{
  "best_metric": 0.02853687417768363,
  "best_model_checkpoint": "./checkpoints/easyrec-large",
  "epoch": 2.588844433984467,
  "eval_steps": 1000,
  "global_step": 11000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11767474699929395,
      "grad_norm": 99.0,
      "learning_rate": 4.803875421667844e-05,
      "loss": 2.8035,
      "step": 500
    },
    {
      "epoch": 0.2353494939985879,
      "grad_norm": 120.5,
      "learning_rate": 4.607750843335687e-05,
      "loss": 2.3662,
      "step": 1000
    },
    {
      "epoch": 0.3530242409978819,
      "grad_norm": 46.0,
      "learning_rate": 4.411626265003531e-05,
      "loss": 2.2534,
      "step": 1500
    },
    {
      "epoch": 0.4706989879971758,
      "grad_norm": 41.5,
      "learning_rate": 4.215501686671374e-05,
      "loss": 2.1194,
      "step": 2000
    },
    {
      "epoch": 0.5883737349964697,
      "grad_norm": 56.5,
      "learning_rate": 4.019377108339217e-05,
      "loss": 2.0655,
      "step": 2500
    },
    {
      "epoch": 0.7060484819957638,
      "grad_norm": 56.25,
      "learning_rate": 3.82325253000706e-05,
      "loss": 2.084,
      "step": 3000
    },
    {
      "epoch": 0.8237232289950577,
      "grad_norm": 44.0,
      "learning_rate": 3.627127951674904e-05,
      "loss": 2.0148,
      "step": 3500
    },
    {
      "epoch": 0.9413979759943516,
      "grad_norm": 43.0,
      "learning_rate": 3.431003373342748e-05,
      "loss": 2.0612,
      "step": 4000
    },
    {
      "epoch": 1.0590727229936456,
      "grad_norm": 80.5,
      "learning_rate": 3.234878795010591e-05,
      "loss": 1.9376,
      "step": 4500
    },
    {
      "epoch": 1.1767474699929394,
      "grad_norm": 48.25,
      "learning_rate": 3.0387542166784343e-05,
      "loss": 1.9588,
      "step": 5000
    },
    {
      "epoch": 1.2944222169922335,
      "grad_norm": 67.5,
      "learning_rate": 2.8426296383462774e-05,
      "loss": 1.9291,
      "step": 5500
    },
    {
      "epoch": 1.4120969639915275,
      "grad_norm": 75.5,
      "learning_rate": 2.6465050600141212e-05,
      "loss": 1.9643,
      "step": 6000
    },
    {
      "epoch": 1.5297717109908213,
      "grad_norm": 45.75,
      "learning_rate": 2.4503804816819646e-05,
      "loss": 1.9045,
      "step": 6500
    },
    {
      "epoch": 1.6474464579901154,
      "grad_norm": 44.5,
      "learning_rate": 2.2542559033498077e-05,
      "loss": 1.9263,
      "step": 7000
    },
    {
      "epoch": 1.7651212049894092,
      "grad_norm": 56.25,
      "learning_rate": 2.0581313250176512e-05,
      "loss": 1.9065,
      "step": 7500
    },
    {
      "epoch": 1.8827959519887032,
      "grad_norm": 44.75,
      "learning_rate": 1.862006746685495e-05,
      "loss": 1.9187,
      "step": 8000
    },
    {
      "epoch": 2.0004706989879972,
      "grad_norm": 57.0,
      "learning_rate": 1.665882168353338e-05,
      "loss": 1.9198,
      "step": 8500
    },
    {
      "epoch": 2.1181454459872913,
      "grad_norm": 49.5,
      "learning_rate": 1.4697575900211815e-05,
      "loss": 1.9371,
      "step": 9000
    },
    {
      "epoch": 2.2358201929865853,
      "grad_norm": 45.0,
      "learning_rate": 1.273633011689025e-05,
      "loss": 1.8927,
      "step": 9500
    },
    {
      "epoch": 2.353494939985879,
      "grad_norm": 45.0,
      "learning_rate": 1.0775084333568684e-05,
      "loss": 1.8996,
      "step": 10000
    },
    {
      "epoch": 2.471169686985173,
      "grad_norm": 34.75,
      "learning_rate": 8.813838550247118e-06,
      "loss": 1.8713,
      "step": 10500
    },
    {
      "epoch": 2.588844433984467,
      "grad_norm": 37.75,
      "learning_rate": 6.852592766925552e-06,
      "loss": 1.9081,
      "step": 11000
    }
  ],
  "logging_steps": 500,
  "max_steps": 12747,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}