{
  "best_metric": 8.910418728191871e-06,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.038842493688094774,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007768498737618955,
      "grad_norm": 8.366649627685547,
      "learning_rate": 5e-05,
      "loss": 2.3975,
      "step": 1
    },
    {
      "epoch": 0.0007768498737618955,
      "eval_loss": 2.4055440425872803,
      "eval_runtime": 164.0826,
      "eval_samples_per_second": 52.851,
      "eval_steps_per_second": 6.606,
      "step": 1
    },
    {
      "epoch": 0.001553699747523791,
      "grad_norm": 8.317948341369629,
      "learning_rate": 0.0001,
      "loss": 2.3751,
      "step": 2
    },
    {
      "epoch": 0.0023305496212856864,
      "grad_norm": 5.464844226837158,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.077,
      "step": 3
    },
    {
      "epoch": 0.003107399495047582,
      "grad_norm": 3.1698436737060547,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.45,
      "step": 4
    },
    {
      "epoch": 0.0038842493688094775,
      "grad_norm": 2.960510492324829,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.0182,
      "step": 5
    },
    {
      "epoch": 0.004661099242571373,
      "grad_norm": 3.076589584350586,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.5615,
      "step": 6
    },
    {
      "epoch": 0.005437949116333269,
      "grad_norm": 2.5577547550201416,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.2104,
      "step": 7
    },
    {
      "epoch": 0.006214798990095164,
      "grad_norm": 1.1480977535247803,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0705,
      "step": 8
    },
    {
      "epoch": 0.006991648863857059,
      "grad_norm": 0.39718741178512573,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0156,
      "step": 9
    },
    {
      "epoch": 0.007768498737618955,
      "grad_norm": 0.1475147306919098,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0035,
      "step": 10
    },
    {
      "epoch": 0.00854534861138085,
      "grad_norm": 0.15703143179416656,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0014,
      "step": 11
    },
    {
      "epoch": 0.009322198485142746,
      "grad_norm": 0.010279592126607895,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0002,
      "step": 12
    },
    {
      "epoch": 0.010099048358904641,
      "grad_norm": 0.0038464684039354324,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0001,
      "step": 13
    },
    {
      "epoch": 0.010875898232666537,
      "grad_norm": 0.00869350228458643,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0001,
      "step": 14
    },
    {
      "epoch": 0.011652748106428433,
      "grad_norm": 0.005264031235128641,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0001,
      "step": 15
    },
    {
      "epoch": 0.012429597980190329,
      "grad_norm": 0.00487897265702486,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0001,
      "step": 16
    },
    {
      "epoch": 0.013206447853952225,
      "grad_norm": 0.011261853389441967,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0001,
      "step": 17
    },
    {
      "epoch": 0.013983297727714119,
      "grad_norm": 0.00503259152173996,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.014760147601476014,
      "grad_norm": 0.003699852153658867,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.01553699747523791,
      "grad_norm": 0.0030704208184033632,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.016313847348999804,
      "grad_norm": 0.0022948472760617733,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0170906972227617,
      "grad_norm": 0.0022450312972068787,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.017867547096523596,
      "grad_norm": 0.0016837477451190352,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.01864439697028549,
      "grad_norm": 0.001263755839318037,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.019421246844047387,
      "grad_norm": 0.0010373577242717147,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.019421246844047387,
      "eval_loss": 1.4995711353549268e-05,
      "eval_runtime": 149.2036,
      "eval_samples_per_second": 58.122,
      "eval_steps_per_second": 7.265,
      "step": 25
    },
    {
      "epoch": 0.020198096717809283,
      "grad_norm": 0.001549907959997654,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.02097494659157118,
      "grad_norm": 0.0022201130632311106,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.021751796465333074,
      "grad_norm": 0.0012902269372716546,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.02252864633909497,
      "grad_norm": 0.0013171558966860175,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.023305496212856866,
      "grad_norm": 0.0010842395713552833,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.024082346086618762,
      "grad_norm": 0.0010620245011523366,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.024859195960380658,
      "grad_norm": 0.0009621917852200568,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.025636045834142553,
      "grad_norm": 0.000822453701402992,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.02641289570790445,
      "grad_norm": 0.0008451817557215691,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.02718974558166634,
      "grad_norm": 0.0007389052188955247,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.027966595455428237,
      "grad_norm": 0.0007898600888438523,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.028743445329190133,
      "grad_norm": 0.0007789293886162341,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.02952029520295203,
      "grad_norm": 0.0007223489810712636,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.030297145076713924,
      "grad_norm": 0.0007466123206540942,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.03107399495047582,
      "grad_norm": 0.0007864102954044938,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.031850844824237716,
      "grad_norm": 0.0007756599807180464,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.03262769469799961,
      "grad_norm": 0.000746490724850446,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.03340454457176151,
      "grad_norm": 0.000700855627655983,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.0341813944455234,
      "grad_norm": 0.000752845371607691,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.0349582443192853,
      "grad_norm": 0.0007415320142172277,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.03573509419304719,
      "grad_norm": 0.000640879909042269,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.03651194406680909,
      "grad_norm": 0.000708499806933105,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.03728879394057098,
      "grad_norm": 0.0006713590119034052,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.03806564381433288,
      "grad_norm": 0.0007036121096462011,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.038842493688094774,
      "grad_norm": 0.0015248683048412204,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.038842493688094774,
      "eval_loss": 8.910418728191871e-06,
      "eval_runtime": 150.1581,
      "eval_samples_per_second": 57.752,
      "eval_steps_per_second": 7.219,
      "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": 2.229252309123072e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}