{
  "best_metric": 0.3283706307411194,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.1498618461106168,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029972369222123355,
      "grad_norm": 7.602510929107666,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 7.3791,
      "step": 1
    },
    {
      "epoch": 0.0029972369222123355,
      "eval_loss": 5.100011348724365,
      "eval_runtime": 0.2905,
      "eval_samples_per_second": 172.095,
      "eval_steps_per_second": 44.745,
      "step": 1
    },
    {
      "epoch": 0.005994473844424671,
      "grad_norm": 5.811465263366699,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 5.2052,
      "step": 2
    },
    {
      "epoch": 0.008991710766637007,
      "grad_norm": 6.1456217765808105,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 5.0327,
      "step": 3
    },
    {
      "epoch": 0.011988947688849342,
      "grad_norm": 5.857211112976074,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 4.9457,
      "step": 4
    },
    {
      "epoch": 0.014986184611061678,
      "grad_norm": 5.512299537658691,
      "learning_rate": 7.5e-05,
      "loss": 4.8063,
      "step": 5
    },
    {
      "epoch": 0.017983421533274015,
      "grad_norm": 5.282471179962158,
      "learning_rate": 8.999999999999999e-05,
      "loss": 4.7355,
      "step": 6
    },
    {
      "epoch": 0.02098065845548635,
      "grad_norm": 4.267989158630371,
      "learning_rate": 0.00010499999999999999,
      "loss": 4.4458,
      "step": 7
    },
    {
      "epoch": 0.023977895377698684,
      "grad_norm": 3.799853801727295,
      "learning_rate": 0.00011999999999999999,
      "loss": 4.2302,
      "step": 8
    },
    {
      "epoch": 0.02697513229991102,
      "grad_norm": 3.506157875061035,
      "learning_rate": 0.000135,
      "loss": 3.857,
      "step": 9
    },
    {
      "epoch": 0.029972369222123357,
      "grad_norm": 3.8407812118530273,
      "learning_rate": 0.00015,
      "loss": 3.749,
      "step": 10
    },
    {
      "epoch": 0.03296960614433569,
      "grad_norm": 4.470568656921387,
      "learning_rate": 0.000165,
      "loss": 3.4078,
      "step": 11
    },
    {
      "epoch": 0.03596684306654803,
      "grad_norm": 4.822042465209961,
      "learning_rate": 0.00017999999999999998,
      "loss": 3.0358,
      "step": 12
    },
    {
      "epoch": 0.038964079988760364,
      "grad_norm": 5.060558795928955,
      "learning_rate": 0.000195,
      "loss": 4.5688,
      "step": 13
    },
    {
      "epoch": 0.0419613169109727,
      "grad_norm": 4.888822078704834,
      "learning_rate": 0.00020999999999999998,
      "loss": 3.6099,
      "step": 14
    },
    {
      "epoch": 0.04495855383318503,
      "grad_norm": 3.4810433387756348,
      "learning_rate": 0.000225,
      "loss": 2.4291,
      "step": 15
    },
    {
      "epoch": 0.04795579075539737,
      "grad_norm": 3.577241897583008,
      "learning_rate": 0.00023999999999999998,
      "loss": 2.1686,
      "step": 16
    },
    {
      "epoch": 0.0509530276776097,
      "grad_norm": 3.595766544342041,
      "learning_rate": 0.00025499999999999996,
      "loss": 1.9973,
      "step": 17
    },
    {
      "epoch": 0.05395026459982204,
      "grad_norm": 4.025913715362549,
      "learning_rate": 0.00027,
      "loss": 1.9723,
      "step": 18
    },
    {
      "epoch": 0.05694750152203437,
      "grad_norm": 2.864335536956787,
      "learning_rate": 0.000285,
      "loss": 1.9312,
      "step": 19
    },
    {
      "epoch": 0.05994473844424671,
      "grad_norm": 3.9801218509674072,
      "learning_rate": 0.0003,
      "loss": 1.8875,
      "step": 20
    },
    {
      "epoch": 0.06294197536645904,
      "grad_norm": 3.2217376232147217,
      "learning_rate": 0.00029999841345404617,
      "loss": 1.5763,
      "step": 21
    },
    {
      "epoch": 0.06593921228867138,
      "grad_norm": 19.193851470947266,
      "learning_rate": 0.0002999936538534755,
      "loss": 1.8067,
      "step": 22
    },
    {
      "epoch": 0.06893644921088371,
      "grad_norm": 25.025583267211914,
      "learning_rate": 0.0002999857213101595,
      "loss": 1.4576,
      "step": 23
    },
    {
      "epoch": 0.07193368613309606,
      "grad_norm": 4.855524063110352,
      "learning_rate": 0.00029997461601054764,
      "loss": 1.0614,
      "step": 24
    },
    {
      "epoch": 0.0749309230553084,
      "grad_norm": 3.3954389095306396,
      "learning_rate": 0.00029996033821566326,
      "loss": 0.8964,
      "step": 25
    },
    {
      "epoch": 0.0749309230553084,
      "eval_loss": 1.0534682273864746,
      "eval_runtime": 0.2881,
      "eval_samples_per_second": 173.557,
      "eval_steps_per_second": 45.125,
      "step": 25
    },
    {
      "epoch": 0.07792815997752073,
      "grad_norm": 12.105545997619629,
      "learning_rate": 0.0002999428882610971,
      "loss": 3.0311,
      "step": 26
    },
    {
      "epoch": 0.08092539689973306,
      "grad_norm": 3.334498882293701,
      "learning_rate": 0.00029992226655699945,
      "loss": 1.2946,
      "step": 27
    },
    {
      "epoch": 0.0839226338219454,
      "grad_norm": 2.8498733043670654,
      "learning_rate": 0.00029989847358807104,
      "loss": 1.1872,
      "step": 28
    },
    {
      "epoch": 0.08691987074415773,
      "grad_norm": 2.367673873901367,
      "learning_rate": 0.0002998715099135508,
      "loss": 1.0292,
      "step": 29
    },
    {
      "epoch": 0.08991710766637007,
      "grad_norm": 8.79304313659668,
      "learning_rate": 0.00029984137616720325,
      "loss": 1.2032,
      "step": 30
    },
    {
      "epoch": 0.0929143445885824,
      "grad_norm": 8.142653465270996,
      "learning_rate": 0.00029980807305730374,
      "loss": 1.2389,
      "step": 31
    },
    {
      "epoch": 0.09591158151079474,
      "grad_norm": 4.5038628578186035,
      "learning_rate": 0.0002997716013666212,
      "loss": 1.0933,
      "step": 32
    },
    {
      "epoch": 0.09890881843300707,
      "grad_norm": 2.439879894256592,
      "learning_rate": 0.0002997319619524003,
      "loss": 0.922,
      "step": 33
    },
    {
      "epoch": 0.1019060553552194,
      "grad_norm": 2.002732992172241,
      "learning_rate": 0.0002996891557463412,
      "loss": 0.8141,
      "step": 34
    },
    {
      "epoch": 0.10490329227743174,
      "grad_norm": 1.9198921918869019,
      "learning_rate": 0.00029964318375457725,
      "loss": 0.5868,
      "step": 35
    },
    {
      "epoch": 0.10790052919964407,
      "grad_norm": 1.1390972137451172,
      "learning_rate": 0.00029959404705765186,
      "loss": 0.4158,
      "step": 36
    },
    {
      "epoch": 0.11089776612185641,
      "grad_norm": 0.9061455130577087,
      "learning_rate": 0.00029954174681049296,
      "loss": 0.3104,
      "step": 37
    },
    {
      "epoch": 0.11389500304406874,
      "grad_norm": 3.6855151653289795,
      "learning_rate": 0.0002994862842423856,
      "loss": 1.3318,
      "step": 38
    },
    {
      "epoch": 0.11689223996628108,
      "grad_norm": 2.992558717727661,
      "learning_rate": 0.00029942766065694333,
      "loss": 1.0331,
      "step": 39
    },
    {
      "epoch": 0.11988947688849343,
      "grad_norm": 2.762493133544922,
      "learning_rate": 0.00029936587743207736,
      "loss": 0.7132,
      "step": 40
    },
    {
      "epoch": 0.12288671381070576,
      "grad_norm": 2.2291383743286133,
      "learning_rate": 0.00029930093601996446,
      "loss": 0.5774,
      "step": 41
    },
    {
      "epoch": 0.12588395073291808,
      "grad_norm": 1.1489959955215454,
      "learning_rate": 0.0002992328379470125,
      "loss": 0.5567,
      "step": 42
    },
    {
      "epoch": 0.12888118765513043,
      "grad_norm": 6.168476104736328,
      "learning_rate": 0.00029916158481382474,
      "loss": 0.6131,
      "step": 43
    },
    {
      "epoch": 0.13187842457734275,
      "grad_norm": 5.408211708068848,
      "learning_rate": 0.0002990871782951623,
      "loss": 0.6638,
      "step": 44
    },
    {
      "epoch": 0.1348756614995551,
      "grad_norm": 1.5306873321533203,
      "learning_rate": 0.0002990096201399045,
      "loss": 0.5488,
      "step": 45
    },
    {
      "epoch": 0.13787289842176742,
      "grad_norm": 1.8623676300048828,
      "learning_rate": 0.00029892891217100817,
      "loss": 0.4659,
      "step": 46
    },
    {
      "epoch": 0.14087013534397977,
      "grad_norm": 1.6640721559524536,
      "learning_rate": 0.0002988450562854644,
      "loss": 0.4368,
      "step": 47
    },
    {
      "epoch": 0.14386737226619212,
      "grad_norm": 0.3559802174568176,
      "learning_rate": 0.0002987580544542541,
      "loss": 0.0507,
      "step": 48
    },
    {
      "epoch": 0.14686460918840444,
      "grad_norm": 0.4540441334247589,
      "learning_rate": 0.0002986679087223018,
      "loss": 0.087,
      "step": 49
    },
    {
      "epoch": 0.1498618461106168,
      "grad_norm": 0.8076233267784119,
      "learning_rate": 0.00029857462120842744,
      "loss": 0.1023,
      "step": 50
    },
    {
      "epoch": 0.1498618461106168,
      "eval_loss": 0.3283706307411194,
      "eval_runtime": 0.2882,
      "eval_samples_per_second": 173.489,
      "eval_steps_per_second": 45.107,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 668,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2.296200128626688e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}