{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 314,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3184713375796178,
      "grad_norm": 7.391959190368652,
      "learning_rate": 4.219745222929937e-05,
      "loss": 1.2631,
      "step": 50
    },
    {
      "epoch": 0.6369426751592356,
      "grad_norm": 10.160829544067383,
      "learning_rate": 3.423566878980892e-05,
      "loss": 0.545,
      "step": 100
    },
    {
      "epoch": 0.9554140127388535,
      "grad_norm": 8.946599960327148,
      "learning_rate": 2.6273885350318473e-05,
      "loss": 0.401,
      "step": 150
    },
    {
      "epoch": 1.2738853503184713,
      "grad_norm": 7.462524890899658,
      "learning_rate": 1.8312101910828026e-05,
      "loss": 0.255,
      "step": 200
    },
    {
      "epoch": 1.5923566878980893,
      "grad_norm": 9.983671188354492,
      "learning_rate": 1.0350318471337581e-05,
      "loss": 0.2057,
      "step": 250
    },
    {
      "epoch": 1.910828025477707,
      "grad_norm": 9.440059661865234,
      "learning_rate": 2.388535031847134e-06,
      "loss": 0.1919,
      "step": 300
    }
  ],
  "logging_steps": 50,
  "max_steps": 314,
  "num_input_tokens_seen": 0,
  "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": 9.982437728256e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}