{
  "best_metric": 11.912154197692871,
  "best_model_checkpoint": "miner_id_24/checkpoint-3000",
  "epoch": 5.01356710498852,
  "eval_steps": 300,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016697975370486328,
      "eval_loss": 11.931979179382324,
      "eval_runtime": 9.6502,
      "eval_samples_per_second": 209.115,
      "eval_steps_per_second": 26.217,
      "step": 1
    },
    {
      "epoch": 0.5009392611145899,
      "grad_norm": 0.03646502271294594,
      "learning_rate": 0.00039532411114201737,
      "loss": 11.9228,
      "step": 300
    },
    {
      "epoch": 0.5009392611145899,
      "eval_loss": 11.915942192077637,
      "eval_runtime": 9.5678,
      "eval_samples_per_second": 210.917,
      "eval_steps_per_second": 26.443,
      "step": 300
    },
    {
      "epoch": 1.002713420997704,
      "grad_norm": 0.013963569886982441,
      "learning_rate": 0.00037137143523351785,
      "loss": 11.9411,
      "step": 600
    },
    {
      "epoch": 1.002713420997704,
      "eval_loss": 11.914015769958496,
      "eval_runtime": 9.5987,
      "eval_samples_per_second": 210.238,
      "eval_steps_per_second": 26.358,
      "step": 600
    },
    {
      "epoch": 1.503652682112294,
      "grad_norm": 0.016350438818335533,
      "learning_rate": 0.00032947725695636553,
      "loss": 11.9139,
      "step": 900
    },
    {
      "epoch": 1.503652682112294,
      "eval_loss": 11.91312026977539,
      "eval_runtime": 9.5664,
      "eval_samples_per_second": 210.946,
      "eval_steps_per_second": 26.447,
      "step": 900
    },
    {
      "epoch": 2.005426841995408,
      "grad_norm": 0.01071674283593893,
      "learning_rate": 0.0002740276310679829,
      "loss": 11.9376,
      "step": 1200
    },
    {
      "epoch": 2.005426841995408,
      "eval_loss": 11.912792205810547,
      "eval_runtime": 9.6853,
      "eval_samples_per_second": 208.356,
      "eval_steps_per_second": 26.122,
      "step": 1200
    },
    {
      "epoch": 2.5063661031099977,
      "grad_norm": 0.011973950080573559,
      "learning_rate": 0.00021082778171708353,
      "loss": 11.9132,
      "step": 1500
    },
    {
      "epoch": 2.5063661031099977,
      "eval_loss": 11.91252613067627,
      "eval_runtime": 9.7489,
      "eval_samples_per_second": 206.998,
      "eval_steps_per_second": 25.952,
      "step": 1500
    },
    {
      "epoch": 3.008140262993112,
      "grad_norm": 0.013220425695180893,
      "learning_rate": 0.00014649433229415587,
      "loss": 11.9376,
      "step": 1800
    },
    {
      "epoch": 3.008140262993112,
      "eval_loss": 11.91238021850586,
      "eval_runtime": 9.6136,
      "eval_samples_per_second": 209.911,
      "eval_steps_per_second": 26.317,
      "step": 1800
    },
    {
      "epoch": 3.509079524107702,
      "grad_norm": 0.013742562383413315,
      "learning_rate": 8.776258692752355e-05,
      "loss": 11.9128,
      "step": 2100
    },
    {
      "epoch": 3.509079524107702,
      "eval_loss": 11.912261962890625,
      "eval_runtime": 9.5679,
      "eval_samples_per_second": 210.914,
      "eval_steps_per_second": 26.443,
      "step": 2100
    },
    {
      "epoch": 4.010853683990816,
      "grad_norm": 0.015797816216945648,
      "learning_rate": 4.078138685887125e-05,
      "loss": 11.9377,
      "step": 2400
    },
    {
      "epoch": 4.010853683990816,
      "eval_loss": 11.91218090057373,
      "eval_runtime": 9.6462,
      "eval_samples_per_second": 209.202,
      "eval_steps_per_second": 26.228,
      "step": 2400
    },
    {
      "epoch": 4.511792945105406,
      "grad_norm": 0.012792945839464664,
      "learning_rate": 1.0469365763439531e-05,
      "loss": 11.9128,
      "step": 2700
    },
    {
      "epoch": 4.511792945105406,
      "eval_loss": 11.912158012390137,
      "eval_runtime": 9.6282,
      "eval_samples_per_second": 209.592,
      "eval_steps_per_second": 26.277,
      "step": 2700
    },
    {
      "epoch": 5.01356710498852,
      "grad_norm": 0.012090091593563557,
      "learning_rate": 0.0,
      "loss": 11.9374,
      "step": 3000
    },
    {
      "epoch": 5.01356710498852,
      "eval_loss": 11.912154197692871,
      "eval_runtime": 9.5524,
      "eval_samples_per_second": 211.256,
      "eval_steps_per_second": 26.485,
      "step": 3000
    }
  ],
  "logging_steps": 300,
  "max_steps": 3000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 300,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5671747584000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}