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
No log	0	0	1.5354	0.0028	1262.6022	875.1692	172.0	570.0	0.3018	170.0	0.2982	154.0	154.0	158.0	0.9747	0.9747	0.0	0.0	152.0	0.0	0.0	15.0	17.0	142.0	0.1197	0.1056	1.0	1.0	118.0	0.0085	0.0085
1.1645	1.0	8	1.2427	0.0028	1021.9553	708.3654	358.0	570.0	0.6281	354.0	0.6211	104.0	106.0	158.0	0.6709	0.6582	63.0	64.0	152.0	0.4211	0.4145	111.0	111.0	142.0	0.7817	0.7817	76.0	77.0	118.0	0.6525	0.6441
0.5365	2.0	16	0.9998	0.0028	822.1312	569.8579	398.0	570.0	0.6982	398.0	0.6982	112.0	112.0	158.0	0.7089	0.7089	109.0	109.0	152.0	0.7171	0.7171	104.0	104.0	142.0	0.7324	0.7324	73.0	73.0	118.0	0.6186	0.6186
0.2407	3.0	24	1.7101	0.0028	1406.2791	974.7584	393.0	570.0	0.6895	392.0	0.6877	98.0	99.0	158.0	0.6266	0.6203	104.0	104.0	152.0	0.6842	0.6842	109.0	109.0	142.0	0.7676	0.7676	81.0	81.0	118.0	0.6864	0.6864
0.0882	4.0	32	1.5139	0.0028	1244.9139	862.9086	384.0	570.0	0.6737	380.0	0.6667	108.0	110.0	158.0	0.6962	0.6835	116.0	117.0	152.0	0.7697	0.7632	93.0	94.0	142.0	0.6620	0.6549	63.0	63.0	118.0	0.5339	0.5339
0.0068	5.0	40	2.4577	0.0028	2021.0226	1400.8661	400.0	570.0	0.7018	391.0	0.6860	113.0	115.0	158.0	0.7278	0.7152	103.0	109.0	152.0	0.7171	0.6776	96.0	96.0	142.0	0.6761	0.6761	79.0	80.0	118.0	0.6780	0.6695
0.0002	6.0	48	2.9360	0.0028	2414.3942	1673.5305	394.0	570.0	0.6912	383.0	0.6719	119.0	120.0	158.0	0.7595	0.7532	101.0	108.0	152.0	0.7105	0.6645	94.0	96.0	142.0	0.6761	0.6620	69.0	70.0	118.0	0.5932	0.5847
0.0001	7.0	56	2.9475	0.0028	2423.8483	1680.0836	394.0	570.0	0.6912	382.0	0.6702	112.0	113.0	158.0	0.7152	0.7089	105.0	115.0	152.0	0.7566	0.6908	99.0	99.0	142.0	0.6972	0.6972	66.0	67.0	118.0	0.5678	0.5593
0.0001	8.0	64	2.8929	0.0028	2378.9126	1648.9366	395.0	570.0	0.6930	376.0	0.6596	109.0	110.0	158.0	0.6962	0.6899	97.0	111.0	152.0	0.7303	0.6382	99.0	100.0	142.0	0.7042	0.6972	71.0	74.0	118.0	0.6271	0.6017
0.0004	9.0	72	3.4450	0.0028	2832.9687	1963.6643	390.0	570.0	0.6842	389.0	0.6825	111.0	112.0	158.0	0.7089	0.7025	115.0	115.0	152.0	0.7566	0.7566	99.0	99.0	142.0	0.6972	0.6972	64.0	64.0	118.0	0.5424	0.5424
0.0015	10.0	80	3.5763	0.0028	2940.9268	2038.4952	388.0	570.0	0.6807	387.0	0.6789	111.0	112.0	158.0	0.7089	0.7025	111.0	111.0	152.0	0.7303	0.7303	102.0	102.0	142.0	0.7183	0.7183	63.0	63.0	118.0	0.5339	0.5339
0.0	11.0	88	3.5949	0.0028	2956.1769	2049.0657	386.0	570.0	0.6772	383.0	0.6719	116.0	117.0	158.0	0.7405	0.7342	103.0	104.0	152.0	0.6842	0.6776	100.0	100.0	142.0	0.7042	0.7042	64.0	65.0	118.0	0.5508	0.5424
0.0	12.0	96	3.7333	0.0028	3070.0089	2127.9680	383.0	570.0	0.6719	382.0	0.6702	117.0	118.0	158.0	0.7468	0.7405	105.0	105.0	152.0	0.6908	0.6908	97.0	97.0	142.0	0.6831	0.6831	63.0	63.0	118.0	0.5339	0.5339
0.0	13.0	104	3.8287	0.0028	3148.4799	2182.3600	381.0	570.0	0.6684	379.0	0.6649	116.0	117.0	158.0	0.7405	0.7342	105.0	105.0	152.0	0.6908	0.6908	95.0	96.0	142.0	0.6761	0.6690	63.0	63.0	118.0	0.5339	0.5339
0.0	14.0	112	3.8543	0.0028	3169.5456	2196.9616	382.0	570.0	0.6702	381.0	0.6684	115.0	116.0	158.0	0.7342	0.7278	106.0	106.0	152.0	0.6974	0.6974	97.0	97.0	142.0	0.6831	0.6831	63.0	63.0	118.0	0.5339	0.5339
0.0	15.0	120	3.8314	0.0028	3150.6978	2183.8973	384.0	570.0	0.6737	382.0	0.6702	117.0	118.0	158.0	0.7468	0.7405	106.0	106.0	152.0	0.6974	0.6974	96.0	97.0	142.0	0.6831	0.6761	63.0	63.0	118.0	0.5339	0.5339

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

donoway/ARC-Easy_Llama-3.2-1B-pvhtx4ka

ARC-Easy_Llama-3.2-1B-pvhtx4ka

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

donoway/
ARC-Easy_Llama-3.2-1B-pvhtx4ka