{
  "best_metric": 0.19602450728416443,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.14919806042521447,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005967922417008579,
      "grad_norm": 7.630735397338867,
      "learning_rate": 5e-05,
      "loss": 11.2996,
      "step": 1
    },
    {
      "epoch": 0.005967922417008579,
      "eval_loss": 14.502853393554688,
      "eval_runtime": 30.9622,
      "eval_samples_per_second": 36.464,
      "eval_steps_per_second": 4.586,
      "step": 1
    },
    {
      "epoch": 0.011935844834017158,
      "grad_norm": 8.498875617980957,
      "learning_rate": 0.0001,
      "loss": 13.3156,
      "step": 2
    },
    {
      "epoch": 0.017903767251025736,
      "grad_norm": 10.48371410369873,
      "learning_rate": 9.989294616193017e-05,
      "loss": 14.6208,
      "step": 3
    },
    {
      "epoch": 0.023871689668034317,
      "grad_norm": 14.176517486572266,
      "learning_rate": 9.957224306869053e-05,
      "loss": 12.6207,
      "step": 4
    },
    {
      "epoch": 0.029839612085042894,
      "grad_norm": 18.65481185913086,
      "learning_rate": 9.903926402016153e-05,
      "loss": 9.486,
      "step": 5
    },
    {
      "epoch": 0.03580753450205147,
      "grad_norm": 23.32438087463379,
      "learning_rate": 9.829629131445342e-05,
      "loss": 6.2831,
      "step": 6
    },
    {
      "epoch": 0.04177545691906005,
      "grad_norm": 19.06107521057129,
      "learning_rate": 9.73465064747553e-05,
      "loss": 3.8596,
      "step": 7
    },
    {
      "epoch": 0.047743379336068634,
      "grad_norm": 18.039409637451172,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0305,
      "step": 8
    },
    {
      "epoch": 0.05371130175307721,
      "grad_norm": 13.042880058288574,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.6457,
      "step": 9
    },
    {
      "epoch": 0.05967922417008579,
      "grad_norm": 17.44416618347168,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.4549,
      "step": 10
    },
    {
      "epoch": 0.06564714658709436,
      "grad_norm": 14.713529586791992,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.2746,
      "step": 11
    },
    {
      "epoch": 0.07161506900410294,
      "grad_norm": 1.3361420631408691,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.119,
      "step": 12
    },
    {
      "epoch": 0.07758299142111152,
      "grad_norm": 21.481016159057617,
      "learning_rate": 8.759199037394887e-05,
      "loss": 4.3288,
      "step": 13
    },
    {
      "epoch": 0.0835509138381201,
      "grad_norm": 24.79412269592285,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.7187,
      "step": 14
    },
    {
      "epoch": 0.08951883625512869,
      "grad_norm": 8.959016799926758,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.8043,
      "step": 15
    },
    {
      "epoch": 0.09548675867213727,
      "grad_norm": 3.256594181060791,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.2179,
      "step": 16
    },
    {
      "epoch": 0.10145468108914583,
      "grad_norm": 1.7809871435165405,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1289,
      "step": 17
    },
    {
      "epoch": 0.10742260350615442,
      "grad_norm": 0.3080448806285858,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0303,
      "step": 18
    },
    {
      "epoch": 0.113390525923163,
      "grad_norm": 0.23879069089889526,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0308,
      "step": 19
    },
    {
      "epoch": 0.11935844834017158,
      "grad_norm": 0.25249990820884705,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0221,
      "step": 20
    },
    {
      "epoch": 0.12532637075718014,
      "grad_norm": 0.3994295299053192,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0354,
      "step": 21
    },
    {
      "epoch": 0.13129429317418873,
      "grad_norm": 0.4217870235443115,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0323,
      "step": 22
    },
    {
      "epoch": 0.1372622155911973,
      "grad_norm": 0.30424413084983826,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0254,
      "step": 23
    },
    {
      "epoch": 0.1432301380082059,
      "grad_norm": 0.30896347761154175,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0062,
      "step": 24
    },
    {
      "epoch": 0.14919806042521447,
      "grad_norm": 0.1574530303478241,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0031,
      "step": 25
    },
    {
      "epoch": 0.14919806042521447,
      "eval_loss": 0.19602450728416443,
      "eval_runtime": 30.9735,
      "eval_samples_per_second": 36.45,
      "eval_steps_per_second": 4.585,
      "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": 2.812028905324544e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}