{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9221902017291066,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018443804034582133,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.018443804034582133,
      "eval_loss": NaN,
      "eval_runtime": 9.3165,
      "eval_samples_per_second": 39.285,
      "eval_steps_per_second": 9.875,
      "step": 1
    },
    {
      "epoch": 0.03688760806916427,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0553314121037464,
      "grad_norm": NaN,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.07377521613832853,
      "grad_norm": NaN,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.09221902017291066,
      "grad_norm": NaN,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.1106628242074928,
      "grad_norm": NaN,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.12910662824207492,
      "grad_norm": NaN,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.14755043227665707,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.1659942363112392,
      "grad_norm": NaN,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.1844380403458213,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.20288184438040346,
      "grad_norm": NaN,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.2213256484149856,
      "grad_norm": NaN,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.2397694524495677,
      "grad_norm": NaN,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.2397694524495677,
      "eval_loss": NaN,
      "eval_runtime": 8.8251,
      "eval_samples_per_second": 41.472,
      "eval_steps_per_second": 10.425,
      "step": 13
    },
    {
      "epoch": 0.25821325648414983,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.276657060518732,
      "grad_norm": NaN,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.29510086455331414,
      "grad_norm": NaN,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.31354466858789626,
      "grad_norm": NaN,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.3319884726224784,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.3504322766570605,
      "grad_norm": NaN,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.3688760806916426,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.3873198847262248,
      "grad_norm": NaN,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.40576368876080693,
      "grad_norm": NaN,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.42420749279538905,
      "grad_norm": NaN,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.4426512968299712,
      "grad_norm": NaN,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.4610951008645533,
      "grad_norm": NaN,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.4795389048991354,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.4795389048991354,
      "eval_loss": NaN,
      "eval_runtime": 8.8259,
      "eval_samples_per_second": 41.469,
      "eval_steps_per_second": 10.424,
      "step": 26
    },
    {
      "epoch": 0.4979827089337176,
      "grad_norm": NaN,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.5164265129682997,
      "grad_norm": NaN,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.5348703170028818,
      "grad_norm": NaN,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.553314121037464,
      "grad_norm": NaN,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.5717579250720461,
      "grad_norm": NaN,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.5902017291066283,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.6086455331412104,
      "grad_norm": NaN,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.6270893371757925,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.6455331412103746,
      "grad_norm": NaN,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.6639769452449568,
      "grad_norm": NaN,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.6824207492795389,
      "grad_norm": NaN,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.700864553314121,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.7193083573487031,
      "grad_norm": NaN,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.7193083573487031,
      "eval_loss": NaN,
      "eval_runtime": 8.8268,
      "eval_samples_per_second": 41.464,
      "eval_steps_per_second": 10.423,
      "step": 39
    },
    {
      "epoch": 0.7377521613832853,
      "grad_norm": NaN,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.7561959654178675,
      "grad_norm": NaN,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.7746397694524496,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.7930835734870317,
      "grad_norm": NaN,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.8115273775216139,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.829971181556196,
      "grad_norm": NaN,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.8484149855907781,
      "grad_norm": NaN,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.8668587896253602,
      "grad_norm": NaN,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.8853025936599423,
      "grad_norm": NaN,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.9037463976945245,
      "grad_norm": NaN,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.9221902017291066,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.7676344066048e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}