{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.99644128113879,
  "eval_steps": 35,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1423487544483986,
      "grad_norm": 3.915436267852783,
      "learning_rate": 2.380952380952381e-05,
      "loss": 4.6057,
      "step": 5
    },
    {
      "epoch": 0.2846975088967972,
      "grad_norm": 4.926669597625732,
      "learning_rate": 4.761904761904762e-05,
      "loss": 4.3259,
      "step": 10
    },
    {
      "epoch": 0.42704626334519574,
      "grad_norm": 3.071687936782837,
      "learning_rate": 7.142857142857143e-05,
      "loss": 3.5782,
      "step": 15
    },
    {
      "epoch": 0.5693950177935944,
      "grad_norm": 1.5628787279129028,
      "learning_rate": 9.523809523809524e-05,
      "loss": 2.542,
      "step": 20
    },
    {
      "epoch": 0.7117437722419929,
      "grad_norm": 0.6052073240280151,
      "learning_rate": 9.988952191691925e-05,
      "loss": 2.0288,
      "step": 25
    },
    {
      "epoch": 0.8540925266903915,
      "grad_norm": 0.4768967032432556,
      "learning_rate": 9.944154131125642e-05,
      "loss": 1.9283,
      "step": 30
    },
    {
      "epoch": 0.99644128113879,
      "grad_norm": 0.3471652865409851,
      "learning_rate": 9.865224352899119e-05,
      "loss": 1.9221,
      "step": 35
    },
    {
      "epoch": 0.99644128113879,
      "eval_loss": 1.9122635126113892,
      "eval_runtime": 2.7209,
      "eval_samples_per_second": 16.906,
      "eval_steps_per_second": 16.906,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 210,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.941753715195904e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}