{
  "best_metric": 6.83262300491333,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.003493327744008943,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.986655488017886e-05,
      "grad_norm": 0.395611435174942,
      "learning_rate": 0.0001,
      "loss": 6.9008,
      "step": 1
    },
    {
      "epoch": 6.986655488017886e-05,
      "eval_loss": 6.905076026916504,
      "eval_runtime": 20.8788,
      "eval_samples_per_second": 288.666,
      "eval_steps_per_second": 144.357,
      "step": 1
    },
    {
      "epoch": 0.00013973310976035772,
      "grad_norm": 0.5029837489128113,
      "learning_rate": 0.0002,
      "loss": 6.8782,
      "step": 2
    },
    {
      "epoch": 0.00020959966464053657,
      "grad_norm": 0.5331994295120239,
      "learning_rate": 0.00019978589232386035,
      "loss": 6.9237,
      "step": 3
    },
    {
      "epoch": 0.00027946621952071543,
      "grad_norm": 0.48590007424354553,
      "learning_rate": 0.00019914448613738106,
      "loss": 6.8979,
      "step": 4
    },
    {
      "epoch": 0.0003493327744008943,
      "grad_norm": 0.5032398700714111,
      "learning_rate": 0.00019807852804032305,
      "loss": 6.9011,
      "step": 5
    },
    {
      "epoch": 0.00041919932928107315,
      "grad_norm": 0.41302594542503357,
      "learning_rate": 0.00019659258262890683,
      "loss": 6.8937,
      "step": 6
    },
    {
      "epoch": 0.000489065884161252,
      "grad_norm": 0.4476993978023529,
      "learning_rate": 0.0001946930129495106,
      "loss": 6.9063,
      "step": 7
    },
    {
      "epoch": 0.0005589324390414309,
      "grad_norm": 0.4608771502971649,
      "learning_rate": 0.0001923879532511287,
      "loss": 6.8993,
      "step": 8
    },
    {
      "epoch": 0.0006287989939216097,
      "grad_norm": 0.4379900097846985,
      "learning_rate": 0.00018968727415326884,
      "loss": 6.898,
      "step": 9
    },
    {
      "epoch": 0.0006986655488017886,
      "grad_norm": 0.4840511977672577,
      "learning_rate": 0.00018660254037844388,
      "loss": 6.8798,
      "step": 10
    },
    {
      "epoch": 0.0007685321036819675,
      "grad_norm": 0.5115653872489929,
      "learning_rate": 0.00018314696123025454,
      "loss": 6.8621,
      "step": 11
    },
    {
      "epoch": 0.0008383986585621463,
      "grad_norm": 0.444229394197464,
      "learning_rate": 0.00017933533402912354,
      "loss": 6.9023,
      "step": 12
    },
    {
      "epoch": 0.0009082652134423251,
      "grad_norm": 0.45873820781707764,
      "learning_rate": 0.00017518398074789775,
      "loss": 6.8931,
      "step": 13
    },
    {
      "epoch": 0.000978131768322504,
      "grad_norm": 0.39180684089660645,
      "learning_rate": 0.00017071067811865476,
      "loss": 6.8851,
      "step": 14
    },
    {
      "epoch": 0.0010479983232026828,
      "grad_norm": 0.4363069236278534,
      "learning_rate": 0.00016593458151000688,
      "loss": 6.8823,
      "step": 15
    },
    {
      "epoch": 0.0011178648780828617,
      "grad_norm": 0.5417330861091614,
      "learning_rate": 0.00016087614290087208,
      "loss": 6.8601,
      "step": 16
    },
    {
      "epoch": 0.0011877314329630407,
      "grad_norm": 0.39207905530929565,
      "learning_rate": 0.00015555702330196023,
      "loss": 6.8779,
      "step": 17
    },
    {
      "epoch": 0.0012575979878432194,
      "grad_norm": 0.4979099929332733,
      "learning_rate": 0.00015000000000000001,
      "loss": 6.8537,
      "step": 18
    },
    {
      "epoch": 0.0013274645427233983,
      "grad_norm": 0.45185598731040955,
      "learning_rate": 0.00014422886902190014,
      "loss": 6.8755,
      "step": 19
    },
    {
      "epoch": 0.0013973310976035773,
      "grad_norm": 0.3816322982311249,
      "learning_rate": 0.000138268343236509,
      "loss": 6.8769,
      "step": 20
    },
    {
      "epoch": 0.001467197652483756,
      "grad_norm": 0.4933607578277588,
      "learning_rate": 0.00013214394653031616,
      "loss": 6.8645,
      "step": 21
    },
    {
      "epoch": 0.001537064207363935,
      "grad_norm": 0.4466155767440796,
      "learning_rate": 0.00012588190451025207,
      "loss": 6.8549,
      "step": 22
    },
    {
      "epoch": 0.0016069307622441137,
      "grad_norm": 0.42802491784095764,
      "learning_rate": 0.00011950903220161285,
      "loss": 6.855,
      "step": 23
    },
    {
      "epoch": 0.0016767973171242926,
      "grad_norm": 0.5487078428268433,
      "learning_rate": 0.00011305261922200519,
      "loss": 6.8383,
      "step": 24
    },
    {
      "epoch": 0.0017466638720044715,
      "grad_norm": 0.4641954302787781,
      "learning_rate": 0.00010654031292301432,
      "loss": 6.8455,
      "step": 25
    },
    {
      "epoch": 0.0017466638720044715,
      "eval_loss": 6.848521709442139,
      "eval_runtime": 20.4444,
      "eval_samples_per_second": 294.8,
      "eval_steps_per_second": 147.424,
      "step": 25
    },
    {
      "epoch": 0.0018165304268846503,
      "grad_norm": 0.4626302123069763,
      "learning_rate": 0.0001,
      "loss": 6.8368,
      "step": 26
    },
    {
      "epoch": 0.0018863969817648292,
      "grad_norm": 0.46538764238357544,
      "learning_rate": 9.345968707698569e-05,
      "loss": 6.8595,
      "step": 27
    },
    {
      "epoch": 0.001956263536645008,
      "grad_norm": 0.5668134093284607,
      "learning_rate": 8.694738077799488e-05,
      "loss": 6.8305,
      "step": 28
    },
    {
      "epoch": 0.002026130091525187,
      "grad_norm": 0.4846513867378235,
      "learning_rate": 8.049096779838719e-05,
      "loss": 6.8458,
      "step": 29
    },
    {
      "epoch": 0.0020959966464053656,
      "grad_norm": 0.5467333197593689,
      "learning_rate": 7.411809548974792e-05,
      "loss": 6.8318,
      "step": 30
    },
    {
      "epoch": 0.0021658632012855447,
      "grad_norm": 0.540037214756012,
      "learning_rate": 6.785605346968386e-05,
      "loss": 6.8427,
      "step": 31
    },
    {
      "epoch": 0.0022357297561657235,
      "grad_norm": 0.49980029463768005,
      "learning_rate": 6.173165676349103e-05,
      "loss": 6.8372,
      "step": 32
    },
    {
      "epoch": 0.002305596311045902,
      "grad_norm": 0.467425674200058,
      "learning_rate": 5.577113097809989e-05,
      "loss": 6.8629,
      "step": 33
    },
    {
      "epoch": 0.0023754628659260813,
      "grad_norm": 0.48374143242836,
      "learning_rate": 5.000000000000002e-05,
      "loss": 6.8463,
      "step": 34
    },
    {
      "epoch": 0.00244532942080626,
      "grad_norm": 0.4555916488170624,
      "learning_rate": 4.444297669803981e-05,
      "loss": 6.8526,
      "step": 35
    },
    {
      "epoch": 0.0025151959756864388,
      "grad_norm": 0.5127541422843933,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 6.8357,
      "step": 36
    },
    {
      "epoch": 0.002585062530566618,
      "grad_norm": 0.44566676020622253,
      "learning_rate": 3.406541848999312e-05,
      "loss": 6.8396,
      "step": 37
    },
    {
      "epoch": 0.0026549290854467967,
      "grad_norm": 0.4989950358867645,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 6.8291,
      "step": 38
    },
    {
      "epoch": 0.0027247956403269754,
      "grad_norm": 0.4991087019443512,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 6.8387,
      "step": 39
    },
    {
      "epoch": 0.0027946621952071545,
      "grad_norm": 0.5077288150787354,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 6.8349,
      "step": 40
    },
    {
      "epoch": 0.0028645287500873333,
      "grad_norm": 0.4772498905658722,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 6.8435,
      "step": 41
    },
    {
      "epoch": 0.002934395304967512,
      "grad_norm": 0.4704778492450714,
      "learning_rate": 1.339745962155613e-05,
      "loss": 6.8389,
      "step": 42
    },
    {
      "epoch": 0.0030042618598476907,
      "grad_norm": 0.47462359070777893,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 6.8362,
      "step": 43
    },
    {
      "epoch": 0.00307412841472787,
      "grad_norm": 0.42201927304267883,
      "learning_rate": 7.612046748871327e-06,
      "loss": 6.8744,
      "step": 44
    },
    {
      "epoch": 0.0031439949696080486,
      "grad_norm": 0.4583438038825989,
      "learning_rate": 5.306987050489442e-06,
      "loss": 6.8459,
      "step": 45
    },
    {
      "epoch": 0.0032138615244882273,
      "grad_norm": 0.40070590376853943,
      "learning_rate": 3.40741737109318e-06,
      "loss": 6.8537,
      "step": 46
    },
    {
      "epoch": 0.0032837280793684065,
      "grad_norm": 0.4594520628452301,
      "learning_rate": 1.921471959676957e-06,
      "loss": 6.8449,
      "step": 47
    },
    {
      "epoch": 0.003353594634248585,
      "grad_norm": 0.5334432125091553,
      "learning_rate": 8.555138626189618e-07,
      "loss": 6.8251,
      "step": 48
    },
    {
      "epoch": 0.003423461189128764,
      "grad_norm": 0.5096091628074646,
      "learning_rate": 2.141076761396521e-07,
      "loss": 6.8198,
      "step": 49
    },
    {
      "epoch": 0.003493327744008943,
      "grad_norm": 0.566801130771637,
      "learning_rate": 0.0,
      "loss": 6.8349,
      "step": 50
    },
    {
      "epoch": 0.003493327744008943,
      "eval_loss": 6.83262300491333,
      "eval_runtime": 20.4848,
      "eval_samples_per_second": 294.218,
      "eval_steps_per_second": 147.134,
      "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": 589302988800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}