{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0462620281273131,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0046262028127313105,
      "grad_norm": 0.4456588923931122,
      "learning_rate": 0.00019909326424870466,
      "loss": 0.8481,
      "step": 50
    },
    {
      "epoch": 0.009252405625462621,
      "grad_norm": 0.36097365617752075,
      "learning_rate": 0.0001981680236861584,
      "loss": 0.6286,
      "step": 100
    },
    {
      "epoch": 0.01387860843819393,
      "grad_norm": 0.42441412806510925,
      "learning_rate": 0.00019724278312361216,
      "loss": 0.6207,
      "step": 150
    },
    {
      "epoch": 0.018504811250925242,
      "grad_norm": 0.42437243461608887,
      "learning_rate": 0.0001963175425610659,
      "loss": 0.5968,
      "step": 200
    },
    {
      "epoch": 0.02313101406365655,
      "grad_norm": 0.39017853140830994,
      "learning_rate": 0.00019539230199851963,
      "loss": 0.6014,
      "step": 250
    },
    {
      "epoch": 0.02775721687638786,
      "grad_norm": 0.39022767543792725,
      "learning_rate": 0.00019446706143597334,
      "loss": 0.6082,
      "step": 300
    },
    {
      "epoch": 0.03238341968911917,
      "grad_norm": 0.35285571217536926,
      "learning_rate": 0.0001935418208734271,
      "loss": 0.5834,
      "step": 350
    },
    {
      "epoch": 0.037009622501850484,
      "grad_norm": 0.35125309228897095,
      "learning_rate": 0.00019261658031088084,
      "loss": 0.5622,
      "step": 400
    },
    {
      "epoch": 0.04163582531458179,
      "grad_norm": 0.39975836873054504,
      "learning_rate": 0.00019169133974833457,
      "loss": 0.574,
      "step": 450
    },
    {
      "epoch": 0.0462620281273131,
      "grad_norm": 0.3551945984363556,
      "learning_rate": 0.0001907660991857883,
      "loss": 0.5919,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 10808,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5.777697637023744e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}