{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 52,
  "global_step": 52,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 13.78187084197998,
      "learning_rate": 1e-05,
      "loss": 2.6171875,
      "step": 1
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 9.845561981201172,
      "learning_rate": 9.990877771116588e-06,
      "loss": 2.373046875,
      "step": 2
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 8.01469898223877,
      "learning_rate": 9.96354437049027e-06,
      "loss": 2.2021484375,
      "step": 3
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 5.164867877960205,
      "learning_rate": 9.91809953473572e-06,
      "loss": 1.9962158203125,
      "step": 4
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 4.263365268707275,
      "learning_rate": 9.854709087130261e-06,
      "loss": 1.894287109375,
      "step": 5
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 3.3784377574920654,
      "learning_rate": 9.77360433254273e-06,
      "loss": 1.86181640625,
      "step": 6
    },
    {
      "epoch": 0.2692307692307692,
      "grad_norm": 2.9527230262756348,
      "learning_rate": 9.675081213427076e-06,
      "loss": 1.834716796875,
      "step": 7
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 2.2422053813934326,
      "learning_rate": 9.55949922996045e-06,
      "loss": 1.65478515625,
      "step": 8
    },
    {
      "epoch": 0.34615384615384615,
      "grad_norm": 1.7632695436477661,
      "learning_rate": 9.427280128266049e-06,
      "loss": 1.589111328125,
      "step": 9
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 1.6509746313095093,
      "learning_rate": 9.278906361507238e-06,
      "loss": 1.593994140625,
      "step": 10
    },
    {
      "epoch": 0.4230769230769231,
      "grad_norm": 1.3932156562805176,
      "learning_rate": 9.114919329468283e-06,
      "loss": 1.4892578125,
      "step": 11
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 1.2194513082504272,
      "learning_rate": 8.935917403045251e-06,
      "loss": 1.54052734375,
      "step": 12
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.9014191031455994,
      "learning_rate": 8.742553740855507e-06,
      "loss": 1.5517578125,
      "step": 13
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.7796593904495239,
      "learning_rate": 8.535533905932739e-06,
      "loss": 1.50323486328125,
      "step": 14
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 0.6279335021972656,
      "learning_rate": 8.315613291203977e-06,
      "loss": 1.46630859375,
      "step": 15
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.6258265972137451,
      "learning_rate": 8.083594363142717e-06,
      "loss": 1.45782470703125,
      "step": 16
    },
    {
      "epoch": 0.6538461538461539,
      "grad_norm": 0.5115531086921692,
      "learning_rate": 7.84032373365578e-06,
      "loss": 1.43798828125,
      "step": 17
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.4573651850223541,
      "learning_rate": 7.586689070888284e-06,
      "loss": 1.4058837890625,
      "step": 18
    },
    {
      "epoch": 0.7307692307692307,
      "grad_norm": 0.46966230869293213,
      "learning_rate": 7.323615860218844e-06,
      "loss": 1.47265625,
      "step": 19
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.3782135546207428,
      "learning_rate": 7.052064027263785e-06,
      "loss": 1.4276123046875,
      "step": 20
    },
    {
      "epoch": 0.8076923076923077,
      "grad_norm": 0.3979575037956238,
      "learning_rate": 6.773024435212678e-06,
      "loss": 1.484375,
      "step": 21
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.41323113441467285,
      "learning_rate": 6.487515269276015e-06,
      "loss": 1.370269775390625,
      "step": 22
    },
    {
      "epoch": 0.8846153846153846,
      "grad_norm": 0.384005606174469,
      "learning_rate": 6.1965783214377895e-06,
      "loss": 1.41943359375,
      "step": 23
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.3821006715297699,
      "learning_rate": 5.90127518906953e-06,
      "loss": 1.39990234375,
      "step": 24
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 0.385856032371521,
      "learning_rate": 5.6026834012766155e-06,
      "loss": 1.47509765625,
      "step": 25
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.32634466886520386,
      "learning_rate": 5.301892487111431e-06,
      "loss": 1.41748046875,
      "step": 26
    },
    {
      "epoch": 1.0384615384615385,
      "grad_norm": 0.3082049489021301,
      "learning_rate": 5e-06,
      "loss": 1.37939453125,
      "step": 27
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.2960004210472107,
      "learning_rate": 4.69810751288857e-06,
      "loss": 1.431640625,
      "step": 28
    },
    {
      "epoch": 1.1153846153846154,
      "grad_norm": 0.2712954878807068,
      "learning_rate": 4.397316598723385e-06,
      "loss": 1.39599609375,
      "step": 29
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.2660493552684784,
      "learning_rate": 4.098724810930472e-06,
      "loss": 1.3868408203125,
      "step": 30
    },
    {
      "epoch": 1.1923076923076923,
      "grad_norm": 0.2757558822631836,
      "learning_rate": 3.803421678562213e-06,
      "loss": 1.3758544921875,
      "step": 31
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.26696985960006714,
      "learning_rate": 3.5124847307239863e-06,
      "loss": 1.4422607421875,
      "step": 32
    },
    {
      "epoch": 1.2692307692307692,
      "grad_norm": 0.29158878326416016,
      "learning_rate": 3.226975564787322e-06,
      "loss": 1.507568359375,
      "step": 33
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.2519815266132355,
      "learning_rate": 2.947935972736217e-06,
      "loss": 1.3935546875,
      "step": 34
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 0.24109189212322235,
      "learning_rate": 2.6763841397811576e-06,
      "loss": 1.364501953125,
      "step": 35
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.2500540316104889,
      "learning_rate": 2.4133109291117156e-06,
      "loss": 1.392822265625,
      "step": 36
    },
    {
      "epoch": 1.4230769230769231,
      "grad_norm": 0.35815808176994324,
      "learning_rate": 2.159676266344222e-06,
      "loss": 1.31640625,
      "step": 37
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.299280047416687,
      "learning_rate": 1.9164056368572847e-06,
      "loss": 1.385498046875,
      "step": 38
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.263439804315567,
      "learning_rate": 1.6843867087960252e-06,
      "loss": 1.42724609375,
      "step": 39
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.22188825905323029,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 1.391357421875,
      "step": 40
    },
    {
      "epoch": 1.5769230769230769,
      "grad_norm": 0.23454146087169647,
      "learning_rate": 1.257446259144494e-06,
      "loss": 1.3671875,
      "step": 41
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.2985825538635254,
      "learning_rate": 1.0640825969547498e-06,
      "loss": 1.36846923828125,
      "step": 42
    },
    {
      "epoch": 1.6538461538461537,
      "grad_norm": 0.21381421387195587,
      "learning_rate": 8.850806705317183e-07,
      "loss": 1.3594970703125,
      "step": 43
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.21711355447769165,
      "learning_rate": 7.210936384927631e-07,
      "loss": 1.3319091796875,
      "step": 44
    },
    {
      "epoch": 1.7307692307692308,
      "grad_norm": 0.2467353194952011,
      "learning_rate": 5.727198717339511e-07,
      "loss": 1.40771484375,
      "step": 45
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.22233083844184875,
      "learning_rate": 4.405007700395497e-07,
      "loss": 1.37060546875,
      "step": 46
    },
    {
      "epoch": 1.8076923076923077,
      "grad_norm": 0.2567121088504791,
      "learning_rate": 3.2491878657292643e-07,
      "loss": 1.43212890625,
      "step": 47
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.25618961453437805,
      "learning_rate": 2.2639566745727203e-07,
      "loss": 1.32318115234375,
      "step": 48
    },
    {
      "epoch": 1.8846153846153846,
      "grad_norm": 0.2310512363910675,
      "learning_rate": 1.4529091286973994e-07,
      "loss": 1.375732421875,
      "step": 49
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.2249426245689392,
      "learning_rate": 8.190046526428241e-08,
      "loss": 1.361328125,
      "step": 50
    },
    {
      "epoch": 1.9615384615384617,
      "grad_norm": 0.25166356563568115,
      "learning_rate": 3.645562950973014e-08,
      "loss": 1.4404296875,
      "step": 51
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.21272313594818115,
      "learning_rate": 9.12222888341252e-09,
      "loss": 1.3857421875,
      "step": 52
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.439453125,
      "eval_runtime": 9.74,
      "eval_samples_per_second": 0.308,
      "eval_steps_per_second": 0.103,
      "step": 52
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 52,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.0288909949167206e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}