{
  "best_metric": 0.03121613711118698,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.2656924609764198,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005313849219528396,
      "grad_norm": 23.735429763793945,
      "learning_rate": 5e-05,
      "loss": 10.8963,
      "step": 1
    },
    {
      "epoch": 0.005313849219528396,
      "eval_loss": 11.031381607055664,
      "eval_runtime": 3.8477,
      "eval_samples_per_second": 12.995,
      "eval_steps_per_second": 3.379,
      "step": 1
    },
    {
      "epoch": 0.010627698439056792,
      "grad_norm": 23.870187759399414,
      "learning_rate": 0.0001,
      "loss": 11.0229,
      "step": 2
    },
    {
      "epoch": 0.015941547658585187,
      "grad_norm": 27.29892349243164,
      "learning_rate": 9.990365154573717e-05,
      "loss": 9.6982,
      "step": 3
    },
    {
      "epoch": 0.021255396878113585,
      "grad_norm": 23.930377960205078,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.9348,
      "step": 4
    },
    {
      "epoch": 0.02656924609764198,
      "grad_norm": 6.183684349060059,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.9608,
      "step": 5
    },
    {
      "epoch": 0.031883095317170373,
      "grad_norm": 11.842926025390625,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.0285,
      "step": 6
    },
    {
      "epoch": 0.03719694453669877,
      "grad_norm": 1.7357816696166992,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.7126,
      "step": 7
    },
    {
      "epoch": 0.04251079375622717,
      "grad_norm": 1.9517472982406616,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.7058,
      "step": 8
    },
    {
      "epoch": 0.04782464297575556,
      "grad_norm": 2.457921266555786,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.7232,
      "step": 9
    },
    {
      "epoch": 0.05313849219528396,
      "grad_norm": 1.7132893800735474,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.6842,
      "step": 10
    },
    {
      "epoch": 0.058452341414812356,
      "grad_norm": 1.8711906671524048,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.6185,
      "step": 11
    },
    {
      "epoch": 0.06376619063434075,
      "grad_norm": 3.989243507385254,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.5226,
      "step": 12
    },
    {
      "epoch": 0.06908003985386915,
      "grad_norm": 5.848659515380859,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.4455,
      "step": 13
    },
    {
      "epoch": 0.07439388907339754,
      "grad_norm": 3.6532959938049316,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.3719,
      "step": 14
    },
    {
      "epoch": 0.07970773829292593,
      "grad_norm": 5.245995044708252,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.3358,
      "step": 15
    },
    {
      "epoch": 0.08502158751245434,
      "grad_norm": 2.672791004180908,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.3515,
      "step": 16
    },
    {
      "epoch": 0.09033543673198273,
      "grad_norm": 3.914903163909912,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.3683,
      "step": 17
    },
    {
      "epoch": 0.09564928595151112,
      "grad_norm": 2.5333163738250732,
      "learning_rate": 7.75e-05,
      "loss": 0.3497,
      "step": 18
    },
    {
      "epoch": 0.10096313517103953,
      "grad_norm": 2.873622417449951,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.2874,
      "step": 19
    },
    {
      "epoch": 0.10627698439056792,
      "grad_norm": 2.7790403366088867,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.2946,
      "step": 20
    },
    {
      "epoch": 0.11159083361009631,
      "grad_norm": 2.632528066635132,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.2481,
      "step": 21
    },
    {
      "epoch": 0.11690468282962471,
      "grad_norm": 1.862103819847107,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.2376,
      "step": 22
    },
    {
      "epoch": 0.1222185320491531,
      "grad_norm": 2.213386058807373,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.2337,
      "step": 23
    },
    {
      "epoch": 0.1275323812686815,
      "grad_norm": 2.59668231010437,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.2321,
      "step": 24
    },
    {
      "epoch": 0.1328462304882099,
      "grad_norm": 2.26269268989563,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.168,
      "step": 25
    },
    {
      "epoch": 0.1328462304882099,
      "eval_loss": 0.09762722998857498,
      "eval_runtime": 3.4978,
      "eval_samples_per_second": 14.295,
      "eval_steps_per_second": 3.717,
      "step": 25
    },
    {
      "epoch": 0.1381600797077383,
      "grad_norm": 1.816712498664856,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.1879,
      "step": 26
    },
    {
      "epoch": 0.14347392892726668,
      "grad_norm": 2.036473274230957,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.1885,
      "step": 27
    },
    {
      "epoch": 0.14878777814679509,
      "grad_norm": 2.3719797134399414,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.137,
      "step": 28
    },
    {
      "epoch": 0.1541016273663235,
      "grad_norm": 1.672696590423584,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.1344,
      "step": 29
    },
    {
      "epoch": 0.15941547658585187,
      "grad_norm": 2.002915859222412,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.1307,
      "step": 30
    },
    {
      "epoch": 0.16472932580538027,
      "grad_norm": 1.9717336893081665,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0723,
      "step": 31
    },
    {
      "epoch": 0.17004317502490868,
      "grad_norm": 2.640728712081909,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.1429,
      "step": 32
    },
    {
      "epoch": 0.17535702424443705,
      "grad_norm": 2.67779803276062,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.2118,
      "step": 33
    },
    {
      "epoch": 0.18067087346396546,
      "grad_norm": 2.2781598567962646,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.1246,
      "step": 34
    },
    {
      "epoch": 0.18598472268349386,
      "grad_norm": 1.9362671375274658,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.1466,
      "step": 35
    },
    {
      "epoch": 0.19129857190302224,
      "grad_norm": 1.3575589656829834,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0624,
      "step": 36
    },
    {
      "epoch": 0.19661242112255065,
      "grad_norm": 1.8417307138442993,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.1473,
      "step": 37
    },
    {
      "epoch": 0.20192627034207905,
      "grad_norm": 1.4421743154525757,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.1223,
      "step": 38
    },
    {
      "epoch": 0.20724011956160743,
      "grad_norm": 1.2103627920150757,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0951,
      "step": 39
    },
    {
      "epoch": 0.21255396878113583,
      "grad_norm": 1.4762458801269531,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.1311,
      "step": 40
    },
    {
      "epoch": 0.21786781800066424,
      "grad_norm": 1.3953089714050293,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.1134,
      "step": 41
    },
    {
      "epoch": 0.22318166722019261,
      "grad_norm": 1.0033924579620361,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.1072,
      "step": 42
    },
    {
      "epoch": 0.22849551643972102,
      "grad_norm": 1.3283861875534058,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0743,
      "step": 43
    },
    {
      "epoch": 0.23380936565924942,
      "grad_norm": 1.3830900192260742,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0845,
      "step": 44
    },
    {
      "epoch": 0.2391232148787778,
      "grad_norm": 1.0678446292877197,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0436,
      "step": 45
    },
    {
      "epoch": 0.2444370640983062,
      "grad_norm": 1.7523692846298218,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0892,
      "step": 46
    },
    {
      "epoch": 0.2497509133178346,
      "grad_norm": 1.321276068687439,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0527,
      "step": 47
    },
    {
      "epoch": 0.255064762537363,
      "grad_norm": 1.239159345626831,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0494,
      "step": 48
    },
    {
      "epoch": 0.2603786117568914,
      "grad_norm": 2.1219425201416016,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0874,
      "step": 49
    },
    {
      "epoch": 0.2656924609764198,
      "grad_norm": 1.0668234825134277,
      "learning_rate": 1e-05,
      "loss": 0.0246,
      "step": 50
    },
    {
      "epoch": 0.2656924609764198,
      "eval_loss": 0.03121613711118698,
      "eval_runtime": 3.4987,
      "eval_samples_per_second": 14.291,
      "eval_steps_per_second": 3.716,
      "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": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}