{
  "best_metric": 6.368386268615723,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.1867704280155642,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002490272373540856,
      "grad_norm": 4.651301383972168,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 7.3638,
      "step": 1
    },
    {
      "epoch": 0.002490272373540856,
      "eval_loss": 7.0145440101623535,
      "eval_runtime": 0.468,
      "eval_samples_per_second": 106.837,
      "eval_steps_per_second": 27.777,
      "step": 1
    },
    {
      "epoch": 0.004980544747081712,
      "grad_norm": 2.4325013160705566,
      "learning_rate": 6.666666666666667e-05,
      "loss": 7.2351,
      "step": 2
    },
    {
      "epoch": 0.007470817120622568,
      "grad_norm": 2.669245719909668,
      "learning_rate": 0.0001,
      "loss": 7.4741,
      "step": 3
    },
    {
      "epoch": 0.009961089494163425,
      "grad_norm": 2.6087687015533447,
      "learning_rate": 9.99571699711836e-05,
      "loss": 7.4151,
      "step": 4
    },
    {
      "epoch": 0.012451361867704281,
      "grad_norm": 2.327425241470337,
      "learning_rate": 9.982876141412856e-05,
      "loss": 7.3941,
      "step": 5
    },
    {
      "epoch": 0.014941634241245135,
      "grad_norm": 2.1162900924682617,
      "learning_rate": 9.961501876182148e-05,
      "loss": 7.2274,
      "step": 6
    },
    {
      "epoch": 0.017431906614785993,
      "grad_norm": 2.0817477703094482,
      "learning_rate": 9.931634888554937e-05,
      "loss": 7.3322,
      "step": 7
    },
    {
      "epoch": 0.01992217898832685,
      "grad_norm": 1.9033664464950562,
      "learning_rate": 9.893332032039701e-05,
      "loss": 7.241,
      "step": 8
    },
    {
      "epoch": 0.022412451361867706,
      "grad_norm": 2.0073659420013428,
      "learning_rate": 9.846666218300807e-05,
      "loss": 7.165,
      "step": 9
    },
    {
      "epoch": 0.024902723735408562,
      "grad_norm": 2.191962242126465,
      "learning_rate": 9.791726278367022e-05,
      "loss": 7.1324,
      "step": 10
    },
    {
      "epoch": 0.027392996108949415,
      "grad_norm": 2.5749411582946777,
      "learning_rate": 9.728616793536588e-05,
      "loss": 7.1557,
      "step": 11
    },
    {
      "epoch": 0.02988326848249027,
      "grad_norm": 3.204463005065918,
      "learning_rate": 9.657457896300791e-05,
      "loss": 6.5895,
      "step": 12
    },
    {
      "epoch": 0.03237354085603113,
      "grad_norm": 1.7733168601989746,
      "learning_rate": 9.578385041664925e-05,
      "loss": 6.9292,
      "step": 13
    },
    {
      "epoch": 0.03486381322957199,
      "grad_norm": 1.2914466857910156,
      "learning_rate": 9.491548749301997e-05,
      "loss": 6.8379,
      "step": 14
    },
    {
      "epoch": 0.03735408560311284,
      "grad_norm": 1.261443853378296,
      "learning_rate": 9.397114317029975e-05,
      "loss": 7.0811,
      "step": 15
    },
    {
      "epoch": 0.0398443579766537,
      "grad_norm": 1.2122100591659546,
      "learning_rate": 9.295261506157986e-05,
      "loss": 7.038,
      "step": 16
    },
    {
      "epoch": 0.04233463035019455,
      "grad_norm": 1.1478087902069092,
      "learning_rate": 9.186184199300464e-05,
      "loss": 7.0881,
      "step": 17
    },
    {
      "epoch": 0.04482490272373541,
      "grad_norm": 1.0610593557357788,
      "learning_rate": 9.070090031310558e-05,
      "loss": 7.0056,
      "step": 18
    },
    {
      "epoch": 0.047315175097276264,
      "grad_norm": 1.1188586950302124,
      "learning_rate": 8.947199994035401e-05,
      "loss": 6.9136,
      "step": 19
    },
    {
      "epoch": 0.049805447470817124,
      "grad_norm": 1.1458325386047363,
      "learning_rate": 8.817748015645558e-05,
      "loss": 6.9737,
      "step": 20
    },
    {
      "epoch": 0.05229571984435798,
      "grad_norm": 1.067223310470581,
      "learning_rate": 8.681980515339464e-05,
      "loss": 6.876,
      "step": 21
    },
    {
      "epoch": 0.05478599221789883,
      "grad_norm": 1.486210823059082,
      "learning_rate": 8.540155934270471e-05,
      "loss": 6.7558,
      "step": 22
    },
    {
      "epoch": 0.05727626459143969,
      "grad_norm": 1.893701434135437,
      "learning_rate": 8.392544243589427e-05,
      "loss": 6.7791,
      "step": 23
    },
    {
      "epoch": 0.05976653696498054,
      "grad_norm": 2.173220157623291,
      "learning_rate": 8.239426430539243e-05,
      "loss": 6.7891,
      "step": 24
    },
    {
      "epoch": 0.0622568093385214,
      "grad_norm": 2.901264190673828,
      "learning_rate": 8.081093963579707e-05,
      "loss": 6.4873,
      "step": 25
    },
    {
      "epoch": 0.0622568093385214,
      "eval_loss": 6.543909072875977,
      "eval_runtime": 0.4765,
      "eval_samples_per_second": 104.926,
      "eval_steps_per_second": 27.281,
      "step": 25
    },
    {
      "epoch": 0.06474708171206225,
      "grad_norm": 3.1084837913513184,
      "learning_rate": 7.917848237560709e-05,
      "loss": 6.6169,
      "step": 26
    },
    {
      "epoch": 0.06723735408560311,
      "grad_norm": 1.2209361791610718,
      "learning_rate": 7.75e-05,
      "loss": 6.7791,
      "step": 27
    },
    {
      "epoch": 0.06972762645914397,
      "grad_norm": 1.1099854707717896,
      "learning_rate": 7.577868759557654e-05,
      "loss": 6.936,
      "step": 28
    },
    {
      "epoch": 0.07221789883268483,
      "grad_norm": 1.0699315071105957,
      "learning_rate": 7.401782177833148e-05,
      "loss": 6.8154,
      "step": 29
    },
    {
      "epoch": 0.07470817120622568,
      "grad_norm": 0.9406839609146118,
      "learning_rate": 7.222075445642904e-05,
      "loss": 6.988,
      "step": 30
    },
    {
      "epoch": 0.07719844357976653,
      "grad_norm": 0.9526640176773071,
      "learning_rate": 7.03909064496551e-05,
      "loss": 6.7899,
      "step": 31
    },
    {
      "epoch": 0.0796887159533074,
      "grad_norm": 0.8295072913169861,
      "learning_rate": 6.853176097769229e-05,
      "loss": 6.7357,
      "step": 32
    },
    {
      "epoch": 0.08217898832684825,
      "grad_norm": 0.9567013382911682,
      "learning_rate": 6.664685702961344e-05,
      "loss": 6.797,
      "step": 33
    },
    {
      "epoch": 0.0846692607003891,
      "grad_norm": 1.071341872215271,
      "learning_rate": 6.473978262721463e-05,
      "loss": 6.6351,
      "step": 34
    },
    {
      "epoch": 0.08715953307392996,
      "grad_norm": 1.3368276357650757,
      "learning_rate": 6.281416799501188e-05,
      "loss": 6.6517,
      "step": 35
    },
    {
      "epoch": 0.08964980544747082,
      "grad_norm": 1.7732629776000977,
      "learning_rate": 6.087367864990233e-05,
      "loss": 6.4047,
      "step": 36
    },
    {
      "epoch": 0.09214007782101168,
      "grad_norm": 2.385563850402832,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 6.4936,
      "step": 37
    },
    {
      "epoch": 0.09463035019455253,
      "grad_norm": 2.034431219100952,
      "learning_rate": 5.696287243144013e-05,
      "loss": 7.0241,
      "step": 38
    },
    {
      "epoch": 0.09712062256809338,
      "grad_norm": 0.9206064343452454,
      "learning_rate": 5.500000000000001e-05,
      "loss": 6.7179,
      "step": 39
    },
    {
      "epoch": 0.09961089494163425,
      "grad_norm": 0.995243489742279,
      "learning_rate": 5.303712756855988e-05,
      "loss": 6.8535,
      "step": 40
    },
    {
      "epoch": 0.1021011673151751,
      "grad_norm": 0.9085476994514465,
      "learning_rate": 5.107799157635538e-05,
      "loss": 6.7739,
      "step": 41
    },
    {
      "epoch": 0.10459143968871595,
      "grad_norm": 0.8075990080833435,
      "learning_rate": 4.912632135009769e-05,
      "loss": 6.8463,
      "step": 42
    },
    {
      "epoch": 0.1070817120622568,
      "grad_norm": 0.7797780632972717,
      "learning_rate": 4.718583200498814e-05,
      "loss": 6.7627,
      "step": 43
    },
    {
      "epoch": 0.10957198443579766,
      "grad_norm": 0.7625030279159546,
      "learning_rate": 4.526021737278538e-05,
      "loss": 6.7574,
      "step": 44
    },
    {
      "epoch": 0.11206225680933853,
      "grad_norm": 0.788215160369873,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 6.653,
      "step": 45
    },
    {
      "epoch": 0.11455252918287938,
      "grad_norm": 1.022986888885498,
      "learning_rate": 4.146823902230772e-05,
      "loss": 6.7437,
      "step": 46
    },
    {
      "epoch": 0.11704280155642023,
      "grad_norm": 1.1553353071212769,
      "learning_rate": 3.960909355034491e-05,
      "loss": 6.5571,
      "step": 47
    },
    {
      "epoch": 0.11953307392996108,
      "grad_norm": 1.4759111404418945,
      "learning_rate": 3.777924554357096e-05,
      "loss": 6.4163,
      "step": 48
    },
    {
      "epoch": 0.12202334630350195,
      "grad_norm": 1.8967125415802002,
      "learning_rate": 3.598217822166854e-05,
      "loss": 6.7076,
      "step": 49
    },
    {
      "epoch": 0.1245136186770428,
      "grad_norm": 2.9591472148895264,
      "learning_rate": 3.422131240442349e-05,
      "loss": 6.5811,
      "step": 50
    },
    {
      "epoch": 0.1245136186770428,
      "eval_loss": 6.405816078186035,
      "eval_runtime": 0.4887,
      "eval_samples_per_second": 102.322,
      "eval_steps_per_second": 26.604,
      "step": 50
    },
    {
      "epoch": 0.12700389105058366,
      "grad_norm": 0.8649512529373169,
      "learning_rate": 3.250000000000001e-05,
      "loss": 6.7933,
      "step": 51
    },
    {
      "epoch": 0.1294941634241245,
      "grad_norm": 0.8127966523170471,
      "learning_rate": 3.082151762439293e-05,
      "loss": 6.8069,
      "step": 52
    },
    {
      "epoch": 0.13198443579766536,
      "grad_norm": 0.8927196264266968,
      "learning_rate": 2.9189060364202943e-05,
      "loss": 6.707,
      "step": 53
    },
    {
      "epoch": 0.13447470817120621,
      "grad_norm": 0.7540999054908752,
      "learning_rate": 2.760573569460757e-05,
      "loss": 6.8266,
      "step": 54
    },
    {
      "epoch": 0.1369649805447471,
      "grad_norm": 0.7092488408088684,
      "learning_rate": 2.6074557564105727e-05,
      "loss": 6.7882,
      "step": 55
    },
    {
      "epoch": 0.13945525291828795,
      "grad_norm": 0.6673146486282349,
      "learning_rate": 2.459844065729529e-05,
      "loss": 6.7766,
      "step": 56
    },
    {
      "epoch": 0.1419455252918288,
      "grad_norm": 0.7161771655082703,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 6.821,
      "step": 57
    },
    {
      "epoch": 0.14443579766536965,
      "grad_norm": 0.8523626327514648,
      "learning_rate": 2.1822519843544424e-05,
      "loss": 6.6849,
      "step": 58
    },
    {
      "epoch": 0.1469260700389105,
      "grad_norm": 1.0966269969940186,
      "learning_rate": 2.0528000059645997e-05,
      "loss": 6.6321,
      "step": 59
    },
    {
      "epoch": 0.14941634241245136,
      "grad_norm": 1.2441387176513672,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 6.4888,
      "step": 60
    },
    {
      "epoch": 0.1519066147859922,
      "grad_norm": 1.6971194744110107,
      "learning_rate": 1.8138158006995364e-05,
      "loss": 6.4694,
      "step": 61
    },
    {
      "epoch": 0.15439688715953306,
      "grad_norm": 2.2189457416534424,
      "learning_rate": 1.7047384938420154e-05,
      "loss": 6.4204,
      "step": 62
    },
    {
      "epoch": 0.15688715953307392,
      "grad_norm": 1.4777802228927612,
      "learning_rate": 1.602885682970026e-05,
      "loss": 6.7514,
      "step": 63
    },
    {
      "epoch": 0.1593774319066148,
      "grad_norm": 1.0032076835632324,
      "learning_rate": 1.5084512506980026e-05,
      "loss": 6.4532,
      "step": 64
    },
    {
      "epoch": 0.16186770428015565,
      "grad_norm": 0.8604456186294556,
      "learning_rate": 1.4216149583350754e-05,
      "loss": 6.7384,
      "step": 65
    },
    {
      "epoch": 0.1643579766536965,
      "grad_norm": 0.8361185789108276,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 6.7395,
      "step": 66
    },
    {
      "epoch": 0.16684824902723736,
      "grad_norm": 0.7592188119888306,
      "learning_rate": 1.2713832064634126e-05,
      "loss": 6.7701,
      "step": 67
    },
    {
      "epoch": 0.1693385214007782,
      "grad_norm": 0.6846341490745544,
      "learning_rate": 1.2082737216329794e-05,
      "loss": 6.8228,
      "step": 68
    },
    {
      "epoch": 0.17182879377431906,
      "grad_norm": 0.7539795637130737,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 6.8373,
      "step": 69
    },
    {
      "epoch": 0.1743190661478599,
      "grad_norm": 0.7585219740867615,
      "learning_rate": 1.1066679679603e-05,
      "loss": 6.7546,
      "step": 70
    },
    {
      "epoch": 0.17680933852140077,
      "grad_norm": 0.9256238341331482,
      "learning_rate": 1.0683651114450641e-05,
      "loss": 6.6777,
      "step": 71
    },
    {
      "epoch": 0.17929961089494165,
      "grad_norm": 1.067570686340332,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 6.5155,
      "step": 72
    },
    {
      "epoch": 0.1817898832684825,
      "grad_norm": 1.4094899892807007,
      "learning_rate": 1.017123858587145e-05,
      "loss": 6.5212,
      "step": 73
    },
    {
      "epoch": 0.18428015564202335,
      "grad_norm": 1.8948956727981567,
      "learning_rate": 1.00428300288164e-05,
      "loss": 6.3666,
      "step": 74
    },
    {
      "epoch": 0.1867704280155642,
      "grad_norm": 2.406057834625244,
      "learning_rate": 1e-05,
      "loss": 6.5367,
      "step": 75
    },
    {
      "epoch": 0.1867704280155642,
      "eval_loss": 6.368386268615723,
      "eval_runtime": 0.4803,
      "eval_samples_per_second": 104.107,
      "eval_steps_per_second": 27.068,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 348056949096448.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}