Spaces:

inflaton-ai
/

logical-reasoning

Build error

App Files Files Community

dh-mc commited on Sep 27, 2024

Commit

0e5f859

1 Parent(s): e31a782

clean up data

Browse files

Files changed (15) hide show

data/Llama3.1-8B-Chinese-Chat_results.csv +0 -0
data/Qwen2.5-1.5B-Instruct_metrics.csv +11 -11
data/Qwen2.5-1.5B-Instruct_shots_metrics.csv +2 -2
data/Qwen2.5-7B-Instruct_metrics.csv +11 -11
data/Qwen2.5-7B-Instruct_results.csv +0 -0
data/Qwen2.5-7B-Instruct_shots_metrics.csv +7 -7
data/best_metrics.csv +2 -2
data/best_results.csv +0 -0
data/few-shots_metrics.csv +17 -16
data/fine-tuning_metrics.csv +33 -33
notebooks/00_Data Analysis.ipynb +2 -2
notebooks/02d_Qwen2.5-7B-Instruct_analysis.ipynb +2 -2
notebooks/02e_Qwen2.5-1.5B-Instruct_analysis.ipynb +2 -2
notebooks/02g_Qwen2.5-72B-Instruct_analysis.ipynb +2 -2
notebooks/03a_Llama3.1-8B-Chinese-Chat_analysis.ipynb +2 -2

data/Llama3.1-8B-Chinese-Chat_results.csv CHANGED Viewed

The diff for this file is too large to render. See raw diff

data/Qwen2.5-1.5B-Instruct_metrics.csv CHANGED Viewed

@@ -1,12 +1,12 @@
 epoch,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
-0.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct_torch.float16_lf,0.20166666666666666,0.5269756683734005,0.20166666666666666,0.24069835329504388,0.9223333333333333
-0.2,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-35_torch.float16_lf,0.48533333333333334,0.654166887199198,0.48533333333333334,0.5381849571995003,0.9996666666666667
-0.4,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-70_torch.float16_lf,0.573,0.7037737273232145,0.573,0.6131069400231612,0.9996666666666667
-0.6,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-105_torch.float16_lf,0.539,0.7162869126454278,0.539,0.5961610389687657,1.0
-0.8,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-140_torch.float16_lf,0.6443333333333333,0.7218750831357578,0.6443333333333333,0.6721473356905486,1.0
-1.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-175_torch.float16_lf,0.6296666666666667,0.7065049203038848,0.6296666666666667,0.6496809196018393,1.0
-1.2,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-210_torch.float16_lf,0.5836666666666667,0.7222805944180548,0.5836666666666667,0.6314346830311218,1.0
-1.4,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-245_torch.float16_lf,0.6493333333333333,0.7440287895607589,0.6493333333333333,0.6815314583590799,1.0
-1.6,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-280_torch.float16_lf,0.6293333333333333,0.7332138067544355,0.6293333333333333,0.6634330572585689,1.0
-1.8,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-315_torch.float16_lf,0.599,0.7297954686265763,0.599,0.6396292878324805,1.0
-2.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-350_torch.float16_lf,0.6056666666666667,0.7305580205770756,0.6056666666666667,0.6426785514786738,1.0

 epoch,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
+0.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct_torch.bfloat16_lf,0.178,0.5082549494185494,0.17800000000000005,0.2206670187667368,0.9403333333333334
+0.2,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-35_torch.bfloat16_lf,0.521,0.6393141994049955,0.521,0.5543058103456981,1.0
+0.4,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-70_torch.bfloat16_lf,0.5786666666666667,0.6827334710464682,0.5786666666666667,0.6055896299128966,1.0
+0.6,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-105_torch.bfloat16_lf,0.544,0.7064593462910856,0.544,0.5946365105633672,1.0
+0.8,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-140_torch.bfloat16_lf,0.659,0.7267092412287238,0.659,0.6825875108247536,1.0
+1.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-175_torch.bfloat16_lf,0.637,0.7191389576964738,0.637,0.6562859054038414,1.0
+1.2,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-210_torch.bfloat16_lf,0.6086666666666667,0.7293412868960213,0.6086666666666667,0.6479350184617141,1.0
+1.4,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-245_torch.bfloat16_lf,0.6326666666666667,0.716380475510422,0.6326666666666667,0.6591217616290708,1.0
+1.6,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-280_torch.bfloat16_lf,0.6273333333333333,0.7224778228100358,0.6273333333333333,0.6551405164716649,1.0
+1.8,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-315_torch.bfloat16_lf,0.5973333333333334,0.7263124149931549,0.5973333333333334,0.6349391744052281,1.0
+2.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-350_torch.bfloat16_lf,0.6046666666666667,0.7203284046544999,0.6046666666666667,0.6377776248713325,1.0

data/Qwen2.5-1.5B-Instruct_shots_metrics.csv CHANGED Viewed

@@ -1,6 +1,6 @@
 shots,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
-0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-00,0.20166666666666666,0.5269756683734005,0.20166666666666666,0.24069835329504388,0.9223333333333333
-5,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-05,0.3933333333333333,0.578886379886985,0.3933333333333333,0.43554636943558694,0.8283333333333334
 10,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-10,0.407,0.5820145311822223,0.407,0.459589777544246,0.9156666666666666
 20,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-20,0.232,0.5282610881631451,0.232,0.3093707499897376,0.676
 30,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-30,0.23,0.5479545947886839,0.23,0.3064381040560128,0.661

 shots,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
+0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-00,0.18366666666666667,0.5244570465301668,0.18366666666666667,0.23286492799102732,0.931
+5,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-05,0.349,0.5695965528635436,0.349,0.3771117506970461,0.9756666666666667
 10,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-10,0.407,0.5820145311822223,0.407,0.459589777544246,0.9156666666666666
 20,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-20,0.232,0.5282610881631451,0.232,0.3093707499897376,0.676
 30,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-30,0.23,0.5479545947886839,0.23,0.3064381040560128,0.661

data/Qwen2.5-7B-Instruct_metrics.csv CHANGED Viewed

@@ -1,12 +1,12 @@
 epoch,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
-0.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct_torch.bfloat16_lf,0.644,0.7200261355300325,0.644,0.6101052277961244,1.0
-0.2,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-35_torch.bfloat16_lf,0.745,0.7643041174791825,0.745,0.7482828029872421,0.998
-0.4,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-70_torch.bfloat16_lf,0.7446666666666667,0.7800215227839997,0.7446666666666667,0.7576550061479678,0.9996666666666667
-0.6,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-105_torch.bfloat16_lf,0.7513333333333333,0.7996792149630704,0.7513333333333333,0.7693730206330721,0.9996666666666667
-0.8,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-140_torch.bfloat16_lf,0.75,0.7923028105975739,0.75,0.7665531868559959,1.0
-1.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-175_torch.bfloat16_lf,0.771,0.8005814962709542,0.771,0.7814602739241332,0.9993333333333333
-1.2,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-210_torch.bfloat16_lf,0.7443333333333333,0.79978900243777,0.7443333333333333,0.7660506505481828,1.0
-1.4,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-245_torch.bfloat16_lf,0.7486666666666667,0.7974562319123832,0.7486666666666667,0.7655275916268014,0.9993333333333333
-1.6,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-280_torch.bfloat16_lf,0.7566666666666667,0.7939852407869384,0.7566666666666667,0.7689495073735431,0.9996666666666667
-1.8,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-315_torch.bfloat16_lf,0.755,0.7940575522966016,0.755,0.7681326415137147,0.9993333333333333
-2.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-350_torch.bfloat16_lf,0.756,0.7982464722401461,0.756,0.7704035278260453,0.9996666666666667

 epoch,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
+0.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct_torch.bfloat16_lf,0.6436666666666667,0.717651042027604,0.6436666666666667,0.6066932578767255,1.0
+0.2,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-35_torch.bfloat16_lf,0.7473333333333333,0.759526705532232,0.7473333333333333,0.7480522291877509,0.998
+0.4,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-70_torch.bfloat16_lf,0.752,0.7774114736945115,0.752,0.7611191332452362,0.9996666666666667
+0.6,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-105_torch.bfloat16_lf,0.7623333333333333,0.7987495507688677,0.7623333333333333,0.7754658001873385,0.9996666666666667
+0.8,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-140_torch.bfloat16_lf,0.7596666666666667,0.7923123268836624,0.7596666666666667,0.7724543387690386,1.0
+1.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-175_torch.bfloat16_lf,0.782,0.8023938029436536,0.782,0.7888740758699296,0.9993333333333333
+1.2,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-210_torch.bfloat16_lf,0.7563333333333333,0.7997527018417315,0.7563333333333333,0.7728761539215637,1.0
+1.4,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-245_torch.bfloat16_lf,0.762,0.7997301280029149,0.762,0.7743858484379207,0.9993333333333333
+1.6,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-280_torch.bfloat16_lf,0.7726666666666666,0.8006851113573145,0.7726666666666666,0.7813968284378919,0.9996666666666667
+1.8,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-315_torch.bfloat16_lf,0.7696666666666667,0.799287702962426,0.7696666666666667,0.7792120245789584,0.9993333333333333
+2.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-350_torch.bfloat16_lf,0.769,0.8010881984531473,0.769,0.7793801070552965,0.9996666666666667

data/Qwen2.5-7B-Instruct_results.csv CHANGED Viewed

The diff for this file is too large to render. See raw diff

data/Qwen2.5-7B-Instruct_shots_metrics.csv CHANGED Viewed

@@ -1,8 +1,8 @@
 shots,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
-0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-00,0.644,0.7200261355300325,0.644,0.6101052277961244,1.0
-5,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-05,0.6346666666666667,0.7653343185471776,0.6346666666666667,0.6219419633691871,0.998
-10,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-10,0.678,0.7675951017673515,0.678,0.6790860659550377,0.9796666666666667
-20,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-20,0.7353333333333333,0.7702034737275962,0.7353333333333333,0.7278047438569933,0.807
-30,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-30,0.7646666666666667,0.7787918401418651,0.7646666666666667,0.7527649874769439,0.805
-40,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-40,0.759,0.7736852689131295,0.759,0.7472252604775926,0.8546666666666667
-50,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-50,0.7586666666666667,0.7640431634617543,0.7586666666666667,0.7414332963557551,0.7563333333333333

 shots,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
+0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-00,0.6436666666666667,0.717651042027604,0.6436666666666667,0.6066932578767255,1.0
+5,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-05,0.63,0.7622571683877091,0.63,0.6151126410759672,0.998
+10,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-10,0.677,0.7663956674673086,0.677,0.6770580664953397,0.9796666666666667
+20,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-20,0.7343333333333333,0.7730863408305184,0.7343333333333333,0.7243291573141537,0.807
+30,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-30,0.765,0.7840432806350224,0.765,0.7512220322751986,0.805
+40,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-40,0.757,0.7733827213068922,0.757,0.7427592763321033,0.8546666666666667
+50,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-50,0.758,0.763149679724481,0.758,0.7376580515312735,0.7563333333333333

data/best_metrics.csv CHANGED Viewed

@@ -6,8 +6,8 @@ index,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
 5,InternLM2.5-7B-1M (0.8-epoch),InternLM2.5-7B-1M (0.8-epoch),0.8076666666666666,0.8048844422436796,0.8076666666666666,0.8049749805997191,1.0
 6,InternLM2.5-20B (0.8-epoch),InternLM2.5-20B (0.8-epoch),0.8063333333333333,0.8207793607428686,0.8063333333333333,0.811239851005161,1.0
 7,Qwen2.5-0.5B (1.4-epoch),Qwen2.5-0.5B (1.4-epoch),0.5903333333333334,0.6503049529377274,0.5903333333333334,0.6094397514027766,1.0
-8,Qwen2.5-1.5B (1.4-epoch),Qwen2.5-1.5B (1.4-epoch),0.6493333333333333,0.7440287895607589,0.6493333333333333,0.6815314583590799,1.0
-9,Qwen2.5-3B (1.4-epoch),Qwen2.5-3B (1.4-epoch),0.7326666666666667,0.7716369414239331,0.7326666666666667,0.7468182490858526,1.0
 10,Qwen2.5-7B (1.0-epoch),Qwen2.5-7B (1.0-epoch),0.782,0.8023938029436536,0.782,0.7888740758699296,0.9993333333333333
 11,Qwen2.5-72B (0.8-epoch),Qwen2.5-72B (0.8-epoch),0.8213333333333334,0.8447926258362122,0.8213333333333334,0.8299486611547571,1.0
 12,gpt-4o-mini (0-shot),gpt-4o-mini (0-shot),0.7166666666666667,0.7800918028217227,0.7166666666666667,0.7260056154268697,1.0

 5,InternLM2.5-7B-1M (0.8-epoch),InternLM2.5-7B-1M (0.8-epoch),0.8076666666666666,0.8048844422436796,0.8076666666666666,0.8049749805997191,1.0
 6,InternLM2.5-20B (0.8-epoch),InternLM2.5-20B (0.8-epoch),0.8063333333333333,0.8207793607428686,0.8063333333333333,0.811239851005161,1.0
 7,Qwen2.5-0.5B (1.4-epoch),Qwen2.5-0.5B (1.4-epoch),0.5903333333333334,0.6503049529377274,0.5903333333333334,0.6094397514027766,1.0
+8,Qwen2.5-1.5B (0.8-epoch),Qwen2.5-1.5B (0.8-epoch),0.659,0.7267092412287238,0.659,0.6825875108247536,1.0
+9,Qwen2.5-3B (1.4-epoch),Qwen2.5-3B (1.4-epoch),0.7303333333333333,0.7695138336135122,0.7303333333333333,0.7445711153936881,1.0
 10,Qwen2.5-7B (1.0-epoch),Qwen2.5-7B (1.0-epoch),0.782,0.8023938029436536,0.782,0.7888740758699296,0.9993333333333333
 11,Qwen2.5-72B (0.8-epoch),Qwen2.5-72B (0.8-epoch),0.8213333333333334,0.8447926258362122,0.8213333333333334,0.8299486611547571,1.0
 12,gpt-4o-mini (0-shot),gpt-4o-mini (0-shot),0.7166666666666667,0.7800918028217227,0.7166666666666667,0.7260056154268697,1.0

data/best_results.csv CHANGED Viewed

The diff for this file is too large to render. See raw diff

data/few-shots_metrics.csv CHANGED Viewed

@@ -44,6 +44,7 @@ shots,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
 10,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/shots-10,0.612,0.7259976964524691,0.612,0.6501410678512595,0.1063333333333333
 20,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/shots-20,0.6336666666666667,0.7315100617022602,0.6336666666666667,0.6683245802083553,0.0826666666666666
 30,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/shots-30,0.665,0.7374233826761456,0.665,0.6872462947319797,0.07
 0,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/shots-00,0.7063333333333334,0.7369785607161373,0.7063333333333334,0.6895815239121195,1.0
 5,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/shots-05,0.747,0.7433195768374967,0.747,0.7232456014841266,0.999
 10,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/shots-10,0.559,0.7306434812774306,0.559,0.6287391975839828,0.9883333333333332
@@ -66,26 +67,26 @@ shots,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
 30,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-30,0.39,0.5367753683204347,0.39,0.4299603249123421,0.0756666666666666
 40,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-40,0.466,0.5400134144413437,0.466,0.495429756139619,0.324
 50,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-50,0.496,0.5465409839032335,0.496,0.5069942984615308,0.2433333333333333
-0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-00,0.2016666666666666,0.5269756683734005,0.2016666666666666,0.2406983532950438,0.9223333333333332
-5,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-05,0.3933333333333333,0.578886379886985,0.3933333333333333,0.4355463694355869,0.8283333333333334
 10,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-10,0.407,0.5820145311822223,0.407,0.459589777544246,0.9156666666666666
 20,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-20,0.232,0.5282610881631451,0.232,0.3093707499897376,0.676
 30,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-30,0.23,0.5479545947886839,0.23,0.3064381040560128,0.661
 40,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-40,0.2923333333333333,0.5608411738006117,0.2923333333333333,0.3751714671158081,0.5206666666666667
 50,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-50,0.29,0.5646814860840066,0.29,0.3688382652659246,0.4603333333333333
-0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-00,0.5796666666666667,0.6966500240864278,0.5796666666666667,0.5506370828782681,1.0
-5,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-05,0.639,0.7226431221398603,0.639,0.641568790114368,0.9973333333333332
-10,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-10,0.625,0.7164154004131771,0.625,0.6402584852791593,0.995
-20,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-20,0.4666666666666667,0.6987641430848737,0.4666666666666667,0.5265074036660548,0.9316666666666666
-30,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-30,0.475,0.6880994914236809,0.475,0.5310948082593374,0.904
-40,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-40,0.584,0.7065303262365236,0.584,0.6214992664375876,0.7173333333333334
-50,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-50,0.6093333333333333,0.7120506480394511,0.6093333333333333,0.6451959368825358,0.574
-0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-00,0.644,0.7200261355300325,0.644,0.6101052277961244,1.0
-5,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-05,0.6346666666666667,0.7653343185471776,0.6346666666666667,0.6219419633691871,0.998
-10,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-10,0.678,0.7675951017673515,0.678,0.6790860659550377,0.9796666666666668
-20,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-20,0.7353333333333333,0.7702034737275962,0.7353333333333333,0.7278047438569933,0.807
-30,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-30,0.7646666666666667,0.7787918401418651,0.7646666666666667,0.7527649874769439,0.805
-40,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-40,0.759,0.7736852689131295,0.759,0.7472252604775926,0.8546666666666667
-50,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-50,0.7586666666666667,0.7640431634617543,0.7586666666666667,0.7414332963557551,0.7563333333333333
 0,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/shots-00,0.7956666666666666,0.8098073411161181,0.7956666666666666,0.7771317592221199,0.994
 5,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/shots-05,0.819,0.8182324679666184,0.819,0.8095367865845521,0.9416666666666668

 10,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/shots-10,0.612,0.7259976964524691,0.612,0.6501410678512595,0.1063333333333333
 20,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/shots-20,0.6336666666666667,0.7315100617022602,0.6336666666666667,0.6683245802083553,0.0826666666666666
 30,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/shots-30,0.665,0.7374233826761456,0.665,0.6872462947319797,0.07
+40,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/shots-40,0.6306666666666667,0.7422868762493116,0.6306666666666667,0.6670711390706651,0.0633333333333333
 0,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/shots-00,0.7063333333333334,0.7369785607161373,0.7063333333333334,0.6895815239121195,1.0
 5,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/shots-05,0.747,0.7433195768374967,0.747,0.7232456014841266,0.999
 10,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/shots-10,0.559,0.7306434812774306,0.559,0.6287391975839828,0.9883333333333332
 30,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-30,0.39,0.5367753683204347,0.39,0.4299603249123421,0.0756666666666666
 40,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-40,0.466,0.5400134144413437,0.466,0.495429756139619,0.324
 50,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/shots-50,0.496,0.5465409839032335,0.496,0.5069942984615308,0.2433333333333333
+0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-00,0.1836666666666666,0.5244570465301668,0.1836666666666666,0.2328649279910273,0.931
+5,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-05,0.349,0.5695965528635436,0.349,0.3771117506970461,0.9756666666666668
 10,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-10,0.407,0.5820145311822223,0.407,0.459589777544246,0.9156666666666666
 20,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-20,0.232,0.5282610881631451,0.232,0.3093707499897376,0.676
 30,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-30,0.23,0.5479545947886839,0.23,0.3064381040560128,0.661
 40,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-40,0.2923333333333333,0.5608411738006117,0.2923333333333333,0.3751714671158081,0.5206666666666667
 50,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/shots-50,0.29,0.5646814860840066,0.29,0.3688382652659246,0.4603333333333333
+0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-00,0.5783333333333334,0.6938704799615603,0.5783333333333334,0.5482371104670698,1.0
+5,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-05,0.6446666666666667,0.7230280501918229,0.6446666666666667,0.6455439085887453,0.9973333333333332
+10,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-10,0.6356666666666667,0.717399441576705,0.6356666666666667,0.647050125518008,0.995
+20,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-20,0.4806666666666667,0.6978154586535756,0.4806666666666667,0.5325218737400426,0.9316666666666666
+30,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-30,0.4883333333333333,0.6902162639713183,0.4883333333333333,0.5393146850625054,0.904
+40,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-40,0.595,0.7060453498136213,0.595,0.6271468055875201,0.7173333333333334
+50,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/shots-50,0.6186666666666667,0.7088242726720394,0.6186666666666667,0.6483835468519816,0.574
+0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-00,0.6436666666666667,0.717651042027604,0.6436666666666667,0.6066932578767255,1.0
+5,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-05,0.63,0.7622571683877091,0.63,0.6151126410759672,0.998
+10,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-10,0.677,0.7663956674673086,0.677,0.6770580664953397,0.9796666666666668
+20,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-20,0.7343333333333333,0.7730863408305184,0.7343333333333333,0.7243291573141537,0.807
+30,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-30,0.765,0.7840432806350224,0.765,0.7512220322751986,0.805
+40,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-40,0.757,0.7733827213068922,0.757,0.7427592763321033,0.8546666666666667
+50,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/shots-50,0.758,0.763149679724481,0.758,0.7376580515312735,0.7563333333333333
 0,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/shots-00,0.7956666666666666,0.8098073411161181,0.7956666666666666,0.7771317592221199,0.994
 5,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/shots-05,0.819,0.8182324679666184,0.819,0.8095367865845521,0.9416666666666668

data/fine-tuning_metrics.csv CHANGED Viewed

@@ -76,39 +76,39 @@ epoch,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
 1.6,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-280_torch.float16_lf,0.5286666666666666,0.6532851084098983,0.5286666666666666,0.5617239467523474,1.0
 1.8,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-315_torch.float16_lf,0.5336666666666666,0.6607103736450911,0.5336666666666666,0.5622949959647037,1.0
 2.0,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-350_torch.float16_lf,0.5156666666666667,0.652809461208547,0.5156666666666667,0.549955024535151,1.0
-0.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct_torch.float16_lf,0.2016666666666666,0.5269756683734005,0.2016666666666666,0.2406983532950438,0.9223333333333332
-0.2,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-35_torch.float16_lf,0.4853333333333333,0.654166887199198,0.4853333333333333,0.5381849571995003,0.9996666666666668
-0.4,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-70_torch.float16_lf,0.573,0.7037737273232145,0.573,0.6131069400231612,0.9996666666666668
-0.6,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-105_torch.float16_lf,0.539,0.7162869126454278,0.539,0.5961610389687657,1.0
-0.8,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-140_torch.float16_lf,0.6443333333333333,0.7218750831357578,0.6443333333333333,0.6721473356905486,1.0
-1.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-175_torch.float16_lf,0.6296666666666667,0.7065049203038848,0.6296666666666667,0.6496809196018393,1.0
-1.2,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-210_torch.float16_lf,0.5836666666666667,0.7222805944180548,0.5836666666666667,0.6314346830311218,1.0
-1.4,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-245_torch.float16_lf,0.6493333333333333,0.7440287895607589,0.6493333333333333,0.6815314583590799,1.0
-1.6,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-280_torch.float16_lf,0.6293333333333333,0.7332138067544355,0.6293333333333333,0.6634330572585689,1.0
-1.8,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-315_torch.float16_lf,0.599,0.7297954686265763,0.599,0.6396292878324805,1.0
-2.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-350_torch.float16_lf,0.6056666666666667,0.7305580205770756,0.6056666666666667,0.6426785514786738,1.0
-0.0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct_torch.float16_lf,0.5796666666666667,0.6966500240864278,0.5796666666666667,0.5506370828782681,1.0
-0.2,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-35_torch.float16_lf,0.689,0.7450174119748659,0.689,0.709114466474576,0.9986666666666668
-0.4,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-70_torch.float16_lf,0.6556666666666666,0.7590430811422313,0.6556666666666666,0.6934194398116857,1.0
-0.6,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-105_torch.float16_lf,0.6963333333333334,0.7550938479315918,0.6963333333333334,0.71844324172961,1.0
-0.8,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-140_torch.float16_lf,0.6853333333333333,0.7542524799326954,0.6853333333333333,0.7128732915785243,1.0
-1.0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-175_torch.float16_lf,0.6846666666666666,0.7564071354272528,0.6846666666666666,0.7125676758538035,1.0
-1.2,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-210_torch.float16_lf,0.6896666666666667,0.7690917466956201,0.6896666666666667,0.720231747443145,1.0
-1.4,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-245_torch.float16_lf,0.7256666666666667,0.7753705482689578,0.7256666666666667,0.7440390153124937,1.0
-1.6,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-280_torch.float16_lf,0.708,0.7659638403826392,0.708,0.7293997518219294,1.0
-1.8,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-315_torch.float16_lf,0.7056666666666667,0.7717562122699148,0.7056666666666667,0.729817759784445,1.0
-2.0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-350_torch.float16_lf,0.7003333333333334,0.7698824212888824,0.7003333333333334,0.726563613830647,1.0
-0.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct_torch.bfloat16_lf,0.644,0.7200261355300325,0.644,0.6101052277961244,1.0
-0.2,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-35_torch.bfloat16_lf,0.745,0.7643041174791825,0.745,0.7482828029872421,0.998
-0.4,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-70_torch.bfloat16_lf,0.7446666666666667,0.7800215227839997,0.7446666666666667,0.7576550061479678,0.9996666666666668
-0.6,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-105_torch.bfloat16_lf,0.7513333333333333,0.7996792149630704,0.7513333333333333,0.7693730206330721,0.9996666666666668
-0.8,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-140_torch.bfloat16_lf,0.75,0.7923028105975739,0.75,0.7665531868559959,1.0
-1.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-175_torch.bfloat16_lf,0.771,0.8005814962709542,0.771,0.7814602739241332,0.9993333333333332
-1.2,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-210_torch.bfloat16_lf,0.7443333333333333,0.79978900243777,0.7443333333333333,0.7660506505481828,1.0
-1.4,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-245_torch.bfloat16_lf,0.7486666666666667,0.7974562319123832,0.7486666666666667,0.7655275916268014,0.9993333333333332
-1.6,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-280_torch.bfloat16_lf,0.7566666666666667,0.7939852407869384,0.7566666666666667,0.7689495073735431,0.9996666666666668
-1.8,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-315_torch.bfloat16_lf,0.755,0.7940575522966016,0.755,0.7681326415137147,0.9993333333333332
-2.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-350_torch.bfloat16_lf,0.756,0.7982464722401461,0.756,0.7704035278260453,0.9996666666666668
 0.0,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct_torch.bfloat16_4bit_lf,0.7956666666666666,0.8098073411161181,0.7956666666666666,0.7771317592221199,0.994
 0.2,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-35_torch.bfloat16_4bit_lf,0.792,0.8180793658647517,0.792,0.80166512366027,1.0
 0.4,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-70_torch.bfloat16_4bit_lf,0.7716666666666666,0.8199569804721152,0.7716666666666666,0.7895879011938259,1.0

 1.6,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-280_torch.float16_lf,0.5286666666666666,0.6532851084098983,0.5286666666666666,0.5617239467523474,1.0
 1.8,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-315_torch.float16_lf,0.5336666666666666,0.6607103736450911,0.5336666666666666,0.5622949959647037,1.0
 2.0,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-350_torch.float16_lf,0.5156666666666667,0.652809461208547,0.5156666666666667,0.549955024535151,1.0
+0.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct_torch.bfloat16_lf,0.178,0.5082549494185494,0.178,0.2206670187667368,0.9403333333333334
+0.2,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-35_torch.bfloat16_lf,0.521,0.6393141994049955,0.521,0.5543058103456981,1.0
+0.4,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-70_torch.bfloat16_lf,0.5786666666666667,0.6827334710464682,0.5786666666666667,0.6055896299128966,1.0
+0.6,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-105_torch.bfloat16_lf,0.544,0.7064593462910856,0.544,0.5946365105633672,1.0
+0.8,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-140_torch.bfloat16_lf,0.659,0.7267092412287238,0.659,0.6825875108247536,1.0
+1.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-175_torch.bfloat16_lf,0.637,0.7191389576964738,0.637,0.6562859054038414,1.0
+1.2,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-210_torch.bfloat16_lf,0.6086666666666667,0.7293412868960213,0.6086666666666667,0.6479350184617141,1.0
+1.4,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-245_torch.bfloat16_lf,0.6326666666666667,0.716380475510422,0.6326666666666667,0.6591217616290708,1.0
+1.6,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-280_torch.bfloat16_lf,0.6273333333333333,0.7224778228100358,0.6273333333333333,0.6551405164716649,1.0
+1.8,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-315_torch.bfloat16_lf,0.5973333333333334,0.7263124149931549,0.5973333333333334,0.6349391744052281,1.0
+2.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-350_torch.bfloat16_lf,0.6046666666666667,0.7203284046544999,0.6046666666666667,0.6377776248713325,1.0
+0.0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct_torch.bfloat16_lf,0.569,0.6886829973126811,0.569,0.5333701103243736,1.0
+0.2,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-35_torch.bfloat16_lf,0.6833333333333333,0.7269965624622317,0.6833333333333333,0.6985990460224034,0.999
+0.4,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-70_torch.bfloat16_lf,0.6766666666666666,0.7583682510610537,0.6766666666666666,0.705917900971524,1.0
+0.6,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-105_torch.bfloat16_lf,0.7023333333333334,0.7500816082620184,0.7023333333333334,0.7196546370690564,1.0
+0.8,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-140_torch.bfloat16_lf,0.71,0.7658586215313521,0.71,0.7318979017034846,1.0
+1.0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-175_torch.bfloat16_lf,0.7053333333333334,0.7645466069416816,0.7053333333333334,0.7278931369071717,1.0
+1.2,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-210_torch.bfloat16_lf,0.6943333333333334,0.7711644797484947,0.6943333333333334,0.7225635970673485,1.0
+1.4,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-245_torch.bfloat16_lf,0.7303333333333333,0.7695138336135122,0.7303333333333333,0.7445711153936881,1.0
+1.6,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-280_torch.bfloat16_lf,0.7273333333333334,0.7726772149368513,0.7273333333333334,0.7426310656072148,1.0
+1.8,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-315_torch.bfloat16_lf,0.7093333333333334,0.7726776026356509,0.7093333333333334,0.7321516443823387,1.0
+2.0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-350_torch.bfloat16_lf,0.7166666666666667,0.7741275713911147,0.7166666666666667,0.7370173522943904,1.0
+0.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct_torch.bfloat16_lf,0.6436666666666667,0.717651042027604,0.6436666666666667,0.6066932578767255,1.0
+0.2,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-35_torch.bfloat16_lf,0.7473333333333333,0.759526705532232,0.7473333333333333,0.7480522291877509,0.998
+0.4,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-70_torch.bfloat16_lf,0.752,0.7774114736945115,0.752,0.7611191332452362,0.9996666666666668
+0.6,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-105_torch.bfloat16_lf,0.7623333333333333,0.7987495507688677,0.7623333333333333,0.7754658001873385,0.9996666666666668
+0.8,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-140_torch.bfloat16_lf,0.7596666666666667,0.7923123268836624,0.7596666666666667,0.7724543387690386,1.0
+1.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-175_torch.bfloat16_lf,0.782,0.8023938029436536,0.782,0.7888740758699296,0.9993333333333332
+1.2,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-210_torch.bfloat16_lf,0.7563333333333333,0.7997527018417315,0.7563333333333333,0.7728761539215637,1.0
+1.4,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-245_torch.bfloat16_lf,0.762,0.7997301280029149,0.762,0.7743858484379207,0.9993333333333332
+1.6,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-280_torch.bfloat16_lf,0.7726666666666666,0.8006851113573145,0.7726666666666666,0.7813968284378919,0.9996666666666668
+1.8,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-315_torch.bfloat16_lf,0.7696666666666667,0.799287702962426,0.7696666666666667,0.7792120245789584,0.9993333333333332
+2.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-350_torch.bfloat16_lf,0.769,0.8010881984531473,0.769,0.7793801070552965,0.9996666666666668
 0.0,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct_torch.bfloat16_4bit_lf,0.7956666666666666,0.8098073411161181,0.7956666666666666,0.7771317592221199,0.994
 0.2,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-35_torch.bfloat16_4bit_lf,0.792,0.8180793658647517,0.792,0.80166512366027,1.0
 0.4,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-70_torch.bfloat16_4bit_lf,0.7716666666666666,0.8199569804721152,0.7716666666666666,0.7895879011938259,1.0

notebooks/00_Data Analysis.ipynb CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3585dace069eccc30163da497132a91cbc0a69803beaab9a1d92e47d8529969e
-size 1067873

 version https://git-lfs.github.com/spec/v1
+oid sha256:83f64886f5f2753fd4bb2ffaa80b6b1cd711854f5479fb223c6ba67afe204ec6
+size 1065121

notebooks/02d_Qwen2.5-7B-Instruct_analysis.ipynb CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0c77fcd9be77a5305398cae5cc24db0bb7eebe24530f1645145fac3982edb0
-size 7876413

 version https://git-lfs.github.com/spec/v1
+oid sha256:b0dff7d4d0e788b1d9c954a3ae1bfefbc972c618dcb3868ceab6868b1ca66611
+size 7864021

notebooks/02e_Qwen2.5-1.5B-Instruct_analysis.ipynb CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea5ef736646432a76a0862b4ace6760d5571910206959b14067652d858ef67f
-size 631284

 version https://git-lfs.github.com/spec/v1
+oid sha256:cee23ede296e87e9fff4736351ec493a48a3881930f7ec6ec882132dfe249c0f
+size 6320983

notebooks/02g_Qwen2.5-72B-Instruct_analysis.ipynb CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b743cd87983573f2661bb649022a9304cedfcf811af22dd2c79fc78109099b56
-size 1663584

 version https://git-lfs.github.com/spec/v1
+oid sha256:a3188eb1c2108d50b16351e9aacb498bd36b6a256cb3a804bfce2eb937811d9c
+size 1663585

notebooks/03a_Llama3.1-8B-Chinese-Chat_analysis.ipynb CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c30bb9917cb847112d1abbec4936826948beada3578bd05853fe2dd67c9fa0c0
-size 6564932

 version https://git-lfs.github.com/spec/v1
+oid sha256:cb8e975c1e831a7958ca09dfe915a9e176fda04c67bb963d572564561255375e
+size 6564713