{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005283736658564937,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.283736658564937e-05,
      "grad_norm": 2.747178077697754,
      "learning_rate": 2e-05,
      "loss": 11.0005,
      "step": 1
    },
    {
      "epoch": 5.283736658564937e-05,
      "eval_loss": 11.326530456542969,
      "eval_runtime": 418.9579,
      "eval_samples_per_second": 19.021,
      "eval_steps_per_second": 9.512,
      "step": 1
    },
    {
      "epoch": 0.00010567473317129874,
      "grad_norm": 2.8278725147247314,
      "learning_rate": 4e-05,
      "loss": 10.6605,
      "step": 2
    },
    {
      "epoch": 0.00015851209975694812,
      "grad_norm": 3.1282999515533447,
      "learning_rate": 6e-05,
      "loss": 11.229,
      "step": 3
    },
    {
      "epoch": 0.00015851209975694812,
      "eval_loss": 11.303915023803711,
      "eval_runtime": 416.8904,
      "eval_samples_per_second": 19.115,
      "eval_steps_per_second": 9.559,
      "step": 3
    },
    {
      "epoch": 0.00021134946634259749,
      "grad_norm": 3.4735445976257324,
      "learning_rate": 8e-05,
      "loss": 11.5361,
      "step": 4
    },
    {
      "epoch": 0.00026418683292824685,
      "grad_norm": 3.3279993534088135,
      "learning_rate": 0.0001,
      "loss": 11.1128,
      "step": 5
    },
    {
      "epoch": 0.00031702419951389624,
      "grad_norm": 3.8359556198120117,
      "learning_rate": 0.00012,
      "loss": 10.8322,
      "step": 6
    },
    {
      "epoch": 0.00031702419951389624,
      "eval_loss": 10.792028427124023,
      "eval_runtime": 417.5966,
      "eval_samples_per_second": 19.083,
      "eval_steps_per_second": 9.543,
      "step": 6
    },
    {
      "epoch": 0.0003698615660995456,
      "grad_norm": 4.748237133026123,
      "learning_rate": 0.00014,
      "loss": 10.8447,
      "step": 7
    },
    {
      "epoch": 0.00042269893268519497,
      "grad_norm": 5.545794486999512,
      "learning_rate": 0.00016,
      "loss": 10.1694,
      "step": 8
    },
    {
      "epoch": 0.00047553629927084436,
      "grad_norm": 6.876077651977539,
      "learning_rate": 0.00018,
      "loss": 9.2215,
      "step": 9
    },
    {
      "epoch": 0.00047553629927084436,
      "eval_loss": 8.000694274902344,
      "eval_runtime": 417.6416,
      "eval_samples_per_second": 19.081,
      "eval_steps_per_second": 9.542,
      "step": 9
    },
    {
      "epoch": 0.0005283736658564937,
      "grad_norm": 8.654719352722168,
      "learning_rate": 0.0002,
      "loss": 7.6911,
      "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": 3446998397091840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}