{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015384023691396485,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015384023691396484,
      "grad_norm": 11396.142578125,
      "learning_rate": 3e-07,
      "loss": 8.8759,
      "step": 10
    },
    {
      "epoch": 0.003076804738279297,
      "grad_norm": 689.1935424804688,
      "learning_rate": 1.2999999999999998e-06,
      "loss": 8.2644,
      "step": 20
    },
    {
      "epoch": 0.004615207107418946,
      "grad_norm": 454.8230285644531,
      "learning_rate": 2.2999999999999996e-06,
      "loss": 7.2145,
      "step": 30
    },
    {
      "epoch": 0.006153609476558594,
      "grad_norm": 169.3773193359375,
      "learning_rate": 3.2999999999999993e-06,
      "loss": 6.899,
      "step": 40
    },
    {
      "epoch": 0.007692011845698243,
      "grad_norm": 121.77935028076172,
      "learning_rate": 4.2999999999999995e-06,
      "loss": 6.7803,
      "step": 50
    },
    {
      "epoch": 0.009230414214837892,
      "grad_norm": 1289.1287841796875,
      "learning_rate": 5.3e-06,
      "loss": 6.5956,
      "step": 60
    },
    {
      "epoch": 0.010768816583977539,
      "grad_norm": 157.25286865234375,
      "learning_rate": 6.3e-06,
      "loss": 6.6402,
      "step": 70
    },
    {
      "epoch": 0.012307218953117188,
      "grad_norm": 384.85919189453125,
      "learning_rate": 7.299999999999999e-06,
      "loss": 6.4978,
      "step": 80
    },
    {
      "epoch": 0.013845621322256836,
      "grad_norm": 301.0735778808594,
      "learning_rate": 8.299999999999998e-06,
      "loss": 6.3964,
      "step": 90
    },
    {
      "epoch": 0.015384023691396485,
      "grad_norm": 226.9570770263672,
      "learning_rate": 9.299999999999999e-06,
      "loss": 6.3804,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 16,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1921989197070336.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}