{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01263157894736842,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004210526315789474,
      "eval_loss": NaN,
      "eval_runtime": 159.7399,
      "eval_samples_per_second": 6.26,
      "eval_steps_per_second": 3.13,
      "step": 1
    },
    {
      "epoch": 0.0012631578947368421,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.002105263157894737,
      "eval_loss": NaN,
      "eval_runtime": 159.8215,
      "eval_samples_per_second": 6.257,
      "eval_steps_per_second": 3.128,
      "step": 5
    },
    {
      "epoch": 0.0025263157894736842,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.003789473684210526,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.004210526315789474,
      "eval_loss": NaN,
      "eval_runtime": 159.8322,
      "eval_samples_per_second": 6.257,
      "eval_steps_per_second": 3.128,
      "step": 10
    },
    {
      "epoch": 0.0050526315789473685,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00631578947368421,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00631578947368421,
      "eval_loss": NaN,
      "eval_runtime": 159.7677,
      "eval_samples_per_second": 6.259,
      "eval_steps_per_second": 3.13,
      "step": 15
    },
    {
      "epoch": 0.007578947368421052,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.008421052631578947,
      "eval_loss": NaN,
      "eval_runtime": 159.7086,
      "eval_samples_per_second": 6.261,
      "eval_steps_per_second": 3.131,
      "step": 20
    },
    {
      "epoch": 0.008842105263157894,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.010105263157894737,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.010526315789473684,
      "eval_loss": NaN,
      "eval_runtime": 159.7891,
      "eval_samples_per_second": 6.258,
      "eval_steps_per_second": 3.129,
      "step": 25
    },
    {
      "epoch": 0.01136842105263158,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.01263157894736842,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.01263157894736842,
      "eval_loss": NaN,
      "eval_runtime": 159.7433,
      "eval_samples_per_second": 6.26,
      "eval_steps_per_second": 3.13,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.048558039990272e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}