{
  "best_metric": 3.1727869510650635,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.007667535654040792,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015335071308081582,
      "grad_norm": 0.7997976541519165,
      "learning_rate": 0.0001,
      "loss": 3.1127,
      "step": 1
    },
    {
      "epoch": 0.00015335071308081582,
      "eval_loss": 5.525876998901367,
      "eval_runtime": 557.5914,
      "eval_samples_per_second": 4.925,
      "eval_steps_per_second": 2.462,
      "step": 1
    },
    {
      "epoch": 0.00030670142616163164,
      "grad_norm": 1.1707472801208496,
      "learning_rate": 0.0002,
      "loss": 3.2453,
      "step": 2
    },
    {
      "epoch": 0.00046005213924244745,
      "grad_norm": 1.3338841199874878,
      "learning_rate": 0.00019978589232386035,
      "loss": 3.732,
      "step": 3
    },
    {
      "epoch": 0.0006134028523232633,
      "grad_norm": 1.7665603160858154,
      "learning_rate": 0.00019914448613738106,
      "loss": 3.6919,
      "step": 4
    },
    {
      "epoch": 0.0007667535654040791,
      "grad_norm": 1.6085811853408813,
      "learning_rate": 0.00019807852804032305,
      "loss": 3.2734,
      "step": 5
    },
    {
      "epoch": 0.0009201042784848949,
      "grad_norm": 1.7934327125549316,
      "learning_rate": 0.00019659258262890683,
      "loss": 3.8984,
      "step": 6
    },
    {
      "epoch": 0.0010734549915657108,
      "grad_norm": 1.9547220468521118,
      "learning_rate": 0.0001946930129495106,
      "loss": 3.6314,
      "step": 7
    },
    {
      "epoch": 0.0012268057046465265,
      "grad_norm": 1.9883716106414795,
      "learning_rate": 0.0001923879532511287,
      "loss": 3.3708,
      "step": 8
    },
    {
      "epoch": 0.0013801564177273425,
      "grad_norm": 1.9317203760147095,
      "learning_rate": 0.00018968727415326884,
      "loss": 3.7997,
      "step": 9
    },
    {
      "epoch": 0.0015335071308081583,
      "grad_norm": 2.4271035194396973,
      "learning_rate": 0.00018660254037844388,
      "loss": 3.2367,
      "step": 10
    },
    {
      "epoch": 0.001686857843888974,
      "grad_norm": 2.3820462226867676,
      "learning_rate": 0.00018314696123025454,
      "loss": 3.3188,
      "step": 11
    },
    {
      "epoch": 0.0018402085569697898,
      "grad_norm": 2.1267054080963135,
      "learning_rate": 0.00017933533402912354,
      "loss": 3.3126,
      "step": 12
    },
    {
      "epoch": 0.001993559270050606,
      "grad_norm": 2.168290853500366,
      "learning_rate": 0.00017518398074789775,
      "loss": 3.6043,
      "step": 13
    },
    {
      "epoch": 0.0021469099831314216,
      "grad_norm": 1.9459383487701416,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.135,
      "step": 14
    },
    {
      "epoch": 0.0023002606962122373,
      "grad_norm": 2.097008466720581,
      "learning_rate": 0.00016593458151000688,
      "loss": 3.4381,
      "step": 15
    },
    {
      "epoch": 0.002453611409293053,
      "grad_norm": 2.320244073867798,
      "learning_rate": 0.00016087614290087208,
      "loss": 3.5288,
      "step": 16
    },
    {
      "epoch": 0.002606962122373869,
      "grad_norm": 2.2773730754852295,
      "learning_rate": 0.00015555702330196023,
      "loss": 3.2589,
      "step": 17
    },
    {
      "epoch": 0.002760312835454685,
      "grad_norm": 2.7196455001831055,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.3563,
      "step": 18
    },
    {
      "epoch": 0.002913663548535501,
      "grad_norm": 2.3228931427001953,
      "learning_rate": 0.00014422886902190014,
      "loss": 3.2545,
      "step": 19
    },
    {
      "epoch": 0.0030670142616163166,
      "grad_norm": 2.5198240280151367,
      "learning_rate": 0.000138268343236509,
      "loss": 3.2305,
      "step": 20
    },
    {
      "epoch": 0.0032203649746971323,
      "grad_norm": 2.7375056743621826,
      "learning_rate": 0.00013214394653031616,
      "loss": 2.8752,
      "step": 21
    },
    {
      "epoch": 0.003373715687777948,
      "grad_norm": 3.36525821685791,
      "learning_rate": 0.00012588190451025207,
      "loss": 3.6056,
      "step": 22
    },
    {
      "epoch": 0.003527066400858764,
      "grad_norm": 2.757669448852539,
      "learning_rate": 0.00011950903220161285,
      "loss": 3.0775,
      "step": 23
    },
    {
      "epoch": 0.0036804171139395796,
      "grad_norm": 2.888826370239258,
      "learning_rate": 0.00011305261922200519,
      "loss": 3.2092,
      "step": 24
    },
    {
      "epoch": 0.003833767827020396,
      "grad_norm": 2.731863498687744,
      "learning_rate": 0.00010654031292301432,
      "loss": 3.0959,
      "step": 25
    },
    {
      "epoch": 0.003833767827020396,
      "eval_loss": 3.2420172691345215,
      "eval_runtime": 563.2148,
      "eval_samples_per_second": 4.876,
      "eval_steps_per_second": 2.438,
      "step": 25
    },
    {
      "epoch": 0.003987118540101212,
      "grad_norm": 2.5246529579162598,
      "learning_rate": 0.0001,
      "loss": 3.4743,
      "step": 26
    },
    {
      "epoch": 0.004140469253182027,
      "grad_norm": 2.2808432579040527,
      "learning_rate": 9.345968707698569e-05,
      "loss": 2.5311,
      "step": 27
    },
    {
      "epoch": 0.004293819966262843,
      "grad_norm": 3.2546892166137695,
      "learning_rate": 8.694738077799488e-05,
      "loss": 2.9244,
      "step": 28
    },
    {
      "epoch": 0.004447170679343659,
      "grad_norm": 3.6420068740844727,
      "learning_rate": 8.049096779838719e-05,
      "loss": 3.8467,
      "step": 29
    },
    {
      "epoch": 0.004600521392424475,
      "grad_norm": 3.000694990158081,
      "learning_rate": 7.411809548974792e-05,
      "loss": 3.6467,
      "step": 30
    },
    {
      "epoch": 0.00475387210550529,
      "grad_norm": 3.8289284706115723,
      "learning_rate": 6.785605346968386e-05,
      "loss": 3.0787,
      "step": 31
    },
    {
      "epoch": 0.004907222818586106,
      "grad_norm": 2.4866862297058105,
      "learning_rate": 6.173165676349103e-05,
      "loss": 3.0888,
      "step": 32
    },
    {
      "epoch": 0.005060573531666922,
      "grad_norm": 4.410055160522461,
      "learning_rate": 5.577113097809989e-05,
      "loss": 2.6185,
      "step": 33
    },
    {
      "epoch": 0.005213924244747738,
      "grad_norm": 3.6001877784729004,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.1256,
      "step": 34
    },
    {
      "epoch": 0.005367274957828554,
      "grad_norm": 2.8873212337493896,
      "learning_rate": 4.444297669803981e-05,
      "loss": 2.9412,
      "step": 35
    },
    {
      "epoch": 0.00552062567090937,
      "grad_norm": 2.546860456466675,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 2.6947,
      "step": 36
    },
    {
      "epoch": 0.005673976383990186,
      "grad_norm": 3.3024210929870605,
      "learning_rate": 3.406541848999312e-05,
      "loss": 2.747,
      "step": 37
    },
    {
      "epoch": 0.005827327097071002,
      "grad_norm": 2.899991512298584,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 2.6494,
      "step": 38
    },
    {
      "epoch": 0.005980677810151817,
      "grad_norm": 2.936243772506714,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 2.5826,
      "step": 39
    },
    {
      "epoch": 0.006134028523232633,
      "grad_norm": 4.207485675811768,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 3.1752,
      "step": 40
    },
    {
      "epoch": 0.006287379236313449,
      "grad_norm": 3.71284556388855,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 3.7207,
      "step": 41
    },
    {
      "epoch": 0.006440729949394265,
      "grad_norm": 4.887681007385254,
      "learning_rate": 1.339745962155613e-05,
      "loss": 3.5925,
      "step": 42
    },
    {
      "epoch": 0.00659408066247508,
      "grad_norm": 4.211059093475342,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 2.6441,
      "step": 43
    },
    {
      "epoch": 0.006747431375555896,
      "grad_norm": 7.138034820556641,
      "learning_rate": 7.612046748871327e-06,
      "loss": 3.9675,
      "step": 44
    },
    {
      "epoch": 0.006900782088636712,
      "grad_norm": 5.270826816558838,
      "learning_rate": 5.306987050489442e-06,
      "loss": 2.8757,
      "step": 45
    },
    {
      "epoch": 0.007054132801717528,
      "grad_norm": 4.441748142242432,
      "learning_rate": 3.40741737109318e-06,
      "loss": 2.7692,
      "step": 46
    },
    {
      "epoch": 0.0072074835147983435,
      "grad_norm": 4.473811149597168,
      "learning_rate": 1.921471959676957e-06,
      "loss": 2.4088,
      "step": 47
    },
    {
      "epoch": 0.007360834227879159,
      "grad_norm": 4.914578914642334,
      "learning_rate": 8.555138626189618e-07,
      "loss": 2.8022,
      "step": 48
    },
    {
      "epoch": 0.007514184940959976,
      "grad_norm": 6.2961812019348145,
      "learning_rate": 2.141076761396521e-07,
      "loss": 3.0815,
      "step": 49
    },
    {
      "epoch": 0.007667535654040792,
      "grad_norm": 7.806097030639648,
      "learning_rate": 0.0,
      "loss": 2.7287,
      "step": 50
    },
    {
      "epoch": 0.007667535654040792,
      "eval_loss": 3.1727869510650635,
      "eval_runtime": 563.243,
      "eval_samples_per_second": 4.875,
      "eval_steps_per_second": 2.438,
      "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": 2.75713949171712e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}