{
  "best_metric": 0.5612907409667969,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0648508430609598,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012970168612191958,
      "grad_norm": 43.15007019042969,
      "learning_rate": 1e-06,
      "loss": 24.5956,
      "step": 1
    },
    {
      "epoch": 0.0012970168612191958,
      "eval_loss": 11.099210739135742,
      "eval_runtime": 43.2298,
      "eval_samples_per_second": 7.518,
      "eval_steps_per_second": 1.897,
      "step": 1
    },
    {
      "epoch": 0.0025940337224383916,
      "grad_norm": 34.01232147216797,
      "learning_rate": 2e-06,
      "loss": 21.4527,
      "step": 2
    },
    {
      "epoch": 0.0038910505836575876,
      "grad_norm": 43.92300796508789,
      "learning_rate": 3e-06,
      "loss": 21.7764,
      "step": 3
    },
    {
      "epoch": 0.005188067444876783,
      "grad_norm": 36.848297119140625,
      "learning_rate": 4e-06,
      "loss": 22.2293,
      "step": 4
    },
    {
      "epoch": 0.00648508430609598,
      "grad_norm": 34.78293991088867,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 21.3363,
      "step": 5
    },
    {
      "epoch": 0.007782101167315175,
      "grad_norm": 43.606285095214844,
      "learning_rate": 6e-06,
      "loss": 21.3269,
      "step": 6
    },
    {
      "epoch": 0.009079118028534372,
      "grad_norm": 35.7335319519043,
      "learning_rate": 7e-06,
      "loss": 18.8252,
      "step": 7
    },
    {
      "epoch": 0.010376134889753566,
      "grad_norm": 39.83949661254883,
      "learning_rate": 8e-06,
      "loss": 20.006,
      "step": 8
    },
    {
      "epoch": 0.011673151750972763,
      "grad_norm": 32.874061584472656,
      "learning_rate": 9e-06,
      "loss": 19.244,
      "step": 9
    },
    {
      "epoch": 0.01297016861219196,
      "grad_norm": 35.38383102416992,
      "learning_rate": 9.999999999999999e-06,
      "loss": 21.033,
      "step": 10
    },
    {
      "epoch": 0.014267185473411154,
      "grad_norm": 42.5994987487793,
      "learning_rate": 1.1e-05,
      "loss": 19.4729,
      "step": 11
    },
    {
      "epoch": 0.01556420233463035,
      "grad_norm": 32.3964958190918,
      "learning_rate": 1.2e-05,
      "loss": 19.9392,
      "step": 12
    },
    {
      "epoch": 0.016861219195849545,
      "grad_norm": 34.603797912597656,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 18.9286,
      "step": 13
    },
    {
      "epoch": 0.018158236057068743,
      "grad_norm": 22.889278411865234,
      "learning_rate": 1.4e-05,
      "loss": 19.2667,
      "step": 14
    },
    {
      "epoch": 0.019455252918287938,
      "grad_norm": 20.571109771728516,
      "learning_rate": 1.5e-05,
      "loss": 17.9724,
      "step": 15
    },
    {
      "epoch": 0.020752269779507133,
      "grad_norm": 24.65373992919922,
      "learning_rate": 1.6e-05,
      "loss": 18.7244,
      "step": 16
    },
    {
      "epoch": 0.02204928664072633,
      "grad_norm": 20.301925659179688,
      "learning_rate": 1.7e-05,
      "loss": 15.1692,
      "step": 17
    },
    {
      "epoch": 0.023346303501945526,
      "grad_norm": 20.82584571838379,
      "learning_rate": 1.8e-05,
      "loss": 15.8121,
      "step": 18
    },
    {
      "epoch": 0.02464332036316472,
      "grad_norm": 20.620403289794922,
      "learning_rate": 1.9e-05,
      "loss": 14.7579,
      "step": 19
    },
    {
      "epoch": 0.02594033722438392,
      "grad_norm": 38.9058952331543,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 13.4066,
      "step": 20
    },
    {
      "epoch": 0.027237354085603113,
      "grad_norm": 24.992218017578125,
      "learning_rate": 2.1e-05,
      "loss": 12.6445,
      "step": 21
    },
    {
      "epoch": 0.028534370946822308,
      "grad_norm": 29.613855361938477,
      "learning_rate": 2.2e-05,
      "loss": 11.2814,
      "step": 22
    },
    {
      "epoch": 0.029831387808041506,
      "grad_norm": 24.93452262878418,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 9.3331,
      "step": 23
    },
    {
      "epoch": 0.0311284046692607,
      "grad_norm": 27.680971145629883,
      "learning_rate": 2.4e-05,
      "loss": 8.6512,
      "step": 24
    },
    {
      "epoch": 0.0324254215304799,
      "grad_norm": 29.876705169677734,
      "learning_rate": 2.5e-05,
      "loss": 7.8155,
      "step": 25
    },
    {
      "epoch": 0.03372243839169909,
      "grad_norm": 35.160499572753906,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 5.7938,
      "step": 26
    },
    {
      "epoch": 0.03501945525291829,
      "grad_norm": 27.901893615722656,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 4.1644,
      "step": 27
    },
    {
      "epoch": 0.03631647211413749,
      "grad_norm": 26.058135986328125,
      "learning_rate": 2.8e-05,
      "loss": 3.4339,
      "step": 28
    },
    {
      "epoch": 0.03761348897535668,
      "grad_norm": 21.99599838256836,
      "learning_rate": 2.9e-05,
      "loss": 2.2824,
      "step": 29
    },
    {
      "epoch": 0.038910505836575876,
      "grad_norm": 25.322467803955078,
      "learning_rate": 3e-05,
      "loss": 1.5445,
      "step": 30
    },
    {
      "epoch": 0.040207522697795074,
      "grad_norm": 16.150192260742188,
      "learning_rate": 2.9984895998119723e-05,
      "loss": 1.1335,
      "step": 31
    },
    {
      "epoch": 0.041504539559014265,
      "grad_norm": 23.29557228088379,
      "learning_rate": 2.993961440992859e-05,
      "loss": 2.223,
      "step": 32
    },
    {
      "epoch": 0.042801556420233464,
      "grad_norm": 11.53945541381836,
      "learning_rate": 2.9864246426519023e-05,
      "loss": 0.357,
      "step": 33
    },
    {
      "epoch": 0.04409857328145266,
      "grad_norm": 16.441926956176758,
      "learning_rate": 2.9758943828979444e-05,
      "loss": 0.4553,
      "step": 34
    },
    {
      "epoch": 0.04539559014267185,
      "grad_norm": 13.965824127197266,
      "learning_rate": 2.9623918682727355e-05,
      "loss": 0.8248,
      "step": 35
    },
    {
      "epoch": 0.04669260700389105,
      "grad_norm": 21.11853790283203,
      "learning_rate": 2.9459442910437798e-05,
      "loss": 1.1816,
      "step": 36
    },
    {
      "epoch": 0.04798962386511025,
      "grad_norm": 21.567947387695312,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 2.031,
      "step": 37
    },
    {
      "epoch": 0.04928664072632944,
      "grad_norm": 18.425945281982422,
      "learning_rate": 2.904352305959606e-05,
      "loss": 0.9298,
      "step": 38
    },
    {
      "epoch": 0.05058365758754864,
      "grad_norm": 7.7157511711120605,
      "learning_rate": 2.8792916588271762e-05,
      "loss": 0.4712,
      "step": 39
    },
    {
      "epoch": 0.05188067444876784,
      "grad_norm": 40.98714065551758,
      "learning_rate": 2.8514533018536286e-05,
      "loss": 1.8018,
      "step": 40
    },
    {
      "epoch": 0.05317769130998703,
      "grad_norm": 36.11446762084961,
      "learning_rate": 2.820893297785107e-05,
      "loss": 1.6269,
      "step": 41
    },
    {
      "epoch": 0.054474708171206226,
      "grad_norm": 40.24372482299805,
      "learning_rate": 2.7876731904027994e-05,
      "loss": 1.417,
      "step": 42
    },
    {
      "epoch": 0.055771725032425425,
      "grad_norm": 37.61830520629883,
      "learning_rate": 2.7518598805819542e-05,
      "loss": 0.8011,
      "step": 43
    },
    {
      "epoch": 0.057068741893644616,
      "grad_norm": 7.277573108673096,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.1595,
      "step": 44
    },
    {
      "epoch": 0.058365758754863814,
      "grad_norm": 7.73269510269165,
      "learning_rate": 2.672747223702045e-05,
      "loss": 0.2451,
      "step": 45
    },
    {
      "epoch": 0.05966277561608301,
      "grad_norm": 5.931721210479736,
      "learning_rate": 2.6296071990054167e-05,
      "loss": 0.086,
      "step": 46
    },
    {
      "epoch": 0.0609597924773022,
      "grad_norm": 18.46846580505371,
      "learning_rate": 2.5841922957410875e-05,
      "loss": 0.8838,
      "step": 47
    },
    {
      "epoch": 0.0622568093385214,
      "grad_norm": 20.60508155822754,
      "learning_rate": 2.5365939734802973e-05,
      "loss": 2.3646,
      "step": 48
    },
    {
      "epoch": 0.06355382619974059,
      "grad_norm": 12.769781112670898,
      "learning_rate": 2.4869080889095693e-05,
      "loss": 1.2122,
      "step": 49
    },
    {
      "epoch": 0.0648508430609598,
      "grad_norm": 19.520858764648438,
      "learning_rate": 2.4352347027881003e-05,
      "loss": 1.8933,
      "step": 50
    },
    {
      "epoch": 0.0648508430609598,
      "eval_loss": 0.5612907409667969,
      "eval_runtime": 44.2478,
      "eval_samples_per_second": 7.345,
      "eval_steps_per_second": 1.853,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 1.66313582395392e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}