{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.412177562713623,
      "learning_rate": 1e-05,
      "loss": 18.077,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4204994440078735,
      "learning_rate": 1e-05,
      "loss": 17.7146,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.401440978050232,
      "learning_rate": 1e-05,
      "loss": 17.8803,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4028569459915161,
      "learning_rate": 1e-05,
      "loss": 17.9714,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4051861763000488,
      "learning_rate": 1e-05,
      "loss": 17.9678,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4186344146728516,
      "learning_rate": 1e-05,
      "loss": 18.0201,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4067703485488892,
      "learning_rate": 1e-05,
      "loss": 17.9391,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.4187040328979492,
      "learning_rate": 1e-05,
      "loss": 17.9879,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4154680967330933,
      "learning_rate": 1e-05,
      "loss": 17.8092,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.406417727470398,
      "learning_rate": 1e-05,
      "loss": 18.208,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.3953747749328613,
      "learning_rate": 1e-05,
      "loss": 18.0082,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.4039994478225708,
      "learning_rate": 1e-05,
      "loss": 18.2389,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.419633388519287,
      "learning_rate": 1e-05,
      "loss": 18.0777,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 0.9483278393745422,
      "learning_rate": 1e-05,
      "loss": 17.9972,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.0498645305633545,
      "learning_rate": 1e-05,
      "loss": 18.6637,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.1194356679916382,
      "learning_rate": 1e-05,
      "loss": 18.7012,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 0.6664244532585144,
      "learning_rate": 1e-05,
      "loss": 18.9728,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.2018729448318481,
      "learning_rate": 1e-05,
      "loss": 18.8177,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 0.7720096111297607,
      "learning_rate": 1e-05,
      "loss": 19.1833,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.835421085357666,
      "learning_rate": 1e-05,
      "loss": 19.4092,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}