bbytxt's picture
Training in progress, step 150, checkpoint
60869f2 verified
raw
history blame
27.7 kB
{
"best_metric": 0.3055230975151062,
"best_model_checkpoint": "miner_id_24/checkpoint-150",
"epoch": 0.15535991714137753,
"eval_steps": 50,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0010357327809425167,
"grad_norm": 2.934951066970825,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.3458,
"step": 1
},
{
"epoch": 0.0010357327809425167,
"eval_loss": 2.4307608604431152,
"eval_runtime": 131.1348,
"eval_samples_per_second": 12.399,
"eval_steps_per_second": 6.2,
"step": 1
},
{
"epoch": 0.0020714655618850335,
"grad_norm": 3.631234884262085,
"learning_rate": 6.666666666666667e-06,
"loss": 1.5473,
"step": 2
},
{
"epoch": 0.0031071983428275505,
"grad_norm": 3.7098679542541504,
"learning_rate": 1e-05,
"loss": 1.7358,
"step": 3
},
{
"epoch": 0.004142931123770067,
"grad_norm": 4.27931547164917,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.3322,
"step": 4
},
{
"epoch": 0.005178663904712584,
"grad_norm": 4.007849216461182,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.5253,
"step": 5
},
{
"epoch": 0.006214396685655101,
"grad_norm": 5.52664041519165,
"learning_rate": 2e-05,
"loss": 1.8545,
"step": 6
},
{
"epoch": 0.0072501294665976174,
"grad_norm": 3.834798574447632,
"learning_rate": 2.3333333333333336e-05,
"loss": 1.3665,
"step": 7
},
{
"epoch": 0.008285862247540134,
"grad_norm": 3.7450332641601562,
"learning_rate": 2.6666666666666667e-05,
"loss": 1.3339,
"step": 8
},
{
"epoch": 0.009321595028482652,
"grad_norm": 3.6901252269744873,
"learning_rate": 3e-05,
"loss": 1.4489,
"step": 9
},
{
"epoch": 0.010357327809425169,
"grad_norm": 3.269052505493164,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.9925,
"step": 10
},
{
"epoch": 0.011393060590367685,
"grad_norm": 3.4667394161224365,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.0799,
"step": 11
},
{
"epoch": 0.012428793371310202,
"grad_norm": 4.5746917724609375,
"learning_rate": 4e-05,
"loss": 1.0442,
"step": 12
},
{
"epoch": 0.013464526152252718,
"grad_norm": 3.5450432300567627,
"learning_rate": 4.3333333333333334e-05,
"loss": 0.9699,
"step": 13
},
{
"epoch": 0.014500258933195235,
"grad_norm": 2.999580144882202,
"learning_rate": 4.666666666666667e-05,
"loss": 0.8588,
"step": 14
},
{
"epoch": 0.015535991714137753,
"grad_norm": 2.0789074897766113,
"learning_rate": 5e-05,
"loss": 0.7789,
"step": 15
},
{
"epoch": 0.016571724495080268,
"grad_norm": 2.5798442363739014,
"learning_rate": 5.333333333333333e-05,
"loss": 0.7985,
"step": 16
},
{
"epoch": 0.017607457276022784,
"grad_norm": 2.789106607437134,
"learning_rate": 5.666666666666667e-05,
"loss": 0.8539,
"step": 17
},
{
"epoch": 0.018643190056965304,
"grad_norm": 2.157308578491211,
"learning_rate": 6e-05,
"loss": 0.7339,
"step": 18
},
{
"epoch": 0.01967892283790782,
"grad_norm": 2.024956464767456,
"learning_rate": 6.333333333333333e-05,
"loss": 0.6393,
"step": 19
},
{
"epoch": 0.020714655618850338,
"grad_norm": 2.095165967941284,
"learning_rate": 6.666666666666667e-05,
"loss": 0.7112,
"step": 20
},
{
"epoch": 0.021750388399792854,
"grad_norm": 2.395766258239746,
"learning_rate": 7e-05,
"loss": 0.5803,
"step": 21
},
{
"epoch": 0.02278612118073537,
"grad_norm": 1.9139028787612915,
"learning_rate": 7.333333333333333e-05,
"loss": 0.5602,
"step": 22
},
{
"epoch": 0.023821853961677887,
"grad_norm": 1.8153733015060425,
"learning_rate": 7.666666666666667e-05,
"loss": 0.5852,
"step": 23
},
{
"epoch": 0.024857586742620404,
"grad_norm": 1.7927237749099731,
"learning_rate": 8e-05,
"loss": 0.5787,
"step": 24
},
{
"epoch": 0.02589331952356292,
"grad_norm": 2.2322211265563965,
"learning_rate": 8.333333333333334e-05,
"loss": 0.7009,
"step": 25
},
{
"epoch": 0.026929052304505437,
"grad_norm": 1.8694380521774292,
"learning_rate": 8.666666666666667e-05,
"loss": 0.6042,
"step": 26
},
{
"epoch": 0.027964785085447953,
"grad_norm": 1.5141125917434692,
"learning_rate": 9e-05,
"loss": 0.5847,
"step": 27
},
{
"epoch": 0.02900051786639047,
"grad_norm": 1.4388060569763184,
"learning_rate": 9.333333333333334e-05,
"loss": 0.533,
"step": 28
},
{
"epoch": 0.03003625064733299,
"grad_norm": 1.4760385751724243,
"learning_rate": 9.666666666666667e-05,
"loss": 0.4269,
"step": 29
},
{
"epoch": 0.031071983428275506,
"grad_norm": 1.4737350940704346,
"learning_rate": 0.0001,
"loss": 0.3929,
"step": 30
},
{
"epoch": 0.03210771620921802,
"grad_norm": 1.3517489433288574,
"learning_rate": 9.999146252290264e-05,
"loss": 0.4369,
"step": 31
},
{
"epoch": 0.033143448990160536,
"grad_norm": 1.7029956579208374,
"learning_rate": 9.996585300715116e-05,
"loss": 0.453,
"step": 32
},
{
"epoch": 0.03417918177110305,
"grad_norm": 2.4142861366271973,
"learning_rate": 9.99231801983717e-05,
"loss": 0.5166,
"step": 33
},
{
"epoch": 0.03521491455204557,
"grad_norm": 1.5307400226593018,
"learning_rate": 9.986345866928941e-05,
"loss": 0.4085,
"step": 34
},
{
"epoch": 0.03625064733298809,
"grad_norm": 1.6694791316986084,
"learning_rate": 9.978670881475172e-05,
"loss": 0.2848,
"step": 35
},
{
"epoch": 0.03728638011393061,
"grad_norm": 0.9046441316604614,
"learning_rate": 9.96929568447637e-05,
"loss": 0.1912,
"step": 36
},
{
"epoch": 0.038322112894873125,
"grad_norm": 1.6716495752334595,
"learning_rate": 9.958223477553714e-05,
"loss": 0.632,
"step": 37
},
{
"epoch": 0.03935784567581564,
"grad_norm": 2.2129456996917725,
"learning_rate": 9.94545804185573e-05,
"loss": 0.8857,
"step": 38
},
{
"epoch": 0.04039357845675816,
"grad_norm": 3.774207592010498,
"learning_rate": 9.931003736767013e-05,
"loss": 1.4254,
"step": 39
},
{
"epoch": 0.041429311237700675,
"grad_norm": 1.758363127708435,
"learning_rate": 9.91486549841951e-05,
"loss": 0.8625,
"step": 40
},
{
"epoch": 0.04246504401864319,
"grad_norm": 1.6825367212295532,
"learning_rate": 9.89704883800683e-05,
"loss": 0.6659,
"step": 41
},
{
"epoch": 0.04350077679958571,
"grad_norm": 1.9193270206451416,
"learning_rate": 9.877559839902184e-05,
"loss": 0.5724,
"step": 42
},
{
"epoch": 0.044536509580528225,
"grad_norm": 1.610196828842163,
"learning_rate": 9.85640515958057e-05,
"loss": 0.5503,
"step": 43
},
{
"epoch": 0.04557224236147074,
"grad_norm": 1.7814068794250488,
"learning_rate": 9.833592021345937e-05,
"loss": 0.4417,
"step": 44
},
{
"epoch": 0.04660797514241326,
"grad_norm": 1.386198878288269,
"learning_rate": 9.809128215864097e-05,
"loss": 0.3452,
"step": 45
},
{
"epoch": 0.047643707923355774,
"grad_norm": 1.408173680305481,
"learning_rate": 9.783022097502204e-05,
"loss": 0.259,
"step": 46
},
{
"epoch": 0.04867944070429829,
"grad_norm": 4.415549278259277,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9239,
"step": 47
},
{
"epoch": 0.04971517348524081,
"grad_norm": 3.1557812690734863,
"learning_rate": 9.725919140804099e-05,
"loss": 0.8021,
"step": 48
},
{
"epoch": 0.050750906266183324,
"grad_norm": 3.0184805393218994,
"learning_rate": 9.694941803075283e-05,
"loss": 0.6193,
"step": 49
},
{
"epoch": 0.05178663904712584,
"grad_norm": 2.46248197555542,
"learning_rate": 9.662361147021779e-05,
"loss": 0.848,
"step": 50
},
{
"epoch": 0.05178663904712584,
"eval_loss": 0.8538514971733093,
"eval_runtime": 133.2166,
"eval_samples_per_second": 12.206,
"eval_steps_per_second": 6.103,
"step": 50
},
{
"epoch": 0.05282237182806836,
"grad_norm": 5.02744197845459,
"learning_rate": 9.628188298907782e-05,
"loss": 0.9884,
"step": 51
},
{
"epoch": 0.05385810460901087,
"grad_norm": 2.4663264751434326,
"learning_rate": 9.592434928729616e-05,
"loss": 0.8416,
"step": 52
},
{
"epoch": 0.05489383738995339,
"grad_norm": 1.7390788793563843,
"learning_rate": 9.555113246230442e-05,
"loss": 0.8593,
"step": 53
},
{
"epoch": 0.055929570170895906,
"grad_norm": 1.908245325088501,
"learning_rate": 9.516235996730645e-05,
"loss": 0.732,
"step": 54
},
{
"epoch": 0.05696530295183842,
"grad_norm": 2.3819148540496826,
"learning_rate": 9.475816456775313e-05,
"loss": 0.6403,
"step": 55
},
{
"epoch": 0.05800103573278094,
"grad_norm": 1.402185082435608,
"learning_rate": 9.43386842960031e-05,
"loss": 0.6708,
"step": 56
},
{
"epoch": 0.059036768513723456,
"grad_norm": 1.2513192892074585,
"learning_rate": 9.39040624041849e-05,
"loss": 0.6277,
"step": 57
},
{
"epoch": 0.06007250129466598,
"grad_norm": 1.1688061952590942,
"learning_rate": 9.345444731527642e-05,
"loss": 0.5229,
"step": 58
},
{
"epoch": 0.061108234075608496,
"grad_norm": 1.108825922012329,
"learning_rate": 9.298999257241863e-05,
"loss": 0.5915,
"step": 59
},
{
"epoch": 0.06214396685655101,
"grad_norm": 1.0653815269470215,
"learning_rate": 9.251085678648072e-05,
"loss": 0.6964,
"step": 60
},
{
"epoch": 0.06317969963749352,
"grad_norm": 1.674397587776184,
"learning_rate": 9.201720358189464e-05,
"loss": 0.5143,
"step": 61
},
{
"epoch": 0.06421543241843604,
"grad_norm": 0.9258373379707336,
"learning_rate": 9.150920154077754e-05,
"loss": 0.4886,
"step": 62
},
{
"epoch": 0.06525116519937856,
"grad_norm": 0.8897579908370972,
"learning_rate": 9.098702414536107e-05,
"loss": 0.4374,
"step": 63
},
{
"epoch": 0.06628689798032107,
"grad_norm": 0.9600769281387329,
"learning_rate": 9.045084971874738e-05,
"loss": 0.4138,
"step": 64
},
{
"epoch": 0.06732263076126359,
"grad_norm": 0.7555741667747498,
"learning_rate": 8.9900861364012e-05,
"loss": 0.35,
"step": 65
},
{
"epoch": 0.0683583635422061,
"grad_norm": 1.175614595413208,
"learning_rate": 8.933724690167417e-05,
"loss": 0.5386,
"step": 66
},
{
"epoch": 0.06939409632314862,
"grad_norm": 0.9770200252532959,
"learning_rate": 8.876019880555649e-05,
"loss": 0.4241,
"step": 67
},
{
"epoch": 0.07042982910409114,
"grad_norm": 1.079787254333496,
"learning_rate": 8.816991413705516e-05,
"loss": 0.4143,
"step": 68
},
{
"epoch": 0.07146556188503367,
"grad_norm": 0.921312689781189,
"learning_rate": 8.756659447784368e-05,
"loss": 0.3022,
"step": 69
},
{
"epoch": 0.07250129466597618,
"grad_norm": 0.830862283706665,
"learning_rate": 8.695044586103296e-05,
"loss": 0.2061,
"step": 70
},
{
"epoch": 0.0735370274469187,
"grad_norm": 0.9453504085540771,
"learning_rate": 8.632167870081121e-05,
"loss": 0.283,
"step": 71
},
{
"epoch": 0.07457276022786122,
"grad_norm": 1.1474324464797974,
"learning_rate": 8.568050772058762e-05,
"loss": 0.4113,
"step": 72
},
{
"epoch": 0.07560849300880373,
"grad_norm": 1.249191164970398,
"learning_rate": 8.502715187966455e-05,
"loss": 0.5516,
"step": 73
},
{
"epoch": 0.07664422578974625,
"grad_norm": 1.1734344959259033,
"learning_rate": 8.436183429846313e-05,
"loss": 0.5408,
"step": 74
},
{
"epoch": 0.07767995857068877,
"grad_norm": 1.2528908252716064,
"learning_rate": 8.368478218232787e-05,
"loss": 0.5155,
"step": 75
},
{
"epoch": 0.07871569135163128,
"grad_norm": 0.936934232711792,
"learning_rate": 8.299622674393614e-05,
"loss": 0.2787,
"step": 76
},
{
"epoch": 0.0797514241325738,
"grad_norm": 0.708920419216156,
"learning_rate": 8.229640312433937e-05,
"loss": 0.3339,
"step": 77
},
{
"epoch": 0.08078715691351632,
"grad_norm": 1.2183189392089844,
"learning_rate": 8.158555031266254e-05,
"loss": 0.5208,
"step": 78
},
{
"epoch": 0.08182288969445883,
"grad_norm": 1.1501481533050537,
"learning_rate": 8.086391106448965e-05,
"loss": 0.408,
"step": 79
},
{
"epoch": 0.08285862247540135,
"grad_norm": 0.823788046836853,
"learning_rate": 8.013173181896283e-05,
"loss": 0.3337,
"step": 80
},
{
"epoch": 0.08389435525634387,
"grad_norm": 0.9144259095191956,
"learning_rate": 7.938926261462366e-05,
"loss": 0.3301,
"step": 81
},
{
"epoch": 0.08493008803728638,
"grad_norm": 0.7938789129257202,
"learning_rate": 7.863675700402526e-05,
"loss": 0.234,
"step": 82
},
{
"epoch": 0.0859658208182289,
"grad_norm": 0.8019108772277832,
"learning_rate": 7.787447196714427e-05,
"loss": 0.2253,
"step": 83
},
{
"epoch": 0.08700155359917142,
"grad_norm": 0.9795384407043457,
"learning_rate": 7.710266782362247e-05,
"loss": 0.3915,
"step": 84
},
{
"epoch": 0.08803728638011393,
"grad_norm": 1.122196912765503,
"learning_rate": 7.63216081438678e-05,
"loss": 0.4886,
"step": 85
},
{
"epoch": 0.08907301916105645,
"grad_norm": 0.8640231490135193,
"learning_rate": 7.553155965904535e-05,
"loss": 0.2448,
"step": 86
},
{
"epoch": 0.09010875194199897,
"grad_norm": 2.5851869583129883,
"learning_rate": 7.473279216998895e-05,
"loss": 0.3743,
"step": 87
},
{
"epoch": 0.09114448472294148,
"grad_norm": 0.8353838920593262,
"learning_rate": 7.392557845506432e-05,
"loss": 0.3504,
"step": 88
},
{
"epoch": 0.092180217503884,
"grad_norm": 1.0095223188400269,
"learning_rate": 7.311019417701566e-05,
"loss": 0.3531,
"step": 89
},
{
"epoch": 0.09321595028482652,
"grad_norm": 1.6652759313583374,
"learning_rate": 7.228691778882693e-05,
"loss": 0.4985,
"step": 90
},
{
"epoch": 0.09425168306576903,
"grad_norm": 1.2830318212509155,
"learning_rate": 7.145603043863045e-05,
"loss": 0.5003,
"step": 91
},
{
"epoch": 0.09528741584671155,
"grad_norm": 0.8330721855163574,
"learning_rate": 7.061781587369519e-05,
"loss": 0.1982,
"step": 92
},
{
"epoch": 0.09632314862765406,
"grad_norm": 0.6261827945709229,
"learning_rate": 6.977256034352712e-05,
"loss": 0.2427,
"step": 93
},
{
"epoch": 0.09735888140859658,
"grad_norm": 0.6739867925643921,
"learning_rate": 6.892055250211552e-05,
"loss": 0.2442,
"step": 94
},
{
"epoch": 0.0983946141895391,
"grad_norm": 0.5700361132621765,
"learning_rate": 6.806208330935766e-05,
"loss": 0.09,
"step": 95
},
{
"epoch": 0.09943034697048161,
"grad_norm": 1.3761444091796875,
"learning_rate": 6.719744593169641e-05,
"loss": 0.1098,
"step": 96
},
{
"epoch": 0.10046607975142413,
"grad_norm": 1.5139930248260498,
"learning_rate": 6.632693564200416e-05,
"loss": 0.5464,
"step": 97
},
{
"epoch": 0.10150181253236665,
"grad_norm": 0.995734691619873,
"learning_rate": 6.545084971874738e-05,
"loss": 0.4197,
"step": 98
},
{
"epoch": 0.10253754531330916,
"grad_norm": 1.7123396396636963,
"learning_rate": 6.456948734446624e-05,
"loss": 0.4591,
"step": 99
},
{
"epoch": 0.10357327809425168,
"grad_norm": 1.226818323135376,
"learning_rate": 6.368314950360415e-05,
"loss": 0.4507,
"step": 100
},
{
"epoch": 0.10357327809425168,
"eval_loss": 0.46107152104377747,
"eval_runtime": 132.5673,
"eval_samples_per_second": 12.265,
"eval_steps_per_second": 6.133,
"step": 100
},
{
"epoch": 0.1046090108751942,
"grad_norm": 0.9650932550430298,
"learning_rate": 6.279213887972179e-05,
"loss": 0.6433,
"step": 101
},
{
"epoch": 0.10564474365613671,
"grad_norm": 1.0569595098495483,
"learning_rate": 6.189675975213094e-05,
"loss": 0.6046,
"step": 102
},
{
"epoch": 0.10668047643707923,
"grad_norm": 1.3118841648101807,
"learning_rate": 6.099731789198344e-05,
"loss": 0.6978,
"step": 103
},
{
"epoch": 0.10771620921802175,
"grad_norm": 0.9649919867515564,
"learning_rate": 6.009412045785051e-05,
"loss": 0.5771,
"step": 104
},
{
"epoch": 0.10875194199896426,
"grad_norm": 0.8630145788192749,
"learning_rate": 5.918747589082853e-05,
"loss": 0.4207,
"step": 105
},
{
"epoch": 0.10978767477990678,
"grad_norm": 0.8723099231719971,
"learning_rate": 5.82776938092065e-05,
"loss": 0.4919,
"step": 106
},
{
"epoch": 0.1108234075608493,
"grad_norm": 1.1895697116851807,
"learning_rate": 5.736508490273188e-05,
"loss": 0.5618,
"step": 107
},
{
"epoch": 0.11185914034179181,
"grad_norm": 1.1931686401367188,
"learning_rate": 5.644996082651017e-05,
"loss": 0.4773,
"step": 108
},
{
"epoch": 0.11289487312273433,
"grad_norm": 1.6731840372085571,
"learning_rate": 5.553263409457504e-05,
"loss": 0.4266,
"step": 109
},
{
"epoch": 0.11393060590367685,
"grad_norm": 1.227846622467041,
"learning_rate": 5.4613417973165106e-05,
"loss": 0.5589,
"step": 110
},
{
"epoch": 0.11496633868461936,
"grad_norm": 1.0807693004608154,
"learning_rate": 5.3692626373743706e-05,
"loss": 0.4194,
"step": 111
},
{
"epoch": 0.11600207146556188,
"grad_norm": 0.823137104511261,
"learning_rate": 5.27705737457985e-05,
"loss": 0.623,
"step": 112
},
{
"epoch": 0.1170378042465044,
"grad_norm": 0.9013914465904236,
"learning_rate": 5.184757496945726e-05,
"loss": 0.4202,
"step": 113
},
{
"epoch": 0.11807353702744691,
"grad_norm": 0.896589457988739,
"learning_rate": 5.092394524795649e-05,
"loss": 0.4487,
"step": 114
},
{
"epoch": 0.11910926980838944,
"grad_norm": 0.7383155226707458,
"learning_rate": 5e-05,
"loss": 0.3712,
"step": 115
},
{
"epoch": 0.12014500258933196,
"grad_norm": 1.5368659496307373,
"learning_rate": 4.907605475204352e-05,
"loss": 0.3895,
"step": 116
},
{
"epoch": 0.12118073537027448,
"grad_norm": 0.825655996799469,
"learning_rate": 4.8152425030542766e-05,
"loss": 0.3584,
"step": 117
},
{
"epoch": 0.12221646815121699,
"grad_norm": 0.7657477855682373,
"learning_rate": 4.72294262542015e-05,
"loss": 0.3234,
"step": 118
},
{
"epoch": 0.12325220093215951,
"grad_norm": 0.7747549414634705,
"learning_rate": 4.6307373626256306e-05,
"loss": 0.363,
"step": 119
},
{
"epoch": 0.12428793371310203,
"grad_norm": 1.066019892692566,
"learning_rate": 4.5386582026834906e-05,
"loss": 0.4481,
"step": 120
},
{
"epoch": 0.12532366649404453,
"grad_norm": 0.8845261931419373,
"learning_rate": 4.446736590542497e-05,
"loss": 0.2096,
"step": 121
},
{
"epoch": 0.12635939927498704,
"grad_norm": 0.969825267791748,
"learning_rate": 4.3550039173489845e-05,
"loss": 0.3525,
"step": 122
},
{
"epoch": 0.12739513205592956,
"grad_norm": 0.9056379199028015,
"learning_rate": 4.2634915097268115e-05,
"loss": 0.3636,
"step": 123
},
{
"epoch": 0.12843086483687208,
"grad_norm": 0.8290777206420898,
"learning_rate": 4.1722306190793495e-05,
"loss": 0.2886,
"step": 124
},
{
"epoch": 0.1294665976178146,
"grad_norm": 0.8031933903694153,
"learning_rate": 4.0812524109171476e-05,
"loss": 0.336,
"step": 125
},
{
"epoch": 0.1305023303987571,
"grad_norm": 1.104204773902893,
"learning_rate": 3.99058795421495e-05,
"loss": 0.3722,
"step": 126
},
{
"epoch": 0.13153806317969963,
"grad_norm": 0.9014912247657776,
"learning_rate": 3.9002682108016585e-05,
"loss": 0.3251,
"step": 127
},
{
"epoch": 0.13257379596064214,
"grad_norm": 0.5569969415664673,
"learning_rate": 3.8103240247869075e-05,
"loss": 0.2197,
"step": 128
},
{
"epoch": 0.13360952874158466,
"grad_norm": 0.5489453077316284,
"learning_rate": 3.720786112027822e-05,
"loss": 0.157,
"step": 129
},
{
"epoch": 0.13464526152252718,
"grad_norm": 0.700421929359436,
"learning_rate": 3.631685049639586e-05,
"loss": 0.2833,
"step": 130
},
{
"epoch": 0.1356809943034697,
"grad_norm": 0.8463655114173889,
"learning_rate": 3.543051265553377e-05,
"loss": 0.3084,
"step": 131
},
{
"epoch": 0.1367167270844122,
"grad_norm": 1.074282169342041,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.2022,
"step": 132
},
{
"epoch": 0.13775245986535473,
"grad_norm": 0.7204672694206238,
"learning_rate": 3.367306435799584e-05,
"loss": 0.1456,
"step": 133
},
{
"epoch": 0.13878819264629724,
"grad_norm": 1.4383536577224731,
"learning_rate": 3.2802554068303596e-05,
"loss": 0.2751,
"step": 134
},
{
"epoch": 0.13982392542723976,
"grad_norm": 0.6281360387802124,
"learning_rate": 3.1937916690642356e-05,
"loss": 0.0874,
"step": 135
},
{
"epoch": 0.14085965820818228,
"grad_norm": 0.6139625906944275,
"learning_rate": 3.107944749788449e-05,
"loss": 0.1965,
"step": 136
},
{
"epoch": 0.1418953909891248,
"grad_norm": 1.241881012916565,
"learning_rate": 3.0227439656472877e-05,
"loss": 0.2662,
"step": 137
},
{
"epoch": 0.14293112377006734,
"grad_norm": 0.6423341631889343,
"learning_rate": 2.9382184126304834e-05,
"loss": 0.1051,
"step": 138
},
{
"epoch": 0.14396685655100985,
"grad_norm": 1.093138337135315,
"learning_rate": 2.8543969561369556e-05,
"loss": 0.2853,
"step": 139
},
{
"epoch": 0.14500258933195237,
"grad_norm": 1.1384899616241455,
"learning_rate": 2.771308221117309e-05,
"loss": 0.3369,
"step": 140
},
{
"epoch": 0.14603832211289489,
"grad_norm": 0.7722360491752625,
"learning_rate": 2.688980582298435e-05,
"loss": 0.2649,
"step": 141
},
{
"epoch": 0.1470740548938374,
"grad_norm": 1.1144746541976929,
"learning_rate": 2.607442154493568e-05,
"loss": 0.2119,
"step": 142
},
{
"epoch": 0.14810978767477992,
"grad_norm": 0.6660451292991638,
"learning_rate": 2.5267207830011068e-05,
"loss": 0.1605,
"step": 143
},
{
"epoch": 0.14914552045572244,
"grad_norm": 0.6069556474685669,
"learning_rate": 2.446844034095466e-05,
"loss": 0.1004,
"step": 144
},
{
"epoch": 0.15018125323666495,
"grad_norm": 0.9130787253379822,
"learning_rate": 2.3678391856132204e-05,
"loss": 0.1797,
"step": 145
},
{
"epoch": 0.15121698601760747,
"grad_norm": 0.6856268644332886,
"learning_rate": 2.2897332176377528e-05,
"loss": 0.1913,
"step": 146
},
{
"epoch": 0.15225271879854999,
"grad_norm": 1.281296730041504,
"learning_rate": 2.2125528032855724e-05,
"loss": 0.4095,
"step": 147
},
{
"epoch": 0.1532884515794925,
"grad_norm": 1.5272610187530518,
"learning_rate": 2.136324299597474e-05,
"loss": 0.5091,
"step": 148
},
{
"epoch": 0.15432418436043502,
"grad_norm": 1.2128320932388306,
"learning_rate": 2.061073738537635e-05,
"loss": 0.3015,
"step": 149
},
{
"epoch": 0.15535991714137753,
"grad_norm": 0.903167724609375,
"learning_rate": 1.9868268181037185e-05,
"loss": 0.3632,
"step": 150
},
{
"epoch": 0.15535991714137753,
"eval_loss": 0.3055230975151062,
"eval_runtime": 132.6347,
"eval_samples_per_second": 12.259,
"eval_steps_per_second": 6.13,
"step": 150
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.995744869351424e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}