{
  "best_metric": 0.030457014217972755,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.10934937124111536,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002186987424822307,
      "grad_norm": 0.1379365772008896,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.0589,
      "step": 1
    },
    {
      "epoch": 0.002186987424822307,
      "eval_loss": 0.23621612787246704,
      "eval_runtime": 2.127,
      "eval_samples_per_second": 23.508,
      "eval_steps_per_second": 3.291,
      "step": 1
    },
    {
      "epoch": 0.004373974849644614,
      "grad_norm": 0.12105759233236313,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.0552,
      "step": 2
    },
    {
      "epoch": 0.0065609622744669215,
      "grad_norm": 0.11737111210823059,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.0608,
      "step": 3
    },
    {
      "epoch": 0.008747949699289229,
      "grad_norm": 0.11113476753234863,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.0471,
      "step": 4
    },
    {
      "epoch": 0.010934937124111536,
      "grad_norm": 0.12482555210590363,
      "learning_rate": 0.00015,
      "loss": 0.0495,
      "step": 5
    },
    {
      "epoch": 0.013121924548933843,
      "grad_norm": 0.15192073583602905,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.0574,
      "step": 6
    },
    {
      "epoch": 0.01530891197375615,
      "grad_norm": 0.15852989256381989,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.0594,
      "step": 7
    },
    {
      "epoch": 0.017495899398578457,
      "grad_norm": 0.15277495980262756,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.0651,
      "step": 8
    },
    {
      "epoch": 0.019682886823400764,
      "grad_norm": 0.1454448699951172,
      "learning_rate": 0.00027,
      "loss": 0.059,
      "step": 9
    },
    {
      "epoch": 0.02186987424822307,
      "grad_norm": 0.2372606247663498,
      "learning_rate": 0.0003,
      "loss": 0.059,
      "step": 10
    },
    {
      "epoch": 0.02405686167304538,
      "grad_norm": 0.21213853359222412,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.045,
      "step": 11
    },
    {
      "epoch": 0.026243849097867686,
      "grad_norm": 0.17461541295051575,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.0373,
      "step": 12
    },
    {
      "epoch": 0.028430836522689993,
      "grad_norm": 0.12617610394954681,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.0266,
      "step": 13
    },
    {
      "epoch": 0.0306178239475123,
      "grad_norm": 0.19508954882621765,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.031,
      "step": 14
    },
    {
      "epoch": 0.03280481137233461,
      "grad_norm": 0.21883797645568848,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.0271,
      "step": 15
    },
    {
      "epoch": 0.034991798797156914,
      "grad_norm": 0.26026102900505066,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.0303,
      "step": 16
    },
    {
      "epoch": 0.037178786221979225,
      "grad_norm": 0.21829484403133392,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.0339,
      "step": 17
    },
    {
      "epoch": 0.03936577364680153,
      "grad_norm": 0.1891174167394638,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.0267,
      "step": 18
    },
    {
      "epoch": 0.04155276107162384,
      "grad_norm": 0.1897806078195572,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.0209,
      "step": 19
    },
    {
      "epoch": 0.04373974849644614,
      "grad_norm": 0.14886467158794403,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.026,
      "step": 20
    },
    {
      "epoch": 0.045926735921268454,
      "grad_norm": 0.14559559524059296,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.025,
      "step": 21
    },
    {
      "epoch": 0.04811372334609076,
      "grad_norm": 0.19482867419719696,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.0305,
      "step": 22
    },
    {
      "epoch": 0.05030071077091307,
      "grad_norm": 0.1720445454120636,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.0329,
      "step": 23
    },
    {
      "epoch": 0.05248769819573537,
      "grad_norm": 0.158674418926239,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.0241,
      "step": 24
    },
    {
      "epoch": 0.05467468562055768,
      "grad_norm": 0.2127903699874878,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.0281,
      "step": 25
    },
    {
      "epoch": 0.05467468562055768,
      "eval_loss": 0.03313703089952469,
      "eval_runtime": 1.3445,
      "eval_samples_per_second": 37.188,
      "eval_steps_per_second": 5.206,
      "step": 25
    },
    {
      "epoch": 0.056861673045379986,
      "grad_norm": 0.1662108302116394,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.0259,
      "step": 26
    },
    {
      "epoch": 0.0590486604702023,
      "grad_norm": 0.14126865565776825,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.019,
      "step": 27
    },
    {
      "epoch": 0.0612356478950246,
      "grad_norm": 0.20812584459781647,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.0269,
      "step": 28
    },
    {
      "epoch": 0.0634226353198469,
      "grad_norm": 0.16265930235385895,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.0166,
      "step": 29
    },
    {
      "epoch": 0.06560962274466922,
      "grad_norm": 0.1864025890827179,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.0298,
      "step": 30
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 0.2999975085258484,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.0342,
      "step": 31
    },
    {
      "epoch": 0.06998359759431383,
      "grad_norm": 0.18503515422344208,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.0305,
      "step": 32
    },
    {
      "epoch": 0.07217058501913615,
      "grad_norm": 0.2400880604982376,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.0218,
      "step": 33
    },
    {
      "epoch": 0.07435757244395845,
      "grad_norm": 0.17187494039535522,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.0238,
      "step": 34
    },
    {
      "epoch": 0.07654455986878075,
      "grad_norm": 0.17750395834445953,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.0274,
      "step": 35
    },
    {
      "epoch": 0.07873154729360306,
      "grad_norm": 0.24035736918449402,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.0327,
      "step": 36
    },
    {
      "epoch": 0.08091853471842538,
      "grad_norm": 0.17879100143909454,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.0273,
      "step": 37
    },
    {
      "epoch": 0.08310552214324768,
      "grad_norm": 0.5411270260810852,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.0349,
      "step": 38
    },
    {
      "epoch": 0.08529250956806998,
      "grad_norm": 0.21817879378795624,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.0326,
      "step": 39
    },
    {
      "epoch": 0.08747949699289229,
      "grad_norm": 1.6915651559829712,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.037,
      "step": 40
    },
    {
      "epoch": 0.0896664844177146,
      "grad_norm": 0.2748837172985077,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.0307,
      "step": 41
    },
    {
      "epoch": 0.09185347184253691,
      "grad_norm": 0.27645471692085266,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.0406,
      "step": 42
    },
    {
      "epoch": 0.09404045926735921,
      "grad_norm": 0.2864626944065094,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.0361,
      "step": 43
    },
    {
      "epoch": 0.09622744669218151,
      "grad_norm": 0.267821729183197,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.0375,
      "step": 44
    },
    {
      "epoch": 0.09841443411700383,
      "grad_norm": 0.9943220019340515,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.0658,
      "step": 45
    },
    {
      "epoch": 0.10060142154182614,
      "grad_norm": 0.37693554162979126,
      "learning_rate": 0.000274201324672203,
      "loss": 0.0562,
      "step": 46
    },
    {
      "epoch": 0.10278840896664844,
      "grad_norm": 0.4007059335708618,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.0629,
      "step": 47
    },
    {
      "epoch": 0.10497539639147074,
      "grad_norm": 0.559242308139801,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.0811,
      "step": 48
    },
    {
      "epoch": 0.10716238381629306,
      "grad_norm": 0.8317009806632996,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.1323,
      "step": 49
    },
    {
      "epoch": 0.10934937124111536,
      "grad_norm": 1.7056876420974731,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.2221,
      "step": 50
    },
    {
      "epoch": 0.10934937124111536,
      "eval_loss": 0.030457014217972755,
      "eval_runtime": 1.3502,
      "eval_samples_per_second": 37.032,
      "eval_steps_per_second": 5.185,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1464488316305408e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}