{
  "best_metric": 2.149948835372925,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.7316017316017316,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017316017316017316,
      "grad_norm": 2.8118698596954346,
      "learning_rate": 1e-05,
      "loss": 2.1187,
      "step": 1
    },
    {
      "epoch": 0.017316017316017316,
      "eval_loss": 3.7099266052246094,
      "eval_runtime": 4.3893,
      "eval_samples_per_second": 22.327,
      "eval_steps_per_second": 5.696,
      "step": 1
    },
    {
      "epoch": 0.03463203463203463,
      "grad_norm": 4.973637104034424,
      "learning_rate": 2e-05,
      "loss": 2.7977,
      "step": 2
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 4.760875225067139,
      "learning_rate": 3e-05,
      "loss": 2.7876,
      "step": 3
    },
    {
      "epoch": 0.06926406926406926,
      "grad_norm": 4.113471508026123,
      "learning_rate": 4e-05,
      "loss": 2.7467,
      "step": 4
    },
    {
      "epoch": 0.08658008658008658,
      "grad_norm": 3.091151475906372,
      "learning_rate": 5e-05,
      "loss": 2.8543,
      "step": 5
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 2.6705322265625,
      "learning_rate": 6e-05,
      "loss": 2.9262,
      "step": 6
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.8101789951324463,
      "learning_rate": 7e-05,
      "loss": 2.6595,
      "step": 7
    },
    {
      "epoch": 0.13852813852813853,
      "grad_norm": 3.463834285736084,
      "learning_rate": 8e-05,
      "loss": 2.833,
      "step": 8
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 3.838789701461792,
      "learning_rate": 9e-05,
      "loss": 2.8904,
      "step": 9
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 3.6583943367004395,
      "learning_rate": 0.0001,
      "loss": 2.8253,
      "step": 10
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.103412628173828,
      "learning_rate": 9.999071352056675e-05,
      "loss": 2.5754,
      "step": 11
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 4.752767562866211,
      "learning_rate": 9.9962857531815e-05,
      "loss": 2.7909,
      "step": 12
    },
    {
      "epoch": 0.22510822510822512,
      "grad_norm": 4.6153974533081055,
      "learning_rate": 9.99164423811074e-05,
      "loss": 2.8612,
      "step": 13
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 5.671820163726807,
      "learning_rate": 9.985148530977767e-05,
      "loss": 3.2352,
      "step": 14
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 1.8995760679244995,
      "learning_rate": 9.976801044672608e-05,
      "loss": 1.8384,
      "step": 15
    },
    {
      "epoch": 0.27705627705627706,
      "grad_norm": 1.86356782913208,
      "learning_rate": 9.966604879945659e-05,
      "loss": 2.4272,
      "step": 16
    },
    {
      "epoch": 0.2943722943722944,
      "grad_norm": 1.6119074821472168,
      "learning_rate": 9.954563824255878e-05,
      "loss": 2.3626,
      "step": 17
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 1.67992103099823,
      "learning_rate": 9.940682350363912e-05,
      "loss": 2.2748,
      "step": 18
    },
    {
      "epoch": 0.329004329004329,
      "grad_norm": 1.6707350015640259,
      "learning_rate": 9.924965614670629e-05,
      "loss": 2.1881,
      "step": 19
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 1.8515558242797852,
      "learning_rate": 9.907419455301741e-05,
      "loss": 2.0334,
      "step": 20
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.1287074089050293,
      "learning_rate": 9.888050389939172e-05,
      "loss": 2.3509,
      "step": 21
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.0685789585113525,
      "learning_rate": 9.866865613400008e-05,
      "loss": 2.2955,
      "step": 22
    },
    {
      "epoch": 0.39826839826839827,
      "grad_norm": 2.199742317199707,
      "learning_rate": 9.843872994963911e-05,
      "loss": 2.3759,
      "step": 23
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 2.4112186431884766,
      "learning_rate": 9.819081075450014e-05,
      "loss": 2.5115,
      "step": 24
    },
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 2.319316864013672,
      "learning_rate": 9.792499064044342e-05,
      "loss": 2.5079,
      "step": 25
    },
    {
      "epoch": 0.45021645021645024,
      "grad_norm": 2.4952006340026855,
      "learning_rate": 9.764136834878986e-05,
      "loss": 2.546,
      "step": 26
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 2.641359329223633,
      "learning_rate": 9.734004923364257e-05,
      "loss": 2.4089,
      "step": 27
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 5.115784168243408,
      "learning_rate": 9.702114522275216e-05,
      "loss": 3.1355,
      "step": 28
    },
    {
      "epoch": 0.5021645021645021,
      "grad_norm": 1.3380645513534546,
      "learning_rate": 9.66847747759402e-05,
      "loss": 1.6216,
      "step": 29
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 2.2748000621795654,
      "learning_rate": 9.63310628410961e-05,
      "loss": 2.2642,
      "step": 30
    },
    {
      "epoch": 0.5367965367965368,
      "grad_norm": 1.6783227920532227,
      "learning_rate": 9.596014080776423e-05,
      "loss": 2.0759,
      "step": 31
    },
    {
      "epoch": 0.5541125541125541,
      "grad_norm": 1.5664422512054443,
      "learning_rate": 9.557214645833792e-05,
      "loss": 2.0632,
      "step": 32
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.5744460821151733,
      "learning_rate": 9.516722391687902e-05,
      "loss": 2.0214,
      "step": 33
    },
    {
      "epoch": 0.5887445887445888,
      "grad_norm": 1.7587584257125854,
      "learning_rate": 9.474552359558166e-05,
      "loss": 2.0404,
      "step": 34
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.9254662990570068,
      "learning_rate": 9.43072021389003e-05,
      "loss": 2.2543,
      "step": 35
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 1.965366005897522,
      "learning_rate": 9.38524223653626e-05,
      "loss": 2.1501,
      "step": 36
    },
    {
      "epoch": 0.6406926406926406,
      "grad_norm": 2.1672956943511963,
      "learning_rate": 9.338135320708911e-05,
      "loss": 2.3718,
      "step": 37
    },
    {
      "epoch": 0.658008658008658,
      "grad_norm": 2.3108174800872803,
      "learning_rate": 9.289416964704185e-05,
      "loss": 2.6269,
      "step": 38
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 2.326822280883789,
      "learning_rate": 9.239105265402525e-05,
      "loss": 2.3544,
      "step": 39
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 2.420606851577759,
      "learning_rate": 9.187218911546362e-05,
      "loss": 2.33,
      "step": 40
    },
    {
      "epoch": 0.70995670995671,
      "grad_norm": 2.5650737285614014,
      "learning_rate": 9.133777176798013e-05,
      "loss": 2.3837,
      "step": 41
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 4.262178897857666,
      "learning_rate": 9.078799912580304e-05,
      "loss": 2.3165,
      "step": 42
    },
    {
      "epoch": 0.7445887445887446,
      "grad_norm": 0.9868830442428589,
      "learning_rate": 9.022307540702576e-05,
      "loss": 1.7471,
      "step": 43
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.710825800895691,
      "learning_rate": 8.964321045774807e-05,
      "loss": 2.0541,
      "step": 44
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 1.7059110403060913,
      "learning_rate": 8.904861967412703e-05,
      "loss": 2.0234,
      "step": 45
    },
    {
      "epoch": 0.7965367965367965,
      "grad_norm": 1.6046017408370972,
      "learning_rate": 8.843952392236594e-05,
      "loss": 1.8639,
      "step": 46
    },
    {
      "epoch": 0.8138528138528138,
      "grad_norm": 1.6054553985595703,
      "learning_rate": 8.781614945667169e-05,
      "loss": 2.1819,
      "step": 47
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 1.4989557266235352,
      "learning_rate": 8.717872783521047e-05,
      "loss": 2.0109,
      "step": 48
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 1.6607235670089722,
      "learning_rate": 8.65274958340934e-05,
      "loss": 1.8743,
      "step": 49
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 1.8187165260314941,
      "learning_rate": 8.586269535942385e-05,
      "loss": 2.148,
      "step": 50
    },
    {
      "epoch": 0.8658008658008658,
      "eval_loss": 2.256721258163452,
      "eval_runtime": 4.4013,
      "eval_samples_per_second": 22.266,
      "eval_steps_per_second": 5.68,
      "step": 50
    },
    {
      "epoch": 0.8831168831168831,
      "grad_norm": 2.1010754108428955,
      "learning_rate": 8.518457335743926e-05,
      "loss": 2.3307,
      "step": 51
    },
    {
      "epoch": 0.9004329004329005,
      "grad_norm": 2.3242135047912598,
      "learning_rate": 8.449338172278059e-05,
      "loss": 2.4806,
      "step": 52
    },
    {
      "epoch": 0.9177489177489178,
      "grad_norm": 2.3536064624786377,
      "learning_rate": 8.378937720492384e-05,
      "loss": 2.2132,
      "step": 53
    },
    {
      "epoch": 0.935064935064935,
      "grad_norm": 2.595224618911743,
      "learning_rate": 8.307282131280804e-05,
      "loss": 2.2525,
      "step": 54
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 2.8772056102752686,
      "learning_rate": 8.23439802176954e-05,
      "loss": 2.4023,
      "step": 55
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 5.285353660583496,
      "learning_rate": 8.160312465429952e-05,
      "loss": 2.8273,
      "step": 56
    },
    {
      "epoch": 0.987012987012987,
      "grad_norm": 1.2868059873580933,
      "learning_rate": 8.085052982021847e-05,
      "loss": 1.8018,
      "step": 57
    },
    {
      "epoch": 1.0043290043290043,
      "grad_norm": 3.5397348403930664,
      "learning_rate": 8.008647527371023e-05,
      "loss": 2.9306,
      "step": 58
    },
    {
      "epoch": 1.0216450216450217,
      "grad_norm": 0.9906024932861328,
      "learning_rate": 7.931124482984802e-05,
      "loss": 1.6357,
      "step": 59
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 1.0218256711959839,
      "learning_rate": 7.85251264550948e-05,
      "loss": 1.729,
      "step": 60
    },
    {
      "epoch": 1.0562770562770563,
      "grad_norm": 1.1563177108764648,
      "learning_rate": 7.772841216033533e-05,
      "loss": 1.7074,
      "step": 61
    },
    {
      "epoch": 1.0735930735930737,
      "grad_norm": 1.2730008363723755,
      "learning_rate": 7.692139789240611e-05,
      "loss": 1.6385,
      "step": 62
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.366668701171875,
      "learning_rate": 7.610438342416319e-05,
      "loss": 1.5181,
      "step": 63
    },
    {
      "epoch": 1.1082251082251082,
      "grad_norm": 1.6161524057388306,
      "learning_rate": 7.527767224312883e-05,
      "loss": 1.8762,
      "step": 64
    },
    {
      "epoch": 1.1255411255411256,
      "grad_norm": 1.4192622900009155,
      "learning_rate": 7.44415714387582e-05,
      "loss": 1.4841,
      "step": 65
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.495239496231079,
      "learning_rate": 7.359639158836828e-05,
      "loss": 1.7021,
      "step": 66
    },
    {
      "epoch": 1.1601731601731602,
      "grad_norm": 1.729372262954712,
      "learning_rate": 7.274244664177097e-05,
      "loss": 1.8888,
      "step": 67
    },
    {
      "epoch": 1.1774891774891776,
      "grad_norm": 1.9363900423049927,
      "learning_rate": 7.188005380465364e-05,
      "loss": 1.734,
      "step": 68
    },
    {
      "epoch": 1.1948051948051948,
      "grad_norm": 2.3331375122070312,
      "learning_rate": 7.10095334207501e-05,
      "loss": 1.7476,
      "step": 69
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 2.6032962799072266,
      "learning_rate": 7.013120885284598e-05,
      "loss": 1.9506,
      "step": 70
    },
    {
      "epoch": 1.2294372294372296,
      "grad_norm": 2.9084725379943848,
      "learning_rate": 6.924540636266272e-05,
      "loss": 1.783,
      "step": 71
    },
    {
      "epoch": 1.2467532467532467,
      "grad_norm": 3.581970453262329,
      "learning_rate": 6.835245498966461e-05,
      "loss": 1.8422,
      "step": 72
    },
    {
      "epoch": 1.2640692640692641,
      "grad_norm": 1.1855902671813965,
      "learning_rate": 6.745268642883404e-05,
      "loss": 1.3828,
      "step": 73
    },
    {
      "epoch": 1.2813852813852815,
      "grad_norm": 1.5189799070358276,
      "learning_rate": 6.654643490746042e-05,
      "loss": 1.8042,
      "step": 74
    },
    {
      "epoch": 1.2987012987012987,
      "grad_norm": 1.53164541721344,
      "learning_rate": 6.563403706098833e-05,
      "loss": 1.9113,
      "step": 75
    },
    {
      "epoch": 1.316017316017316,
      "grad_norm": 1.3554658889770508,
      "learning_rate": 6.471583180797121e-05,
      "loss": 1.3116,
      "step": 76
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.5969181060791016,
      "learning_rate": 6.379216022417696e-05,
      "loss": 1.7443,
      "step": 77
    },
    {
      "epoch": 1.3506493506493507,
      "grad_norm": 1.6001543998718262,
      "learning_rate": 6.286336541589224e-05,
      "loss": 1.6611,
      "step": 78
    },
    {
      "epoch": 1.3679653679653678,
      "grad_norm": 1.6653358936309814,
      "learning_rate": 6.192979239247243e-05,
      "loss": 1.5659,
      "step": 79
    },
    {
      "epoch": 1.3852813852813852,
      "grad_norm": 1.736785888671875,
      "learning_rate": 6.0991787938184784e-05,
      "loss": 1.773,
      "step": 80
    },
    {
      "epoch": 1.4025974025974026,
      "grad_norm": 1.7712799310684204,
      "learning_rate": 6.004970048339226e-05,
      "loss": 1.5936,
      "step": 81
    },
    {
      "epoch": 1.4199134199134198,
      "grad_norm": 1.8556205034255981,
      "learning_rate": 5.910387997512573e-05,
      "loss": 1.7578,
      "step": 82
    },
    {
      "epoch": 1.4372294372294372,
      "grad_norm": 2.0250351428985596,
      "learning_rate": 5.8154677747093134e-05,
      "loss": 1.6592,
      "step": 83
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 2.347397565841675,
      "learning_rate": 5.7202446389173223e-05,
      "loss": 1.8997,
      "step": 84
    },
    {
      "epoch": 1.4718614718614718,
      "grad_norm": 2.838571786880493,
      "learning_rate": 5.624753961644281e-05,
      "loss": 1.6595,
      "step": 85
    },
    {
      "epoch": 1.4891774891774892,
      "grad_norm": 2.8864710330963135,
      "learning_rate": 5.5290312137786146e-05,
      "loss": 1.5153,
      "step": 86
    },
    {
      "epoch": 1.5064935064935066,
      "grad_norm": 0.9010306000709534,
      "learning_rate": 5.433111952413495e-05,
      "loss": 1.4468,
      "step": 87
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 1.2178982496261597,
      "learning_rate": 5.33703180763884e-05,
      "loss": 1.8386,
      "step": 88
    },
    {
      "epoch": 1.5411255411255411,
      "grad_norm": 1.256874918937683,
      "learning_rate": 5.240826469306187e-05,
      "loss": 1.6508,
      "step": 89
    },
    {
      "epoch": 1.5584415584415585,
      "grad_norm": 1.3813403844833374,
      "learning_rate": 5.144531673771363e-05,
      "loss": 1.4675,
      "step": 90
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 1.4501692056655884,
      "learning_rate": 5.048183190619904e-05,
      "loss": 1.5286,
      "step": 91
    },
    {
      "epoch": 1.593073593073593,
      "grad_norm": 1.596665382385254,
      "learning_rate": 4.951816809380097e-05,
      "loss": 1.5156,
      "step": 92
    },
    {
      "epoch": 1.6103896103896105,
      "grad_norm": 1.736958384513855,
      "learning_rate": 4.855468326228638e-05,
      "loss": 1.554,
      "step": 93
    },
    {
      "epoch": 1.6277056277056277,
      "grad_norm": 1.8774197101593018,
      "learning_rate": 4.759173530693814e-05,
      "loss": 1.6657,
      "step": 94
    },
    {
      "epoch": 1.645021645021645,
      "grad_norm": 2.086031675338745,
      "learning_rate": 4.6629681923611603e-05,
      "loss": 1.7142,
      "step": 95
    },
    {
      "epoch": 1.6623376623376624,
      "grad_norm": 2.1625614166259766,
      "learning_rate": 4.566888047586507e-05,
      "loss": 1.8664,
      "step": 96
    },
    {
      "epoch": 1.6796536796536796,
      "grad_norm": 2.298473358154297,
      "learning_rate": 4.4709687862213866e-05,
      "loss": 1.6924,
      "step": 97
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 2.3079867362976074,
      "learning_rate": 4.3752460383557195e-05,
      "loss": 1.7353,
      "step": 98
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 3.372159004211426,
      "learning_rate": 4.27975536108268e-05,
      "loss": 1.8684,
      "step": 99
    },
    {
      "epoch": 1.7316017316017316,
      "grad_norm": 3.0336737632751465,
      "learning_rate": 4.1845322252906864e-05,
      "loss": 1.4009,
      "step": 100
    },
    {
      "epoch": 1.7316017316017316,
      "eval_loss": 2.149948835372925,
      "eval_runtime": 4.3993,
      "eval_samples_per_second": 22.276,
      "eval_steps_per_second": 5.683,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 173,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 4.137205760262144e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}