{
  "best_metric": 1.885321855545044,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.19464720194647203,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0038929440389294406,
      "grad_norm": 4.0478925704956055,
      "learning_rate": 5e-05,
      "loss": 4.039,
      "step": 1
    },
    {
      "epoch": 0.0038929440389294406,
      "eval_loss": 4.5366411209106445,
      "eval_runtime": 39.4092,
      "eval_samples_per_second": 43.924,
      "eval_steps_per_second": 5.506,
      "step": 1
    },
    {
      "epoch": 0.007785888077858881,
      "grad_norm": 4.422729015350342,
      "learning_rate": 0.0001,
      "loss": 4.136,
      "step": 2
    },
    {
      "epoch": 0.01167883211678832,
      "grad_norm": 4.750208854675293,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.2946,
      "step": 3
    },
    {
      "epoch": 0.015571776155717762,
      "grad_norm": 2.915879487991333,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.49,
      "step": 4
    },
    {
      "epoch": 0.019464720194647202,
      "grad_norm": 2.1194448471069336,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.26,
      "step": 5
    },
    {
      "epoch": 0.02335766423357664,
      "grad_norm": 2.5568413734436035,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.0088,
      "step": 6
    },
    {
      "epoch": 0.027250608272506083,
      "grad_norm": 2.879448890686035,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.7909,
      "step": 7
    },
    {
      "epoch": 0.031143552311435525,
      "grad_norm": 2.762845516204834,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.5088,
      "step": 8
    },
    {
      "epoch": 0.035036496350364967,
      "grad_norm": 3.063811779022217,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.5089,
      "step": 9
    },
    {
      "epoch": 0.038929440389294405,
      "grad_norm": 2.6537387371063232,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.346,
      "step": 10
    },
    {
      "epoch": 0.04282238442822384,
      "grad_norm": 1.3532145023345947,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.2197,
      "step": 11
    },
    {
      "epoch": 0.04671532846715328,
      "grad_norm": 2.851814031600952,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.1905,
      "step": 12
    },
    {
      "epoch": 0.05060827250608273,
      "grad_norm": 2.3687894344329834,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.1106,
      "step": 13
    },
    {
      "epoch": 0.054501216545012166,
      "grad_norm": 1.584920883178711,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.3399,
      "step": 14
    },
    {
      "epoch": 0.058394160583941604,
      "grad_norm": 1.197147250175476,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.1255,
      "step": 15
    },
    {
      "epoch": 0.06228710462287105,
      "grad_norm": 1.144870638847351,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.2358,
      "step": 16
    },
    {
      "epoch": 0.06618004866180048,
      "grad_norm": 1.4016952514648438,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.9848,
      "step": 17
    },
    {
      "epoch": 0.07007299270072993,
      "grad_norm": 1.0766123533248901,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0187,
      "step": 18
    },
    {
      "epoch": 0.07396593673965937,
      "grad_norm": 0.961541473865509,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.0025,
      "step": 19
    },
    {
      "epoch": 0.07785888077858881,
      "grad_norm": 0.9874019622802734,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0617,
      "step": 20
    },
    {
      "epoch": 0.08175182481751825,
      "grad_norm": 0.8068956136703491,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.9873,
      "step": 21
    },
    {
      "epoch": 0.08564476885644769,
      "grad_norm": 0.9123897552490234,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.0779,
      "step": 22
    },
    {
      "epoch": 0.08953771289537713,
      "grad_norm": 0.7243121862411499,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.8197,
      "step": 23
    },
    {
      "epoch": 0.09343065693430656,
      "grad_norm": 0.8814667463302612,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.9748,
      "step": 24
    },
    {
      "epoch": 0.09732360097323602,
      "grad_norm": 1.0969183444976807,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.9981,
      "step": 25
    },
    {
      "epoch": 0.09732360097323602,
      "eval_loss": 1.9103429317474365,
      "eval_runtime": 36.7589,
      "eval_samples_per_second": 47.091,
      "eval_steps_per_second": 5.903,
      "step": 25
    },
    {
      "epoch": 0.10121654501216545,
      "grad_norm": 0.8730716109275818,
      "learning_rate": 5e-05,
      "loss": 2.1233,
      "step": 26
    },
    {
      "epoch": 0.10510948905109489,
      "grad_norm": 0.9246626496315002,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 2.2101,
      "step": 27
    },
    {
      "epoch": 0.10900243309002433,
      "grad_norm": 0.8004997372627258,
      "learning_rate": 4.347369038899744e-05,
      "loss": 2.0681,
      "step": 28
    },
    {
      "epoch": 0.11289537712895377,
      "grad_norm": 0.7172746658325195,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 2.0711,
      "step": 29
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 0.7176663279533386,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.8255,
      "step": 30
    },
    {
      "epoch": 0.12068126520681265,
      "grad_norm": 0.7020939588546753,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.8726,
      "step": 31
    },
    {
      "epoch": 0.1245742092457421,
      "grad_norm": 0.7199696898460388,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.0506,
      "step": 32
    },
    {
      "epoch": 0.12846715328467154,
      "grad_norm": 0.7078929543495178,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.9991,
      "step": 33
    },
    {
      "epoch": 0.13236009732360096,
      "grad_norm": 0.7883986234664917,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.9867,
      "step": 34
    },
    {
      "epoch": 0.1362530413625304,
      "grad_norm": 1.1987528800964355,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.8544,
      "step": 35
    },
    {
      "epoch": 0.14014598540145987,
      "grad_norm": 0.9711931347846985,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.8425,
      "step": 36
    },
    {
      "epoch": 0.1440389294403893,
      "grad_norm": 0.9126873016357422,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.8503,
      "step": 37
    },
    {
      "epoch": 0.14793187347931874,
      "grad_norm": 0.7694374322891235,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.0683,
      "step": 38
    },
    {
      "epoch": 0.15182481751824817,
      "grad_norm": 0.6620789170265198,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.9371,
      "step": 39
    },
    {
      "epoch": 0.15571776155717762,
      "grad_norm": 0.7303202152252197,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 2.0504,
      "step": 40
    },
    {
      "epoch": 0.15961070559610704,
      "grad_norm": 0.6710600256919861,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.8286,
      "step": 41
    },
    {
      "epoch": 0.1635036496350365,
      "grad_norm": 0.7300748825073242,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.1142,
      "step": 42
    },
    {
      "epoch": 0.16739659367396595,
      "grad_norm": 0.7144145369529724,
      "learning_rate": 5.156362923365588e-06,
      "loss": 2.1115,
      "step": 43
    },
    {
      "epoch": 0.17128953771289537,
      "grad_norm": 0.6737845540046692,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.0772,
      "step": 44
    },
    {
      "epoch": 0.17518248175182483,
      "grad_norm": 0.7557979822158813,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.8919,
      "step": 45
    },
    {
      "epoch": 0.17907542579075425,
      "grad_norm": 0.7306810617446899,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.9798,
      "step": 46
    },
    {
      "epoch": 0.1829683698296837,
      "grad_norm": 0.7133315205574036,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.7939,
      "step": 47
    },
    {
      "epoch": 0.18686131386861313,
      "grad_norm": 0.721962571144104,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.8628,
      "step": 48
    },
    {
      "epoch": 0.19075425790754258,
      "grad_norm": 0.7585230469703674,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.9218,
      "step": 49
    },
    {
      "epoch": 0.19464720194647203,
      "grad_norm": 0.9087316393852234,
      "learning_rate": 0.0,
      "loss": 1.6011,
      "step": 50
    },
    {
      "epoch": 0.19464720194647203,
      "eval_loss": 1.885321855545044,
      "eval_runtime": 18.8729,
      "eval_samples_per_second": 91.719,
      "eval_steps_per_second": 11.498,
      "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": 1.059536353886208e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}