{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.15594541910331383,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015594541910331384,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0015594541910331384,
      "eval_loss": NaN,
      "eval_runtime": 30.1553,
      "eval_samples_per_second": 35.815,
      "eval_steps_per_second": 8.954,
      "step": 1
    },
    {
      "epoch": 0.0031189083820662767,
      "grad_norm": NaN,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.004678362573099415,
      "grad_norm": NaN,
      "learning_rate": 1.5e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.006237816764132553,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.007797270955165692,
      "grad_norm": NaN,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": NaN,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.01091617933723197,
      "grad_norm": NaN,
      "learning_rate": 3.5e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.012475633528265107,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": NaN,
      "learning_rate": 4.5e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.015594541910331383,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.017153996101364522,
      "grad_norm": NaN,
      "learning_rate": 4.99847706754774e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": NaN,
      "learning_rate": 4.993910125649561e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0202729044834308,
      "grad_norm": NaN,
      "learning_rate": 4.986304738420684e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.02183235867446394,
      "grad_norm": NaN,
      "learning_rate": 4.975670171853926e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": NaN,
      "learning_rate": 4.962019382530521e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.024951267056530214,
      "grad_norm": NaN,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.026510721247563353,
      "grad_norm": NaN,
      "learning_rate": 4.925739315689991e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": NaN,
      "learning_rate": 4.903154239845798e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": NaN,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.031189083820662766,
      "grad_norm": NaN,
      "learning_rate": 4.849231551964771e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.03274853801169591,
      "grad_norm": NaN,
      "learning_rate": 4.817959636416969e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.034307992202729044,
      "grad_norm": NaN,
      "learning_rate": 4.783863644106502e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.03586744639376218,
      "grad_norm": NaN,
      "learning_rate": 4.746985115747918e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": NaN,
      "learning_rate": 4.707368982147318e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.03898635477582846,
      "grad_norm": NaN,
      "learning_rate": 4.665063509461098e-06,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0405458089668616,
      "grad_norm": NaN,
      "learning_rate": 4.620120240391065e-06,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": NaN,
      "learning_rate": 4.572593931387604e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.04366471734892788,
      "grad_norm": NaN,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.045224171539961014,
      "grad_norm": NaN,
      "learning_rate": 4.470026884016805e-06,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": NaN,
      "learning_rate": 4.415111107797445e-06,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.04834307992202729,
      "grad_norm": NaN,
      "learning_rate": 4.357862063693486e-06,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.04990253411306043,
      "grad_norm": NaN,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.05146198830409357,
      "grad_norm": NaN,
      "learning_rate": 4.236645926147493e-06,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.053021442495126705,
      "grad_norm": NaN,
      "learning_rate": 4.172826515897146e-06,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.05458089668615984,
      "grad_norm": NaN,
      "learning_rate": 4.106969024216348e-06,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": NaN,
      "learning_rate": 4.039153688314146e-06,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.05769980506822612,
      "grad_norm": NaN,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": NaN,
      "learning_rate": 3.897982258676867e-06,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.0608187134502924,
      "grad_norm": NaN,
      "learning_rate": 3.824798160583012e-06,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.06237816764132553,
      "grad_norm": NaN,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.06393762183235867,
      "grad_norm": NaN,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.06549707602339182,
      "grad_norm": NaN,
      "learning_rate": 3.595927866972694e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.06705653021442495,
      "grad_norm": NaN,
      "learning_rate": 3.516841607689501e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.06861598440545809,
      "grad_norm": NaN,
      "learning_rate": 3.436516483539781e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": NaN,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.07173489278752436,
      "grad_norm": NaN,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.07329434697855751,
      "grad_norm": NaN,
      "learning_rate": 3.189093389542498e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.07485380116959064,
      "grad_norm": NaN,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.07641325536062378,
      "grad_norm": NaN,
      "learning_rate": 3.019779227044398e-06,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.07797270955165692,
      "grad_norm": NaN,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.07797270955165692,
      "eval_loss": NaN,
      "eval_runtime": 30.1834,
      "eval_samples_per_second": 35.781,
      "eval_steps_per_second": 8.945,
      "step": 50
    },
    {
      "epoch": 0.07953216374269007,
      "grad_norm": NaN,
      "learning_rate": 2.847932752400164e-06,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.0810916179337232,
      "grad_norm": NaN,
      "learning_rate": 2.761321158169134e-06,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.08265107212475634,
      "grad_norm": NaN,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": NaN,
      "learning_rate": 2.587248741756253e-06,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.08576998050682261,
      "grad_norm": NaN,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.08732943469785576,
      "grad_norm": NaN,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": NaN,
      "learning_rate": 2.325608815639687e-06,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.09044834307992203,
      "grad_norm": NaN,
      "learning_rate": 2.238678841830867e-06,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.09200779727095516,
      "grad_norm": NaN,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": NaN,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.09512670565302145,
      "grad_norm": NaN,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.09668615984405458,
      "grad_norm": NaN,
      "learning_rate": 1.895195261000831e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.09824561403508772,
      "grad_norm": NaN,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.09980506822612085,
      "grad_norm": NaN,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.10136452241715399,
      "grad_norm": NaN,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.10292397660818714,
      "grad_norm": NaN,
      "learning_rate": 1.56348351646022e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.10448343079922028,
      "grad_norm": NaN,
      "learning_rate": 1.4831583923105e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.10604288499025341,
      "grad_norm": NaN,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.10760233918128655,
      "grad_norm": NaN,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.10916179337231968,
      "grad_norm": NaN,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.11072124756335283,
      "grad_norm": NaN,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.11228070175438597,
      "grad_norm": NaN,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.1138401559454191,
      "grad_norm": NaN,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.11539961013645224,
      "grad_norm": NaN,
      "learning_rate": 9.608463116858544e-07,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": NaN,
      "learning_rate": 8.930309757836517e-07,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": NaN,
      "learning_rate": 8.271734841028553e-07,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.12007797270955166,
      "grad_norm": NaN,
      "learning_rate": 7.633540738525066e-07,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.1216374269005848,
      "grad_norm": NaN,
      "learning_rate": 7.016504991533727e-07,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.12319688109161793,
      "grad_norm": NaN,
      "learning_rate": 6.421379363065142e-07,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.12475633528265107,
      "grad_norm": NaN,
      "learning_rate": 5.848888922025553e-07,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": NaN,
      "learning_rate": 5.299731159831953e-07,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.12787524366471734,
      "grad_norm": NaN,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.12943469785575049,
      "grad_norm": NaN,
      "learning_rate": 4.27406068612396e-07,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.13099415204678364,
      "grad_norm": NaN,
      "learning_rate": 3.798797596089351e-07,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.13255360623781676,
      "grad_norm": NaN,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.1341130604288499,
      "grad_norm": NaN,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.13567251461988303,
      "grad_norm": NaN,
      "learning_rate": 2.53014884252083e-07,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.13723196881091618,
      "grad_norm": NaN,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.13879142300194933,
      "grad_norm": NaN,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": NaN,
      "learning_rate": 1.507684480352292e-07,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.1419103313840156,
      "grad_norm": NaN,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.14346978557504872,
      "grad_norm": NaN,
      "learning_rate": 9.684576015420277e-08,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.14502923976608187,
      "grad_norm": NaN,
      "learning_rate": 7.426068431000883e-08,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.14658869395711502,
      "grad_norm": NaN,
      "learning_rate": 5.463099816548578e-08,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": NaN,
      "learning_rate": 3.798061746947995e-08,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.1497076023391813,
      "grad_norm": NaN,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.15126705653021444,
      "grad_norm": NaN,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.15282651072124756,
      "grad_norm": NaN,
      "learning_rate": 6.089874350439507e-09,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.1543859649122807,
      "grad_norm": NaN,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.15594541910331383,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.15594541910331383,
      "eval_loss": NaN,
      "eval_runtime": 30.2001,
      "eval_samples_per_second": 35.761,
      "eval_steps_per_second": 8.94,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 2.61253767364608e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}