{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21462105969148224,
  "eval_steps": 200,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02682763246143528,
      "grad_norm": 7.5027008056640625,
      "learning_rate": 0.00019991475902800314,
      "loss": 18.1731,
      "step": 50
    },
    {
      "epoch": 0.05365526492287056,
      "grad_norm": 5.68405294418335,
      "learning_rate": 0.0001996521945196495,
      "loss": 16.1431,
      "step": 100
    },
    {
      "epoch": 0.08048289738430583,
      "grad_norm": 5.743220806121826,
      "learning_rate": 0.00019921273704680872,
      "loss": 16.2968,
      "step": 150
    },
    {
      "epoch": 0.10731052984574112,
      "grad_norm": 6.115276336669922,
      "learning_rate": 0.0001985971666920019,
      "loss": 15.9962,
      "step": 200
    },
    {
      "epoch": 0.10731052984574112,
      "eval_loss": 1.7225275039672852,
      "eval_runtime": 27.5115,
      "eval_samples_per_second": 3.635,
      "eval_steps_per_second": 1.817,
      "step": 200
    },
    {
      "epoch": 0.1341381623071764,
      "grad_norm": 8.04736328125,
      "learning_rate": 0.00019780657615635263,
      "loss": 15.9676,
      "step": 250
    },
    {
      "epoch": 0.16096579476861167,
      "grad_norm": 6.840994358062744,
      "learning_rate": 0.0001968423688199291,
      "loss": 15.7539,
      "step": 300
    },
    {
      "epoch": 0.18779342723004694,
      "grad_norm": 8.343657493591309,
      "learning_rate": 0.00019570625625059935,
      "loss": 15.5103,
      "step": 350
    },
    {
      "epoch": 0.21462105969148224,
      "grad_norm": 6.539078712463379,
      "learning_rate": 0.00019440025516582107,
      "loss": 15.4896,
      "step": 400
    },
    {
      "epoch": 0.21462105969148224,
      "eval_loss": 1.6813037395477295,
      "eval_runtime": 27.4264,
      "eval_samples_per_second": 3.646,
      "eval_steps_per_second": 1.823,
      "step": 400
    }
  ],
  "logging_steps": 50,
  "max_steps": 3728,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.905312772017152e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}