{
  "best_metric": 0.8472527861595154,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.0779220779220777,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04155844155844156,
      "grad_norm": 26.678537368774414,
      "learning_rate": 5e-05,
      "loss": 0.9014,
      "step": 1
    },
    {
      "epoch": 0.04155844155844156,
      "eval_loss": 1.0242455005645752,
      "eval_runtime": 13.1988,
      "eval_samples_per_second": 12.35,
      "eval_steps_per_second": 1.591,
      "step": 1
    },
    {
      "epoch": 0.08311688311688312,
      "grad_norm": 32.76892852783203,
      "learning_rate": 0.0001,
      "loss": 0.942,
      "step": 2
    },
    {
      "epoch": 0.12467532467532468,
      "grad_norm": 7.723164081573486,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.93,
      "step": 3
    },
    {
      "epoch": 0.16623376623376623,
      "grad_norm": 11.668654441833496,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.9356,
      "step": 4
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 9.524209976196289,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.9274,
      "step": 5
    },
    {
      "epoch": 0.24935064935064935,
      "grad_norm": 24.48626136779785,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.158,
      "step": 6
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 5.578686237335205,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.8959,
      "step": 7
    },
    {
      "epoch": 0.33246753246753247,
      "grad_norm": 4.922216415405273,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.8454,
      "step": 8
    },
    {
      "epoch": 0.37402597402597404,
      "grad_norm": 5.787694931030273,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.8614,
      "step": 9
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 6.185394763946533,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.8619,
      "step": 10
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 8.231844902038574,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.9014,
      "step": 11
    },
    {
      "epoch": 0.4987012987012987,
      "grad_norm": 16.160648345947266,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.1022,
      "step": 12
    },
    {
      "epoch": 0.5402597402597402,
      "grad_norm": 4.799185276031494,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.823,
      "step": 13
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 4.614773750305176,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8274,
      "step": 14
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 5.092803478240967,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.8557,
      "step": 15
    },
    {
      "epoch": 0.6649350649350649,
      "grad_norm": 5.591392517089844,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8268,
      "step": 16
    },
    {
      "epoch": 0.7064935064935065,
      "grad_norm": 6.882678031921387,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.846,
      "step": 17
    },
    {
      "epoch": 0.7480519480519481,
      "grad_norm": 13.18076229095459,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0256,
      "step": 18
    },
    {
      "epoch": 0.7896103896103897,
      "grad_norm": 4.476304054260254,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.8561,
      "step": 19
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 4.694456577301025,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8597,
      "step": 20
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 4.749151229858398,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.8267,
      "step": 21
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 5.093811988830566,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8135,
      "step": 22
    },
    {
      "epoch": 0.9558441558441558,
      "grad_norm": 6.440086841583252,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.8457,
      "step": 23
    },
    {
      "epoch": 0.9974025974025974,
      "grad_norm": 14.743223190307617,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.0421,
      "step": 24
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 6.859409332275391,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.7857,
      "step": 25
    },
    {
      "epoch": 1.0389610389610389,
      "eval_loss": 0.8574177622795105,
      "eval_runtime": 5.972,
      "eval_samples_per_second": 27.294,
      "eval_steps_per_second": 3.516,
      "step": 25
    },
    {
      "epoch": 1.0805194805194804,
      "grad_norm": 7.461629390716553,
      "learning_rate": 5e-05,
      "loss": 0.7891,
      "step": 26
    },
    {
      "epoch": 1.122077922077922,
      "grad_norm": 8.457158088684082,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.746,
      "step": 27
    },
    {
      "epoch": 1.1636363636363636,
      "grad_norm": 9.096592903137207,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.7679,
      "step": 28
    },
    {
      "epoch": 1.2051948051948052,
      "grad_norm": 11.256149291992188,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.7985,
      "step": 29
    },
    {
      "epoch": 1.2467532467532467,
      "grad_norm": 19.310684204101562,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8611,
      "step": 30
    },
    {
      "epoch": 1.2883116883116883,
      "grad_norm": 8.05862808227539,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.7934,
      "step": 31
    },
    {
      "epoch": 1.3298701298701299,
      "grad_norm": 8.173073768615723,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7804,
      "step": 32
    },
    {
      "epoch": 1.3714285714285714,
      "grad_norm": 8.027366638183594,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.7394,
      "step": 33
    },
    {
      "epoch": 1.412987012987013,
      "grad_norm": 10.47994613647461,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7495,
      "step": 34
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 12.401349067687988,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.7311,
      "step": 35
    },
    {
      "epoch": 1.4961038961038962,
      "grad_norm": 20.069787979125977,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.8611,
      "step": 36
    },
    {
      "epoch": 1.5376623376623377,
      "grad_norm": 8.742693901062012,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.7572,
      "step": 37
    },
    {
      "epoch": 1.5792207792207793,
      "grad_norm": 8.219439506530762,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7444,
      "step": 38
    },
    {
      "epoch": 1.6207792207792209,
      "grad_norm": 9.581369400024414,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.7499,
      "step": 39
    },
    {
      "epoch": 1.6623376623376624,
      "grad_norm": 9.756193161010742,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.695,
      "step": 40
    },
    {
      "epoch": 1.703896103896104,
      "grad_norm": 12.657617568969727,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.7158,
      "step": 41
    },
    {
      "epoch": 1.7454545454545456,
      "grad_norm": 18.518951416015625,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.7977,
      "step": 42
    },
    {
      "epoch": 1.7870129870129872,
      "grad_norm": 8.128936767578125,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.7749,
      "step": 43
    },
    {
      "epoch": 1.8285714285714287,
      "grad_norm": 8.058290481567383,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7658,
      "step": 44
    },
    {
      "epoch": 1.87012987012987,
      "grad_norm": 8.940549850463867,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.774,
      "step": 45
    },
    {
      "epoch": 1.9116883116883117,
      "grad_norm": 10.234519958496094,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.7182,
      "step": 46
    },
    {
      "epoch": 1.9532467532467532,
      "grad_norm": 12.169855117797852,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.698,
      "step": 47
    },
    {
      "epoch": 1.9948051948051948,
      "grad_norm": 21.937511444091797,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.8068,
      "step": 48
    },
    {
      "epoch": 2.036363636363636,
      "grad_norm": 8.143593788146973,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.7351,
      "step": 49
    },
    {
      "epoch": 2.0779220779220777,
      "grad_norm": 7.586548328399658,
      "learning_rate": 0.0,
      "loss": 0.7503,
      "step": 50
    },
    {
      "epoch": 2.0779220779220777,
      "eval_loss": 0.8472527861595154,
      "eval_runtime": 6.2447,
      "eval_samples_per_second": 26.102,
      "eval_steps_per_second": 3.363,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5.7188690633844326e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}