{
  "best_metric": 1.4432059526443481,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.6756756756756757,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 1.182604193687439,
      "learning_rate": 5.000000000000001e-07,
      "loss": 1.5157,
      "step": 1
    },
    {
      "epoch": 0.013513513513513514,
      "eval_loss": 1.6760309934616089,
      "eval_runtime": 40.4948,
      "eval_samples_per_second": 6.174,
      "eval_steps_per_second": 1.556,
      "step": 1
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.2888565063476562,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.7694,
      "step": 2
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 1.2827200889587402,
      "learning_rate": 1.5e-06,
      "loss": 1.6787,
      "step": 3
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.1944496631622314,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.6116,
      "step": 4
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 1.2333825826644897,
      "learning_rate": 2.5e-06,
      "loss": 1.6405,
      "step": 5
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.4027087688446045,
      "learning_rate": 3e-06,
      "loss": 1.6888,
      "step": 6
    },
    {
      "epoch": 0.0945945945945946,
      "grad_norm": 1.1837018728256226,
      "learning_rate": 3.5000000000000004e-06,
      "loss": 1.5811,
      "step": 7
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 1.3160983324050903,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.6628,
      "step": 8
    },
    {
      "epoch": 0.12162162162162163,
      "grad_norm": 1.328890323638916,
      "learning_rate": 4.5e-06,
      "loss": 1.6113,
      "step": 9
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 1.36015784740448,
      "learning_rate": 5e-06,
      "loss": 1.734,
      "step": 10
    },
    {
      "epoch": 0.14864864864864866,
      "grad_norm": 1.2641745805740356,
      "learning_rate": 5.500000000000001e-06,
      "loss": 1.6575,
      "step": 11
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 1.195217251777649,
      "learning_rate": 6e-06,
      "loss": 1.6533,
      "step": 12
    },
    {
      "epoch": 0.17567567567567569,
      "grad_norm": 1.534934401512146,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 1.7857,
      "step": 13
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 1.2150381803512573,
      "learning_rate": 7.000000000000001e-06,
      "loss": 1.7598,
      "step": 14
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 1.2849867343902588,
      "learning_rate": 7.5e-06,
      "loss": 1.6906,
      "step": 15
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 1.3215241432189941,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.5991,
      "step": 16
    },
    {
      "epoch": 0.22972972972972974,
      "grad_norm": 1.0337059497833252,
      "learning_rate": 8.500000000000002e-06,
      "loss": 1.6426,
      "step": 17
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 1.2015763521194458,
      "learning_rate": 9e-06,
      "loss": 1.6674,
      "step": 18
    },
    {
      "epoch": 0.25675675675675674,
      "grad_norm": 1.0645320415496826,
      "learning_rate": 9.5e-06,
      "loss": 1.4811,
      "step": 19
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 0.9516133666038513,
      "learning_rate": 1e-05,
      "loss": 1.4088,
      "step": 20
    },
    {
      "epoch": 0.28378378378378377,
      "grad_norm": 1.0448931455612183,
      "learning_rate": 1.05e-05,
      "loss": 1.5424,
      "step": 21
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 1.1775983572006226,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.637,
      "step": 22
    },
    {
      "epoch": 0.3108108108108108,
      "grad_norm": 1.1113003492355347,
      "learning_rate": 1.1500000000000002e-05,
      "loss": 1.4857,
      "step": 23
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 1.1821614503860474,
      "learning_rate": 1.2e-05,
      "loss": 1.6479,
      "step": 24
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 1.0641610622406006,
      "learning_rate": 1.25e-05,
      "loss": 1.5605,
      "step": 25
    },
    {
      "epoch": 0.33783783783783783,
      "eval_loss": 1.535617470741272,
      "eval_runtime": 40.491,
      "eval_samples_per_second": 6.174,
      "eval_steps_per_second": 1.556,
      "step": 25
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 1.1770542860031128,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.4731,
      "step": 26
    },
    {
      "epoch": 0.36486486486486486,
      "grad_norm": 0.9612252712249756,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 1.5683,
      "step": 27
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 1.5425941944122314,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.5621,
      "step": 28
    },
    {
      "epoch": 0.3918918918918919,
      "grad_norm": 1.084754467010498,
      "learning_rate": 1.45e-05,
      "loss": 1.5416,
      "step": 29
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 1.1460059881210327,
      "learning_rate": 1.5e-05,
      "loss": 1.6328,
      "step": 30
    },
    {
      "epoch": 0.4189189189189189,
      "grad_norm": 1.1955316066741943,
      "learning_rate": 1.55e-05,
      "loss": 1.6108,
      "step": 31
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 1.0282008647918701,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.3907,
      "step": 32
    },
    {
      "epoch": 0.44594594594594594,
      "grad_norm": 1.2764079570770264,
      "learning_rate": 1.65e-05,
      "loss": 1.6327,
      "step": 33
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 1.15719473361969,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 1.4977,
      "step": 34
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 1.1096899509429932,
      "learning_rate": 1.75e-05,
      "loss": 1.5142,
      "step": 35
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 1.0471147298812866,
      "learning_rate": 1.8e-05,
      "loss": 1.3773,
      "step": 36
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.9455012679100037,
      "learning_rate": 1.85e-05,
      "loss": 1.4532,
      "step": 37
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 1.1317943334579468,
      "learning_rate": 1.9e-05,
      "loss": 1.482,
      "step": 38
    },
    {
      "epoch": 0.527027027027027,
      "grad_norm": 1.1226030588150024,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 1.5163,
      "step": 39
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 1.0144020318984985,
      "learning_rate": 2e-05,
      "loss": 1.4357,
      "step": 40
    },
    {
      "epoch": 0.5540540540540541,
      "grad_norm": 1.3154661655426025,
      "learning_rate": 2.05e-05,
      "loss": 1.6364,
      "step": 41
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 1.1747310161590576,
      "learning_rate": 2.1e-05,
      "loss": 1.3186,
      "step": 42
    },
    {
      "epoch": 0.581081081081081,
      "grad_norm": 0.9352157711982727,
      "learning_rate": 2.15e-05,
      "loss": 1.5016,
      "step": 43
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 0.992979109287262,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.4764,
      "step": 44
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 1.1484577655792236,
      "learning_rate": 2.25e-05,
      "loss": 1.493,
      "step": 45
    },
    {
      "epoch": 0.6216216216216216,
      "grad_norm": 1.063947081565857,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 1.4308,
      "step": 46
    },
    {
      "epoch": 0.6351351351351351,
      "grad_norm": 1.0236965417861938,
      "learning_rate": 2.35e-05,
      "loss": 1.5211,
      "step": 47
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 1.165647029876709,
      "learning_rate": 2.4e-05,
      "loss": 1.4569,
      "step": 48
    },
    {
      "epoch": 0.6621621621621622,
      "grad_norm": 0.9427868723869324,
      "learning_rate": 2.45e-05,
      "loss": 1.4874,
      "step": 49
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 1.046981692314148,
      "learning_rate": 2.5e-05,
      "loss": 1.4938,
      "step": 50
    },
    {
      "epoch": 0.6756756756756757,
      "eval_loss": 1.4432059526443481,
      "eval_runtime": 40.4738,
      "eval_samples_per_second": 6.177,
      "eval_steps_per_second": 1.557,
      "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": 3.017027157491712e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}