{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03203972926428772,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006407945852857543,
      "grad_norm": NaN,
      "learning_rate": 0.00015,
      "loss": 5953676.0,
      "step": 1
    },
    {
      "epoch": 0.0006407945852857543,
      "eval_loss": NaN,
      "eval_runtime": 1.4895,
      "eval_samples_per_second": 33.568,
      "eval_steps_per_second": 8.728,
      "step": 1
    },
    {
      "epoch": 0.0012815891705715086,
      "grad_norm": NaN,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.001922383755857263,
      "grad_norm": NaN,
      "learning_rate": 0.000299878360437632,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.002563178341143017,
      "grad_norm": NaN,
      "learning_rate": 0.00029951366095324104,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0032039729264287716,
      "grad_norm": NaN,
      "learning_rate": 0.00029890655875994835,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.003844767511714526,
      "grad_norm": NaN,
      "learning_rate": 0.0002980581478969406,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00448556209700028,
      "grad_norm": NaN,
      "learning_rate": 0.00029696995725793764,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.005126356682286034,
      "grad_norm": NaN,
      "learning_rate": 0.00029564394783602234,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.005767151267571789,
      "grad_norm": NaN,
      "learning_rate": 0.0002940825091897988,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.006407945852857543,
      "grad_norm": NaN,
      "learning_rate": 0.00029228845513724634,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.007048740438143298,
      "grad_norm": NaN,
      "learning_rate": 0.00029026501868502873,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.007689535023429052,
      "grad_norm": NaN,
      "learning_rate": 0.0002880158462023983,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.008330329608714807,
      "grad_norm": NaN,
      "learning_rate": 0.0002855449908501917,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.00897112419400056,
      "grad_norm": NaN,
      "learning_rate": 0.00028285690527676035,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.009611918779286315,
      "grad_norm": NaN,
      "learning_rate": 0.000279956433593997,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.010252713364572069,
      "grad_norm": NaN,
      "learning_rate": 0.00027684880264791867,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.010893507949857825,
      "grad_norm": NaN,
      "learning_rate": 0.00027353961259953696,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.011534302535143579,
      "grad_norm": NaN,
      "learning_rate": 0.00027003482683298933,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.012175097120429332,
      "grad_norm": NaN,
      "learning_rate": 0.00026634076120911777,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.012815891705715086,
      "grad_norm": NaN,
      "learning_rate": 0.0002624640726838608,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.01345668629100084,
      "grad_norm": NaN,
      "learning_rate": 0.00025841174731196877,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.014097480876286596,
      "grad_norm": NaN,
      "learning_rate": 0.000254191087657661,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.01473827546157235,
      "grad_norm": NaN,
      "learning_rate": 0.0002498096996349117,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.015379070046858104,
      "grad_norm": NaN,
      "learning_rate": 0.0002452754788010787,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.01601986463214386,
      "grad_norm": NaN,
      "learning_rate": 0.00024059659612857536,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.01601986463214386,
      "eval_loss": NaN,
      "eval_runtime": 1.49,
      "eval_samples_per_second": 33.557,
      "eval_steps_per_second": 8.725,
      "step": 25
    },
    {
      "epoch": 0.016660659217429614,
      "grad_norm": NaN,
      "learning_rate": 0.00023578148328022626,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.017301453802715368,
      "grad_norm": NaN,
      "learning_rate": 0.00023083881741484068,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.01794224838800112,
      "grad_norm": NaN,
      "learning_rate": 0.00022577750555038587,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.018583042973286876,
      "grad_norm": NaN,
      "learning_rate": 0.000220606668512939,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.01922383755857263,
      "grad_norm": NaN,
      "learning_rate": 0.00021533562450034164,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.019864632143858384,
      "grad_norm": NaN,
      "learning_rate": 0.00020997387229017774,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.020505426729144138,
      "grad_norm": NaN,
      "learning_rate": 0.00020453107412233428,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.02114622131442989,
      "grad_norm": NaN,
      "learning_rate": 0.0001990170382869919,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.02178701589971565,
      "grad_norm": NaN,
      "learning_rate": 0.00019344170144942302,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.022427810485001403,
      "grad_norm": NaN,
      "learning_rate": 0.00018781511074344962,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.023068605070287157,
      "grad_norm": NaN,
      "learning_rate": 0.0001821474056658286,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.02370939965557291,
      "grad_norm": NaN,
      "learning_rate": 0.00017644879980419374,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.024350194240858665,
      "grad_norm": NaN,
      "learning_rate": 0.00017072956243148002,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.02499098882614442,
      "grad_norm": NaN,
      "learning_rate": 0.000165,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.025631783411430173,
      "grad_norm": NaN,
      "learning_rate": 0.00015927043756852,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.026272577996715927,
      "grad_norm": NaN,
      "learning_rate": 0.0001535512001958063,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.02691337258200168,
      "grad_norm": NaN,
      "learning_rate": 0.00014785259433417133,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.027554167167287435,
      "grad_norm": NaN,
      "learning_rate": 0.00014218488925655037,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.028194961752573192,
      "grad_norm": NaN,
      "learning_rate": 0.00013655829855057698,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.028835756337858946,
      "grad_norm": NaN,
      "learning_rate": 0.00013098296171300814,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0294765509231447,
      "grad_norm": NaN,
      "learning_rate": 0.0001254689258776657,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.030117345508430454,
      "grad_norm": NaN,
      "learning_rate": 0.00012002612770982222,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.030758140093716208,
      "grad_norm": NaN,
      "learning_rate": 0.00011466437549965834,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.03139893467900196,
      "grad_norm": NaN,
      "learning_rate": 0.00010939333148706099,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.03203972926428772,
      "grad_norm": NaN,
      "learning_rate": 0.00010422249444961407,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.03203972926428772,
      "eval_loss": NaN,
      "eval_runtime": 1.4906,
      "eval_samples_per_second": 33.543,
      "eval_steps_per_second": 8.721,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 76,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.786210897147986e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}