{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.941952506596306,
  "eval_steps": 5000,
  "global_step": 46,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.42216358839050133,
      "grad_norm": 13.42656421661377,
      "learning_rate": 9.36024704071904e-06,
      "loss": 8.6209,
      "step": 10
    },
    {
      "epoch": 0.8443271767810027,
      "grad_norm": 9.004769325256348,
      "learning_rate": 6.614402023857231e-06,
      "loss": 5.3354,
      "step": 20
    },
    {
      "epoch": 1.266490765171504,
      "grad_norm": 6.205361843109131,
      "learning_rate": 3.044476397549221e-06,
      "loss": 4.18,
      "step": 30
    },
    {
      "epoch": 1.6886543535620053,
      "grad_norm": 5.6094651222229,
      "learning_rate": 4.727588125342669e-07,
      "loss": 3.8146,
      "step": 40
    },
    {
      "epoch": 1.941952506596306,
      "step": 46,
      "total_flos": 1.8959322667863245e+17,
      "train_loss": 5.261244110439135,
      "train_runtime": 307.2859,
      "train_samples_per_second": 39.423,
      "train_steps_per_second": 0.15
    }
  ],
  "logging_steps": 10,
  "max_steps": 46,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8959322667863245e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}