{
  "best_metric": 1.4591978788375854,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.016478536705940513,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006591414682376205,
      "grad_norm": 0.6790323257446289,
      "learning_rate": 5e-05,
      "loss": 1.6222,
      "step": 1
    },
    {
      "epoch": 0.0006591414682376205,
      "eval_loss": 1.836203932762146,
      "eval_runtime": 296.9586,
      "eval_samples_per_second": 34.419,
      "eval_steps_per_second": 4.304,
      "step": 1
    },
    {
      "epoch": 0.001318282936475241,
      "grad_norm": 0.6822174191474915,
      "learning_rate": 0.0001,
      "loss": 1.6474,
      "step": 2
    },
    {
      "epoch": 0.0019774244047128615,
      "grad_norm": 0.6467229127883911,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.6169,
      "step": 3
    },
    {
      "epoch": 0.002636565872950482,
      "grad_norm": 0.545185387134552,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.5051,
      "step": 4
    },
    {
      "epoch": 0.0032957073411881027,
      "grad_norm": 0.2817743420600891,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.4512,
      "step": 5
    },
    {
      "epoch": 0.003954848809425723,
      "grad_norm": 0.4623984694480896,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.4715,
      "step": 6
    },
    {
      "epoch": 0.004613990277663344,
      "grad_norm": 0.6100432872772217,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.4865,
      "step": 7
    },
    {
      "epoch": 0.005273131745900964,
      "grad_norm": 0.46749556064605713,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.5081,
      "step": 8
    },
    {
      "epoch": 0.0059322732141385845,
      "grad_norm": 0.31567704677581787,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.6606,
      "step": 9
    },
    {
      "epoch": 0.006591414682376205,
      "grad_norm": 0.45639654994010925,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8446,
      "step": 10
    },
    {
      "epoch": 0.007250556150613825,
      "grad_norm": 0.4724658727645874,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8538,
      "step": 11
    },
    {
      "epoch": 0.007909697618851446,
      "grad_norm": 0.4332147538661957,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.9509,
      "step": 12
    },
    {
      "epoch": 0.008568839087089067,
      "grad_norm": 0.2523305416107178,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.3743,
      "step": 13
    },
    {
      "epoch": 0.009227980555326688,
      "grad_norm": 0.23553816974163055,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3544,
      "step": 14
    },
    {
      "epoch": 0.009887122023564307,
      "grad_norm": 0.21183012425899506,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.3465,
      "step": 15
    },
    {
      "epoch": 0.010546263491801927,
      "grad_norm": 0.16247883439064026,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.3308,
      "step": 16
    },
    {
      "epoch": 0.011205404960039548,
      "grad_norm": 0.14963077008724213,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.3331,
      "step": 17
    },
    {
      "epoch": 0.011864546428277169,
      "grad_norm": 0.1518392562866211,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3469,
      "step": 18
    },
    {
      "epoch": 0.01252368789651479,
      "grad_norm": 0.15816082060337067,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.326,
      "step": 19
    },
    {
      "epoch": 0.01318282936475241,
      "grad_norm": 0.17692376673221588,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3788,
      "step": 20
    },
    {
      "epoch": 0.01384197083299003,
      "grad_norm": 0.19621223211288452,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.46,
      "step": 21
    },
    {
      "epoch": 0.01450111230122765,
      "grad_norm": 0.3078196048736572,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.6276,
      "step": 22
    },
    {
      "epoch": 0.015160253769465271,
      "grad_norm": 0.40529724955558777,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.6692,
      "step": 23
    },
    {
      "epoch": 0.015819395237702892,
      "grad_norm": 0.3335389792919159,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.7462,
      "step": 24
    },
    {
      "epoch": 0.016478536705940513,
      "grad_norm": 0.3342079818248749,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.7909,
      "step": 25
    },
    {
      "epoch": 0.016478536705940513,
      "eval_loss": 1.4591978788375854,
      "eval_runtime": 287.7398,
      "eval_samples_per_second": 35.522,
      "eval_steps_per_second": 4.442,
      "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": 2.629552387915776e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}