{
  "best_metric": 11.93052864074707,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06609385327164574,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026437541308658294,
      "grad_norm": 0.011571128852665424,
      "learning_rate": 5e-05,
      "loss": 11.9318,
      "step": 1
    },
    {
      "epoch": 0.0026437541308658294,
      "eval_loss": 11.931646347045898,
      "eval_runtime": 4.9851,
      "eval_samples_per_second": 511.327,
      "eval_steps_per_second": 63.991,
      "step": 1
    },
    {
      "epoch": 0.005287508261731659,
      "grad_norm": 0.011736417189240456,
      "learning_rate": 0.0001,
      "loss": 11.9326,
      "step": 2
    },
    {
      "epoch": 0.007931262392597489,
      "grad_norm": 0.012523532845079899,
      "learning_rate": 9.989294616193017e-05,
      "loss": 11.9325,
      "step": 3
    },
    {
      "epoch": 0.010575016523463317,
      "grad_norm": 0.01372375339269638,
      "learning_rate": 9.957224306869053e-05,
      "loss": 11.9327,
      "step": 4
    },
    {
      "epoch": 0.013218770654329148,
      "grad_norm": 0.015330009162425995,
      "learning_rate": 9.903926402016153e-05,
      "loss": 11.9324,
      "step": 5
    },
    {
      "epoch": 0.015862524785194978,
      "grad_norm": 0.016725467517971992,
      "learning_rate": 9.829629131445342e-05,
      "loss": 11.932,
      "step": 6
    },
    {
      "epoch": 0.018506278916060808,
      "grad_norm": 0.015466302633285522,
      "learning_rate": 9.73465064747553e-05,
      "loss": 11.9309,
      "step": 7
    },
    {
      "epoch": 0.021150033046926635,
      "grad_norm": 0.019924353808164597,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.931,
      "step": 8
    },
    {
      "epoch": 0.023793787177792465,
      "grad_norm": 0.019885575398802757,
      "learning_rate": 9.484363707663442e-05,
      "loss": 11.931,
      "step": 9
    },
    {
      "epoch": 0.026437541308658295,
      "grad_norm": 0.025339337065815926,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.9306,
      "step": 10
    },
    {
      "epoch": 0.029081295439524125,
      "grad_norm": 0.03201381489634514,
      "learning_rate": 9.157348061512727e-05,
      "loss": 11.9293,
      "step": 11
    },
    {
      "epoch": 0.031725049570389956,
      "grad_norm": 0.03648433834314346,
      "learning_rate": 8.966766701456177e-05,
      "loss": 11.9288,
      "step": 12
    },
    {
      "epoch": 0.034368803701255786,
      "grad_norm": 0.01616472750902176,
      "learning_rate": 8.759199037394887e-05,
      "loss": 11.932,
      "step": 13
    },
    {
      "epoch": 0.037012557832121616,
      "grad_norm": 0.015822507441043854,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.932,
      "step": 14
    },
    {
      "epoch": 0.03965631196298744,
      "grad_norm": 0.01776200346648693,
      "learning_rate": 8.296729075500344e-05,
      "loss": 11.9316,
      "step": 15
    },
    {
      "epoch": 0.04230006609385327,
      "grad_norm": 0.01780272088944912,
      "learning_rate": 8.043807145043604e-05,
      "loss": 11.9313,
      "step": 16
    },
    {
      "epoch": 0.0449438202247191,
      "grad_norm": 0.020823033526539803,
      "learning_rate": 7.777851165098012e-05,
      "loss": 11.9313,
      "step": 17
    },
    {
      "epoch": 0.04758757435558493,
      "grad_norm": 0.01967339590191841,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.9314,
      "step": 18
    },
    {
      "epoch": 0.05023132848645076,
      "grad_norm": 0.020374463871121407,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.9329,
      "step": 19
    },
    {
      "epoch": 0.05287508261731659,
      "grad_norm": 0.02226845547556877,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9298,
      "step": 20
    },
    {
      "epoch": 0.05551883674818242,
      "grad_norm": 0.03149580955505371,
      "learning_rate": 6.607197326515808e-05,
      "loss": 11.9312,
      "step": 21
    },
    {
      "epoch": 0.05816259087904825,
      "grad_norm": 0.034391093999147415,
      "learning_rate": 6.294095225512603e-05,
      "loss": 11.9302,
      "step": 22
    },
    {
      "epoch": 0.06080634500991408,
      "grad_norm": 0.02833605743944645,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 11.9305,
      "step": 23
    },
    {
      "epoch": 0.06345009914077991,
      "grad_norm": 0.03860155865550041,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 11.9292,
      "step": 24
    },
    {
      "epoch": 0.06609385327164574,
      "grad_norm": 0.06872212886810303,
      "learning_rate": 5.327015646150716e-05,
      "loss": 11.9279,
      "step": 25
    },
    {
      "epoch": 0.06609385327164574,
      "eval_loss": 11.93052864074707,
      "eval_runtime": 4.9898,
      "eval_samples_per_second": 510.842,
      "eval_steps_per_second": 63.93,
      "step": 25
    }
  ],
  "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": 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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 521247129600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}