{
  "best_metric": 1.2578116655349731,
  "best_model_checkpoint": "data/Llama-31-8B_task-1_180-samples_config-3/checkpoint-255",
  "epoch": 22.0,
  "eval_steps": 500,
  "global_step": 374,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 1.8065106868743896,
      "learning_rate": 3.9215686274509804e-08,
      "loss": 2.1281,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 1.5079913139343262,
      "learning_rate": 7.843137254901961e-08,
      "loss": 1.9223,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.8093640804290771,
      "learning_rate": 1.5686274509803921e-07,
      "loss": 2.0122,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 1.6770484447479248,
      "learning_rate": 2.3529411764705883e-07,
      "loss": 2.1372,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.7670574188232422,
      "learning_rate": 3.1372549019607843e-07,
      "loss": 1.9583,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 1.669092059135437,
      "learning_rate": 3.921568627450981e-07,
      "loss": 2.1276,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.7997708320617676,
      "learning_rate": 4.7058823529411767e-07,
      "loss": 2.0952,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 1.5819483995437622,
      "learning_rate": 5.490196078431373e-07,
      "loss": 2.0738,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.8713793754577637,
      "learning_rate": 6.274509803921569e-07,
      "loss": 2.1142,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.066502809524536,
      "eval_runtime": 14.5349,
      "eval_samples_per_second": 2.477,
      "eval_steps_per_second": 2.477,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 1.7850439548492432,
      "learning_rate": 7.058823529411766e-07,
      "loss": 2.0455,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.6843671798706055,
      "learning_rate": 7.843137254901962e-07,
      "loss": 2.0741,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 1.7580695152282715,
      "learning_rate": 8.627450980392157e-07,
      "loss": 2.0505,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 1.7383497953414917,
      "learning_rate": 9.411764705882353e-07,
      "loss": 2.1409,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 1.8907734155654907,
      "learning_rate": 1.019607843137255e-06,
      "loss": 2.159,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 1.6468881368637085,
      "learning_rate": 1.0980392156862745e-06,
      "loss": 2.0287,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 1.5174058675765991,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 1.9636,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 1.958832025527954,
      "learning_rate": 1.2549019607843137e-06,
      "loss": 2.0552,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.8774864673614502,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 1.999,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.0372772216796875,
      "eval_runtime": 14.5623,
      "eval_samples_per_second": 2.472,
      "eval_steps_per_second": 2.472,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 1.5743886232376099,
      "learning_rate": 1.4117647058823531e-06,
      "loss": 1.9504,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 1.7804455757141113,
      "learning_rate": 1.4901960784313726e-06,
      "loss": 2.1437,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 2.0183544158935547,
      "learning_rate": 1.5686274509803923e-06,
      "loss": 1.9372,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 1.6332387924194336,
      "learning_rate": 1.6470588235294118e-06,
      "loss": 2.0966,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 1.7222906351089478,
      "learning_rate": 1.7254901960784315e-06,
      "loss": 2.0629,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 1.7061312198638916,
      "learning_rate": 1.8039215686274512e-06,
      "loss": 2.0279,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 1.9475563764572144,
      "learning_rate": 1.8823529411764707e-06,
      "loss": 1.9566,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 1.9611753225326538,
      "learning_rate": 1.96078431372549e-06,
      "loss": 1.9478,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.9762768745422363,
      "eval_runtime": 14.5515,
      "eval_samples_per_second": 2.474,
      "eval_steps_per_second": 2.474,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 1.9749150276184082,
      "learning_rate": 2.03921568627451e-06,
      "loss": 1.9698,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 1.8049449920654297,
      "learning_rate": 2.1176470588235296e-06,
      "loss": 1.9968,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 1.8159747123718262,
      "learning_rate": 2.196078431372549e-06,
      "loss": 1.8908,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 1.912788987159729,
      "learning_rate": 2.274509803921569e-06,
      "loss": 1.8648,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 1.9382165670394897,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 2.0148,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 1.9832690954208374,
      "learning_rate": 2.431372549019608e-06,
      "loss": 1.9367,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 1.720550298690796,
      "learning_rate": 2.5098039215686274e-06,
      "loss": 1.8145,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 1.8487679958343506,
      "learning_rate": 2.5882352941176473e-06,
      "loss": 1.9428,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.808930516242981,
      "learning_rate": 2.666666666666667e-06,
      "loss": 1.8469,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.8650811910629272,
      "eval_runtime": 14.5507,
      "eval_samples_per_second": 2.474,
      "eval_steps_per_second": 2.474,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 1.7737135887145996,
      "learning_rate": 2.7450980392156867e-06,
      "loss": 1.8195,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 1.7860044240951538,
      "learning_rate": 2.8235294117647062e-06,
      "loss": 1.8308,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 1.478087067604065,
      "learning_rate": 2.901960784313726e-06,
      "loss": 1.8569,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 1.8686025142669678,
      "learning_rate": 2.980392156862745e-06,
      "loss": 1.7475,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 1.4561829566955566,
      "learning_rate": 3.058823529411765e-06,
      "loss": 1.8159,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 1.5028529167175293,
      "learning_rate": 3.1372549019607846e-06,
      "loss": 1.6996,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 1.4778685569763184,
      "learning_rate": 3.2156862745098045e-06,
      "loss": 1.7772,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 1.6509016752243042,
      "learning_rate": 3.2941176470588236e-06,
      "loss": 1.7424,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.7082933187484741,
      "eval_runtime": 14.5117,
      "eval_samples_per_second": 2.481,
      "eval_steps_per_second": 2.481,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 1.4689080715179443,
      "learning_rate": 3.3725490196078435e-06,
      "loss": 1.7082,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 1.3921902179718018,
      "learning_rate": 3.450980392156863e-06,
      "loss": 1.5562,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 0.9668921828269958,
      "learning_rate": 3.529411764705883e-06,
      "loss": 1.6878,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 1.1552764177322388,
      "learning_rate": 3.6078431372549024e-06,
      "loss": 1.6425,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 1.0703318119049072,
      "learning_rate": 3.6862745098039223e-06,
      "loss": 1.5746,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 1.2990978956222534,
      "learning_rate": 3.7647058823529414e-06,
      "loss": 1.6453,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 0.9483143091201782,
      "learning_rate": 3.843137254901962e-06,
      "loss": 1.6347,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.784504771232605,
      "learning_rate": 3.92156862745098e-06,
      "loss": 1.5737,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7174596190452576,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.6109,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.591265320777893,
      "eval_runtime": 14.5187,
      "eval_samples_per_second": 2.48,
      "eval_steps_per_second": 2.48,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 0.7151546478271484,
      "learning_rate": 4.07843137254902e-06,
      "loss": 1.5874,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 0.6694661378860474,
      "learning_rate": 4.15686274509804e-06,
      "loss": 1.5791,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 0.6767610907554626,
      "learning_rate": 4.235294117647059e-06,
      "loss": 1.5153,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 0.7270079255104065,
      "learning_rate": 4.313725490196079e-06,
      "loss": 1.6142,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 0.6579761505126953,
      "learning_rate": 4.392156862745098e-06,
      "loss": 1.4975,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 0.7445734143257141,
      "learning_rate": 4.4705882352941184e-06,
      "loss": 1.5589,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 0.8089240789413452,
      "learning_rate": 4.549019607843138e-06,
      "loss": 1.4252,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 0.681290328502655,
      "learning_rate": 4.627450980392157e-06,
      "loss": 1.4629,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.533902645111084,
      "eval_runtime": 14.5134,
      "eval_samples_per_second": 2.48,
      "eval_steps_per_second": 2.48,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.6512688398361206,
      "learning_rate": 4.705882352941177e-06,
      "loss": 1.5663,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 0.6992992758750916,
      "learning_rate": 4.784313725490196e-06,
      "loss": 1.5244,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 0.6933541893959045,
      "learning_rate": 4.862745098039216e-06,
      "loss": 1.5546,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 0.6808838844299316,
      "learning_rate": 4.941176470588236e-06,
      "loss": 1.4226,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 0.6868391036987305,
      "learning_rate": 5.019607843137255e-06,
      "loss": 1.5075,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 0.7137860655784607,
      "learning_rate": 5.098039215686274e-06,
      "loss": 1.4272,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 0.7875804305076599,
      "learning_rate": 5.176470588235295e-06,
      "loss": 1.4287,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 0.6994704008102417,
      "learning_rate": 5.254901960784314e-06,
      "loss": 1.388,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.6940603256225586,
      "learning_rate": 5.333333333333334e-06,
      "loss": 1.4728,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.4789927005767822,
      "eval_runtime": 14.5049,
      "eval_samples_per_second": 2.482,
      "eval_steps_per_second": 2.482,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 0.627068817615509,
      "learning_rate": 5.411764705882353e-06,
      "loss": 1.3927,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 0.723114550113678,
      "learning_rate": 5.4901960784313735e-06,
      "loss": 1.4771,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 0.6911653876304626,
      "learning_rate": 5.568627450980393e-06,
      "loss": 1.4533,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 0.7171194553375244,
      "learning_rate": 5.6470588235294125e-06,
      "loss": 1.4565,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 0.7567141056060791,
      "learning_rate": 5.725490196078431e-06,
      "loss": 1.3616,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 0.6596878170967102,
      "learning_rate": 5.803921568627452e-06,
      "loss": 1.3604,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 0.6585553884506226,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.3845,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 0.7967809438705444,
      "learning_rate": 5.96078431372549e-06,
      "loss": 1.4044,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.4184479713439941,
      "eval_runtime": 14.5411,
      "eval_samples_per_second": 2.476,
      "eval_steps_per_second": 2.476,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 0.7969270348548889,
      "learning_rate": 6.03921568627451e-06,
      "loss": 1.3666,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 0.6962817907333374,
      "learning_rate": 6.11764705882353e-06,
      "loss": 1.388,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 0.7494238018989563,
      "learning_rate": 6.19607843137255e-06,
      "loss": 1.3444,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 0.7607508897781372,
      "learning_rate": 6.274509803921569e-06,
      "loss": 1.3855,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 0.6827089786529541,
      "learning_rate": 6.352941176470589e-06,
      "loss": 1.3163,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 0.7205786108970642,
      "learning_rate": 6.431372549019609e-06,
      "loss": 1.3293,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 0.7232930660247803,
      "learning_rate": 6.5098039215686285e-06,
      "loss": 1.3026,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 0.7706201672554016,
      "learning_rate": 6.588235294117647e-06,
      "loss": 1.295,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.8153946995735168,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.2885,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.3676073551177979,
      "eval_runtime": 14.5083,
      "eval_samples_per_second": 2.481,
      "eval_steps_per_second": 2.481,
      "step": 170
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 0.8457947969436646,
      "learning_rate": 6.745098039215687e-06,
      "loss": 1.3127,
      "step": 172
    },
    {
      "epoch": 10.235294117647058,
      "grad_norm": 0.7665146589279175,
      "learning_rate": 6.8235294117647065e-06,
      "loss": 1.2394,
      "step": 174
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 0.8373514413833618,
      "learning_rate": 6.901960784313726e-06,
      "loss": 1.2378,
      "step": 176
    },
    {
      "epoch": 10.470588235294118,
      "grad_norm": 0.753107488155365,
      "learning_rate": 6.9803921568627454e-06,
      "loss": 1.3008,
      "step": 178
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 0.7053059935569763,
      "learning_rate": 7.058823529411766e-06,
      "loss": 1.1693,
      "step": 180
    },
    {
      "epoch": 10.705882352941176,
      "grad_norm": 0.7962371110916138,
      "learning_rate": 7.137254901960785e-06,
      "loss": 1.3542,
      "step": 182
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 1.0228960514068604,
      "learning_rate": 7.215686274509805e-06,
      "loss": 1.3089,
      "step": 184
    },
    {
      "epoch": 10.941176470588236,
      "grad_norm": 0.9287481307983398,
      "learning_rate": 7.294117647058823e-06,
      "loss": 1.3419,
      "step": 186
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.3272498846054077,
      "eval_runtime": 14.5286,
      "eval_samples_per_second": 2.478,
      "eval_steps_per_second": 2.478,
      "step": 187
    },
    {
      "epoch": 11.058823529411764,
      "grad_norm": 0.710625410079956,
      "learning_rate": 7.372549019607845e-06,
      "loss": 1.3064,
      "step": 188
    },
    {
      "epoch": 11.176470588235293,
      "grad_norm": 0.9955301284790039,
      "learning_rate": 7.450980392156863e-06,
      "loss": 1.226,
      "step": 190
    },
    {
      "epoch": 11.294117647058824,
      "grad_norm": 0.9241538047790527,
      "learning_rate": 7.529411764705883e-06,
      "loss": 1.2302,
      "step": 192
    },
    {
      "epoch": 11.411764705882353,
      "grad_norm": 0.8634198307991028,
      "learning_rate": 7.607843137254902e-06,
      "loss": 1.2513,
      "step": 194
    },
    {
      "epoch": 11.529411764705882,
      "grad_norm": 0.8533808588981628,
      "learning_rate": 7.686274509803923e-06,
      "loss": 1.2978,
      "step": 196
    },
    {
      "epoch": 11.647058823529411,
      "grad_norm": 0.9525836110115051,
      "learning_rate": 7.764705882352941e-06,
      "loss": 1.1996,
      "step": 198
    },
    {
      "epoch": 11.764705882352942,
      "grad_norm": 1.0654942989349365,
      "learning_rate": 7.84313725490196e-06,
      "loss": 1.2378,
      "step": 200
    },
    {
      "epoch": 11.882352941176471,
      "grad_norm": 0.9135450124740601,
      "learning_rate": 7.92156862745098e-06,
      "loss": 1.146,
      "step": 202
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.9282100200653076,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.1269,
      "step": 204
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.301060676574707,
      "eval_runtime": 14.5109,
      "eval_samples_per_second": 2.481,
      "eval_steps_per_second": 2.481,
      "step": 204
    },
    {
      "epoch": 12.117647058823529,
      "grad_norm": 0.907046377658844,
      "learning_rate": 8.07843137254902e-06,
      "loss": 1.2013,
      "step": 206
    },
    {
      "epoch": 12.235294117647058,
      "grad_norm": 1.231627345085144,
      "learning_rate": 8.15686274509804e-06,
      "loss": 1.2579,
      "step": 208
    },
    {
      "epoch": 12.352941176470589,
      "grad_norm": 0.8959000110626221,
      "learning_rate": 8.23529411764706e-06,
      "loss": 1.0843,
      "step": 210
    },
    {
      "epoch": 12.470588235294118,
      "grad_norm": 0.876553475856781,
      "learning_rate": 8.31372549019608e-06,
      "loss": 1.1332,
      "step": 212
    },
    {
      "epoch": 12.588235294117647,
      "grad_norm": 1.0384048223495483,
      "learning_rate": 8.392156862745099e-06,
      "loss": 1.168,
      "step": 214
    },
    {
      "epoch": 12.705882352941176,
      "grad_norm": 1.0361497402191162,
      "learning_rate": 8.470588235294118e-06,
      "loss": 1.1616,
      "step": 216
    },
    {
      "epoch": 12.823529411764707,
      "grad_norm": 1.1576528549194336,
      "learning_rate": 8.549019607843138e-06,
      "loss": 1.2672,
      "step": 218
    },
    {
      "epoch": 12.941176470588236,
      "grad_norm": 1.0647550821304321,
      "learning_rate": 8.627450980392157e-06,
      "loss": 1.1586,
      "step": 220
    },
    {
      "epoch": 13.0,
      "eval_loss": 1.2765165567398071,
      "eval_runtime": 14.509,
      "eval_samples_per_second": 2.481,
      "eval_steps_per_second": 2.481,
      "step": 221
    },
    {
      "epoch": 13.058823529411764,
      "grad_norm": 0.8864277601242065,
      "learning_rate": 8.705882352941177e-06,
      "loss": 1.0941,
      "step": 222
    },
    {
      "epoch": 13.176470588235293,
      "grad_norm": 0.9786349534988403,
      "learning_rate": 8.784313725490196e-06,
      "loss": 1.1632,
      "step": 224
    },
    {
      "epoch": 13.294117647058824,
      "grad_norm": 1.0802189111709595,
      "learning_rate": 8.862745098039216e-06,
      "loss": 1.1514,
      "step": 226
    },
    {
      "epoch": 13.411764705882353,
      "grad_norm": 1.2572766542434692,
      "learning_rate": 8.941176470588237e-06,
      "loss": 1.1185,
      "step": 228
    },
    {
      "epoch": 13.529411764705882,
      "grad_norm": 1.118306040763855,
      "learning_rate": 9.019607843137256e-06,
      "loss": 1.1392,
      "step": 230
    },
    {
      "epoch": 13.647058823529411,
      "grad_norm": 1.0128273963928223,
      "learning_rate": 9.098039215686276e-06,
      "loss": 1.105,
      "step": 232
    },
    {
      "epoch": 13.764705882352942,
      "grad_norm": 1.0232294797897339,
      "learning_rate": 9.176470588235294e-06,
      "loss": 1.0412,
      "step": 234
    },
    {
      "epoch": 13.882352941176471,
      "grad_norm": 1.0292689800262451,
      "learning_rate": 9.254901960784315e-06,
      "loss": 1.1141,
      "step": 236
    },
    {
      "epoch": 14.0,
      "grad_norm": 1.068185806274414,
      "learning_rate": 9.333333333333334e-06,
      "loss": 1.1923,
      "step": 238
    },
    {
      "epoch": 14.0,
      "eval_loss": 1.2690058946609497,
      "eval_runtime": 14.5015,
      "eval_samples_per_second": 2.482,
      "eval_steps_per_second": 2.482,
      "step": 238
    },
    {
      "epoch": 14.117647058823529,
      "grad_norm": 1.1385935544967651,
      "learning_rate": 9.411764705882354e-06,
      "loss": 1.0398,
      "step": 240
    },
    {
      "epoch": 14.235294117647058,
      "grad_norm": 1.2786375284194946,
      "learning_rate": 9.490196078431373e-06,
      "loss": 1.072,
      "step": 242
    },
    {
      "epoch": 14.352941176470589,
      "grad_norm": 1.196818232536316,
      "learning_rate": 9.568627450980393e-06,
      "loss": 1.0577,
      "step": 244
    },
    {
      "epoch": 14.470588235294118,
      "grad_norm": 1.1373463869094849,
      "learning_rate": 9.647058823529412e-06,
      "loss": 1.1057,
      "step": 246
    },
    {
      "epoch": 14.588235294117647,
      "grad_norm": 1.315521001815796,
      "learning_rate": 9.725490196078432e-06,
      "loss": 1.1863,
      "step": 248
    },
    {
      "epoch": 14.705882352941176,
      "grad_norm": 1.2734661102294922,
      "learning_rate": 9.803921568627451e-06,
      "loss": 0.9691,
      "step": 250
    },
    {
      "epoch": 14.823529411764707,
      "grad_norm": 1.3599973917007446,
      "learning_rate": 9.882352941176472e-06,
      "loss": 1.039,
      "step": 252
    },
    {
      "epoch": 14.941176470588236,
      "grad_norm": 1.3458846807479858,
      "learning_rate": 9.960784313725492e-06,
      "loss": 1.1147,
      "step": 254
    },
    {
      "epoch": 15.0,
      "eval_loss": 1.2578116655349731,
      "eval_runtime": 14.5041,
      "eval_samples_per_second": 2.482,
      "eval_steps_per_second": 2.482,
      "step": 255
    },
    {
      "epoch": 15.058823529411764,
      "grad_norm": 1.3280770778656006,
      "learning_rate": 9.999995315380667e-06,
      "loss": 1.088,
      "step": 256
    },
    {
      "epoch": 15.176470588235293,
      "grad_norm": 1.144983172416687,
      "learning_rate": 9.99995783847866e-06,
      "loss": 0.9861,
      "step": 258
    },
    {
      "epoch": 15.294117647058824,
      "grad_norm": 1.3691227436065674,
      "learning_rate": 9.999882884955554e-06,
      "loss": 1.0412,
      "step": 260
    },
    {
      "epoch": 15.411764705882353,
      "grad_norm": 1.275398850440979,
      "learning_rate": 9.99977045537315e-06,
      "loss": 1.0658,
      "step": 262
    },
    {
      "epoch": 15.529411764705882,
      "grad_norm": 1.3578075170516968,
      "learning_rate": 9.999620550574155e-06,
      "loss": 0.9766,
      "step": 264
    },
    {
      "epoch": 15.647058823529411,
      "grad_norm": 1.3639436960220337,
      "learning_rate": 9.999433171682158e-06,
      "loss": 1.0073,
      "step": 266
    },
    {
      "epoch": 15.764705882352942,
      "grad_norm": 1.5169048309326172,
      "learning_rate": 9.999208320101643e-06,
      "loss": 1.0132,
      "step": 268
    },
    {
      "epoch": 15.882352941176471,
      "grad_norm": 1.488381266593933,
      "learning_rate": 9.998945997517957e-06,
      "loss": 0.996,
      "step": 270
    },
    {
      "epoch": 16.0,
      "grad_norm": 1.3266804218292236,
      "learning_rate": 9.99864620589731e-06,
      "loss": 1.0264,
      "step": 272
    },
    {
      "epoch": 16.0,
      "eval_loss": 1.2624274492263794,
      "eval_runtime": 14.5034,
      "eval_samples_per_second": 2.482,
      "eval_steps_per_second": 2.482,
      "step": 272
    },
    {
      "epoch": 16.11764705882353,
      "grad_norm": 1.3687496185302734,
      "learning_rate": 9.998308947486753e-06,
      "loss": 0.8802,
      "step": 274
    },
    {
      "epoch": 16.235294117647058,
      "grad_norm": 1.3879331350326538,
      "learning_rate": 9.997934224814173e-06,
      "loss": 0.9461,
      "step": 276
    },
    {
      "epoch": 16.352941176470587,
      "grad_norm": 1.655788540840149,
      "learning_rate": 9.997522040688258e-06,
      "loss": 1.0403,
      "step": 278
    },
    {
      "epoch": 16.470588235294116,
      "grad_norm": 1.6199966669082642,
      "learning_rate": 9.997072398198492e-06,
      "loss": 0.9535,
      "step": 280
    },
    {
      "epoch": 16.58823529411765,
      "grad_norm": 1.5855011940002441,
      "learning_rate": 9.996585300715117e-06,
      "loss": 0.9787,
      "step": 282
    },
    {
      "epoch": 16.705882352941178,
      "grad_norm": 1.4658994674682617,
      "learning_rate": 9.996060751889114e-06,
      "loss": 0.9774,
      "step": 284
    },
    {
      "epoch": 16.823529411764707,
      "grad_norm": 1.6470533609390259,
      "learning_rate": 9.995498755652186e-06,
      "loss": 0.9284,
      "step": 286
    },
    {
      "epoch": 16.941176470588236,
      "grad_norm": 1.3454952239990234,
      "learning_rate": 9.994899316216709e-06,
      "loss": 0.9349,
      "step": 288
    },
    {
      "epoch": 17.0,
      "eval_loss": 1.2616850137710571,
      "eval_runtime": 14.5073,
      "eval_samples_per_second": 2.482,
      "eval_steps_per_second": 2.482,
      "step": 289
    },
    {
      "epoch": 17.058823529411764,
      "grad_norm": 1.4319393634796143,
      "learning_rate": 9.994262438075713e-06,
      "loss": 0.9814,
      "step": 290
    },
    {
      "epoch": 17.176470588235293,
      "grad_norm": 1.571878433227539,
      "learning_rate": 9.993588126002848e-06,
      "loss": 0.8682,
      "step": 292
    },
    {
      "epoch": 17.294117647058822,
      "grad_norm": 1.692639946937561,
      "learning_rate": 9.992876385052346e-06,
      "loss": 0.8339,
      "step": 294
    },
    {
      "epoch": 17.41176470588235,
      "grad_norm": 2.15378999710083,
      "learning_rate": 9.992127220558976e-06,
      "loss": 0.8994,
      "step": 296
    },
    {
      "epoch": 17.529411764705884,
      "grad_norm": 1.8467787504196167,
      "learning_rate": 9.991340638138022e-06,
      "loss": 0.942,
      "step": 298
    },
    {
      "epoch": 17.647058823529413,
      "grad_norm": 1.8218432664871216,
      "learning_rate": 9.990516643685222e-06,
      "loss": 0.8622,
      "step": 300
    },
    {
      "epoch": 17.764705882352942,
      "grad_norm": 2.077235221862793,
      "learning_rate": 9.98965524337673e-06,
      "loss": 0.9586,
      "step": 302
    },
    {
      "epoch": 17.88235294117647,
      "grad_norm": 1.856018304824829,
      "learning_rate": 9.988756443669081e-06,
      "loss": 0.9054,
      "step": 304
    },
    {
      "epoch": 18.0,
      "grad_norm": 1.8019486665725708,
      "learning_rate": 9.987820251299121e-06,
      "loss": 0.8531,
      "step": 306
    },
    {
      "epoch": 18.0,
      "eval_loss": 1.2745150327682495,
      "eval_runtime": 14.4992,
      "eval_samples_per_second": 2.483,
      "eval_steps_per_second": 2.483,
      "step": 306
    },
    {
      "epoch": 18.11764705882353,
      "grad_norm": 1.9146708250045776,
      "learning_rate": 9.98684667328398e-06,
      "loss": 0.8219,
      "step": 308
    },
    {
      "epoch": 18.235294117647058,
      "grad_norm": 2.01367449760437,
      "learning_rate": 9.985835716921e-06,
      "loss": 0.7866,
      "step": 310
    },
    {
      "epoch": 18.352941176470587,
      "grad_norm": 2.060014486312866,
      "learning_rate": 9.984787389787689e-06,
      "loss": 0.9394,
      "step": 312
    },
    {
      "epoch": 18.470588235294116,
      "grad_norm": 2.0984644889831543,
      "learning_rate": 9.983701699741668e-06,
      "loss": 0.8506,
      "step": 314
    },
    {
      "epoch": 18.58823529411765,
      "grad_norm": 2.2392311096191406,
      "learning_rate": 9.982578654920601e-06,
      "loss": 0.8764,
      "step": 316
    },
    {
      "epoch": 18.705882352941178,
      "grad_norm": 1.995686411857605,
      "learning_rate": 9.981418263742148e-06,
      "loss": 0.7213,
      "step": 318
    },
    {
      "epoch": 18.823529411764707,
      "grad_norm": 1.9784153699874878,
      "learning_rate": 9.980220534903889e-06,
      "loss": 0.808,
      "step": 320
    },
    {
      "epoch": 18.941176470588236,
      "grad_norm": 2.239561080932617,
      "learning_rate": 9.978985477383264e-06,
      "loss": 0.7922,
      "step": 322
    },
    {
      "epoch": 19.0,
      "eval_loss": 1.323697805404663,
      "eval_runtime": 14.5112,
      "eval_samples_per_second": 2.481,
      "eval_steps_per_second": 2.481,
      "step": 323
    },
    {
      "epoch": 19.058823529411764,
      "grad_norm": 1.975653886795044,
      "learning_rate": 9.97771310043751e-06,
      "loss": 0.8048,
      "step": 324
    },
    {
      "epoch": 19.176470588235293,
      "grad_norm": 2.0462775230407715,
      "learning_rate": 9.97640341360358e-06,
      "loss": 0.861,
      "step": 326
    },
    {
      "epoch": 19.294117647058822,
      "grad_norm": 2.0673797130584717,
      "learning_rate": 9.975056426698094e-06,
      "loss": 0.8036,
      "step": 328
    },
    {
      "epoch": 19.41176470588235,
      "grad_norm": 2.2183079719543457,
      "learning_rate": 9.973672149817232e-06,
      "loss": 0.6738,
      "step": 330
    },
    {
      "epoch": 19.529411764705884,
      "grad_norm": 2.3562233448028564,
      "learning_rate": 9.972250593336689e-06,
      "loss": 0.7818,
      "step": 332
    },
    {
      "epoch": 19.647058823529413,
      "grad_norm": 2.5257391929626465,
      "learning_rate": 9.970791767911581e-06,
      "loss": 0.7123,
      "step": 334
    },
    {
      "epoch": 19.764705882352942,
      "grad_norm": 2.551309823989868,
      "learning_rate": 9.96929568447637e-06,
      "loss": 0.7208,
      "step": 336
    },
    {
      "epoch": 19.88235294117647,
      "grad_norm": 2.2066383361816406,
      "learning_rate": 9.967762354244778e-06,
      "loss": 0.7553,
      "step": 338
    },
    {
      "epoch": 20.0,
      "grad_norm": 2.0966691970825195,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.7745,
      "step": 340
    },
    {
      "epoch": 20.0,
      "eval_loss": 1.355035662651062,
      "eval_runtime": 14.5057,
      "eval_samples_per_second": 2.482,
      "eval_steps_per_second": 2.482,
      "step": 340
    },
    {
      "epoch": 20.11764705882353,
      "grad_norm": 2.2480452060699463,
      "learning_rate": 9.964583999643174e-06,
      "loss": 0.7137,
      "step": 342
    },
    {
      "epoch": 20.235294117647058,
      "grad_norm": 2.643707513809204,
      "learning_rate": 9.962938999096159e-06,
      "loss": 0.624,
      "step": 344
    },
    {
      "epoch": 20.352941176470587,
      "grad_norm": 2.4683399200439453,
      "learning_rate": 9.961256799398584e-06,
      "loss": 0.7796,
      "step": 346
    },
    {
      "epoch": 20.470588235294116,
      "grad_norm": 2.5370218753814697,
      "learning_rate": 9.95953741315919e-06,
      "loss": 0.7474,
      "step": 348
    },
    {
      "epoch": 20.58823529411765,
      "grad_norm": 2.785471200942993,
      "learning_rate": 9.957780853265441e-06,
      "loss": 0.6173,
      "step": 350
    },
    {
      "epoch": 20.705882352941178,
      "grad_norm": 2.926558494567871,
      "learning_rate": 9.955987132883435e-06,
      "loss": 0.6487,
      "step": 352
    },
    {
      "epoch": 20.823529411764707,
      "grad_norm": 2.633388042449951,
      "learning_rate": 9.954156265457801e-06,
      "loss": 0.5935,
      "step": 354
    },
    {
      "epoch": 20.941176470588236,
      "grad_norm": 2.62455677986145,
      "learning_rate": 9.952288264711601e-06,
      "loss": 0.7142,
      "step": 356
    },
    {
      "epoch": 21.0,
      "eval_loss": 1.42457115650177,
      "eval_runtime": 14.5129,
      "eval_samples_per_second": 2.481,
      "eval_steps_per_second": 2.481,
      "step": 357
    },
    {
      "epoch": 21.058823529411764,
      "grad_norm": 2.937354326248169,
      "learning_rate": 9.950383144646221e-06,
      "loss": 0.6242,
      "step": 358
    },
    {
      "epoch": 21.176470588235293,
      "grad_norm": 2.5222437381744385,
      "learning_rate": 9.948440919541277e-06,
      "loss": 0.6387,
      "step": 360
    },
    {
      "epoch": 21.294117647058822,
      "grad_norm": 2.9972007274627686,
      "learning_rate": 9.946461603954499e-06,
      "loss": 0.6939,
      "step": 362
    },
    {
      "epoch": 21.41176470588235,
      "grad_norm": 3.4149131774902344,
      "learning_rate": 9.944445212721619e-06,
      "loss": 0.6166,
      "step": 364
    },
    {
      "epoch": 21.529411764705884,
      "grad_norm": 2.921032190322876,
      "learning_rate": 9.942391760956277e-06,
      "loss": 0.6338,
      "step": 366
    },
    {
      "epoch": 21.647058823529413,
      "grad_norm": 2.995636463165283,
      "learning_rate": 9.940301264049885e-06,
      "loss": 0.5784,
      "step": 368
    },
    {
      "epoch": 21.764705882352942,
      "grad_norm": 2.860006332397461,
      "learning_rate": 9.938173737671531e-06,
      "loss": 0.5467,
      "step": 370
    },
    {
      "epoch": 21.88235294117647,
      "grad_norm": 2.901470184326172,
      "learning_rate": 9.936009197767847e-06,
      "loss": 0.6088,
      "step": 372
    },
    {
      "epoch": 22.0,
      "grad_norm": 3.1448581218719482,
      "learning_rate": 9.933807660562898e-06,
      "loss": 0.4873,
      "step": 374
    },
    {
      "epoch": 22.0,
      "eval_loss": 1.5459914207458496,
      "eval_runtime": 14.5012,
      "eval_samples_per_second": 2.483,
      "eval_steps_per_second": 2.483,
      "step": 374
    },
    {
      "epoch": 22.0,
      "step": 374,
      "total_flos": 4.76256860635136e+16,
      "train_loss": 1.309851686744129,
      "train_runtime": 3534.2998,
      "train_samples_per_second": 5.772,
      "train_steps_per_second": 0.722
    }
  ],
  "logging_steps": 2,
  "max_steps": 2550,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 150,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 7,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.76256860635136e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}