{
  "best_metric": 2.892958164215088,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.11695906432748537,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 2.253100872039795,
      "learning_rate": 2e-05,
      "loss": 16.8342,
      "step": 1
    },
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 4.158441066741943,
      "eval_runtime": 16.5022,
      "eval_samples_per_second": 5.454,
      "eval_steps_per_second": 2.727,
      "step": 1
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 2.4783618450164795,
      "learning_rate": 4e-05,
      "loss": 15.9541,
      "step": 2
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 2.0137407779693604,
      "learning_rate": 6e-05,
      "loss": 14.8217,
      "step": 3
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 2.190727949142456,
      "learning_rate": 8e-05,
      "loss": 16.3956,
      "step": 4
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 2.345444440841675,
      "learning_rate": 0.0001,
      "loss": 15.749,
      "step": 5
    },
    {
      "epoch": 0.023391812865497075,
      "eval_loss": 4.097043037414551,
      "eval_runtime": 16.0473,
      "eval_samples_per_second": 5.608,
      "eval_steps_per_second": 2.804,
      "step": 5
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 3.2830240726470947,
      "learning_rate": 0.00012,
      "loss": 16.8322,
      "step": 6
    },
    {
      "epoch": 0.03274853801169591,
      "grad_norm": 2.974461793899536,
      "learning_rate": 0.00014,
      "loss": 16.0088,
      "step": 7
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": 3.1687026023864746,
      "learning_rate": 0.00016,
      "loss": 15.9364,
      "step": 8
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 3.5214297771453857,
      "learning_rate": 0.00018,
      "loss": 14.8681,
      "step": 9
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 4.196442127227783,
      "learning_rate": 0.0002,
      "loss": 14.6799,
      "step": 10
    },
    {
      "epoch": 0.04678362573099415,
      "eval_loss": 3.503246307373047,
      "eval_runtime": 16.2617,
      "eval_samples_per_second": 5.534,
      "eval_steps_per_second": 2.767,
      "step": 10
    },
    {
      "epoch": 0.05146198830409357,
      "grad_norm": 4.277874946594238,
      "learning_rate": 0.00019781476007338058,
      "loss": 14.2522,
      "step": 11
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 3.801171064376831,
      "learning_rate": 0.0001913545457642601,
      "loss": 13.4107,
      "step": 12
    },
    {
      "epoch": 0.0608187134502924,
      "grad_norm": 4.525282382965088,
      "learning_rate": 0.00018090169943749476,
      "loss": 13.6431,
      "step": 13
    },
    {
      "epoch": 0.06549707602339182,
      "grad_norm": 4.023133277893066,
      "learning_rate": 0.00016691306063588583,
      "loss": 12.3407,
      "step": 14
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 5.790004730224609,
      "learning_rate": 0.00015000000000000001,
      "loss": 12.456,
      "step": 15
    },
    {
      "epoch": 0.07017543859649122,
      "eval_loss": 3.0637786388397217,
      "eval_runtime": 16.0091,
      "eval_samples_per_second": 5.622,
      "eval_steps_per_second": 2.811,
      "step": 15
    },
    {
      "epoch": 0.07485380116959064,
      "grad_norm": 6.088311195373535,
      "learning_rate": 0.00013090169943749476,
      "loss": 12.2347,
      "step": 16
    },
    {
      "epoch": 0.07953216374269007,
      "grad_norm": 5.730970859527588,
      "learning_rate": 0.00011045284632676536,
      "loss": 12.0377,
      "step": 17
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 5.611118793487549,
      "learning_rate": 8.954715367323468e-05,
      "loss": 11.4511,
      "step": 18
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 4.9706950187683105,
      "learning_rate": 6.909830056250527e-05,
      "loss": 11.446,
      "step": 19
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 4.709040641784668,
      "learning_rate": 5.000000000000002e-05,
      "loss": 11.6786,
      "step": 20
    },
    {
      "epoch": 0.0935672514619883,
      "eval_loss": 2.9236652851104736,
      "eval_runtime": 16.1604,
      "eval_samples_per_second": 5.569,
      "eval_steps_per_second": 2.785,
      "step": 20
    },
    {
      "epoch": 0.09824561403508772,
      "grad_norm": 3.8449292182922363,
      "learning_rate": 3.308693936411421e-05,
      "loss": 11.0454,
      "step": 21
    },
    {
      "epoch": 0.10292397660818714,
      "grad_norm": 4.184327125549316,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 12.3282,
      "step": 22
    },
    {
      "epoch": 0.10760233918128655,
      "grad_norm": 3.6719348430633545,
      "learning_rate": 8.645454235739903e-06,
      "loss": 12.619,
      "step": 23
    },
    {
      "epoch": 0.11228070175438597,
      "grad_norm": 3.6676769256591797,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 11.6547,
      "step": 24
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 3.906043767929077,
      "learning_rate": 0.0,
      "loss": 11.233,
      "step": 25
    },
    {
      "epoch": 0.11695906432748537,
      "eval_loss": 2.892958164215088,
      "eval_runtime": 17.3914,
      "eval_samples_per_second": 5.175,
      "eval_steps_per_second": 2.587,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 3600976006963200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}