{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9952941176470587,
  "eval_steps": 500,
  "global_step": 424,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023529411764705882,
      "grad_norm": 2.0912532806396484,
      "learning_rate": 4.998284588246634e-05,
      "loss": 1.5824,
      "num_input_tokens_seen": 47376,
      "step": 5
    },
    {
      "epoch": 0.047058823529411764,
      "grad_norm": 1.2301002740859985,
      "learning_rate": 4.9931407070965254e-05,
      "loss": 1.1238,
      "num_input_tokens_seen": 97888,
      "step": 10
    },
    {
      "epoch": 0.07058823529411765,
      "grad_norm": 1.0708130598068237,
      "learning_rate": 4.984575415649019e-05,
      "loss": 0.9474,
      "num_input_tokens_seen": 145664,
      "step": 15
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 0.8778848648071289,
      "learning_rate": 4.97260046830541e-05,
      "loss": 0.7893,
      "num_input_tokens_seen": 192544,
      "step": 20
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.9257701635360718,
      "learning_rate": 4.957232298638036e-05,
      "loss": 0.7478,
      "num_input_tokens_seen": 241760,
      "step": 25
    },
    {
      "epoch": 0.1411764705882353,
      "grad_norm": 0.8825921416282654,
      "learning_rate": 4.9384919968379945e-05,
      "loss": 0.6895,
      "num_input_tokens_seen": 289600,
      "step": 30
    },
    {
      "epoch": 0.16470588235294117,
      "grad_norm": 0.8157197833061218,
      "learning_rate": 4.916405280772462e-05,
      "loss": 0.6936,
      "num_input_tokens_seen": 340816,
      "step": 35
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 0.8392460346221924,
      "learning_rate": 4.891002460691306e-05,
      "loss": 0.6835,
      "num_input_tokens_seen": 389424,
      "step": 40
    },
    {
      "epoch": 0.21176470588235294,
      "grad_norm": 0.7645203471183777,
      "learning_rate": 4.862318397631434e-05,
      "loss": 0.6284,
      "num_input_tokens_seen": 438224,
      "step": 45
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.0171334743499756,
      "learning_rate": 4.83039245557597e-05,
      "loss": 0.6165,
      "num_input_tokens_seen": 486496,
      "step": 50
    },
    {
      "epoch": 0.25882352941176473,
      "grad_norm": 0.7693806290626526,
      "learning_rate": 4.795268447433907e-05,
      "loss": 0.5757,
      "num_input_tokens_seen": 537520,
      "step": 55
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 0.8031296133995056,
      "learning_rate": 4.756994574914359e-05,
      "loss": 0.5638,
      "num_input_tokens_seen": 584288,
      "step": 60
    },
    {
      "epoch": 0.3058823529411765,
      "grad_norm": 0.7544689774513245,
      "learning_rate": 4.715623362377939e-05,
      "loss": 0.5522,
      "num_input_tokens_seen": 633984,
      "step": 65
    },
    {
      "epoch": 0.32941176470588235,
      "grad_norm": 0.8555608987808228,
      "learning_rate": 4.6712115847560355e-05,
      "loss": 0.5217,
      "num_input_tokens_seen": 685600,
      "step": 70
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 0.8717510104179382,
      "learning_rate": 4.6238201896369055e-05,
      "loss": 0.5436,
      "num_input_tokens_seen": 734496,
      "step": 75
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 0.9173887372016907,
      "learning_rate": 4.573514213625505e-05,
      "loss": 0.514,
      "num_input_tokens_seen": 784720,
      "step": 80
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8762289881706238,
      "learning_rate": 4.5203626930918455e-05,
      "loss": 0.5073,
      "num_input_tokens_seen": 837808,
      "step": 85
    },
    {
      "epoch": 0.4235294117647059,
      "grad_norm": 0.9715367555618286,
      "learning_rate": 4.464438569430354e-05,
      "loss": 0.5384,
      "num_input_tokens_seen": 888032,
      "step": 90
    },
    {
      "epoch": 0.4470588235294118,
      "grad_norm": 0.9435672163963318,
      "learning_rate": 4.40581858896025e-05,
      "loss": 0.521,
      "num_input_tokens_seen": 938032,
      "step": 95
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.8672516345977783,
      "learning_rate": 4.344583197604318e-05,
      "loss": 0.4765,
      "num_input_tokens_seen": 988176,
      "step": 100
    },
    {
      "epoch": 0.49411764705882355,
      "grad_norm": 1.0466370582580566,
      "learning_rate": 4.2808164304906026e-05,
      "loss": 0.5121,
      "num_input_tokens_seen": 1040016,
      "step": 105
    },
    {
      "epoch": 0.5176470588235295,
      "grad_norm": 0.9898332953453064,
      "learning_rate": 4.214605796628527e-05,
      "loss": 0.4972,
      "num_input_tokens_seen": 1090624,
      "step": 110
    },
    {
      "epoch": 0.5411764705882353,
      "grad_norm": 1.0176562070846558,
      "learning_rate": 4.14604215881771e-05,
      "loss": 0.488,
      "num_input_tokens_seen": 1143280,
      "step": 115
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.9806397557258606,
      "learning_rate": 4.075219608954278e-05,
      "loss": 0.489,
      "num_input_tokens_seen": 1191616,
      "step": 120
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.9629871249198914,
      "learning_rate": 4.00223533890578e-05,
      "loss": 0.4853,
      "num_input_tokens_seen": 1240144,
      "step": 125
    },
    {
      "epoch": 0.611764705882353,
      "grad_norm": 0.9678134918212891,
      "learning_rate": 3.927189507131938e-05,
      "loss": 0.4718,
      "num_input_tokens_seen": 1288912,
      "step": 130
    },
    {
      "epoch": 0.6352941176470588,
      "grad_norm": 1.0481890439987183,
      "learning_rate": 3.8501851012342446e-05,
      "loss": 0.4936,
      "num_input_tokens_seen": 1335472,
      "step": 135
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.9465301632881165,
      "learning_rate": 3.7713277966230514e-05,
      "loss": 0.4673,
      "num_input_tokens_seen": 1385568,
      "step": 140
    },
    {
      "epoch": 0.6823529411764706,
      "grad_norm": 1.0117136240005493,
      "learning_rate": 3.690725811496092e-05,
      "loss": 0.4676,
      "num_input_tokens_seen": 1434384,
      "step": 145
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.9891406297683716,
      "learning_rate": 3.608489758327472e-05,
      "loss": 0.5079,
      "num_input_tokens_seen": 1488448,
      "step": 150
    },
    {
      "epoch": 0.7294117647058823,
      "grad_norm": 0.9826067090034485,
      "learning_rate": 3.524732492070915e-05,
      "loss": 0.4713,
      "num_input_tokens_seen": 1537472,
      "step": 155
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.9447062611579895,
      "learning_rate": 3.4395689552855955e-05,
      "loss": 0.4616,
      "num_input_tokens_seen": 1587072,
      "step": 160
    },
    {
      "epoch": 0.7764705882352941,
      "grad_norm": 1.0301213264465332,
      "learning_rate": 3.3531160203970805e-05,
      "loss": 0.4445,
      "num_input_tokens_seen": 1636624,
      "step": 165
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.1652017831802368,
      "learning_rate": 3.265492329309867e-05,
      "loss": 0.4762,
      "num_input_tokens_seen": 1687904,
      "step": 170
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 1.1255770921707153,
      "learning_rate": 3.1768181305916066e-05,
      "loss": 0.4626,
      "num_input_tokens_seen": 1734544,
      "step": 175
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 1.0519174337387085,
      "learning_rate": 3.0872151144524595e-05,
      "loss": 0.4554,
      "num_input_tokens_seen": 1781216,
      "step": 180
    },
    {
      "epoch": 0.8705882352941177,
      "grad_norm": 1.1458220481872559,
      "learning_rate": 2.996806245746044e-05,
      "loss": 0.4418,
      "num_input_tokens_seen": 1830144,
      "step": 185
    },
    {
      "epoch": 0.8941176470588236,
      "grad_norm": 1.2313694953918457,
      "learning_rate": 2.9057155952211502e-05,
      "loss": 0.4676,
      "num_input_tokens_seen": 1876288,
      "step": 190
    },
    {
      "epoch": 0.9176470588235294,
      "grad_norm": 1.2109845876693726,
      "learning_rate": 2.8140681692558035e-05,
      "loss": 0.4425,
      "num_input_tokens_seen": 1925792,
      "step": 195
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.0616289377212524,
      "learning_rate": 2.7219897383073373e-05,
      "loss": 0.4548,
      "num_input_tokens_seen": 1974368,
      "step": 200
    },
    {
      "epoch": 0.9647058823529412,
      "grad_norm": 1.1032544374465942,
      "learning_rate": 2.629606664313896e-05,
      "loss": 0.4302,
      "num_input_tokens_seen": 2022080,
      "step": 205
    },
    {
      "epoch": 0.9882352941176471,
      "grad_norm": 1.2024751901626587,
      "learning_rate": 2.537045727284232e-05,
      "loss": 0.4132,
      "num_input_tokens_seen": 2069920,
      "step": 210
    },
    {
      "epoch": 1.011764705882353,
      "grad_norm": 1.0001943111419678,
      "learning_rate": 2.444433951313772e-05,
      "loss": 0.4214,
      "num_input_tokens_seen": 2120704,
      "step": 215
    },
    {
      "epoch": 1.035294117647059,
      "grad_norm": 1.0397372245788574,
      "learning_rate": 2.3518984302657146e-05,
      "loss": 0.4088,
      "num_input_tokens_seen": 2171968,
      "step": 220
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 1.1281183958053589,
      "learning_rate": 2.259566153356389e-05,
      "loss": 0.4199,
      "num_input_tokens_seen": 2223472,
      "step": 225
    },
    {
      "epoch": 1.0823529411764705,
      "grad_norm": 1.1637018918991089,
      "learning_rate": 2.1675638308842145e-05,
      "loss": 0.4273,
      "num_input_tokens_seen": 2273296,
      "step": 230
    },
    {
      "epoch": 1.1058823529411765,
      "grad_norm": 1.2093477249145508,
      "learning_rate": 2.0760177203414368e-05,
      "loss": 0.4042,
      "num_input_tokens_seen": 2323008,
      "step": 235
    },
    {
      "epoch": 1.1294117647058823,
      "grad_norm": 1.1976971626281738,
      "learning_rate": 1.9850534531472546e-05,
      "loss": 0.4275,
      "num_input_tokens_seen": 2373744,
      "step": 240
    },
    {
      "epoch": 1.1529411764705881,
      "grad_norm": 1.1152101755142212,
      "learning_rate": 1.8947958622401328e-05,
      "loss": 0.4483,
      "num_input_tokens_seen": 2425216,
      "step": 245
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.0972641706466675,
      "learning_rate": 1.8053688107658908e-05,
      "loss": 0.4024,
      "num_input_tokens_seen": 2472864,
      "step": 250
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.12717604637146,
      "learning_rate": 1.7168950220966614e-05,
      "loss": 0.4363,
      "num_input_tokens_seen": 2523344,
      "step": 255
    },
    {
      "epoch": 1.223529411764706,
      "grad_norm": 1.2230875492095947,
      "learning_rate": 1.6294959114140034e-05,
      "loss": 0.383,
      "num_input_tokens_seen": 2571936,
      "step": 260
    },
    {
      "epoch": 1.2470588235294118,
      "grad_norm": 1.2656056880950928,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.4287,
      "num_input_tokens_seen": 2622560,
      "step": 265
    },
    {
      "epoch": 1.2705882352941176,
      "grad_norm": 1.186041235923767,
      "learning_rate": 1.4583998460759424e-05,
      "loss": 0.3686,
      "num_input_tokens_seen": 2669232,
      "step": 270
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 1.2343655824661255,
      "learning_rate": 1.3749376915816886e-05,
      "loss": 0.4059,
      "num_input_tokens_seen": 2718128,
      "step": 275
    },
    {
      "epoch": 1.3176470588235294,
      "grad_norm": 1.131495714187622,
      "learning_rate": 1.2930194931731382e-05,
      "loss": 0.4242,
      "num_input_tokens_seen": 2766432,
      "step": 280
    },
    {
      "epoch": 1.3411764705882354,
      "grad_norm": 1.0469223260879517,
      "learning_rate": 1.2127576696025828e-05,
      "loss": 0.4326,
      "num_input_tokens_seen": 2819760,
      "step": 285
    },
    {
      "epoch": 1.3647058823529412,
      "grad_norm": 1.315108060836792,
      "learning_rate": 1.1342623665304209e-05,
      "loss": 0.4266,
      "num_input_tokens_seen": 2867920,
      "step": 290
    },
    {
      "epoch": 1.388235294117647,
      "grad_norm": 1.168626308441162,
      "learning_rate": 1.0576413053690327e-05,
      "loss": 0.4049,
      "num_input_tokens_seen": 2914944,
      "step": 295
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 1.13846755027771,
      "learning_rate": 9.829996354535172e-06,
      "loss": 0.4102,
      "num_input_tokens_seen": 2965600,
      "step": 300
    },
    {
      "epoch": 1.4352941176470588,
      "grad_norm": 1.24168062210083,
      "learning_rate": 9.104397897421623e-06,
      "loss": 0.4261,
      "num_input_tokens_seen": 3015728,
      "step": 305
    },
    {
      "epoch": 1.4588235294117646,
      "grad_norm": 1.1973497867584229,
      "learning_rate": 8.400613442446948e-06,
      "loss": 0.4109,
      "num_input_tokens_seen": 3065328,
      "step": 310
    },
    {
      "epoch": 1.4823529411764707,
      "grad_norm": 1.0736428499221802,
      "learning_rate": 7.719608813711848e-06,
      "loss": 0.3982,
      "num_input_tokens_seen": 3114720,
      "step": 315
    },
    {
      "epoch": 1.5058823529411764,
      "grad_norm": 1.2293542623519897,
      "learning_rate": 7.062318573891716e-06,
      "loss": 0.4265,
      "num_input_tokens_seen": 3163008,
      "step": 320
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 1.2456164360046387,
      "learning_rate": 6.429644741708779e-06,
      "loss": 0.4014,
      "num_input_tokens_seen": 3211408,
      "step": 325
    },
    {
      "epoch": 1.5529411764705883,
      "grad_norm": 1.1817117929458618,
      "learning_rate": 5.822455554065217e-06,
      "loss": 0.425,
      "num_input_tokens_seen": 3263808,
      "step": 330
    },
    {
      "epoch": 1.576470588235294,
      "grad_norm": 1.2817317247390747,
      "learning_rate": 5.241584274536259e-06,
      "loss": 0.3785,
      "num_input_tokens_seen": 3311056,
      "step": 335
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.2116546630859375,
      "learning_rate": 4.687828049857967e-06,
      "loss": 0.4034,
      "num_input_tokens_seen": 3358224,
      "step": 340
    },
    {
      "epoch": 1.6235294117647059,
      "grad_norm": 1.3325591087341309,
      "learning_rate": 4.161946815979403e-06,
      "loss": 0.4075,
      "num_input_tokens_seen": 3409024,
      "step": 345
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 1.0810184478759766,
      "learning_rate": 3.6646622551801345e-06,
      "loss": 0.3496,
      "num_input_tokens_seen": 3457616,
      "step": 350
    },
    {
      "epoch": 1.6705882352941175,
      "grad_norm": 1.0979664325714111,
      "learning_rate": 3.19665680568445e-06,
      "loss": 0.4106,
      "num_input_tokens_seen": 3510768,
      "step": 355
    },
    {
      "epoch": 1.6941176470588235,
      "grad_norm": 1.143621563911438,
      "learning_rate": 2.75857272513132e-06,
      "loss": 0.4093,
      "num_input_tokens_seen": 3556912,
      "step": 360
    },
    {
      "epoch": 1.7176470588235295,
      "grad_norm": 1.2018797397613525,
      "learning_rate": 2.351011209185336e-06,
      "loss": 0.379,
      "num_input_tokens_seen": 3606016,
      "step": 365
    },
    {
      "epoch": 1.7411764705882353,
      "grad_norm": 1.0897295475006104,
      "learning_rate": 1.9745315664982276e-06,
      "loss": 0.3996,
      "num_input_tokens_seen": 3654256,
      "step": 370
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 1.2107083797454834,
      "learning_rate": 1.6296504511531836e-06,
      "loss": 0.4016,
      "num_input_tokens_seen": 3704528,
      "step": 375
    },
    {
      "epoch": 1.788235294117647,
      "grad_norm": 1.1322784423828125,
      "learning_rate": 1.3168411536452152e-06,
      "loss": 0.3769,
      "num_input_tokens_seen": 3752208,
      "step": 380
    },
    {
      "epoch": 1.811764705882353,
      "grad_norm": 1.1542903184890747,
      "learning_rate": 1.036532951370736e-06,
      "loss": 0.4045,
      "num_input_tokens_seen": 3805232,
      "step": 385
    },
    {
      "epoch": 1.835294117647059,
      "grad_norm": 1.2877768278121948,
      "learning_rate": 7.891105195175358e-07,
      "loss": 0.4051,
      "num_input_tokens_seen": 3854864,
      "step": 390
    },
    {
      "epoch": 1.8588235294117648,
      "grad_norm": 1.2475833892822266,
      "learning_rate": 5.749134031637349e-07,
      "loss": 0.3934,
      "num_input_tokens_seen": 3904880,
      "step": 395
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 1.152550458908081,
      "learning_rate": 3.9423555131007925e-07,
      "loss": 0.41,
      "num_input_tokens_seen": 3953728,
      "step": 400
    },
    {
      "epoch": 1.9058823529411764,
      "grad_norm": 1.1438477039337158,
      "learning_rate": 2.473249134850808e-07,
      "loss": 0.3902,
      "num_input_tokens_seen": 4002944,
      "step": 405
    },
    {
      "epoch": 1.9294117647058824,
      "grad_norm": 1.143480896949768,
      "learning_rate": 1.343830994765982e-07,
      "loss": 0.3766,
      "num_input_tokens_seen": 4050880,
      "step": 410
    },
    {
      "epoch": 1.9529411764705882,
      "grad_norm": 1.2639435529708862,
      "learning_rate": 5.5565102656787714e-08,
      "loss": 0.3826,
      "num_input_tokens_seen": 4098064,
      "step": 415
    },
    {
      "epoch": 1.9764705882352942,
      "grad_norm": 1.1847045421600342,
      "learning_rate": 1.0979087280141298e-08,
      "loss": 0.4366,
      "num_input_tokens_seen": 4147296,
      "step": 420
    },
    {
      "epoch": 1.9952941176470587,
      "num_input_tokens_seen": 4186528,
      "step": 424,
      "total_flos": 5.002960174252032e+16,
      "train_loss": 0.48991220936460317,
      "train_runtime": 1751.8031,
      "train_samples_per_second": 3.882,
      "train_steps_per_second": 0.242
    }
  ],
  "logging_steps": 5,
  "max_steps": 424,
  "num_input_tokens_seen": 4186528,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.002960174252032e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}