{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 29,
  "global_step": 145,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034482758620689655,
      "grad_norm": 0.9141239523887634,
      "learning_rate": 0.0,
      "loss": 1.248046875,
      "step": 1
    },
    {
      "epoch": 0.06896551724137931,
      "grad_norm": 1.1608076095581055,
      "learning_rate": 1.25e-05,
      "loss": 1.353515625,
      "step": 2
    },
    {
      "epoch": 0.10344827586206896,
      "grad_norm": 1.1571086645126343,
      "learning_rate": 2.5e-05,
      "loss": 1.32421875,
      "step": 3
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 0.38539037108421326,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.84967041015625,
      "step": 4
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 0.6293753981590271,
      "learning_rate": 5e-05,
      "loss": 1.2001953125,
      "step": 5
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": 0.38309770822525024,
      "learning_rate": 6.25e-05,
      "loss": 1.12646484375,
      "step": 6
    },
    {
      "epoch": 0.2413793103448276,
      "grad_norm": 0.6449037194252014,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.97705078125,
      "step": 7
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 0.3187286853790283,
      "learning_rate": 8.75e-05,
      "loss": 1.037109375,
      "step": 8
    },
    {
      "epoch": 0.3103448275862069,
      "grad_norm": 0.1745445281267166,
      "learning_rate": 0.0001,
      "loss": 1.0234375,
      "step": 9
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.19780467450618744,
      "learning_rate": 9.99881689824633e-05,
      "loss": 1.09228515625,
      "step": 10
    },
    {
      "epoch": 0.3793103448275862,
      "grad_norm": 0.10462570935487747,
      "learning_rate": 9.995268215087426e-05,
      "loss": 0.837646484375,
      "step": 11
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 0.10926361382007599,
      "learning_rate": 9.989355816502525e-05,
      "loss": 0.9892578125,
      "step": 12
    },
    {
      "epoch": 0.4482758620689655,
      "grad_norm": 0.08940163999795914,
      "learning_rate": 9.981082811366797e-05,
      "loss": 1.00048828125,
      "step": 13
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 0.07245241850614548,
      "learning_rate": 9.970453549816632e-05,
      "loss": 0.9296875,
      "step": 14
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.07076121121644974,
      "learning_rate": 9.957473620962246e-05,
      "loss": 0.98681640625,
      "step": 15
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.0740443766117096,
      "learning_rate": 9.94214984994879e-05,
      "loss": 0.95068359375,
      "step": 16
    },
    {
      "epoch": 0.5862068965517241,
      "grad_norm": 0.07254257798194885,
      "learning_rate": 9.924490294367533e-05,
      "loss": 0.94580078125,
      "step": 17
    },
    {
      "epoch": 0.6206896551724138,
      "grad_norm": 0.0706133171916008,
      "learning_rate": 9.904504240019e-05,
      "loss": 0.87451171875,
      "step": 18
    },
    {
      "epoch": 0.6551724137931034,
      "grad_norm": 0.0796641930937767,
      "learning_rate": 9.88220219603028e-05,
      "loss": 0.97119140625,
      "step": 19
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.06700394302606583,
      "learning_rate": 9.85759588932908e-05,
      "loss": 0.95751953125,
      "step": 20
    },
    {
      "epoch": 0.7241379310344828,
      "grad_norm": 0.05687156319618225,
      "learning_rate": 9.830698258477458e-05,
      "loss": 0.94189453125,
      "step": 21
    },
    {
      "epoch": 0.7586206896551724,
      "grad_norm": 0.28273341059684753,
      "learning_rate": 9.801523446868399e-05,
      "loss": 0.798828125,
      "step": 22
    },
    {
      "epoch": 0.7931034482758621,
      "grad_norm": 0.051940660923719406,
      "learning_rate": 9.770086795288913e-05,
      "loss": 0.9365234375,
      "step": 23
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 0.047991909086704254,
      "learning_rate": 9.736404833853502e-05,
      "loss": 0.80908203125,
      "step": 24
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.04962654784321785,
      "learning_rate": 9.700495273312223e-05,
      "loss": 0.9521484375,
      "step": 25
    },
    {
      "epoch": 0.896551724137931,
      "grad_norm": 0.04889737442135811,
      "learning_rate": 9.662376995737989e-05,
      "loss": 0.931640625,
      "step": 26
    },
    {
      "epoch": 0.9310344827586207,
      "grad_norm": 0.044876836240291595,
      "learning_rate": 9.622070044597935e-05,
      "loss": 0.834228515625,
      "step": 27
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 0.04438192769885063,
      "learning_rate": 9.579595614214087e-05,
      "loss": 0.92919921875,
      "step": 28
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.046951454132795334,
      "learning_rate": 9.534976038618931e-05,
      "loss": 0.89111328125,
      "step": 29
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.734954833984375,
      "eval_runtime": 2.1997,
      "eval_samples_per_second": 3.182,
      "eval_steps_per_second": 0.455,
      "step": 29
    },
    {
      "epoch": 1.0344827586206897,
      "grad_norm": 0.04781215265393257,
      "learning_rate": 9.488234779811635e-05,
      "loss": 0.87841796875,
      "step": 30
    },
    {
      "epoch": 1.0689655172413792,
      "grad_norm": 0.050589919090270996,
      "learning_rate": 9.439396415421204e-05,
      "loss": 0.865234375,
      "step": 31
    },
    {
      "epoch": 1.103448275862069,
      "grad_norm": 0.043824728578329086,
      "learning_rate": 9.388486625782995e-05,
      "loss": 0.8408203125,
      "step": 32
    },
    {
      "epoch": 1.1379310344827587,
      "grad_norm": 0.03810536861419678,
      "learning_rate": 9.335532180435412e-05,
      "loss": 0.671539306640625,
      "step": 33
    },
    {
      "epoch": 1.1724137931034484,
      "grad_norm": 0.045897550880908966,
      "learning_rate": 9.280560924043858e-05,
      "loss": 0.9423828125,
      "step": 34
    },
    {
      "epoch": 1.206896551724138,
      "grad_norm": 0.04141751676797867,
      "learning_rate": 9.223601761759367e-05,
      "loss": 0.9345703125,
      "step": 35
    },
    {
      "epoch": 1.2413793103448276,
      "grad_norm": 0.04160734638571739,
      "learning_rate": 9.164684644019624e-05,
      "loss": 0.7381591796875,
      "step": 36
    },
    {
      "epoch": 1.2758620689655173,
      "grad_norm": 0.039669815450906754,
      "learning_rate": 9.103840550800329e-05,
      "loss": 0.85546875,
      "step": 37
    },
    {
      "epoch": 1.3103448275862069,
      "grad_norm": 0.04144350066781044,
      "learning_rate": 9.041101475325209e-05,
      "loss": 0.890625,
      "step": 38
    },
    {
      "epoch": 1.3448275862068966,
      "grad_norm": 0.044221483170986176,
      "learning_rate": 8.976500407243247e-05,
      "loss": 0.94873046875,
      "step": 39
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 0.039581846445798874,
      "learning_rate": 8.910071315281975e-05,
      "loss": 0.7294921875,
      "step": 40
    },
    {
      "epoch": 1.4137931034482758,
      "grad_norm": 0.042304378002882004,
      "learning_rate": 8.841849129385921e-05,
      "loss": 0.88818359375,
      "step": 41
    },
    {
      "epoch": 1.4482758620689655,
      "grad_norm": 0.042420923709869385,
      "learning_rate": 8.771869722349651e-05,
      "loss": 0.90087890625,
      "step": 42
    },
    {
      "epoch": 1.4827586206896552,
      "grad_norm": 0.03962633013725281,
      "learning_rate": 8.700169890955027e-05,
      "loss": 0.84912109375,
      "step": 43
    },
    {
      "epoch": 1.5172413793103448,
      "grad_norm": 0.044396448880434036,
      "learning_rate": 8.626787336622607e-05,
      "loss": 0.90234375,
      "step": 44
    },
    {
      "epoch": 1.5517241379310345,
      "grad_norm": 0.04070088267326355,
      "learning_rate": 8.55176064558738e-05,
      "loss": 0.8720703125,
      "step": 45
    },
    {
      "epoch": 1.5862068965517242,
      "grad_norm": 0.037677083164453506,
      "learning_rate": 8.475129268609227e-05,
      "loss": 0.86962890625,
      "step": 46
    },
    {
      "epoch": 1.6206896551724137,
      "grad_norm": 0.03817937895655632,
      "learning_rate": 8.396933500228808e-05,
      "loss": 0.798583984375,
      "step": 47
    },
    {
      "epoch": 1.6551724137931034,
      "grad_norm": 0.041942279785871506,
      "learning_rate": 8.317214457579773e-05,
      "loss": 0.896484375,
      "step": 48
    },
    {
      "epoch": 1.6896551724137931,
      "grad_norm": 0.04131230339407921,
      "learning_rate": 8.23601405876841e-05,
      "loss": 0.88671875,
      "step": 49
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 0.03989393636584282,
      "learning_rate": 8.153375000832157e-05,
      "loss": 0.88134765625,
      "step": 50
    },
    {
      "epoch": 1.7586206896551724,
      "grad_norm": 0.03887653350830078,
      "learning_rate": 8.069340737288512e-05,
      "loss": 0.7451171875,
      "step": 51
    },
    {
      "epoch": 1.793103448275862,
      "grad_norm": 0.044195547699928284,
      "learning_rate": 7.98395545528617e-05,
      "loss": 0.87646484375,
      "step": 52
    },
    {
      "epoch": 1.8275862068965516,
      "grad_norm": 0.03915185481309891,
      "learning_rate": 7.897264052370409e-05,
      "loss": 0.7509765625,
      "step": 53
    },
    {
      "epoch": 1.8620689655172413,
      "grad_norm": 0.04271269962191582,
      "learning_rate": 7.809312112874924e-05,
      "loss": 0.89453125,
      "step": 54
    },
    {
      "epoch": 1.896551724137931,
      "grad_norm": 0.03963204845786095,
      "learning_rate": 7.720145883952544e-05,
      "loss": 0.876953125,
      "step": 55
    },
    {
      "epoch": 1.9310344827586206,
      "grad_norm": 0.041339099407196045,
      "learning_rate": 7.629812251257401e-05,
      "loss": 0.7861328125,
      "step": 56
    },
    {
      "epoch": 1.9655172413793105,
      "grad_norm": 0.04127822443842888,
      "learning_rate": 7.53835871429139e-05,
      "loss": 0.8779296875,
      "step": 57
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.041708704084157944,
      "learning_rate": 7.445833361427828e-05,
      "loss": 0.8349609375,
      "step": 58
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.7025985717773438,
      "eval_runtime": 2.1741,
      "eval_samples_per_second": 3.22,
      "eval_steps_per_second": 0.46,
      "step": 58
    },
    {
      "epoch": 2.0344827586206895,
      "grad_norm": 0.04129553586244583,
      "learning_rate": 7.352284844625481e-05,
      "loss": 0.82177734375,
      "step": 59
    },
    {
      "epoch": 2.0689655172413794,
      "grad_norm": 0.0444064661860466,
      "learning_rate": 7.257762353846257e-05,
      "loss": 0.817138671875,
      "step": 60
    },
    {
      "epoch": 2.103448275862069,
      "grad_norm": 0.04007135331630707,
      "learning_rate": 7.162315591189978e-05,
      "loss": 0.79296875,
      "step": 61
    },
    {
      "epoch": 2.1379310344827585,
      "grad_norm": 0.035818614065647125,
      "learning_rate": 7.065994744759879e-05,
      "loss": 0.638580322265625,
      "step": 62
    },
    {
      "epoch": 2.1724137931034484,
      "grad_norm": 0.048203978687524796,
      "learning_rate": 6.96885046227255e-05,
      "loss": 0.90087890625,
      "step": 63
    },
    {
      "epoch": 2.206896551724138,
      "grad_norm": 0.04193362593650818,
      "learning_rate": 6.8709338244262e-05,
      "loss": 0.892578125,
      "step": 64
    },
    {
      "epoch": 2.2413793103448274,
      "grad_norm": 0.03875169903039932,
      "learning_rate": 6.772296318041253e-05,
      "loss": 0.6998291015625,
      "step": 65
    },
    {
      "epoch": 2.2758620689655173,
      "grad_norm": 0.040379852056503296,
      "learning_rate": 6.672989808987385e-05,
      "loss": 0.8154296875,
      "step": 66
    },
    {
      "epoch": 2.310344827586207,
      "grad_norm": 0.042849261313676834,
      "learning_rate": 6.573066514911273e-05,
      "loss": 0.8544921875,
      "step": 67
    },
    {
      "epoch": 2.344827586206897,
      "grad_norm": 0.046527985483407974,
      "learning_rate": 6.472578977779339e-05,
      "loss": 0.90771484375,
      "step": 68
    },
    {
      "epoch": 2.3793103448275863,
      "grad_norm": 0.03771306201815605,
      "learning_rate": 6.371580036249985e-05,
      "loss": 0.694580078125,
      "step": 69
    },
    {
      "epoch": 2.413793103448276,
      "grad_norm": 0.044022396206855774,
      "learning_rate": 6.270122797889806e-05,
      "loss": 0.853515625,
      "step": 70
    },
    {
      "epoch": 2.4482758620689653,
      "grad_norm": 0.04467899724841118,
      "learning_rate": 6.168260611248417e-05,
      "loss": 0.8642578125,
      "step": 71
    },
    {
      "epoch": 2.4827586206896552,
      "grad_norm": 0.04010975360870361,
      "learning_rate": 6.066047037806549e-05,
      "loss": 0.814453125,
      "step": 72
    },
    {
      "epoch": 2.5172413793103448,
      "grad_norm": 0.045232899487018585,
      "learning_rate": 5.9635358238121954e-05,
      "loss": 0.86669921875,
      "step": 73
    },
    {
      "epoch": 2.5517241379310347,
      "grad_norm": 0.041606999933719635,
      "learning_rate": 5.860780872019601e-05,
      "loss": 0.837890625,
      "step": 74
    },
    {
      "epoch": 2.586206896551724,
      "grad_norm": 0.042455825954675674,
      "learning_rate": 5.7578362133459494e-05,
      "loss": 0.83447265625,
      "step": 75
    },
    {
      "epoch": 2.6206896551724137,
      "grad_norm": 0.04038050025701523,
      "learning_rate": 5.6547559784606675e-05,
      "loss": 0.765380859375,
      "step": 76
    },
    {
      "epoch": 2.655172413793103,
      "grad_norm": 0.04546913877129555,
      "learning_rate": 5.551594369322271e-05,
      "loss": 0.865234375,
      "step": 77
    },
    {
      "epoch": 2.689655172413793,
      "grad_norm": 0.04499706253409386,
      "learning_rate": 5.44840563067773e-05,
      "loss": 0.85693359375,
      "step": 78
    },
    {
      "epoch": 2.7241379310344827,
      "grad_norm": 0.04100987687706947,
      "learning_rate": 5.3452440215393315e-05,
      "loss": 0.8515625,
      "step": 79
    },
    {
      "epoch": 2.7586206896551726,
      "grad_norm": 0.04000319540500641,
      "learning_rate": 5.242163786654051e-05,
      "loss": 0.7203369140625,
      "step": 80
    },
    {
      "epoch": 2.793103448275862,
      "grad_norm": 0.04476683586835861,
      "learning_rate": 5.139219127980399e-05,
      "loss": 0.8447265625,
      "step": 81
    },
    {
      "epoch": 2.8275862068965516,
      "grad_norm": 0.042925991117954254,
      "learning_rate": 5.036464176187806e-05,
      "loss": 0.72216796875,
      "step": 82
    },
    {
      "epoch": 2.862068965517241,
      "grad_norm": 0.04376095533370972,
      "learning_rate": 4.933952962193452e-05,
      "loss": 0.8662109375,
      "step": 83
    },
    {
      "epoch": 2.896551724137931,
      "grad_norm": 0.04183020070195198,
      "learning_rate": 4.831739388751584e-05,
      "loss": 0.849609375,
      "step": 84
    },
    {
      "epoch": 2.9310344827586206,
      "grad_norm": 0.0416734516620636,
      "learning_rate": 4.729877202110195e-05,
      "loss": 0.760986328125,
      "step": 85
    },
    {
      "epoch": 2.9655172413793105,
      "grad_norm": 0.04293662682175636,
      "learning_rate": 4.628419963750016e-05,
      "loss": 0.8505859375,
      "step": 86
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.046213313937187195,
      "learning_rate": 4.527421022220663e-05,
      "loss": 0.7978515625,
      "step": 87
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.688873291015625,
      "eval_runtime": 2.161,
      "eval_samples_per_second": 3.239,
      "eval_steps_per_second": 0.463,
      "step": 87
    },
    {
      "epoch": 3.0344827586206895,
      "grad_norm": 0.043874748051166534,
      "learning_rate": 4.426933485088729e-05,
      "loss": 0.78662109375,
      "step": 88
    },
    {
      "epoch": 3.0689655172413794,
      "grad_norm": 0.044054560363292694,
      "learning_rate": 4.327010191012617e-05,
      "loss": 0.789306640625,
      "step": 89
    },
    {
      "epoch": 3.103448275862069,
      "grad_norm": 0.04392517730593681,
      "learning_rate": 4.227703681958749e-05,
      "loss": 0.76708984375,
      "step": 90
    },
    {
      "epoch": 3.1379310344827585,
      "grad_norm": 0.040220849215984344,
      "learning_rate": 4.1290661755738e-05,
      "loss": 0.619903564453125,
      "step": 91
    },
    {
      "epoch": 3.1724137931034484,
      "grad_norm": 0.04874297231435776,
      "learning_rate": 4.03114953772745e-05,
      "loss": 0.87451171875,
      "step": 92
    },
    {
      "epoch": 3.206896551724138,
      "grad_norm": 0.044029586017131805,
      "learning_rate": 3.934005255240122e-05,
      "loss": 0.8671875,
      "step": 93
    },
    {
      "epoch": 3.2413793103448274,
      "grad_norm": 0.041890013962984085,
      "learning_rate": 3.837684408810023e-05,
      "loss": 0.6788330078125,
      "step": 94
    },
    {
      "epoch": 3.2758620689655173,
      "grad_norm": 0.04235467687249184,
      "learning_rate": 3.7422376461537435e-05,
      "loss": 0.79052734375,
      "step": 95
    },
    {
      "epoch": 3.310344827586207,
      "grad_norm": 0.04666660726070404,
      "learning_rate": 3.647715155374519e-05,
      "loss": 0.83056640625,
      "step": 96
    },
    {
      "epoch": 3.344827586206897,
      "grad_norm": 0.0479116328060627,
      "learning_rate": 3.554166638572175e-05,
      "loss": 0.88623046875,
      "step": 97
    },
    {
      "epoch": 3.3793103448275863,
      "grad_norm": 0.03947301581501961,
      "learning_rate": 3.461641285708611e-05,
      "loss": 0.673828125,
      "step": 98
    },
    {
      "epoch": 3.413793103448276,
      "grad_norm": 0.04651173576712608,
      "learning_rate": 3.370187748742601e-05,
      "loss": 0.8310546875,
      "step": 99
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 0.04680432006716728,
      "learning_rate": 3.279854116047457e-05,
      "loss": 0.84326171875,
      "step": 100
    },
    {
      "epoch": 3.4827586206896552,
      "grad_norm": 0.04312792047858238,
      "learning_rate": 3.190687887125077e-05,
      "loss": 0.79443359375,
      "step": 101
    },
    {
      "epoch": 3.5172413793103448,
      "grad_norm": 0.047171998769044876,
      "learning_rate": 3.102735947629594e-05,
      "loss": 0.84619140625,
      "step": 102
    },
    {
      "epoch": 3.5517241379310347,
      "grad_norm": 0.044388387352228165,
      "learning_rate": 3.0160445447138308e-05,
      "loss": 0.81884765625,
      "step": 103
    },
    {
      "epoch": 3.586206896551724,
      "grad_norm": 0.044332217425107956,
      "learning_rate": 2.9306592627114883e-05,
      "loss": 0.81494140625,
      "step": 104
    },
    {
      "epoch": 3.6206896551724137,
      "grad_norm": 0.04357318580150604,
      "learning_rate": 2.846624999167843e-05,
      "loss": 0.74609375,
      "step": 105
    },
    {
      "epoch": 3.655172413793103,
      "grad_norm": 0.04777277261018753,
      "learning_rate": 2.7639859412315917e-05,
      "loss": 0.8447265625,
      "step": 106
    },
    {
      "epoch": 3.689655172413793,
      "grad_norm": 0.04683416336774826,
      "learning_rate": 2.682785542420229e-05,
      "loss": 0.8369140625,
      "step": 107
    },
    {
      "epoch": 3.7241379310344827,
      "grad_norm": 0.04757894203066826,
      "learning_rate": 2.603066499771192e-05,
      "loss": 0.8310546875,
      "step": 108
    },
    {
      "epoch": 3.7586206896551726,
      "grad_norm": 0.04141659662127495,
      "learning_rate": 2.5248707313907747e-05,
      "loss": 0.7044677734375,
      "step": 109
    },
    {
      "epoch": 3.793103448275862,
      "grad_norm": 0.0487089529633522,
      "learning_rate": 2.4482393544126215e-05,
      "loss": 0.82763671875,
      "step": 110
    },
    {
      "epoch": 3.8275862068965516,
      "grad_norm": 0.04605620726943016,
      "learning_rate": 2.3732126633773928e-05,
      "loss": 0.705322265625,
      "step": 111
    },
    {
      "epoch": 3.862068965517241,
      "grad_norm": 0.04972607642412186,
      "learning_rate": 2.2998301090449738e-05,
      "loss": 0.84716796875,
      "step": 112
    },
    {
      "epoch": 3.896551724137931,
      "grad_norm": 0.04776594042778015,
      "learning_rate": 2.2281302776503497e-05,
      "loss": 0.8310546875,
      "step": 113
    },
    {
      "epoch": 3.9310344827586206,
      "grad_norm": 0.04310367628931999,
      "learning_rate": 2.1581508706140802e-05,
      "loss": 0.74755859375,
      "step": 114
    },
    {
      "epoch": 3.9655172413793105,
      "grad_norm": 0.04755757004022598,
      "learning_rate": 2.0899286847180243e-05,
      "loss": 0.83544921875,
      "step": 115
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0534578338265419,
      "learning_rate": 2.0234995927567523e-05,
      "loss": 0.77685546875,
      "step": 116
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6829910278320312,
      "eval_runtime": 2.2094,
      "eval_samples_per_second": 3.168,
      "eval_steps_per_second": 0.453,
      "step": 116
    },
    {
      "epoch": 4.0344827586206895,
      "grad_norm": 0.04993898421525955,
      "learning_rate": 1.9588985246747925e-05,
      "loss": 0.76513671875,
      "step": 117
    },
    {
      "epoch": 4.068965517241379,
      "grad_norm": 0.04440940171480179,
      "learning_rate": 1.896159449199672e-05,
      "loss": 0.7744140625,
      "step": 118
    },
    {
      "epoch": 4.103448275862069,
      "grad_norm": 0.046776678413152695,
      "learning_rate": 1.835315355980376e-05,
      "loss": 0.752197265625,
      "step": 119
    },
    {
      "epoch": 4.137931034482759,
      "grad_norm": 0.04259359464049339,
      "learning_rate": 1.7763982382406352e-05,
      "loss": 0.609619140625,
      "step": 120
    },
    {
      "epoch": 4.172413793103448,
      "grad_norm": 0.052434712648391724,
      "learning_rate": 1.7194390759561453e-05,
      "loss": 0.8603515625,
      "step": 121
    },
    {
      "epoch": 4.206896551724138,
      "grad_norm": 0.05287640169262886,
      "learning_rate": 1.664467819564588e-05,
      "loss": 0.85302734375,
      "step": 122
    },
    {
      "epoch": 4.241379310344827,
      "grad_norm": 0.046187352389097214,
      "learning_rate": 1.6115133742170053e-05,
      "loss": 0.665771484375,
      "step": 123
    },
    {
      "epoch": 4.275862068965517,
      "grad_norm": 0.04718184843659401,
      "learning_rate": 1.5606035845787987e-05,
      "loss": 0.77734375,
      "step": 124
    },
    {
      "epoch": 4.310344827586207,
      "grad_norm": 0.04889068007469177,
      "learning_rate": 1.511765220188367e-05,
      "loss": 0.81884765625,
      "step": 125
    },
    {
      "epoch": 4.344827586206897,
      "grad_norm": 0.049949802458286285,
      "learning_rate": 1.4650239613810693e-05,
      "loss": 0.8720703125,
      "step": 126
    },
    {
      "epoch": 4.379310344827586,
      "grad_norm": 0.04106840118765831,
      "learning_rate": 1.4204043857859129e-05,
      "loss": 0.663330078125,
      "step": 127
    },
    {
      "epoch": 4.413793103448276,
      "grad_norm": 0.04871964454650879,
      "learning_rate": 1.3779299554020672e-05,
      "loss": 0.82177734375,
      "step": 128
    },
    {
      "epoch": 4.448275862068965,
      "grad_norm": 0.04913930594921112,
      "learning_rate": 1.3376230042620109e-05,
      "loss": 0.8310546875,
      "step": 129
    },
    {
      "epoch": 4.482758620689655,
      "grad_norm": 0.045162830501794815,
      "learning_rate": 1.2995047266877775e-05,
      "loss": 0.783203125,
      "step": 130
    },
    {
      "epoch": 4.517241379310345,
      "grad_norm": 0.05215758830308914,
      "learning_rate": 1.2635951661464995e-05,
      "loss": 0.83544921875,
      "step": 131
    },
    {
      "epoch": 4.551724137931035,
      "grad_norm": 0.05053786560893059,
      "learning_rate": 1.2299132047110876e-05,
      "loss": 0.80712890625,
      "step": 132
    },
    {
      "epoch": 4.586206896551724,
      "grad_norm": 0.04842638224363327,
      "learning_rate": 1.1984765531316038e-05,
      "loss": 0.80517578125,
      "step": 133
    },
    {
      "epoch": 4.620689655172414,
      "grad_norm": 0.04590578377246857,
      "learning_rate": 1.1693017415225432e-05,
      "loss": 0.736572265625,
      "step": 134
    },
    {
      "epoch": 4.655172413793103,
      "grad_norm": 0.04723084345459938,
      "learning_rate": 1.1424041106709194e-05,
      "loss": 0.83740234375,
      "step": 135
    },
    {
      "epoch": 4.689655172413794,
      "grad_norm": 0.047631967812776566,
      "learning_rate": 1.1177978039697217e-05,
      "loss": 0.82763671875,
      "step": 136
    },
    {
      "epoch": 4.724137931034483,
      "grad_norm": 0.04777703434228897,
      "learning_rate": 1.0954957599810003e-05,
      "loss": 0.822265625,
      "step": 137
    },
    {
      "epoch": 4.758620689655173,
      "grad_norm": 0.04737548157572746,
      "learning_rate": 1.0755097056324672e-05,
      "loss": 0.6964111328125,
      "step": 138
    },
    {
      "epoch": 4.793103448275862,
      "grad_norm": 0.05136754736304283,
      "learning_rate": 1.0578501500512109e-05,
      "loss": 0.81787109375,
      "step": 139
    },
    {
      "epoch": 4.827586206896552,
      "grad_norm": 0.04480571672320366,
      "learning_rate": 1.042526379037754e-05,
      "loss": 0.697265625,
      "step": 140
    },
    {
      "epoch": 4.862068965517241,
      "grad_norm": 0.048113927245140076,
      "learning_rate": 1.0295464501833682e-05,
      "loss": 0.84033203125,
      "step": 141
    },
    {
      "epoch": 4.896551724137931,
      "grad_norm": 0.04913536086678505,
      "learning_rate": 1.0189171886332038e-05,
      "loss": 0.82470703125,
      "step": 142
    },
    {
      "epoch": 4.931034482758621,
      "grad_norm": 0.044891249388456345,
      "learning_rate": 1.0106441834974748e-05,
      "loss": 0.740478515625,
      "step": 143
    },
    {
      "epoch": 4.9655172413793105,
      "grad_norm": 0.047014325857162476,
      "learning_rate": 1.0047317849125743e-05,
      "loss": 0.82763671875,
      "step": 144
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.051313262432813644,
      "learning_rate": 1.0011831017536722e-05,
      "loss": 0.76416015625,
      "step": 145
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6805343627929688,
      "eval_runtime": 2.2025,
      "eval_samples_per_second": 3.178,
      "eval_steps_per_second": 0.454,
      "step": 145
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 145,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.060858300796502e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}