{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015180265654648957,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015180265654648956,
      "grad_norm": 3.4350709915161133,
      "learning_rate": 2e-05,
      "loss": 2.3927,
      "step": 1
    },
    {
      "epoch": 0.0015180265654648956,
      "eval_loss": 2.4993908405303955,
      "eval_runtime": 41.5313,
      "eval_samples_per_second": 6.694,
      "eval_steps_per_second": 3.347,
      "step": 1
    },
    {
      "epoch": 0.0030360531309297912,
      "grad_norm": 3.9095571041107178,
      "learning_rate": 4e-05,
      "loss": 2.7899,
      "step": 2
    },
    {
      "epoch": 0.004554079696394687,
      "grad_norm": 4.459805965423584,
      "learning_rate": 6e-05,
      "loss": 2.7947,
      "step": 3
    },
    {
      "epoch": 0.004554079696394687,
      "eval_loss": 2.4646143913269043,
      "eval_runtime": 41.5334,
      "eval_samples_per_second": 6.693,
      "eval_steps_per_second": 3.347,
      "step": 3
    },
    {
      "epoch": 0.0060721062618595825,
      "grad_norm": 3.9064364433288574,
      "learning_rate": 8e-05,
      "loss": 2.6989,
      "step": 4
    },
    {
      "epoch": 0.007590132827324478,
      "grad_norm": 3.5368027687072754,
      "learning_rate": 0.0001,
      "loss": 2.1321,
      "step": 5
    },
    {
      "epoch": 0.009108159392789373,
      "grad_norm": 3.331127166748047,
      "learning_rate": 0.00012,
      "loss": 2.0712,
      "step": 6
    },
    {
      "epoch": 0.009108159392789373,
      "eval_loss": 2.1698570251464844,
      "eval_runtime": 41.5367,
      "eval_samples_per_second": 6.693,
      "eval_steps_per_second": 3.346,
      "step": 6
    },
    {
      "epoch": 0.01062618595825427,
      "grad_norm": 3.8248586654663086,
      "learning_rate": 0.00014,
      "loss": 1.9819,
      "step": 7
    },
    {
      "epoch": 0.012144212523719165,
      "grad_norm": 6.30928373336792,
      "learning_rate": 0.00016,
      "loss": 1.96,
      "step": 8
    },
    {
      "epoch": 0.01366223908918406,
      "grad_norm": 4.482444763183594,
      "learning_rate": 0.00018,
      "loss": 1.8714,
      "step": 9
    },
    {
      "epoch": 0.01366223908918406,
      "eval_loss": 1.6795495748519897,
      "eval_runtime": 41.5436,
      "eval_samples_per_second": 6.692,
      "eval_steps_per_second": 3.346,
      "step": 9
    },
    {
      "epoch": 0.015180265654648957,
      "grad_norm": 4.6534504890441895,
      "learning_rate": 0.0002,
      "loss": 1.4058,
      "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": 1935445139128320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}