{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009339875137544255,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.6699375687721277e-05,
      "grad_norm": 3.923980951309204,
      "learning_rate": 1e-05,
      "loss": 177.8125,
      "step": 1
    },
    {
      "epoch": 4.6699375687721277e-05,
      "eval_loss": 11.114120483398438,
      "eval_runtime": 80.7936,
      "eval_samples_per_second": 446.385,
      "eval_steps_per_second": 223.198,
      "step": 1
    },
    {
      "epoch": 9.339875137544255e-05,
      "grad_norm": 3.08783221244812,
      "learning_rate": 2e-05,
      "loss": 177.6875,
      "step": 2
    },
    {
      "epoch": 0.00014009812706316382,
      "grad_norm": 3.221004009246826,
      "learning_rate": 3e-05,
      "loss": 177.75,
      "step": 3
    },
    {
      "epoch": 0.0001867975027508851,
      "grad_norm": 3.4536359310150146,
      "learning_rate": 4e-05,
      "loss": 177.9375,
      "step": 4
    },
    {
      "epoch": 0.00023349687843860636,
      "grad_norm": 3.2778360843658447,
      "learning_rate": 5e-05,
      "loss": 177.8125,
      "step": 5
    },
    {
      "epoch": 0.00023349687843860636,
      "eval_loss": 11.112356185913086,
      "eval_runtime": 61.2595,
      "eval_samples_per_second": 588.725,
      "eval_steps_per_second": 294.37,
      "step": 5
    },
    {
      "epoch": 0.00028019625412632765,
      "grad_norm": 3.054042339324951,
      "learning_rate": 6e-05,
      "loss": 177.8125,
      "step": 6
    },
    {
      "epoch": 0.0003268956298140489,
      "grad_norm": 3.209878444671631,
      "learning_rate": 7e-05,
      "loss": 177.8125,
      "step": 7
    },
    {
      "epoch": 0.0003735950055017702,
      "grad_norm": 3.8219175338745117,
      "learning_rate": 8e-05,
      "loss": 177.75,
      "step": 8
    },
    {
      "epoch": 0.00042029438118949147,
      "grad_norm": 3.903371572494507,
      "learning_rate": 9e-05,
      "loss": 177.625,
      "step": 9
    },
    {
      "epoch": 0.0004669937568772127,
      "grad_norm": 3.0673434734344482,
      "learning_rate": 0.0001,
      "loss": 177.6875,
      "step": 10
    },
    {
      "epoch": 0.0004669937568772127,
      "eval_loss": 11.103985786437988,
      "eval_runtime": 61.5867,
      "eval_samples_per_second": 585.598,
      "eval_steps_per_second": 292.807,
      "step": 10
    },
    {
      "epoch": 0.000513693132564934,
      "grad_norm": 4.010018825531006,
      "learning_rate": 9.755282581475769e-05,
      "loss": 177.6875,
      "step": 11
    },
    {
      "epoch": 0.0005603925082526553,
      "grad_norm": 3.2741129398345947,
      "learning_rate": 9.045084971874738e-05,
      "loss": 177.6875,
      "step": 12
    },
    {
      "epoch": 0.0006070918839403765,
      "grad_norm": 3.3117642402648926,
      "learning_rate": 7.938926261462366e-05,
      "loss": 177.875,
      "step": 13
    },
    {
      "epoch": 0.0006537912596280978,
      "grad_norm": 3.361257791519165,
      "learning_rate": 6.545084971874738e-05,
      "loss": 177.75,
      "step": 14
    },
    {
      "epoch": 0.0007004906353158192,
      "grad_norm": 4.330252647399902,
      "learning_rate": 5e-05,
      "loss": 177.375,
      "step": 15
    },
    {
      "epoch": 0.0007004906353158192,
      "eval_loss": 11.09012508392334,
      "eval_runtime": 61.4037,
      "eval_samples_per_second": 587.342,
      "eval_steps_per_second": 293.679,
      "step": 15
    },
    {
      "epoch": 0.0007471900110035404,
      "grad_norm": 5.150496006011963,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 177.25,
      "step": 16
    },
    {
      "epoch": 0.0007938893866912617,
      "grad_norm": 3.8563666343688965,
      "learning_rate": 2.061073738537635e-05,
      "loss": 177.4375,
      "step": 17
    },
    {
      "epoch": 0.0008405887623789829,
      "grad_norm": 4.245285987854004,
      "learning_rate": 9.549150281252633e-06,
      "loss": 177.375,
      "step": 18
    },
    {
      "epoch": 0.0008872881380667042,
      "grad_norm": 4.283419609069824,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 177.3125,
      "step": 19
    },
    {
      "epoch": 0.0009339875137544255,
      "grad_norm": 4.510223865509033,
      "learning_rate": 0.0,
      "loss": 177.25,
      "step": 20
    },
    {
      "epoch": 0.0009339875137544255,
      "eval_loss": 11.086313247680664,
      "eval_runtime": 61.2994,
      "eval_samples_per_second": 588.341,
      "eval_steps_per_second": 294.179,
      "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": 1282758672384.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}