{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.027311211252219036,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013655605626109517,
      "eval_loss": 11.5,
      "eval_runtime": 35.0696,
      "eval_samples_per_second": 87.939,
      "eval_steps_per_second": 21.985,
      "step": 1
    },
    {
      "epoch": 0.0013655605626109518,
      "grad_norm": 4.888439434580505e-06,
      "learning_rate": 4.12e-05,
      "loss": 23.0,
      "step": 10
    },
    {
      "epoch": 0.0027311211252219036,
      "grad_norm": 1.274573241971666e-05,
      "learning_rate": 8.24e-05,
      "loss": 23.0,
      "step": 20
    },
    {
      "epoch": 0.004096681687832855,
      "grad_norm": 1.1897797776327934e-05,
      "learning_rate": 0.0001236,
      "loss": 23.0,
      "step": 30
    },
    {
      "epoch": 0.005462242250443807,
      "grad_norm": 1.6764104657340795e-05,
      "learning_rate": 0.0001648,
      "loss": 23.0,
      "step": 40
    },
    {
      "epoch": 0.006827802813054759,
      "grad_norm": 3.6385521525517106e-05,
      "learning_rate": 0.000206,
      "loss": 23.0,
      "step": 50
    },
    {
      "epoch": 0.006827802813054759,
      "eval_loss": 11.5,
      "eval_runtime": 34.9847,
      "eval_samples_per_second": 88.153,
      "eval_steps_per_second": 22.038,
      "step": 50
    },
    {
      "epoch": 0.00819336337566571,
      "grad_norm": 2.2429987438954413e-05,
      "learning_rate": 0.0002057490971767619,
      "loss": 23.0,
      "step": 60
    },
    {
      "epoch": 0.009558923938276663,
      "grad_norm": 3.156892489641905e-05,
      "learning_rate": 0.00020499761108038175,
      "loss": 23.0,
      "step": 70
    },
    {
      "epoch": 0.010924484500887614,
      "grad_norm": 2.4492210286553018e-05,
      "learning_rate": 0.00020374920287558198,
      "loss": 23.0,
      "step": 80
    },
    {
      "epoch": 0.012290045063498567,
      "grad_norm": 1.4094251127971802e-05,
      "learning_rate": 0.00020200995468164684,
      "loss": 23.0,
      "step": 90
    },
    {
      "epoch": 0.013655605626109518,
      "grad_norm": 0.00013197172665968537,
      "learning_rate": 0.00019978833994094855,
      "loss": 23.0,
      "step": 100
    },
    {
      "epoch": 0.013655605626109518,
      "eval_loss": 11.5,
      "eval_runtime": 34.9937,
      "eval_samples_per_second": 88.13,
      "eval_steps_per_second": 22.033,
      "step": 100
    },
    {
      "epoch": 0.01502116618872047,
      "grad_norm": 6.907564966240898e-05,
      "learning_rate": 0.00019709518213718787,
      "loss": 23.0,
      "step": 110
    },
    {
      "epoch": 0.01638672675133142,
      "grad_norm": 2.6268724468536675e-05,
      "learning_rate": 0.00019394360206446948,
      "loss": 23.0,
      "step": 120
    },
    {
      "epoch": 0.017752287313942374,
      "grad_norm": 0.00011045205610571429,
      "learning_rate": 0.00019034895390411186,
      "loss": 23.0,
      "step": 130
    },
    {
      "epoch": 0.019117847876553327,
      "grad_norm": 0.00011072980123572052,
      "learning_rate": 0.0001863287504206196,
      "loss": 23.0,
      "step": 140
    },
    {
      "epoch": 0.020483408439164276,
      "grad_norm": 0.00032751320395618677,
      "learning_rate": 0.00018190257764125471,
      "loss": 23.0,
      "step": 150
    },
    {
      "epoch": 0.020483408439164276,
      "eval_loss": 11.5,
      "eval_runtime": 35.0218,
      "eval_samples_per_second": 88.06,
      "eval_steps_per_second": 22.015,
      "step": 150
    },
    {
      "epoch": 0.02184896900177523,
      "grad_norm": 0.00021085802291054279,
      "learning_rate": 0.00017709199943488106,
      "loss": 23.0,
      "step": 160
    },
    {
      "epoch": 0.02321452956438618,
      "grad_norm": 0.00017776116146706045,
      "learning_rate": 0.00017192045245496238,
      "loss": 23.0,
      "step": 170
    },
    {
      "epoch": 0.024580090126997134,
      "grad_norm": 7.381874456768855e-05,
      "learning_rate": 0.00016641313195854277,
      "loss": 23.0,
      "step": 180
    },
    {
      "epoch": 0.025945650689608083,
      "grad_norm": 0.0005210270173847675,
      "learning_rate": 0.0001605968690574869,
      "loss": 23.0,
      "step": 190
    },
    {
      "epoch": 0.027311211252219036,
      "grad_norm": 0.0003010142536368221,
      "learning_rate": 0.0001545,
      "loss": 23.0,
      "step": 200
    },
    {
      "epoch": 0.027311211252219036,
      "eval_loss": 11.5,
      "eval_runtime": 35.0475,
      "eval_samples_per_second": 87.995,
      "eval_steps_per_second": 21.999,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7101503766528.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}