Llama-3.7B-Instruct-lora-JR / trainer_state.json
jm02's picture
Upload trainer_state.json with huggingface_hub
ca4f9ff verified
raw
history blame
38.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.9730941704035874,
"eval_steps": 500,
"global_step": 220,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.017937219730941704,
"grad_norm": 1.1350524425506592,
"learning_rate": 4e-05,
"loss": 2.626,
"step": 1
},
{
"epoch": 0.03587443946188341,
"grad_norm": 1.1098030805587769,
"learning_rate": 8e-05,
"loss": 2.564,
"step": 2
},
{
"epoch": 0.053811659192825115,
"grad_norm": 1.004073143005371,
"learning_rate": 0.00012,
"loss": 2.5371,
"step": 3
},
{
"epoch": 0.07174887892376682,
"grad_norm": 1.0235692262649536,
"learning_rate": 0.00016,
"loss": 2.3217,
"step": 4
},
{
"epoch": 0.08968609865470852,
"grad_norm": 0.9896207451820374,
"learning_rate": 0.0002,
"loss": 2.1635,
"step": 5
},
{
"epoch": 0.10762331838565023,
"grad_norm": 1.0160284042358398,
"learning_rate": 0.00019906976744186048,
"loss": 1.9974,
"step": 6
},
{
"epoch": 0.12556053811659193,
"grad_norm": 1.6710572242736816,
"learning_rate": 0.00019813953488372096,
"loss": 1.721,
"step": 7
},
{
"epoch": 0.14349775784753363,
"grad_norm": 1.414752721786499,
"learning_rate": 0.0001972093023255814,
"loss": 1.5117,
"step": 8
},
{
"epoch": 0.16143497757847533,
"grad_norm": 1.0044751167297363,
"learning_rate": 0.00019627906976744185,
"loss": 1.3689,
"step": 9
},
{
"epoch": 0.17937219730941703,
"grad_norm": 0.8621335029602051,
"learning_rate": 0.00019534883720930232,
"loss": 1.3251,
"step": 10
},
{
"epoch": 0.19730941704035873,
"grad_norm": 0.7370575666427612,
"learning_rate": 0.0001944186046511628,
"loss": 1.2459,
"step": 11
},
{
"epoch": 0.21524663677130046,
"grad_norm": 0.7463206648826599,
"learning_rate": 0.00019348837209302326,
"loss": 1.1113,
"step": 12
},
{
"epoch": 0.23318385650224216,
"grad_norm": 0.9221929907798767,
"learning_rate": 0.00019255813953488374,
"loss": 1.1779,
"step": 13
},
{
"epoch": 0.25112107623318386,
"grad_norm": 0.8653731346130371,
"learning_rate": 0.0001916279069767442,
"loss": 1.056,
"step": 14
},
{
"epoch": 0.26905829596412556,
"grad_norm": 0.8368218541145325,
"learning_rate": 0.00019069767441860466,
"loss": 1.0355,
"step": 15
},
{
"epoch": 0.28699551569506726,
"grad_norm": 0.9069833755493164,
"learning_rate": 0.00018976744186046513,
"loss": 1.076,
"step": 16
},
{
"epoch": 0.30493273542600896,
"grad_norm": 1.010295033454895,
"learning_rate": 0.00018883720930232557,
"loss": 1.037,
"step": 17
},
{
"epoch": 0.32286995515695066,
"grad_norm": 0.9165616631507874,
"learning_rate": 0.00018790697674418605,
"loss": 1.0841,
"step": 18
},
{
"epoch": 0.34080717488789236,
"grad_norm": 1.2438362836837769,
"learning_rate": 0.00018697674418604652,
"loss": 0.928,
"step": 19
},
{
"epoch": 0.35874439461883406,
"grad_norm": 1.1386940479278564,
"learning_rate": 0.000186046511627907,
"loss": 0.9742,
"step": 20
},
{
"epoch": 0.37668161434977576,
"grad_norm": 1.0614705085754395,
"learning_rate": 0.00018511627906976744,
"loss": 0.986,
"step": 21
},
{
"epoch": 0.39461883408071746,
"grad_norm": 1.1421048641204834,
"learning_rate": 0.0001841860465116279,
"loss": 0.9306,
"step": 22
},
{
"epoch": 0.4125560538116592,
"grad_norm": 0.9451465606689453,
"learning_rate": 0.00018325581395348838,
"loss": 0.9888,
"step": 23
},
{
"epoch": 0.4304932735426009,
"grad_norm": 0.753145158290863,
"learning_rate": 0.00018232558139534886,
"loss": 0.9598,
"step": 24
},
{
"epoch": 0.4484304932735426,
"grad_norm": 0.6006896495819092,
"learning_rate": 0.0001813953488372093,
"loss": 0.8188,
"step": 25
},
{
"epoch": 0.4663677130044843,
"grad_norm": 0.6499263048171997,
"learning_rate": 0.00018046511627906977,
"loss": 0.9449,
"step": 26
},
{
"epoch": 0.484304932735426,
"grad_norm": 0.6340591907501221,
"learning_rate": 0.00017953488372093025,
"loss": 1.0643,
"step": 27
},
{
"epoch": 0.5022421524663677,
"grad_norm": 0.7478179335594177,
"learning_rate": 0.0001786046511627907,
"loss": 0.9822,
"step": 28
},
{
"epoch": 0.5201793721973094,
"grad_norm": 0.6700637936592102,
"learning_rate": 0.00017767441860465117,
"loss": 0.9793,
"step": 29
},
{
"epoch": 0.5381165919282511,
"grad_norm": 0.6026176810264587,
"learning_rate": 0.00017674418604651164,
"loss": 1.0611,
"step": 30
},
{
"epoch": 0.5560538116591929,
"grad_norm": 0.5661296248435974,
"learning_rate": 0.0001758139534883721,
"loss": 0.9952,
"step": 31
},
{
"epoch": 0.5739910313901345,
"grad_norm": 0.6180285811424255,
"learning_rate": 0.00017488372093023258,
"loss": 0.9497,
"step": 32
},
{
"epoch": 0.5919282511210763,
"grad_norm": 0.6067416667938232,
"learning_rate": 0.00017395348837209303,
"loss": 0.9015,
"step": 33
},
{
"epoch": 0.6098654708520179,
"grad_norm": 0.6353489756584167,
"learning_rate": 0.00017302325581395348,
"loss": 0.9297,
"step": 34
},
{
"epoch": 0.6278026905829597,
"grad_norm": 0.6017511487007141,
"learning_rate": 0.00017209302325581395,
"loss": 0.8634,
"step": 35
},
{
"epoch": 0.6457399103139013,
"grad_norm": 0.701750636100769,
"learning_rate": 0.00017116279069767442,
"loss": 0.9088,
"step": 36
},
{
"epoch": 0.6636771300448431,
"grad_norm": 0.6852689385414124,
"learning_rate": 0.0001702325581395349,
"loss": 0.9195,
"step": 37
},
{
"epoch": 0.6816143497757847,
"grad_norm": 0.6971113681793213,
"learning_rate": 0.00016930232558139537,
"loss": 0.8599,
"step": 38
},
{
"epoch": 0.6995515695067265,
"grad_norm": 0.6576591730117798,
"learning_rate": 0.00016837209302325584,
"loss": 0.764,
"step": 39
},
{
"epoch": 0.7174887892376681,
"grad_norm": 0.8312844038009644,
"learning_rate": 0.00016744186046511629,
"loss": 0.8577,
"step": 40
},
{
"epoch": 0.7354260089686099,
"grad_norm": 0.7586076259613037,
"learning_rate": 0.00016651162790697673,
"loss": 0.8069,
"step": 41
},
{
"epoch": 0.7533632286995515,
"grad_norm": 0.6356410384178162,
"learning_rate": 0.0001655813953488372,
"loss": 0.7753,
"step": 42
},
{
"epoch": 0.7713004484304933,
"grad_norm": 0.6421555280685425,
"learning_rate": 0.00016465116279069768,
"loss": 0.8733,
"step": 43
},
{
"epoch": 0.7892376681614349,
"grad_norm": 0.8002834916114807,
"learning_rate": 0.00016372093023255815,
"loss": 1.0058,
"step": 44
},
{
"epoch": 0.8071748878923767,
"grad_norm": 0.6567667126655579,
"learning_rate": 0.00016279069767441862,
"loss": 0.8771,
"step": 45
},
{
"epoch": 0.8251121076233184,
"grad_norm": 0.5926035642623901,
"learning_rate": 0.00016186046511627907,
"loss": 0.8556,
"step": 46
},
{
"epoch": 0.8430493273542601,
"grad_norm": 0.613197922706604,
"learning_rate": 0.00016093023255813954,
"loss": 0.85,
"step": 47
},
{
"epoch": 0.8609865470852018,
"grad_norm": 0.7108270525932312,
"learning_rate": 0.00016,
"loss": 0.8383,
"step": 48
},
{
"epoch": 0.8789237668161435,
"grad_norm": 0.6039162874221802,
"learning_rate": 0.00015906976744186046,
"loss": 0.898,
"step": 49
},
{
"epoch": 0.8968609865470852,
"grad_norm": 0.6543579697608948,
"learning_rate": 0.00015813953488372093,
"loss": 0.8442,
"step": 50
},
{
"epoch": 0.9147982062780269,
"grad_norm": 0.6246331334114075,
"learning_rate": 0.0001572093023255814,
"loss": 0.7756,
"step": 51
},
{
"epoch": 0.9327354260089686,
"grad_norm": 0.6133050322532654,
"learning_rate": 0.00015627906976744188,
"loss": 0.8701,
"step": 52
},
{
"epoch": 0.9506726457399103,
"grad_norm": 0.6625930070877075,
"learning_rate": 0.00015534883720930232,
"loss": 0.9818,
"step": 53
},
{
"epoch": 0.968609865470852,
"grad_norm": 0.6724585294723511,
"learning_rate": 0.0001544186046511628,
"loss": 0.957,
"step": 54
},
{
"epoch": 0.9865470852017937,
"grad_norm": 0.5864427089691162,
"learning_rate": 0.00015348837209302327,
"loss": 0.7588,
"step": 55
},
{
"epoch": 1.0134529147982063,
"grad_norm": 1.4326505661010742,
"learning_rate": 0.00015255813953488374,
"loss": 1.2876,
"step": 56
},
{
"epoch": 1.031390134529148,
"grad_norm": 0.7354760766029358,
"learning_rate": 0.0001516279069767442,
"loss": 0.6682,
"step": 57
},
{
"epoch": 1.0493273542600896,
"grad_norm": 0.7175352573394775,
"learning_rate": 0.00015069767441860466,
"loss": 0.6862,
"step": 58
},
{
"epoch": 1.0672645739910314,
"grad_norm": 0.7436112761497498,
"learning_rate": 0.0001497674418604651,
"loss": 0.7319,
"step": 59
},
{
"epoch": 1.0852017937219731,
"grad_norm": 0.7228017449378967,
"learning_rate": 0.00014883720930232558,
"loss": 0.842,
"step": 60
},
{
"epoch": 1.1031390134529149,
"grad_norm": 0.7761241793632507,
"learning_rate": 0.00014790697674418605,
"loss": 0.6666,
"step": 61
},
{
"epoch": 1.1210762331838564,
"grad_norm": 0.8203029632568359,
"learning_rate": 0.00014697674418604652,
"loss": 0.7403,
"step": 62
},
{
"epoch": 1.1390134529147982,
"grad_norm": 0.7372130751609802,
"learning_rate": 0.000146046511627907,
"loss": 0.7426,
"step": 63
},
{
"epoch": 1.15695067264574,
"grad_norm": 0.7927672863006592,
"learning_rate": 0.00014511627906976747,
"loss": 0.7717,
"step": 64
},
{
"epoch": 1.1748878923766817,
"grad_norm": 0.7056854367256165,
"learning_rate": 0.00014418604651162791,
"loss": 0.6855,
"step": 65
},
{
"epoch": 1.1928251121076232,
"grad_norm": 0.8383380174636841,
"learning_rate": 0.00014325581395348836,
"loss": 0.7222,
"step": 66
},
{
"epoch": 1.210762331838565,
"grad_norm": 0.6172988414764404,
"learning_rate": 0.00014232558139534883,
"loss": 0.6318,
"step": 67
},
{
"epoch": 1.2286995515695067,
"grad_norm": 0.7639912962913513,
"learning_rate": 0.0001413953488372093,
"loss": 0.6523,
"step": 68
},
{
"epoch": 1.2466367713004485,
"grad_norm": 0.7420268654823303,
"learning_rate": 0.00014046511627906978,
"loss": 0.7358,
"step": 69
},
{
"epoch": 1.2645739910313902,
"grad_norm": 0.781150758266449,
"learning_rate": 0.00013953488372093025,
"loss": 0.6927,
"step": 70
},
{
"epoch": 1.2825112107623318,
"grad_norm": 0.7435458302497864,
"learning_rate": 0.00013860465116279072,
"loss": 0.7508,
"step": 71
},
{
"epoch": 1.3004484304932735,
"grad_norm": 0.7637338042259216,
"learning_rate": 0.00013767441860465117,
"loss": 0.5798,
"step": 72
},
{
"epoch": 1.3183856502242153,
"grad_norm": 0.9575199484825134,
"learning_rate": 0.00013674418604651162,
"loss": 0.8045,
"step": 73
},
{
"epoch": 1.336322869955157,
"grad_norm": 0.836318850517273,
"learning_rate": 0.0001358139534883721,
"loss": 0.7916,
"step": 74
},
{
"epoch": 1.3542600896860986,
"grad_norm": 0.7818664908409119,
"learning_rate": 0.00013488372093023256,
"loss": 0.7037,
"step": 75
},
{
"epoch": 1.3721973094170403,
"grad_norm": 0.7612494826316833,
"learning_rate": 0.00013395348837209303,
"loss": 0.6847,
"step": 76
},
{
"epoch": 1.390134529147982,
"grad_norm": 0.6829874515533447,
"learning_rate": 0.0001330232558139535,
"loss": 0.6848,
"step": 77
},
{
"epoch": 1.4080717488789238,
"grad_norm": 0.6923062801361084,
"learning_rate": 0.00013209302325581395,
"loss": 0.6928,
"step": 78
},
{
"epoch": 1.4260089686098656,
"grad_norm": 0.6936827898025513,
"learning_rate": 0.00013116279069767442,
"loss": 0.8813,
"step": 79
},
{
"epoch": 1.4439461883408071,
"grad_norm": 0.7367523908615112,
"learning_rate": 0.0001302325581395349,
"loss": 0.7386,
"step": 80
},
{
"epoch": 1.4618834080717489,
"grad_norm": 0.7084159255027771,
"learning_rate": 0.00012930232558139534,
"loss": 0.604,
"step": 81
},
{
"epoch": 1.4798206278026906,
"grad_norm": 0.817794144153595,
"learning_rate": 0.00012837209302325582,
"loss": 0.7644,
"step": 82
},
{
"epoch": 1.4977578475336322,
"grad_norm": 0.7807640433311462,
"learning_rate": 0.0001274418604651163,
"loss": 0.8061,
"step": 83
},
{
"epoch": 1.515695067264574,
"grad_norm": 0.7616767883300781,
"learning_rate": 0.00012651162790697676,
"loss": 0.7786,
"step": 84
},
{
"epoch": 1.5336322869955157,
"grad_norm": 0.7925138473510742,
"learning_rate": 0.0001255813953488372,
"loss": 0.6859,
"step": 85
},
{
"epoch": 1.5515695067264574,
"grad_norm": 0.7205699682235718,
"learning_rate": 0.00012465116279069768,
"loss": 0.7581,
"step": 86
},
{
"epoch": 1.5695067264573992,
"grad_norm": 0.6984810829162598,
"learning_rate": 0.00012372093023255815,
"loss": 0.6652,
"step": 87
},
{
"epoch": 1.587443946188341,
"grad_norm": 0.7267066836357117,
"learning_rate": 0.00012279069767441863,
"loss": 0.6419,
"step": 88
},
{
"epoch": 1.6053811659192825,
"grad_norm": 0.7686505913734436,
"learning_rate": 0.00012186046511627907,
"loss": 0.7497,
"step": 89
},
{
"epoch": 1.6233183856502242,
"grad_norm": 0.755163311958313,
"learning_rate": 0.00012093023255813953,
"loss": 0.7757,
"step": 90
},
{
"epoch": 1.6412556053811658,
"grad_norm": 0.7927355766296387,
"learning_rate": 0.00012,
"loss": 0.7754,
"step": 91
},
{
"epoch": 1.6591928251121075,
"grad_norm": 0.6950364708900452,
"learning_rate": 0.00011906976744186048,
"loss": 0.6059,
"step": 92
},
{
"epoch": 1.6771300448430493,
"grad_norm": 0.7365448474884033,
"learning_rate": 0.00011813953488372094,
"loss": 0.673,
"step": 93
},
{
"epoch": 1.695067264573991,
"grad_norm": 0.7940488457679749,
"learning_rate": 0.00011720930232558141,
"loss": 0.5726,
"step": 94
},
{
"epoch": 1.7130044843049328,
"grad_norm": 0.8307069540023804,
"learning_rate": 0.00011627906976744187,
"loss": 0.6949,
"step": 95
},
{
"epoch": 1.7309417040358746,
"grad_norm": 0.876649796962738,
"learning_rate": 0.00011534883720930234,
"loss": 0.6415,
"step": 96
},
{
"epoch": 1.7488789237668163,
"grad_norm": 0.9207577109336853,
"learning_rate": 0.00011441860465116279,
"loss": 0.674,
"step": 97
},
{
"epoch": 1.7668161434977578,
"grad_norm": 0.8050037026405334,
"learning_rate": 0.00011348837209302326,
"loss": 0.5656,
"step": 98
},
{
"epoch": 1.7847533632286996,
"grad_norm": 0.878441333770752,
"learning_rate": 0.00011255813953488372,
"loss": 0.7596,
"step": 99
},
{
"epoch": 1.8026905829596411,
"grad_norm": 0.91168612241745,
"learning_rate": 0.00011162790697674419,
"loss": 0.8177,
"step": 100
},
{
"epoch": 1.8206278026905829,
"grad_norm": 0.7757384777069092,
"learning_rate": 0.00011069767441860466,
"loss": 0.652,
"step": 101
},
{
"epoch": 1.8385650224215246,
"grad_norm": 0.8266631960868835,
"learning_rate": 0.00010976744186046512,
"loss": 0.8207,
"step": 102
},
{
"epoch": 1.8565022421524664,
"grad_norm": 0.7787818312644958,
"learning_rate": 0.0001088372093023256,
"loss": 0.6802,
"step": 103
},
{
"epoch": 1.8744394618834082,
"grad_norm": 0.8642717003822327,
"learning_rate": 0.00010790697674418607,
"loss": 0.7011,
"step": 104
},
{
"epoch": 1.89237668161435,
"grad_norm": 0.7537955641746521,
"learning_rate": 0.00010697674418604651,
"loss": 0.6297,
"step": 105
},
{
"epoch": 1.9103139013452914,
"grad_norm": 0.8498083353042603,
"learning_rate": 0.00010604651162790697,
"loss": 0.6764,
"step": 106
},
{
"epoch": 1.9282511210762332,
"grad_norm": 0.8197365403175354,
"learning_rate": 0.00010511627906976745,
"loss": 0.7126,
"step": 107
},
{
"epoch": 1.9461883408071747,
"grad_norm": 0.797406792640686,
"learning_rate": 0.0001041860465116279,
"loss": 0.7664,
"step": 108
},
{
"epoch": 1.9641255605381165,
"grad_norm": 0.8513347506523132,
"learning_rate": 0.00010325581395348838,
"loss": 0.7572,
"step": 109
},
{
"epoch": 1.9820627802690582,
"grad_norm": 0.8408546447753906,
"learning_rate": 0.00010232558139534885,
"loss": 0.5291,
"step": 110
},
{
"epoch": 2.008968609865471,
"grad_norm": 1.9233133792877197,
"learning_rate": 0.00010139534883720931,
"loss": 1.3532,
"step": 111
},
{
"epoch": 2.0269058295964126,
"grad_norm": 0.782871663570404,
"learning_rate": 0.00010046511627906978,
"loss": 0.4679,
"step": 112
},
{
"epoch": 2.0448430493273544,
"grad_norm": 0.7588692307472229,
"learning_rate": 9.953488372093024e-05,
"loss": 0.4962,
"step": 113
},
{
"epoch": 2.062780269058296,
"grad_norm": 0.8635579943656921,
"learning_rate": 9.86046511627907e-05,
"loss": 0.474,
"step": 114
},
{
"epoch": 2.0807174887892375,
"grad_norm": 0.8822935819625854,
"learning_rate": 9.767441860465116e-05,
"loss": 0.4129,
"step": 115
},
{
"epoch": 2.098654708520179,
"grad_norm": 0.9706945419311523,
"learning_rate": 9.674418604651163e-05,
"loss": 0.4961,
"step": 116
},
{
"epoch": 2.116591928251121,
"grad_norm": 1.1239269971847534,
"learning_rate": 9.58139534883721e-05,
"loss": 0.5805,
"step": 117
},
{
"epoch": 2.1345291479820627,
"grad_norm": 1.1263116598129272,
"learning_rate": 9.488372093023256e-05,
"loss": 0.4252,
"step": 118
},
{
"epoch": 2.1524663677130045,
"grad_norm": 1.2772897481918335,
"learning_rate": 9.395348837209302e-05,
"loss": 0.4534,
"step": 119
},
{
"epoch": 2.1704035874439462,
"grad_norm": 1.0017895698547363,
"learning_rate": 9.30232558139535e-05,
"loss": 0.3835,
"step": 120
},
{
"epoch": 2.188340807174888,
"grad_norm": 1.1340886354446411,
"learning_rate": 9.209302325581396e-05,
"loss": 0.4089,
"step": 121
},
{
"epoch": 2.2062780269058297,
"grad_norm": 1.011704921722412,
"learning_rate": 9.116279069767443e-05,
"loss": 0.4298,
"step": 122
},
{
"epoch": 2.2242152466367715,
"grad_norm": 0.9829872250556946,
"learning_rate": 9.023255813953489e-05,
"loss": 0.4568,
"step": 123
},
{
"epoch": 2.242152466367713,
"grad_norm": 1.0418094396591187,
"learning_rate": 8.930232558139535e-05,
"loss": 0.5086,
"step": 124
},
{
"epoch": 2.2600896860986546,
"grad_norm": 0.9814426302909851,
"learning_rate": 8.837209302325582e-05,
"loss": 0.5033,
"step": 125
},
{
"epoch": 2.2780269058295963,
"grad_norm": 1.0506559610366821,
"learning_rate": 8.744186046511629e-05,
"loss": 0.455,
"step": 126
},
{
"epoch": 2.295964125560538,
"grad_norm": 0.9949473738670349,
"learning_rate": 8.651162790697674e-05,
"loss": 0.4637,
"step": 127
},
{
"epoch": 2.31390134529148,
"grad_norm": 1.0186420679092407,
"learning_rate": 8.558139534883721e-05,
"loss": 0.4877,
"step": 128
},
{
"epoch": 2.3318385650224216,
"grad_norm": 1.0602444410324097,
"learning_rate": 8.465116279069768e-05,
"loss": 0.4941,
"step": 129
},
{
"epoch": 2.3497757847533634,
"grad_norm": 1.0107648372650146,
"learning_rate": 8.372093023255814e-05,
"loss": 0.4339,
"step": 130
},
{
"epoch": 2.367713004484305,
"grad_norm": 1.1475372314453125,
"learning_rate": 8.27906976744186e-05,
"loss": 0.5158,
"step": 131
},
{
"epoch": 2.3856502242152464,
"grad_norm": 1.0330064296722412,
"learning_rate": 8.186046511627907e-05,
"loss": 0.4266,
"step": 132
},
{
"epoch": 2.403587443946188,
"grad_norm": 1.3457512855529785,
"learning_rate": 8.093023255813953e-05,
"loss": 0.617,
"step": 133
},
{
"epoch": 2.42152466367713,
"grad_norm": 1.1562917232513428,
"learning_rate": 8e-05,
"loss": 0.4976,
"step": 134
},
{
"epoch": 2.4394618834080717,
"grad_norm": 1.087751030921936,
"learning_rate": 7.906976744186047e-05,
"loss": 0.4836,
"step": 135
},
{
"epoch": 2.4573991031390134,
"grad_norm": 1.0045045614242554,
"learning_rate": 7.813953488372094e-05,
"loss": 0.4294,
"step": 136
},
{
"epoch": 2.475336322869955,
"grad_norm": 1.0355446338653564,
"learning_rate": 7.72093023255814e-05,
"loss": 0.4472,
"step": 137
},
{
"epoch": 2.493273542600897,
"grad_norm": 1.163203239440918,
"learning_rate": 7.627906976744187e-05,
"loss": 0.4853,
"step": 138
},
{
"epoch": 2.5112107623318387,
"grad_norm": 1.0705980062484741,
"learning_rate": 7.534883720930233e-05,
"loss": 0.4142,
"step": 139
},
{
"epoch": 2.5291479820627805,
"grad_norm": 1.172975778579712,
"learning_rate": 7.441860465116279e-05,
"loss": 0.5348,
"step": 140
},
{
"epoch": 2.547085201793722,
"grad_norm": 0.9890033006668091,
"learning_rate": 7.348837209302326e-05,
"loss": 0.3867,
"step": 141
},
{
"epoch": 2.5650224215246635,
"grad_norm": 1.3716145753860474,
"learning_rate": 7.255813953488373e-05,
"loss": 0.4829,
"step": 142
},
{
"epoch": 2.5829596412556053,
"grad_norm": 1.1363354921340942,
"learning_rate": 7.162790697674418e-05,
"loss": 0.4112,
"step": 143
},
{
"epoch": 2.600896860986547,
"grad_norm": 1.180514931678772,
"learning_rate": 7.069767441860465e-05,
"loss": 0.4212,
"step": 144
},
{
"epoch": 2.618834080717489,
"grad_norm": 1.1589065790176392,
"learning_rate": 6.976744186046513e-05,
"loss": 0.4382,
"step": 145
},
{
"epoch": 2.6367713004484306,
"grad_norm": 1.1208486557006836,
"learning_rate": 6.883720930232558e-05,
"loss": 0.4852,
"step": 146
},
{
"epoch": 2.6547085201793723,
"grad_norm": 1.1670925617218018,
"learning_rate": 6.790697674418604e-05,
"loss": 0.4801,
"step": 147
},
{
"epoch": 2.672645739910314,
"grad_norm": 1.1497890949249268,
"learning_rate": 6.697674418604652e-05,
"loss": 0.4581,
"step": 148
},
{
"epoch": 2.6905829596412554,
"grad_norm": 1.1380338668823242,
"learning_rate": 6.604651162790698e-05,
"loss": 0.4974,
"step": 149
},
{
"epoch": 2.708520179372197,
"grad_norm": 1.2095478773117065,
"learning_rate": 6.511627906976745e-05,
"loss": 0.4958,
"step": 150
},
{
"epoch": 2.726457399103139,
"grad_norm": 1.1369256973266602,
"learning_rate": 6.418604651162791e-05,
"loss": 0.4518,
"step": 151
},
{
"epoch": 2.7443946188340806,
"grad_norm": 1.1578013896942139,
"learning_rate": 6.325581395348838e-05,
"loss": 0.5655,
"step": 152
},
{
"epoch": 2.7623318385650224,
"grad_norm": 1.0805268287658691,
"learning_rate": 6.232558139534884e-05,
"loss": 0.5004,
"step": 153
},
{
"epoch": 2.780269058295964,
"grad_norm": 1.1408129930496216,
"learning_rate": 6.139534883720931e-05,
"loss": 0.4059,
"step": 154
},
{
"epoch": 2.798206278026906,
"grad_norm": 1.0206074714660645,
"learning_rate": 6.0465116279069765e-05,
"loss": 0.4119,
"step": 155
},
{
"epoch": 2.8161434977578477,
"grad_norm": 0.9685718417167664,
"learning_rate": 5.953488372093024e-05,
"loss": 0.4574,
"step": 156
},
{
"epoch": 2.8340807174887894,
"grad_norm": 1.0425866842269897,
"learning_rate": 5.8604651162790704e-05,
"loss": 0.4774,
"step": 157
},
{
"epoch": 2.852017937219731,
"grad_norm": 1.0325255393981934,
"learning_rate": 5.767441860465117e-05,
"loss": 0.4317,
"step": 158
},
{
"epoch": 2.8699551569506725,
"grad_norm": 1.0784574747085571,
"learning_rate": 5.674418604651163e-05,
"loss": 0.3921,
"step": 159
},
{
"epoch": 2.8878923766816142,
"grad_norm": 1.081007957458496,
"learning_rate": 5.5813953488372095e-05,
"loss": 0.4515,
"step": 160
},
{
"epoch": 2.905829596412556,
"grad_norm": 1.1916303634643555,
"learning_rate": 5.488372093023256e-05,
"loss": 0.4556,
"step": 161
},
{
"epoch": 2.9237668161434978,
"grad_norm": 1.2342188358306885,
"learning_rate": 5.3953488372093034e-05,
"loss": 0.4772,
"step": 162
},
{
"epoch": 2.9417040358744395,
"grad_norm": 1.0315567255020142,
"learning_rate": 5.3023255813953486e-05,
"loss": 0.3233,
"step": 163
},
{
"epoch": 2.9596412556053813,
"grad_norm": 1.3380693197250366,
"learning_rate": 5.209302325581395e-05,
"loss": 0.5098,
"step": 164
},
{
"epoch": 2.977578475336323,
"grad_norm": 1.2268236875534058,
"learning_rate": 5.1162790697674425e-05,
"loss": 0.4125,
"step": 165
},
{
"epoch": 3.004484304932735,
"grad_norm": 2.589136838912964,
"learning_rate": 5.023255813953489e-05,
"loss": 0.7637,
"step": 166
},
{
"epoch": 3.022421524663677,
"grad_norm": 0.9620673060417175,
"learning_rate": 4.930232558139535e-05,
"loss": 0.2501,
"step": 167
},
{
"epoch": 3.0403587443946187,
"grad_norm": 1.0851328372955322,
"learning_rate": 4.8372093023255816e-05,
"loss": 0.3299,
"step": 168
},
{
"epoch": 3.0582959641255605,
"grad_norm": 1.081047773361206,
"learning_rate": 4.744186046511628e-05,
"loss": 0.319,
"step": 169
},
{
"epoch": 3.0762331838565022,
"grad_norm": 0.9016939997673035,
"learning_rate": 4.651162790697675e-05,
"loss": 0.2505,
"step": 170
},
{
"epoch": 3.094170403587444,
"grad_norm": 1.279685616493225,
"learning_rate": 4.5581395348837214e-05,
"loss": 0.3574,
"step": 171
},
{
"epoch": 3.1121076233183858,
"grad_norm": 1.1288567781448364,
"learning_rate": 4.465116279069767e-05,
"loss": 0.2322,
"step": 172
},
{
"epoch": 3.1300448430493275,
"grad_norm": 1.0982707738876343,
"learning_rate": 4.3720930232558146e-05,
"loss": 0.2557,
"step": 173
},
{
"epoch": 3.1479820627802693,
"grad_norm": 1.2716487646102905,
"learning_rate": 4.2790697674418605e-05,
"loss": 0.2683,
"step": 174
},
{
"epoch": 3.1659192825112106,
"grad_norm": 1.277907371520996,
"learning_rate": 4.186046511627907e-05,
"loss": 0.3359,
"step": 175
},
{
"epoch": 3.1838565022421523,
"grad_norm": 1.767809510231018,
"learning_rate": 4.093023255813954e-05,
"loss": 0.3141,
"step": 176
},
{
"epoch": 3.201793721973094,
"grad_norm": 1.5723196268081665,
"learning_rate": 4e-05,
"loss": 0.2696,
"step": 177
},
{
"epoch": 3.219730941704036,
"grad_norm": 1.2438582181930542,
"learning_rate": 3.906976744186047e-05,
"loss": 0.2261,
"step": 178
},
{
"epoch": 3.2376681614349776,
"grad_norm": 1.3772393465042114,
"learning_rate": 3.8139534883720935e-05,
"loss": 0.2699,
"step": 179
},
{
"epoch": 3.2556053811659194,
"grad_norm": 1.1731289625167847,
"learning_rate": 3.7209302325581394e-05,
"loss": 0.2809,
"step": 180
},
{
"epoch": 3.273542600896861,
"grad_norm": 1.3203359842300415,
"learning_rate": 3.627906976744187e-05,
"loss": 0.2798,
"step": 181
},
{
"epoch": 3.291479820627803,
"grad_norm": 1.0982232093811035,
"learning_rate": 3.5348837209302326e-05,
"loss": 0.2503,
"step": 182
},
{
"epoch": 3.3094170403587446,
"grad_norm": 1.2753369808197021,
"learning_rate": 3.441860465116279e-05,
"loss": 0.2893,
"step": 183
},
{
"epoch": 3.327354260089686,
"grad_norm": 1.2293989658355713,
"learning_rate": 3.348837209302326e-05,
"loss": 0.2585,
"step": 184
},
{
"epoch": 3.3452914798206277,
"grad_norm": 1.3043240308761597,
"learning_rate": 3.2558139534883724e-05,
"loss": 0.2203,
"step": 185
},
{
"epoch": 3.3632286995515694,
"grad_norm": 1.1034027338027954,
"learning_rate": 3.162790697674419e-05,
"loss": 0.2501,
"step": 186
},
{
"epoch": 3.381165919282511,
"grad_norm": 0.9731037020683289,
"learning_rate": 3.0697674418604656e-05,
"loss": 0.1944,
"step": 187
},
{
"epoch": 3.399103139013453,
"grad_norm": 1.069287657737732,
"learning_rate": 2.976744186046512e-05,
"loss": 0.2041,
"step": 188
},
{
"epoch": 3.4170403587443947,
"grad_norm": 1.3233182430267334,
"learning_rate": 2.8837209302325585e-05,
"loss": 0.2713,
"step": 189
},
{
"epoch": 3.4349775784753365,
"grad_norm": 1.2428154945373535,
"learning_rate": 2.7906976744186048e-05,
"loss": 0.2002,
"step": 190
},
{
"epoch": 3.452914798206278,
"grad_norm": 1.20328688621521,
"learning_rate": 2.6976744186046517e-05,
"loss": 0.2646,
"step": 191
},
{
"epoch": 3.4708520179372195,
"grad_norm": 1.3479125499725342,
"learning_rate": 2.6046511627906976e-05,
"loss": 0.2911,
"step": 192
},
{
"epoch": 3.4887892376681613,
"grad_norm": 1.2266180515289307,
"learning_rate": 2.5116279069767445e-05,
"loss": 0.2811,
"step": 193
},
{
"epoch": 3.506726457399103,
"grad_norm": 1.2345128059387207,
"learning_rate": 2.4186046511627908e-05,
"loss": 0.2237,
"step": 194
},
{
"epoch": 3.524663677130045,
"grad_norm": 1.3437424898147583,
"learning_rate": 2.3255813953488374e-05,
"loss": 0.283,
"step": 195
},
{
"epoch": 3.5426008968609866,
"grad_norm": 1.4216517210006714,
"learning_rate": 2.2325581395348837e-05,
"loss": 0.2871,
"step": 196
},
{
"epoch": 3.5605381165919283,
"grad_norm": 1.1113003492355347,
"learning_rate": 2.1395348837209303e-05,
"loss": 0.219,
"step": 197
},
{
"epoch": 3.57847533632287,
"grad_norm": 1.592371940612793,
"learning_rate": 2.046511627906977e-05,
"loss": 0.3161,
"step": 198
},
{
"epoch": 3.596412556053812,
"grad_norm": 1.2963297367095947,
"learning_rate": 1.9534883720930235e-05,
"loss": 0.2242,
"step": 199
},
{
"epoch": 3.6143497757847536,
"grad_norm": 1.1588383913040161,
"learning_rate": 1.8604651162790697e-05,
"loss": 0.2079,
"step": 200
},
{
"epoch": 3.6322869955156953,
"grad_norm": 1.2683604955673218,
"learning_rate": 1.7674418604651163e-05,
"loss": 0.2501,
"step": 201
},
{
"epoch": 3.6502242152466366,
"grad_norm": 1.3655322790145874,
"learning_rate": 1.674418604651163e-05,
"loss": 0.2299,
"step": 202
},
{
"epoch": 3.6681614349775784,
"grad_norm": 1.3018665313720703,
"learning_rate": 1.5813953488372095e-05,
"loss": 0.2148,
"step": 203
},
{
"epoch": 3.68609865470852,
"grad_norm": 1.388330101966858,
"learning_rate": 1.488372093023256e-05,
"loss": 0.2512,
"step": 204
},
{
"epoch": 3.704035874439462,
"grad_norm": 1.535142421722412,
"learning_rate": 1.3953488372093024e-05,
"loss": 0.2579,
"step": 205
},
{
"epoch": 3.7219730941704037,
"grad_norm": 1.4287734031677246,
"learning_rate": 1.3023255813953488e-05,
"loss": 0.2708,
"step": 206
},
{
"epoch": 3.7399103139013454,
"grad_norm": 1.5674840211868286,
"learning_rate": 1.2093023255813954e-05,
"loss": 0.3017,
"step": 207
},
{
"epoch": 3.7578475336322867,
"grad_norm": 1.261733889579773,
"learning_rate": 1.1162790697674418e-05,
"loss": 0.2584,
"step": 208
},
{
"epoch": 3.7757847533632285,
"grad_norm": 1.4881441593170166,
"learning_rate": 1.0232558139534884e-05,
"loss": 0.3086,
"step": 209
},
{
"epoch": 3.7937219730941703,
"grad_norm": 1.1449949741363525,
"learning_rate": 9.302325581395349e-06,
"loss": 0.2277,
"step": 210
},
{
"epoch": 3.811659192825112,
"grad_norm": 1.3948498964309692,
"learning_rate": 8.372093023255815e-06,
"loss": 0.2668,
"step": 211
},
{
"epoch": 3.8295964125560538,
"grad_norm": 1.1462297439575195,
"learning_rate": 7.44186046511628e-06,
"loss": 0.2142,
"step": 212
},
{
"epoch": 3.8475336322869955,
"grad_norm": 1.4967782497406006,
"learning_rate": 6.511627906976744e-06,
"loss": 0.275,
"step": 213
},
{
"epoch": 3.8654708520179373,
"grad_norm": 1.3958649635314941,
"learning_rate": 5.581395348837209e-06,
"loss": 0.2833,
"step": 214
},
{
"epoch": 3.883408071748879,
"grad_norm": 1.4644280672073364,
"learning_rate": 4.651162790697674e-06,
"loss": 0.3475,
"step": 215
},
{
"epoch": 3.901345291479821,
"grad_norm": 1.3760302066802979,
"learning_rate": 3.72093023255814e-06,
"loss": 0.2892,
"step": 216
},
{
"epoch": 3.9192825112107625,
"grad_norm": 1.320532202720642,
"learning_rate": 2.7906976744186046e-06,
"loss": 0.2542,
"step": 217
},
{
"epoch": 3.9372197309417043,
"grad_norm": 1.1825841665267944,
"learning_rate": 1.86046511627907e-06,
"loss": 0.2306,
"step": 218
},
{
"epoch": 3.9551569506726456,
"grad_norm": 1.3918488025665283,
"learning_rate": 9.30232558139535e-07,
"loss": 0.2958,
"step": 219
},
{
"epoch": 3.9730941704035874,
"grad_norm": 1.3532480001449585,
"learning_rate": 0.0,
"loss": 0.2748,
"step": 220
}
],
"logging_steps": 1,
"max_steps": 220,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 9925730977234944.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}