learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 112
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 32	Correct Preds 32	Total Labels 32	Accuracy 32	Gen Accuracy 32	Correct Gen Preds 33	Correct Preds 33	Total Labels 33	Accuracy 33	Gen Accuracy 33	Correct Gen Preds 34	Correct Preds 34	Total Labels 34	Accuracy 34	Gen Accuracy 34	Correct Gen Preds 35	Correct Preds 35	Total Labels 35	Accuracy 35	Gen Accuracy 35	Total Labels 36
No log	0	0	1.6389	0.0058	706.9523	490.0220	66.0	299.0	0.2207	66.0	0.2207	62.0	62.0	64.0	0.9688	0.9688	0.0	0.0	73.0	0.0	0.0	4.0	4.0	78.0	0.0513	0.0513	0.0	0.0	83.0	0.0	0.0	1.0
1.6217	1.0	2	3.0846	0.0058	1330.6119	922.3099	73.0	299.0	0.2441	73.0	0.2441	0.0	0.0	64.0	0.0	0.0	73.0	73.0	73.0	1.0	1.0	0.0	0.0	78.0	0.0	0.0	0.0	0.0	83.0	0.0	0.0	1.0
1.8042	2.0	4	1.6582	0.0058	715.3105	495.8155	64.0	299.0	0.2140	64.0	0.2140	64.0	64.0	64.0	1.0	1.0	0.0	0.0	73.0	0.0	0.0	0.0	0.0	78.0	0.0	0.0	0.0	0.0	83.0	0.0	0.0	1.0
0.9831	3.0	6	1.9878	0.0058	857.4570	594.3439	62.0	299.0	0.2074	31.0	0.1037	31.0	58.0	64.0	0.9062	0.4844	0.0	2.0	73.0	0.0274	0.0	0.0	1.0	78.0	0.0128	0.0	0.0	1.0	83.0	0.0120	0.0	1.0
1.1227	4.0	8	1.5926	0.0058	687.0006	476.1926	66.0	299.0	0.2207	35.0	0.1171	33.0	59.0	64.0	0.9219	0.5156	0.0	0.0	73.0	0.0	0.0	2.0	7.0	78.0	0.0897	0.0256	0.0	0.0	83.0	0.0	0.0	1.0
1.5365	5.0	10	1.4332	0.0058	618.2170	428.5154	80.0	299.0	0.2676	78.0	0.2609	58.0	59.0	64.0	0.9219	0.9062	14.0	14.0	73.0	0.1918	0.1918	4.0	5.0	78.0	0.0641	0.0513	2.0	2.0	83.0	0.0241	0.0241	1.0
1.3437	6.0	12	1.4601	0.0058	629.8535	436.5812	81.0	299.0	0.2709	27.0	0.0903	11.0	27.0	64.0	0.4219	0.1719	10.0	26.0	73.0	0.3562	0.1370	5.0	16.0	78.0	0.2051	0.0641	1.0	12.0	83.0	0.1446	0.0120	1.0
0.7483	7.0	14	1.7795	0.0058	767.6192	532.0731	76.0	299.0	0.2542	26.0	0.0870	20.0	53.0	64.0	0.8281	0.3125	2.0	11.0	73.0	0.1507	0.0274	3.0	7.0	78.0	0.0897	0.0385	1.0	5.0	83.0	0.0602	0.0120	1.0
0.4273	8.0	16	1.7187	0.0058	741.3764	513.8830	92.0	299.0	0.3077	12.0	0.0401	2.0	31.0	64.0	0.4844	0.0312	4.0	25.0	73.0	0.3425	0.0548	5.0	19.0	78.0	0.2436	0.0641	1.0	17.0	83.0	0.2048	0.0120	1.0
0.0267	9.0	18	2.3781	0.0058	1025.8224	711.0459	94.0	299.0	0.3144	8.0	0.0268	0.0	22.0	64.0	0.3438	0.0	0.0	31.0	73.0	0.4247	0.0	5.0	22.0	78.0	0.2821	0.0641	3.0	19.0	83.0	0.2289	0.0361	1.0
0.0121	10.0	20	2.6549	0.0058	1145.2173	793.8041	89.0	299.0	0.2977	11.0	0.0368	0.0	26.0	64.0	0.4062	0.0	3.0	31.0	73.0	0.4247	0.0411	4.0	17.0	78.0	0.2179	0.0513	4.0	15.0	83.0	0.1807	0.0482	1.0
0.0338	11.0	22	3.4477	0.0058	1487.2357	1030.8732	91.0	299.0	0.3043	10.0	0.0334	1.0	35.0	64.0	0.5469	0.0156	1.0	26.0	73.0	0.3562	0.0137	3.0	14.0	78.0	0.1795	0.0385	5.0	16.0	83.0	0.1928	0.0602	1.0
0.0002	12.0	24	3.9812	0.0058	1717.3427	1190.3712	87.0	299.0	0.2910	10.0	0.0334	1.0	30.0	64.0	0.4688	0.0156	1.0	26.0	73.0	0.3562	0.0137	2.0	14.0	78.0	0.1795	0.0256	6.0	17.0	83.0	0.2048	0.0723	1.0
0.0001	13.0	26	4.3205	0.0058	1863.6984	1291.8173	86.0	299.0	0.2876	13.0	0.0435	2.0	30.0	64.0	0.4688	0.0312	3.0	26.0	73.0	0.3562	0.0411	3.0	16.0	78.0	0.2051	0.0385	5.0	14.0	83.0	0.1687	0.0602	1.0
0.0	14.0	28	4.5366	0.0058	1956.9398	1356.4473	89.0	299.0	0.2977	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	3.0	26.0	73.0	0.3562	0.0411	2.0	16.0	78.0	0.2051	0.0256	5.0	17.0	83.0	0.2048	0.0602	1.0
0.0	15.0	30	4.6811	0.0058	2019.2794	1399.6578	89.0	299.0	0.2977	14.0	0.0468	3.0	29.0	64.0	0.4531	0.0469	4.0	24.0	73.0	0.3288	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	16.0	32	4.7816	0.0058	2062.6183	1429.6980	88.0	299.0	0.2943	12.0	0.0401	3.0	30.0	64.0	0.4688	0.0469	3.0	22.0	73.0	0.3014	0.0411	2.0	18.0	78.0	0.2308	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	17.0	34	4.8408	0.0058	2088.1473	1447.3934	89.0	299.0	0.2977	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	22.0	73.0	0.3014	0.0548	2.0	19.0	78.0	0.2436	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	18.0	36	4.8937	0.0058	2110.9718	1463.2141	87.0	299.0	0.2910	13.0	0.0435	3.0	29.0	64.0	0.4531	0.0469	4.0	22.0	73.0	0.3014	0.0548	2.0	18.0	78.0	0.2308	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	19.0	38	4.9153	0.0058	2120.2857	1469.6701	88.0	299.0	0.2943	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	20.0	40	4.9474	0.0058	2134.1312	1479.2670	88.0	299.0	0.2943	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	21.0	42	4.9635	0.0058	2141.0853	1484.0872	89.0	299.0	0.2977	13.0	0.0435	3.0	31.0	64.0	0.4844	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	22.0	44	4.9713	0.0058	2144.4693	1486.4329	88.0	299.0	0.2943	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	22.0	73.0	0.3014	0.0548	2.0	18.0	78.0	0.2308	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	23.0	46	4.9759	0.0058	2146.4259	1487.7890	88.0	299.0	0.2943	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	24.0	48	4.9796	0.0058	2148.0201	1488.8940	87.0	299.0	0.2910	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	25.0	50	4.9919	0.0058	2153.3399	1492.5815	88.0	299.0	0.2943	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	26.0	52	4.9893	0.0058	2152.2123	1491.7999	88.0	299.0	0.2943	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	27.0	54	4.9926	0.0058	2153.6267	1492.7803	89.0	299.0	0.2977	14.0	0.0468	3.0	31.0	64.0	0.4844	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	28.0	56	4.9908	0.0058	2152.8635	1492.2513	88.0	299.0	0.2943	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	29.0	58	4.9906	0.0058	2152.7687	1492.1856	86.0	299.0	0.2876	13.0	0.0435	3.0	29.0	64.0	0.4531	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	30.0	60	4.9916	0.0058	2153.2147	1492.4947	89.0	299.0	0.2977	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	5.0	19.0	83.0	0.2289	0.0602	1.0
0.0	31.0	62	4.9890	0.0058	2152.0878	1491.7136	89.0	299.0	0.2977	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	22.0	73.0	0.3014	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	32.0	64	4.9952	0.0058	2154.7667	1493.5705	87.0	299.0	0.2910	13.0	0.0435	3.0	31.0	64.0	0.4844	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	18.0	78.0	0.2308	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	33.0	66	4.9926	0.0058	2153.6256	1492.7795	89.0	299.0	0.2977	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	19.0	83.0	0.2289	0.0482	1.0
0.0	34.0	68	4.9868	0.0058	2151.1314	1491.0507	87.0	299.0	0.2910	14.0	0.0468	3.0	29.0	64.0	0.4531	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	19.0	78.0	0.2436	0.0256	5.0	19.0	83.0	0.2289	0.0602	1.0
0.0	35.0	70	4.9850	0.0058	2150.3622	1490.5175	87.0	299.0	0.2910	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	36.0	72	5.0066	0.0058	2159.6634	1496.9646	87.0	299.0	0.2910	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	37.0	74	5.0066	0.0058	2159.6814	1496.9771	87.0	299.0	0.2910	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	38.0	76	5.0029	0.0058	2158.1010	1495.8816	88.0	299.0	0.2943	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	19.0	83.0	0.2289	0.0482	1.0
0.0	39.0	78	4.9957	0.0058	2154.9806	1493.7187	89.0	299.0	0.2977	14.0	0.0468	3.0	31.0	64.0	0.4844	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	19.0	78.0	0.2436	0.0256	5.0	19.0	83.0	0.2289	0.0602	1.0
0.0	40.0	80	4.9985	0.0058	2156.1785	1494.5490	88.0	299.0	0.2943	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	22.0	73.0	0.3014	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	41.0	82	5.0046	0.0058	2158.8302	1496.3871	86.0	299.0	0.2876	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	42.0	84	5.0020	0.0058	2157.6753	1495.5866	89.0	299.0	0.2977	13.0	0.0435	3.0	31.0	64.0	0.4844	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	43.0	86	5.0015	0.0058	2157.4668	1495.4420	88.0	299.0	0.2943	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	19.0	83.0	0.2289	0.0482	1.0
0.0	44.0	88	4.9949	0.0058	2154.6395	1493.4823	89.0	299.0	0.2977	14.0	0.0468	3.0	31.0	64.0	0.4844	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	19.0	78.0	0.2436	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	45.0	90	5.0054	0.0058	2159.1554	1496.6125	86.0	299.0	0.2876	14.0	0.0468	3.0	29.0	64.0	0.4531	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	46.0	92	5.0031	0.0058	2158.1526	1495.9174	86.0	299.0	0.2876	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	19.0	73.0	0.2603	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	47.0	94	5.0044	0.0058	2158.7442	1496.3275	88.0	299.0	0.2943	14.0	0.0468	3.0	31.0	64.0	0.4844	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	48.0	96	5.0045	0.0058	2158.7689	1496.3445	86.0	299.0	0.2876	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	49.0	98	4.9983	0.0058	2156.0793	1494.4803	88.0	299.0	0.2943	13.0	0.0435	3.0	31.0	64.0	0.4844	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	18.0	78.0	0.2308	0.0256	4.0	19.0	83.0	0.2289	0.0482	1.0
0.0	50.0	100	5.0049	0.0058	2158.9576	1496.4754	86.0	299.0	0.2876	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	18.0	78.0	0.2308	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	51.0	102	5.0059	0.0058	2159.3619	1496.7556	87.0	299.0	0.2910	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	52.0	104	5.0100	0.0058	2161.1238	1497.9769	85.0	299.0	0.2843	14.0	0.0468	3.0	29.0	64.0	0.4531	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	53.0	106	5.0030	0.0058	2158.1205	1495.8951	87.0	299.0	0.2910	14.0	0.0468	3.0	31.0	64.0	0.4844	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	54.0	108	5.0083	0.0058	2160.4072	1497.4801	86.0	299.0	0.2876	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	19.0	73.0	0.2603	0.0548	2.0	19.0	78.0	0.2436	0.0256	5.0	18.0	83.0	0.2169	0.0602	1.0
0.0	55.0	110	4.9989	0.0058	2156.3668	1494.6796	88.0	299.0	0.2943	14.0	0.0468	3.0	30.0	64.0	0.4688	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	5.0	19.0	83.0	0.2289	0.0602	1.0
0.0	56.0	112	4.9910	0.0058	2152.9416	1492.3054	88.0	299.0	0.2943	13.0	0.0435	3.0	31.0	64.0	0.4844	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	57.0	114	5.0090	0.0058	2160.7282	1497.7027	86.0	299.0	0.2876	13.0	0.0435	3.0	29.0	64.0	0.4531	0.0469	4.0	21.0	73.0	0.2877	0.0548	2.0	18.0	78.0	0.2308	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	58.0	116	4.9993	0.0058	2156.5316	1494.7938	87.0	299.0	0.2910	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	19.0	78.0	0.2436	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0
0.0	59.0	118	5.0173	0.0058	2164.3103	1500.1856	86.0	299.0	0.2876	13.0	0.0435	3.0	30.0	64.0	0.4688	0.0469	4.0	20.0	73.0	0.2740	0.0548	2.0	18.0	78.0	0.2308	0.0256	4.0	18.0	83.0	0.2169	0.0482	1.0

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

donoway/ARC-Challenge_Llama-3.2-1B-kaj9v3a8

ARC-Challenge_Llama-3.2-1B-kaj9v3a8

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

donoway/
ARC-Challenge_Llama-3.2-1B-kaj9v3a8