{
  "best_metric": 0.8743540048599243,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.039619651347068144,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001584786053882726,
      "grad_norm": 2.344426393508911,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.1155,
      "step": 1
    },
    {
      "epoch": 0.001584786053882726,
      "eval_loss": 4.5734944343566895,
      "eval_runtime": 3.2337,
      "eval_samples_per_second": 15.462,
      "eval_steps_per_second": 4.02,
      "step": 1
    },
    {
      "epoch": 0.003169572107765452,
      "grad_norm": 1.989837884902954,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.0433,
      "step": 2
    },
    {
      "epoch": 0.004754358161648178,
      "grad_norm": 2.0686755180358887,
      "learning_rate": 0.0001,
      "loss": 3.0158,
      "step": 3
    },
    {
      "epoch": 0.006339144215530904,
      "grad_norm": 2.5443685054779053,
      "learning_rate": 9.997376600647783e-05,
      "loss": 2.9057,
      "step": 4
    },
    {
      "epoch": 0.00792393026941363,
      "grad_norm": 2.039285659790039,
      "learning_rate": 9.989509461357426e-05,
      "loss": 2.3574,
      "step": 5
    },
    {
      "epoch": 0.009508716323296355,
      "grad_norm": 2.248792886734009,
      "learning_rate": 9.976407754861426e-05,
      "loss": 2.1331,
      "step": 6
    },
    {
      "epoch": 0.011093502377179081,
      "grad_norm": 1.847161889076233,
      "learning_rate": 9.958086757163489e-05,
      "loss": 1.762,
      "step": 7
    },
    {
      "epoch": 0.012678288431061807,
      "grad_norm": 2.0366954803466797,
      "learning_rate": 9.934567829727386e-05,
      "loss": 1.6532,
      "step": 8
    },
    {
      "epoch": 0.014263074484944533,
      "grad_norm": 2.5140931606292725,
      "learning_rate": 9.905878394570453e-05,
      "loss": 1.4923,
      "step": 9
    },
    {
      "epoch": 0.01584786053882726,
      "grad_norm": 2.7745964527130127,
      "learning_rate": 9.872051902290737e-05,
      "loss": 1.0749,
      "step": 10
    },
    {
      "epoch": 0.017432646592709985,
      "grad_norm": 2.2155520915985107,
      "learning_rate": 9.833127793065098e-05,
      "loss": 0.9472,
      "step": 11
    },
    {
      "epoch": 0.01901743264659271,
      "grad_norm": 3.2750940322875977,
      "learning_rate": 9.789151450663723e-05,
      "loss": 1.2059,
      "step": 12
    },
    {
      "epoch": 0.020602218700475437,
      "grad_norm": 7.851731777191162,
      "learning_rate": 9.740174149534693e-05,
      "loss": 1.2002,
      "step": 13
    },
    {
      "epoch": 0.022187004754358162,
      "grad_norm": 2.0609889030456543,
      "learning_rate": 9.686252995020249e-05,
      "loss": 1.0557,
      "step": 14
    },
    {
      "epoch": 0.02377179080824089,
      "grad_norm": 1.621334433555603,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.8744,
      "step": 15
    },
    {
      "epoch": 0.025356576862123614,
      "grad_norm": 1.06352961063385,
      "learning_rate": 9.563836295460398e-05,
      "loss": 0.9567,
      "step": 16
    },
    {
      "epoch": 0.02694136291600634,
      "grad_norm": 1.0080907344818115,
      "learning_rate": 9.495483482810688e-05,
      "loss": 0.9841,
      "step": 17
    },
    {
      "epoch": 0.028526148969889066,
      "grad_norm": 1.0307260751724243,
      "learning_rate": 9.422472115147382e-05,
      "loss": 0.8911,
      "step": 18
    },
    {
      "epoch": 0.030110935023771792,
      "grad_norm": 0.9563176035881042,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.8358,
      "step": 19
    },
    {
      "epoch": 0.03169572107765452,
      "grad_norm": 0.9397155046463013,
      "learning_rate": 9.2628195591462e-05,
      "loss": 0.6939,
      "step": 20
    },
    {
      "epoch": 0.03328050713153724,
      "grad_norm": 0.9912440180778503,
      "learning_rate": 9.176364518546989e-05,
      "loss": 0.6091,
      "step": 21
    },
    {
      "epoch": 0.03486529318541997,
      "grad_norm": 0.9592384099960327,
      "learning_rate": 9.08562300137157e-05,
      "loss": 0.7451,
      "step": 22
    },
    {
      "epoch": 0.03645007923930269,
      "grad_norm": 1.3581793308258057,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.6801,
      "step": 23
    },
    {
      "epoch": 0.03803486529318542,
      "grad_norm": 1.7192140817642212,
      "learning_rate": 8.891708613973126e-05,
      "loss": 0.7422,
      "step": 24
    },
    {
      "epoch": 0.039619651347068144,
      "grad_norm": 1.995835304260254,
      "learning_rate": 8.788761839251559e-05,
      "loss": 0.8001,
      "step": 25
    },
    {
      "epoch": 0.039619651347068144,
      "eval_loss": 0.8743540048599243,
      "eval_runtime": 3.2909,
      "eval_samples_per_second": 15.193,
      "eval_steps_per_second": 3.95,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "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": 2.66009604784128e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}