{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0682523267838677,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5170630816959669,
      "grad_norm": 0.07793747633695602,
      "learning_rate": 4.138228197173389e-05,
      "loss": 0.5111,
      "step": 500
    },
    {
      "epoch": 1.0341261633919339,
      "grad_norm": 0.1947256475687027,
      "learning_rate": 3.276456394346777e-05,
      "loss": 0.0911,
      "step": 1000
    },
    {
      "epoch": 1.5511892450879006,
      "grad_norm": 0.8741845488548279,
      "learning_rate": 2.4146845915201654e-05,
      "loss": 0.0476,
      "step": 1500
    },
    {
      "epoch": 2.0682523267838677,
      "grad_norm": 0.00605323351919651,
      "learning_rate": 1.5529127886935542e-05,
      "loss": 0.0166,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2901,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2118190926028800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}