{
  "best_metric": 11.929275512695312,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.20964360587002095,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008385744234800839,
      "grad_norm": 0.028302129358053207,
      "learning_rate": 5e-05,
      "loss": 11.9244,
      "step": 1
    },
    {
      "epoch": 0.008385744234800839,
      "eval_loss": 11.931392669677734,
      "eval_runtime": 1.7366,
      "eval_samples_per_second": 462.968,
      "eval_steps_per_second": 58.159,
      "step": 1
    },
    {
      "epoch": 0.016771488469601678,
      "grad_norm": 0.025225507095456123,
      "learning_rate": 0.0001,
      "loss": 11.9287,
      "step": 2
    },
    {
      "epoch": 0.025157232704402517,
      "grad_norm": 0.025965744629502296,
      "learning_rate": 9.989294616193017e-05,
      "loss": 11.9274,
      "step": 3
    },
    {
      "epoch": 0.033542976939203356,
      "grad_norm": 0.025864940136671066,
      "learning_rate": 9.957224306869053e-05,
      "loss": 11.9299,
      "step": 4
    },
    {
      "epoch": 0.041928721174004195,
      "grad_norm": 0.0286379586905241,
      "learning_rate": 9.903926402016153e-05,
      "loss": 11.9299,
      "step": 5
    },
    {
      "epoch": 0.050314465408805034,
      "grad_norm": 0.028485065326094627,
      "learning_rate": 9.829629131445342e-05,
      "loss": 11.931,
      "step": 6
    },
    {
      "epoch": 0.05870020964360587,
      "grad_norm": 0.027851169928908348,
      "learning_rate": 9.73465064747553e-05,
      "loss": 11.9301,
      "step": 7
    },
    {
      "epoch": 0.06708595387840671,
      "grad_norm": 0.02716955542564392,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9305,
      "step": 8
    },
    {
      "epoch": 0.07547169811320754,
      "grad_norm": 0.03554312884807587,
      "learning_rate": 9.484363707663442e-05,
      "loss": 11.9322,
      "step": 9
    },
    {
      "epoch": 0.08385744234800839,
      "grad_norm": 0.025717342272400856,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.9337,
      "step": 10
    },
    {
      "epoch": 0.09224318658280922,
      "grad_norm": 0.04107967019081116,
      "learning_rate": 9.157348061512727e-05,
      "loss": 11.932,
      "step": 11
    },
    {
      "epoch": 0.10062893081761007,
      "grad_norm": 0.033041615039110184,
      "learning_rate": 8.966766701456177e-05,
      "loss": 11.9331,
      "step": 12
    },
    {
      "epoch": 0.1090146750524109,
      "grad_norm": 0.03018532134592533,
      "learning_rate": 8.759199037394887e-05,
      "loss": 11.9233,
      "step": 13
    },
    {
      "epoch": 0.11740041928721175,
      "grad_norm": 0.030003391206264496,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9242,
      "step": 14
    },
    {
      "epoch": 0.12578616352201258,
      "grad_norm": 0.027340294793248177,
      "learning_rate": 8.296729075500344e-05,
      "loss": 11.9269,
      "step": 15
    },
    {
      "epoch": 0.13417190775681342,
      "grad_norm": 0.03445419296622276,
      "learning_rate": 8.043807145043604e-05,
      "loss": 11.9269,
      "step": 16
    },
    {
      "epoch": 0.14255765199161424,
      "grad_norm": 0.033826183527708054,
      "learning_rate": 7.777851165098012e-05,
      "loss": 11.9288,
      "step": 17
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 0.04148228466510773,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.9278,
      "step": 18
    },
    {
      "epoch": 0.15932914046121593,
      "grad_norm": 0.04665839672088623,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.9292,
      "step": 19
    },
    {
      "epoch": 0.16771488469601678,
      "grad_norm": 0.04396500810980797,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9288,
      "step": 20
    },
    {
      "epoch": 0.1761006289308176,
      "grad_norm": 0.04329974576830864,
      "learning_rate": 6.607197326515808e-05,
      "loss": 11.9283,
      "step": 21
    },
    {
      "epoch": 0.18448637316561844,
      "grad_norm": 0.04438428208231926,
      "learning_rate": 6.294095225512603e-05,
      "loss": 11.9338,
      "step": 22
    },
    {
      "epoch": 0.1928721174004193,
      "grad_norm": 0.052561450749635696,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 11.9309,
      "step": 23
    },
    {
      "epoch": 0.20125786163522014,
      "grad_norm": 0.048290323466062546,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 11.9308,
      "step": 24
    },
    {
      "epoch": 0.20964360587002095,
      "grad_norm": 0.04853208363056183,
      "learning_rate": 5.327015646150716e-05,
      "loss": 11.9345,
      "step": 25
    },
    {
      "epoch": 0.20964360587002095,
      "eval_loss": 11.929275512695312,
      "eval_runtime": 1.7367,
      "eval_samples_per_second": 462.955,
      "eval_steps_per_second": 58.157,
      "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": 521247129600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}