{
  "best_metric": 10.35035228729248,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.022655188038060717,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00045310376076121433,
      "grad_norm": 0.08214962482452393,
      "learning_rate": 2e-05,
      "loss": 10.3726,
      "step": 1
    },
    {
      "epoch": 0.00045310376076121433,
      "eval_loss": 10.372055053710938,
      "eval_runtime": 6.1256,
      "eval_samples_per_second": 606.801,
      "eval_steps_per_second": 75.911,
      "step": 1
    },
    {
      "epoch": 0.0009062075215224287,
      "grad_norm": 0.0846695676445961,
      "learning_rate": 4e-05,
      "loss": 10.3757,
      "step": 2
    },
    {
      "epoch": 0.001359311282283643,
      "grad_norm": 0.076853908598423,
      "learning_rate": 6e-05,
      "loss": 10.3727,
      "step": 3
    },
    {
      "epoch": 0.0018124150430448573,
      "grad_norm": 0.07561151683330536,
      "learning_rate": 8e-05,
      "loss": 10.3751,
      "step": 4
    },
    {
      "epoch": 0.0022655188038060714,
      "grad_norm": 0.08088299632072449,
      "learning_rate": 0.0001,
      "loss": 10.3735,
      "step": 5
    },
    {
      "epoch": 0.002718622564567286,
      "grad_norm": 0.08890769630670547,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3709,
      "step": 6
    },
    {
      "epoch": 0.0031717263253285004,
      "grad_norm": 0.08019179105758667,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3732,
      "step": 7
    },
    {
      "epoch": 0.0036248300860897147,
      "grad_norm": 0.09421122074127197,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3725,
      "step": 8
    },
    {
      "epoch": 0.0040779338468509285,
      "grad_norm": 0.0971372202038765,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3685,
      "step": 9
    },
    {
      "epoch": 0.004531037607612143,
      "grad_norm": 0.09252215176820755,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3698,
      "step": 10
    },
    {
      "epoch": 0.004984141368373357,
      "grad_norm": 0.10680188983678818,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3665,
      "step": 11
    },
    {
      "epoch": 0.005437245129134572,
      "grad_norm": 0.09999203681945801,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3684,
      "step": 12
    },
    {
      "epoch": 0.0058903488898957865,
      "grad_norm": 0.10176604986190796,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3649,
      "step": 13
    },
    {
      "epoch": 0.006343452650657001,
      "grad_norm": 0.10781875997781754,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3683,
      "step": 14
    },
    {
      "epoch": 0.006796556411418215,
      "grad_norm": 0.11113500595092773,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.366,
      "step": 15
    },
    {
      "epoch": 0.007249660172179429,
      "grad_norm": 0.11764982342720032,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3658,
      "step": 16
    },
    {
      "epoch": 0.007702763932940644,
      "grad_norm": 0.12170328199863434,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3657,
      "step": 17
    },
    {
      "epoch": 0.008155867693701857,
      "grad_norm": 0.12587465345859528,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3624,
      "step": 18
    },
    {
      "epoch": 0.008608971454463071,
      "grad_norm": 0.14366334676742554,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3616,
      "step": 19
    },
    {
      "epoch": 0.009062075215224286,
      "grad_norm": 0.15799346566200256,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3629,
      "step": 20
    },
    {
      "epoch": 0.0095151789759855,
      "grad_norm": 0.12464886158704758,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3621,
      "step": 21
    },
    {
      "epoch": 0.009968282736746714,
      "grad_norm": 0.13898994028568268,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3571,
      "step": 22
    },
    {
      "epoch": 0.01042138649750793,
      "grad_norm": 0.1414911299943924,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3614,
      "step": 23
    },
    {
      "epoch": 0.010874490258269144,
      "grad_norm": 0.13739123940467834,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3593,
      "step": 24
    },
    {
      "epoch": 0.011327594019030359,
      "grad_norm": 0.15723730623722076,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3598,
      "step": 25
    },
    {
      "epoch": 0.011327594019030359,
      "eval_loss": 10.357394218444824,
      "eval_runtime": 6.1267,
      "eval_samples_per_second": 606.693,
      "eval_steps_per_second": 75.898,
      "step": 25
    },
    {
      "epoch": 0.011780697779791573,
      "grad_norm": 0.1885799765586853,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3603,
      "step": 26
    },
    {
      "epoch": 0.012233801540552787,
      "grad_norm": 0.16406424343585968,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3557,
      "step": 27
    },
    {
      "epoch": 0.012686905301314002,
      "grad_norm": 0.17430010437965393,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3564,
      "step": 28
    },
    {
      "epoch": 0.013140009062075216,
      "grad_norm": 0.1869587004184723,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3561,
      "step": 29
    },
    {
      "epoch": 0.01359311282283643,
      "grad_norm": 0.16364026069641113,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3571,
      "step": 30
    },
    {
      "epoch": 0.014046216583597644,
      "grad_norm": 0.13922007381916046,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.357,
      "step": 31
    },
    {
      "epoch": 0.014499320344358859,
      "grad_norm": 0.1661142110824585,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3528,
      "step": 32
    },
    {
      "epoch": 0.014952424105120073,
      "grad_norm": 0.17683999240398407,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3551,
      "step": 33
    },
    {
      "epoch": 0.015405527865881287,
      "grad_norm": 0.15338218212127686,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3499,
      "step": 34
    },
    {
      "epoch": 0.0158586316266425,
      "grad_norm": 0.17775611579418182,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.351,
      "step": 35
    },
    {
      "epoch": 0.016311735387403714,
      "grad_norm": 0.17701967060565948,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3541,
      "step": 36
    },
    {
      "epoch": 0.01676483914816493,
      "grad_norm": 0.15589460730552673,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3524,
      "step": 37
    },
    {
      "epoch": 0.017217942908926143,
      "grad_norm": 0.14376643300056458,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3524,
      "step": 38
    },
    {
      "epoch": 0.017671046669687357,
      "grad_norm": 0.17480316758155823,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3501,
      "step": 39
    },
    {
      "epoch": 0.01812415043044857,
      "grad_norm": 0.17131978273391724,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3545,
      "step": 40
    },
    {
      "epoch": 0.018577254191209785,
      "grad_norm": 0.14923687279224396,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3502,
      "step": 41
    },
    {
      "epoch": 0.019030357951971,
      "grad_norm": 0.1653790920972824,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3535,
      "step": 42
    },
    {
      "epoch": 0.019483461712732214,
      "grad_norm": 0.14821237325668335,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3546,
      "step": 43
    },
    {
      "epoch": 0.01993656547349343,
      "grad_norm": 0.1650238186120987,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3489,
      "step": 44
    },
    {
      "epoch": 0.020389669234254643,
      "grad_norm": 0.13781306147575378,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3507,
      "step": 45
    },
    {
      "epoch": 0.02084277299501586,
      "grad_norm": 0.16543304920196533,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3499,
      "step": 46
    },
    {
      "epoch": 0.021295876755777075,
      "grad_norm": 0.15752767026424408,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3518,
      "step": 47
    },
    {
      "epoch": 0.02174898051653829,
      "grad_norm": 0.1764352172613144,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3515,
      "step": 48
    },
    {
      "epoch": 0.022202084277299503,
      "grad_norm": 0.15777145326137543,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3515,
      "step": 49
    },
    {
      "epoch": 0.022655188038060717,
      "grad_norm": 0.1509462594985962,
      "learning_rate": 0.0,
      "loss": 10.35,
      "step": 50
    },
    {
      "epoch": 0.022655188038060717,
      "eval_loss": 10.35035228729248,
      "eval_runtime": 6.129,
      "eval_samples_per_second": 606.456,
      "eval_steps_per_second": 75.868,
      "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": 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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4099486777344.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}