{
  "best_metric": 1.0717943906784058,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.34916201117318435,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006983240223463687,
      "eval_loss": 1.370945930480957,
      "eval_runtime": 51.907,
      "eval_samples_per_second": 11.617,
      "eval_steps_per_second": 2.909,
      "step": 1
    },
    {
      "epoch": 0.006983240223463687,
      "grad_norm": 0.8086255788803101,
      "learning_rate": 4.34e-05,
      "loss": 1.074,
      "step": 10
    },
    {
      "epoch": 0.013966480446927373,
      "grad_norm": 0.5126949548721313,
      "learning_rate": 8.68e-05,
      "loss": 0.9041,
      "step": 20
    },
    {
      "epoch": 0.02094972067039106,
      "grad_norm": 0.6224434971809387,
      "learning_rate": 0.0001302,
      "loss": 0.9133,
      "step": 30
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 0.596337616443634,
      "learning_rate": 0.0001736,
      "loss": 0.8771,
      "step": 40
    },
    {
      "epoch": 0.034916201117318434,
      "grad_norm": 1.162047266960144,
      "learning_rate": 0.000217,
      "loss": 2.273,
      "step": 50
    },
    {
      "epoch": 0.034916201117318434,
      "eval_loss": 1.2856680154800415,
      "eval_runtime": 51.8319,
      "eval_samples_per_second": 11.634,
      "eval_steps_per_second": 2.913,
      "step": 50
    },
    {
      "epoch": 0.04189944134078212,
      "grad_norm": 0.47395944595336914,
      "learning_rate": 0.00021673569945319091,
      "loss": 0.9326,
      "step": 60
    },
    {
      "epoch": 0.04888268156424581,
      "grad_norm": 0.45159703493118286,
      "learning_rate": 0.00021594408545846038,
      "loss": 0.864,
      "step": 70
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 0.48672589659690857,
      "learning_rate": 0.0002146290146796179,
      "loss": 0.9053,
      "step": 80
    },
    {
      "epoch": 0.06284916201117319,
      "grad_norm": 0.6035557389259338,
      "learning_rate": 0.0002127968940093076,
      "loss": 0.9917,
      "step": 90
    },
    {
      "epoch": 0.06983240223463687,
      "grad_norm": 1.352277398109436,
      "learning_rate": 0.00021045664935527106,
      "loss": 2.3177,
      "step": 100
    },
    {
      "epoch": 0.06983240223463687,
      "eval_loss": 1.2862142324447632,
      "eval_runtime": 51.6109,
      "eval_samples_per_second": 11.684,
      "eval_steps_per_second": 2.926,
      "step": 100
    },
    {
      "epoch": 0.07681564245810056,
      "grad_norm": 0.5764887928962708,
      "learning_rate": 0.00020761968215422217,
      "loss": 0.9639,
      "step": 110
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 0.45929816365242004,
      "learning_rate": 0.00020429981382519356,
      "loss": 0.9454,
      "step": 120
    },
    {
      "epoch": 0.09078212290502793,
      "grad_norm": 0.5289813280105591,
      "learning_rate": 0.00020051321843297219,
      "loss": 0.8689,
      "step": 130
    },
    {
      "epoch": 0.09776536312849161,
      "grad_norm": 0.5550933480262756,
      "learning_rate": 0.0001962783438896818,
      "loss": 0.8495,
      "step": 140
    },
    {
      "epoch": 0.10474860335195531,
      "grad_norm": 1.3829443454742432,
      "learning_rate": 0.0001916158220784091,
      "loss": 2.1619,
      "step": 150
    },
    {
      "epoch": 0.10474860335195531,
      "eval_loss": 1.2346261739730835,
      "eval_runtime": 51.8194,
      "eval_samples_per_second": 11.637,
      "eval_steps_per_second": 2.914,
      "step": 150
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 0.4873850345611572,
      "learning_rate": 0.00018654836833674362,
      "loss": 0.9312,
      "step": 160
    },
    {
      "epoch": 0.11871508379888268,
      "grad_norm": 0.4591498076915741,
      "learning_rate": 0.0001811006707899361,
      "loss": 0.8553,
      "step": 170
    },
    {
      "epoch": 0.12569832402234637,
      "grad_norm": 0.44848743081092834,
      "learning_rate": 0.0001752992700728339,
      "loss": 0.8601,
      "step": 180
    },
    {
      "epoch": 0.13268156424581007,
      "grad_norm": 0.49805349111557007,
      "learning_rate": 0.00016917243002657602,
      "loss": 0.7799,
      "step": 190
    },
    {
      "epoch": 0.13966480446927373,
      "grad_norm": 1.24271821975708,
      "learning_rate": 0.00016275,
      "loss": 1.9841,
      "step": 200
    },
    {
      "epoch": 0.13966480446927373,
      "eval_loss": 1.2006936073303223,
      "eval_runtime": 51.8223,
      "eval_samples_per_second": 11.636,
      "eval_steps_per_second": 2.914,
      "step": 200
    },
    {
      "epoch": 0.14664804469273743,
      "grad_norm": 0.45036932826042175,
      "learning_rate": 0.0001560632694266149,
      "loss": 0.9129,
      "step": 210
    },
    {
      "epoch": 0.15363128491620112,
      "grad_norm": 0.4322090446949005,
      "learning_rate": 0.00014914481538562646,
      "loss": 0.9577,
      "step": 220
    },
    {
      "epoch": 0.16061452513966482,
      "grad_norm": 0.4544154703617096,
      "learning_rate": 0.0001420283438896818,
      "loss": 0.7483,
      "step": 230
    },
    {
      "epoch": 0.16759776536312848,
      "grad_norm": 0.6254767179489136,
      "learning_rate": 0.00013474852567256393,
      "loss": 0.961,
      "step": 240
    },
    {
      "epoch": 0.17458100558659218,
      "grad_norm": 1.0982528924942017,
      "learning_rate": 0.00012734082727686196,
      "loss": 2.2834,
      "step": 250
    },
    {
      "epoch": 0.17458100558659218,
      "eval_loss": 1.151829481124878,
      "eval_runtime": 51.8371,
      "eval_samples_per_second": 11.633,
      "eval_steps_per_second": 2.913,
      "step": 250
    },
    {
      "epoch": 0.18156424581005587,
      "grad_norm": 0.49490973353385925,
      "learning_rate": 0.0001198413382645404,
      "loss": 0.9051,
      "step": 260
    },
    {
      "epoch": 0.18854748603351956,
      "grad_norm": 0.419166624546051,
      "learning_rate": 0.00011228659539222137,
      "loss": 0.856,
      "step": 270
    },
    {
      "epoch": 0.19553072625698323,
      "grad_norm": 0.44810253381729126,
      "learning_rate": 0.00010471340460777866,
      "loss": 0.772,
      "step": 280
    },
    {
      "epoch": 0.20251396648044692,
      "grad_norm": 0.5431365370750427,
      "learning_rate": 9.715866173545961e-05,
      "loss": 0.8117,
      "step": 290
    },
    {
      "epoch": 0.20949720670391062,
      "grad_norm": 1.623485803604126,
      "learning_rate": 8.965917272313806e-05,
      "loss": 1.9584,
      "step": 300
    },
    {
      "epoch": 0.20949720670391062,
      "eval_loss": 1.1206214427947998,
      "eval_runtime": 51.6387,
      "eval_samples_per_second": 11.677,
      "eval_steps_per_second": 2.924,
      "step": 300
    },
    {
      "epoch": 0.2164804469273743,
      "grad_norm": 0.4230874478816986,
      "learning_rate": 8.225147432743606e-05,
      "loss": 0.9144,
      "step": 310
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 0.41244614124298096,
      "learning_rate": 7.497165611031821e-05,
      "loss": 0.8197,
      "step": 320
    },
    {
      "epoch": 0.23044692737430167,
      "grad_norm": 0.46321332454681396,
      "learning_rate": 6.785518461437353e-05,
      "loss": 0.8108,
      "step": 330
    },
    {
      "epoch": 0.23743016759776536,
      "grad_norm": 0.4879332184791565,
      "learning_rate": 6.093673057338509e-05,
      "loss": 0.8025,
      "step": 340
    },
    {
      "epoch": 0.24441340782122906,
      "grad_norm": 1.3698660135269165,
      "learning_rate": 5.4250000000000024e-05,
      "loss": 2.2907,
      "step": 350
    },
    {
      "epoch": 0.24441340782122906,
      "eval_loss": 1.0982829332351685,
      "eval_runtime": 51.8499,
      "eval_samples_per_second": 11.63,
      "eval_steps_per_second": 2.912,
      "step": 350
    },
    {
      "epoch": 0.25139664804469275,
      "grad_norm": 0.40256136655807495,
      "learning_rate": 4.782756997342398e-05,
      "loss": 0.8455,
      "step": 360
    },
    {
      "epoch": 0.25837988826815644,
      "grad_norm": 0.4019988775253296,
      "learning_rate": 4.170072992716607e-05,
      "loss": 0.8504,
      "step": 370
    },
    {
      "epoch": 0.26536312849162014,
      "grad_norm": 0.46585512161254883,
      "learning_rate": 3.5899329210063916e-05,
      "loss": 0.7688,
      "step": 380
    },
    {
      "epoch": 0.2723463687150838,
      "grad_norm": 0.49366164207458496,
      "learning_rate": 3.045163166325637e-05,
      "loss": 0.9192,
      "step": 390
    },
    {
      "epoch": 0.27932960893854747,
      "grad_norm": 1.1542916297912598,
      "learning_rate": 2.5384177921590895e-05,
      "loss": 2.3411,
      "step": 400
    },
    {
      "epoch": 0.27932960893854747,
      "eval_loss": 1.0796287059783936,
      "eval_runtime": 51.6139,
      "eval_samples_per_second": 11.683,
      "eval_steps_per_second": 2.926,
      "step": 400
    },
    {
      "epoch": 0.28631284916201116,
      "grad_norm": 0.40678611397743225,
      "learning_rate": 2.0721656110318213e-05,
      "loss": 0.8682,
      "step": 410
    },
    {
      "epoch": 0.29329608938547486,
      "grad_norm": 0.38841360807418823,
      "learning_rate": 1.6486781567027783e-05,
      "loss": 0.797,
      "step": 420
    },
    {
      "epoch": 0.30027932960893855,
      "grad_norm": 0.4177733361721039,
      "learning_rate": 1.2700186174806422e-05,
      "loss": 0.7461,
      "step": 430
    },
    {
      "epoch": 0.30726256983240224,
      "grad_norm": 0.5100810527801514,
      "learning_rate": 9.380317845777794e-06,
      "loss": 0.8731,
      "step": 440
    },
    {
      "epoch": 0.31424581005586594,
      "grad_norm": 1.1657980680465698,
      "learning_rate": 6.543350644728947e-06,
      "loss": 2.3673,
      "step": 450
    },
    {
      "epoch": 0.31424581005586594,
      "eval_loss": 1.072546362876892,
      "eval_runtime": 51.6984,
      "eval_samples_per_second": 11.664,
      "eval_steps_per_second": 2.921,
      "step": 450
    },
    {
      "epoch": 0.32122905027932963,
      "grad_norm": 0.3935563862323761,
      "learning_rate": 4.2031059906924e-06,
      "loss": 0.8383,
      "step": 460
    },
    {
      "epoch": 0.32821229050279327,
      "grad_norm": 0.3855022192001343,
      "learning_rate": 2.3709853203820825e-06,
      "loss": 0.7788,
      "step": 470
    },
    {
      "epoch": 0.33519553072625696,
      "grad_norm": 0.4132440984249115,
      "learning_rate": 1.0559145415396157e-06,
      "loss": 0.7524,
      "step": 480
    },
    {
      "epoch": 0.34217877094972066,
      "grad_norm": 0.4790831208229065,
      "learning_rate": 2.643005468090745e-07,
      "loss": 0.8183,
      "step": 490
    },
    {
      "epoch": 0.34916201117318435,
      "grad_norm": 1.258919596672058,
      "learning_rate": 0.0,
      "loss": 2.1397,
      "step": 500
    },
    {
      "epoch": 0.34916201117318435,
      "eval_loss": 1.0717943906784058,
      "eval_runtime": 52.0261,
      "eval_samples_per_second": 11.59,
      "eval_steps_per_second": 2.902,
      "step": 500
    }
  ],
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.408558478917632e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}