.0	2026.0	0.8218	0.8193	937.0	937.0	1231.0	0.7612	0.7612
0.0	19.0	1026	1.7110	0.0058	8071.9707	5595.0637	2603.0	3270.0	0.7960	2607.0	0.7972	1661.0	1666.0	2026.0	0.8223	0.8198	937.0	937.0	1231.0	0.7612	0.7612
0.0	20.0	1080	1.7147	0.0058	8089.1272	5606.9557	2602.0	3270.0	0.7957	2605.0	0.7966	1659.0	1665.0	2026.0	0.8218	0.8189	937.0	937.0	1231.0	0.7612	0.7612
0.0	21.0	1134	1.7125	0.0058	8079.1133	5600.0146	2605.0	3270.0	0.7966	2609.0	0.7979	1662.0	1667.0	2026.0	0.8228	0.8203	938.0	938.0	1231.0	0.7620	0.7620
0.0	22.0	1188	1.7151	0.0058	8091.0910	5608.3169	2604.0	3270.0	0.7963	2607.0	0.7972	1659.0	1665.0	2026.0	0.8218	0.8189	939.0	939.0	1231.0	0.7628	0.7628
0.0	23.0	1242	1.7160	0.0058	8095.3381	5611.2608	2602.0	3270.0	0.7957	2606.0	0.7969	1660.0	1665.0	2026.0	0.8218	0.8193	937.0	937.0	1231.0	0.7612	0.7612
0.0	24.0	1296	1.7144	0.0058	8087.7767	5606.0196	2605.0	3270.0	0.7966	2609.0	0.7979	1663.0	1668.0	2026.0	0.8233	0.8208	937.0	937.0	1231.0	0.7612	0.7612
0.0	25.0	1350	1.7150	0.0058	8090.7756	5608.0983	2604.0	3270.0	0.7963	2608.0	0.7976	1662.0	1667.0	2026.0	0.8228	0.8203	937.0	937.0	1231.0	0.7612	0.7612
0.0	26.0	1404	1.7128	0.0058	8080.3770	5600.8906	2603.0	3270.0	0.7960	2607.0	0.7972	1662.0	1667.0	2026.0	0.8228	0.8203	936.0	936.0	1231.0	0.7604	0.7604
0.0	27.0	1458	1.7153	0.0058	8092.1583	5609.0567	2605.0	3270.0	0.7966	2609.0	0.7979	1662.0	1667.0	2026.0	0.8228	0.8203	938.0	938.0	1231.0	0.7620	0.7620
0.0	28.0	1512	1.7140	0.0058	8086.0919	5604.8518	2604.0	3270.0	0.7963	2607.0	0.7972	1660.0	1666.0	2026.0	0.8223	0.8193	938.0	938.0	1231.0	0.7620	0.7620
0.0	29.0	1566	1.7153	0.0058	8092.1390	5609.0433	2602.0	3270.0	0.7957	2606.0	0.7969	1660.0	1665.0	2026.0	0.8218	0.8193	937.0	937.0	1231.0	0.7612	0.7612
0.0	30.0	1620	1.7134	0.0058	8083.1388	5602.8049	2605.0	3270.0	0.7966	2609.0	0.7979	1663.0	1668.0	2026.0	0.8233	0.8208	937.0	937.0	1231.0	0.7612	0.7612
0.0	31.0	1674	1.7155	0.0058	8092.8767	5609.5547	2604.0	3270.0	0.7963	2608.0	0.7976	1661.0	1666.0	2026.0	0.8223	0.8198	938.0	938.0	1231.0	0.7620	0.7620
0.0	32.0	1728	1.7118	0.0058	8075.5841	5597.5684	2605.0	3270.0	0.7966	2610.0	0.7982	1663.0	1667.0	2026.0	0.8228	0.8208	938.0	938.0	1231.0	0.7620	0.7620
0.0	33.0	1782	1.7150	0.0058	8090.7632	5608.0897	2605.0	3270.0	0.7966	2609.0	0.7979	1663.0	1668.0	2026.0	0.8233	0.8208	937.0	937.0	1231.0	0.7612	0.7612
0.0	34.0	1836	1.7158	0.0058	8094.6523	5610.7854	2605.0	3270.0	0.7966	2609.0	0.7979	1663.0	1668.0	2026.0	0.8233	0.8208	937.0	937.0	1231.0	0.7612	0.7612
0.0	35.0	1890	1.7144	0.0058	8087.7042	5605.9694	2606.0	3270.0	0.7969	2610.0	0.7982	1664.0	1669.0	2026.0	0.8238	0.8213	937.0	937.0	1231.0	0.7612	0.7612
0.0	36.0	1944	1.7155	0.0058	8093.0727	5609.6905	2602.0	3270.0	0.7957	2607.0	0.7972	1660.0	1664.0	2026.0	0.8213	0.8193	938.0	938.0	1231.0	0.7620	0.7620
0.0	37.0	1998	1.7157	0.0058	8094.0158	5610.3442	2604.0	3270.0	0.7963	2608.0	0.7976	1662.0	1667.0	2026.0	0.8228	0.8203	937.0	937.0	1231.0	0.7612	0.7612

Framework versions

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