{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13245033112582782,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013245033112582781,
      "grad_norm": 0.11526601761579514,
      "learning_rate": 2e-05,
      "loss": 11.9304,
      "step": 1
    },
    {
      "epoch": 0.013245033112582781,
      "eval_loss": 11.935847282409668,
      "eval_runtime": 0.1243,
      "eval_samples_per_second": 257.339,
      "eval_steps_per_second": 128.67,
      "step": 1
    },
    {
      "epoch": 0.026490066225165563,
      "grad_norm": 0.10667196661233902,
      "learning_rate": 4e-05,
      "loss": 11.9355,
      "step": 2
    },
    {
      "epoch": 0.039735099337748346,
      "grad_norm": 0.1387435495853424,
      "learning_rate": 6e-05,
      "loss": 11.931,
      "step": 3
    },
    {
      "epoch": 0.039735099337748346,
      "eval_loss": 11.935783386230469,
      "eval_runtime": 0.1282,
      "eval_samples_per_second": 249.622,
      "eval_steps_per_second": 124.811,
      "step": 3
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 0.11713223159313202,
      "learning_rate": 8e-05,
      "loss": 11.935,
      "step": 4
    },
    {
      "epoch": 0.06622516556291391,
      "grad_norm": 0.10138162970542908,
      "learning_rate": 0.0001,
      "loss": 11.9354,
      "step": 5
    },
    {
      "epoch": 0.07947019867549669,
      "grad_norm": 0.12049002945423126,
      "learning_rate": 0.00012,
      "loss": 11.9304,
      "step": 6
    },
    {
      "epoch": 0.07947019867549669,
      "eval_loss": 11.93551254272461,
      "eval_runtime": 0.1421,
      "eval_samples_per_second": 225.227,
      "eval_steps_per_second": 112.614,
      "step": 6
    },
    {
      "epoch": 0.09271523178807947,
      "grad_norm": 0.10570518672466278,
      "learning_rate": 0.00014,
      "loss": 11.9351,
      "step": 7
    },
    {
      "epoch": 0.10596026490066225,
      "grad_norm": 0.1032499223947525,
      "learning_rate": 0.00016,
      "loss": 11.937,
      "step": 8
    },
    {
      "epoch": 0.11920529801324503,
      "grad_norm": 0.11217149347066879,
      "learning_rate": 0.00018,
      "loss": 11.9311,
      "step": 9
    },
    {
      "epoch": 0.11920529801324503,
      "eval_loss": 11.935047149658203,
      "eval_runtime": 0.1304,
      "eval_samples_per_second": 245.488,
      "eval_steps_per_second": 122.744,
      "step": 9
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 0.1060936376452446,
      "learning_rate": 0.0002,
      "loss": 11.9333,
      "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": 1181614080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}