{
  "best_metric": 0.8221143484115601,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.744186046511628,
  "eval_steps": 50,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 50.48418045043945,
      "learning_rate": 5e-06,
      "loss": 5.7595,
      "step": 1
    },
    {
      "epoch": 0.023255813953488372,
      "eval_loss": 5.616752624511719,
      "eval_runtime": 42.1306,
      "eval_samples_per_second": 3.442,
      "eval_steps_per_second": 0.878,
      "step": 1
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 50.452247619628906,
      "learning_rate": 1e-05,
      "loss": 5.5406,
      "step": 2
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 53.459651947021484,
      "learning_rate": 1.5e-05,
      "loss": 5.4502,
      "step": 3
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 45.73939514160156,
      "learning_rate": 2e-05,
      "loss": 4.5592,
      "step": 4
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 24.405733108520508,
      "learning_rate": 2.5e-05,
      "loss": 3.057,
      "step": 5
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 7.204668998718262,
      "learning_rate": 3e-05,
      "loss": 2.2398,
      "step": 6
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 4.946572780609131,
      "learning_rate": 3.5e-05,
      "loss": 1.9191,
      "step": 7
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 4.044290065765381,
      "learning_rate": 4e-05,
      "loss": 1.634,
      "step": 8
    },
    {
      "epoch": 0.20930232558139536,
      "grad_norm": 2.9764981269836426,
      "learning_rate": 4.5e-05,
      "loss": 1.4995,
      "step": 9
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 2.4178900718688965,
      "learning_rate": 5e-05,
      "loss": 1.1601,
      "step": 10
    },
    {
      "epoch": 0.2558139534883721,
      "grad_norm": 2.078669309616089,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.0951,
      "step": 11
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 1.4749664068222046,
      "learning_rate": 6e-05,
      "loss": 0.9903,
      "step": 12
    },
    {
      "epoch": 0.3023255813953488,
      "grad_norm": 1.5175457000732422,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.008,
      "step": 13
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 1.7559329271316528,
      "learning_rate": 7e-05,
      "loss": 0.9669,
      "step": 14
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 1.3696329593658447,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9701,
      "step": 15
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 1.3774824142456055,
      "learning_rate": 8e-05,
      "loss": 0.8967,
      "step": 16
    },
    {
      "epoch": 0.3953488372093023,
      "grad_norm": 1.3635125160217285,
      "learning_rate": 8.5e-05,
      "loss": 0.891,
      "step": 17
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 1.294816255569458,
      "learning_rate": 9e-05,
      "loss": 0.9375,
      "step": 18
    },
    {
      "epoch": 0.4418604651162791,
      "grad_norm": 1.046218752861023,
      "learning_rate": 9.5e-05,
      "loss": 0.9259,
      "step": 19
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 1.0287326574325562,
      "learning_rate": 0.0001,
      "loss": 0.9037,
      "step": 20
    },
    {
      "epoch": 0.4883720930232558,
      "grad_norm": 1.1668330430984497,
      "learning_rate": 9.991845519630678e-05,
      "loss": 0.9566,
      "step": 21
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 0.9371416568756104,
      "learning_rate": 9.967408676742751e-05,
      "loss": 0.8835,
      "step": 22
    },
    {
      "epoch": 0.5348837209302325,
      "grad_norm": 1.042136311531067,
      "learning_rate": 9.926769179238466e-05,
      "loss": 0.8463,
      "step": 23
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 0.9777133464813232,
      "learning_rate": 9.870059584711668e-05,
      "loss": 0.867,
      "step": 24
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 0.8836668729782104,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.8464,
      "step": 25
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 0.9614817500114441,
      "learning_rate": 9.709221818197624e-05,
      "loss": 0.919,
      "step": 26
    },
    {
      "epoch": 0.627906976744186,
      "grad_norm": 0.9123168587684631,
      "learning_rate": 9.60561826557425e-05,
      "loss": 0.9602,
      "step": 27
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 0.8339196443557739,
      "learning_rate": 9.486992143456792e-05,
      "loss": 0.9228,
      "step": 28
    },
    {
      "epoch": 0.6744186046511628,
      "grad_norm": 0.77012699842453,
      "learning_rate": 9.353730385598887e-05,
      "loss": 0.8319,
      "step": 29
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.8256942629814148,
      "learning_rate": 9.206267664155907e-05,
      "loss": 0.9154,
      "step": 30
    },
    {
      "epoch": 0.7209302325581395,
      "grad_norm": 0.778258740901947,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8017,
      "step": 31
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 0.7635379433631897,
      "learning_rate": 8.870708053195413e-05,
      "loss": 0.8697,
      "step": 32
    },
    {
      "epoch": 0.7674418604651163,
      "grad_norm": 0.8458096981048584,
      "learning_rate": 8.683705689382024e-05,
      "loss": 0.8319,
      "step": 33
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 0.8728878498077393,
      "learning_rate": 8.484687843276469e-05,
      "loss": 0.9108,
      "step": 34
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 0.8373196125030518,
      "learning_rate": 8.274303669726426e-05,
      "loss": 0.8106,
      "step": 35
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 0.7850401997566223,
      "learning_rate": 8.053239398177191e-05,
      "loss": 0.8616,
      "step": 36
    },
    {
      "epoch": 0.8604651162790697,
      "grad_norm": 0.7604936361312866,
      "learning_rate": 7.822216094333847e-05,
      "loss": 0.8385,
      "step": 37
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 0.7320814728736877,
      "learning_rate": 7.58198730819481e-05,
      "loss": 0.8121,
      "step": 38
    },
    {
      "epoch": 0.9069767441860465,
      "grad_norm": 0.7471502423286438,
      "learning_rate": 7.333336616128369e-05,
      "loss": 0.9422,
      "step": 39
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.7802324295043945,
      "learning_rate": 7.077075065009433e-05,
      "loss": 0.8585,
      "step": 40
    },
    {
      "epoch": 0.9534883720930233,
      "grad_norm": 0.7679800391197205,
      "learning_rate": 6.814038526753205e-05,
      "loss": 0.9584,
      "step": 41
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 0.7143554091453552,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8121,
      "step": 42
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8469040989875793,
      "learning_rate": 6.271091670967436e-05,
      "loss": 0.8752,
      "step": 43
    },
    {
      "epoch": 1.0232558139534884,
      "grad_norm": 0.7578158974647522,
      "learning_rate": 5.992952333228728e-05,
      "loss": 0.6256,
      "step": 44
    },
    {
      "epoch": 1.0465116279069768,
      "grad_norm": 0.6882212162017822,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 0.6837,
      "step": 45
    },
    {
      "epoch": 1.069767441860465,
      "grad_norm": 0.6590960621833801,
      "learning_rate": 5.427875042394199e-05,
      "loss": 0.6697,
      "step": 46
    },
    {
      "epoch": 1.0930232558139534,
      "grad_norm": 0.7072633504867554,
      "learning_rate": 5.142780253968481e-05,
      "loss": 0.7084,
      "step": 47
    },
    {
      "epoch": 1.1162790697674418,
      "grad_norm": 0.6782570481300354,
      "learning_rate": 4.85721974603152e-05,
      "loss": 0.6804,
      "step": 48
    },
    {
      "epoch": 1.1395348837209303,
      "grad_norm": 0.7885217070579529,
      "learning_rate": 4.5721249576058027e-05,
      "loss": 0.7327,
      "step": 49
    },
    {
      "epoch": 1.1627906976744187,
      "grad_norm": 0.7307140827178955,
      "learning_rate": 4.288425808633575e-05,
      "loss": 0.686,
      "step": 50
    },
    {
      "epoch": 1.1627906976744187,
      "eval_loss": 0.8221143484115601,
      "eval_runtime": 42.4173,
      "eval_samples_per_second": 3.418,
      "eval_steps_per_second": 0.872,
      "step": 50
    },
    {
      "epoch": 1.1860465116279069,
      "grad_norm": 0.8067054748535156,
      "learning_rate": 4.007047666771274e-05,
      "loss": 0.7265,
      "step": 51
    },
    {
      "epoch": 1.2093023255813953,
      "grad_norm": 0.8744948506355286,
      "learning_rate": 3.728908329032567e-05,
      "loss": 0.6423,
      "step": 52
    },
    {
      "epoch": 1.2325581395348837,
      "grad_norm": 0.7776987552642822,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6799,
      "step": 53
    },
    {
      "epoch": 1.255813953488372,
      "grad_norm": 0.8160903453826904,
      "learning_rate": 3.1859614732467954e-05,
      "loss": 0.695,
      "step": 54
    },
    {
      "epoch": 1.2790697674418605,
      "grad_norm": 0.7703461050987244,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 0.6877,
      "step": 55
    },
    {
      "epoch": 1.302325581395349,
      "grad_norm": 0.8165169358253479,
      "learning_rate": 2.6666633838716314e-05,
      "loss": 0.7457,
      "step": 56
    },
    {
      "epoch": 1.3255813953488373,
      "grad_norm": 0.7522884011268616,
      "learning_rate": 2.418012691805191e-05,
      "loss": 0.655,
      "step": 57
    },
    {
      "epoch": 1.3488372093023255,
      "grad_norm": 0.7273982763290405,
      "learning_rate": 2.1777839056661554e-05,
      "loss": 0.724,
      "step": 58
    },
    {
      "epoch": 1.372093023255814,
      "grad_norm": 0.7481361627578735,
      "learning_rate": 1.946760601822809e-05,
      "loss": 0.7128,
      "step": 59
    },
    {
      "epoch": 1.3953488372093024,
      "grad_norm": 0.7823900580406189,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.6229,
      "step": 60
    },
    {
      "epoch": 1.4186046511627908,
      "grad_norm": 0.7414326071739197,
      "learning_rate": 1.5153121567235335e-05,
      "loss": 0.6519,
      "step": 61
    },
    {
      "epoch": 1.441860465116279,
      "grad_norm": 0.7793033123016357,
      "learning_rate": 1.3162943106179749e-05,
      "loss": 0.642,
      "step": 62
    },
    {
      "epoch": 1.4651162790697674,
      "grad_norm": 0.762286365032196,
      "learning_rate": 1.1292919468045877e-05,
      "loss": 0.6366,
      "step": 63
    },
    {
      "epoch": 1.4883720930232558,
      "grad_norm": 0.6895043253898621,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6346,
      "step": 64
    },
    {
      "epoch": 1.5116279069767442,
      "grad_norm": 0.7879940271377563,
      "learning_rate": 7.937323358440935e-06,
      "loss": 0.7114,
      "step": 65
    },
    {
      "epoch": 1.5348837209302326,
      "grad_norm": 0.7544711828231812,
      "learning_rate": 6.462696144011149e-06,
      "loss": 0.67,
      "step": 66
    },
    {
      "epoch": 1.558139534883721,
      "grad_norm": 0.7758604884147644,
      "learning_rate": 5.13007856543209e-06,
      "loss": 0.6304,
      "step": 67
    },
    {
      "epoch": 1.5813953488372094,
      "grad_norm": 0.8291249871253967,
      "learning_rate": 3.9438173442575e-06,
      "loss": 0.6292,
      "step": 68
    },
    {
      "epoch": 1.6046511627906976,
      "grad_norm": 0.8326449394226074,
      "learning_rate": 2.9077818180237693e-06,
      "loss": 0.6636,
      "step": 69
    },
    {
      "epoch": 1.627906976744186,
      "grad_norm": 0.7169848084449768,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 0.591,
      "step": 70
    },
    {
      "epoch": 1.6511627906976745,
      "grad_norm": 0.7567453384399414,
      "learning_rate": 1.2994041528833266e-06,
      "loss": 0.6059,
      "step": 71
    },
    {
      "epoch": 1.6744186046511627,
      "grad_norm": 0.7726857662200928,
      "learning_rate": 7.323082076153509e-07,
      "loss": 0.6268,
      "step": 72
    },
    {
      "epoch": 1.697674418604651,
      "grad_norm": 0.7845696210861206,
      "learning_rate": 3.2591323257248893e-07,
      "loss": 0.7064,
      "step": 73
    },
    {
      "epoch": 1.7209302325581395,
      "grad_norm": 0.7475423216819763,
      "learning_rate": 8.15448036932176e-08,
      "loss": 0.6419,
      "step": 74
    },
    {
      "epoch": 1.744186046511628,
      "grad_norm": 0.7256861329078674,
      "learning_rate": 0.0,
      "loss": 0.5977,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 5.037258675585024e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}