{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.0520446096654275,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05947955390334572,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.05947955390334572,
      "eval_loss": NaN,
      "eval_runtime": 6.8456,
      "eval_samples_per_second": 16.653,
      "eval_steps_per_second": 2.191,
      "step": 1
    },
    {
      "epoch": 0.11895910780669144,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.17843866171003717,
      "grad_norm": NaN,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.2379182156133829,
      "grad_norm": NaN,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.29739776951672864,
      "grad_norm": NaN,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.35687732342007433,
      "grad_norm": NaN,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.4163568773234201,
      "grad_norm": NaN,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.4758364312267658,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.5353159851301115,
      "grad_norm": NaN,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.5947955390334573,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.654275092936803,
      "grad_norm": NaN,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.7137546468401487,
      "grad_norm": NaN,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.7732342007434945,
      "grad_norm": NaN,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.8327137546468402,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.8921933085501859,
      "grad_norm": NaN,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.9516728624535316,
      "grad_norm": NaN,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.037174721189591,
      "grad_norm": NaN,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.096654275092937,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.1561338289962826,
      "grad_norm": NaN,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.2156133828996283,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.275092936802974,
      "grad_norm": NaN,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.3345724907063197,
      "grad_norm": NaN,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.3940520446096654,
      "grad_norm": NaN,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.453531598513011,
      "grad_norm": NaN,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.513011152416357,
      "grad_norm": NaN,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.513011152416357,
      "eval_loss": NaN,
      "eval_runtime": 6.836,
      "eval_samples_per_second": 16.676,
      "eval_steps_per_second": 2.194,
      "step": 25
    },
    {
      "epoch": 1.5724907063197024,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 1.6319702602230484,
      "grad_norm": NaN,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 1.691449814126394,
      "grad_norm": NaN,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 1.7509293680297398,
      "grad_norm": NaN,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 1.8104089219330854,
      "grad_norm": NaN,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 1.8698884758364311,
      "grad_norm": NaN,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 1.929368029739777,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 2.0148698884758365,
      "grad_norm": NaN,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 2.074349442379182,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 2.133828996282528,
      "grad_norm": NaN,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 2.193308550185874,
      "grad_norm": NaN,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 2.2527881040892193,
      "grad_norm": NaN,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 2.312267657992565,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 2.3717472118959106,
      "grad_norm": NaN,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 2.4312267657992566,
      "grad_norm": NaN,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 2.4907063197026025,
      "grad_norm": NaN,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 2.550185873605948,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 2.6096654275092934,
      "grad_norm": NaN,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 2.6691449814126393,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 2.7286245353159853,
      "grad_norm": NaN,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 2.7881040892193307,
      "grad_norm": NaN,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 2.8475836431226766,
      "grad_norm": NaN,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 2.907063197026022,
      "grad_norm": NaN,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 2.966542750929368,
      "grad_norm": NaN,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 3.0520446096654275,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 3.0520446096654275,
      "eval_loss": NaN,
      "eval_runtime": 6.8611,
      "eval_samples_per_second": 16.616,
      "eval_steps_per_second": 2.186,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}