{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.10803324099723,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0110803324099723,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0110803324099723,
      "eval_loss": NaN,
      "eval_runtime": 7.2492,
      "eval_samples_per_second": 21.106,
      "eval_steps_per_second": 5.38,
      "step": 1
    },
    {
      "epoch": 0.0221606648199446,
      "grad_norm": NaN,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0332409972299169,
      "grad_norm": NaN,
      "learning_rate": 1.5e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0443213296398892,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.055401662049861494,
      "grad_norm": NaN,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0664819944598338,
      "grad_norm": NaN,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.07756232686980609,
      "grad_norm": NaN,
      "learning_rate": 3.5e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0886426592797784,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0997229916897507,
      "grad_norm": NaN,
      "learning_rate": 4.5e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.11080332409972299,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.12188365650969529,
      "grad_norm": NaN,
      "learning_rate": 4.99847706754774e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.1329639889196676,
      "grad_norm": NaN,
      "learning_rate": 4.993910125649561e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.1440443213296399,
      "grad_norm": NaN,
      "learning_rate": 4.986304738420684e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.15512465373961218,
      "grad_norm": NaN,
      "learning_rate": 4.975670171853926e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.16620498614958448,
      "grad_norm": NaN,
      "learning_rate": 4.962019382530521e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.1772853185595568,
      "grad_norm": NaN,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.1883656509695291,
      "grad_norm": NaN,
      "learning_rate": 4.925739315689991e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.1994459833795014,
      "grad_norm": NaN,
      "learning_rate": 4.903154239845798e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": NaN,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.22160664819944598,
      "grad_norm": NaN,
      "learning_rate": 4.849231551964771e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.23268698060941828,
      "grad_norm": NaN,
      "learning_rate": 4.817959636416969e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.24376731301939059,
      "grad_norm": NaN,
      "learning_rate": 4.783863644106502e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.2548476454293629,
      "grad_norm": NaN,
      "learning_rate": 4.746985115747918e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.2659279778393352,
      "grad_norm": NaN,
      "learning_rate": 4.707368982147318e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.2770083102493075,
      "grad_norm": NaN,
      "learning_rate": 4.665063509461098e-06,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.2880886426592798,
      "grad_norm": NaN,
      "learning_rate": 4.620120240391065e-06,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.29916897506925205,
      "grad_norm": NaN,
      "learning_rate": 4.572593931387604e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.31024930747922436,
      "grad_norm": NaN,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.32132963988919666,
      "grad_norm": NaN,
      "learning_rate": 4.470026884016805e-06,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.33240997229916897,
      "grad_norm": NaN,
      "learning_rate": 4.415111107797445e-06,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.34349030470914127,
      "grad_norm": NaN,
      "learning_rate": 4.357862063693486e-06,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.3545706371191136,
      "grad_norm": NaN,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.3656509695290859,
      "grad_norm": NaN,
      "learning_rate": 4.236645926147493e-06,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.3767313019390582,
      "grad_norm": NaN,
      "learning_rate": 4.172826515897146e-06,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.3878116343490305,
      "grad_norm": NaN,
      "learning_rate": 4.106969024216348e-06,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.3988919667590028,
      "grad_norm": NaN,
      "learning_rate": 4.039153688314146e-06,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.4099722991689751,
      "grad_norm": NaN,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": NaN,
      "learning_rate": 3.897982258676867e-06,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.43213296398891965,
      "grad_norm": NaN,
      "learning_rate": 3.824798160583012e-06,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.44321329639889195,
      "grad_norm": NaN,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.45429362880886426,
      "grad_norm": NaN,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.46537396121883656,
      "grad_norm": NaN,
      "learning_rate": 3.595927866972694e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.47645429362880887,
      "grad_norm": NaN,
      "learning_rate": 3.516841607689501e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.48753462603878117,
      "grad_norm": NaN,
      "learning_rate": 3.436516483539781e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.4986149584487535,
      "grad_norm": NaN,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.5096952908587258,
      "grad_norm": NaN,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.5207756232686981,
      "grad_norm": NaN,
      "learning_rate": 3.189093389542498e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.5318559556786704,
      "grad_norm": NaN,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.5429362880886427,
      "grad_norm": NaN,
      "learning_rate": 3.019779227044398e-06,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.554016620498615,
      "grad_norm": NaN,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.554016620498615,
      "eval_loss": NaN,
      "eval_runtime": 6.7415,
      "eval_samples_per_second": 22.695,
      "eval_steps_per_second": 5.785,
      "step": 50
    },
    {
      "epoch": 0.5650969529085873,
      "grad_norm": NaN,
      "learning_rate": 2.847932752400164e-06,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.5761772853185596,
      "grad_norm": NaN,
      "learning_rate": 2.761321158169134e-06,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.5872576177285319,
      "grad_norm": NaN,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.5983379501385041,
      "grad_norm": NaN,
      "learning_rate": 2.587248741756253e-06,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.6094182825484764,
      "grad_norm": NaN,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.6204986149584487,
      "grad_norm": NaN,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": NaN,
      "learning_rate": 2.325608815639687e-06,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.6426592797783933,
      "grad_norm": NaN,
      "learning_rate": 2.238678841830867e-06,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.6537396121883656,
      "grad_norm": NaN,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.6648199445983379,
      "grad_norm": NaN,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.6759002770083102,
      "grad_norm": NaN,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.6869806094182825,
      "grad_norm": NaN,
      "learning_rate": 1.895195261000831e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.6980609418282548,
      "grad_norm": NaN,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.7091412742382271,
      "grad_norm": NaN,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.7202216066481995,
      "grad_norm": NaN,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.7313019390581718,
      "grad_norm": NaN,
      "learning_rate": 1.56348351646022e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.7423822714681441,
      "grad_norm": NaN,
      "learning_rate": 1.4831583923105e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.7534626038781164,
      "grad_norm": NaN,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.7645429362880887,
      "grad_norm": NaN,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.775623268698061,
      "grad_norm": NaN,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.7867036011080333,
      "grad_norm": NaN,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.7977839335180056,
      "grad_norm": NaN,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.8088642659279779,
      "grad_norm": NaN,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.8199445983379502,
      "grad_norm": NaN,
      "learning_rate": 9.608463116858544e-07,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.8310249307479224,
      "grad_norm": NaN,
      "learning_rate": 8.930309757836517e-07,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": NaN,
      "learning_rate": 8.271734841028553e-07,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.853185595567867,
      "grad_norm": NaN,
      "learning_rate": 7.633540738525066e-07,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.8642659279778393,
      "grad_norm": NaN,
      "learning_rate": 7.016504991533727e-07,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.8753462603878116,
      "grad_norm": NaN,
      "learning_rate": 6.421379363065142e-07,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.8864265927977839,
      "grad_norm": NaN,
      "learning_rate": 5.848888922025553e-07,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.8975069252077562,
      "grad_norm": NaN,
      "learning_rate": 5.299731159831953e-07,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.9085872576177285,
      "grad_norm": NaN,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.9196675900277008,
      "grad_norm": NaN,
      "learning_rate": 4.27406068612396e-07,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.9307479224376731,
      "grad_norm": NaN,
      "learning_rate": 3.798797596089351e-07,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.9418282548476454,
      "grad_norm": NaN,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.9529085872576177,
      "grad_norm": NaN,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.96398891966759,
      "grad_norm": NaN,
      "learning_rate": 2.53014884252083e-07,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.9750692520775623,
      "grad_norm": NaN,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.9861495844875346,
      "grad_norm": NaN,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.997229916897507,
      "grad_norm": NaN,
      "learning_rate": 1.507684480352292e-07,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 1.0083102493074791,
      "grad_norm": NaN,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 1.0193905817174516,
      "grad_norm": NaN,
      "learning_rate": 9.684576015420277e-08,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 1.0304709141274238,
      "grad_norm": NaN,
      "learning_rate": 7.426068431000883e-08,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 1.0415512465373962,
      "grad_norm": NaN,
      "learning_rate": 5.463099816548578e-08,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": NaN,
      "learning_rate": 3.798061746947995e-08,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 1.0637119113573408,
      "grad_norm": NaN,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 1.074792243767313,
      "grad_norm": NaN,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 1.0858725761772854,
      "grad_norm": NaN,
      "learning_rate": 6.089874350439507e-09,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 1.0969529085872576,
      "grad_norm": NaN,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 1.10803324099723,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 1.10803324099723,
      "eval_loss": NaN,
      "eval_runtime": 6.743,
      "eval_samples_per_second": 22.69,
      "eval_steps_per_second": 5.784,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.631608502406349e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}