{
  "best_metric": 11.720179557800293,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.028072145413713244,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005614429082742648,
      "grad_norm": 1.1291954517364502,
      "learning_rate": 5e-05,
      "loss": 11.9347,
      "step": 1
    },
    {
      "epoch": 0.0005614429082742648,
      "eval_loss": 11.954967498779297,
      "eval_runtime": 68.615,
      "eval_samples_per_second": 174.874,
      "eval_steps_per_second": 21.861,
      "step": 1
    },
    {
      "epoch": 0.0011228858165485296,
      "grad_norm": 1.8763145208358765,
      "learning_rate": 0.0001,
      "loss": 11.953,
      "step": 2
    },
    {
      "epoch": 0.0016843287248227946,
      "grad_norm": 2.3550071716308594,
      "learning_rate": 9.989294616193017e-05,
      "loss": 11.9563,
      "step": 3
    },
    {
      "epoch": 0.0022457716330970593,
      "grad_norm": 2.2010278701782227,
      "learning_rate": 9.957224306869053e-05,
      "loss": 11.9405,
      "step": 4
    },
    {
      "epoch": 0.0028072145413713242,
      "grad_norm": 1.841884732246399,
      "learning_rate": 9.903926402016153e-05,
      "loss": 11.9253,
      "step": 5
    },
    {
      "epoch": 0.003368657449645589,
      "grad_norm": 1.818913459777832,
      "learning_rate": 9.829629131445342e-05,
      "loss": 11.9198,
      "step": 6
    },
    {
      "epoch": 0.003930100357919854,
      "grad_norm": 1.7659637928009033,
      "learning_rate": 9.73465064747553e-05,
      "loss": 11.9124,
      "step": 7
    },
    {
      "epoch": 0.004491543266194119,
      "grad_norm": 1.8123968839645386,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.8914,
      "step": 8
    },
    {
      "epoch": 0.005052986174468384,
      "grad_norm": 1.6680165529251099,
      "learning_rate": 9.484363707663442e-05,
      "loss": 11.8784,
      "step": 9
    },
    {
      "epoch": 0.0056144290827426484,
      "grad_norm": 1.6414878368377686,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.8743,
      "step": 10
    },
    {
      "epoch": 0.006175871991016914,
      "grad_norm": 1.8350379467010498,
      "learning_rate": 9.157348061512727e-05,
      "loss": 11.8483,
      "step": 11
    },
    {
      "epoch": 0.006737314899291178,
      "grad_norm": 1.651247501373291,
      "learning_rate": 8.966766701456177e-05,
      "loss": 11.8572,
      "step": 12
    },
    {
      "epoch": 0.007298757807565443,
      "grad_norm": 1.382866621017456,
      "learning_rate": 8.759199037394887e-05,
      "loss": 11.8664,
      "step": 13
    },
    {
      "epoch": 0.007860200715839708,
      "grad_norm": 1.4371793270111084,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.8688,
      "step": 14
    },
    {
      "epoch": 0.008421643624113974,
      "grad_norm": 1.987817406654358,
      "learning_rate": 8.296729075500344e-05,
      "loss": 11.8159,
      "step": 15
    },
    {
      "epoch": 0.008983086532388237,
      "grad_norm": 1.9868531227111816,
      "learning_rate": 8.043807145043604e-05,
      "loss": 11.8038,
      "step": 16
    },
    {
      "epoch": 0.009544529440662503,
      "grad_norm": 1.740243911743164,
      "learning_rate": 7.777851165098012e-05,
      "loss": 11.7998,
      "step": 17
    },
    {
      "epoch": 0.010105972348936768,
      "grad_norm": 1.4886868000030518,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.8032,
      "step": 18
    },
    {
      "epoch": 0.010667415257211032,
      "grad_norm": 1.448880672454834,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.7966,
      "step": 19
    },
    {
      "epoch": 0.011228858165485297,
      "grad_norm": 1.4590189456939697,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.7845,
      "step": 20
    },
    {
      "epoch": 0.011790301073759562,
      "grad_norm": 1.4270671606063843,
      "learning_rate": 6.607197326515808e-05,
      "loss": 11.7782,
      "step": 21
    },
    {
      "epoch": 0.012351743982033828,
      "grad_norm": 1.352054476737976,
      "learning_rate": 6.294095225512603e-05,
      "loss": 11.7704,
      "step": 22
    },
    {
      "epoch": 0.012913186890308091,
      "grad_norm": 1.3217723369598389,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 11.7758,
      "step": 23
    },
    {
      "epoch": 0.013474629798582357,
      "grad_norm": 1.3245567083358765,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 11.7778,
      "step": 24
    },
    {
      "epoch": 0.014036072706856622,
      "grad_norm": 1.3613450527191162,
      "learning_rate": 5.327015646150716e-05,
      "loss": 11.7622,
      "step": 25
    },
    {
      "epoch": 0.014036072706856622,
      "eval_loss": 11.755112648010254,
      "eval_runtime": 70.5782,
      "eval_samples_per_second": 170.01,
      "eval_steps_per_second": 21.253,
      "step": 25
    },
    {
      "epoch": 0.014597515615130886,
      "grad_norm": 1.398974061012268,
      "learning_rate": 5e-05,
      "loss": 11.8343,
      "step": 26
    },
    {
      "epoch": 0.015158958523405151,
      "grad_norm": 1.5043359994888306,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 11.7449,
      "step": 27
    },
    {
      "epoch": 0.015720401431679416,
      "grad_norm": 1.8410756587982178,
      "learning_rate": 4.347369038899744e-05,
      "loss": 11.7265,
      "step": 28
    },
    {
      "epoch": 0.01628184433995368,
      "grad_norm": 1.659067153930664,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 11.7217,
      "step": 29
    },
    {
      "epoch": 0.016843287248227947,
      "grad_norm": 1.1002304553985596,
      "learning_rate": 3.705904774487396e-05,
      "loss": 11.7432,
      "step": 30
    },
    {
      "epoch": 0.01740473015650221,
      "grad_norm": 1.1968733072280884,
      "learning_rate": 3.392802673484193e-05,
      "loss": 11.7378,
      "step": 31
    },
    {
      "epoch": 0.017966173064776474,
      "grad_norm": 1.057620644569397,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.742,
      "step": 32
    },
    {
      "epoch": 0.01852761597305074,
      "grad_norm": 1.080743670463562,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 11.7437,
      "step": 33
    },
    {
      "epoch": 0.019089058881325005,
      "grad_norm": 1.1043583154678345,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.7329,
      "step": 34
    },
    {
      "epoch": 0.01965050178959927,
      "grad_norm": 1.0628371238708496,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 11.7246,
      "step": 35
    },
    {
      "epoch": 0.020211944697873536,
      "grad_norm": 1.0919686555862427,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 11.7271,
      "step": 36
    },
    {
      "epoch": 0.0207733876061478,
      "grad_norm": 1.1903443336486816,
      "learning_rate": 1.703270924499656e-05,
      "loss": 11.7213,
      "step": 37
    },
    {
      "epoch": 0.021334830514422063,
      "grad_norm": 0.9018011689186096,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.7787,
      "step": 38
    },
    {
      "epoch": 0.02189627342269633,
      "grad_norm": 1.1237108707427979,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 11.7984,
      "step": 39
    },
    {
      "epoch": 0.022457716330970594,
      "grad_norm": 1.689167857170105,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 11.695,
      "step": 40
    },
    {
      "epoch": 0.02301915923924486,
      "grad_norm": 1.6919984817504883,
      "learning_rate": 8.426519384872733e-06,
      "loss": 11.6956,
      "step": 41
    },
    {
      "epoch": 0.023580602147519125,
      "grad_norm": 1.2629735469818115,
      "learning_rate": 6.698729810778065e-06,
      "loss": 11.7071,
      "step": 42
    },
    {
      "epoch": 0.024142045055793388,
      "grad_norm": 0.9501758813858032,
      "learning_rate": 5.156362923365588e-06,
      "loss": 11.7307,
      "step": 43
    },
    {
      "epoch": 0.024703487964067655,
      "grad_norm": 0.9177296161651611,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.7405,
      "step": 44
    },
    {
      "epoch": 0.02526493087234192,
      "grad_norm": 1.065750241279602,
      "learning_rate": 2.653493525244721e-06,
      "loss": 11.7187,
      "step": 45
    },
    {
      "epoch": 0.025826373780616182,
      "grad_norm": 1.078781247138977,
      "learning_rate": 1.70370868554659e-06,
      "loss": 11.7146,
      "step": 46
    },
    {
      "epoch": 0.02638781668889045,
      "grad_norm": 1.0444191694259644,
      "learning_rate": 9.607359798384785e-07,
      "loss": 11.7233,
      "step": 47
    },
    {
      "epoch": 0.026949259597164713,
      "grad_norm": 0.9315354824066162,
      "learning_rate": 4.277569313094809e-07,
      "loss": 11.7313,
      "step": 48
    },
    {
      "epoch": 0.027510702505438977,
      "grad_norm": 0.9638807773590088,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 11.7381,
      "step": 49
    },
    {
      "epoch": 0.028072145413713244,
      "grad_norm": 1.1096824407577515,
      "learning_rate": 0.0,
      "loss": 11.7157,
      "step": 50
    },
    {
      "epoch": 0.028072145413713244,
      "eval_loss": 11.720179557800293,
      "eval_runtime": 71.1233,
      "eval_samples_per_second": 168.707,
      "eval_steps_per_second": 21.09,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 550104860721152.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}