{
  "best_metric": 1.151829481124878,
  "best_model_checkpoint": "miner_id_24/checkpoint-250",
  "epoch": 0.17458100558659218,
  "eval_steps": 50,
  "global_step": 250,
  "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
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.06500940529664e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}