{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 68,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029411764705882353,
      "grad_norm": 14.516290664672852,
      "learning_rate": 1.4285714285714285e-07,
      "loss": 0.1544,
      "num_input_tokens_seen": 14872,
      "step": 1
    },
    {
      "epoch": 0.14705882352941177,
      "grad_norm": 13.605290412902832,
      "learning_rate": 7.142857142857143e-07,
      "loss": 0.1988,
      "num_input_tokens_seen": 73216,
      "step": 5
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 4.2562994956970215,
      "learning_rate": 9.940439480455385e-07,
      "loss": 0.1299,
      "num_input_tokens_seen": 144064,
      "step": 10
    },
    {
      "epoch": 0.4411764705882353,
      "grad_norm": 17.544828414916992,
      "learning_rate": 9.581584522435023e-07,
      "loss": 0.1386,
      "num_input_tokens_seen": 216920,
      "step": 15
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 15.67272663116455,
      "learning_rate": 8.920599032883552e-07,
      "loss": 0.0869,
      "num_input_tokens_seen": 289168,
      "step": 20
    },
    {
      "epoch": 0.7352941176470589,
      "grad_norm": 5.556459903717041,
      "learning_rate": 8.001071402741842e-07,
      "loss": 0.1256,
      "num_input_tokens_seen": 361064,
      "step": 25
    },
    {
      "epoch": 0.8823529411764706,
      "grad_norm": 8.599447250366211,
      "learning_rate": 6.883639468175925e-07,
      "loss": 0.1745,
      "num_input_tokens_seen": 434320,
      "step": 30
    },
    {
      "epoch": 1.0294117647058822,
      "grad_norm": 4.350680828094482,
      "learning_rate": 5.641991775732755e-07,
      "loss": 0.0644,
      "num_input_tokens_seen": 507376,
      "step": 35
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 2.298635959625244,
      "learning_rate": 4.3580082242672444e-07,
      "loss": 0.0797,
      "num_input_tokens_seen": 580072,
      "step": 40
    },
    {
      "epoch": 1.3235294117647058,
      "grad_norm": 14.147461891174316,
      "learning_rate": 3.1163605318240736e-07,
      "loss": 0.0671,
      "num_input_tokens_seen": 655712,
      "step": 45
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 3.8819336891174316,
      "learning_rate": 1.9989285972581593e-07,
      "loss": 0.0814,
      "num_input_tokens_seen": 729256,
      "step": 50
    },
    {
      "epoch": 1.6176470588235294,
      "grad_norm": 13.997014045715332,
      "learning_rate": 1.0794009671164483e-07,
      "loss": 0.0997,
      "num_input_tokens_seen": 801752,
      "step": 55
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 5.050583839416504,
      "learning_rate": 4.1841547756497675e-08,
      "loss": 0.0549,
      "num_input_tokens_seen": 875152,
      "step": 60
    },
    {
      "epoch": 1.9117647058823528,
      "grad_norm": 7.370588779449463,
      "learning_rate": 5.956051954461472e-09,
      "loss": 0.0407,
      "num_input_tokens_seen": 945544,
      "step": 65
    }
  ],
  "logging_steps": 5,
  "max_steps": 68,
  "num_input_tokens_seen": 984624,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5360404119552.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}