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
No log	0	0	1.5354	0.0062	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
0.4578	1.0	36	0.7925	0.0062	651.6956	451.7210	390.0	570.0	0.6842	390.0	0.6842	141.0	141.0	158.0	0.8924	0.8924	89.0	89.0	152.0	0.5855	0.5855	81.0	81.0	142.0	0.5704	0.5704	79.0	79.0	118.0	0.6695	0.6695
0.3401	2.0	72	0.8064	0.0062	663.1252	459.6433	406.0	570.0	0.7123	405.0	0.7105	135.0	136.0	158.0	0.8608	0.8544	109.0	109.0	152.0	0.7171	0.7171	87.0	87.0	142.0	0.6127	0.6127	74.0	74.0	118.0	0.6271	0.6271
0.0029	3.0	108	1.1509	0.0062	946.4028	655.9965	440.0	570.0	0.7719	439.0	0.7702	110.0	111.0	158.0	0.7025	0.6962	133.0	133.0	152.0	0.875	0.875	109.0	109.0	142.0	0.7676	0.7676	87.0	87.0	118.0	0.7373	0.7373
0.0039	4.0	144	1.2837	0.0062	1055.6098	731.6930	437.0	570.0	0.7667	436.0	0.7649	113.0	114.0	158.0	0.7215	0.7152	134.0	134.0	152.0	0.8816	0.8816	113.0	113.0	142.0	0.7958	0.7958	76.0	76.0	118.0	0.6441	0.6441
0.0011	5.0	180	1.9569	0.0062	1609.2304	1115.4335	422.0	570.0	0.7404	420.0	0.7368	121.0	123.0	158.0	0.7785	0.7658	118.0	118.0	152.0	0.7763	0.7763	105.0	105.0	142.0	0.7394	0.7394	76.0	76.0	118.0	0.6441	0.6441
0.0001	6.0	216	1.7405	0.0062	1431.2739	992.0834	429.0	570.0	0.7526	429.0	0.7526	114.0	114.0	158.0	0.7215	0.7215	113.0	113.0	152.0	0.7434	0.7434	110.0	110.0	142.0	0.7746	0.7746	92.0	92.0	118.0	0.7797	0.7797
0.0001	7.0	252	2.0143	0.0062	1656.4159	1148.1400	430.0	570.0	0.7544	429.0	0.7526	112.0	113.0	158.0	0.7152	0.7089	115.0	115.0	152.0	0.7566	0.7566	111.0	111.0	142.0	0.7817	0.7817	91.0	91.0	118.0	0.7712	0.7712
0.0016	8.0	288	1.8334	0.0062	1507.6687	1045.0363	428.0	570.0	0.7509	427.0	0.7491	125.0	126.0	158.0	0.7975	0.7911	110.0	110.0	152.0	0.7237	0.7237	112.0	112.0	142.0	0.7887	0.7887	80.0	80.0	118.0	0.6780	0.6780
0.0	9.0	324	2.7143	0.0062	2232.0899	1547.1668	425.0	570.0	0.7456	425.0	0.7456	106.0	106.0	158.0	0.6709	0.6709	125.0	125.0	152.0	0.8224	0.8224	109.0	109.0	142.0	0.7676	0.7676	85.0	85.0	118.0	0.7203	0.7203
0.0	10.0	360	2.6413	0.0062	2171.9994	1505.5152	424.0	570.0	0.7439	424.0	0.7439	114.0	114.0	158.0	0.7215	0.7215	109.0	109.0	152.0	0.7171	0.7171	117.0	117.0	142.0	0.8239	0.8239	84.0	84.0	118.0	0.7119	0.7119
0.0	11.0	396	2.7628	0.0062	2271.9653	1574.8063	422.0	570.0	0.7404	422.0	0.7404	125.0	125.0	158.0	0.7911	0.7911	108.0	108.0	152.0	0.7105	0.7105	109.0	109.0	142.0	0.7676	0.7676	80.0	80.0	118.0	0.6780	0.6780
0.0	12.0	432	2.7814	0.0062	2287.2186	1585.3792	421.0	570.0	0.7386	421.0	0.7386	124.0	124.0	158.0	0.7848	0.7848	108.0	108.0	152.0	0.7105	0.7105	108.0	108.0	142.0	0.7606	0.7606	81.0	81.0	118.0	0.6864	0.6864
0.0	13.0	468	2.7721	0.0062	2279.6203	1580.1124	422.0	570.0	0.7404	422.0	0.7404	125.0	125.0	158.0	0.7911	0.7911	108.0	108.0	152.0	0.7105	0.7105	108.0	108.0	142.0	0.7606	0.7606	81.0	81.0	118.0	0.6864	0.6864

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-qsx0hz5e

ARC-Easy_Llama-3.2-1B-qsx0hz5e

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

donoway/
ARC-Easy_Llama-3.2-1B-qsx0hz5e