{
  "best_metric": 0.29087916016578674,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.1380473962727203,
  "eval_steps": 50,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003067719917171562,
      "eval_loss": 0.42013826966285706,
      "eval_runtime": 763.0051,
      "eval_samples_per_second": 7.195,
      "eval_steps_per_second": 1.799,
      "step": 1
    },
    {
      "epoch": 0.0030677199171715622,
      "grad_norm": 0.12315841019153595,
      "learning_rate": 0.0001,
      "loss": 0.3099,
      "step": 10
    },
    {
      "epoch": 0.0061354398343431244,
      "grad_norm": 0.10838135331869125,
      "learning_rate": 9.987260573051269e-05,
      "loss": 0.3765,
      "step": 20
    },
    {
      "epoch": 0.009203159751514686,
      "grad_norm": 0.11101564764976501,
      "learning_rate": 9.949107209404665e-05,
      "loss": 0.3504,
      "step": 30
    },
    {
      "epoch": 0.012270879668686249,
      "grad_norm": 0.11831510066986084,
      "learning_rate": 9.885734329855798e-05,
      "loss": 0.2782,
      "step": 40
    },
    {
      "epoch": 0.015338599585857812,
      "grad_norm": 0.35711294412612915,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.2235,
      "step": 50
    },
    {
      "epoch": 0.015338599585857812,
      "eval_loss": 0.3108671307563782,
      "eval_runtime": 766.1358,
      "eval_samples_per_second": 7.166,
      "eval_steps_per_second": 1.792,
      "step": 50
    },
    {
      "epoch": 0.018406319503029372,
      "grad_norm": 0.10238589346408844,
      "learning_rate": 9.68474862499881e-05,
      "loss": 0.2815,
      "step": 60
    },
    {
      "epoch": 0.021474039420200937,
      "grad_norm": 0.11004552245140076,
      "learning_rate": 9.548159976772592e-05,
      "loss": 0.3691,
      "step": 70
    },
    {
      "epoch": 0.024541759337372498,
      "grad_norm": 0.10997151583433151,
      "learning_rate": 9.388394947836279e-05,
      "loss": 0.357,
      "step": 80
    },
    {
      "epoch": 0.02760947925454406,
      "grad_norm": 0.1159084290266037,
      "learning_rate": 9.206267664155907e-05,
      "loss": 0.2697,
      "step": 90
    },
    {
      "epoch": 0.030677199171715623,
      "grad_norm": 0.3277042508125305,
      "learning_rate": 9.002706204621803e-05,
      "loss": 0.2269,
      "step": 100
    },
    {
      "epoch": 0.030677199171715623,
      "eval_loss": 0.313243567943573,
      "eval_runtime": 766.9783,
      "eval_samples_per_second": 7.158,
      "eval_steps_per_second": 1.79,
      "step": 100
    },
    {
      "epoch": 0.03374491908888719,
      "grad_norm": 0.09407459944486618,
      "learning_rate": 8.778747871771292e-05,
      "loss": 0.2725,
      "step": 110
    },
    {
      "epoch": 0.036812639006058745,
      "grad_norm": 0.1076802909374237,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.3743,
      "step": 120
    },
    {
      "epoch": 0.03988035892323031,
      "grad_norm": 0.11247926205396652,
      "learning_rate": 8.274303669726426e-05,
      "loss": 0.3612,
      "step": 130
    },
    {
      "epoch": 0.042948078840401874,
      "grad_norm": 0.13004067540168762,
      "learning_rate": 7.996388332556735e-05,
      "loss": 0.2636,
      "step": 140
    },
    {
      "epoch": 0.04601579875757343,
      "grad_norm": 0.41083377599716187,
      "learning_rate": 7.703204087277988e-05,
      "loss": 0.2176,
      "step": 150
    },
    {
      "epoch": 0.04601579875757343,
      "eval_loss": 0.30073416233062744,
      "eval_runtime": 765.9106,
      "eval_samples_per_second": 7.168,
      "eval_steps_per_second": 1.793,
      "step": 150
    },
    {
      "epoch": 0.049083518674744996,
      "grad_norm": 0.09948628395795822,
      "learning_rate": 7.396244933600285e-05,
      "loss": 0.28,
      "step": 160
    },
    {
      "epoch": 0.05215123859191656,
      "grad_norm": 0.10903914272785187,
      "learning_rate": 7.077075065009433e-05,
      "loss": 0.3643,
      "step": 170
    },
    {
      "epoch": 0.05521895850908812,
      "grad_norm": 0.11725682765245438,
      "learning_rate": 6.747320897995493e-05,
      "loss": 0.3636,
      "step": 180
    },
    {
      "epoch": 0.05828667842625968,
      "grad_norm": 0.10994742065668106,
      "learning_rate": 6.408662784207149e-05,
      "loss": 0.2732,
      "step": 190
    },
    {
      "epoch": 0.061354398343431246,
      "grad_norm": 0.251674085855484,
      "learning_rate": 6.062826447764883e-05,
      "loss": 0.2081,
      "step": 200
    },
    {
      "epoch": 0.061354398343431246,
      "eval_loss": 0.295357346534729,
      "eval_runtime": 767.7606,
      "eval_samples_per_second": 7.151,
      "eval_steps_per_second": 1.788,
      "step": 200
    },
    {
      "epoch": 0.0644221182606028,
      "grad_norm": 0.09594530612230301,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 0.2597,
      "step": 210
    },
    {
      "epoch": 0.06748983817777437,
      "grad_norm": 0.10894957929849625,
      "learning_rate": 5.3566959159961615e-05,
      "loss": 0.3608,
      "step": 220
    },
    {
      "epoch": 0.07055755809494593,
      "grad_norm": 0.103450708091259,
      "learning_rate": 5e-05,
      "loss": 0.3554,
      "step": 230
    },
    {
      "epoch": 0.07362527801211749,
      "grad_norm": 0.1029270738363266,
      "learning_rate": 4.643304084003839e-05,
      "loss": 0.282,
      "step": 240
    },
    {
      "epoch": 0.07669299792928906,
      "grad_norm": 0.35574325919151306,
      "learning_rate": 4.288425808633575e-05,
      "loss": 0.2095,
      "step": 250
    },
    {
      "epoch": 0.07669299792928906,
      "eval_loss": 0.29382532835006714,
      "eval_runtime": 766.7704,
      "eval_samples_per_second": 7.16,
      "eval_steps_per_second": 1.791,
      "step": 250
    },
    {
      "epoch": 0.07976071784646062,
      "grad_norm": 0.08866327255964279,
      "learning_rate": 3.937173552235117e-05,
      "loss": 0.2725,
      "step": 260
    },
    {
      "epoch": 0.08282843776363218,
      "grad_norm": 0.10799609124660492,
      "learning_rate": 3.591337215792852e-05,
      "loss": 0.3543,
      "step": 270
    },
    {
      "epoch": 0.08589615768080375,
      "grad_norm": 0.10899989306926727,
      "learning_rate": 3.2526791020045086e-05,
      "loss": 0.3616,
      "step": 280
    },
    {
      "epoch": 0.0889638775979753,
      "grad_norm": 0.1085992082953453,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 0.292,
      "step": 290
    },
    {
      "epoch": 0.09203159751514686,
      "grad_norm": 0.2433381974697113,
      "learning_rate": 2.603755066399718e-05,
      "loss": 0.2056,
      "step": 300
    },
    {
      "epoch": 0.09203159751514686,
      "eval_loss": 0.2922627031803131,
      "eval_runtime": 766.4427,
      "eval_samples_per_second": 7.163,
      "eval_steps_per_second": 1.791,
      "step": 300
    },
    {
      "epoch": 0.09509931743231843,
      "grad_norm": 0.0941392332315445,
      "learning_rate": 2.296795912722014e-05,
      "loss": 0.275,
      "step": 310
    },
    {
      "epoch": 0.09816703734948999,
      "grad_norm": 0.11052852123975754,
      "learning_rate": 2.0036116674432654e-05,
      "loss": 0.3692,
      "step": 320
    },
    {
      "epoch": 0.10123475726666155,
      "grad_norm": 0.10507681220769882,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.3476,
      "step": 330
    },
    {
      "epoch": 0.10430247718383312,
      "grad_norm": 0.10875732451677322,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2607,
      "step": 340
    },
    {
      "epoch": 0.10737019710100468,
      "grad_norm": 0.23030522465705872,
      "learning_rate": 1.2212521282287092e-05,
      "loss": 0.1934,
      "step": 350
    },
    {
      "epoch": 0.10737019710100468,
      "eval_loss": 0.29142311215400696,
      "eval_runtime": 765.9528,
      "eval_samples_per_second": 7.168,
      "eval_steps_per_second": 1.793,
      "step": 350
    },
    {
      "epoch": 0.11043791701817623,
      "grad_norm": 0.10388277471065521,
      "learning_rate": 9.972937953781986e-06,
      "loss": 0.2745,
      "step": 360
    },
    {
      "epoch": 0.1135056369353478,
      "grad_norm": 0.10279553383588791,
      "learning_rate": 7.937323358440935e-06,
      "loss": 0.3599,
      "step": 370
    },
    {
      "epoch": 0.11657335685251936,
      "grad_norm": 0.10545451194047928,
      "learning_rate": 6.116050521637218e-06,
      "loss": 0.3421,
      "step": 380
    },
    {
      "epoch": 0.11964107676969092,
      "grad_norm": 0.11335179954767227,
      "learning_rate": 4.5184002322740785e-06,
      "loss": 0.2616,
      "step": 390
    },
    {
      "epoch": 0.12270879668686249,
      "grad_norm": 0.22902686893939972,
      "learning_rate": 3.1525137500119207e-06,
      "loss": 0.1961,
      "step": 400
    },
    {
      "epoch": 0.12270879668686249,
      "eval_loss": 0.29096364974975586,
      "eval_runtime": 767.6702,
      "eval_samples_per_second": 7.152,
      "eval_steps_per_second": 1.789,
      "step": 400
    },
    {
      "epoch": 0.12577651660403405,
      "grad_norm": 0.09514732658863068,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 0.2589,
      "step": 410
    },
    {
      "epoch": 0.1288442365212056,
      "grad_norm": 0.10798075050115585,
      "learning_rate": 1.1426567014420297e-06,
      "loss": 0.3551,
      "step": 420
    },
    {
      "epoch": 0.13191195643837716,
      "grad_norm": 0.10427014529705048,
      "learning_rate": 5.089279059533658e-07,
      "loss": 0.3446,
      "step": 430
    },
    {
      "epoch": 0.13497967635554875,
      "grad_norm": 0.1093059629201889,
      "learning_rate": 1.2739426948732424e-07,
      "loss": 0.2696,
      "step": 440
    },
    {
      "epoch": 0.1380473962727203,
      "grad_norm": 0.2530665993690491,
      "learning_rate": 0.0,
      "loss": 0.1993,
      "step": 450
    },
    {
      "epoch": 0.1380473962727203,
      "eval_loss": 0.29087916016578674,
      "eval_runtime": 766.9955,
      "eval_samples_per_second": 7.158,
      "eval_steps_per_second": 1.79,
      "step": 450
    }
  ],
  "logging_steps": 10,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 1.2833863064239473e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}