BoolQ_Llama-3.2-1B-8f4o6kcm

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: 1.5793
• Model Preparation Time: 0.0057
• Mdl: 7450.5715
• Accumulated Loss: 5164.3426
• Correct Preds: 2634.0
• Total Preds: 3270.0
• Accuracy: 0.8055
• Correct Gen Preds: 2638.0
• Gen Accuracy: 0.8067
• Correct Gen Preds 9642: 1699.0
• Correct Preds 9642: 1701.0
• Total Labels 9642: 2026.0
• Accuracy 9642: 0.8396
• Gen Accuracy 9642: 0.8386
• Correct Gen Preds 2822: 930.0
• Correct Preds 2822: 933.0
• Total Labels 2822: 1231.0
• Accuracy 2822: 0.7579
• Gen Accuracy 2822: 0.7555

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	0.0057	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
0.4667	1.0	69	0.6104	0.0057	2879.4424	1995.8774	2384.0	3270.0	0.7291	2390.0	0.7309	1351.0	1351.0	2026.0	0.6668	0.6668	1031.0	1033.0	1231.0	0.8392	0.8375
0.4652	2.0	138	0.5854	0.0057	2761.8042	1914.3368	2618.0	3270.0	0.8006	2476.0	0.7572	1601.0	1693.0	2026.0	0.8356	0.7902	869.0	925.0	1231.0	0.7514	0.7059
0.2361	3.0	207	0.9383	0.0057	4426.4291	3068.1669	2615.0	3270.0	0.7997	2598.0	0.7945	1691.0	1708.0	2026.0	0.8430	0.8346	900.0	907.0	1231.0	0.7368	0.7311
0.0138	4.0	276	1.2278	0.0057	5792.2561	4014.8860	2550.0	3270.0	0.7798	2530.0	0.7737	1541.0	1562.0	2026.0	0.7710	0.7606	981.0	988.0	1231.0	0.8026	0.7969
0.0	5.0	345	1.6244	0.0057	7663.1836	5311.7141	2604.0	3270.0	0.7963	2607.0	0.7972	1634.0	1636.0	2026.0	0.8075	0.8065	965.0	968.0	1231.0	0.7864	0.7839
0.0001	6.0	414	1.3741	0.0057	6482.3648	4493.2329	2627.0	3270.0	0.8034	2631.0	0.8046	1700.0	1702.0	2026.0	0.8401	0.8391	923.0	925.0	1231.0	0.7514	0.7498
0.0	7.0	483	1.4617	0.0057	6895.6302	4779.6866	2630.0	3270.0	0.8043	2634.0	0.8055	1701.0	1703.0	2026.0	0.8406	0.8396	924.0	927.0	1231.0	0.7530	0.7506
0.0	8.0	552	1.4956	0.0057	7055.6245	4890.5862	2625.0	3270.0	0.8028	2629.0	0.8040	1695.0	1697.0	2026.0	0.8376	0.8366	925.0	928.0	1231.0	0.7539	0.7514
0.0	9.0	621	1.5171	0.0057	7157.2276	4961.0122	2625.0	3270.0	0.8028	2629.0	0.8040	1698.0	1700.0	2026.0	0.8391	0.8381	922.0	925.0	1231.0	0.7514	0.7490
0.0001	10.0	690	1.5322	0.0057	7228.4800	5010.4005	2628.0	3270.0	0.8037	2632.0	0.8049	1698.0	1700.0	2026.0	0.8391	0.8381	925.0	928.0	1231.0	0.7539	0.7514
0.0	11.0	759	1.5461	0.0057	7293.7816	5055.6641	2629.0	3270.0	0.8040	2633.0	0.8052	1696.0	1698.0	2026.0	0.8381	0.8371	928.0	931.0	1231.0	0.7563	0.7539
0.0	12.0	828	1.5571	0.0057	7345.8001	5091.7207	2630.0	3270.0	0.8043	2634.0	0.8055	1698.0	1700.0	2026.0	0.8391	0.8381	927.0	930.0	1231.0	0.7555	0.7530
0.0	13.0	897	1.5696	0.0057	7404.5688	5132.4560	2628.0	3270.0	0.8037	2633.0	0.8052	1695.0	1697.0	2026.0	0.8376	0.8366	929.0	931.0	1231.0	0.7563	0.7547
0.0	14.0	966	1.5735	0.0057	7423.3806	5145.4953	2629.0	3270.0	0.8040	2633.0	0.8052	1692.0	1694.0	2026.0	0.8361	0.8351	932.0	935.0	1231.0	0.7595	0.7571
0.0	15.0	1035	1.5793	0.0057	7450.5715	5164.3426	2634.0	3270.0	0.8055	2638.0	0.8067	1699.0	1701.0	2026.0	0.8396	0.8386	930.0	933.0	1231.0	0.7579	0.7555
0.0	16.0	1104	1.5878	0.0057	7490.8020	5192.2283	2629.0	3270.0	0.8040	2633.0	0.8052	1694.0	1696.0	2026.0	0.8371	0.8361	930.0	933.0	1231.0	0.7579	0.7555
0.0	17.0	1173	1.5863	0.0057	7483.6533	5187.2732	2629.0	3270.0	0.8040	2633.0	0.8052	1696.0	1698.0	2026.0	0.8381	0.8371	928.0	931.0	1231.0	0.7563	0.7539
0.0	18.0	1242	1.5880	0.0057	7491.6557	5192.8201	2629.0	3270.0	0.8040	2634.0	0.8055	1693.0	1695.0	2026.0	0.8366	0.8356	932.0	934.0	1231.0	0.7587	0.7571
0.0	19.0	1311	1.5920	0.0057	7510.3381	5205.7697	2628.0	3270.0	0.8037	2633.0	0.8052	1693.0	1695.0	2026.0	0.8366	0.8356	931.0	933.0	1231.0	0.7579	0.7563
0.0	20.0	1380	1.5951	0.0057	7524.8328	5215.8166	2627.0	3270.0	0.8034	2631.0	0.8046	1691.0	1693.0	2026.0	0.8356	0.8346	931.0	934.0	1231.0	0.7587	0.7563
0.0	21.0	1449	1.5937	0.0057	7518.3160	5211.2995	2623.0	3270.0	0.8021	2628.0	0.8037	1689.0	1691.0	2026.0	0.8346	0.8337	930.0	932.0	1231.0	0.7571	0.7555
0.0	22.0	1518	1.5941	0.0057	7520.5677	5212.8603	2626.0	3270.0	0.8031	2631.0	0.8046	1693.0	1695.0	2026.0	0.8366	0.8356	929.0	931.0	1231.0	0.7563	0.7547
0.4705	23.0	1587	1.5944	0.0057	7521.8050	5213.7179	2629.0	3270.0	0.8040	2633.0	0.8052	1693.0	1695.0	2026.0	0.8366	0.8356	931.0	934.0	1231.0	0.7587	0.7563
0.0	24.0	1656	1.5942	0.0057	7520.9457	5213.1223	2626.0	3270.0	0.8031	2631.0	0.8046	1691.0	1693.0	2026.0	0.8356	0.8346	931.0	933.0	1231.0	0.7579	0.7563
0.0	25.0	1725	1.5932	0.0057	7516.1335	5209.7867	2628.0	3270.0	0.8037	2633.0	0.8052	1692.0	1694.0	2026.0	0.8361	0.8351	932.0	934.0	1231.0	0.7587	0.7571
0.0	26.0	1794	1.5939	0.0057	7519.3793	5212.0365	2631.0	3270.0	0.8046	2635.0	0.8058	1695.0	1697.0	2026.0	0.8376	0.8366	931.0	934.0	1231.0	0.7587	0.7563
0.0	27.0	1863	1.5943	0.0057	7521.3797	5213.4231	2631.0	3270.0	0.8046	2636.0	0.8061	1694.0	1696.0	2026.0	0.8371	0.8361	933.0	935.0	1231.0	0.7595	0.7579
0.0	28.0	1932	1.5947	0.0057	7522.9538	5214.5142	2631.0	3270.0	0.8046	2636.0	0.8061	1693.0	1695.0	2026.0	0.8366	0.8356	934.0	936.0	1231.0	0.7604	0.7587
0.0	29.0	2001	1.5970	0.0057	7534.0599	5222.2124	2628.0	3270.0	0.8037	2633.0	0.8052	1694.0	1696.0	2026.0	0.8371	0.8361	930.0	932.0	1231.0	0.7571	0.7555
0.0	30.0	2070	1.5937	0.0057	7518.6664	5211.5424	2631.0	3270.0	0.8046	2636.0	0.8061	1696.0	1698.0	2026.0	0.8381	0.8371	931.0	933.0	1231.0	0.7579	0.7563
0.0	31.0	2139	1.5975	0.0057	7536.3698	5223.8135	2632.0	3270.0	0.8049	2637.0	0.8064	1693.0	1695.0	2026.0	0.8366	0.8356	935.0	937.0	1231.0	0.7612	0.7595
0.0	32.0	2208	1.5958	0.0057	7528.2450	5218.1818	2626.0	3270.0	0.8031	2631.0	0.8046	1692.0	1694.0	2026.0	0.8361	0.8351	930.0	932.0	1231.0	0.7571	0.7555
0.0	33.0	2277	1.5946	0.0057	7522.6503	5214.3039	2630.0	3270.0	0.8043	2635.0	0.8058	1693.0	1695.0	2026.0	0.8366	0.8356	933.0	935.0	1231.0	0.7595	0.7579
0.0	34.0	2346	1.5958	0.0057	7528.1556	5218.1199	2630.0	3270.0	0.8043	2635.0	0.8058	1691.0	1693.0	2026.0	0.8356	0.8346	935.0	937.0	1231.0	0.7612	0.7595
0.0	35.0	2415	1.5955	0.0057	7527.0160	5217.3299	2630.0	3270.0	0.8043	2634.0	0.8055	1694.0	1696.0	2026.0	0.8371	0.8361	931.0	934.0	1231.0	0.7587	0.7563
0.0	36.0	2484	1.5979	0.0057	7538.4257	5225.2385	2630.0	3270.0	0.8043	2635.0	0.8058	1693.0	1695.0	2026.0	0.8366	0.8356	933.0	935.0	1231.0	0.7595	0.7579
0.0	37.0	2553	1.5989	0.0057	7543.1657	5228.5240	2626.0	3270.0	0.8031	2631.0	0.8046	1692.0	1694.0	2026.0	0.8361	0.8351	930.0	932.0	1231.0	0.7571	0.7555
0.0	38.0	2622	1.5947	0.0057	7523.0421	5214.5755	2629.0	3270.0	0.8040	2634.0	0.8055	1693.0	1695.0	2026.0	0.8366	0.8356	932.0	934.0	1231.0	0.7587	0.7571
0.0	39.0	2691	1.5952	0.0057	7525.4233	5216.2259	2627.0	3270.0	0.8034	2632.0	0.8049	1692.0	1694.0	2026.0	0.8361	0.8351	931.0	933.0	1231.0	0.7579	0.7563
0.0	40.0	2760	1.5979	0.0057	7538.3492	5225.1855	2625.0	3270.0	0.8028	2629.0	0.8040	1690.0	1692.0	2026.0	0.8351	0.8342	930.0	933.0	1231.0	0.7579	0.7555
0.0	41.0	2829	1.5955	0.0057	7526.7286	5217.1307	2631.0	3270.0	0.8046	2636.0	0.8061	1692.0	1694.0	2026.0	0.8361	0.8351	935.0	937.0	1231.0	0.7612	0.7595
0.0	42.0	2898	1.5972	0.0057	7535.1989	5223.0019	2631.0	3270.0	0.8046	2635.0	0.8058	1696.0	1698.0	2026.0	0.8381	0.8371	930.0	933.0	1231.0	0.7579	0.7555
0.0	43.0	2967	1.5954	0.0057	7526.2516	5216.8001	2629.0	3270.0	0.8040	2634.0	0.8055	1689.0	1691.0	2026.0	0.8346	0.8337	936.0	938.0	1231.0	0.7620	0.7604
0.0	44.0	3036	1.5961	0.0057	7530.0068	5219.4030	2629.0	3270.0	0.8040	2634.0	0.8055	1691.0	1693.0	2026.0	0.8356	0.8346	934.0	936.0	1231.0	0.7604	0.7587
0.0	45.0	3105	1.5990	0.0057	7543.2270	5228.5665	2627.0	3270.0	0.8034	2632.0	0.8049	1691.0	1693.0	2026.0	0.8356	0.8346	932.0	934.0	1231.0	0.7587	0.7571

Framework versions

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