{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13652809065465218,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001365280906546522,
      "eval_loss": 3.0663866996765137,
      "eval_runtime": 174.8965,
      "eval_samples_per_second": 35.267,
      "eval_steps_per_second": 8.817,
      "step": 1
    },
    {
      "epoch": 0.00682640453273261,
      "grad_norm": 49.984615325927734,
      "learning_rate": 0.00025,
      "loss": 8.7347,
      "step": 50
    },
    {
      "epoch": 0.01365280906546522,
      "grad_norm": 81.82232666015625,
      "learning_rate": 0.00025,
      "loss": 8.9878,
      "step": 100
    },
    {
      "epoch": 0.01365280906546522,
      "eval_loss": 2.4946627616882324,
      "eval_runtime": 175.4739,
      "eval_samples_per_second": 35.151,
      "eval_steps_per_second": 8.788,
      "step": 100
    },
    {
      "epoch": 0.020479213598197828,
      "grad_norm": 56.2267951965332,
      "learning_rate": 0.00025,
      "loss": 8.5546,
      "step": 150
    },
    {
      "epoch": 0.02730561813093044,
      "grad_norm": 141.20570373535156,
      "learning_rate": 0.00025,
      "loss": 9.0165,
      "step": 200
    },
    {
      "epoch": 0.02730561813093044,
      "eval_loss": 2.3397319316864014,
      "eval_runtime": 175.5397,
      "eval_samples_per_second": 35.137,
      "eval_steps_per_second": 8.784,
      "step": 200
    },
    {
      "epoch": 0.034132022663663046,
      "grad_norm": 71.43548583984375,
      "learning_rate": 0.00025,
      "loss": 8.9307,
      "step": 250
    },
    {
      "epoch": 0.040958427196395655,
      "grad_norm": 74.2425765991211,
      "learning_rate": 0.00025,
      "loss": 8.8931,
      "step": 300
    },
    {
      "epoch": 0.040958427196395655,
      "eval_loss": 2.365124225616455,
      "eval_runtime": 175.691,
      "eval_samples_per_second": 35.107,
      "eval_steps_per_second": 8.777,
      "step": 300
    },
    {
      "epoch": 0.04778483172912827,
      "grad_norm": 58.193336486816406,
      "learning_rate": 0.00025,
      "loss": 8.7392,
      "step": 350
    },
    {
      "epoch": 0.05461123626186088,
      "grad_norm": 86.09171295166016,
      "learning_rate": 0.00025,
      "loss": 8.7976,
      "step": 400
    },
    {
      "epoch": 0.05461123626186088,
      "eval_loss": 2.31371808052063,
      "eval_runtime": 175.49,
      "eval_samples_per_second": 35.147,
      "eval_steps_per_second": 8.787,
      "step": 400
    },
    {
      "epoch": 0.06143764079459349,
      "grad_norm": 72.92398834228516,
      "learning_rate": 0.00025,
      "loss": 8.8149,
      "step": 450
    },
    {
      "epoch": 0.06826404532732609,
      "grad_norm": 64.2607192993164,
      "learning_rate": 0.00025,
      "loss": 8.8603,
      "step": 500
    },
    {
      "epoch": 0.06826404532732609,
      "eval_loss": 2.338709592819214,
      "eval_runtime": 175.6396,
      "eval_samples_per_second": 35.117,
      "eval_steps_per_second": 8.779,
      "step": 500
    },
    {
      "epoch": 0.07509044986005871,
      "grad_norm": 88.5269775390625,
      "learning_rate": 0.00025,
      "loss": 8.8715,
      "step": 550
    },
    {
      "epoch": 0.08191685439279131,
      "grad_norm": 69.88550567626953,
      "learning_rate": 0.00025,
      "loss": 9.0193,
      "step": 600
    },
    {
      "epoch": 0.08191685439279131,
      "eval_loss": 2.384012222290039,
      "eval_runtime": 175.5682,
      "eval_samples_per_second": 35.132,
      "eval_steps_per_second": 8.783,
      "step": 600
    },
    {
      "epoch": 0.08874325892552393,
      "grad_norm": 93.70142364501953,
      "learning_rate": 0.00025,
      "loss": 9.1371,
      "step": 650
    },
    {
      "epoch": 0.09556966345825654,
      "grad_norm": 98.56558227539062,
      "learning_rate": 0.00025,
      "loss": 9.2194,
      "step": 700
    },
    {
      "epoch": 0.09556966345825654,
      "eval_loss": 2.415971040725708,
      "eval_runtime": 175.6059,
      "eval_samples_per_second": 35.124,
      "eval_steps_per_second": 8.781,
      "step": 700
    },
    {
      "epoch": 0.10239606799098915,
      "grad_norm": 93.90786743164062,
      "learning_rate": 0.00025,
      "loss": 8.9364,
      "step": 750
    },
    {
      "epoch": 0.10922247252372176,
      "grad_norm": 77.11343383789062,
      "learning_rate": 0.00025,
      "loss": 9.0858,
      "step": 800
    },
    {
      "epoch": 0.10922247252372176,
      "eval_loss": 2.4181454181671143,
      "eval_runtime": 175.1085,
      "eval_samples_per_second": 35.224,
      "eval_steps_per_second": 8.806,
      "step": 800
    },
    {
      "epoch": 0.11604887705645436,
      "grad_norm": 81.04496002197266,
      "learning_rate": 0.00025,
      "loss": 9.0347,
      "step": 850
    },
    {
      "epoch": 0.12287528158918698,
      "grad_norm": 125.09262084960938,
      "learning_rate": 0.00025,
      "loss": 9.0613,
      "step": 900
    },
    {
      "epoch": 0.12287528158918698,
      "eval_loss": 2.4733426570892334,
      "eval_runtime": 175.0699,
      "eval_samples_per_second": 35.232,
      "eval_steps_per_second": 8.808,
      "step": 900
    },
    {
      "epoch": 0.1297016861219196,
      "grad_norm": 110.23700714111328,
      "learning_rate": 0.00025,
      "loss": 9.1768,
      "step": 950
    },
    {
      "epoch": 0.13652809065465218,
      "grad_norm": 100.71356964111328,
      "learning_rate": 0.00025,
      "loss": 9.0456,
      "step": 1000
    },
    {
      "epoch": 0.13652809065465218,
      "eval_loss": 2.4080352783203125,
      "eval_runtime": 174.9154,
      "eval_samples_per_second": 35.263,
      "eval_steps_per_second": 8.816,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.53626333642752e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}