{
  "best_metric": 1.39730966091156,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.9237875288683602,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03695150115473441,
      "grad_norm": 1.0628507137298584,
      "learning_rate": 5e-05,
      "loss": 2.134,
      "step": 1
    },
    {
      "epoch": 0.03695150115473441,
      "eval_loss": 2.0157902240753174,
      "eval_runtime": 5.591,
      "eval_samples_per_second": 32.552,
      "eval_steps_per_second": 4.114,
      "step": 1
    },
    {
      "epoch": 0.07390300230946882,
      "grad_norm": 1.1720733642578125,
      "learning_rate": 0.0001,
      "loss": 2.0829,
      "step": 2
    },
    {
      "epoch": 0.11085450346420324,
      "grad_norm": 1.1043386459350586,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.015,
      "step": 3
    },
    {
      "epoch": 0.14780600461893764,
      "grad_norm": 1.0133167505264282,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.8927,
      "step": 4
    },
    {
      "epoch": 0.18475750577367206,
      "grad_norm": 1.1658165454864502,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.7146,
      "step": 5
    },
    {
      "epoch": 0.22170900692840648,
      "grad_norm": 0.944509744644165,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.5414,
      "step": 6
    },
    {
      "epoch": 0.2586605080831409,
      "grad_norm": 0.613703727722168,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.4056,
      "step": 7
    },
    {
      "epoch": 0.2956120092378753,
      "grad_norm": 0.8270657658576965,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6956,
      "step": 8
    },
    {
      "epoch": 0.3325635103926097,
      "grad_norm": 0.49155479669570923,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.6785,
      "step": 9
    },
    {
      "epoch": 0.3695150115473441,
      "grad_norm": 0.48842838406562805,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5975,
      "step": 10
    },
    {
      "epoch": 0.4064665127020785,
      "grad_norm": 0.5849675536155701,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.5599,
      "step": 11
    },
    {
      "epoch": 0.44341801385681295,
      "grad_norm": 0.622815728187561,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.5254,
      "step": 12
    },
    {
      "epoch": 0.48036951501154734,
      "grad_norm": 0.526707112789154,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.3566,
      "step": 13
    },
    {
      "epoch": 0.5173210161662818,
      "grad_norm": 0.3933887481689453,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.4329,
      "step": 14
    },
    {
      "epoch": 0.5542725173210161,
      "grad_norm": 0.5503090620040894,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.5994,
      "step": 15
    },
    {
      "epoch": 0.5912240184757506,
      "grad_norm": 0.5241612195968628,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.5383,
      "step": 16
    },
    {
      "epoch": 0.628175519630485,
      "grad_norm": 0.44455692172050476,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.5573,
      "step": 17
    },
    {
      "epoch": 0.6651270207852193,
      "grad_norm": 0.36662575602531433,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5157,
      "step": 18
    },
    {
      "epoch": 0.7020785219399538,
      "grad_norm": 0.3800973892211914,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.4676,
      "step": 19
    },
    {
      "epoch": 0.7390300230946882,
      "grad_norm": 0.5022615194320679,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3377,
      "step": 20
    },
    {
      "epoch": 0.7759815242494227,
      "grad_norm": 0.33681997656822205,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.3919,
      "step": 21
    },
    {
      "epoch": 0.812933025404157,
      "grad_norm": 0.3332096040248871,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.5652,
      "step": 22
    },
    {
      "epoch": 0.8498845265588915,
      "grad_norm": 0.3324725329875946,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.4968,
      "step": 23
    },
    {
      "epoch": 0.8868360277136259,
      "grad_norm": 0.3355538249015808,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.4671,
      "step": 24
    },
    {
      "epoch": 0.9237875288683602,
      "grad_norm": 0.33890247344970703,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.4538,
      "step": 25
    },
    {
      "epoch": 0.9237875288683602,
      "eval_loss": 1.39730966091156,
      "eval_runtime": 5.5764,
      "eval_samples_per_second": 32.638,
      "eval_steps_per_second": 4.125,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.822877455843328e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}