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: 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 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	0.0057	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
1.5824	1.0	2	1.5290	0.0057	659.5595	457.1718	82.0	299.0	0.2742	82.0	0.2742	0.0	0.0	64.0	0.0	0.0	63.0	63.0	73.0	0.8630	0.8630	14.0	14.0	78.0	0.1795	0.1795	5.0	5.0	83.0	0.0602	0.0602	1.0
1.391	2.0	4	1.8724	0.0057	807.6951	559.8515	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
1.3398	3.0	6	1.4056	0.0057	606.3214	420.2699	80.0	299.0	0.2676	10.0	0.0334	0.0	3.0	64.0	0.0469	0.0	7.0	56.0	73.0	0.7671	0.0959	0.0	0.0	78.0	0.0	0.0	3.0	21.0	83.0	0.2530	0.0361	1.0
1.1747	4.0	8	1.6453	0.0057	709.7387	491.9534	90.0	299.0	0.3010	73.0	0.2441	40.0	53.0	64.0	0.8281	0.625	13.0	13.0	73.0	0.1781	0.1781	4.0	5.0	78.0	0.0641	0.0513	16.0	19.0	83.0	0.2289	0.1928	1.0
0.8016	5.0	10	1.5549	0.0057	670.7152	464.9043	115.0	299.0	0.3846	100.0	0.3344	11.0	16.0	64.0	0.25	0.1719	32.0	35.0	73.0	0.4795	0.4384	35.0	37.0	78.0	0.4744	0.4487	22.0	27.0	83.0	0.3253	0.2651	1.0
0.2902	6.0	12	2.4866	0.0057	1072.6400	743.4974	113.0	299.0	0.3779	90.0	0.3010	21.0	34.0	64.0	0.5312	0.3281	24.0	24.0	73.0	0.3288	0.3288	15.0	22.0	78.0	0.2821	0.1923	30.0	33.0	83.0	0.3976	0.3614	1.0
0.0689	7.0	14	2.9274	0.0057	1262.7762	875.2898	110.0	299.0	0.3679	65.0	0.2174	7.0	26.0	64.0	0.4062	0.1094	23.0	36.0	73.0	0.4932	0.3151	12.0	21.0	78.0	0.2692	0.1538	23.0	27.0	83.0	0.3253	0.2771	1.0
0.0039	8.0	16	4.4436	0.0057	1916.8228	1328.6403	113.0	299.0	0.3779	97.0	0.3244	17.0	23.0	64.0	0.3594	0.2656	30.0	33.0	73.0	0.4521	0.4110	23.0	28.0	78.0	0.3590	0.2949	27.0	29.0	83.0	0.3494	0.3253	1.0
0.0001	9.0	18	5.7154	0.0057	2465.4352	1708.9095	115.0	299.0	0.3846	110.0	0.3679	23.0	25.0	64.0	0.3906	0.3594	32.0	32.0	73.0	0.4384	0.4384	23.0	25.0	78.0	0.3205	0.2949	32.0	33.0	83.0	0.3976	0.3855	1.0
0.0	10.0	20	6.5504	0.0057	2825.6372	1958.5825	117.0	299.0	0.3913	113.0	0.3779	29.0	29.0	64.0	0.4531	0.4531	29.0	31.0	73.0	0.4247	0.3973	21.0	22.0	78.0	0.2821	0.2692	34.0	35.0	83.0	0.4217	0.4096	1.0
0.0	11.0	22	7.1073	0.0057	3065.8467	2125.0830	116.0	299.0	0.3880	111.0	0.3712	29.0	29.0	64.0	0.4531	0.4531	26.0	30.0	73.0	0.4110	0.3562	22.0	22.0	78.0	0.2821	0.2821	34.0	35.0	83.0	0.4217	0.4096	1.0
0.0343	12.0	24	7.5292	0.0057	3247.8469	2251.2359	113.0	299.0	0.3779	106.0	0.3545	29.0	29.0	64.0	0.4531	0.4531	24.0	30.0	73.0	0.4110	0.3288	21.0	21.0	78.0	0.2692	0.2692	32.0	33.0	83.0	0.3976	0.3855	1.0
0.0	13.0	26	7.8418	0.0057	3382.6720	2344.6896	112.0	299.0	0.3746	105.0	0.3512	27.0	27.0	64.0	0.4219	0.4219	23.0	29.0	73.0	0.3973	0.3151	23.0	23.0	78.0	0.2949	0.2949	32.0	33.0	83.0	0.3976	0.3855	1.0
0.0	14.0	28	7.9378	0.0057	3424.1167	2373.4169	109.0	299.0	0.3645	102.0	0.3411	26.0	26.0	64.0	0.4062	0.4062	23.0	29.0	73.0	0.3973	0.3151	23.0	24.0	78.0	0.3077	0.2949	30.0	30.0	83.0	0.3614	0.3614	1.0
0.0	15.0	30	8.1470	0.0057	3514.3228	2435.9429	109.0	299.0	0.3645	100.0	0.3344	25.0	26.0	64.0	0.4062	0.3906	22.0	29.0	73.0	0.3973	0.3014	23.0	24.0	78.0	0.3077	0.2949	30.0	30.0	83.0	0.3614	0.3614	1.0
0.0	16.0	32	8.2369	0.0057	3553.1326	2462.8438	108.0	299.0	0.3612	98.0	0.3278	25.0	25.0	64.0	0.3906	0.3906	21.0	29.0	73.0	0.3973	0.2877	23.0	25.0	78.0	0.3205	0.2949	29.0	29.0	83.0	0.3494	0.3494	1.0
0.0	17.0	34	8.3693	0.0057	3610.2461	2502.4319	105.0	299.0	0.3512	96.0	0.3211	23.0	24.0	64.0	0.375	0.3594	22.0	29.0	73.0	0.3973	0.3014	24.0	25.0	78.0	0.3205	0.3077	27.0	27.0	83.0	0.3253	0.3253	1.0
0.0	18.0	36	8.3376	0.0057	3596.5378	2492.9301	104.0	299.0	0.3478	94.0	0.3144	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	27.0	27.0	83.0	0.3253	0.3253	1.0
0.0	19.0	38	8.3801	0.0057	3614.8683	2505.6357	105.0	299.0	0.3512	95.0	0.3177	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	28.0	28.0	83.0	0.3373	0.3373	1.0
0.0	20.0	40	8.4213	0.0057	3632.6567	2517.9658	104.0	299.0	0.3478	94.0	0.3144	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	27.0	27.0	83.0	0.3253	0.3253	1.0
0.0	21.0	42	8.3955	0.0057	3621.5497	2510.2670	104.0	299.0	0.3478	94.0	0.3144	24.0	25.0	64.0	0.3906	0.375	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	22.0	44	8.4237	0.0057	3633.7116	2518.6970	105.0	299.0	0.3512	95.0	0.3177	24.0	25.0	64.0	0.3906	0.375	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	27.0	27.0	83.0	0.3253	0.3253	1.0
0.0	23.0	46	8.4279	0.0057	3635.5270	2519.9553	104.0	299.0	0.3478	94.0	0.3144	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	27.0	27.0	83.0	0.3253	0.3253	1.0
0.0	24.0	48	8.4049	0.0057	3625.5675	2513.0519	102.0	299.0	0.3411	92.0	0.3077	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	25.0	25.0	83.0	0.3012	0.3012	1.0
0.0	25.0	50	8.4318	0.0057	3637.2027	2521.1168	103.0	299.0	0.3445	93.0	0.3110	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	26.0	52	8.4607	0.0057	3649.6682	2529.7572	104.0	299.0	0.3478	95.0	0.3177	24.0	25.0	64.0	0.3906	0.375	22.0	28.0	73.0	0.3836	0.3014	23.0	25.0	78.0	0.3205	0.2949	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	27.0	54	8.4487	0.0057	3644.4992	2526.1744	104.0	299.0	0.3478	94.0	0.3144	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	27.0	27.0	83.0	0.3253	0.3253	1.0
0.0	28.0	56	8.4672	0.0057	3652.4796	2531.7059	103.0	299.0	0.3445	93.0	0.3110	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	29.0	58	8.4649	0.0057	3651.4547	2530.9955	104.0	299.0	0.3478	93.0	0.3110	24.0	25.0	64.0	0.3906	0.375	21.0	29.0	73.0	0.3973	0.2877	23.0	25.0	78.0	0.3205	0.2949	25.0	25.0	83.0	0.3012	0.3012	1.0
0.0	30.0	60	8.4701	0.0057	3653.6933	2532.5472	104.0	299.0	0.3478	94.0	0.3144	24.0	25.0	64.0	0.3906	0.375	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	31.0	62	8.4412	0.0057	3641.2534	2523.9246	105.0	299.0	0.3512	94.0	0.3144	23.0	24.0	64.0	0.375	0.3594	21.0	29.0	73.0	0.3973	0.2877	23.0	25.0	78.0	0.3205	0.2949	27.0	27.0	83.0	0.3253	0.3253	1.0
0.0	32.0	64	8.4430	0.0057	3642.0297	2524.4626	102.0	299.0	0.3411	92.0	0.3077	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	22.0	24.0	78.0	0.3077	0.2821	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	33.0	66	8.4289	0.0057	3635.9534	2520.2509	104.0	299.0	0.3478	94.0	0.3144	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	27.0	27.0	83.0	0.3253	0.3253	1.0
0.0	34.0	68	8.4415	0.0057	3641.3606	2523.9988	103.0	299.0	0.3445	93.0	0.3110	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	35.0	70	8.4527	0.0057	3646.1986	2527.3523	104.0	299.0	0.3478	94.0	0.3144	24.0	25.0	64.0	0.3906	0.375	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	36.0	72	8.4533	0.0057	3646.4774	2527.5455	104.0	299.0	0.3478	94.0	0.3144	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	27.0	27.0	83.0	0.3253	0.3253	1.0
0.0	37.0	74	8.4248	0.0057	3634.1888	2519.0277	105.0	299.0	0.3512	94.0	0.3144	24.0	25.0	64.0	0.3906	0.375	21.0	28.0	73.0	0.3836	0.2877	23.0	26.0	78.0	0.3333	0.2949	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	38.0	76	8.4667	0.0057	3652.2541	2531.5496	103.0	299.0	0.3445	94.0	0.3144	24.0	25.0	64.0	0.3906	0.375	22.0	28.0	73.0	0.3836	0.3014	22.0	24.0	78.0	0.3077	0.2821	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	39.0	78	8.4449	0.0057	3642.8541	2525.0341	103.0	299.0	0.3445	93.0	0.3110	23.0	24.0	64.0	0.375	0.3594	21.0	28.0	73.0	0.3836	0.2877	23.0	25.0	78.0	0.3205	0.2949	26.0	26.0	83.0	0.3133	0.3133	1.0
0.0	40.0	80	8.4700	0.0057	3653.6768	2532.5358	102.0	299.0	0.3411	93.0	0.3110	23.0	24.0	64.0	0.375	0.3594	22.0	28.0	73.0	0.3836	0.3014	23.0	25.0	78.0	0.3205	0.2949	25.0	25.0	83.0	0.3012	0.3012	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-ham6wkrg

ARC-Challenge_Llama-3.2-1B-ham6wkrg

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

donoway/
ARC-Challenge_Llama-3.2-1B-ham6wkrg