{
  "best_metric": 0.151916965842247,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.7889546351084813,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03155818540433925,
      "grad_norm": 17.565650939941406,
      "learning_rate": 5e-05,
      "loss": 4.6439,
      "step": 1
    },
    {
      "epoch": 0.03155818540433925,
      "eval_loss": 4.760210037231445,
      "eval_runtime": 6.4519,
      "eval_samples_per_second": 33.168,
      "eval_steps_per_second": 4.185,
      "step": 1
    },
    {
      "epoch": 0.0631163708086785,
      "grad_norm": 17.935976028442383,
      "learning_rate": 0.0001,
      "loss": 4.4718,
      "step": 2
    },
    {
      "epoch": 0.09467455621301775,
      "grad_norm": 16.03348159790039,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.873,
      "step": 3
    },
    {
      "epoch": 0.126232741617357,
      "grad_norm": 9.228546142578125,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.7819,
      "step": 4
    },
    {
      "epoch": 0.15779092702169625,
      "grad_norm": 6.207879543304443,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.7804,
      "step": 5
    },
    {
      "epoch": 0.1893491124260355,
      "grad_norm": 2.618436336517334,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.3484,
      "step": 6
    },
    {
      "epoch": 0.22090729783037474,
      "grad_norm": 0.9351277947425842,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.2636,
      "step": 7
    },
    {
      "epoch": 0.252465483234714,
      "grad_norm": 1.046271800994873,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2464,
      "step": 8
    },
    {
      "epoch": 0.28402366863905326,
      "grad_norm": 0.6872361898422241,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.1927,
      "step": 9
    },
    {
      "epoch": 0.3155818540433925,
      "grad_norm": 0.7025558352470398,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.161,
      "step": 10
    },
    {
      "epoch": 0.34714003944773175,
      "grad_norm": 1.1809933185577393,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.2081,
      "step": 11
    },
    {
      "epoch": 0.378698224852071,
      "grad_norm": 1.0617340803146362,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.1448,
      "step": 12
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 1.0864554643630981,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.1972,
      "step": 13
    },
    {
      "epoch": 0.4418145956607495,
      "grad_norm": 0.6403315663337708,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1312,
      "step": 14
    },
    {
      "epoch": 0.47337278106508873,
      "grad_norm": 1.6343156099319458,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.1939,
      "step": 15
    },
    {
      "epoch": 0.504930966469428,
      "grad_norm": 2.0772101879119873,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.2926,
      "step": 16
    },
    {
      "epoch": 0.5364891518737672,
      "grad_norm": 0.8417810201644897,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1349,
      "step": 17
    },
    {
      "epoch": 0.5680473372781065,
      "grad_norm": 0.8884596228599548,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1732,
      "step": 18
    },
    {
      "epoch": 0.5996055226824457,
      "grad_norm": 0.9711158275604248,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.1872,
      "step": 19
    },
    {
      "epoch": 0.631163708086785,
      "grad_norm": 0.6484895944595337,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1574,
      "step": 20
    },
    {
      "epoch": 0.6627218934911243,
      "grad_norm": 0.5051418542861938,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.1604,
      "step": 21
    },
    {
      "epoch": 0.6942800788954635,
      "grad_norm": 0.8070167899131775,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1725,
      "step": 22
    },
    {
      "epoch": 0.7258382642998028,
      "grad_norm": 0.9816901087760925,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1586,
      "step": 23
    },
    {
      "epoch": 0.757396449704142,
      "grad_norm": 0.9378854632377625,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.2083,
      "step": 24
    },
    {
      "epoch": 0.7889546351084813,
      "grad_norm": 0.6547884345054626,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.1263,
      "step": 25
    },
    {
      "epoch": 0.7889546351084813,
      "eval_loss": 0.151916965842247,
      "eval_runtime": 6.4349,
      "eval_samples_per_second": 33.256,
      "eval_steps_per_second": 4.196,
      "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": 2.629553998528512e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}