{
  "best_metric": 11.927434921264648,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.5151515151515151,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 0.042927198112010956,
      "learning_rate": 5e-05,
      "loss": 11.9298,
      "step": 1
    },
    {
      "epoch": 0.030303030303030304,
      "eval_loss": 11.934499740600586,
      "eval_runtime": 0.1997,
      "eval_samples_per_second": 250.329,
      "eval_steps_per_second": 65.085,
      "step": 1
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 0.044990092515945435,
      "learning_rate": 0.0001,
      "loss": 11.9292,
      "step": 2
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.04351016506552696,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.9287,
      "step": 3
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.05512431636452675,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.9304,
      "step": 4
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 0.04697095602750778,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.9291,
      "step": 5
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.053055908530950546,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.9278,
      "step": 6
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 0.05407289043068886,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.9257,
      "step": 7
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.05828668549656868,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.9267,
      "step": 8
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.0520884171128273,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.9293,
      "step": 9
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.05817096680402756,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.9294,
      "step": 10
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.06539630889892578,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.9268,
      "step": 11
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.06663810461759567,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.9255,
      "step": 12
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 0.06866007298231125,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.9267,
      "step": 13
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.06065688654780388,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9296,
      "step": 14
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.07108743488788605,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.9263,
      "step": 15
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.09032683074474335,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9254,
      "step": 16
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 0.07295548170804977,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.929,
      "step": 17
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.08159720152616501,
      "learning_rate": 7.75e-05,
      "loss": 11.9283,
      "step": 18
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 0.08011110126972198,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.9288,
      "step": 19
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.09746745973825455,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.9222,
      "step": 20
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.09830505400896072,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.9218,
      "step": 21
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.10161171108484268,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.9259,
      "step": 22
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 0.09210245311260223,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.9247,
      "step": 23
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.09468359500169754,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.9262,
      "step": 24
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.11315794289112091,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.9223,
      "step": 25
    },
    {
      "epoch": 0.7575757575757576,
      "eval_loss": 11.93030071258545,
      "eval_runtime": 0.2002,
      "eval_samples_per_second": 249.731,
      "eval_steps_per_second": 64.93,
      "step": 25
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 0.1211697906255722,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.9209,
      "step": 26
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.1045660525560379,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.9241,
      "step": 27
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.11985132843255997,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.9256,
      "step": 28
    },
    {
      "epoch": 0.8787878787878788,
      "grad_norm": 0.12262695282697678,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.9233,
      "step": 29
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.13156487047672272,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.9212,
      "step": 30
    },
    {
      "epoch": 0.9393939393939394,
      "grad_norm": 0.12108948081731796,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.9256,
      "step": 31
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.1368885636329651,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.9225,
      "step": 32
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.13319207727909088,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.9226,
      "step": 33
    },
    {
      "epoch": 1.0303030303030303,
      "grad_norm": 0.14346179366111755,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.9214,
      "step": 34
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 0.15200822055339813,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 11.9177,
      "step": 35
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.1317354142665863,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.9246,
      "step": 36
    },
    {
      "epoch": 1.121212121212121,
      "grad_norm": 0.1376199722290039,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.9216,
      "step": 37
    },
    {
      "epoch": 1.1515151515151516,
      "grad_norm": 0.1418801099061966,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.9197,
      "step": 38
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.14652688801288605,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.9229,
      "step": 39
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.1499054878950119,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.9196,
      "step": 40
    },
    {
      "epoch": 1.2424242424242424,
      "grad_norm": 0.15601606667041779,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.9212,
      "step": 41
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.13926267623901367,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.9248,
      "step": 42
    },
    {
      "epoch": 1.303030303030303,
      "grad_norm": 0.15400037169456482,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.9213,
      "step": 43
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.1433720588684082,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.9234,
      "step": 44
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.1614866405725479,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.9216,
      "step": 45
    },
    {
      "epoch": 1.393939393939394,
      "grad_norm": 0.1457948535680771,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.9237,
      "step": 46
    },
    {
      "epoch": 1.4242424242424243,
      "grad_norm": 0.17013579607009888,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.9177,
      "step": 47
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.1702655702829361,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.9181,
      "step": 48
    },
    {
      "epoch": 1.4848484848484849,
      "grad_norm": 0.1586163192987442,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 11.924,
      "step": 49
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.158153235912323,
      "learning_rate": 1e-05,
      "loss": 11.9204,
      "step": 50
    },
    {
      "epoch": 1.5151515151515151,
      "eval_loss": 11.927434921264648,
      "eval_runtime": 0.2015,
      "eval_samples_per_second": 248.126,
      "eval_steps_per_second": 64.513,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1047055171584.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}