ARC-Easy_Llama-3.2-1B-6jgnsuv6

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: 0.8919
• Model Preparation Time: 0.0056
• Mdl: 733.4736
• Accumulated Loss: 508.4052
• Correct Preds: 427.0
• Total Preds: 570.0
• Accuracy: 0.7491
• Correct Gen Preds: 427.0
• Gen Accuracy: 0.7491
• Correct Gen Preds 32: 129.0
• Correct Preds 32: 129.0
• Total Labels 32: 158.0
• Accuracy 32: 0.8165
• Gen Accuracy 32: 0.8165
• Correct Gen Preds 33: 108.0
• Correct Preds 33: 108.0
• Total Labels 33: 152.0
• Accuracy 33: 0.7105
• Gen Accuracy 33: 0.7105
• Correct Gen Preds 34: 115.0
• Correct Preds 34: 115.0
• Total Labels 34: 142.0
• Accuracy 34: 0.8099
• Gen Accuracy 34: 0.8099
• Correct Gen Preds 35: 75.0
• Correct Preds 35: 75.0
• Total Labels 35: 118.0
• Accuracy 35: 0.6356
• Gen Accuracy 35: 0.6356
• Correct Gen Preds 36: 0.0
• Correct Preds 36: 0.0
• Total Labels 36: 0.0
• Accuracy 36: 0.0
• Gen Accuracy 36: 0.0

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: 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	Correct Gen Preds 36	Correct Preds 36	Total Labels 36	Accuracy 36	Gen Accuracy 36
No log	0	0	1.5354	0.0056	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	0.0	0.0	0.0	0.0	0.0
0.4726	1.0	25	0.8475	0.0056	696.9144	483.0642	394.0	570.0	0.6912	391.0	0.6860	87.0	90.0	158.0	0.5696	0.5506	104.0	104.0	152.0	0.6842	0.6842	109.0	109.0	142.0	0.7676	0.7676	91.0	91.0	118.0	0.7712	0.7712	0.0	0.0	0.0	0.0	0.0
0.7886	2.0	50	0.7247	0.0056	595.9247	413.0635	415.0	570.0	0.7281	415.0	0.7281	133.0	133.0	158.0	0.8418	0.8418	107.0	107.0	152.0	0.7039	0.7039	93.0	93.0	142.0	0.6549	0.6549	82.0	82.0	118.0	0.6949	0.6949	0.0	0.0	0.0	0.0	0.0
0.1428	3.0	75	0.8919	0.0056	733.4736	508.4052	427.0	570.0	0.7491	427.0	0.7491	129.0	129.0	158.0	0.8165	0.8165	108.0	108.0	152.0	0.7105	0.7105	115.0	115.0	142.0	0.8099	0.8099	75.0	75.0	118.0	0.6356	0.6356	0.0	0.0	0.0	0.0	0.0
0.0066	4.0	100	1.4142	0.0056	1162.9830	806.1184	420.0	570.0	0.7368	403.0	0.7070	119.0	125.0	158.0	0.7911	0.7532	119.0	123.0	152.0	0.8092	0.7829	100.0	103.0	142.0	0.7254	0.7042	65.0	69.0	118.0	0.5847	0.5508	0.0	0.0	0.0	0.0	0.0
0.0066	5.0	125	1.6364	0.0056	1345.6457	932.7305	406.0	570.0	0.7123	399.0	0.7	107.0	113.0	158.0	0.7152	0.6772	101.0	101.0	152.0	0.6645	0.6645	106.0	106.0	142.0	0.7465	0.7465	85.0	86.0	118.0	0.7288	0.7203	0.0	0.0	0.0	0.0	0.0
0.0001	6.0	150	2.3995	0.0056	1973.1559	1367.6875	407.0	570.0	0.7140	392.0	0.6877	93.0	104.0	158.0	0.6582	0.5886	113.0	114.0	152.0	0.75	0.7434	102.0	104.0	142.0	0.7324	0.7183	84.0	85.0	118.0	0.7203	0.7119	0.0	0.0	0.0	0.0	0.0
0.0	7.0	175	2.5540	0.0056	2100.2596	1455.7890	414.0	570.0	0.7263	408.0	0.7158	108.0	113.0	158.0	0.7152	0.6835	117.0	117.0	152.0	0.7697	0.7697	102.0	102.0	142.0	0.7183	0.7183	81.0	82.0	118.0	0.6949	0.6864	0.0	0.0	0.0	0.0	0.0
0.0001	8.0	200	2.5711	0.0056	2114.2895	1465.5138	418.0	570.0	0.7333	410.0	0.7193	106.0	113.0	158.0	0.7152	0.6709	122.0	123.0	152.0	0.8092	0.8026	102.0	102.0	142.0	0.7183	0.7183	80.0	80.0	118.0	0.6780	0.6780	0.0	0.0	0.0	0.0	0.0
0.0001	9.0	225	2.5896	0.0056	2129.5119	1476.0652	419.0	570.0	0.7351	410.0	0.7193	104.0	112.0	158.0	0.7089	0.6582	122.0	123.0	152.0	0.8092	0.8026	103.0	103.0	142.0	0.7254	0.7254	81.0	81.0	118.0	0.6864	0.6864	0.0	0.0	0.0	0.0	0.0
0.0	10.0	250	2.6097	0.0056	2146.0783	1487.5481	419.0	570.0	0.7351	411.0	0.7211	105.0	112.0	158.0	0.7089	0.6646	122.0	123.0	152.0	0.8092	0.8026	102.0	102.0	142.0	0.7183	0.7183	82.0	82.0	118.0	0.6949	0.6949	0.0	0.0	0.0	0.0	0.0
0.0	11.0	275	2.6133	0.0056	2149.0502	1489.6081	419.0	570.0	0.7351	411.0	0.7211	105.0	112.0	158.0	0.7089	0.6646	122.0	123.0	152.0	0.8092	0.8026	103.0	103.0	142.0	0.7254	0.7254	81.0	81.0	118.0	0.6864	0.6864	0.0	0.0	0.0	0.0	0.0
0.0	12.0	300	2.6221	0.0056	2156.2876	1494.6247	418.0	570.0	0.7333	410.0	0.7193	105.0	112.0	158.0	0.7089	0.6646	122.0	123.0	152.0	0.8092	0.8026	102.0	102.0	142.0	0.7183	0.7183	81.0	81.0	118.0	0.6864	0.6864	0.0	0.0	0.0	0.0	0.0
0.0	13.0	325	2.6192	0.0056	2153.8311	1492.9219	418.0	570.0	0.7333	410.0	0.7193	104.0	111.0	158.0	0.7025	0.6582	122.0	123.0	152.0	0.8092	0.8026	102.0	102.0	142.0	0.7183	0.7183	82.0	82.0	118.0	0.6949	0.6949	0.0	0.0	0.0	0.0	0.0
0.0	14.0	350	2.6335	0.0056	2165.6088	1501.0857	419.0	570.0	0.7351	411.0	0.7211	106.0	113.0	158.0	0.7152	0.6709	122.0	123.0	152.0	0.8092	0.8026	102.0	102.0	142.0	0.7183	0.7183	81.0	81.0	118.0	0.6864	0.6864	0.0	0.0	0.0	0.0	0.0
0.0	15.0	375	2.6250	0.0056	2158.6426	1496.2570	420.0	570.0	0.7368	412.0	0.7228	106.0	113.0	158.0	0.7152	0.6709	122.0	123.0	152.0	0.8092	0.8026	103.0	103.0	142.0	0.7254	0.7254	81.0	81.0	118.0	0.6864	0.6864	0.0	0.0	0.0	0.0	0.0
0.0	16.0	400	2.6439	0.0056	2174.2071	1507.0456	419.0	570.0	0.7351	411.0	0.7211	105.0	112.0	158.0	0.7089	0.6646	122.0	123.0	152.0	0.8092	0.8026	103.0	103.0	142.0	0.7254	0.7254	81.0	81.0	118.0	0.6864	0.6864	0.0	0.0	0.0	0.0	0.0
0.0	17.0	425	2.6435	0.0056	2173.8519	1506.7993	421.0	570.0	0.7386	413.0	0.7246	105.0	112.0	158.0	0.7089	0.6646	123.0	124.0	152.0	0.8158	0.8092	103.0	103.0	142.0	0.7254	0.7254	82.0	82.0	118.0	0.6949	0.6949	0.0	0.0	0.0	0.0	0.0

Framework versions

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