{
  "best_metric": 0.6429993510246277,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.05466721333880006,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002186688533552002,
      "grad_norm": 1.1105414628982544,
      "learning_rate": 5e-05,
      "loss": 0.6609,
      "step": 1
    },
    {
      "epoch": 0.002186688533552002,
      "eval_loss": 1.4441356658935547,
      "eval_runtime": 182.5843,
      "eval_samples_per_second": 16.874,
      "eval_steps_per_second": 2.114,
      "step": 1
    },
    {
      "epoch": 0.004373377067104004,
      "grad_norm": 1.3735562562942505,
      "learning_rate": 0.0001,
      "loss": 0.8495,
      "step": 2
    },
    {
      "epoch": 0.006560065600656006,
      "grad_norm": 1.4012031555175781,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.935,
      "step": 3
    },
    {
      "epoch": 0.008746754134208008,
      "grad_norm": 0.6011267304420471,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.7601,
      "step": 4
    },
    {
      "epoch": 0.01093344266776001,
      "grad_norm": 0.5295389890670776,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.7598,
      "step": 5
    },
    {
      "epoch": 0.013120131201312012,
      "grad_norm": 0.6502489447593689,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.7563,
      "step": 6
    },
    {
      "epoch": 0.015306819734864016,
      "grad_norm": 0.5572352409362793,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.7585,
      "step": 7
    },
    {
      "epoch": 0.017493508268416016,
      "grad_norm": 0.4851221740245819,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.7714,
      "step": 8
    },
    {
      "epoch": 0.01968019680196802,
      "grad_norm": 0.406841903924942,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.7604,
      "step": 9
    },
    {
      "epoch": 0.02186688533552002,
      "grad_norm": 0.41418033838272095,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7886,
      "step": 10
    },
    {
      "epoch": 0.024053573869072024,
      "grad_norm": 0.4525168836116791,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.8056,
      "step": 11
    },
    {
      "epoch": 0.026240262402624025,
      "grad_norm": 0.5825612545013428,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.8127,
      "step": 12
    },
    {
      "epoch": 0.02842695093617603,
      "grad_norm": 0.3739285171031952,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.3493,
      "step": 13
    },
    {
      "epoch": 0.030613639469728032,
      "grad_norm": 0.20394007861614227,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.4709,
      "step": 14
    },
    {
      "epoch": 0.03280032800328003,
      "grad_norm": 0.21499967575073242,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.5838,
      "step": 15
    },
    {
      "epoch": 0.03498701653683203,
      "grad_norm": 0.18819545209407806,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.5984,
      "step": 16
    },
    {
      "epoch": 0.03717370507038404,
      "grad_norm": 0.21380701661109924,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.5902,
      "step": 17
    },
    {
      "epoch": 0.03936039360393604,
      "grad_norm": 0.22303147614002228,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6519,
      "step": 18
    },
    {
      "epoch": 0.04154708213748804,
      "grad_norm": 0.2147863209247589,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.6503,
      "step": 19
    },
    {
      "epoch": 0.04373377067104004,
      "grad_norm": 0.2406228929758072,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6872,
      "step": 20
    },
    {
      "epoch": 0.04592045920459205,
      "grad_norm": 0.2548230290412903,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.6664,
      "step": 21
    },
    {
      "epoch": 0.04810714773814405,
      "grad_norm": 0.30359193682670593,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.6854,
      "step": 22
    },
    {
      "epoch": 0.05029383627169605,
      "grad_norm": 0.41962817311286926,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.7442,
      "step": 23
    },
    {
      "epoch": 0.05248052480524805,
      "grad_norm": 0.45455101132392883,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.7666,
      "step": 24
    },
    {
      "epoch": 0.05466721333880006,
      "grad_norm": 0.5619322061538696,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.7485,
      "step": 25
    },
    {
      "epoch": 0.05466721333880006,
      "eval_loss": 0.6429993510246277,
      "eval_runtime": 180.7656,
      "eval_samples_per_second": 17.044,
      "eval_steps_per_second": 2.135,
      "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": 3.4068723732054016e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}