{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02014098690835851,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002014098690835851,
      "grad_norm": 5.569177627563477,
      "learning_rate": 2e-05,
      "loss": 20.2967,
      "step": 1
    },
    {
      "epoch": 0.002014098690835851,
      "eval_loss": 5.018499851226807,
      "eval_runtime": 1.5348,
      "eval_samples_per_second": 136.828,
      "eval_steps_per_second": 68.414,
      "step": 1
    },
    {
      "epoch": 0.004028197381671702,
      "grad_norm": 5.464927673339844,
      "learning_rate": 4e-05,
      "loss": 21.8838,
      "step": 2
    },
    {
      "epoch": 0.006042296072507553,
      "grad_norm": 5.967401504516602,
      "learning_rate": 6e-05,
      "loss": 24.2247,
      "step": 3
    },
    {
      "epoch": 0.006042296072507553,
      "eval_loss": 5.019221782684326,
      "eval_runtime": 1.5216,
      "eval_samples_per_second": 138.014,
      "eval_steps_per_second": 69.007,
      "step": 3
    },
    {
      "epoch": 0.008056394763343404,
      "grad_norm": 6.489200592041016,
      "learning_rate": 8e-05,
      "loss": 22.8343,
      "step": 4
    },
    {
      "epoch": 0.010070493454179255,
      "grad_norm": 4.522333145141602,
      "learning_rate": 0.0001,
      "loss": 20.0108,
      "step": 5
    },
    {
      "epoch": 0.012084592145015106,
      "grad_norm": 4.048852920532227,
      "learning_rate": 0.00012,
      "loss": 12.5678,
      "step": 6
    },
    {
      "epoch": 0.012084592145015106,
      "eval_loss": 4.998569011688232,
      "eval_runtime": 1.5208,
      "eval_samples_per_second": 138.083,
      "eval_steps_per_second": 69.041,
      "step": 6
    },
    {
      "epoch": 0.014098690835850957,
      "grad_norm": 5.816758632659912,
      "learning_rate": 0.00014,
      "loss": 20.1612,
      "step": 7
    },
    {
      "epoch": 0.016112789526686808,
      "grad_norm": 3.4646284580230713,
      "learning_rate": 0.00016,
      "loss": 15.4685,
      "step": 8
    },
    {
      "epoch": 0.01812688821752266,
      "grad_norm": 9.026902198791504,
      "learning_rate": 0.00018,
      "loss": 27.3843,
      "step": 9
    },
    {
      "epoch": 0.01812688821752266,
      "eval_loss": 4.925699234008789,
      "eval_runtime": 1.5429,
      "eval_samples_per_second": 136.106,
      "eval_steps_per_second": 68.053,
      "step": 9
    },
    {
      "epoch": 0.02014098690835851,
      "grad_norm": 9.26620101928711,
      "learning_rate": 0.0002,
      "loss": 26.9209,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 21222716866560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}