{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7619047619047619,
  "eval_steps": 5,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01904761904761905,
      "eval_loss": 7.428563117980957,
      "eval_runtime": 0.4979,
      "eval_samples_per_second": 44.184,
      "eval_steps_per_second": 12.05,
      "step": 1
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 2354.0830078125,
      "learning_rate": 3e-05,
      "loss": 14.6828,
      "step": 3
    },
    {
      "epoch": 0.09523809523809523,
      "eval_loss": 7.463829040527344,
      "eval_runtime": 0.0988,
      "eval_samples_per_second": 222.589,
      "eval_steps_per_second": 60.706,
      "step": 5
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 2209.059814453125,
      "learning_rate": 6e-05,
      "loss": 14.6992,
      "step": 6
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 1919.69482421875,
      "learning_rate": 9e-05,
      "loss": 14.8264,
      "step": 9
    },
    {
      "epoch": 0.19047619047619047,
      "eval_loss": 7.168332099914551,
      "eval_runtime": 0.0976,
      "eval_samples_per_second": 225.344,
      "eval_steps_per_second": 61.458,
      "step": 10
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 1912.1866455078125,
      "learning_rate": 0.00012,
      "loss": 14.0871,
      "step": 12
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2132.776123046875,
      "learning_rate": 0.00015000000000000001,
      "loss": 13.9853,
      "step": 15
    },
    {
      "epoch": 0.2857142857142857,
      "eval_loss": 6.985106945037842,
      "eval_runtime": 0.099,
      "eval_samples_per_second": 222.313,
      "eval_steps_per_second": 60.631,
      "step": 15
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 1974.28076171875,
      "learning_rate": 0.00018,
      "loss": 13.8445,
      "step": 18
    },
    {
      "epoch": 0.38095238095238093,
      "eval_loss": 6.910727024078369,
      "eval_runtime": 0.0955,
      "eval_samples_per_second": 230.251,
      "eval_steps_per_second": 62.796,
      "step": 20
    },
    {
      "epoch": 0.4,
      "grad_norm": 2037.5367431640625,
      "learning_rate": 0.00019876883405951377,
      "loss": 13.7064,
      "step": 21
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 1787.888671875,
      "learning_rate": 0.00018090169943749476,
      "loss": 13.8959,
      "step": 24
    },
    {
      "epoch": 0.47619047619047616,
      "eval_loss": 6.688287734985352,
      "eval_runtime": 0.0989,
      "eval_samples_per_second": 222.419,
      "eval_steps_per_second": 60.66,
      "step": 25
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 2035.425537109375,
      "learning_rate": 0.00014539904997395468,
      "loss": 13.6203,
      "step": 27
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2253.046875,
      "learning_rate": 0.0001,
      "loss": 13.3387,
      "step": 30
    },
    {
      "epoch": 0.5714285714285714,
      "eval_loss": 6.705076217651367,
      "eval_runtime": 0.1247,
      "eval_samples_per_second": 176.415,
      "eval_steps_per_second": 48.113,
      "step": 30
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 1498.140380859375,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 12.9927,
      "step": 33
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 6.740316390991211,
      "eval_runtime": 0.0977,
      "eval_samples_per_second": 225.14,
      "eval_steps_per_second": 61.402,
      "step": 35
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 1960.5146484375,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 13.6963,
      "step": 36
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 1050.917724609375,
      "learning_rate": 1.231165940486234e-06,
      "loss": 13.3819,
      "step": 39
    },
    {
      "epoch": 0.7619047619047619,
      "eval_loss": 6.635408401489258,
      "eval_runtime": 0.0974,
      "eval_samples_per_second": 225.782,
      "eval_steps_per_second": 61.577,
      "step": 40
    }
  ],
  "logging_steps": 3,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 15385378160640.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}