{
  "best_metric": 1.7541568279266357,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.02689437235258522,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010757748941034088,
      "grad_norm": 3.2264199256896973,
      "learning_rate": 5e-05,
      "loss": 1.7643,
      "step": 1
    },
    {
      "epoch": 0.0010757748941034088,
      "eval_loss": 2.036266326904297,
      "eval_runtime": 185.7404,
      "eval_samples_per_second": 33.719,
      "eval_steps_per_second": 4.216,
      "step": 1
    },
    {
      "epoch": 0.0021515497882068175,
      "grad_norm": 2.033907651901245,
      "learning_rate": 0.0001,
      "loss": 1.865,
      "step": 2
    },
    {
      "epoch": 0.0032273246823102267,
      "grad_norm": 1.849198341369629,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.7607,
      "step": 3
    },
    {
      "epoch": 0.004303099576413635,
      "grad_norm": 1.3527692556381226,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.756,
      "step": 4
    },
    {
      "epoch": 0.005378874470517044,
      "grad_norm": 1.7999598979949951,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.763,
      "step": 5
    },
    {
      "epoch": 0.006454649364620453,
      "grad_norm": 0.7398207187652588,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.7906,
      "step": 6
    },
    {
      "epoch": 0.007530424258723862,
      "grad_norm": 0.732106626033783,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.8386,
      "step": 7
    },
    {
      "epoch": 0.00860619915282727,
      "grad_norm": 0.6868982911109924,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7422,
      "step": 8
    },
    {
      "epoch": 0.00968197404693068,
      "grad_norm": 0.7857877016067505,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.7897,
      "step": 9
    },
    {
      "epoch": 0.010757748941034088,
      "grad_norm": 0.7129908800125122,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8489,
      "step": 10
    },
    {
      "epoch": 0.011833523835137498,
      "grad_norm": 0.7833899259567261,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8363,
      "step": 11
    },
    {
      "epoch": 0.012909298729240907,
      "grad_norm": 0.9306832551956177,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.0062,
      "step": 12
    },
    {
      "epoch": 0.013985073623344316,
      "grad_norm": 1.6075146198272705,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.6619,
      "step": 13
    },
    {
      "epoch": 0.015060848517447724,
      "grad_norm": 1.3217817544937134,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6411,
      "step": 14
    },
    {
      "epoch": 0.016136623411551133,
      "grad_norm": 1.06163489818573,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.6299,
      "step": 15
    },
    {
      "epoch": 0.01721239830565454,
      "grad_norm": 0.7463550567626953,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.6279,
      "step": 16
    },
    {
      "epoch": 0.01828817319975795,
      "grad_norm": 0.6530005931854248,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.6898,
      "step": 17
    },
    {
      "epoch": 0.01936394809386136,
      "grad_norm": 0.6885256767272949,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7274,
      "step": 18
    },
    {
      "epoch": 0.02043972298796477,
      "grad_norm": 0.6047241687774658,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.7427,
      "step": 19
    },
    {
      "epoch": 0.021515497882068177,
      "grad_norm": 0.6158456802368164,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.7781,
      "step": 20
    },
    {
      "epoch": 0.022591272776171584,
      "grad_norm": 0.6341370344161987,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.7478,
      "step": 21
    },
    {
      "epoch": 0.023667047670274995,
      "grad_norm": 0.6382009387016296,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.8192,
      "step": 22
    },
    {
      "epoch": 0.024742822564378403,
      "grad_norm": 0.702714204788208,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.7944,
      "step": 23
    },
    {
      "epoch": 0.025818597458481814,
      "grad_norm": 0.7899352312088013,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.9513,
      "step": 24
    },
    {
      "epoch": 0.02689437235258522,
      "grad_norm": 1.0243830680847168,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.1505,
      "step": 25
    },
    {
      "epoch": 0.02689437235258522,
      "eval_loss": 1.7541568279266357,
      "eval_runtime": 185.7953,
      "eval_samples_per_second": 33.709,
      "eval_steps_per_second": 4.214,
      "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": 2.829012279754752e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}