{
  "best_metric": 0.8538514971733093,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.05178663904712584,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010357327809425167,
      "grad_norm": 2.934951066970825,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.3458,
      "step": 1
    },
    {
      "epoch": 0.0010357327809425167,
      "eval_loss": 2.4307608604431152,
      "eval_runtime": 131.1348,
      "eval_samples_per_second": 12.399,
      "eval_steps_per_second": 6.2,
      "step": 1
    },
    {
      "epoch": 0.0020714655618850335,
      "grad_norm": 3.631234884262085,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.5473,
      "step": 2
    },
    {
      "epoch": 0.0031071983428275505,
      "grad_norm": 3.7098679542541504,
      "learning_rate": 1e-05,
      "loss": 1.7358,
      "step": 3
    },
    {
      "epoch": 0.004142931123770067,
      "grad_norm": 4.27931547164917,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.3322,
      "step": 4
    },
    {
      "epoch": 0.005178663904712584,
      "grad_norm": 4.007849216461182,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.5253,
      "step": 5
    },
    {
      "epoch": 0.006214396685655101,
      "grad_norm": 5.52664041519165,
      "learning_rate": 2e-05,
      "loss": 1.8545,
      "step": 6
    },
    {
      "epoch": 0.0072501294665976174,
      "grad_norm": 3.834798574447632,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 1.3665,
      "step": 7
    },
    {
      "epoch": 0.008285862247540134,
      "grad_norm": 3.7450332641601562,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.3339,
      "step": 8
    },
    {
      "epoch": 0.009321595028482652,
      "grad_norm": 3.6901252269744873,
      "learning_rate": 3e-05,
      "loss": 1.4489,
      "step": 9
    },
    {
      "epoch": 0.010357327809425169,
      "grad_norm": 3.269052505493164,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.9925,
      "step": 10
    },
    {
      "epoch": 0.011393060590367685,
      "grad_norm": 3.4667394161224365,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 1.0799,
      "step": 11
    },
    {
      "epoch": 0.012428793371310202,
      "grad_norm": 4.5746917724609375,
      "learning_rate": 4e-05,
      "loss": 1.0442,
      "step": 12
    },
    {
      "epoch": 0.013464526152252718,
      "grad_norm": 3.5450432300567627,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.9699,
      "step": 13
    },
    {
      "epoch": 0.014500258933195235,
      "grad_norm": 2.999580144882202,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.8588,
      "step": 14
    },
    {
      "epoch": 0.015535991714137753,
      "grad_norm": 2.0789074897766113,
      "learning_rate": 5e-05,
      "loss": 0.7789,
      "step": 15
    },
    {
      "epoch": 0.016571724495080268,
      "grad_norm": 2.5798442363739014,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.7985,
      "step": 16
    },
    {
      "epoch": 0.017607457276022784,
      "grad_norm": 2.789106607437134,
      "learning_rate": 5.666666666666667e-05,
      "loss": 0.8539,
      "step": 17
    },
    {
      "epoch": 0.018643190056965304,
      "grad_norm": 2.157308578491211,
      "learning_rate": 6e-05,
      "loss": 0.7339,
      "step": 18
    },
    {
      "epoch": 0.01967892283790782,
      "grad_norm": 2.024956464767456,
      "learning_rate": 6.333333333333333e-05,
      "loss": 0.6393,
      "step": 19
    },
    {
      "epoch": 0.020714655618850338,
      "grad_norm": 2.095165967941284,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.7112,
      "step": 20
    },
    {
      "epoch": 0.021750388399792854,
      "grad_norm": 2.395766258239746,
      "learning_rate": 7e-05,
      "loss": 0.5803,
      "step": 21
    },
    {
      "epoch": 0.02278612118073537,
      "grad_norm": 1.9139028787612915,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.5602,
      "step": 22
    },
    {
      "epoch": 0.023821853961677887,
      "grad_norm": 1.8153733015060425,
      "learning_rate": 7.666666666666667e-05,
      "loss": 0.5852,
      "step": 23
    },
    {
      "epoch": 0.024857586742620404,
      "grad_norm": 1.7927237749099731,
      "learning_rate": 8e-05,
      "loss": 0.5787,
      "step": 24
    },
    {
      "epoch": 0.02589331952356292,
      "grad_norm": 2.2322211265563965,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.7009,
      "step": 25
    },
    {
      "epoch": 0.026929052304505437,
      "grad_norm": 1.8694380521774292,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.6042,
      "step": 26
    },
    {
      "epoch": 0.027964785085447953,
      "grad_norm": 1.5141125917434692,
      "learning_rate": 9e-05,
      "loss": 0.5847,
      "step": 27
    },
    {
      "epoch": 0.02900051786639047,
      "grad_norm": 1.4388060569763184,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.533,
      "step": 28
    },
    {
      "epoch": 0.03003625064733299,
      "grad_norm": 1.4760385751724243,
      "learning_rate": 9.666666666666667e-05,
      "loss": 0.4269,
      "step": 29
    },
    {
      "epoch": 0.031071983428275506,
      "grad_norm": 1.4737350940704346,
      "learning_rate": 0.0001,
      "loss": 0.3929,
      "step": 30
    },
    {
      "epoch": 0.03210771620921802,
      "grad_norm": 1.3517489433288574,
      "learning_rate": 9.999146252290264e-05,
      "loss": 0.4369,
      "step": 31
    },
    {
      "epoch": 0.033143448990160536,
      "grad_norm": 1.7029956579208374,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.453,
      "step": 32
    },
    {
      "epoch": 0.03417918177110305,
      "grad_norm": 2.4142861366271973,
      "learning_rate": 9.99231801983717e-05,
      "loss": 0.5166,
      "step": 33
    },
    {
      "epoch": 0.03521491455204557,
      "grad_norm": 1.5307400226593018,
      "learning_rate": 9.986345866928941e-05,
      "loss": 0.4085,
      "step": 34
    },
    {
      "epoch": 0.03625064733298809,
      "grad_norm": 1.6694791316986084,
      "learning_rate": 9.978670881475172e-05,
      "loss": 0.2848,
      "step": 35
    },
    {
      "epoch": 0.03728638011393061,
      "grad_norm": 0.9046441316604614,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.1912,
      "step": 36
    },
    {
      "epoch": 0.038322112894873125,
      "grad_norm": 1.6716495752334595,
      "learning_rate": 9.958223477553714e-05,
      "loss": 0.632,
      "step": 37
    },
    {
      "epoch": 0.03935784567581564,
      "grad_norm": 2.2129456996917725,
      "learning_rate": 9.94545804185573e-05,
      "loss": 0.8857,
      "step": 38
    },
    {
      "epoch": 0.04039357845675816,
      "grad_norm": 3.774207592010498,
      "learning_rate": 9.931003736767013e-05,
      "loss": 1.4254,
      "step": 39
    },
    {
      "epoch": 0.041429311237700675,
      "grad_norm": 1.758363127708435,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.8625,
      "step": 40
    },
    {
      "epoch": 0.04246504401864319,
      "grad_norm": 1.6825367212295532,
      "learning_rate": 9.89704883800683e-05,
      "loss": 0.6659,
      "step": 41
    },
    {
      "epoch": 0.04350077679958571,
      "grad_norm": 1.9193270206451416,
      "learning_rate": 9.877559839902184e-05,
      "loss": 0.5724,
      "step": 42
    },
    {
      "epoch": 0.044536509580528225,
      "grad_norm": 1.610196828842163,
      "learning_rate": 9.85640515958057e-05,
      "loss": 0.5503,
      "step": 43
    },
    {
      "epoch": 0.04557224236147074,
      "grad_norm": 1.7814068794250488,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.4417,
      "step": 44
    },
    {
      "epoch": 0.04660797514241326,
      "grad_norm": 1.386198878288269,
      "learning_rate": 9.809128215864097e-05,
      "loss": 0.3452,
      "step": 45
    },
    {
      "epoch": 0.047643707923355774,
      "grad_norm": 1.408173680305481,
      "learning_rate": 9.783022097502204e-05,
      "loss": 0.259,
      "step": 46
    },
    {
      "epoch": 0.04867944070429829,
      "grad_norm": 4.415549278259277,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9239,
      "step": 47
    },
    {
      "epoch": 0.04971517348524081,
      "grad_norm": 3.1557812690734863,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.8021,
      "step": 48
    },
    {
      "epoch": 0.050750906266183324,
      "grad_norm": 3.0184805393218994,
      "learning_rate": 9.694941803075283e-05,
      "loss": 0.6193,
      "step": 49
    },
    {
      "epoch": 0.05178663904712584,
      "grad_norm": 2.46248197555542,
      "learning_rate": 9.662361147021779e-05,
      "loss": 0.848,
      "step": 50
    },
    {
      "epoch": 0.05178663904712584,
      "eval_loss": 0.8538514971733093,
      "eval_runtime": 133.2166,
      "eval_samples_per_second": 12.206,
      "eval_steps_per_second": 6.103,
      "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": 5,
        "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": 6.65248289783808e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}