{
  "best_metric": 0.14272888004779816,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.4434589800443459,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008869179600886918,
      "eval_loss": 2.8770248889923096,
      "eval_runtime": 38.1113,
      "eval_samples_per_second": 12.463,
      "eval_steps_per_second": 3.122,
      "step": 1
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": 2.364651918411255,
      "learning_rate": 4.02e-05,
      "loss": 1.7045,
      "step": 10
    },
    {
      "epoch": 0.017738359201773836,
      "grad_norm": 5.935655117034912,
      "learning_rate": 8.04e-05,
      "loss": 1.2618,
      "step": 20
    },
    {
      "epoch": 0.026607538802660754,
      "grad_norm": 2.099881172180176,
      "learning_rate": 0.0001206,
      "loss": 0.6453,
      "step": 30
    },
    {
      "epoch": 0.03547671840354767,
      "grad_norm": 1.2235733270645142,
      "learning_rate": 0.0001608,
      "loss": 0.3949,
      "step": 40
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": 2.9881107807159424,
      "learning_rate": 0.000201,
      "loss": 0.4097,
      "step": 50
    },
    {
      "epoch": 0.04434589800443459,
      "eval_loss": 0.5164891481399536,
      "eval_runtime": 38.3505,
      "eval_samples_per_second": 12.386,
      "eval_steps_per_second": 3.103,
      "step": 50
    },
    {
      "epoch": 0.05321507760532151,
      "grad_norm": 1.0847694873809814,
      "learning_rate": 0.00020075518705111234,
      "loss": 0.412,
      "step": 60
    },
    {
      "epoch": 0.06208425720620843,
      "grad_norm": 2.6469056606292725,
      "learning_rate": 0.00020002194090852784,
      "loss": 0.4117,
      "step": 70
    },
    {
      "epoch": 0.07095343680709534,
      "grad_norm": 1.295844554901123,
      "learning_rate": 0.00019880383387374748,
      "loss": 0.4179,
      "step": 80
    },
    {
      "epoch": 0.07982261640798226,
      "grad_norm": 1.5523910522460938,
      "learning_rate": 0.00019710680044180106,
      "loss": 0.3102,
      "step": 90
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": 1.0117522478103638,
      "learning_rate": 0.0001949391083889838,
      "loss": 0.2715,
      "step": 100
    },
    {
      "epoch": 0.08869179600886919,
      "eval_loss": 0.38211727142333984,
      "eval_runtime": 38.181,
      "eval_samples_per_second": 12.441,
      "eval_steps_per_second": 3.117,
      "step": 100
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.8537772297859192,
      "learning_rate": 0.00019231131849308138,
      "loss": 0.3774,
      "step": 110
    },
    {
      "epoch": 0.10643015521064302,
      "grad_norm": 2.790709972381592,
      "learning_rate": 0.00018923623308232218,
      "loss": 0.3956,
      "step": 120
    },
    {
      "epoch": 0.11529933481152993,
      "grad_norm": 1.3601632118225098,
      "learning_rate": 0.00018572883366372081,
      "loss": 0.4427,
      "step": 130
    },
    {
      "epoch": 0.12416851441241686,
      "grad_norm": 1.0446776151657104,
      "learning_rate": 0.00018180620793468224,
      "loss": 0.2675,
      "step": 140
    },
    {
      "epoch": 0.13303769401330376,
      "grad_norm": 2.1166090965270996,
      "learning_rate": 0.00017748746653345728,
      "loss": 0.2237,
      "step": 150
    },
    {
      "epoch": 0.13303769401330376,
      "eval_loss": 0.31679707765579224,
      "eval_runtime": 38.1684,
      "eval_samples_per_second": 12.445,
      "eval_steps_per_second": 3.118,
      "step": 150
    },
    {
      "epoch": 0.1419068736141907,
      "grad_norm": 0.9246871471405029,
      "learning_rate": 0.00017279364993403443,
      "loss": 0.312,
      "step": 160
    },
    {
      "epoch": 0.15077605321507762,
      "grad_norm": 2.4459915161132812,
      "learning_rate": 0.00016774762593906525,
      "loss": 0.3171,
      "step": 170
    },
    {
      "epoch": 0.15964523281596452,
      "grad_norm": 1.1200841665267944,
      "learning_rate": 0.00016237397827022866,
      "loss": 0.2871,
      "step": 180
    },
    {
      "epoch": 0.16851441241685144,
      "grad_norm": 1.3566011190414429,
      "learning_rate": 0.00015669888679881007,
      "loss": 0.171,
      "step": 190
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": 1.6793667078018188,
      "learning_rate": 0.00015075,
      "loss": 0.1994,
      "step": 200
    },
    {
      "epoch": 0.17738359201773837,
      "eval_loss": 0.3108082711696625,
      "eval_runtime": 38.1848,
      "eval_samples_per_second": 12.44,
      "eval_steps_per_second": 3.116,
      "step": 200
    },
    {
      "epoch": 0.18625277161862527,
      "grad_norm": 0.7012319564819336,
      "learning_rate": 0.00014455630025230227,
      "loss": 0.3329,
      "step": 210
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 1.5228286981582642,
      "learning_rate": 0.00013814796263829918,
      "loss": 0.3096,
      "step": 220
    },
    {
      "epoch": 0.2039911308203991,
      "grad_norm": 0.6246249079704285,
      "learning_rate": 0.00013155620793468223,
      "loss": 0.2082,
      "step": 230
    },
    {
      "epoch": 0.21286031042128603,
      "grad_norm": 1.0557504892349243,
      "learning_rate": 0.0001248131505077666,
      "loss": 0.2378,
      "step": 240
    },
    {
      "epoch": 0.22172949002217296,
      "grad_norm": 1.1284499168395996,
      "learning_rate": 0.00011795164185552652,
      "loss": 0.1585,
      "step": 250
    },
    {
      "epoch": 0.22172949002217296,
      "eval_loss": 0.25602078437805176,
      "eval_runtime": 38.5281,
      "eval_samples_per_second": 12.329,
      "eval_steps_per_second": 3.089,
      "step": 250
    },
    {
      "epoch": 0.23059866962305986,
      "grad_norm": 0.9151793718338013,
      "learning_rate": 0.00011100511055839919,
      "loss": 0.2358,
      "step": 260
    },
    {
      "epoch": 0.2394678492239468,
      "grad_norm": 4.036000728607178,
      "learning_rate": 0.00010400739941860137,
      "loss": 0.2748,
      "step": 270
    },
    {
      "epoch": 0.24833702882483372,
      "grad_norm": 0.6628141403198242,
      "learning_rate": 9.699260058139868e-05,
      "loss": 0.2109,
      "step": 280
    },
    {
      "epoch": 0.2572062084257206,
      "grad_norm": 0.4428306818008423,
      "learning_rate": 8.999488944160085e-05,
      "loss": 0.1508,
      "step": 290
    },
    {
      "epoch": 0.2660753880266075,
      "grad_norm": 1.0661782026290894,
      "learning_rate": 8.30483581444735e-05,
      "loss": 0.1516,
      "step": 300
    },
    {
      "epoch": 0.2660753880266075,
      "eval_loss": 0.23859120905399323,
      "eval_runtime": 38.2194,
      "eval_samples_per_second": 12.428,
      "eval_steps_per_second": 3.114,
      "step": 300
    },
    {
      "epoch": 0.2749445676274945,
      "grad_norm": 0.5670942068099976,
      "learning_rate": 7.618684949223341e-05,
      "loss": 0.2459,
      "step": 310
    },
    {
      "epoch": 0.2838137472283814,
      "grad_norm": 0.9786374568939209,
      "learning_rate": 6.94437920653178e-05,
      "loss": 0.2879,
      "step": 320
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.6507399082183838,
      "learning_rate": 6.285203736170084e-05,
      "loss": 0.1876,
      "step": 330
    },
    {
      "epoch": 0.30155210643015523,
      "grad_norm": 0.4873329699039459,
      "learning_rate": 5.6443699747697714e-05,
      "loss": 0.1806,
      "step": 340
    },
    {
      "epoch": 0.31042128603104213,
      "grad_norm": 1.1811214685440063,
      "learning_rate": 5.025000000000002e-05,
      "loss": 0.1805,
      "step": 350
    },
    {
      "epoch": 0.31042128603104213,
      "eval_loss": 0.17829522490501404,
      "eval_runtime": 38.3654,
      "eval_samples_per_second": 12.381,
      "eval_steps_per_second": 3.102,
      "step": 350
    },
    {
      "epoch": 0.31929046563192903,
      "grad_norm": 0.5968577861785889,
      "learning_rate": 4.430111320118996e-05,
      "loss": 0.1979,
      "step": 360
    },
    {
      "epoch": 0.328159645232816,
      "grad_norm": 0.9261394143104553,
      "learning_rate": 3.862602172977134e-05,
      "loss": 0.2349,
      "step": 370
    },
    {
      "epoch": 0.3370288248337029,
      "grad_norm": 0.9118176698684692,
      "learning_rate": 3.325237406093478e-05,
      "loss": 0.1553,
      "step": 380
    },
    {
      "epoch": 0.3458980044345898,
      "grad_norm": 0.4677368402481079,
      "learning_rate": 2.820635006596558e-05,
      "loss": 0.1094,
      "step": 390
    },
    {
      "epoch": 0.35476718403547675,
      "grad_norm": 1.093851089477539,
      "learning_rate": 2.351253346654272e-05,
      "loss": 0.1338,
      "step": 400
    },
    {
      "epoch": 0.35476718403547675,
      "eval_loss": 0.15545837581157684,
      "eval_runtime": 38.2038,
      "eval_samples_per_second": 12.433,
      "eval_steps_per_second": 3.115,
      "step": 400
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.46255141496658325,
      "learning_rate": 1.9193792065317794e-05,
      "loss": 0.1739,
      "step": 410
    },
    {
      "epoch": 0.37250554323725055,
      "grad_norm": 0.9228695034980774,
      "learning_rate": 1.5271166336279193e-05,
      "loss": 0.2283,
      "step": 420
    },
    {
      "epoch": 0.38137472283813745,
      "grad_norm": 0.3832451105117798,
      "learning_rate": 1.1763766917677837e-05,
      "loss": 0.1433,
      "step": 430
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.49726876616477966,
      "learning_rate": 8.688681506918602e-06,
      "loss": 0.1177,
      "step": 440
    },
    {
      "epoch": 0.3991130820399113,
      "grad_norm": 0.3981192708015442,
      "learning_rate": 6.060891611016215e-06,
      "loss": 0.1133,
      "step": 450
    },
    {
      "epoch": 0.3991130820399113,
      "eval_loss": 0.14272888004779816,
      "eval_runtime": 38.3479,
      "eval_samples_per_second": 12.387,
      "eval_steps_per_second": 3.103,
      "step": 450
    },
    {
      "epoch": 0.4079822616407982,
      "grad_norm": 0.6553061604499817,
      "learning_rate": 3.893199558198952e-06,
      "loss": 0.1552,
      "step": 460
    },
    {
      "epoch": 0.41685144124168516,
      "grad_norm": 1.4326709508895874,
      "learning_rate": 2.1961661262525285e-06,
      "loss": 0.1773,
      "step": 470
    },
    {
      "epoch": 0.42572062084257206,
      "grad_norm": 0.36754101514816284,
      "learning_rate": 9.780590914721787e-07,
      "loss": 0.1508,
      "step": 480
    },
    {
      "epoch": 0.43458980044345896,
      "grad_norm": 0.2781977355480194,
      "learning_rate": 2.4481294888766817e-07,
      "loss": 0.1077,
      "step": 490
    },
    {
      "epoch": 0.4434589800443459,
      "grad_norm": 1.0655410289764404,
      "learning_rate": 0.0,
      "loss": 0.104,
      "step": 500
    },
    {
      "epoch": 0.4434589800443459,
      "eval_loss": 0.14348678290843964,
      "eval_runtime": 38.233,
      "eval_samples_per_second": 12.424,
      "eval_steps_per_second": 3.112,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2480978011081933e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}