{
  "best_metric": 4.124782085418701,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.6125574272588055,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01225114854517611,
      "grad_norm": 10.575071334838867,
      "learning_rate": 5e-05,
      "loss": 12.2523,
      "step": 1
    },
    {
      "epoch": 0.01225114854517611,
      "eval_loss": 16.951570510864258,
      "eval_runtime": 3.8799,
      "eval_samples_per_second": 12.887,
      "eval_steps_per_second": 3.351,
      "step": 1
    },
    {
      "epoch": 0.02450229709035222,
      "grad_norm": 12.328155517578125,
      "learning_rate": 0.0001,
      "loss": 13.7723,
      "step": 2
    },
    {
      "epoch": 0.036753445635528334,
      "grad_norm": 12.458799362182617,
      "learning_rate": 9.990365154573717e-05,
      "loss": 14.5012,
      "step": 3
    },
    {
      "epoch": 0.04900459418070444,
      "grad_norm": 13.457901954650879,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.1365,
      "step": 4
    },
    {
      "epoch": 0.06125574272588055,
      "grad_norm": 13.712512016296387,
      "learning_rate": 9.913533761814537e-05,
      "loss": 10.2128,
      "step": 5
    },
    {
      "epoch": 0.07350689127105667,
      "grad_norm": 13.127202987670898,
      "learning_rate": 9.846666218300807e-05,
      "loss": 9.2836,
      "step": 6
    },
    {
      "epoch": 0.08575803981623277,
      "grad_norm": 12.485448837280273,
      "learning_rate": 9.761185582727977e-05,
      "loss": 8.0624,
      "step": 7
    },
    {
      "epoch": 0.09800918836140889,
      "grad_norm": 8.79636287689209,
      "learning_rate": 9.657457896300791e-05,
      "loss": 6.7086,
      "step": 8
    },
    {
      "epoch": 0.11026033690658499,
      "grad_norm": 10.279217720031738,
      "learning_rate": 9.535927336897098e-05,
      "loss": 5.9996,
      "step": 9
    },
    {
      "epoch": 0.1225114854517611,
      "grad_norm": 10.29515552520752,
      "learning_rate": 9.397114317029975e-05,
      "loss": 5.5281,
      "step": 10
    },
    {
      "epoch": 0.13476263399693722,
      "grad_norm": 6.9765625,
      "learning_rate": 9.241613255361455e-05,
      "loss": 5.2014,
      "step": 11
    },
    {
      "epoch": 0.14701378254211334,
      "grad_norm": 6.097973823547363,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.9461,
      "step": 12
    },
    {
      "epoch": 0.15926493108728942,
      "grad_norm": 4.98734712600708,
      "learning_rate": 8.883279133655399e-05,
      "loss": 4.4112,
      "step": 13
    },
    {
      "epoch": 0.17151607963246554,
      "grad_norm": 4.975678443908691,
      "learning_rate": 8.681980515339464e-05,
      "loss": 3.8226,
      "step": 14
    },
    {
      "epoch": 0.18376722817764166,
      "grad_norm": 4.569962978363037,
      "learning_rate": 8.467056167950311e-05,
      "loss": 3.7938,
      "step": 15
    },
    {
      "epoch": 0.19601837672281777,
      "grad_norm": 4.054300308227539,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.1932,
      "step": 16
    },
    {
      "epoch": 0.2082695252679939,
      "grad_norm": 4.394216060638428,
      "learning_rate": 8.000066048588211e-05,
      "loss": 4.2387,
      "step": 17
    },
    {
      "epoch": 0.22052067381316998,
      "grad_norm": 4.765974521636963,
      "learning_rate": 7.75e-05,
      "loss": 4.1675,
      "step": 18
    },
    {
      "epoch": 0.2327718223583461,
      "grad_norm": 4.124263763427734,
      "learning_rate": 7.490299105985507e-05,
      "loss": 4.34,
      "step": 19
    },
    {
      "epoch": 0.2450229709035222,
      "grad_norm": 4.744834899902344,
      "learning_rate": 7.222075445642904e-05,
      "loss": 4.4745,
      "step": 20
    },
    {
      "epoch": 0.2572741194486983,
      "grad_norm": 3.426642417907715,
      "learning_rate": 6.946477593864228e-05,
      "loss": 4.1778,
      "step": 21
    },
    {
      "epoch": 0.26952526799387444,
      "grad_norm": 3.3985297679901123,
      "learning_rate": 6.664685702961344e-05,
      "loss": 3.9037,
      "step": 22
    },
    {
      "epoch": 0.28177641653905056,
      "grad_norm": 3.363964080810547,
      "learning_rate": 6.377906449072578e-05,
      "loss": 3.8301,
      "step": 23
    },
    {
      "epoch": 0.29402756508422667,
      "grad_norm": 3.379330635070801,
      "learning_rate": 6.087367864990233e-05,
      "loss": 4.1785,
      "step": 24
    },
    {
      "epoch": 0.30627871362940273,
      "grad_norm": 4.273047924041748,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.3698,
      "step": 25
    },
    {
      "epoch": 0.30627871362940273,
      "eval_loss": 4.303714752197266,
      "eval_runtime": 3.4948,
      "eval_samples_per_second": 14.307,
      "eval_steps_per_second": 3.72,
      "step": 25
    },
    {
      "epoch": 0.31852986217457885,
      "grad_norm": 7.1779561042785645,
      "learning_rate": 5.500000000000001e-05,
      "loss": 3.17,
      "step": 26
    },
    {
      "epoch": 0.33078101071975496,
      "grad_norm": 3.5469911098480225,
      "learning_rate": 5.205685918464356e-05,
      "loss": 3.5137,
      "step": 27
    },
    {
      "epoch": 0.3430321592649311,
      "grad_norm": 2.8225502967834473,
      "learning_rate": 4.912632135009769e-05,
      "loss": 3.2536,
      "step": 28
    },
    {
      "epoch": 0.3552833078101072,
      "grad_norm": 3.2358927726745605,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 3.4745,
      "step": 29
    },
    {
      "epoch": 0.3675344563552833,
      "grad_norm": 4.149901390075684,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 3.6246,
      "step": 30
    },
    {
      "epoch": 0.37978560490045943,
      "grad_norm": 3.0618069171905518,
      "learning_rate": 4.053522406135775e-05,
      "loss": 3.6646,
      "step": 31
    },
    {
      "epoch": 0.39203675344563554,
      "grad_norm": 4.720259189605713,
      "learning_rate": 3.777924554357096e-05,
      "loss": 3.8053,
      "step": 32
    },
    {
      "epoch": 0.40428790199081166,
      "grad_norm": 2.7804815769195557,
      "learning_rate": 3.509700894014496e-05,
      "loss": 3.3949,
      "step": 33
    },
    {
      "epoch": 0.4165390505359878,
      "grad_norm": 3.4043445587158203,
      "learning_rate": 3.250000000000001e-05,
      "loss": 3.8051,
      "step": 34
    },
    {
      "epoch": 0.42879019908116384,
      "grad_norm": 3.489053964614868,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 3.7363,
      "step": 35
    },
    {
      "epoch": 0.44104134762633995,
      "grad_norm": 3.47819185256958,
      "learning_rate": 2.760573569460757e-05,
      "loss": 3.6668,
      "step": 36
    },
    {
      "epoch": 0.45329249617151607,
      "grad_norm": 3.2192630767822266,
      "learning_rate": 2.53294383204969e-05,
      "loss": 4.1236,
      "step": 37
    },
    {
      "epoch": 0.4655436447166922,
      "grad_norm": 3.5141780376434326,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 3.3018,
      "step": 38
    },
    {
      "epoch": 0.4777947932618683,
      "grad_norm": 3.293383836746216,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 3.3655,
      "step": 39
    },
    {
      "epoch": 0.4900459418070444,
      "grad_norm": 3.6325714588165283,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 3.5624,
      "step": 40
    },
    {
      "epoch": 0.5022970903522205,
      "grad_norm": 3.457775354385376,
      "learning_rate": 1.758386744638546e-05,
      "loss": 3.7964,
      "step": 41
    },
    {
      "epoch": 0.5145482388973966,
      "grad_norm": 2.97334623336792,
      "learning_rate": 1.602885682970026e-05,
      "loss": 3.7029,
      "step": 42
    },
    {
      "epoch": 0.5267993874425727,
      "grad_norm": 3.7691123485565186,
      "learning_rate": 1.464072663102903e-05,
      "loss": 3.9081,
      "step": 43
    },
    {
      "epoch": 0.5390505359877489,
      "grad_norm": 3.316641092300415,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 4.0407,
      "step": 44
    },
    {
      "epoch": 0.5513016845329249,
      "grad_norm": 3.486757755279541,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 3.9519,
      "step": 45
    },
    {
      "epoch": 0.5635528330781011,
      "grad_norm": 3.3748724460601807,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 3.8977,
      "step": 46
    },
    {
      "epoch": 0.5758039816232772,
      "grad_norm": 3.2216415405273438,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 4.1025,
      "step": 47
    },
    {
      "epoch": 0.5880551301684533,
      "grad_norm": 4.37778902053833,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 3.7138,
      "step": 48
    },
    {
      "epoch": 0.6003062787136294,
      "grad_norm": 4.192712306976318,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 4.0474,
      "step": 49
    },
    {
      "epoch": 0.6125574272588055,
      "grad_norm": 4.064006805419922,
      "learning_rate": 1e-05,
      "loss": 4.2144,
      "step": 50
    },
    {
      "epoch": 0.6125574272588055,
      "eval_loss": 4.124782085418701,
      "eval_runtime": 3.5052,
      "eval_samples_per_second": 14.265,
      "eval_steps_per_second": 3.709,
      "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": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}