{
  "best_metric": 3.9180445671081543,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06749915626054674,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013499831252109348,
      "grad_norm": 165.77716064453125,
      "learning_rate": 5e-05,
      "loss": 55.2222,
      "step": 1
    },
    {
      "epoch": 0.0013499831252109348,
      "eval_loss": 110.49451446533203,
      "eval_runtime": 369.2173,
      "eval_samples_per_second": 13.515,
      "eval_steps_per_second": 1.69,
      "step": 1
    },
    {
      "epoch": 0.0026999662504218697,
      "grad_norm": 211.95211791992188,
      "learning_rate": 0.0001,
      "loss": 73.7774,
      "step": 2
    },
    {
      "epoch": 0.004049949375632805,
      "grad_norm": 193.2682647705078,
      "learning_rate": 9.989294616193017e-05,
      "loss": 72.7463,
      "step": 3
    },
    {
      "epoch": 0.005399932500843739,
      "grad_norm": 238.9132843017578,
      "learning_rate": 9.957224306869053e-05,
      "loss": 63.7791,
      "step": 4
    },
    {
      "epoch": 0.006749915626054675,
      "grad_norm": 326.07623291015625,
      "learning_rate": 9.903926402016153e-05,
      "loss": 50.26,
      "step": 5
    },
    {
      "epoch": 0.00809989875126561,
      "grad_norm": 421.47900390625,
      "learning_rate": 9.829629131445342e-05,
      "loss": 38.9118,
      "step": 6
    },
    {
      "epoch": 0.009449881876476544,
      "grad_norm": 418.64678955078125,
      "learning_rate": 9.73465064747553e-05,
      "loss": 17.7872,
      "step": 7
    },
    {
      "epoch": 0.010799865001687479,
      "grad_norm": 34.50855255126953,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.7823,
      "step": 8
    },
    {
      "epoch": 0.012149848126898413,
      "grad_norm": 76.25312805175781,
      "learning_rate": 9.484363707663442e-05,
      "loss": 5.9349,
      "step": 9
    },
    {
      "epoch": 0.01349983125210935,
      "grad_norm": 109.61444854736328,
      "learning_rate": 9.330127018922194e-05,
      "loss": 6.6484,
      "step": 10
    },
    {
      "epoch": 0.014849814377320284,
      "grad_norm": 99.42346954345703,
      "learning_rate": 9.157348061512727e-05,
      "loss": 6.4242,
      "step": 11
    },
    {
      "epoch": 0.01619979750253122,
      "grad_norm": 19.366714477539062,
      "learning_rate": 8.966766701456177e-05,
      "loss": 6.3274,
      "step": 12
    },
    {
      "epoch": 0.017549780627742154,
      "grad_norm": 14.371905326843262,
      "learning_rate": 8.759199037394887e-05,
      "loss": 4.4881,
      "step": 13
    },
    {
      "epoch": 0.01889976375295309,
      "grad_norm": 15.031280517578125,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.3316,
      "step": 14
    },
    {
      "epoch": 0.020249746878164023,
      "grad_norm": 8.996877670288086,
      "learning_rate": 8.296729075500344e-05,
      "loss": 4.1819,
      "step": 15
    },
    {
      "epoch": 0.021599730003374958,
      "grad_norm": 8.649632453918457,
      "learning_rate": 8.043807145043604e-05,
      "loss": 4.2798,
      "step": 16
    },
    {
      "epoch": 0.022949713128585892,
      "grad_norm": 10.980398178100586,
      "learning_rate": 7.777851165098012e-05,
      "loss": 4.5594,
      "step": 17
    },
    {
      "epoch": 0.024299696253796826,
      "grad_norm": 11.965767860412598,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.7595,
      "step": 18
    },
    {
      "epoch": 0.02564967937900776,
      "grad_norm": 10.571087837219238,
      "learning_rate": 7.211443451095007e-05,
      "loss": 4.7062,
      "step": 19
    },
    {
      "epoch": 0.0269996625042187,
      "grad_norm": 9.564517974853516,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.5425,
      "step": 20
    },
    {
      "epoch": 0.028349645629429633,
      "grad_norm": 23.86448097229004,
      "learning_rate": 6.607197326515808e-05,
      "loss": 4.9562,
      "step": 21
    },
    {
      "epoch": 0.029699628754640568,
      "grad_norm": 43.532196044921875,
      "learning_rate": 6.294095225512603e-05,
      "loss": 4.6615,
      "step": 22
    },
    {
      "epoch": 0.031049611879851502,
      "grad_norm": 35.28922653198242,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 4.8801,
      "step": 23
    },
    {
      "epoch": 0.03239959500506244,
      "grad_norm": 10.912775039672852,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 5.085,
      "step": 24
    },
    {
      "epoch": 0.03374957813027337,
      "grad_norm": 11.722034454345703,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.8866,
      "step": 25
    },
    {
      "epoch": 0.03374957813027337,
      "eval_loss": 4.299006938934326,
      "eval_runtime": 369.2672,
      "eval_samples_per_second": 13.513,
      "eval_steps_per_second": 1.69,
      "step": 25
    },
    {
      "epoch": 0.03509956125548431,
      "grad_norm": 8.628137588500977,
      "learning_rate": 5e-05,
      "loss": 3.2233,
      "step": 26
    },
    {
      "epoch": 0.03644954438069524,
      "grad_norm": 10.846193313598633,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 3.8442,
      "step": 27
    },
    {
      "epoch": 0.03779952750590618,
      "grad_norm": 8.67941951751709,
      "learning_rate": 4.347369038899744e-05,
      "loss": 3.9179,
      "step": 28
    },
    {
      "epoch": 0.03914951063111711,
      "grad_norm": 7.8950676918029785,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 3.7976,
      "step": 29
    },
    {
      "epoch": 0.040499493756328046,
      "grad_norm": 6.960816860198975,
      "learning_rate": 3.705904774487396e-05,
      "loss": 3.9247,
      "step": 30
    },
    {
      "epoch": 0.041849476881538984,
      "grad_norm": 5.280318737030029,
      "learning_rate": 3.392802673484193e-05,
      "loss": 4.0847,
      "step": 31
    },
    {
      "epoch": 0.043199460006749915,
      "grad_norm": 5.189662933349609,
      "learning_rate": 3.086582838174551e-05,
      "loss": 4.0055,
      "step": 32
    },
    {
      "epoch": 0.04454944313196085,
      "grad_norm": 8.99771785736084,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 4.3989,
      "step": 33
    },
    {
      "epoch": 0.045899426257171784,
      "grad_norm": 7.683967113494873,
      "learning_rate": 2.500000000000001e-05,
      "loss": 4.4733,
      "step": 34
    },
    {
      "epoch": 0.04724940938238272,
      "grad_norm": 7.3979105949401855,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 4.586,
      "step": 35
    },
    {
      "epoch": 0.04859939250759365,
      "grad_norm": 11.688506126403809,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 4.817,
      "step": 36
    },
    {
      "epoch": 0.04994937563280459,
      "grad_norm": 11.070033073425293,
      "learning_rate": 1.703270924499656e-05,
      "loss": 4.984,
      "step": 37
    },
    {
      "epoch": 0.05129935875801552,
      "grad_norm": 4.192941188812256,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.1219,
      "step": 38
    },
    {
      "epoch": 0.05264934188322646,
      "grad_norm": 5.510909080505371,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 3.3148,
      "step": 39
    },
    {
      "epoch": 0.0539993250084374,
      "grad_norm": 5.6417131423950195,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 3.3338,
      "step": 40
    },
    {
      "epoch": 0.05534930813364833,
      "grad_norm": 5.337092399597168,
      "learning_rate": 8.426519384872733e-06,
      "loss": 3.639,
      "step": 41
    },
    {
      "epoch": 0.056699291258859266,
      "grad_norm": 4.77625036239624,
      "learning_rate": 6.698729810778065e-06,
      "loss": 3.5133,
      "step": 42
    },
    {
      "epoch": 0.0580492743840702,
      "grad_norm": 4.821012496948242,
      "learning_rate": 5.156362923365588e-06,
      "loss": 3.9282,
      "step": 43
    },
    {
      "epoch": 0.059399257509281135,
      "grad_norm": 4.676504135131836,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.9006,
      "step": 44
    },
    {
      "epoch": 0.060749240634492066,
      "grad_norm": 4.670116901397705,
      "learning_rate": 2.653493525244721e-06,
      "loss": 3.9759,
      "step": 45
    },
    {
      "epoch": 0.062099223759703004,
      "grad_norm": 5.629438400268555,
      "learning_rate": 1.70370868554659e-06,
      "loss": 4.2648,
      "step": 46
    },
    {
      "epoch": 0.06344920688491394,
      "grad_norm": 5.580984592437744,
      "learning_rate": 9.607359798384785e-07,
      "loss": 4.3399,
      "step": 47
    },
    {
      "epoch": 0.06479919001012488,
      "grad_norm": 5.877447605133057,
      "learning_rate": 4.277569313094809e-07,
      "loss": 4.4184,
      "step": 48
    },
    {
      "epoch": 0.0661491731353358,
      "grad_norm": 8.028692245483398,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 4.8048,
      "step": 49
    },
    {
      "epoch": 0.06749915626054674,
      "grad_norm": 8.630199432373047,
      "learning_rate": 0.0,
      "loss": 4.78,
      "step": 50
    },
    {
      "epoch": 0.06749915626054674,
      "eval_loss": 3.9180445671081543,
      "eval_runtime": 369.3832,
      "eval_samples_per_second": 13.509,
      "eval_steps_per_second": 1.689,
      "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": 6.174479344467968e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}