{
  "best_metric": 0.7300238013267517,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.00826685404869177,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001653370809738354,
      "grad_norm": 1.1458706855773926,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.9686,
      "step": 1
    },
    {
      "epoch": 0.0001653370809738354,
      "eval_loss": 1.4532192945480347,
      "eval_runtime": 1.8909,
      "eval_samples_per_second": 26.443,
      "eval_steps_per_second": 3.702,
      "step": 1
    },
    {
      "epoch": 0.0003306741619476708,
      "grad_norm": 1.2934821844100952,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.1419,
      "step": 2
    },
    {
      "epoch": 0.0004960112429215062,
      "grad_norm": 1.3526453971862793,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.1456,
      "step": 3
    },
    {
      "epoch": 0.0006613483238953416,
      "grad_norm": 1.4010525941848755,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.2078,
      "step": 4
    },
    {
      "epoch": 0.000826685404869177,
      "grad_norm": 1.1631656885147095,
      "learning_rate": 0.00015,
      "loss": 1.0343,
      "step": 5
    },
    {
      "epoch": 0.0009920224858430125,
      "grad_norm": 0.9487802982330322,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.0424,
      "step": 6
    },
    {
      "epoch": 0.0011573595668168477,
      "grad_norm": 0.6479355096817017,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.9562,
      "step": 7
    },
    {
      "epoch": 0.0013226966477906832,
      "grad_norm": 1.1392258405685425,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.8981,
      "step": 8
    },
    {
      "epoch": 0.0014880337287645187,
      "grad_norm": 1.2654004096984863,
      "learning_rate": 0.00027,
      "loss": 0.9577,
      "step": 9
    },
    {
      "epoch": 0.001653370809738354,
      "grad_norm": 0.9595345258712769,
      "learning_rate": 0.0003,
      "loss": 0.8777,
      "step": 10
    },
    {
      "epoch": 0.0018187078907121895,
      "grad_norm": 0.5911861062049866,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.8749,
      "step": 11
    },
    {
      "epoch": 0.001984044971686025,
      "grad_norm": 0.46297988295555115,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.7729,
      "step": 12
    },
    {
      "epoch": 0.0021493820526598604,
      "grad_norm": 0.5073149800300598,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.8461,
      "step": 13
    },
    {
      "epoch": 0.0023147191336336955,
      "grad_norm": 0.5063093900680542,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.7949,
      "step": 14
    },
    {
      "epoch": 0.002480056214607531,
      "grad_norm": 0.4964233934879303,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.8145,
      "step": 15
    },
    {
      "epoch": 0.0026453932955813665,
      "grad_norm": 0.46869364380836487,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.7973,
      "step": 16
    },
    {
      "epoch": 0.002810730376555202,
      "grad_norm": 0.48064351081848145,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.7762,
      "step": 17
    },
    {
      "epoch": 0.0029760674575290374,
      "grad_norm": 0.4655352532863617,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.8017,
      "step": 18
    },
    {
      "epoch": 0.003141404538502873,
      "grad_norm": 0.4899359345436096,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.7672,
      "step": 19
    },
    {
      "epoch": 0.003306741619476708,
      "grad_norm": 0.49928662180900574,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.7774,
      "step": 20
    },
    {
      "epoch": 0.0034720787004505435,
      "grad_norm": 0.5411067008972168,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.7915,
      "step": 21
    },
    {
      "epoch": 0.003637415781424379,
      "grad_norm": 0.49483177065849304,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.81,
      "step": 22
    },
    {
      "epoch": 0.0038027528623982144,
      "grad_norm": 0.477321594953537,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.7135,
      "step": 23
    },
    {
      "epoch": 0.00396808994337205,
      "grad_norm": 0.5247819423675537,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.7725,
      "step": 24
    },
    {
      "epoch": 0.004133427024345885,
      "grad_norm": 0.5035298466682434,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.6796,
      "step": 25
    },
    {
      "epoch": 0.004133427024345885,
      "eval_loss": 0.740797221660614,
      "eval_runtime": 1.8714,
      "eval_samples_per_second": 26.719,
      "eval_steps_per_second": 3.741,
      "step": 25
    },
    {
      "epoch": 0.004298764105319721,
      "grad_norm": 0.5274375081062317,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.7499,
      "step": 26
    },
    {
      "epoch": 0.004464101186293556,
      "grad_norm": 0.5270937085151672,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.72,
      "step": 27
    },
    {
      "epoch": 0.004629438267267391,
      "grad_norm": 0.5450596213340759,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.7604,
      "step": 28
    },
    {
      "epoch": 0.004794775348241227,
      "grad_norm": 0.5546329021453857,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.7516,
      "step": 29
    },
    {
      "epoch": 0.004960112429215062,
      "grad_norm": 0.5378047823905945,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.7325,
      "step": 30
    },
    {
      "epoch": 0.005125449510188898,
      "grad_norm": 0.5384945869445801,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.7204,
      "step": 31
    },
    {
      "epoch": 0.005290786591162733,
      "grad_norm": 0.564714252948761,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.7475,
      "step": 32
    },
    {
      "epoch": 0.005456123672136569,
      "grad_norm": 0.5964205861091614,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.7079,
      "step": 33
    },
    {
      "epoch": 0.005621460753110404,
      "grad_norm": 0.5732771754264832,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.6735,
      "step": 34
    },
    {
      "epoch": 0.005786797834084239,
      "grad_norm": 0.5388650298118591,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.6702,
      "step": 35
    },
    {
      "epoch": 0.005952134915058075,
      "grad_norm": 0.5706294775009155,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.6716,
      "step": 36
    },
    {
      "epoch": 0.00611747199603191,
      "grad_norm": 0.5575750470161438,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.6672,
      "step": 37
    },
    {
      "epoch": 0.006282809077005746,
      "grad_norm": 0.6226919889450073,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.669,
      "step": 38
    },
    {
      "epoch": 0.006448146157979581,
      "grad_norm": 0.6209577322006226,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.6994,
      "step": 39
    },
    {
      "epoch": 0.006613483238953416,
      "grad_norm": 0.5951119065284729,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.6644,
      "step": 40
    },
    {
      "epoch": 0.006778820319927252,
      "grad_norm": 0.6036494374275208,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.6463,
      "step": 41
    },
    {
      "epoch": 0.006944157400901087,
      "grad_norm": 0.6368991136550903,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.63,
      "step": 42
    },
    {
      "epoch": 0.007109494481874923,
      "grad_norm": 0.6688757538795471,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.6476,
      "step": 43
    },
    {
      "epoch": 0.007274831562848758,
      "grad_norm": 0.6986092329025269,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.7047,
      "step": 44
    },
    {
      "epoch": 0.007440168643822593,
      "grad_norm": 0.7855607867240906,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.6652,
      "step": 45
    },
    {
      "epoch": 0.007605505724796429,
      "grad_norm": 0.7658830881118774,
      "learning_rate": 0.000274201324672203,
      "loss": 0.705,
      "step": 46
    },
    {
      "epoch": 0.007770842805770264,
      "grad_norm": 0.7558281421661377,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.6567,
      "step": 47
    },
    {
      "epoch": 0.0079361798867441,
      "grad_norm": 0.8528456687927246,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.6641,
      "step": 48
    },
    {
      "epoch": 0.008101516967717935,
      "grad_norm": 0.8852099180221558,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.6517,
      "step": 49
    },
    {
      "epoch": 0.00826685404869177,
      "grad_norm": 1.2807631492614746,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.7514,
      "step": 50
    },
    {
      "epoch": 0.00826685404869177,
      "eval_loss": 0.7300238013267517,
      "eval_runtime": 1.8747,
      "eval_samples_per_second": 26.671,
      "eval_steps_per_second": 3.734,
      "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": 2.121880448060621e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}