{
  "best_metric": 0.26856350898742676,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.020889910173386254,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008355964069354502,
      "grad_norm": 31.66060447692871,
      "learning_rate": 2e-05,
      "loss": 12.8466,
      "step": 1
    },
    {
      "epoch": 0.0008355964069354502,
      "eval_loss": 4.225325107574463,
      "eval_runtime": 43.8591,
      "eval_samples_per_second": 11.491,
      "eval_steps_per_second": 5.746,
      "step": 1
    },
    {
      "epoch": 0.0016711928138709003,
      "grad_norm": 57.35757064819336,
      "learning_rate": 4e-05,
      "loss": 19.4517,
      "step": 2
    },
    {
      "epoch": 0.0025067892208063504,
      "grad_norm": 46.05146408081055,
      "learning_rate": 6e-05,
      "loss": 14.6041,
      "step": 3
    },
    {
      "epoch": 0.0033423856277418006,
      "grad_norm": 46.10567092895508,
      "learning_rate": 8e-05,
      "loss": 15.3004,
      "step": 4
    },
    {
      "epoch": 0.004177982034677251,
      "grad_norm": 44.45639419555664,
      "learning_rate": 0.0001,
      "loss": 13.4761,
      "step": 5
    },
    {
      "epoch": 0.004177982034677251,
      "eval_loss": 2.786395788192749,
      "eval_runtime": 42.3622,
      "eval_samples_per_second": 11.897,
      "eval_steps_per_second": 5.949,
      "step": 5
    },
    {
      "epoch": 0.005013578441612701,
      "grad_norm": 38.13277816772461,
      "learning_rate": 0.00012,
      "loss": 10.7352,
      "step": 6
    },
    {
      "epoch": 0.005849174848548151,
      "grad_norm": 34.82909393310547,
      "learning_rate": 0.00014,
      "loss": 7.4352,
      "step": 7
    },
    {
      "epoch": 0.006684771255483601,
      "grad_norm": 33.55427169799805,
      "learning_rate": 0.00016,
      "loss": 5.6992,
      "step": 8
    },
    {
      "epoch": 0.007520367662419052,
      "grad_norm": 26.17538833618164,
      "learning_rate": 0.00018,
      "loss": 3.4403,
      "step": 9
    },
    {
      "epoch": 0.008355964069354502,
      "grad_norm": 22.743793487548828,
      "learning_rate": 0.0002,
      "loss": 2.2401,
      "step": 10
    },
    {
      "epoch": 0.008355964069354502,
      "eval_loss": 0.45037999749183655,
      "eval_runtime": 42.4692,
      "eval_samples_per_second": 11.867,
      "eval_steps_per_second": 5.934,
      "step": 10
    },
    {
      "epoch": 0.009191560476289952,
      "grad_norm": 15.18215274810791,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.2433,
      "step": 11
    },
    {
      "epoch": 0.010027156883225401,
      "grad_norm": 8.072440147399902,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.786,
      "step": 12
    },
    {
      "epoch": 0.010862753290160853,
      "grad_norm": 16.285877227783203,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.4247,
      "step": 13
    },
    {
      "epoch": 0.011698349697096303,
      "grad_norm": 12.89522647857666,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.2496,
      "step": 14
    },
    {
      "epoch": 0.012533946104031753,
      "grad_norm": 8.819092750549316,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.1286,
      "step": 15
    },
    {
      "epoch": 0.012533946104031753,
      "eval_loss": 0.2794611155986786,
      "eval_runtime": 42.4792,
      "eval_samples_per_second": 11.865,
      "eval_steps_per_second": 5.932,
      "step": 15
    },
    {
      "epoch": 0.013369542510967202,
      "grad_norm": 15.040021896362305,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0071,
      "step": 16
    },
    {
      "epoch": 0.014205138917902652,
      "grad_norm": 12.307514190673828,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.9801,
      "step": 17
    },
    {
      "epoch": 0.015040735324838104,
      "grad_norm": 5.802730083465576,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.8074,
      "step": 18
    },
    {
      "epoch": 0.015876331731773552,
      "grad_norm": 2.801945924758911,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.5972,
      "step": 19
    },
    {
      "epoch": 0.016711928138709004,
      "grad_norm": 29.06494903564453,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.0841,
      "step": 20
    },
    {
      "epoch": 0.016711928138709004,
      "eval_loss": 0.2781434953212738,
      "eval_runtime": 43.062,
      "eval_samples_per_second": 11.704,
      "eval_steps_per_second": 5.852,
      "step": 20
    },
    {
      "epoch": 0.017547524545644455,
      "grad_norm": 12.404900550842285,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.9451,
      "step": 21
    },
    {
      "epoch": 0.018383120952579903,
      "grad_norm": 39.48596954345703,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.9458,
      "step": 22
    },
    {
      "epoch": 0.019218717359515355,
      "grad_norm": 13.155956268310547,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.5234,
      "step": 23
    },
    {
      "epoch": 0.020054313766450803,
      "grad_norm": 9.780112266540527,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.1729,
      "step": 24
    },
    {
      "epoch": 0.020889910173386254,
      "grad_norm": 4.1454315185546875,
      "learning_rate": 0.0,
      "loss": 0.8265,
      "step": 25
    },
    {
      "epoch": 0.020889910173386254,
      "eval_loss": 0.26856350898742676,
      "eval_runtime": 43.1839,
      "eval_samples_per_second": 11.671,
      "eval_steps_per_second": 5.836,
      "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": 1648697042534400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}