{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.987551867219917,
  "eval_steps": 500,
  "global_step": 360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08298755186721991,
      "grad_norm": 0.4138890994781238,
      "learning_rate": 5e-06,
      "loss": 0.6819,
      "step": 10
    },
    {
      "epoch": 0.16597510373443983,
      "grad_norm": 0.29279799441362253,
      "learning_rate": 5e-06,
      "loss": 0.6152,
      "step": 20
    },
    {
      "epoch": 0.24896265560165975,
      "grad_norm": 0.22155490022279595,
      "learning_rate": 5e-06,
      "loss": 0.5911,
      "step": 30
    },
    {
      "epoch": 0.33195020746887965,
      "grad_norm": 0.21703792973144043,
      "learning_rate": 5e-06,
      "loss": 0.5758,
      "step": 40
    },
    {
      "epoch": 0.4149377593360996,
      "grad_norm": 0.19782125949582666,
      "learning_rate": 5e-06,
      "loss": 0.5658,
      "step": 50
    },
    {
      "epoch": 0.4979253112033195,
      "grad_norm": 0.20429620764864578,
      "learning_rate": 5e-06,
      "loss": 0.5621,
      "step": 60
    },
    {
      "epoch": 0.5809128630705395,
      "grad_norm": 0.1947179711144,
      "learning_rate": 5e-06,
      "loss": 0.5481,
      "step": 70
    },
    {
      "epoch": 0.6639004149377593,
      "grad_norm": 0.20952965041956714,
      "learning_rate": 5e-06,
      "loss": 0.5491,
      "step": 80
    },
    {
      "epoch": 0.7468879668049793,
      "grad_norm": 0.2092027679734135,
      "learning_rate": 5e-06,
      "loss": 0.5473,
      "step": 90
    },
    {
      "epoch": 0.8298755186721992,
      "grad_norm": 0.1973704614234666,
      "learning_rate": 5e-06,
      "loss": 0.5412,
      "step": 100
    },
    {
      "epoch": 0.9128630705394191,
      "grad_norm": 0.22215520376065145,
      "learning_rate": 5e-06,
      "loss": 0.5361,
      "step": 110
    },
    {
      "epoch": 0.995850622406639,
      "grad_norm": 0.20002555613598916,
      "learning_rate": 5e-06,
      "loss": 0.5354,
      "step": 120
    },
    {
      "epoch": 0.995850622406639,
      "eval_loss": 0.5283368229866028,
      "eval_runtime": 121.5237,
      "eval_samples_per_second": 26.703,
      "eval_steps_per_second": 0.42,
      "step": 120
    },
    {
      "epoch": 1.0788381742738589,
      "grad_norm": 0.23151869944663353,
      "learning_rate": 5e-06,
      "loss": 0.5334,
      "step": 130
    },
    {
      "epoch": 1.161825726141079,
      "grad_norm": 0.20416069004838694,
      "learning_rate": 5e-06,
      "loss": 0.5122,
      "step": 140
    },
    {
      "epoch": 1.2448132780082988,
      "grad_norm": 0.21256654137396935,
      "learning_rate": 5e-06,
      "loss": 0.509,
      "step": 150
    },
    {
      "epoch": 1.3278008298755186,
      "grad_norm": 0.21018667523519946,
      "learning_rate": 5e-06,
      "loss": 0.5041,
      "step": 160
    },
    {
      "epoch": 1.4107883817427385,
      "grad_norm": 0.219240042940767,
      "learning_rate": 5e-06,
      "loss": 0.4998,
      "step": 170
    },
    {
      "epoch": 1.4937759336099585,
      "grad_norm": 0.22681455392212077,
      "learning_rate": 5e-06,
      "loss": 0.5037,
      "step": 180
    },
    {
      "epoch": 1.5767634854771784,
      "grad_norm": 0.227133839723048,
      "learning_rate": 5e-06,
      "loss": 0.4977,
      "step": 190
    },
    {
      "epoch": 1.6597510373443982,
      "grad_norm": 0.21040711904959797,
      "learning_rate": 5e-06,
      "loss": 0.4941,
      "step": 200
    },
    {
      "epoch": 1.7427385892116183,
      "grad_norm": 0.23482785666403702,
      "learning_rate": 5e-06,
      "loss": 0.4945,
      "step": 210
    },
    {
      "epoch": 1.8257261410788381,
      "grad_norm": 0.2035179907011211,
      "learning_rate": 5e-06,
      "loss": 0.4904,
      "step": 220
    },
    {
      "epoch": 1.908713692946058,
      "grad_norm": 0.21720290177963564,
      "learning_rate": 5e-06,
      "loss": 0.491,
      "step": 230
    },
    {
      "epoch": 1.991701244813278,
      "grad_norm": 0.2214820393037949,
      "learning_rate": 5e-06,
      "loss": 0.4901,
      "step": 240
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5045989155769348,
      "eval_runtime": 122.3281,
      "eval_samples_per_second": 26.527,
      "eval_steps_per_second": 0.417,
      "step": 241
    },
    {
      "epoch": 2.074688796680498,
      "grad_norm": 0.25601226331965665,
      "learning_rate": 5e-06,
      "loss": 0.4945,
      "step": 250
    },
    {
      "epoch": 2.1576763485477177,
      "grad_norm": 0.2537099080076595,
      "learning_rate": 5e-06,
      "loss": 0.4617,
      "step": 260
    },
    {
      "epoch": 2.240663900414938,
      "grad_norm": 0.2445352596834903,
      "learning_rate": 5e-06,
      "loss": 0.4648,
      "step": 270
    },
    {
      "epoch": 2.323651452282158,
      "grad_norm": 0.24195048816699535,
      "learning_rate": 5e-06,
      "loss": 0.4688,
      "step": 280
    },
    {
      "epoch": 2.4066390041493775,
      "grad_norm": 0.3297443855710949,
      "learning_rate": 5e-06,
      "loss": 0.46,
      "step": 290
    },
    {
      "epoch": 2.4896265560165975,
      "grad_norm": 0.2227067008121754,
      "learning_rate": 5e-06,
      "loss": 0.4679,
      "step": 300
    },
    {
      "epoch": 2.572614107883817,
      "grad_norm": 0.24268677689146825,
      "learning_rate": 5e-06,
      "loss": 0.4642,
      "step": 310
    },
    {
      "epoch": 2.6556016597510372,
      "grad_norm": 0.24131530500929413,
      "learning_rate": 5e-06,
      "loss": 0.4597,
      "step": 320
    },
    {
      "epoch": 2.7385892116182573,
      "grad_norm": 0.22997089130920098,
      "learning_rate": 5e-06,
      "loss": 0.4617,
      "step": 330
    },
    {
      "epoch": 2.821576763485477,
      "grad_norm": 0.23994756278793414,
      "learning_rate": 5e-06,
      "loss": 0.4597,
      "step": 340
    },
    {
      "epoch": 2.904564315352697,
      "grad_norm": 0.23257285232469585,
      "learning_rate": 5e-06,
      "loss": 0.4545,
      "step": 350
    },
    {
      "epoch": 2.987551867219917,
      "grad_norm": 0.22525776234601527,
      "learning_rate": 5e-06,
      "loss": 0.4618,
      "step": 360
    },
    {
      "epoch": 2.987551867219917,
      "eval_loss": 0.49428611993789673,
      "eval_runtime": 121.9138,
      "eval_samples_per_second": 26.617,
      "eval_steps_per_second": 0.418,
      "step": 360
    },
    {
      "epoch": 2.987551867219917,
      "step": 360,
      "total_flos": 602804028702720.0,
      "train_loss": 0.5124640332327949,
      "train_runtime": 20041.158,
      "train_samples_per_second": 9.227,
      "train_steps_per_second": 0.018
    }
  ],
  "logging_steps": 10,
  "max_steps": 360,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 602804028702720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}