{
  "best_metric": 0.14917609095573425,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.31695721077654515,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001584786053882726,
      "eval_loss": 2.4650232791900635,
      "eval_runtime": 17.9303,
      "eval_samples_per_second": 11.099,
      "eval_steps_per_second": 2.789,
      "step": 1
    },
    {
      "epoch": 0.01584786053882726,
      "grad_norm": 20.75074577331543,
      "learning_rate": 5.095e-06,
      "loss": 2.0589,
      "step": 10
    },
    {
      "epoch": 0.03169572107765452,
      "grad_norm": 9.49898624420166,
      "learning_rate": 1.019e-05,
      "loss": 1.5745,
      "step": 20
    },
    {
      "epoch": 0.04754358161648178,
      "grad_norm": 3.601550817489624,
      "learning_rate": 9.623888888888889e-06,
      "loss": 0.3848,
      "step": 30
    },
    {
      "epoch": 0.06339144215530904,
      "grad_norm": 1.8625597953796387,
      "learning_rate": 9.057777777777777e-06,
      "loss": 0.1806,
      "step": 40
    },
    {
      "epoch": 0.07923930269413629,
      "grad_norm": 2.3159828186035156,
      "learning_rate": 8.491666666666667e-06,
      "loss": 0.2595,
      "step": 50
    },
    {
      "epoch": 0.07923930269413629,
      "eval_loss": 0.1808389574289322,
      "eval_runtime": 18.1494,
      "eval_samples_per_second": 10.965,
      "eval_steps_per_second": 2.755,
      "step": 50
    },
    {
      "epoch": 0.09508716323296355,
      "grad_norm": 1.0372514724731445,
      "learning_rate": 7.925555555555557e-06,
      "loss": 0.1413,
      "step": 60
    },
    {
      "epoch": 0.1109350237717908,
      "grad_norm": 0.9390221238136292,
      "learning_rate": 7.359444444444445e-06,
      "loss": 0.1367,
      "step": 70
    },
    {
      "epoch": 0.12678288431061807,
      "grad_norm": 0.9148114323616028,
      "learning_rate": 6.793333333333333e-06,
      "loss": 0.178,
      "step": 80
    },
    {
      "epoch": 0.14263074484944532,
      "grad_norm": 1.1273529529571533,
      "learning_rate": 6.227222222222223e-06,
      "loss": 0.1676,
      "step": 90
    },
    {
      "epoch": 0.15847860538827258,
      "grad_norm": 1.4674519300460815,
      "learning_rate": 5.661111111111112e-06,
      "loss": 0.1947,
      "step": 100
    },
    {
      "epoch": 0.15847860538827258,
      "eval_loss": 0.15586192905902863,
      "eval_runtime": 18.201,
      "eval_samples_per_second": 10.933,
      "eval_steps_per_second": 2.747,
      "step": 100
    },
    {
      "epoch": 0.17432646592709986,
      "grad_norm": 1.1320366859436035,
      "learning_rate": 5.095e-06,
      "loss": 0.1502,
      "step": 110
    },
    {
      "epoch": 0.1901743264659271,
      "grad_norm": 1.3633605241775513,
      "learning_rate": 4.5288888888888885e-06,
      "loss": 0.153,
      "step": 120
    },
    {
      "epoch": 0.20602218700475436,
      "grad_norm": 21.038341522216797,
      "learning_rate": 3.9627777777777784e-06,
      "loss": 0.1643,
      "step": 130
    },
    {
      "epoch": 0.2218700475435816,
      "grad_norm": 3.7287445068359375,
      "learning_rate": 3.3966666666666666e-06,
      "loss": 0.1585,
      "step": 140
    },
    {
      "epoch": 0.23771790808240886,
      "grad_norm": 1.4687708616256714,
      "learning_rate": 2.830555555555556e-06,
      "loss": 0.1692,
      "step": 150
    },
    {
      "epoch": 0.23771790808240886,
      "eval_loss": 0.15055163204669952,
      "eval_runtime": 18.1953,
      "eval_samples_per_second": 10.937,
      "eval_steps_per_second": 2.748,
      "step": 150
    },
    {
      "epoch": 0.25356576862123614,
      "grad_norm": 1.835580825805664,
      "learning_rate": 2.2644444444444443e-06,
      "loss": 0.1311,
      "step": 160
    },
    {
      "epoch": 0.2694136291600634,
      "grad_norm": 1.0110487937927246,
      "learning_rate": 1.6983333333333333e-06,
      "loss": 0.1496,
      "step": 170
    },
    {
      "epoch": 0.28526148969889065,
      "grad_norm": 5.238423824310303,
      "learning_rate": 1.1322222222222221e-06,
      "loss": 0.162,
      "step": 180
    },
    {
      "epoch": 0.3011093502377179,
      "grad_norm": 0.5642182230949402,
      "learning_rate": 5.661111111111111e-07,
      "loss": 0.1568,
      "step": 190
    },
    {
      "epoch": 0.31695721077654515,
      "grad_norm": 1.1575543880462646,
      "learning_rate": 0.0,
      "loss": 0.1739,
      "step": 200
    },
    {
      "epoch": 0.31695721077654515,
      "eval_loss": 0.14917609095573425,
      "eval_runtime": 18.2576,
      "eval_samples_per_second": 10.9,
      "eval_steps_per_second": 2.739,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 5.59508141113344e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}