{
  "best_metric": 0.0913226529955864,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.4700352526439483,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01880141010575793,
      "grad_norm": 0.7600845098495483,
      "learning_rate": 5e-05,
      "loss": 0.1707,
      "step": 1
    },
    {
      "epoch": 0.01880141010575793,
      "eval_loss": 0.4366946518421173,
      "eval_runtime": 5.0457,
      "eval_samples_per_second": 9.909,
      "eval_steps_per_second": 2.576,
      "step": 1
    },
    {
      "epoch": 0.03760282021151586,
      "grad_norm": 1.3569352626800537,
      "learning_rate": 0.0001,
      "loss": 0.2471,
      "step": 2
    },
    {
      "epoch": 0.0564042303172738,
      "grad_norm": 0.5642196536064148,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.2538,
      "step": 3
    },
    {
      "epoch": 0.07520564042303172,
      "grad_norm": 0.5840835571289062,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.2145,
      "step": 4
    },
    {
      "epoch": 0.09400705052878966,
      "grad_norm": 0.46224477887153625,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.1904,
      "step": 5
    },
    {
      "epoch": 0.1128084606345476,
      "grad_norm": 0.4062245488166809,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.1852,
      "step": 6
    },
    {
      "epoch": 0.13160987074030553,
      "grad_norm": 0.3530953526496887,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.1477,
      "step": 7
    },
    {
      "epoch": 0.15041128084606345,
      "grad_norm": 0.2826444208621979,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.1289,
      "step": 8
    },
    {
      "epoch": 0.1692126909518214,
      "grad_norm": 0.377310574054718,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.144,
      "step": 9
    },
    {
      "epoch": 0.18801410105757932,
      "grad_norm": 0.3118053078651428,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.1509,
      "step": 10
    },
    {
      "epoch": 0.20681551116333724,
      "grad_norm": 0.3501030504703522,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.1615,
      "step": 11
    },
    {
      "epoch": 0.2256169212690952,
      "grad_norm": 1.3040632009506226,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.1281,
      "step": 12
    },
    {
      "epoch": 0.2444183313748531,
      "grad_norm": 0.16963200271129608,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.068,
      "step": 13
    },
    {
      "epoch": 0.26321974148061106,
      "grad_norm": 0.21708229184150696,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0867,
      "step": 14
    },
    {
      "epoch": 0.282021151586369,
      "grad_norm": 0.134294793009758,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0941,
      "step": 15
    },
    {
      "epoch": 0.3008225616921269,
      "grad_norm": 0.12663644552230835,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0955,
      "step": 16
    },
    {
      "epoch": 0.3196239717978848,
      "grad_norm": 0.1226968914270401,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0999,
      "step": 17
    },
    {
      "epoch": 0.3384253819036428,
      "grad_norm": 0.11707764118909836,
      "learning_rate": 7.75e-05,
      "loss": 0.103,
      "step": 18
    },
    {
      "epoch": 0.3572267920094007,
      "grad_norm": 0.12075494229793549,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.1034,
      "step": 19
    },
    {
      "epoch": 0.37602820211515864,
      "grad_norm": 0.11400816589593887,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.1066,
      "step": 20
    },
    {
      "epoch": 0.39482961222091656,
      "grad_norm": 0.13738061487674713,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.1075,
      "step": 21
    },
    {
      "epoch": 0.4136310223266745,
      "grad_norm": 0.15788087248802185,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.1107,
      "step": 22
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.1624337136745453,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.118,
      "step": 23
    },
    {
      "epoch": 0.4512338425381904,
      "grad_norm": 0.18111398816108704,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.1158,
      "step": 24
    },
    {
      "epoch": 0.4700352526439483,
      "grad_norm": 0.2933941185474396,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0768,
      "step": 25
    },
    {
      "epoch": 0.4700352526439483,
      "eval_loss": 0.0913226529955864,
      "eval_runtime": 5.314,
      "eval_samples_per_second": 9.409,
      "eval_steps_per_second": 2.446,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.09221331952468e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}