{
  "best_metric": 0.864888072013855,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.46893317702227433,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009378663540445486,
      "grad_norm": 1.6919692754745483,
      "learning_rate": 5e-05,
      "loss": 1.9816,
      "step": 1
    },
    {
      "epoch": 0.009378663540445486,
      "eval_loss": 2.5395376682281494,
      "eval_runtime": 21.6934,
      "eval_samples_per_second": 33.098,
      "eval_steps_per_second": 4.149,
      "step": 1
    },
    {
      "epoch": 0.01875732708089097,
      "grad_norm": 2.010314464569092,
      "learning_rate": 0.0001,
      "loss": 2.2339,
      "step": 2
    },
    {
      "epoch": 0.02813599062133646,
      "grad_norm": 2.082699775695801,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.2338,
      "step": 3
    },
    {
      "epoch": 0.03751465416178194,
      "grad_norm": 2.1474432945251465,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.8797,
      "step": 4
    },
    {
      "epoch": 0.04689331770222743,
      "grad_norm": 1.8727260828018188,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.5543,
      "step": 5
    },
    {
      "epoch": 0.05627198124267292,
      "grad_norm": 1.7622548341751099,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.3558,
      "step": 6
    },
    {
      "epoch": 0.06565064478311841,
      "grad_norm": 1.4301575422286987,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.1227,
      "step": 7
    },
    {
      "epoch": 0.07502930832356389,
      "grad_norm": 1.3731272220611572,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0405,
      "step": 8
    },
    {
      "epoch": 0.08440797186400938,
      "grad_norm": 1.420855164527893,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.975,
      "step": 9
    },
    {
      "epoch": 0.09378663540445487,
      "grad_norm": 1.2663978338241577,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9297,
      "step": 10
    },
    {
      "epoch": 0.10316529894490035,
      "grad_norm": 0.9646064639091492,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.8845,
      "step": 11
    },
    {
      "epoch": 0.11254396248534584,
      "grad_norm": 1.0131936073303223,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.7583,
      "step": 12
    },
    {
      "epoch": 0.12192262602579132,
      "grad_norm": 2.2276594638824463,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.2909,
      "step": 13
    },
    {
      "epoch": 0.13130128956623682,
      "grad_norm": 2.046715021133423,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1769,
      "step": 14
    },
    {
      "epoch": 0.1406799531066823,
      "grad_norm": 1.0816984176635742,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.0758,
      "step": 15
    },
    {
      "epoch": 0.15005861664712777,
      "grad_norm": 1.1576021909713745,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.0064,
      "step": 16
    },
    {
      "epoch": 0.15943728018757328,
      "grad_norm": 0.9515407681465149,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.9878,
      "step": 17
    },
    {
      "epoch": 0.16881594372801875,
      "grad_norm": 0.8031420111656189,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9488,
      "step": 18
    },
    {
      "epoch": 0.17819460726846426,
      "grad_norm": 0.8776895999908447,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.8902,
      "step": 19
    },
    {
      "epoch": 0.18757327080890973,
      "grad_norm": 0.6725500226020813,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8929,
      "step": 20
    },
    {
      "epoch": 0.1969519343493552,
      "grad_norm": 0.6378517150878906,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.8383,
      "step": 21
    },
    {
      "epoch": 0.2063305978898007,
      "grad_norm": 0.5901539921760559,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8517,
      "step": 22
    },
    {
      "epoch": 0.21570926143024619,
      "grad_norm": 0.6172890067100525,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.8127,
      "step": 23
    },
    {
      "epoch": 0.2250879249706917,
      "grad_norm": 0.6572589874267578,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.778,
      "step": 24
    },
    {
      "epoch": 0.23446658851113716,
      "grad_norm": 0.8079172968864441,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.7147,
      "step": 25
    },
    {
      "epoch": 0.23446658851113716,
      "eval_loss": 0.9022783637046814,
      "eval_runtime": 21.7408,
      "eval_samples_per_second": 33.025,
      "eval_steps_per_second": 4.14,
      "step": 25
    },
    {
      "epoch": 0.24384525205158264,
      "grad_norm": 1.026550531387329,
      "learning_rate": 5e-05,
      "loss": 1.0879,
      "step": 26
    },
    {
      "epoch": 0.2532239155920281,
      "grad_norm": 1.003537893295288,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.0284,
      "step": 27
    },
    {
      "epoch": 0.26260257913247365,
      "grad_norm": 0.7942367792129517,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.9807,
      "step": 28
    },
    {
      "epoch": 0.2719812426729191,
      "grad_norm": 0.5820752382278442,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.9545,
      "step": 29
    },
    {
      "epoch": 0.2813599062133646,
      "grad_norm": 0.45629891753196716,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8808,
      "step": 30
    },
    {
      "epoch": 0.29073856975381007,
      "grad_norm": 0.6787412762641907,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.9189,
      "step": 31
    },
    {
      "epoch": 0.30011723329425555,
      "grad_norm": 0.7377832531929016,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.8183,
      "step": 32
    },
    {
      "epoch": 0.3094958968347011,
      "grad_norm": 0.7037996649742126,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.8804,
      "step": 33
    },
    {
      "epoch": 0.31887456037514655,
      "grad_norm": 0.6749622225761414,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7713,
      "step": 34
    },
    {
      "epoch": 0.32825322391559203,
      "grad_norm": 0.6450227499008179,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.8081,
      "step": 35
    },
    {
      "epoch": 0.3376318874560375,
      "grad_norm": 0.6441214084625244,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.8022,
      "step": 36
    },
    {
      "epoch": 0.347010550996483,
      "grad_norm": 0.6708666086196899,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.7003,
      "step": 37
    },
    {
      "epoch": 0.3563892145369285,
      "grad_norm": 0.6430343389511108,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.0176,
      "step": 38
    },
    {
      "epoch": 0.365767878077374,
      "grad_norm": 0.7903113961219788,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.986,
      "step": 39
    },
    {
      "epoch": 0.37514654161781946,
      "grad_norm": 0.7977195382118225,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.9674,
      "step": 40
    },
    {
      "epoch": 0.38452520515826494,
      "grad_norm": 0.7614197134971619,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.9324,
      "step": 41
    },
    {
      "epoch": 0.3939038686987104,
      "grad_norm": 0.708970844745636,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.9519,
      "step": 42
    },
    {
      "epoch": 0.40328253223915594,
      "grad_norm": 0.5555177927017212,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.9016,
      "step": 43
    },
    {
      "epoch": 0.4126611957796014,
      "grad_norm": 0.5195717215538025,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.8353,
      "step": 44
    },
    {
      "epoch": 0.4220398593200469,
      "grad_norm": 0.5150408148765564,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.8043,
      "step": 45
    },
    {
      "epoch": 0.43141852286049237,
      "grad_norm": 0.4650251269340515,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.771,
      "step": 46
    },
    {
      "epoch": 0.44079718640093785,
      "grad_norm": 0.48360204696655273,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.7692,
      "step": 47
    },
    {
      "epoch": 0.4501758499413834,
      "grad_norm": 0.5229669809341431,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.8185,
      "step": 48
    },
    {
      "epoch": 0.45955451348182885,
      "grad_norm": 0.5888627171516418,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.7044,
      "step": 49
    },
    {
      "epoch": 0.46893317702227433,
      "grad_norm": 0.861103355884552,
      "learning_rate": 0.0,
      "loss": 0.7366,
      "step": 50
    },
    {
      "epoch": 0.46893317702227433,
      "eval_loss": 0.864888072013855,
      "eval_runtime": 21.7296,
      "eval_samples_per_second": 33.042,
      "eval_steps_per_second": 4.142,
      "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": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}