{
  "best_metric": 1.121554970741272,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.7094017094017095,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.28619083762168884,
      "learning_rate": 5e-05,
      "loss": 1.2226,
      "step": 1
    },
    {
      "epoch": 0.03418803418803419,
      "eval_loss": 1.4675167798995972,
      "eval_runtime": 4.3926,
      "eval_samples_per_second": 11.383,
      "eval_steps_per_second": 2.96,
      "step": 1
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.3590335249900818,
      "learning_rate": 0.0001,
      "loss": 1.3575,
      "step": 2
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.3375117778778076,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.3864,
      "step": 3
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.3046930134296417,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.4179,
      "step": 4
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.30242782831192017,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.5238,
      "step": 5
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.4030556082725525,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.4627,
      "step": 6
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 0.5563144683837891,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.5078,
      "step": 7
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.2303982973098755,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.1034,
      "step": 8
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.28613147139549255,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.1978,
      "step": 9
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.2653099298477173,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.2221,
      "step": 10
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": 0.25059524178504944,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.2526,
      "step": 11
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.2135804444551468,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.3483,
      "step": 12
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.25175967812538147,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.4539,
      "step": 13
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.32141080498695374,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.2929,
      "step": 14
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.18794244527816772,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.0338,
      "step": 15
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.1876486986875534,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.0946,
      "step": 16
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": 0.19815322756767273,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.1279,
      "step": 17
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.17576132714748383,
      "learning_rate": 7.75e-05,
      "loss": 1.134,
      "step": 18
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": 0.19796888530254364,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.2078,
      "step": 19
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.2896368205547333,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.3557,
      "step": 20
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.37429279088974,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.2491,
      "step": 21
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.22006075084209442,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.004,
      "step": 22
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": 0.1414097547531128,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.0723,
      "step": 23
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.1569179743528366,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.1144,
      "step": 24
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.1766042411327362,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.0922,
      "step": 25
    },
    {
      "epoch": 0.8547008547008547,
      "eval_loss": 1.1654691696166992,
      "eval_runtime": 4.4597,
      "eval_samples_per_second": 11.212,
      "eval_steps_per_second": 2.915,
      "step": 25
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.18392470479011536,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.1871,
      "step": 26
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.23653820157051086,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.2762,
      "step": 27
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.2580876648426056,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.2297,
      "step": 28
    },
    {
      "epoch": 0.9914529914529915,
      "grad_norm": 0.4685609042644501,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 1.2434,
      "step": 29
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.3267412483692169,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.9013,
      "step": 30
    },
    {
      "epoch": 1.0598290598290598,
      "grad_norm": 0.16479617357254028,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.01,
      "step": 31
    },
    {
      "epoch": 1.0940170940170941,
      "grad_norm": 0.18420445919036865,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.0739,
      "step": 32
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 0.18077658116817474,
      "learning_rate": 3.509700894014496e-05,
      "loss": 1.1113,
      "step": 33
    },
    {
      "epoch": 1.1623931623931625,
      "grad_norm": 0.21368959546089172,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.1685,
      "step": 34
    },
    {
      "epoch": 1.1965811965811965,
      "grad_norm": 0.28042304515838623,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.2989,
      "step": 35
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3582153618335724,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.1726,
      "step": 36
    },
    {
      "epoch": 1.264957264957265,
      "grad_norm": 0.1842605173587799,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.9198,
      "step": 37
    },
    {
      "epoch": 1.2991452991452992,
      "grad_norm": 0.1638794243335724,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.0364,
      "step": 38
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.161654531955719,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 1.0229,
      "step": 39
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 0.1766486018896103,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.0824,
      "step": 40
    },
    {
      "epoch": 1.4017094017094016,
      "grad_norm": 0.22246946394443512,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.1882,
      "step": 41
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.30594465136528015,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.2985,
      "step": 42
    },
    {
      "epoch": 1.4700854700854702,
      "grad_norm": 0.2768097221851349,
      "learning_rate": 1.464072663102903e-05,
      "loss": 1.1253,
      "step": 43
    },
    {
      "epoch": 1.5042735042735043,
      "grad_norm": 0.16831669211387634,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.7995,
      "step": 44
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.1657053530216217,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.1661,
      "step": 45
    },
    {
      "epoch": 1.5726495726495726,
      "grad_norm": 0.14991974830627441,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.0224,
      "step": 46
    },
    {
      "epoch": 1.606837606837607,
      "grad_norm": 0.17610901594161987,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.0297,
      "step": 47
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.18544097244739532,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.1199,
      "step": 48
    },
    {
      "epoch": 1.6752136752136753,
      "grad_norm": 0.2795030176639557,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.2703,
      "step": 49
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 0.2776411771774292,
      "learning_rate": 1e-05,
      "loss": 1.1317,
      "step": 50
    },
    {
      "epoch": 1.7094017094017095,
      "eval_loss": 1.121554970741272,
      "eval_runtime": 4.456,
      "eval_samples_per_second": 11.221,
      "eval_steps_per_second": 2.917,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.6566376489064858e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}