{
  "best_metric": 3.254734516143799,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06830601092896176,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001366120218579235,
      "grad_norm": 0.4264744818210602,
      "learning_rate": 5e-05,
      "loss": 2.6887,
      "step": 1
    },
    {
      "epoch": 0.001366120218579235,
      "eval_loss": 5.15347146987915,
      "eval_runtime": 2.6797,
      "eval_samples_per_second": 18.659,
      "eval_steps_per_second": 4.851,
      "step": 1
    },
    {
      "epoch": 0.00273224043715847,
      "grad_norm": 0.7313985824584961,
      "learning_rate": 0.0001,
      "loss": 3.4108,
      "step": 2
    },
    {
      "epoch": 0.004098360655737705,
      "grad_norm": 0.8124534487724304,
      "learning_rate": 9.990365154573717e-05,
      "loss": 3.6226,
      "step": 3
    },
    {
      "epoch": 0.00546448087431694,
      "grad_norm": 1.035416841506958,
      "learning_rate": 9.961501876182148e-05,
      "loss": 3.8432,
      "step": 4
    },
    {
      "epoch": 0.006830601092896175,
      "grad_norm": 1.3063868284225464,
      "learning_rate": 9.913533761814537e-05,
      "loss": 4.0185,
      "step": 5
    },
    {
      "epoch": 0.00819672131147541,
      "grad_norm": 1.3012717962265015,
      "learning_rate": 9.846666218300807e-05,
      "loss": 3.971,
      "step": 6
    },
    {
      "epoch": 0.009562841530054645,
      "grad_norm": 1.469678282737732,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.0654,
      "step": 7
    },
    {
      "epoch": 0.01092896174863388,
      "grad_norm": 1.7065930366516113,
      "learning_rate": 9.657457896300791e-05,
      "loss": 4.0649,
      "step": 8
    },
    {
      "epoch": 0.012295081967213115,
      "grad_norm": 2.365776538848877,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.153,
      "step": 9
    },
    {
      "epoch": 0.01366120218579235,
      "grad_norm": 2.0928072929382324,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.0184,
      "step": 10
    },
    {
      "epoch": 0.015027322404371584,
      "grad_norm": 2.631106376647949,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.3098,
      "step": 11
    },
    {
      "epoch": 0.01639344262295082,
      "grad_norm": 3.3695273399353027,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.4752,
      "step": 12
    },
    {
      "epoch": 0.017759562841530054,
      "grad_norm": 2.9824681282043457,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.6337,
      "step": 13
    },
    {
      "epoch": 0.01912568306010929,
      "grad_norm": 3.0734541416168213,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.9202,
      "step": 14
    },
    {
      "epoch": 0.020491803278688523,
      "grad_norm": 2.244558811187744,
      "learning_rate": 8.467056167950311e-05,
      "loss": 3.215,
      "step": 15
    },
    {
      "epoch": 0.02185792349726776,
      "grad_norm": 1.32362699508667,
      "learning_rate": 8.239426430539243e-05,
      "loss": 3.1618,
      "step": 16
    },
    {
      "epoch": 0.023224043715846996,
      "grad_norm": 1.154560923576355,
      "learning_rate": 8.000066048588211e-05,
      "loss": 3.1238,
      "step": 17
    },
    {
      "epoch": 0.02459016393442623,
      "grad_norm": 1.5037178993225098,
      "learning_rate": 7.75e-05,
      "loss": 3.4443,
      "step": 18
    },
    {
      "epoch": 0.025956284153005466,
      "grad_norm": 1.541300654411316,
      "learning_rate": 7.490299105985507e-05,
      "loss": 3.3471,
      "step": 19
    },
    {
      "epoch": 0.0273224043715847,
      "grad_norm": 1.7193808555603027,
      "learning_rate": 7.222075445642904e-05,
      "loss": 3.7188,
      "step": 20
    },
    {
      "epoch": 0.028688524590163935,
      "grad_norm": 1.7405993938446045,
      "learning_rate": 6.946477593864228e-05,
      "loss": 3.7346,
      "step": 21
    },
    {
      "epoch": 0.030054644808743168,
      "grad_norm": 1.88237464427948,
      "learning_rate": 6.664685702961344e-05,
      "loss": 3.8403,
      "step": 22
    },
    {
      "epoch": 0.031420765027322405,
      "grad_norm": 1.7232855558395386,
      "learning_rate": 6.377906449072578e-05,
      "loss": 3.9143,
      "step": 23
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 2.1454970836639404,
      "learning_rate": 6.087367864990233e-05,
      "loss": 3.9158,
      "step": 24
    },
    {
      "epoch": 0.03415300546448088,
      "grad_norm": 2.728879451751709,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.2009,
      "step": 25
    },
    {
      "epoch": 0.03415300546448088,
      "eval_loss": 3.4035658836364746,
      "eval_runtime": 2.0416,
      "eval_samples_per_second": 24.491,
      "eval_steps_per_second": 6.368,
      "step": 25
    },
    {
      "epoch": 0.03551912568306011,
      "grad_norm": 1.473652720451355,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.3435,
      "step": 26
    },
    {
      "epoch": 0.036885245901639344,
      "grad_norm": 2.3803224563598633,
      "learning_rate": 5.205685918464356e-05,
      "loss": 2.9444,
      "step": 27
    },
    {
      "epoch": 0.03825136612021858,
      "grad_norm": 2.5919227600097656,
      "learning_rate": 4.912632135009769e-05,
      "loss": 2.9708,
      "step": 28
    },
    {
      "epoch": 0.03961748633879782,
      "grad_norm": 2.073823928833008,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 3.1827,
      "step": 29
    },
    {
      "epoch": 0.040983606557377046,
      "grad_norm": 1.6544225215911865,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 3.3102,
      "step": 30
    },
    {
      "epoch": 0.04234972677595628,
      "grad_norm": 1.3670271635055542,
      "learning_rate": 4.053522406135775e-05,
      "loss": 3.3568,
      "step": 31
    },
    {
      "epoch": 0.04371584699453552,
      "grad_norm": 1.489598274230957,
      "learning_rate": 3.777924554357096e-05,
      "loss": 3.3932,
      "step": 32
    },
    {
      "epoch": 0.045081967213114756,
      "grad_norm": 1.6354660987854004,
      "learning_rate": 3.509700894014496e-05,
      "loss": 3.6028,
      "step": 33
    },
    {
      "epoch": 0.04644808743169399,
      "grad_norm": 1.849533200263977,
      "learning_rate": 3.250000000000001e-05,
      "loss": 3.4509,
      "step": 34
    },
    {
      "epoch": 0.04781420765027322,
      "grad_norm": 2.0685839653015137,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 3.506,
      "step": 35
    },
    {
      "epoch": 0.04918032786885246,
      "grad_norm": 2.4601333141326904,
      "learning_rate": 2.760573569460757e-05,
      "loss": 3.7161,
      "step": 36
    },
    {
      "epoch": 0.050546448087431695,
      "grad_norm": 2.7234838008880615,
      "learning_rate": 2.53294383204969e-05,
      "loss": 4.0133,
      "step": 37
    },
    {
      "epoch": 0.05191256830601093,
      "grad_norm": 0.6714175939559937,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 2.485,
      "step": 38
    },
    {
      "epoch": 0.05327868852459016,
      "grad_norm": 0.6364284157752991,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 2.6755,
      "step": 39
    },
    {
      "epoch": 0.0546448087431694,
      "grad_norm": 0.7471128106117249,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 2.8658,
      "step": 40
    },
    {
      "epoch": 0.056010928961748634,
      "grad_norm": 0.9513612985610962,
      "learning_rate": 1.758386744638546e-05,
      "loss": 3.1072,
      "step": 41
    },
    {
      "epoch": 0.05737704918032787,
      "grad_norm": 0.9536485075950623,
      "learning_rate": 1.602885682970026e-05,
      "loss": 3.1031,
      "step": 42
    },
    {
      "epoch": 0.05874316939890711,
      "grad_norm": 0.9675177931785583,
      "learning_rate": 1.464072663102903e-05,
      "loss": 3.098,
      "step": 43
    },
    {
      "epoch": 0.060109289617486336,
      "grad_norm": 1.053505301475525,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 3.2611,
      "step": 44
    },
    {
      "epoch": 0.06147540983606557,
      "grad_norm": 1.2233757972717285,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 3.4145,
      "step": 45
    },
    {
      "epoch": 0.06284153005464481,
      "grad_norm": 1.488215684890747,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 3.4454,
      "step": 46
    },
    {
      "epoch": 0.06420765027322405,
      "grad_norm": 1.4474998712539673,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 3.6539,
      "step": 47
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 1.5923969745635986,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 3.5898,
      "step": 48
    },
    {
      "epoch": 0.06693989071038252,
      "grad_norm": 1.9314665794372559,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 3.6862,
      "step": 49
    },
    {
      "epoch": 0.06830601092896176,
      "grad_norm": 3.2003865242004395,
      "learning_rate": 1e-05,
      "loss": 4.0908,
      "step": 50
    },
    {
      "epoch": 0.06830601092896176,
      "eval_loss": 3.254734516143799,
      "eval_runtime": 2.0493,
      "eval_samples_per_second": 24.399,
      "eval_steps_per_second": 6.344,
      "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": 5.971813667564421e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}