{
  "best_metric": 1.4609953165054321,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.2094240837696335,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004188481675392671,
      "grad_norm": 3.926077127456665,
      "learning_rate": 1e-05,
      "loss": 2.0879,
      "step": 1
    },
    {
      "epoch": 0.004188481675392671,
      "eval_loss": 2.2211415767669678,
      "eval_runtime": 28.6548,
      "eval_samples_per_second": 14.064,
      "eval_steps_per_second": 3.525,
      "step": 1
    },
    {
      "epoch": 0.008376963350785341,
      "grad_norm": 5.116100788116455,
      "learning_rate": 2e-05,
      "loss": 2.1233,
      "step": 2
    },
    {
      "epoch": 0.012565445026178011,
      "grad_norm": 4.467835426330566,
      "learning_rate": 3e-05,
      "loss": 2.0685,
      "step": 3
    },
    {
      "epoch": 0.016753926701570682,
      "grad_norm": 3.099653482437134,
      "learning_rate": 4e-05,
      "loss": 2.0546,
      "step": 4
    },
    {
      "epoch": 0.020942408376963352,
      "grad_norm": 2.941957712173462,
      "learning_rate": 5e-05,
      "loss": 1.9169,
      "step": 5
    },
    {
      "epoch": 0.025130890052356022,
      "grad_norm": 1.8964356184005737,
      "learning_rate": 6e-05,
      "loss": 1.7972,
      "step": 6
    },
    {
      "epoch": 0.02931937172774869,
      "grad_norm": 0.822271466255188,
      "learning_rate": 7e-05,
      "loss": 1.6816,
      "step": 7
    },
    {
      "epoch": 0.033507853403141365,
      "grad_norm": 0.7898607850074768,
      "learning_rate": 8e-05,
      "loss": 1.692,
      "step": 8
    },
    {
      "epoch": 0.03769633507853403,
      "grad_norm": 0.8590221405029297,
      "learning_rate": 9e-05,
      "loss": 1.5978,
      "step": 9
    },
    {
      "epoch": 0.041884816753926704,
      "grad_norm": 0.6750182509422302,
      "learning_rate": 0.0001,
      "loss": 1.5605,
      "step": 10
    },
    {
      "epoch": 0.04607329842931937,
      "grad_norm": 0.5955801010131836,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.5164,
      "step": 11
    },
    {
      "epoch": 0.050261780104712044,
      "grad_norm": 0.41977617144584656,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.4814,
      "step": 12
    },
    {
      "epoch": 0.05445026178010471,
      "grad_norm": 0.6115280389785767,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.5194,
      "step": 13
    },
    {
      "epoch": 0.05863874345549738,
      "grad_norm": 0.458881676197052,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.5086,
      "step": 14
    },
    {
      "epoch": 0.06282722513089005,
      "grad_norm": 0.558876097202301,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.4856,
      "step": 15
    },
    {
      "epoch": 0.06701570680628273,
      "grad_norm": 0.45572343468666077,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.5626,
      "step": 16
    },
    {
      "epoch": 0.0712041884816754,
      "grad_norm": 0.5151314735412598,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.4417,
      "step": 17
    },
    {
      "epoch": 0.07539267015706806,
      "grad_norm": 0.4471381902694702,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.4668,
      "step": 18
    },
    {
      "epoch": 0.07958115183246073,
      "grad_norm": 0.4528507888317108,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.4522,
      "step": 19
    },
    {
      "epoch": 0.08376963350785341,
      "grad_norm": 0.4718516767024994,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5029,
      "step": 20
    },
    {
      "epoch": 0.08795811518324607,
      "grad_norm": 0.41982200741767883,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.4611,
      "step": 21
    },
    {
      "epoch": 0.09214659685863874,
      "grad_norm": 0.3980315327644348,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.3786,
      "step": 22
    },
    {
      "epoch": 0.09633507853403141,
      "grad_norm": 0.4060964286327362,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.3963,
      "step": 23
    },
    {
      "epoch": 0.10052356020942409,
      "grad_norm": 0.3943502902984619,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.3841,
      "step": 24
    },
    {
      "epoch": 0.10471204188481675,
      "grad_norm": 0.40681180357933044,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.4104,
      "step": 25
    },
    {
      "epoch": 0.10890052356020942,
      "grad_norm": 0.4119963049888611,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.3985,
      "step": 26
    },
    {
      "epoch": 0.1130890052356021,
      "grad_norm": 0.42287012934684753,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4265,
      "step": 27
    },
    {
      "epoch": 0.11727748691099477,
      "grad_norm": 0.4382915794849396,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.3904,
      "step": 28
    },
    {
      "epoch": 0.12146596858638743,
      "grad_norm": 0.45694679021835327,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.4149,
      "step": 29
    },
    {
      "epoch": 0.1256544502617801,
      "grad_norm": 0.48638594150543213,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.39,
      "step": 30
    },
    {
      "epoch": 0.12984293193717278,
      "grad_norm": 0.5300375819206238,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.3883,
      "step": 31
    },
    {
      "epoch": 0.13403141361256546,
      "grad_norm": 0.5210663676261902,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.4515,
      "step": 32
    },
    {
      "epoch": 0.1382198952879581,
      "grad_norm": 0.5227262377738953,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.3944,
      "step": 33
    },
    {
      "epoch": 0.1424083769633508,
      "grad_norm": 0.5467104315757751,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.4712,
      "step": 34
    },
    {
      "epoch": 0.14659685863874344,
      "grad_norm": 0.5446538329124451,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.3683,
      "step": 35
    },
    {
      "epoch": 0.15078534031413612,
      "grad_norm": 0.5889321565628052,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.3675,
      "step": 36
    },
    {
      "epoch": 0.1549738219895288,
      "grad_norm": 0.5657311677932739,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.3347,
      "step": 37
    },
    {
      "epoch": 0.15916230366492146,
      "grad_norm": 0.6621028780937195,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.3371,
      "step": 38
    },
    {
      "epoch": 0.16335078534031414,
      "grad_norm": 0.5807614326477051,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.3406,
      "step": 39
    },
    {
      "epoch": 0.16753926701570682,
      "grad_norm": 0.5891103744506836,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.3347,
      "step": 40
    },
    {
      "epoch": 0.17172774869109947,
      "grad_norm": 0.6490166187286377,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.3791,
      "step": 41
    },
    {
      "epoch": 0.17591623036649215,
      "grad_norm": 0.670409083366394,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.3146,
      "step": 42
    },
    {
      "epoch": 0.18010471204188483,
      "grad_norm": 0.6172012686729431,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.3258,
      "step": 43
    },
    {
      "epoch": 0.18429319371727748,
      "grad_norm": 0.731728196144104,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.3535,
      "step": 44
    },
    {
      "epoch": 0.18848167539267016,
      "grad_norm": 0.6701034307479858,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.3067,
      "step": 45
    },
    {
      "epoch": 0.19267015706806281,
      "grad_norm": 0.7045776844024658,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.2787,
      "step": 46
    },
    {
      "epoch": 0.1968586387434555,
      "grad_norm": 0.7145847082138062,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.3167,
      "step": 47
    },
    {
      "epoch": 0.20104712041884817,
      "grad_norm": 0.7663804292678833,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2806,
      "step": 48
    },
    {
      "epoch": 0.20523560209424083,
      "grad_norm": 0.9702144265174866,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.3609,
      "step": 49
    },
    {
      "epoch": 0.2094240837696335,
      "grad_norm": 1.0464814901351929,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.2305,
      "step": 50
    },
    {
      "epoch": 0.2094240837696335,
      "eval_loss": 1.4609953165054321,
      "eval_runtime": 29.0147,
      "eval_samples_per_second": 13.889,
      "eval_steps_per_second": 3.481,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.71020323176448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}