{
  "best_metric": 2.521301507949829,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.348280365694384,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006965607313887679,
      "grad_norm": 14.914785385131836,
      "learning_rate": 5e-05,
      "loss": 2.9946,
      "step": 1
    },
    {
      "epoch": 0.006965607313887679,
      "eval_loss": 3.8551180362701416,
      "eval_runtime": 39.8369,
      "eval_samples_per_second": 24.274,
      "eval_steps_per_second": 3.037,
      "step": 1
    },
    {
      "epoch": 0.013931214627775359,
      "grad_norm": 12.962854385375977,
      "learning_rate": 0.0001,
      "loss": 3.1224,
      "step": 2
    },
    {
      "epoch": 0.02089682194166304,
      "grad_norm": 14.299446105957031,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.2202,
      "step": 3
    },
    {
      "epoch": 0.027862429255550717,
      "grad_norm": 19.08392906188965,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.1768,
      "step": 4
    },
    {
      "epoch": 0.0348280365694384,
      "grad_norm": 27.249370574951172,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.1132,
      "step": 5
    },
    {
      "epoch": 0.04179364388332608,
      "grad_norm": 26.656770706176758,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.9958,
      "step": 6
    },
    {
      "epoch": 0.048759251197213756,
      "grad_norm": 32.521759033203125,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.9294,
      "step": 7
    },
    {
      "epoch": 0.055724858511101434,
      "grad_norm": 38.11032485961914,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.8461,
      "step": 8
    },
    {
      "epoch": 0.06269046582498912,
      "grad_norm": 42.11003112792969,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.8183,
      "step": 9
    },
    {
      "epoch": 0.0696560731388768,
      "grad_norm": 45.7680778503418,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.3967,
      "step": 10
    },
    {
      "epoch": 0.07662168045276448,
      "grad_norm": 34.14312744140625,
      "learning_rate": 9.157348061512727e-05,
      "loss": 3.5234,
      "step": 11
    },
    {
      "epoch": 0.08358728776665215,
      "grad_norm": 33.50540542602539,
      "learning_rate": 8.966766701456177e-05,
      "loss": 3.7347,
      "step": 12
    },
    {
      "epoch": 0.09055289508053983,
      "grad_norm": 26.83640480041504,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.4828,
      "step": 13
    },
    {
      "epoch": 0.09751850239442751,
      "grad_norm": 22.63720703125,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.7741,
      "step": 14
    },
    {
      "epoch": 0.10448410970831519,
      "grad_norm": 24.69816780090332,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.6105,
      "step": 15
    },
    {
      "epoch": 0.11144971702220287,
      "grad_norm": 21.516197204589844,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.5476,
      "step": 16
    },
    {
      "epoch": 0.11841532433609055,
      "grad_norm": 37.13068771362305,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.5517,
      "step": 17
    },
    {
      "epoch": 0.12538093164997824,
      "grad_norm": 17.183576583862305,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.4099,
      "step": 18
    },
    {
      "epoch": 0.13234653896386592,
      "grad_norm": 14.289627075195312,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.3682,
      "step": 19
    },
    {
      "epoch": 0.1393121462777536,
      "grad_norm": 9.297135353088379,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.3983,
      "step": 20
    },
    {
      "epoch": 0.14627775359164127,
      "grad_norm": 13.06031322479248,
      "learning_rate": 6.607197326515808e-05,
      "loss": 2.3584,
      "step": 21
    },
    {
      "epoch": 0.15324336090552895,
      "grad_norm": 35.48813247680664,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.808,
      "step": 22
    },
    {
      "epoch": 0.16020896821941663,
      "grad_norm": 52.057186126708984,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.1874,
      "step": 23
    },
    {
      "epoch": 0.1671745755333043,
      "grad_norm": 46.11458969116211,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 3.0909,
      "step": 24
    },
    {
      "epoch": 0.174140182847192,
      "grad_norm": 65.17389678955078,
      "learning_rate": 5.327015646150716e-05,
      "loss": 3.7957,
      "step": 25
    },
    {
      "epoch": 0.174140182847192,
      "eval_loss": 2.6668310165405273,
      "eval_runtime": 39.833,
      "eval_samples_per_second": 24.276,
      "eval_steps_per_second": 3.038,
      "step": 25
    },
    {
      "epoch": 0.18110579016107967,
      "grad_norm": 10.990416526794434,
      "learning_rate": 5e-05,
      "loss": 2.8065,
      "step": 26
    },
    {
      "epoch": 0.18807139747496734,
      "grad_norm": 8.937409400939941,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 2.4433,
      "step": 27
    },
    {
      "epoch": 0.19503700478885502,
      "grad_norm": 11.488622665405273,
      "learning_rate": 4.347369038899744e-05,
      "loss": 2.3725,
      "step": 28
    },
    {
      "epoch": 0.2020026121027427,
      "grad_norm": 9.3021879196167,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 2.3004,
      "step": 29
    },
    {
      "epoch": 0.20896821941663038,
      "grad_norm": 8.825725555419922,
      "learning_rate": 3.705904774487396e-05,
      "loss": 2.2908,
      "step": 30
    },
    {
      "epoch": 0.21593382673051806,
      "grad_norm": 8.21666431427002,
      "learning_rate": 3.392802673484193e-05,
      "loss": 2.2499,
      "step": 31
    },
    {
      "epoch": 0.22289943404440574,
      "grad_norm": 10.44888687133789,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.2541,
      "step": 32
    },
    {
      "epoch": 0.22986504135829341,
      "grad_norm": 12.075174331665039,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 2.299,
      "step": 33
    },
    {
      "epoch": 0.2368306486721811,
      "grad_norm": 13.294587135314941,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.3522,
      "step": 34
    },
    {
      "epoch": 0.24379625598606877,
      "grad_norm": 22.585355758666992,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 2.9737,
      "step": 35
    },
    {
      "epoch": 0.2507618632999565,
      "grad_norm": 34.31892395019531,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 2.6606,
      "step": 36
    },
    {
      "epoch": 0.25772747061384416,
      "grad_norm": 36.366092681884766,
      "learning_rate": 1.703270924499656e-05,
      "loss": 3.1274,
      "step": 37
    },
    {
      "epoch": 0.26469307792773183,
      "grad_norm": 23.1158390045166,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.3618,
      "step": 38
    },
    {
      "epoch": 0.2716586852416195,
      "grad_norm": 6.393037796020508,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 2.5871,
      "step": 39
    },
    {
      "epoch": 0.2786242925555072,
      "grad_norm": 7.840436935424805,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 2.2926,
      "step": 40
    },
    {
      "epoch": 0.28558989986939487,
      "grad_norm": 8.410822868347168,
      "learning_rate": 8.426519384872733e-06,
      "loss": 2.2895,
      "step": 41
    },
    {
      "epoch": 0.29255550718328255,
      "grad_norm": 9.684894561767578,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.2933,
      "step": 42
    },
    {
      "epoch": 0.2995211144971702,
      "grad_norm": 11.069299697875977,
      "learning_rate": 5.156362923365588e-06,
      "loss": 2.2368,
      "step": 43
    },
    {
      "epoch": 0.3064867218110579,
      "grad_norm": 13.160449028015137,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.1627,
      "step": 44
    },
    {
      "epoch": 0.3134523291249456,
      "grad_norm": 13.812862396240234,
      "learning_rate": 2.653493525244721e-06,
      "loss": 2.2141,
      "step": 45
    },
    {
      "epoch": 0.32041793643883326,
      "grad_norm": 16.305538177490234,
      "learning_rate": 1.70370868554659e-06,
      "loss": 2.2591,
      "step": 46
    },
    {
      "epoch": 0.32738354375272094,
      "grad_norm": 23.405792236328125,
      "learning_rate": 9.607359798384785e-07,
      "loss": 2.7118,
      "step": 47
    },
    {
      "epoch": 0.3343491510666086,
      "grad_norm": 32.53597640991211,
      "learning_rate": 4.277569313094809e-07,
      "loss": 2.7714,
      "step": 48
    },
    {
      "epoch": 0.3413147583804963,
      "grad_norm": 41.75061798095703,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 2.5721,
      "step": 49
    },
    {
      "epoch": 0.348280365694384,
      "grad_norm": 44.7559814453125,
      "learning_rate": 0.0,
      "loss": 3.4154,
      "step": 50
    },
    {
      "epoch": 0.348280365694384,
      "eval_loss": 2.521301507949829,
      "eval_runtime": 39.8939,
      "eval_samples_per_second": 24.239,
      "eval_steps_per_second": 3.033,
      "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": 5.259156315439104e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}