{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010973936899862825,
  "eval_steps": 9,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00030483158055174517,
      "eval_loss": 1.6358747482299805,
      "eval_runtime": 393.362,
      "eval_samples_per_second": 14.046,
      "eval_steps_per_second": 1.757,
      "step": 1
    },
    {
      "epoch": 0.0009144947416552355,
      "grad_norm": 17.194887161254883,
      "learning_rate": 1.5e-05,
      "loss": 6.7621,
      "step": 3
    },
    {
      "epoch": 0.001828989483310471,
      "grad_norm": 10.281621932983398,
      "learning_rate": 3e-05,
      "loss": 5.8586,
      "step": 6
    },
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 6.017336845397949,
      "learning_rate": 4.5e-05,
      "loss": 6.2144,
      "step": 9
    },
    {
      "epoch": 0.0027434842249657062,
      "eval_loss": 1.4405845403671265,
      "eval_runtime": 397.296,
      "eval_samples_per_second": 13.907,
      "eval_steps_per_second": 1.739,
      "step": 9
    },
    {
      "epoch": 0.003657978966620942,
      "grad_norm": 5.029771327972412,
      "learning_rate": 4.993910125649561e-05,
      "loss": 5.5157,
      "step": 12
    },
    {
      "epoch": 0.004572473708276178,
      "grad_norm": 4.417510032653809,
      "learning_rate": 4.962019382530521e-05,
      "loss": 5.1545,
      "step": 15
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 4.255384922027588,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 5.7058,
      "step": 18
    },
    {
      "epoch": 0.0054869684499314125,
      "eval_loss": 1.3602502346038818,
      "eval_runtime": 397.5904,
      "eval_samples_per_second": 13.896,
      "eval_steps_per_second": 1.738,
      "step": 18
    },
    {
      "epoch": 0.006401463191586648,
      "grad_norm": 4.237952709197998,
      "learning_rate": 4.817959636416969e-05,
      "loss": 5.1144,
      "step": 21
    },
    {
      "epoch": 0.007315957933241884,
      "grad_norm": 4.633209228515625,
      "learning_rate": 4.707368982147318e-05,
      "loss": 5.8178,
      "step": 24
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 3.6630399227142334,
      "learning_rate": 4.572593931387604e-05,
      "loss": 5.1011,
      "step": 27
    },
    {
      "epoch": 0.00823045267489712,
      "eval_loss": 1.3356471061706543,
      "eval_runtime": 397.6104,
      "eval_samples_per_second": 13.896,
      "eval_steps_per_second": 1.738,
      "step": 27
    },
    {
      "epoch": 0.009144947416552356,
      "grad_norm": 3.946521043777466,
      "learning_rate": 4.415111107797445e-05,
      "loss": 5.4655,
      "step": 30
    },
    {
      "epoch": 0.010059442158207591,
      "grad_norm": 3.9313600063323975,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 5.3857,
      "step": 33
    },
    {
      "epoch": 0.010973936899862825,
      "grad_norm": 3.9708104133605957,
      "learning_rate": 4.039153688314145e-05,
      "loss": 5.1117,
      "step": 36
    },
    {
      "epoch": 0.010973936899862825,
      "eval_loss": 1.3252490758895874,
      "eval_runtime": 397.7349,
      "eval_samples_per_second": 13.891,
      "eval_steps_per_second": 1.737,
      "step": 36
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.062538188711526e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}