{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9952941176470587,
  "eval_steps": 500,
  "global_step": 212,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047058823529411764,
      "grad_norm": 0.8513572216033936,
      "learning_rate": 4.9931407070965254e-05,
      "loss": 0.989,
      "num_input_tokens_seen": 97856,
      "step": 5
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 0.5562562942504883,
      "learning_rate": 4.97260046830541e-05,
      "loss": 0.7203,
      "num_input_tokens_seen": 192320,
      "step": 10
    },
    {
      "epoch": 0.1411764705882353,
      "grad_norm": 0.44545215368270874,
      "learning_rate": 4.9384919968379945e-05,
      "loss": 0.5976,
      "num_input_tokens_seen": 288720,
      "step": 15
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 0.3797588050365448,
      "learning_rate": 4.891002460691306e-05,
      "loss": 0.5496,
      "num_input_tokens_seen": 389008,
      "step": 20
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.3744553327560425,
      "learning_rate": 4.83039245557597e-05,
      "loss": 0.512,
      "num_input_tokens_seen": 485488,
      "step": 25
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 0.33631229400634766,
      "learning_rate": 4.756994574914359e-05,
      "loss": 0.4675,
      "num_input_tokens_seen": 582752,
      "step": 30
    },
    {
      "epoch": 0.32941176470588235,
      "grad_norm": 0.3476051986217499,
      "learning_rate": 4.6712115847560355e-05,
      "loss": 0.4507,
      "num_input_tokens_seen": 684016,
      "step": 35
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 0.3526253402233124,
      "learning_rate": 4.573514213625505e-05,
      "loss": 0.436,
      "num_input_tokens_seen": 782848,
      "step": 40
    },
    {
      "epoch": 0.4235294117647059,
      "grad_norm": 0.34273335337638855,
      "learning_rate": 4.464438569430354e-05,
      "loss": 0.4339,
      "num_input_tokens_seen": 885520,
      "step": 45
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.31332990527153015,
      "learning_rate": 4.344583197604318e-05,
      "loss": 0.4056,
      "num_input_tokens_seen": 985248,
      "step": 50
    },
    {
      "epoch": 0.5176470588235295,
      "grad_norm": 0.38881802558898926,
      "learning_rate": 4.214605796628527e-05,
      "loss": 0.412,
      "num_input_tokens_seen": 1086800,
      "step": 55
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.37956130504608154,
      "learning_rate": 4.075219608954278e-05,
      "loss": 0.3917,
      "num_input_tokens_seen": 1187312,
      "step": 60
    },
    {
      "epoch": 0.611764705882353,
      "grad_norm": 0.36925989389419556,
      "learning_rate": 3.927189507131938e-05,
      "loss": 0.3879,
      "num_input_tokens_seen": 1284656,
      "step": 65
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.3496692478656769,
      "learning_rate": 3.7713277966230514e-05,
      "loss": 0.3828,
      "num_input_tokens_seen": 1380720,
      "step": 70
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.3336363434791565,
      "learning_rate": 3.608489758327472e-05,
      "loss": 0.3897,
      "num_input_tokens_seen": 1483248,
      "step": 75
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.3519847095012665,
      "learning_rate": 3.4395689552855955e-05,
      "loss": 0.368,
      "num_input_tokens_seen": 1581216,
      "step": 80
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.41548871994018555,
      "learning_rate": 3.265492329309867e-05,
      "loss": 0.367,
      "num_input_tokens_seen": 1681520,
      "step": 85
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 0.4266488552093506,
      "learning_rate": 3.0872151144524595e-05,
      "loss": 0.3691,
      "num_input_tokens_seen": 1774368,
      "step": 90
    },
    {
      "epoch": 0.8941176470588236,
      "grad_norm": 0.3932451903820038,
      "learning_rate": 2.9057155952211502e-05,
      "loss": 0.3611,
      "num_input_tokens_seen": 1869344,
      "step": 95
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.3845691382884979,
      "learning_rate": 2.7219897383073373e-05,
      "loss": 0.3534,
      "num_input_tokens_seen": 1967664,
      "step": 100
    },
    {
      "epoch": 0.9882352941176471,
      "grad_norm": 0.391476571559906,
      "learning_rate": 2.537045727284232e-05,
      "loss": 0.3326,
      "num_input_tokens_seen": 2063040,
      "step": 105
    },
    {
      "epoch": 1.035294117647059,
      "grad_norm": 0.43011003732681274,
      "learning_rate": 2.3518984302657146e-05,
      "loss": 0.3415,
      "num_input_tokens_seen": 2164608,
      "step": 110
    },
    {
      "epoch": 1.0823529411764705,
      "grad_norm": 0.4368140995502472,
      "learning_rate": 2.1675638308842145e-05,
      "loss": 0.3523,
      "num_input_tokens_seen": 2265696,
      "step": 115
    },
    {
      "epoch": 1.1294117647058823,
      "grad_norm": 0.42045897245407104,
      "learning_rate": 1.9850534531472546e-05,
      "loss": 0.338,
      "num_input_tokens_seen": 2365488,
      "step": 120
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.4001467525959015,
      "learning_rate": 1.8053688107658908e-05,
      "loss": 0.3509,
      "num_input_tokens_seen": 2464208,
      "step": 125
    },
    {
      "epoch": 1.223529411764706,
      "grad_norm": 0.40329447388648987,
      "learning_rate": 1.6294959114140034e-05,
      "loss": 0.3317,
      "num_input_tokens_seen": 2563424,
      "step": 130
    },
    {
      "epoch": 1.2705882352941176,
      "grad_norm": 0.4356438219547272,
      "learning_rate": 1.4583998460759424e-05,
      "loss": 0.3271,
      "num_input_tokens_seen": 2660752,
      "step": 135
    },
    {
      "epoch": 1.3176470588235294,
      "grad_norm": 0.43610551953315735,
      "learning_rate": 1.2930194931731382e-05,
      "loss": 0.3399,
      "num_input_tokens_seen": 2757168,
      "step": 140
    },
    {
      "epoch": 1.3647058823529412,
      "grad_norm": 0.44853097200393677,
      "learning_rate": 1.1342623665304209e-05,
      "loss": 0.3558,
      "num_input_tokens_seen": 2858336,
      "step": 145
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.3944084942340851,
      "learning_rate": 9.829996354535172e-06,
      "loss": 0.3366,
      "num_input_tokens_seen": 2955472,
      "step": 150
    },
    {
      "epoch": 1.4588235294117646,
      "grad_norm": 0.40302279591560364,
      "learning_rate": 8.400613442446948e-06,
      "loss": 0.346,
      "num_input_tokens_seen": 3054528,
      "step": 155
    },
    {
      "epoch": 1.5058823529411764,
      "grad_norm": 0.4172155559062958,
      "learning_rate": 7.062318573891716e-06,
      "loss": 0.3442,
      "num_input_tokens_seen": 3152064,
      "step": 160
    },
    {
      "epoch": 1.5529411764705883,
      "grad_norm": 0.42591097950935364,
      "learning_rate": 5.822455554065217e-06,
      "loss": 0.3475,
      "num_input_tokens_seen": 3252064,
      "step": 165
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.4681831896305084,
      "learning_rate": 4.687828049857967e-06,
      "loss": 0.322,
      "num_input_tokens_seen": 3346512,
      "step": 170
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.42528390884399414,
      "learning_rate": 3.6646622551801345e-06,
      "loss": 0.3108,
      "num_input_tokens_seen": 3445360,
      "step": 175
    },
    {
      "epoch": 1.6941176470588235,
      "grad_norm": 0.4077628254890442,
      "learning_rate": 2.75857272513132e-06,
      "loss": 0.3432,
      "num_input_tokens_seen": 3544432,
      "step": 180
    },
    {
      "epoch": 1.7411764705882353,
      "grad_norm": 0.4058278501033783,
      "learning_rate": 1.9745315664982276e-06,
      "loss": 0.3236,
      "num_input_tokens_seen": 3641504,
      "step": 185
    },
    {
      "epoch": 1.788235294117647,
      "grad_norm": 0.3715575635433197,
      "learning_rate": 1.3168411536452152e-06,
      "loss": 0.3169,
      "num_input_tokens_seen": 3739504,
      "step": 190
    },
    {
      "epoch": 1.835294117647059,
      "grad_norm": 0.4317086935043335,
      "learning_rate": 7.891105195175358e-07,
      "loss": 0.3325,
      "num_input_tokens_seen": 3841712,
      "step": 195
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.3929608464241028,
      "learning_rate": 3.9423555131007925e-07,
      "loss": 0.3355,
      "num_input_tokens_seen": 3940320,
      "step": 200
    },
    {
      "epoch": 1.9294117647058824,
      "grad_norm": 0.4199908673763275,
      "learning_rate": 1.343830994765982e-07,
      "loss": 0.32,
      "num_input_tokens_seen": 4037264,
      "step": 205
    },
    {
      "epoch": 1.9764705882352942,
      "grad_norm": 0.43150097131729126,
      "learning_rate": 1.0979087280141298e-08,
      "loss": 0.3349,
      "num_input_tokens_seen": 4133360,
      "step": 210
    },
    {
      "epoch": 1.9952941176470587,
      "num_input_tokens_seen": 4172960,
      "step": 212,
      "total_flos": 1.8843158217490432e+17,
      "train_loss": 0.39808354709508287,
      "train_runtime": 2416.3268,
      "train_samples_per_second": 2.814,
      "train_steps_per_second": 0.088
    }
  ],
  "logging_steps": 5,
  "max_steps": 212,
  "num_input_tokens_seen": 4172960,
  "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": 1.8843158217490432e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}