{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0049625953633063,
  "eval_steps": 11,
  "global_step": 106,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009480779201540626,
      "grad_norm": 0.38671875,
      "learning_rate": 2e-05,
      "loss": 0.4197,
      "step": 1
    },
    {
      "epoch": 0.009480779201540626,
      "eval_loss": 0.41279804706573486,
      "eval_runtime": 34.6855,
      "eval_samples_per_second": 20.498,
      "eval_steps_per_second": 20.498,
      "step": 1
    },
    {
      "epoch": 0.018961558403081252,
      "grad_norm": 0.359375,
      "learning_rate": 4e-05,
      "loss": 0.3966,
      "step": 2
    },
    {
      "epoch": 0.02844233760462188,
      "grad_norm": 0.388671875,
      "learning_rate": 6e-05,
      "loss": 0.4257,
      "step": 3
    },
    {
      "epoch": 0.037923116806162505,
      "grad_norm": 0.408203125,
      "learning_rate": 8e-05,
      "loss": 0.4026,
      "step": 4
    },
    {
      "epoch": 0.04740389600770313,
      "grad_norm": 0.384765625,
      "learning_rate": 0.0001,
      "loss": 0.3229,
      "step": 5
    },
    {
      "epoch": 0.05688467520924376,
      "grad_norm": 0.251953125,
      "learning_rate": 0.00012,
      "loss": 0.2408,
      "step": 6
    },
    {
      "epoch": 0.06636545441078438,
      "grad_norm": 0.203125,
      "learning_rate": 0.00014,
      "loss": 0.1709,
      "step": 7
    },
    {
      "epoch": 0.07584623361232501,
      "grad_norm": 0.150390625,
      "learning_rate": 0.00016,
      "loss": 0.1328,
      "step": 8
    },
    {
      "epoch": 0.08532701281386564,
      "grad_norm": 0.1201171875,
      "learning_rate": 0.00018,
      "loss": 0.0993,
      "step": 9
    },
    {
      "epoch": 0.09480779201540626,
      "grad_norm": 0.10888671875,
      "learning_rate": 0.0002,
      "loss": 0.0914,
      "step": 10
    },
    {
      "epoch": 0.10428857121694689,
      "grad_norm": 0.119140625,
      "learning_rate": 0.00019999469523400122,
      "loss": 0.0885,
      "step": 11
    },
    {
      "epoch": 0.10428857121694689,
      "eval_loss": 0.07809103280305862,
      "eval_runtime": 34.2892,
      "eval_samples_per_second": 20.735,
      "eval_steps_per_second": 20.735,
      "step": 11
    },
    {
      "epoch": 0.11376935041848751,
      "grad_norm": 0.09228515625,
      "learning_rate": 0.00019997878149881574,
      "loss": 0.0761,
      "step": 12
    },
    {
      "epoch": 0.12325012962002814,
      "grad_norm": 0.0703125,
      "learning_rate": 0.0001999522604828164,
      "loss": 0.0683,
      "step": 13
    },
    {
      "epoch": 0.13273090882156877,
      "grad_norm": 0.059326171875,
      "learning_rate": 0.00019991513499975882,
      "loss": 0.0696,
      "step": 14
    },
    {
      "epoch": 0.1422116880231094,
      "grad_norm": 0.044921875,
      "learning_rate": 0.00019986740898848306,
      "loss": 0.0615,
      "step": 15
    },
    {
      "epoch": 0.15169246722465002,
      "grad_norm": 0.054443359375,
      "learning_rate": 0.00019980908751249555,
      "loss": 0.0625,
      "step": 16
    },
    {
      "epoch": 0.16117324642619066,
      "grad_norm": 0.04736328125,
      "learning_rate": 0.00019974017675943192,
      "loss": 0.0598,
      "step": 17
    },
    {
      "epoch": 0.17065402562773127,
      "grad_norm": 0.039306640625,
      "learning_rate": 0.0001996606840404006,
      "loss": 0.0573,
      "step": 18
    },
    {
      "epoch": 0.1801348048292719,
      "grad_norm": 0.036376953125,
      "learning_rate": 0.00019957061778920701,
      "loss": 0.0482,
      "step": 19
    },
    {
      "epoch": 0.18961558403081252,
      "grad_norm": 0.039306640625,
      "learning_rate": 0.0001994699875614589,
      "loss": 0.0555,
      "step": 20
    },
    {
      "epoch": 0.19909636323235316,
      "grad_norm": 0.0380859375,
      "learning_rate": 0.00019935880403355253,
      "loss": 0.0495,
      "step": 21
    },
    {
      "epoch": 0.20857714243389378,
      "grad_norm": 0.038818359375,
      "learning_rate": 0.00019923707900153982,
      "loss": 0.0482,
      "step": 22
    },
    {
      "epoch": 0.20857714243389378,
      "eval_loss": 0.05171125754714012,
      "eval_runtime": 34.4113,
      "eval_samples_per_second": 20.662,
      "eval_steps_per_second": 20.662,
      "step": 22
    },
    {
      "epoch": 0.21805792163543442,
      "grad_norm": 0.038818359375,
      "learning_rate": 0.00019910482537987702,
      "loss": 0.0529,
      "step": 23
    },
    {
      "epoch": 0.22753870083697503,
      "grad_norm": 0.031494140625,
      "learning_rate": 0.0001989620572000544,
      "loss": 0.0495,
      "step": 24
    },
    {
      "epoch": 0.23701948003851567,
      "grad_norm": 0.0380859375,
      "learning_rate": 0.00019880878960910772,
      "loss": 0.059,
      "step": 25
    },
    {
      "epoch": 0.24650025924005628,
      "grad_norm": 0.032470703125,
      "learning_rate": 0.00019864503886801106,
      "loss": 0.0545,
      "step": 26
    },
    {
      "epoch": 0.2559810384415969,
      "grad_norm": 0.029296875,
      "learning_rate": 0.00019847082234995171,
      "loss": 0.0417,
      "step": 27
    },
    {
      "epoch": 0.26546181764313753,
      "grad_norm": 0.037109375,
      "learning_rate": 0.00019828615853848688,
      "loss": 0.0459,
      "step": 28
    },
    {
      "epoch": 0.27494259684467814,
      "grad_norm": 0.027099609375,
      "learning_rate": 0.00019809106702558277,
      "loss": 0.0412,
      "step": 29
    },
    {
      "epoch": 0.2844233760462188,
      "grad_norm": 0.032470703125,
      "learning_rate": 0.0001978855685095358,
      "loss": 0.0403,
      "step": 30
    },
    {
      "epoch": 0.2939041552477594,
      "grad_norm": 0.0289306640625,
      "learning_rate": 0.00019766968479277683,
      "loss": 0.0463,
      "step": 31
    },
    {
      "epoch": 0.30338493444930004,
      "grad_norm": 0.0301513671875,
      "learning_rate": 0.00019744343877955788,
      "loss": 0.041,
      "step": 32
    },
    {
      "epoch": 0.3128657136508407,
      "grad_norm": 0.033447265625,
      "learning_rate": 0.00019720685447352209,
      "loss": 0.045,
      "step": 33
    },
    {
      "epoch": 0.3128657136508407,
      "eval_loss": 0.04294149950146675,
      "eval_runtime": 34.2719,
      "eval_samples_per_second": 20.746,
      "eval_steps_per_second": 20.746,
      "step": 33
    },
    {
      "epoch": 0.3223464928523813,
      "grad_norm": 0.028076171875,
      "learning_rate": 0.0001969599569751571,
      "loss": 0.0369,
      "step": 34
    },
    {
      "epoch": 0.33182727205392193,
      "grad_norm": 0.029296875,
      "learning_rate": 0.00019670277247913205,
      "loss": 0.0465,
      "step": 35
    },
    {
      "epoch": 0.34130805125546254,
      "grad_norm": 0.032958984375,
      "learning_rate": 0.0001964353282715183,
      "loss": 0.0382,
      "step": 36
    },
    {
      "epoch": 0.3507888304570032,
      "grad_norm": 0.0299072265625,
      "learning_rate": 0.00019615765272689461,
      "loss": 0.0442,
      "step": 37
    },
    {
      "epoch": 0.3602696096585438,
      "grad_norm": 0.0322265625,
      "learning_rate": 0.00019586977530533677,
      "loss": 0.0481,
      "step": 38
    },
    {
      "epoch": 0.36975038886008443,
      "grad_norm": 0.028076171875,
      "learning_rate": 0.00019557172654929196,
      "loss": 0.0423,
      "step": 39
    },
    {
      "epoch": 0.37923116806162505,
      "grad_norm": 0.0299072265625,
      "learning_rate": 0.00019526353808033825,
      "loss": 0.0384,
      "step": 40
    },
    {
      "epoch": 0.3887119472631657,
      "grad_norm": 0.027587890625,
      "learning_rate": 0.00019494524259582992,
      "loss": 0.0404,
      "step": 41
    },
    {
      "epoch": 0.3981927264647063,
      "grad_norm": 0.0286865234375,
      "learning_rate": 0.00019461687386542826,
      "loss": 0.0394,
      "step": 42
    },
    {
      "epoch": 0.40767350566624694,
      "grad_norm": 0.032958984375,
      "learning_rate": 0.00019427846672751873,
      "loss": 0.0351,
      "step": 43
    },
    {
      "epoch": 0.41715428486778755,
      "grad_norm": 0.02783203125,
      "learning_rate": 0.00019393005708551498,
      "loss": 0.0425,
      "step": 44
    },
    {
      "epoch": 0.41715428486778755,
      "eval_loss": 0.03996235132217407,
      "eval_runtime": 34.3007,
      "eval_samples_per_second": 20.728,
      "eval_steps_per_second": 20.728,
      "step": 44
    },
    {
      "epoch": 0.4266350640693282,
      "grad_norm": 0.030517578125,
      "learning_rate": 0.00019357168190404936,
      "loss": 0.0365,
      "step": 45
    },
    {
      "epoch": 0.43611584327086883,
      "grad_norm": 0.032958984375,
      "learning_rate": 0.00019320337920505153,
      "loss": 0.0438,
      "step": 46
    },
    {
      "epoch": 0.44559662247240944,
      "grad_norm": 0.0306396484375,
      "learning_rate": 0.00019282518806371414,
      "loss": 0.044,
      "step": 47
    },
    {
      "epoch": 0.45507740167395005,
      "grad_norm": 0.037841796875,
      "learning_rate": 0.0001924371486043473,
      "loss": 0.0496,
      "step": 48
    },
    {
      "epoch": 0.4645581808754907,
      "grad_norm": 0.0284423828125,
      "learning_rate": 0.0001920393019961217,
      "loss": 0.0369,
      "step": 49
    },
    {
      "epoch": 0.47403896007703133,
      "grad_norm": 0.0341796875,
      "learning_rate": 0.0001916316904487005,
      "loss": 0.0399,
      "step": 50
    },
    {
      "epoch": 0.48351973927857195,
      "grad_norm": 0.0255126953125,
      "learning_rate": 0.00019121435720776122,
      "loss": 0.0363,
      "step": 51
    },
    {
      "epoch": 0.49300051848011256,
      "grad_norm": 0.0311279296875,
      "learning_rate": 0.0001907873465504076,
      "loss": 0.0384,
      "step": 52
    },
    {
      "epoch": 0.5024812976816532,
      "grad_norm": 0.03271484375,
      "learning_rate": 0.00019035070378047204,
      "loss": 0.0371,
      "step": 53
    },
    {
      "epoch": 0.5119620768831938,
      "grad_norm": 0.0263671875,
      "learning_rate": 0.00018990447522370884,
      "loss": 0.0351,
      "step": 54
    },
    {
      "epoch": 0.5214428560847345,
      "grad_norm": 0.033203125,
      "learning_rate": 0.00018944870822287956,
      "loss": 0.0411,
      "step": 55
    },
    {
      "epoch": 0.5214428560847345,
      "eval_loss": 0.03788134828209877,
      "eval_runtime": 34.6048,
      "eval_samples_per_second": 20.546,
      "eval_steps_per_second": 20.546,
      "step": 55
    },
    {
      "epoch": 0.5309236352862751,
      "grad_norm": 0.0272216796875,
      "learning_rate": 0.00018898345113272998,
      "loss": 0.0337,
      "step": 56
    },
    {
      "epoch": 0.5404044144878157,
      "grad_norm": 0.0245361328125,
      "learning_rate": 0.00018850875331485995,
      "loss": 0.0309,
      "step": 57
    },
    {
      "epoch": 0.5498851936893563,
      "grad_norm": 0.027587890625,
      "learning_rate": 0.00018802466513248632,
      "loss": 0.0329,
      "step": 58
    },
    {
      "epoch": 0.559365972890897,
      "grad_norm": 0.0267333984375,
      "learning_rate": 0.00018753123794509974,
      "loss": 0.0365,
      "step": 59
    },
    {
      "epoch": 0.5688467520924376,
      "grad_norm": 0.02734375,
      "learning_rate": 0.00018702852410301554,
      "loss": 0.0373,
      "step": 60
    },
    {
      "epoch": 0.5783275312939782,
      "grad_norm": 0.025390625,
      "learning_rate": 0.0001865165769418196,
      "loss": 0.0375,
      "step": 61
    },
    {
      "epoch": 0.5878083104955188,
      "grad_norm": 0.02978515625,
      "learning_rate": 0.00018599545077670985,
      "loss": 0.0376,
      "step": 62
    },
    {
      "epoch": 0.5972890896970595,
      "grad_norm": 0.0242919921875,
      "learning_rate": 0.0001854652008967335,
      "loss": 0.0337,
      "step": 63
    },
    {
      "epoch": 0.6067698688986001,
      "grad_norm": 0.02880859375,
      "learning_rate": 0.00018492588355892124,
      "loss": 0.0379,
      "step": 64
    },
    {
      "epoch": 0.6162506481001407,
      "grad_norm": 0.0322265625,
      "learning_rate": 0.00018437755598231856,
      "loss": 0.0392,
      "step": 65
    },
    {
      "epoch": 0.6257314273016814,
      "grad_norm": 0.0269775390625,
      "learning_rate": 0.00018382027634191524,
      "loss": 0.0348,
      "step": 66
    },
    {
      "epoch": 0.6257314273016814,
      "eval_loss": 0.03594927862286568,
      "eval_runtime": 34.2756,
      "eval_samples_per_second": 20.744,
      "eval_steps_per_second": 20.744,
      "step": 66
    },
    {
      "epoch": 0.635212206503222,
      "grad_norm": 0.03515625,
      "learning_rate": 0.00018325410376247294,
      "loss": 0.0379,
      "step": 67
    },
    {
      "epoch": 0.6446929857047626,
      "grad_norm": 0.0301513671875,
      "learning_rate": 0.0001826790983122527,
      "loss": 0.0317,
      "step": 68
    },
    {
      "epoch": 0.6541737649063032,
      "grad_norm": 0.0296630859375,
      "learning_rate": 0.00018209532099664174,
      "loss": 0.0366,
      "step": 69
    },
    {
      "epoch": 0.6636545441078439,
      "grad_norm": 0.0272216796875,
      "learning_rate": 0.00018150283375168114,
      "loss": 0.0345,
      "step": 70
    },
    {
      "epoch": 0.6731353233093845,
      "grad_norm": 0.03125,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0368,
      "step": 71
    },
    {
      "epoch": 0.6826161025109251,
      "grad_norm": 0.032470703125,
      "learning_rate": 0.00018029198183161998,
      "loss": 0.0455,
      "step": 72
    },
    {
      "epoch": 0.6920968817124658,
      "grad_norm": 0.029296875,
      "learning_rate": 0.00017967374562224132,
      "loss": 0.0362,
      "step": 73
    },
    {
      "epoch": 0.7015776609140064,
      "grad_norm": 0.0311279296875,
      "learning_rate": 0.00017904705640132718,
      "loss": 0.0388,
      "step": 74
    },
    {
      "epoch": 0.711058440115547,
      "grad_norm": 0.02685546875,
      "learning_rate": 0.00017841198065767107,
      "loss": 0.0288,
      "step": 75
    },
    {
      "epoch": 0.7205392193170876,
      "grad_norm": 0.0302734375,
      "learning_rate": 0.00017776858576983712,
      "loss": 0.0349,
      "step": 76
    },
    {
      "epoch": 0.7300199985186282,
      "grad_norm": 0.026611328125,
      "learning_rate": 0.0001771169399990119,
      "loss": 0.0288,
      "step": 77
    },
    {
      "epoch": 0.7300199985186282,
      "eval_loss": 0.03419337794184685,
      "eval_runtime": 34.3669,
      "eval_samples_per_second": 20.688,
      "eval_steps_per_second": 20.688,
      "step": 77
    },
    {
      "epoch": 0.7395007777201689,
      "grad_norm": 0.0240478515625,
      "learning_rate": 0.00017645711248176195,
      "loss": 0.0285,
      "step": 78
    },
    {
      "epoch": 0.7489815569217095,
      "grad_norm": 0.025390625,
      "learning_rate": 0.00017578917322269886,
      "loss": 0.0338,
      "step": 79
    },
    {
      "epoch": 0.7584623361232501,
      "grad_norm": 0.0281982421875,
      "learning_rate": 0.00017511319308705198,
      "loss": 0.0316,
      "step": 80
    },
    {
      "epoch": 0.7679431153247908,
      "grad_norm": 0.025146484375,
      "learning_rate": 0.0001744292437931502,
      "loss": 0.0306,
      "step": 81
    },
    {
      "epoch": 0.7774238945263314,
      "grad_norm": 0.027099609375,
      "learning_rate": 0.00017373739790481262,
      "loss": 0.0335,
      "step": 82
    },
    {
      "epoch": 0.786904673727872,
      "grad_norm": 0.0242919921875,
      "learning_rate": 0.00017303772882365016,
      "loss": 0.0271,
      "step": 83
    },
    {
      "epoch": 0.7963854529294127,
      "grad_norm": 0.028564453125,
      "learning_rate": 0.00017233031078127788,
      "loss": 0.0334,
      "step": 84
    },
    {
      "epoch": 0.8058662321309532,
      "grad_norm": 0.0299072265625,
      "learning_rate": 0.00017161521883143934,
      "loss": 0.0403,
      "step": 85
    },
    {
      "epoch": 0.8153470113324939,
      "grad_norm": 0.0294189453125,
      "learning_rate": 0.00017089252884204377,
      "loss": 0.0368,
      "step": 86
    },
    {
      "epoch": 0.8248277905340345,
      "grad_norm": 0.03369140625,
      "learning_rate": 0.0001701623174871168,
      "loss": 0.0335,
      "step": 87
    },
    {
      "epoch": 0.8343085697355751,
      "grad_norm": 0.0277099609375,
      "learning_rate": 0.0001694246622386658,
      "loss": 0.0339,
      "step": 88
    },
    {
      "epoch": 0.8343085697355751,
      "eval_loss": 0.033091045916080475,
      "eval_runtime": 34.4475,
      "eval_samples_per_second": 20.64,
      "eval_steps_per_second": 20.64,
      "step": 88
    },
    {
      "epoch": 0.8437893489371158,
      "grad_norm": 0.02392578125,
      "learning_rate": 0.00016867964135846043,
      "loss": 0.0241,
      "step": 89
    },
    {
      "epoch": 0.8532701281386564,
      "grad_norm": 0.0361328125,
      "learning_rate": 0.00016792733388972932,
      "loss": 0.0387,
      "step": 90
    },
    {
      "epoch": 0.862750907340197,
      "grad_norm": 0.0260009765625,
      "learning_rate": 0.0001671678196487741,
      "loss": 0.0346,
      "step": 91
    },
    {
      "epoch": 0.8722316865417377,
      "grad_norm": 0.0284423828125,
      "learning_rate": 0.00016640117921650117,
      "loss": 0.0378,
      "step": 92
    },
    {
      "epoch": 0.8817124657432783,
      "grad_norm": 0.0279541015625,
      "learning_rate": 0.00016562749392987254,
      "loss": 0.0294,
      "step": 93
    },
    {
      "epoch": 0.8911932449448189,
      "grad_norm": 0.0272216796875,
      "learning_rate": 0.0001648468458732762,
      "loss": 0.0308,
      "step": 94
    },
    {
      "epoch": 0.9006740241463596,
      "grad_norm": 0.0242919921875,
      "learning_rate": 0.00016405931786981755,
      "loss": 0.0326,
      "step": 95
    },
    {
      "epoch": 0.9101548033479001,
      "grad_norm": 0.0262451171875,
      "learning_rate": 0.00016326499347253207,
      "loss": 0.032,
      "step": 96
    },
    {
      "epoch": 0.9196355825494408,
      "grad_norm": 0.0264892578125,
      "learning_rate": 0.00016246395695552085,
      "loss": 0.0321,
      "step": 97
    },
    {
      "epoch": 0.9291163617509814,
      "grad_norm": 0.0244140625,
      "learning_rate": 0.00016165629330500952,
      "loss": 0.0301,
      "step": 98
    },
    {
      "epoch": 0.938597140952522,
      "grad_norm": 0.029052734375,
      "learning_rate": 0.0001608420882103315,
      "loss": 0.0297,
      "step": 99
    },
    {
      "epoch": 0.938597140952522,
      "eval_loss": 0.03182319179177284,
      "eval_runtime": 34.2304,
      "eval_samples_per_second": 20.771,
      "eval_steps_per_second": 20.771,
      "step": 99
    },
    {
      "epoch": 0.9480779201540627,
      "grad_norm": 0.0302734375,
      "learning_rate": 0.00016002142805483685,
      "loss": 0.0327,
      "step": 100
    },
    {
      "epoch": 0.9575586993556033,
      "grad_norm": 0.0260009765625,
      "learning_rate": 0.0001591943999067273,
      "loss": 0.0285,
      "step": 101
    },
    {
      "epoch": 0.9670394785571439,
      "grad_norm": 0.032470703125,
      "learning_rate": 0.00015836109150981886,
      "loss": 0.0308,
      "step": 102
    },
    {
      "epoch": 0.9765202577586846,
      "grad_norm": 0.0283203125,
      "learning_rate": 0.00015752159127423263,
      "loss": 0.0301,
      "step": 103
    },
    {
      "epoch": 0.9860010369602251,
      "grad_norm": 0.027587890625,
      "learning_rate": 0.0001566759882670146,
      "loss": 0.0287,
      "step": 104
    },
    {
      "epoch": 0.9954818161617658,
      "grad_norm": 0.025634765625,
      "learning_rate": 0.00015582437220268647,
      "loss": 0.031,
      "step": 105
    },
    {
      "epoch": 1.0049625953633063,
      "grad_norm": 0.02490234375,
      "learning_rate": 0.0001549668334337271,
      "loss": 0.0275,
      "step": 106
    }
  ],
  "logging_steps": 1,
  "max_steps": 315,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 53,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4413248091848704e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}