{
  "best_metric": 12.457971572875977,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.25252525252525254,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005050505050505051,
      "grad_norm": 0.007967030629515648,
      "learning_rate": 5e-05,
      "loss": 12.4568,
      "step": 1
    },
    {
      "epoch": 0.005050505050505051,
      "eval_loss": 12.458647727966309,
      "eval_runtime": 3.5318,
      "eval_samples_per_second": 377.709,
      "eval_steps_per_second": 47.284,
      "step": 1
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 0.006987428292632103,
      "learning_rate": 0.0001,
      "loss": 12.4586,
      "step": 2
    },
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 0.0076015545055270195,
      "learning_rate": 9.989294616193017e-05,
      "loss": 12.4576,
      "step": 3
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 0.00805005431175232,
      "learning_rate": 9.957224306869053e-05,
      "loss": 12.4582,
      "step": 4
    },
    {
      "epoch": 0.025252525252525252,
      "grad_norm": 0.008620443753898144,
      "learning_rate": 9.903926402016153e-05,
      "loss": 12.4585,
      "step": 5
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 0.009005537256598473,
      "learning_rate": 9.829629131445342e-05,
      "loss": 12.4573,
      "step": 6
    },
    {
      "epoch": 0.03535353535353535,
      "grad_norm": 0.010098621249198914,
      "learning_rate": 9.73465064747553e-05,
      "loss": 12.4578,
      "step": 7
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 0.010264664888381958,
      "learning_rate": 9.619397662556435e-05,
      "loss": 12.4588,
      "step": 8
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.01204642467200756,
      "learning_rate": 9.484363707663442e-05,
      "loss": 12.4587,
      "step": 9
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 0.012393363751471043,
      "learning_rate": 9.330127018922194e-05,
      "loss": 12.4588,
      "step": 10
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.011734955944120884,
      "learning_rate": 9.157348061512727e-05,
      "loss": 12.4603,
      "step": 11
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 0.013777339830994606,
      "learning_rate": 8.966766701456177e-05,
      "loss": 12.4596,
      "step": 12
    },
    {
      "epoch": 0.06565656565656566,
      "grad_norm": 0.009245519526302814,
      "learning_rate": 8.759199037394887e-05,
      "loss": 12.4606,
      "step": 13
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 0.007754751946777105,
      "learning_rate": 8.535533905932738e-05,
      "loss": 12.456,
      "step": 14
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 0.008689296431839466,
      "learning_rate": 8.296729075500344e-05,
      "loss": 12.4586,
      "step": 15
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 0.008963293395936489,
      "learning_rate": 8.043807145043604e-05,
      "loss": 12.4586,
      "step": 16
    },
    {
      "epoch": 0.08585858585858586,
      "grad_norm": 0.009418333880603313,
      "learning_rate": 7.777851165098012e-05,
      "loss": 12.4579,
      "step": 17
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.01009095273911953,
      "learning_rate": 7.500000000000001e-05,
      "loss": 12.4582,
      "step": 18
    },
    {
      "epoch": 0.09595959595959595,
      "grad_norm": 0.011326883919537067,
      "learning_rate": 7.211443451095007e-05,
      "loss": 12.4581,
      "step": 19
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 0.011483768932521343,
      "learning_rate": 6.91341716182545e-05,
      "loss": 12.4581,
      "step": 20
    },
    {
      "epoch": 0.10606060606060606,
      "grad_norm": 0.013455575332045555,
      "learning_rate": 6.607197326515808e-05,
      "loss": 12.4589,
      "step": 21
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.011869244277477264,
      "learning_rate": 6.294095225512603e-05,
      "loss": 12.4589,
      "step": 22
    },
    {
      "epoch": 0.11616161616161616,
      "grad_norm": 0.014639693312346935,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 12.4604,
      "step": 23
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.013897615484893322,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 12.46,
      "step": 24
    },
    {
      "epoch": 0.12626262626262627,
      "grad_norm": 0.019724931567907333,
      "learning_rate": 5.327015646150716e-05,
      "loss": 12.4613,
      "step": 25
    },
    {
      "epoch": 0.12626262626262627,
      "eval_loss": 12.458169937133789,
      "eval_runtime": 3.5133,
      "eval_samples_per_second": 379.697,
      "eval_steps_per_second": 47.533,
      "step": 25
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 0.009966455399990082,
      "learning_rate": 5e-05,
      "loss": 12.4584,
      "step": 26
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.00917417835444212,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 12.4572,
      "step": 27
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 0.011121945455670357,
      "learning_rate": 4.347369038899744e-05,
      "loss": 12.4588,
      "step": 28
    },
    {
      "epoch": 0.14646464646464646,
      "grad_norm": 0.010699532926082611,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 12.4575,
      "step": 29
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 0.010851383209228516,
      "learning_rate": 3.705904774487396e-05,
      "loss": 12.4564,
      "step": 30
    },
    {
      "epoch": 0.15656565656565657,
      "grad_norm": 0.012371523305773735,
      "learning_rate": 3.392802673484193e-05,
      "loss": 12.4582,
      "step": 31
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.012677067890763283,
      "learning_rate": 3.086582838174551e-05,
      "loss": 12.4582,
      "step": 32
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.013413293287158012,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 12.4587,
      "step": 33
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 0.016384758055210114,
      "learning_rate": 2.500000000000001e-05,
      "loss": 12.4577,
      "step": 34
    },
    {
      "epoch": 0.17676767676767677,
      "grad_norm": 0.015265684574842453,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 12.4589,
      "step": 35
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.015503032132983208,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 12.46,
      "step": 36
    },
    {
      "epoch": 0.18686868686868688,
      "grad_norm": 0.01569039560854435,
      "learning_rate": 1.703270924499656e-05,
      "loss": 12.4601,
      "step": 37
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 0.012827031314373016,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 12.4605,
      "step": 38
    },
    {
      "epoch": 0.19696969696969696,
      "grad_norm": 0.010645854286849499,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 12.4548,
      "step": 39
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 0.01111725252121687,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 12.4581,
      "step": 40
    },
    {
      "epoch": 0.20707070707070707,
      "grad_norm": 0.012351098470389843,
      "learning_rate": 8.426519384872733e-06,
      "loss": 12.4571,
      "step": 41
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 0.012415647506713867,
      "learning_rate": 6.698729810778065e-06,
      "loss": 12.4576,
      "step": 42
    },
    {
      "epoch": 0.21717171717171718,
      "grad_norm": 0.011739925481379032,
      "learning_rate": 5.156362923365588e-06,
      "loss": 12.4579,
      "step": 43
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.01330937072634697,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 12.4567,
      "step": 44
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.01405568327754736,
      "learning_rate": 2.653493525244721e-06,
      "loss": 12.4572,
      "step": 45
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 0.015090607106685638,
      "learning_rate": 1.70370868554659e-06,
      "loss": 12.4593,
      "step": 46
    },
    {
      "epoch": 0.23737373737373738,
      "grad_norm": 0.015863122418522835,
      "learning_rate": 9.607359798384785e-07,
      "loss": 12.4583,
      "step": 47
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.0159890316426754,
      "learning_rate": 4.277569313094809e-07,
      "loss": 12.4579,
      "step": 48
    },
    {
      "epoch": 0.2474747474747475,
      "grad_norm": 0.01518325787037611,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 12.4595,
      "step": 49
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 0.02028408646583557,
      "learning_rate": 0.0,
      "loss": 12.4622,
      "step": 50
    },
    {
      "epoch": 0.25252525252525254,
      "eval_loss": 12.457971572875977,
      "eval_runtime": 3.5105,
      "eval_samples_per_second": 380.002,
      "eval_steps_per_second": 47.571,
      "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": 843055104000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}