{
  "best_metric": 0.9848859906196594,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.12012012012012012,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024024024024024023,
      "grad_norm": 2.0971031188964844,
      "learning_rate": 2e-05,
      "loss": 3.0187,
      "step": 1
    },
    {
      "epoch": 0.0024024024024024023,
      "eval_loss": 2.851088523864746,
      "eval_runtime": 48.9037,
      "eval_samples_per_second": 14.334,
      "eval_steps_per_second": 1.799,
      "step": 1
    },
    {
      "epoch": 0.004804804804804805,
      "grad_norm": 2.2249419689178467,
      "learning_rate": 4e-05,
      "loss": 2.6649,
      "step": 2
    },
    {
      "epoch": 0.007207207207207207,
      "grad_norm": 2.2943310737609863,
      "learning_rate": 6e-05,
      "loss": 3.0719,
      "step": 3
    },
    {
      "epoch": 0.00960960960960961,
      "grad_norm": 1.7306230068206787,
      "learning_rate": 8e-05,
      "loss": 2.6095,
      "step": 4
    },
    {
      "epoch": 0.012012012012012012,
      "grad_norm": 1.0318970680236816,
      "learning_rate": 0.0001,
      "loss": 2.3355,
      "step": 5
    },
    {
      "epoch": 0.014414414414414415,
      "grad_norm": 0.6773841381072998,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.6014,
      "step": 6
    },
    {
      "epoch": 0.016816816816816817,
      "grad_norm": 0.7722229957580566,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.8833,
      "step": 7
    },
    {
      "epoch": 0.01921921921921922,
      "grad_norm": 0.8358666896820068,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.8462,
      "step": 8
    },
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 0.7132935523986816,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.5991,
      "step": 9
    },
    {
      "epoch": 0.024024024024024024,
      "grad_norm": 0.6344431042671204,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.4909,
      "step": 10
    },
    {
      "epoch": 0.026426426426426425,
      "grad_norm": 0.7708803415298462,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.4264,
      "step": 11
    },
    {
      "epoch": 0.02882882882882883,
      "grad_norm": 0.6311034560203552,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.3682,
      "step": 12
    },
    {
      "epoch": 0.03123123123123123,
      "grad_norm": 0.567393958568573,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5798,
      "step": 13
    },
    {
      "epoch": 0.033633633633633635,
      "grad_norm": 0.513917088508606,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.382,
      "step": 14
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 0.46948641538619995,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.2904,
      "step": 15
    },
    {
      "epoch": 0.03843843843843844,
      "grad_norm": 0.4837779402732849,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.0935,
      "step": 16
    },
    {
      "epoch": 0.04084084084084084,
      "grad_norm": 0.6037317514419556,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.5422,
      "step": 17
    },
    {
      "epoch": 0.043243243243243246,
      "grad_norm": 0.45345234870910645,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.1688,
      "step": 18
    },
    {
      "epoch": 0.04564564564564565,
      "grad_norm": 0.4484889805316925,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.2741,
      "step": 19
    },
    {
      "epoch": 0.04804804804804805,
      "grad_norm": 0.46147358417510986,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3749,
      "step": 20
    },
    {
      "epoch": 0.05045045045045045,
      "grad_norm": 0.41564714908599854,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.9641,
      "step": 21
    },
    {
      "epoch": 0.05285285285285285,
      "grad_norm": 0.416939914226532,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.8962,
      "step": 22
    },
    {
      "epoch": 0.05525525525525526,
      "grad_norm": 0.4956507086753845,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8582,
      "step": 23
    },
    {
      "epoch": 0.05765765765765766,
      "grad_norm": 0.403537392616272,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.9143,
      "step": 24
    },
    {
      "epoch": 0.06006006006006006,
      "grad_norm": 0.40698733925819397,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.873,
      "step": 25
    },
    {
      "epoch": 0.06006006006006006,
      "eval_loss": 1.116862416267395,
      "eval_runtime": 49.8248,
      "eval_samples_per_second": 14.069,
      "eval_steps_per_second": 1.766,
      "step": 25
    },
    {
      "epoch": 0.06246246246246246,
      "grad_norm": 0.35601821541786194,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.7875,
      "step": 26
    },
    {
      "epoch": 0.06486486486486487,
      "grad_norm": 0.4093438684940338,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.962,
      "step": 27
    },
    {
      "epoch": 0.06726726726726727,
      "grad_norm": 0.4381888508796692,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.0355,
      "step": 28
    },
    {
      "epoch": 0.06966966966966967,
      "grad_norm": 0.394925594329834,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.8719,
      "step": 29
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 0.39502450823783875,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.973,
      "step": 30
    },
    {
      "epoch": 0.07447447447447447,
      "grad_norm": 0.41608545184135437,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.7986,
      "step": 31
    },
    {
      "epoch": 0.07687687687687687,
      "grad_norm": 0.4361729919910431,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9382,
      "step": 32
    },
    {
      "epoch": 0.07927927927927927,
      "grad_norm": 0.42400476336479187,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.0115,
      "step": 33
    },
    {
      "epoch": 0.08168168168168168,
      "grad_norm": 0.39441099762916565,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.8631,
      "step": 34
    },
    {
      "epoch": 0.08408408408408409,
      "grad_norm": 0.42576584219932556,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0433,
      "step": 35
    },
    {
      "epoch": 0.08648648648648649,
      "grad_norm": 0.3904152512550354,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.0188,
      "step": 36
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.5034300088882446,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.1074,
      "step": 37
    },
    {
      "epoch": 0.0912912912912913,
      "grad_norm": 0.6272788643836975,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.1985,
      "step": 38
    },
    {
      "epoch": 0.0936936936936937,
      "grad_norm": 0.5937858819961548,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.3471,
      "step": 39
    },
    {
      "epoch": 0.0960960960960961,
      "grad_norm": 0.646436333656311,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.353,
      "step": 40
    },
    {
      "epoch": 0.0984984984984985,
      "grad_norm": 0.5500105023384094,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.1414,
      "step": 41
    },
    {
      "epoch": 0.1009009009009009,
      "grad_norm": 0.6234367489814758,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.3546,
      "step": 42
    },
    {
      "epoch": 0.1033033033033033,
      "grad_norm": 0.5408471822738647,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.9866,
      "step": 43
    },
    {
      "epoch": 0.1057057057057057,
      "grad_norm": 0.8120220303535461,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.4077,
      "step": 44
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.654384195804596,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.7303,
      "step": 45
    },
    {
      "epoch": 0.11051051051051052,
      "grad_norm": 0.6135900616645813,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.4114,
      "step": 46
    },
    {
      "epoch": 0.11291291291291292,
      "grad_norm": 0.5442359447479248,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.22,
      "step": 47
    },
    {
      "epoch": 0.11531531531531532,
      "grad_norm": 0.5599455237388611,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.5017,
      "step": 48
    },
    {
      "epoch": 0.11771771771771772,
      "grad_norm": 0.6104506254196167,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.4995,
      "step": 49
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 0.44341933727264404,
      "learning_rate": 0.0,
      "loss": 0.8638,
      "step": 50
    },
    {
      "epoch": 0.12012012012012012,
      "eval_loss": 0.9848859906196594,
      "eval_runtime": 49.8489,
      "eval_samples_per_second": 14.063,
      "eval_steps_per_second": 1.765,
      "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": 7.1094434267136e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}