{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007736112603416783,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.595680670463093e-05,
      "grad_norm": 18.901330947875977,
      "learning_rate": 2e-05,
      "loss": 16.1647,
      "step": 1
    },
    {
      "epoch": 8.595680670463093e-05,
      "eval_loss": 4.075713157653809,
      "eval_runtime": 60.7214,
      "eval_samples_per_second": 80.68,
      "eval_steps_per_second": 40.348,
      "step": 1
    },
    {
      "epoch": 0.00017191361340926185,
      "grad_norm": 18.692108154296875,
      "learning_rate": 4e-05,
      "loss": 16.6269,
      "step": 2
    },
    {
      "epoch": 0.0002578704201138928,
      "grad_norm": 16.219650268554688,
      "learning_rate": 6e-05,
      "loss": 15.6047,
      "step": 3
    },
    {
      "epoch": 0.0002578704201138928,
      "eval_loss": 4.017122745513916,
      "eval_runtime": 59.903,
      "eval_samples_per_second": 81.782,
      "eval_steps_per_second": 40.899,
      "step": 3
    },
    {
      "epoch": 0.0003438272268185237,
      "grad_norm": 17.441421508789062,
      "learning_rate": 8e-05,
      "loss": 18.1517,
      "step": 4
    },
    {
      "epoch": 0.00042978403352315463,
      "grad_norm": 16.04598045349121,
      "learning_rate": 0.0001,
      "loss": 16.2902,
      "step": 5
    },
    {
      "epoch": 0.0005157408402277856,
      "grad_norm": 19.427223205566406,
      "learning_rate": 0.00012,
      "loss": 17.3113,
      "step": 6
    },
    {
      "epoch": 0.0005157408402277856,
      "eval_loss": 3.5892412662506104,
      "eval_runtime": 59.4161,
      "eval_samples_per_second": 82.452,
      "eval_steps_per_second": 41.235,
      "step": 6
    },
    {
      "epoch": 0.0006016976469324165,
      "grad_norm": 17.231149673461914,
      "learning_rate": 0.00014,
      "loss": 14.231,
      "step": 7
    },
    {
      "epoch": 0.0006876544536370474,
      "grad_norm": 19.227130889892578,
      "learning_rate": 0.00016,
      "loss": 13.944,
      "step": 8
    },
    {
      "epoch": 0.0007736112603416783,
      "grad_norm": 16.57769775390625,
      "learning_rate": 0.00018,
      "loss": 11.4373,
      "step": 9
    },
    {
      "epoch": 0.0007736112603416783,
      "eval_loss": 2.5734214782714844,
      "eval_runtime": 60.0723,
      "eval_samples_per_second": 81.552,
      "eval_steps_per_second": 40.784,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 268889078366208.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}