{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 4.2845234870910645,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.1395275592803955,
      "step": 10
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.076885938644409,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.09198258519172668,
      "step": 20
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.2846078872680664,
      "learning_rate": 9.992203820909906e-06,
      "loss": 0.07833675146102906,
      "step": 30
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7038628458976746,
      "learning_rate": 9.904775776745959e-06,
      "loss": 0.06727399826049804,
      "step": 40
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9231874346733093,
      "learning_rate": 9.721881851187406e-06,
      "loss": 0.06411659717559814,
      "step": 50
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.0481280088424683,
      "learning_rate": 9.44708186645649e-06,
      "loss": 0.0525032103061676,
      "step": 60
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.8314676880836487,
      "learning_rate": 9.085724491675642e-06,
      "loss": 0.04806323647499085,
      "step": 70
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.7113093733787537,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.05030159950256348,
      "step": 80
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.7916203737258911,
      "learning_rate": 8.133019056822303e-06,
      "loss": 0.045130616426467894,
      "step": 90
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7043232917785645,
      "learning_rate": 7.560214324352858e-06,
      "loss": 0.04170699715614319,
      "step": 100
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.8150236010551453,
      "learning_rate": 6.9375779322605154e-06,
      "loss": 0.03221024870872498,
      "step": 110
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.7333807349205017,
      "learning_rate": 6.277228789678953e-06,
      "loss": 0.02941911220550537,
      "step": 120
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.821044385433197,
      "learning_rate": 5.592019841532507e-06,
      "loss": 0.029835113883018495,
      "step": 130
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.6930698156356812,
      "learning_rate": 4.895287900583216e-06,
      "loss": 0.027946752309799195,
      "step": 140
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7381048798561096,
      "learning_rate": 4.200594061540827e-06,
      "loss": 0.024364133179187775,
      "step": 150
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.0409406423568726,
      "learning_rate": 3.521459749779769e-06,
      "loss": 0.015057653188705444,
      "step": 160
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.8659031391143799,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.013981494307518005,
      "step": 170
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.0307326316833496,
      "learning_rate": 2.2621838825372496e-06,
      "loss": 0.012463082373142243,
      "step": 180
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.637093186378479,
      "learning_rate": 1.7065526994065973e-06,
      "loss": 0.011675777286291123,
      "step": 190
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9585095643997192,
      "learning_rate": 1.2150247217412186e-06,
      "loss": 0.010881078988313675,
      "step": 200
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.68025803565979,
      "learning_rate": 7.971669825215789e-07,
      "loss": 0.003655080869793892,
      "step": 210
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.4042770564556122,
      "learning_rate": 4.6111260733545714e-07,
      "loss": 0.003969649970531464,
      "step": 220
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.24554327130317688,
      "learning_rate": 2.134025123396638e-07,
      "loss": 0.002969801425933838,
      "step": 230
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.5440001487731934,
      "learning_rate": 5.8858092767236084e-08,
      "loss": 0.002937900647521019,
      "step": 240
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.607397735118866,
      "learning_rate": 4.87379953478806e-10,
      "loss": 0.0023729542270302774,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7298085253110825e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}