{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.962025316455696,
  "eval_steps": 500,
  "global_step": 177,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16877637130801687,
      "grad_norm": 0.1649426966905594,
      "learning_rate": 0.00019984815164333163,
      "loss": 0.634,
      "step": 10
    },
    {
      "epoch": 0.33755274261603374,
      "grad_norm": 0.09811161458492279,
      "learning_rate": 0.0001971614350559814,
      "loss": 0.488,
      "step": 20
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.12041426450014114,
      "learning_rate": 0.00019120447901834706,
      "loss": 0.4406,
      "step": 30
    },
    {
      "epoch": 0.6751054852320675,
      "grad_norm": 0.11681783199310303,
      "learning_rate": 0.0001821777815225245,
      "loss": 0.4385,
      "step": 40
    },
    {
      "epoch": 0.8438818565400844,
      "grad_norm": 0.12966671586036682,
      "learning_rate": 0.00017038516128259115,
      "loss": 0.4207,
      "step": 50
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2353854924440384,
      "learning_rate": 0.00015622353186727544,
      "loss": 0.407,
      "step": 60
    },
    {
      "epoch": 1.1687763713080168,
      "grad_norm": 0.172561913728714,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.3725,
      "step": 70
    },
    {
      "epoch": 1.3375527426160336,
      "grad_norm": 0.162893146276474,
      "learning_rate": 0.00012276353492572935,
      "loss": 0.3632,
      "step": 80
    },
    {
      "epoch": 1.5063291139240507,
      "grad_norm": 0.1781071275472641,
      "learning_rate": 0.00010459135704399718,
      "loss": 0.3574,
      "step": 90
    },
    {
      "epoch": 1.6751054852320675,
      "grad_norm": 0.2111092209815979,
      "learning_rate": 8.626464421815919e-05,
      "loss": 0.3303,
      "step": 100
    },
    {
      "epoch": 1.8438818565400843,
      "grad_norm": 0.20615039765834808,
      "learning_rate": 6.840023315140475e-05,
      "loss": 0.3385,
      "step": 110
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.49355044960975647,
      "learning_rate": 5.159940049010015e-05,
      "loss": 0.3286,
      "step": 120
    },
    {
      "epoch": 2.168776371308017,
      "grad_norm": 0.22129110991954803,
      "learning_rate": 3.642762517900322e-05,
      "loss": 0.2901,
      "step": 130
    },
    {
      "epoch": 2.3375527426160336,
      "grad_norm": 0.22937293350696564,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.2916,
      "step": 140
    },
    {
      "epoch": 2.5063291139240507,
      "grad_norm": 0.2439713031053543,
      "learning_rate": 1.294182271221377e-05,
      "loss": 0.2865,
      "step": 150
    },
    {
      "epoch": 2.6751054852320673,
      "grad_norm": 0.23686474561691284,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.2854,
      "step": 160
    },
    {
      "epoch": 2.8438818565400843,
      "grad_norm": 0.2566355764865875,
      "learning_rate": 1.0781410234342094e-06,
      "loss": 0.2898,
      "step": 170
    },
    {
      "epoch": 2.962025316455696,
      "step": 177,
      "total_flos": 1.1532158740468531e+17,
      "train_loss": 0.37109487339601677,
      "train_runtime": 1389.7366,
      "train_samples_per_second": 2.046,
      "train_steps_per_second": 0.127
    }
  ],
  "logging_steps": 10,
  "max_steps": 177,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1532158740468531e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}