{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.039830719442369926,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019915359721184964,
      "grad_norm": 1.2896974086761475,
      "learning_rate": 1e-05,
      "loss": 36.1849,
      "step": 1
    },
    {
      "epoch": 0.0019915359721184964,
      "eval_loss": 2.1876697540283203,
      "eval_runtime": 208.3799,
      "eval_samples_per_second": 4.06,
      "eval_steps_per_second": 2.03,
      "step": 1
    },
    {
      "epoch": 0.003983071944236993,
      "grad_norm": 1.1197001934051514,
      "learning_rate": 2e-05,
      "loss": 32.9364,
      "step": 2
    },
    {
      "epoch": 0.00597460791635549,
      "grad_norm": 1.066008448600769,
      "learning_rate": 3e-05,
      "loss": 36.2816,
      "step": 3
    },
    {
      "epoch": 0.007966143888473986,
      "grad_norm": 1.1513549089431763,
      "learning_rate": 4e-05,
      "loss": 34.4152,
      "step": 4
    },
    {
      "epoch": 0.009957679860592481,
      "grad_norm": 1.076801061630249,
      "learning_rate": 5e-05,
      "loss": 35.6192,
      "step": 5
    },
    {
      "epoch": 0.009957679860592481,
      "eval_loss": 2.1837847232818604,
      "eval_runtime": 58.8468,
      "eval_samples_per_second": 14.376,
      "eval_steps_per_second": 7.188,
      "step": 5
    },
    {
      "epoch": 0.01194921583271098,
      "grad_norm": 1.3358440399169922,
      "learning_rate": 6e-05,
      "loss": 33.6466,
      "step": 6
    },
    {
      "epoch": 0.013940751804829475,
      "grad_norm": 1.407853126525879,
      "learning_rate": 7e-05,
      "loss": 33.7635,
      "step": 7
    },
    {
      "epoch": 0.01593228777694797,
      "grad_norm": 1.700981855392456,
      "learning_rate": 8e-05,
      "loss": 35.9734,
      "step": 8
    },
    {
      "epoch": 0.017923823749066467,
      "grad_norm": 1.9773874282836914,
      "learning_rate": 9e-05,
      "loss": 34.8757,
      "step": 9
    },
    {
      "epoch": 0.019915359721184963,
      "grad_norm": 2.135291576385498,
      "learning_rate": 0.0001,
      "loss": 33.6657,
      "step": 10
    },
    {
      "epoch": 0.019915359721184963,
      "eval_loss": 2.165435791015625,
      "eval_runtime": 61.7976,
      "eval_samples_per_second": 13.69,
      "eval_steps_per_second": 6.845,
      "step": 10
    },
    {
      "epoch": 0.02190689569330346,
      "grad_norm": 1.649067997932434,
      "learning_rate": 9.755282581475769e-05,
      "loss": 34.5891,
      "step": 11
    },
    {
      "epoch": 0.02389843166542196,
      "grad_norm": 2.3715803623199463,
      "learning_rate": 9.045084971874738e-05,
      "loss": 35.4288,
      "step": 12
    },
    {
      "epoch": 0.025889967637540454,
      "grad_norm": 2.4884233474731445,
      "learning_rate": 7.938926261462366e-05,
      "loss": 34.5,
      "step": 13
    },
    {
      "epoch": 0.02788150360965895,
      "grad_norm": 1.779207468032837,
      "learning_rate": 6.545084971874738e-05,
      "loss": 35.1022,
      "step": 14
    },
    {
      "epoch": 0.029873039581777446,
      "grad_norm": 2.0503835678100586,
      "learning_rate": 5e-05,
      "loss": 33.6726,
      "step": 15
    },
    {
      "epoch": 0.029873039581777446,
      "eval_loss": 2.1332011222839355,
      "eval_runtime": 59.0548,
      "eval_samples_per_second": 14.326,
      "eval_steps_per_second": 7.163,
      "step": 15
    },
    {
      "epoch": 0.03186457555389594,
      "grad_norm": 1.835963249206543,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 35.5193,
      "step": 16
    },
    {
      "epoch": 0.03385611152601444,
      "grad_norm": 1.7558304071426392,
      "learning_rate": 2.061073738537635e-05,
      "loss": 34.8392,
      "step": 17
    },
    {
      "epoch": 0.035847647498132934,
      "grad_norm": 1.7630927562713623,
      "learning_rate": 9.549150281252633e-06,
      "loss": 34.1804,
      "step": 18
    },
    {
      "epoch": 0.037839183470251433,
      "grad_norm": 1.4566975831985474,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 34.0237,
      "step": 19
    },
    {
      "epoch": 0.039830719442369926,
      "grad_norm": 1.7513006925582886,
      "learning_rate": 0.0,
      "loss": 35.0961,
      "step": 20
    },
    {
      "epoch": 0.039830719442369926,
      "eval_loss": 2.1275408267974854,
      "eval_runtime": 58.9542,
      "eval_samples_per_second": 14.35,
      "eval_steps_per_second": 7.175,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.013189307039744e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}