{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 94,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.42780748663101603,
      "grad_norm": 5.466801643371582,
      "learning_rate": 0.00015957446808510637,
      "loss": 6.5841,
      "step": 20
    },
    {
      "epoch": 0.8556149732620321,
      "grad_norm": 0.3251476585865021,
      "learning_rate": 0.00011702127659574468,
      "loss": 0.3298,
      "step": 40
    },
    {
      "epoch": 1.2780748663101604,
      "grad_norm": 0.22695721685886383,
      "learning_rate": 7.446808510638298e-05,
      "loss": 0.2475,
      "step": 60
    },
    {
      "epoch": 1.7058823529411766,
      "grad_norm": 0.20470468699932098,
      "learning_rate": 3.191489361702128e-05,
      "loss": 0.2294,
      "step": 80
    }
  ],
  "logging_steps": 20,
  "max_steps": 94,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2379748793647104.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}