{
  "best_metric": 2.272261142730713,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.003957104981995172,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.914209963990345e-05,
      "grad_norm": 0.47334396839141846,
      "learning_rate": 0.0001,
      "loss": 2.6318,
      "step": 1
    },
    {
      "epoch": 7.914209963990345e-05,
      "eval_loss": 2.629798650741577,
      "eval_runtime": 1442.4242,
      "eval_samples_per_second": 3.689,
      "eval_steps_per_second": 1.845,
      "step": 1
    },
    {
      "epoch": 0.0001582841992798069,
      "grad_norm": 1.077744483947754,
      "learning_rate": 0.0002,
      "loss": 2.456,
      "step": 2
    },
    {
      "epoch": 0.00023742629891971033,
      "grad_norm": 0.476300984621048,
      "learning_rate": 0.00019978589232386035,
      "loss": 2.3186,
      "step": 3
    },
    {
      "epoch": 0.0003165683985596138,
      "grad_norm": 0.6186921000480652,
      "learning_rate": 0.00019914448613738106,
      "loss": 2.2567,
      "step": 4
    },
    {
      "epoch": 0.00039571049819951725,
      "grad_norm": 0.5011530518531799,
      "learning_rate": 0.00019807852804032305,
      "loss": 2.4795,
      "step": 5
    },
    {
      "epoch": 0.00047485259783942065,
      "grad_norm": 0.3476628065109253,
      "learning_rate": 0.00019659258262890683,
      "loss": 2.3858,
      "step": 6
    },
    {
      "epoch": 0.0005539946974793241,
      "grad_norm": 0.4523206353187561,
      "learning_rate": 0.0001946930129495106,
      "loss": 2.3486,
      "step": 7
    },
    {
      "epoch": 0.0006331367971192276,
      "grad_norm": 0.2827935516834259,
      "learning_rate": 0.0001923879532511287,
      "loss": 2.3498,
      "step": 8
    },
    {
      "epoch": 0.000712278896759131,
      "grad_norm": 0.33790653944015503,
      "learning_rate": 0.00018968727415326884,
      "loss": 2.2515,
      "step": 9
    },
    {
      "epoch": 0.0007914209963990345,
      "grad_norm": 0.19474512338638306,
      "learning_rate": 0.00018660254037844388,
      "loss": 2.4869,
      "step": 10
    },
    {
      "epoch": 0.000870563096038938,
      "grad_norm": 0.3997777998447418,
      "learning_rate": 0.00018314696123025454,
      "loss": 2.2487,
      "step": 11
    },
    {
      "epoch": 0.0009497051956788413,
      "grad_norm": 0.21606910228729248,
      "learning_rate": 0.00017933533402912354,
      "loss": 2.2909,
      "step": 12
    },
    {
      "epoch": 0.0010288472953187448,
      "grad_norm": 0.22740228474140167,
      "learning_rate": 0.00017518398074789775,
      "loss": 2.3088,
      "step": 13
    },
    {
      "epoch": 0.0011079893949586482,
      "grad_norm": 0.23181860148906708,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.3148,
      "step": 14
    },
    {
      "epoch": 0.0011871314945985517,
      "grad_norm": 0.26544469594955444,
      "learning_rate": 0.00016593458151000688,
      "loss": 2.1442,
      "step": 15
    },
    {
      "epoch": 0.0012662735942384552,
      "grad_norm": 0.22167958319187164,
      "learning_rate": 0.00016087614290087208,
      "loss": 2.238,
      "step": 16
    },
    {
      "epoch": 0.0013454156938783586,
      "grad_norm": 0.33192533254623413,
      "learning_rate": 0.00015555702330196023,
      "loss": 2.4143,
      "step": 17
    },
    {
      "epoch": 0.001424557793518262,
      "grad_norm": 0.2848586440086365,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.0197,
      "step": 18
    },
    {
      "epoch": 0.0015036998931581655,
      "grad_norm": 0.40165361762046814,
      "learning_rate": 0.00014422886902190014,
      "loss": 2.2847,
      "step": 19
    },
    {
      "epoch": 0.001582841992798069,
      "grad_norm": 0.23846222460269928,
      "learning_rate": 0.000138268343236509,
      "loss": 2.1219,
      "step": 20
    },
    {
      "epoch": 0.0016619840924379725,
      "grad_norm": 0.22336062788963318,
      "learning_rate": 0.00013214394653031616,
      "loss": 2.1434,
      "step": 21
    },
    {
      "epoch": 0.001741126192077876,
      "grad_norm": 0.3259464502334595,
      "learning_rate": 0.00012588190451025207,
      "loss": 2.2742,
      "step": 22
    },
    {
      "epoch": 0.0018202682917177794,
      "grad_norm": 0.25928550958633423,
      "learning_rate": 0.00011950903220161285,
      "loss": 2.2165,
      "step": 23
    },
    {
      "epoch": 0.0018994103913576826,
      "grad_norm": 0.31144559383392334,
      "learning_rate": 0.00011305261922200519,
      "loss": 2.3496,
      "step": 24
    },
    {
      "epoch": 0.001978552490997586,
      "grad_norm": 0.33175715804100037,
      "learning_rate": 0.00010654031292301432,
      "loss": 2.3415,
      "step": 25
    },
    {
      "epoch": 0.001978552490997586,
      "eval_loss": 2.2873783111572266,
      "eval_runtime": 1449.5978,
      "eval_samples_per_second": 3.671,
      "eval_steps_per_second": 1.836,
      "step": 25
    },
    {
      "epoch": 0.0020576945906374895,
      "grad_norm": 0.42730939388275146,
      "learning_rate": 0.0001,
      "loss": 2.0884,
      "step": 26
    },
    {
      "epoch": 0.002136836690277393,
      "grad_norm": 0.9263526797294617,
      "learning_rate": 9.345968707698569e-05,
      "loss": 2.3938,
      "step": 27
    },
    {
      "epoch": 0.0022159787899172965,
      "grad_norm": 0.3488403856754303,
      "learning_rate": 8.694738077799488e-05,
      "loss": 2.3595,
      "step": 28
    },
    {
      "epoch": 0.0022951208895572,
      "grad_norm": 0.37862449884414673,
      "learning_rate": 8.049096779838719e-05,
      "loss": 2.1439,
      "step": 29
    },
    {
      "epoch": 0.0023742629891971034,
      "grad_norm": 0.3307685852050781,
      "learning_rate": 7.411809548974792e-05,
      "loss": 2.2033,
      "step": 30
    },
    {
      "epoch": 0.002453405088837007,
      "grad_norm": 0.3769107162952423,
      "learning_rate": 6.785605346968386e-05,
      "loss": 2.4333,
      "step": 31
    },
    {
      "epoch": 0.0025325471884769103,
      "grad_norm": 0.38113144040107727,
      "learning_rate": 6.173165676349103e-05,
      "loss": 2.1927,
      "step": 32
    },
    {
      "epoch": 0.0026116892881168138,
      "grad_norm": 0.33478325605392456,
      "learning_rate": 5.577113097809989e-05,
      "loss": 2.3015,
      "step": 33
    },
    {
      "epoch": 0.0026908313877567172,
      "grad_norm": 0.29439330101013184,
      "learning_rate": 5.000000000000002e-05,
      "loss": 2.2517,
      "step": 34
    },
    {
      "epoch": 0.0027699734873966207,
      "grad_norm": 0.3198701739311218,
      "learning_rate": 4.444297669803981e-05,
      "loss": 2.3491,
      "step": 35
    },
    {
      "epoch": 0.002849115587036524,
      "grad_norm": 0.4098028838634491,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 2.4146,
      "step": 36
    },
    {
      "epoch": 0.0029282576866764276,
      "grad_norm": 0.39363518357276917,
      "learning_rate": 3.406541848999312e-05,
      "loss": 2.4595,
      "step": 37
    },
    {
      "epoch": 0.003007399786316331,
      "grad_norm": 0.37463560700416565,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 2.4214,
      "step": 38
    },
    {
      "epoch": 0.0030865418859562345,
      "grad_norm": 0.35873377323150635,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 2.2987,
      "step": 39
    },
    {
      "epoch": 0.003165683985596138,
      "grad_norm": 0.35473981499671936,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 2.3872,
      "step": 40
    },
    {
      "epoch": 0.0032448260852360414,
      "grad_norm": 0.38532593846321106,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 2.2592,
      "step": 41
    },
    {
      "epoch": 0.003323968184875945,
      "grad_norm": 0.4655337333679199,
      "learning_rate": 1.339745962155613e-05,
      "loss": 2.4574,
      "step": 42
    },
    {
      "epoch": 0.0034031102845158484,
      "grad_norm": 0.4277578294277191,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 2.3818,
      "step": 43
    },
    {
      "epoch": 0.003482252384155752,
      "grad_norm": 0.5126660466194153,
      "learning_rate": 7.612046748871327e-06,
      "loss": 2.4937,
      "step": 44
    },
    {
      "epoch": 0.0035613944837956553,
      "grad_norm": 0.47781333327293396,
      "learning_rate": 5.306987050489442e-06,
      "loss": 2.5162,
      "step": 45
    },
    {
      "epoch": 0.0036405365834355588,
      "grad_norm": 0.525256335735321,
      "learning_rate": 3.40741737109318e-06,
      "loss": 2.275,
      "step": 46
    },
    {
      "epoch": 0.0037196786830754618,
      "grad_norm": 0.6399112939834595,
      "learning_rate": 1.921471959676957e-06,
      "loss": 2.5581,
      "step": 47
    },
    {
      "epoch": 0.0037988207827153652,
      "grad_norm": 0.5539636015892029,
      "learning_rate": 8.555138626189618e-07,
      "loss": 2.5673,
      "step": 48
    },
    {
      "epoch": 0.0038779628823552687,
      "grad_norm": 0.6108574271202087,
      "learning_rate": 2.141076761396521e-07,
      "loss": 2.4309,
      "step": 49
    },
    {
      "epoch": 0.003957104981995172,
      "grad_norm": 0.9037721753120422,
      "learning_rate": 0.0,
      "loss": 2.5523,
      "step": 50
    },
    {
      "epoch": 0.003957104981995172,
      "eval_loss": 2.272261142730713,
      "eval_runtime": 1449.1424,
      "eval_samples_per_second": 3.672,
      "eval_steps_per_second": 1.836,
      "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": 6.59230637948928e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}