{
  "best_metric": 0.13740140199661255,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.020376455006240288,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004075291001248058,
      "grad_norm": 18.37122344970703,
      "learning_rate": 5e-05,
      "loss": 3.8058,
      "step": 1
    },
    {
      "epoch": 0.0004075291001248058,
      "eval_loss": 3.698183059692383,
      "eval_runtime": 237.243,
      "eval_samples_per_second": 69.68,
      "eval_steps_per_second": 8.713,
      "step": 1
    },
    {
      "epoch": 0.0008150582002496116,
      "grad_norm": 22.644386291503906,
      "learning_rate": 0.0001,
      "loss": 3.4645,
      "step": 2
    },
    {
      "epoch": 0.0012225873003744174,
      "grad_norm": 19.61406707763672,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.5998,
      "step": 3
    },
    {
      "epoch": 0.0016301164004992232,
      "grad_norm": 24.494279861450195,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.3956,
      "step": 4
    },
    {
      "epoch": 0.002037645500624029,
      "grad_norm": 21.733304977416992,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.6329,
      "step": 5
    },
    {
      "epoch": 0.002445174600748835,
      "grad_norm": 10.796932220458984,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.2322,
      "step": 6
    },
    {
      "epoch": 0.0028527037008736406,
      "grad_norm": 3.2056634426116943,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0626,
      "step": 7
    },
    {
      "epoch": 0.0032602328009984465,
      "grad_norm": 1.0205552577972412,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0142,
      "step": 8
    },
    {
      "epoch": 0.0036677619011232523,
      "grad_norm": 0.37453579902648926,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0019,
      "step": 9
    },
    {
      "epoch": 0.004075291001248058,
      "grad_norm": 0.03825287148356438,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0004,
      "step": 10
    },
    {
      "epoch": 0.0044828201013728634,
      "grad_norm": 32.95256423950195,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.2467,
      "step": 11
    },
    {
      "epoch": 0.00489034920149767,
      "grad_norm": 74.59322357177734,
      "learning_rate": 8.966766701456177e-05,
      "loss": 5.1846,
      "step": 12
    },
    {
      "epoch": 0.005297878301622475,
      "grad_norm": 48.57853698730469,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.379,
      "step": 13
    },
    {
      "epoch": 0.005705407401747281,
      "grad_norm": 0.10892320424318314,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0008,
      "step": 14
    },
    {
      "epoch": 0.006112936501872087,
      "grad_norm": 0.13808192312717438,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0012,
      "step": 15
    },
    {
      "epoch": 0.006520465601996893,
      "grad_norm": 0.13175702095031738,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.001,
      "step": 16
    },
    {
      "epoch": 0.006927994702121698,
      "grad_norm": 0.05018068850040436,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0005,
      "step": 17
    },
    {
      "epoch": 0.0073355238022465045,
      "grad_norm": 0.025253331288695335,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0003,
      "step": 18
    },
    {
      "epoch": 0.00774305290237131,
      "grad_norm": 0.020915506407618523,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0002,
      "step": 19
    },
    {
      "epoch": 0.008150582002496116,
      "grad_norm": 0.01606067828834057,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0002,
      "step": 20
    },
    {
      "epoch": 0.008558111102620922,
      "grad_norm": 0.013058084063231945,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0001,
      "step": 21
    },
    {
      "epoch": 0.008965640202745727,
      "grad_norm": 0.01016696635633707,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0001,
      "step": 22
    },
    {
      "epoch": 0.009373169302870533,
      "grad_norm": 0.007784224580973387,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0001,
      "step": 23
    },
    {
      "epoch": 0.00978069840299534,
      "grad_norm": 31.09476661682129,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.1506,
      "step": 24
    },
    {
      "epoch": 0.010188227503120144,
      "grad_norm": 24.08420181274414,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.1211,
      "step": 25
    },
    {
      "epoch": 0.010188227503120144,
      "eval_loss": 0.18581102788448334,
      "eval_runtime": 109.6196,
      "eval_samples_per_second": 150.803,
      "eval_steps_per_second": 18.856,
      "step": 25
    },
    {
      "epoch": 0.01059575660324495,
      "grad_norm": 10.906742095947266,
      "learning_rate": 5e-05,
      "loss": 1.3397,
      "step": 26
    },
    {
      "epoch": 0.011003285703369756,
      "grad_norm": 0.29901590943336487,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0026,
      "step": 27
    },
    {
      "epoch": 0.011410814803494563,
      "grad_norm": 0.4468698501586914,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0045,
      "step": 28
    },
    {
      "epoch": 0.011818343903619367,
      "grad_norm": 0.343263179063797,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0034,
      "step": 29
    },
    {
      "epoch": 0.012225873003744173,
      "grad_norm": 0.13799554109573364,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0018,
      "step": 30
    },
    {
      "epoch": 0.01263340210386898,
      "grad_norm": 0.08895780146121979,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0011,
      "step": 31
    },
    {
      "epoch": 0.013040931203993786,
      "grad_norm": 0.06465604156255722,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0008,
      "step": 32
    },
    {
      "epoch": 0.01344846030411859,
      "grad_norm": 0.044299881905317307,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0006,
      "step": 33
    },
    {
      "epoch": 0.013855989404243397,
      "grad_norm": 0.032806701958179474,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0004,
      "step": 34
    },
    {
      "epoch": 0.014263518504368203,
      "grad_norm": 0.024947363883256912,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0003,
      "step": 35
    },
    {
      "epoch": 0.014671047604493009,
      "grad_norm": 8.804998397827148,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.2376,
      "step": 36
    },
    {
      "epoch": 0.015078576704617814,
      "grad_norm": 18.46295928955078,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.8035,
      "step": 37
    },
    {
      "epoch": 0.01548610580474262,
      "grad_norm": 10.507019996643066,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.2105,
      "step": 38
    },
    {
      "epoch": 0.015893634904867424,
      "grad_norm": 0.02539847604930401,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0003,
      "step": 39
    },
    {
      "epoch": 0.016301164004992232,
      "grad_norm": 0.030192432925105095,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0004,
      "step": 40
    },
    {
      "epoch": 0.016708693105117037,
      "grad_norm": 0.03641684353351593,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0005,
      "step": 41
    },
    {
      "epoch": 0.017116222205241845,
      "grad_norm": 0.041325893253088,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0005,
      "step": 42
    },
    {
      "epoch": 0.01752375130536665,
      "grad_norm": 0.04761205241084099,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0006,
      "step": 43
    },
    {
      "epoch": 0.017931280405491454,
      "grad_norm": 0.050131577998399734,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0006,
      "step": 44
    },
    {
      "epoch": 0.01833880950561626,
      "grad_norm": 0.05262096971273422,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0007,
      "step": 45
    },
    {
      "epoch": 0.018746338605741066,
      "grad_norm": 0.05300018563866615,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0007,
      "step": 46
    },
    {
      "epoch": 0.01915386770586587,
      "grad_norm": 0.05538802593946457,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0007,
      "step": 47
    },
    {
      "epoch": 0.01956139680599068,
      "grad_norm": 0.05361310392618179,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0007,
      "step": 48
    },
    {
      "epoch": 0.019968925906115483,
      "grad_norm": 10.175657272338867,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.4815,
      "step": 49
    },
    {
      "epoch": 0.020376455006240288,
      "grad_norm": 10.826835632324219,
      "learning_rate": 0.0,
      "loss": 0.5115,
      "step": 50
    },
    {
      "epoch": 0.020376455006240288,
      "eval_loss": 0.13740140199661255,
      "eval_runtime": 109.8174,
      "eval_samples_per_second": 150.532,
      "eval_steps_per_second": 18.822,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.95300912644096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}