logical-reasoning / data /fine-tuning_metrics.csv
dh-mc's picture
ready for qwen2.5
d5ab5d2
raw
history blame
12.6 kB
epoch,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
0.0,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat_torch.bfloat16_lf,0.705,0.7398041613378253,0.705,0.6906357423169466,1.0
0.2,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-35_torch.bfloat16_lf,0.7193333333333334,0.7863486093365692,0.7193333333333334,0.7330498811142795,1.0
0.4,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-70_torch.bfloat16_lf,0.726,0.7900250828103491,0.726,0.7396583495246526,1.0
0.6,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-105_torch.bfloat16_lf,0.6736666666666666,0.8044565554629858,0.6736666666666666,0.7104123104529902,1.0
0.8,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-140_torch.bfloat16_lf,0.7496666666666667,0.8041871978859686,0.7496666666666667,0.7660159670998776,1.0
1.0,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-175_torch.bfloat16_lf,0.726,0.8094634420846424,0.726,0.751394838822856,1.0
1.2,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-210_torch.bfloat16_lf,0.7276666666666667,0.8039673699820601,0.7276666666666667,0.7488653386949028,1.0
1.4,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-245_torch.bfloat16_lf,0.747,0.8055537753403307,0.747,0.76527383722639,1.0
1.6,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-280_torch.bfloat16_lf,0.7166666666666667,0.8059535682746547,0.7166666666666667,0.7432427946178835,1.0
1.8,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-315_torch.bfloat16_lf,0.6983333333333334,0.8119110469658597,0.6983333333333334,0.7347246872892312,1.0
2.0,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-350_torch.bfloat16_lf,0.7076666666666667,0.8120132783051135,0.7076666666666667,0.7408145046817652,1.0
0.0,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m_torch.bfloat16_lf,0.4813333333333333,0.7605248207587668,0.4813333333333333,0.5244515621126862,0.9986666666666668
0.2,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-35_torch.bfloat16_lf,0.7843333333333333,0.7977648302848388,0.7843333333333333,0.7864944570659659,1.0
0.4,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-70_torch.bfloat16_lf,0.7836666666666666,0.7996977262947886,0.7836666666666666,0.7886881726841081,1.0
0.6,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-105_torch.bfloat16_lf,0.7243333333333334,0.8171172705912051,0.7243333333333334,0.7565804830382912,1.0
0.8,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-140_torch.bfloat16_lf,0.803,0.8031411888150441,0.803,0.8028064320197301,1.0
1.0,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-175_torch.bfloat16_lf,0.7676666666666667,0.8108441731715863,0.7676666666666667,0.7843187816704813,1.0
1.2,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-210_torch.bfloat16_lf,0.7736666666666666,0.8091671780923799,0.7736666666666666,0.7876874850235454,1.0
1.4,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-245_torch.bfloat16_lf,0.7623333333333333,0.8062291602218205,0.7623333333333333,0.777669094563925,1.0
1.6,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-280_torch.bfloat16_lf,0.7553333333333333,0.8086197936829652,0.7553333333333333,0.7755588811428297,1.0
1.8,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-315_torch.bfloat16_lf,0.748,0.8171996792797457,0.748,0.773990849396903,1.0
2.0,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-350_torch.bfloat16_lf,0.756,0.8126875394266148,0.756,0.7777812522863184,1.0
0.0,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat_torch.bfloat16_4bit_lf,0.564,0.7745256693833624,0.564,0.6352190975436365,0.6726666666666666
0.2,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-35_torch.bfloat16_4bit_lf,0.7576666666666667,0.7960640143421251,0.7576666666666667,0.769346697622254,1.0
0.4,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-70_torch.bfloat16_4bit_lf,0.7743333333333333,0.8042791719587958,0.7743333333333333,0.7849233169481004,1.0
0.6,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-105_torch.bfloat16_4bit_lf,0.7053333333333334,0.8070587351344375,0.7053333333333334,0.7421985241641746,1.0
0.8,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-140_torch.bfloat16_4bit_lf,0.795,0.817457691710893,0.795,0.8027552955647029,1.0
1.0,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-175_torch.bfloat16_4bit_lf,0.7786666666666666,0.8220512342362645,0.7786666666666666,0.7938353741035283,1.0
1.2,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-210_torch.bfloat16_4bit_lf,0.7516666666666667,0.8264680853251051,0.7516666666666667,0.7787088167337303,1.0
1.4,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-245_torch.bfloat16_4bit_lf,0.7876666666666666,0.8154190698395475,0.7876666666666666,0.7965399224841393,1.0
1.6,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-280_torch.bfloat16_4bit_lf,0.7753333333333333,0.8181125383376948,0.7753333333333333,0.7899794199099057,1.0
1.8,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-315_torch.bfloat16_4bit_lf,0.7583333333333333,0.8179523170315577,0.7583333333333333,0.7795358413482081,1.0
2.0,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-350_torch.bfloat16_4bit_lf,0.7616666666666667,0.8208475549648238,0.7616666666666667,0.7826736174247095,1.0
0.0,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct_torch.float16_lf,0.683,0.7493103872717293,0.683,0.710140098232232,0.9996666666666668
0.2,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct/checkpoint-35_torch.float16_lf,0.725,0.7840171468707405,0.725,0.748994536667058,0.9996666666666668
0.4,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct/checkpoint-70_torch.float16_lf,0.759,0.8005303465799652,0.759,0.7748745026535183,1.0
0.6,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct/checkpoint-105_torch.float16_lf,0.6926666666666667,0.8039176975550218,0.6926666666666667,0.7332481528585848,1.0
0.8,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct/checkpoint-140_torch.float16_lf,0.725,0.7952719247171957,0.725,0.7476238017654298,1.0
1.0,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct/checkpoint-175_torch.float16_lf,0.6756666666666666,0.7810148934939715,0.6756666666666666,0.708653993277772,1.0
1.2,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct/checkpoint-210_torch.float16_lf,0.7013333333333334,0.7969562600853992,0.7013333333333334,0.7362679665494508,1.0
1.4,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct/checkpoint-245_torch.float16_lf,0.7326666666666667,0.7922538479314682,0.7326666666666667,0.755402136631717,0.9996666666666668
1.6,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct/checkpoint-280_torch.float16_lf,0.6983333333333334,0.785127298428753,0.6983333333333334,0.7292251109166867,1.0
1.8,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct/checkpoint-315_torch.float16_lf,0.6783333333333333,0.785390767631834,0.6783333333333333,0.7164131321837346,1.0
2.0,Qwen2-7B-Instruct,Qwen/Qwen2-7B-Instruct/checkpoint-350_torch.float16_lf,0.689,0.7929715746898984,0.689,0.7259993126510194,1.0
0.0,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct_torch.bfloat16_4bit_lf,0.7516666666666667,0.7949378981748352,0.7516666666666667,0.7572499605227642,0.9773333333333334
0.2,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct/checkpoint-35_torch.bfloat16_4bit_lf,0.7583333333333333,0.8199928526815756,0.7583333333333333,0.782751089787442,1.0
0.4,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct/checkpoint-70_torch.bfloat16_4bit_lf,0.7366666666666667,0.8224865755517643,0.7366666666666667,0.7700627366337021,1.0
0.6,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct/checkpoint-105_torch.bfloat16_4bit_lf,0.757,0.8253824826209251,0.757,0.784000409833628,1.0
0.8,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct/checkpoint-140_torch.bfloat16_4bit_lf,0.7893333333333333,0.8229104753645825,0.7893333333333333,0.8033124955993173,1.0
1.0,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct/checkpoint-175_torch.bfloat16_4bit_lf,0.7376666666666667,0.8243654864769323,0.7376666666666667,0.7699617360961548,1.0
1.2,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct/checkpoint-210_torch.bfloat16_4bit_lf,0.763,0.8318882808702871,0.763,0.7901075708186186,1.0
1.4,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct/checkpoint-245_torch.bfloat16_4bit_lf,0.7656666666666667,0.8288272203240518,0.7656666666666667,0.790627109330698,1.0
1.6,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct/checkpoint-280_torch.bfloat16_4bit_lf,0.7693333333333333,0.8292798021666021,0.7693333333333333,0.7930169589012503,1.0
1.8,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct/checkpoint-315_torch.bfloat16_4bit_lf,0.784,0.8354349234761956,0.784,0.804194683154365,1.0
2.0,Qwen2-72B-Instruct,Qwen/Qwen2-72B-Instruct/checkpoint-350_torch.bfloat16_4bit_lf,0.7736666666666666,0.8330147983140184,0.7736666666666666,0.7973657072550873,1.0
0.0,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat_torch.float16_lf,0.742,0.7477056799746837,0.742,0.7371050181385632,0.8033333333333333
0.2,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-35_torch.float16_lf,0.709,0.7987219597893886,0.709,0.7427961200958145,1.0
0.4,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-70_torch.float16_lf,0.7163333333333334,0.8058657875960304,0.7163333333333334,0.7487811196109319,0.9993333333333332
0.6,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-105_torch.float16_lf,0.6996666666666667,0.802722482275839,0.6996666666666667,0.7370938556711591,1.0
0.8,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-140_torch.float16_lf,0.7716666666666666,0.8092193821623755,0.7716666666666666,0.7864287269398251,1.0
1.0,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-175_torch.float16_lf,0.78,0.810582723471486,0.78,0.7924651054056209,1.0
1.2,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-210_torch.float16_lf,0.7313333333333333,0.8157783263996798,0.7313333333333333,0.7628807622782868,1.0
1.4,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-245_torch.float16_lf,0.751,0.8125856808988221,0.751,0.7745416635653988,1.0
1.6,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-280_torch.float16_lf,0.739,0.8097375095673094,0.739,0.7662329023371559,1.0
1.8,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-315_torch.float16_lf,0.7236666666666667,0.8145530585912838,0.7236666666666667,0.7580428816095297,1.0
2.0,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-350_torch.float16_lf,0.7293333333333333,0.8151184301713545,0.7293333333333333,0.7616699266814145,1.0
0.0,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat_torch.bfloat16_4bit_lf,0.7636666666666667,0.7806653325131986,0.7636666666666667,0.7525813484548423,0.0096666666666666
0.2,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-35_torch.bfloat16_4bit_lf,0.778,0.8148707737020212,0.778,0.7910805488003003,0.9996666666666668
0.4,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-70_torch.bfloat16_4bit_lf,0.7306666666666667,0.8145782271710159,0.7306666666666667,0.7624724104697406,1.0
0.6,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-105_torch.bfloat16_4bit_lf,0.7193333333333334,0.8213567226911125,0.7193333333333334,0.7560702640626931,1.0
0.8,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-140_torch.bfloat16_4bit_lf,0.7563333333333333,0.826789897753756,0.7563333333333333,0.7815164366677209,1.0
1.0,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-175_torch.bfloat16_4bit_lf,0.7963333333333333,0.8248972880055918,0.7963333333333333,0.8076868978089201,1.0
1.2,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-210_torch.bfloat16_4bit_lf,0.7326666666666667,0.8265345821998035,0.7326666666666667,0.7644418492070342,1.0
1.4,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-245_torch.bfloat16_4bit_lf,0.7556666666666667,0.8258994609525315,0.7556666666666667,0.7820405339757727,1.0
1.6,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-280_torch.bfloat16_4bit_lf,0.757,0.8264461657684251,0.757,0.7834496144681513,1.0
1.8,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-315_torch.bfloat16_4bit_lf,0.7546666666666667,0.8277723752096544,0.7546666666666667,0.7823584779069335,1.0
2.0,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-350_torch.bfloat16_4bit_lf,0.7496666666666667,0.8282310230333227,0.7496666666666667,0.7791947625361637,1.0