{
  "best_metric": 0.06993943452835083,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.001703780689349667,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.407561378699334e-05,
      "grad_norm": 1.6369861364364624,
      "learning_rate": 0.0001,
      "loss": 1.7556,
      "step": 1
    },
    {
      "epoch": 3.407561378699334e-05,
      "eval_loss": 5.654007911682129,
      "eval_runtime": 7807.1075,
      "eval_samples_per_second": 1.583,
      "eval_steps_per_second": 0.791,
      "step": 1
    },
    {
      "epoch": 6.815122757398668e-05,
      "grad_norm": 1.4532502889633179,
      "learning_rate": 0.0002,
      "loss": 1.6844,
      "step": 2
    },
    {
      "epoch": 0.00010222684136098001,
      "grad_norm": 1.8847758769989014,
      "learning_rate": 0.00019978589232386035,
      "loss": 2.1247,
      "step": 3
    },
    {
      "epoch": 0.00013630245514797336,
      "grad_norm": 3.8411290645599365,
      "learning_rate": 0.00019914448613738106,
      "loss": 3.575,
      "step": 4
    },
    {
      "epoch": 0.0001703780689349667,
      "grad_norm": 1.9456192255020142,
      "learning_rate": 0.00019807852804032305,
      "loss": 1.2,
      "step": 5
    },
    {
      "epoch": 0.00020445368272196002,
      "grad_norm": 1.49202299118042,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.5976,
      "step": 6
    },
    {
      "epoch": 0.00023852929650895337,
      "grad_norm": 2.527500629425049,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.8912,
      "step": 7
    },
    {
      "epoch": 0.0002726049102959467,
      "grad_norm": 3.4990198612213135,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.8749,
      "step": 8
    },
    {
      "epoch": 0.00030668052408294006,
      "grad_norm": 3.130840539932251,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.6576,
      "step": 9
    },
    {
      "epoch": 0.0003407561378699334,
      "grad_norm": 3.1934773921966553,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.5628,
      "step": 10
    },
    {
      "epoch": 0.0003748317516569267,
      "grad_norm": 2.6294682025909424,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.5822,
      "step": 11
    },
    {
      "epoch": 0.00040890736544392005,
      "grad_norm": 3.5073511600494385,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.4442,
      "step": 12
    },
    {
      "epoch": 0.0004429829792309134,
      "grad_norm": 2.53167724609375,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.3845,
      "step": 13
    },
    {
      "epoch": 0.00047705859301790674,
      "grad_norm": 1.1952067613601685,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.096,
      "step": 14
    },
    {
      "epoch": 0.0005111342068049,
      "grad_norm": 5.002864360809326,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.5768,
      "step": 15
    },
    {
      "epoch": 0.0005452098205918934,
      "grad_norm": 3.0290756225585938,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.3725,
      "step": 16
    },
    {
      "epoch": 0.0005792854343788867,
      "grad_norm": 4.021387100219727,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.4057,
      "step": 17
    },
    {
      "epoch": 0.0006133610481658801,
      "grad_norm": 2.2241063117980957,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.1806,
      "step": 18
    },
    {
      "epoch": 0.0006474366619528734,
      "grad_norm": 1.8962585926055908,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.2396,
      "step": 19
    },
    {
      "epoch": 0.0006815122757398668,
      "grad_norm": 4.102702617645264,
      "learning_rate": 0.000138268343236509,
      "loss": 0.2474,
      "step": 20
    },
    {
      "epoch": 0.0007155878895268601,
      "grad_norm": 1.74402916431427,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.0672,
      "step": 21
    },
    {
      "epoch": 0.0007496635033138534,
      "grad_norm": 1.6142075061798096,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.2294,
      "step": 22
    },
    {
      "epoch": 0.0007837391171008468,
      "grad_norm": 3.392238140106201,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.1841,
      "step": 23
    },
    {
      "epoch": 0.0008178147308878401,
      "grad_norm": 2.080667495727539,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.1486,
      "step": 24
    },
    {
      "epoch": 0.0008518903446748335,
      "grad_norm": 2.0367722511291504,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.1569,
      "step": 25
    },
    {
      "epoch": 0.0008518903446748335,
      "eval_loss": 0.17134732007980347,
      "eval_runtime": 7844.2616,
      "eval_samples_per_second": 1.575,
      "eval_steps_per_second": 0.788,
      "step": 25
    },
    {
      "epoch": 0.0008859659584618268,
      "grad_norm": 0.8896116018295288,
      "learning_rate": 0.0001,
      "loss": 0.0399,
      "step": 26
    },
    {
      "epoch": 0.0009200415722488202,
      "grad_norm": 1.7912120819091797,
      "learning_rate": 9.345968707698569e-05,
      "loss": 0.1075,
      "step": 27
    },
    {
      "epoch": 0.0009541171860358135,
      "grad_norm": 2.0380702018737793,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.1464,
      "step": 28
    },
    {
      "epoch": 0.0009881927998228069,
      "grad_norm": 2.9125843048095703,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.1015,
      "step": 29
    },
    {
      "epoch": 0.0010222684136098,
      "grad_norm": 1.1429842710494995,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.0189,
      "step": 30
    },
    {
      "epoch": 0.0010563440273967935,
      "grad_norm": 2.3157050609588623,
      "learning_rate": 6.785605346968386e-05,
      "loss": 0.0953,
      "step": 31
    },
    {
      "epoch": 0.0010904196411837869,
      "grad_norm": 3.368072509765625,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.1659,
      "step": 32
    },
    {
      "epoch": 0.0011244952549707803,
      "grad_norm": 1.4271526336669922,
      "learning_rate": 5.577113097809989e-05,
      "loss": 0.0579,
      "step": 33
    },
    {
      "epoch": 0.0011585708687577734,
      "grad_norm": 0.96360844373703,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0371,
      "step": 34
    },
    {
      "epoch": 0.0011926464825447668,
      "grad_norm": 1.0970512628555298,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.0368,
      "step": 35
    },
    {
      "epoch": 0.0012267220963317602,
      "grad_norm": 0.5222811698913574,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.014,
      "step": 36
    },
    {
      "epoch": 0.0012607977101187534,
      "grad_norm": 2.5938470363616943,
      "learning_rate": 3.406541848999312e-05,
      "loss": 0.0974,
      "step": 37
    },
    {
      "epoch": 0.0012948733239057468,
      "grad_norm": 0.8170644044876099,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0307,
      "step": 38
    },
    {
      "epoch": 0.0013289489376927402,
      "grad_norm": 0.9838296175003052,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 0.0276,
      "step": 39
    },
    {
      "epoch": 0.0013630245514797336,
      "grad_norm": 2.9819869995117188,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.1533,
      "step": 40
    },
    {
      "epoch": 0.0013971001652667268,
      "grad_norm": 2.393613576889038,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.1044,
      "step": 41
    },
    {
      "epoch": 0.0014311757790537202,
      "grad_norm": 1.6655608415603638,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.048,
      "step": 42
    },
    {
      "epoch": 0.0014652513928407136,
      "grad_norm": 16.368389129638672,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 0.0653,
      "step": 43
    },
    {
      "epoch": 0.0014993270066277068,
      "grad_norm": 2.2346484661102295,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.167,
      "step": 44
    },
    {
      "epoch": 0.0015334026204147002,
      "grad_norm": 2.2778067588806152,
      "learning_rate": 5.306987050489442e-06,
      "loss": 0.0613,
      "step": 45
    },
    {
      "epoch": 0.0015674782342016936,
      "grad_norm": 0.7512469291687012,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.041,
      "step": 46
    },
    {
      "epoch": 0.001601553847988687,
      "grad_norm": 4.560179710388184,
      "learning_rate": 1.921471959676957e-06,
      "loss": 0.0939,
      "step": 47
    },
    {
      "epoch": 0.0016356294617756802,
      "grad_norm": 9.43427848815918,
      "learning_rate": 8.555138626189618e-07,
      "loss": 0.3062,
      "step": 48
    },
    {
      "epoch": 0.0016697050755626736,
      "grad_norm": 8.753609657287598,
      "learning_rate": 2.141076761396521e-07,
      "loss": 0.4055,
      "step": 49
    },
    {
      "epoch": 0.001703780689349667,
      "grad_norm": 5.78505277633667,
      "learning_rate": 0.0,
      "loss": 0.1969,
      "step": 50
    },
    {
      "epoch": 0.001703780689349667,
      "eval_loss": 0.06993943452835083,
      "eval_runtime": 7845.7082,
      "eval_samples_per_second": 1.575,
      "eval_steps_per_second": 0.788,
      "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": 1.3890925538102477e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}