{
  "best_metric": 2.1530466079711914,
  "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": 2.8331797122955322,
      "learning_rate": 1e-05,
      "loss": 2.1187,
      "step": 1
    },
    {
      "epoch": 0.017316017316017316,
      "eval_loss": 3.7099266052246094,
      "eval_runtime": 4.4282,
      "eval_samples_per_second": 22.131,
      "eval_steps_per_second": 5.646,
      "step": 1
    },
    {
      "epoch": 0.03463203463203463,
      "grad_norm": 5.01226806640625,
      "learning_rate": 2e-05,
      "loss": 2.7977,
      "step": 2
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 4.797194480895996,
      "learning_rate": 3e-05,
      "loss": 2.7871,
      "step": 3
    },
    {
      "epoch": 0.06926406926406926,
      "grad_norm": 4.131883144378662,
      "learning_rate": 4e-05,
      "loss": 2.7443,
      "step": 4
    },
    {
      "epoch": 0.08658008658008658,
      "grad_norm": 3.087463855743408,
      "learning_rate": 5e-05,
      "loss": 2.8541,
      "step": 5
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 2.660694122314453,
      "learning_rate": 6e-05,
      "loss": 2.9244,
      "step": 6
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.8298134803771973,
      "learning_rate": 7e-05,
      "loss": 2.6589,
      "step": 7
    },
    {
      "epoch": 0.13852813852813853,
      "grad_norm": 3.4778504371643066,
      "learning_rate": 8e-05,
      "loss": 2.8337,
      "step": 8
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 3.807507038116455,
      "learning_rate": 9e-05,
      "loss": 2.892,
      "step": 9
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 3.6214892864227295,
      "learning_rate": 0.0001,
      "loss": 2.8247,
      "step": 10
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.1061809062957764,
      "learning_rate": 9.999071352056675e-05,
      "loss": 2.5751,
      "step": 11
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 4.615087509155273,
      "learning_rate": 9.9962857531815e-05,
      "loss": 2.7903,
      "step": 12
    },
    {
      "epoch": 0.22510822510822512,
      "grad_norm": 4.513574600219727,
      "learning_rate": 9.99164423811074e-05,
      "loss": 2.8595,
      "step": 13
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 5.717080593109131,
      "learning_rate": 9.985148530977767e-05,
      "loss": 3.224,
      "step": 14
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 1.9179377555847168,
      "learning_rate": 9.976801044672608e-05,
      "loss": 1.8395,
      "step": 15
    },
    {
      "epoch": 0.27705627705627706,
      "grad_norm": 1.8630417585372925,
      "learning_rate": 9.966604879945659e-05,
      "loss": 2.4277,
      "step": 16
    },
    {
      "epoch": 0.2943722943722944,
      "grad_norm": 1.6356393098831177,
      "learning_rate": 9.954563824255878e-05,
      "loss": 2.3636,
      "step": 17
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 1.710647463798523,
      "learning_rate": 9.940682350363912e-05,
      "loss": 2.2757,
      "step": 18
    },
    {
      "epoch": 0.329004329004329,
      "grad_norm": 1.6765035390853882,
      "learning_rate": 9.924965614670629e-05,
      "loss": 2.1883,
      "step": 19
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 1.8588552474975586,
      "learning_rate": 9.907419455301741e-05,
      "loss": 2.0356,
      "step": 20
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.132901191711426,
      "learning_rate": 9.888050389939172e-05,
      "loss": 2.3527,
      "step": 21
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.075359582901001,
      "learning_rate": 9.866865613400008e-05,
      "loss": 2.3003,
      "step": 22
    },
    {
      "epoch": 0.39826839826839827,
      "grad_norm": 2.2094523906707764,
      "learning_rate": 9.843872994963911e-05,
      "loss": 2.3735,
      "step": 23
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 2.4340925216674805,
      "learning_rate": 9.819081075450014e-05,
      "loss": 2.5142,
      "step": 24
    },
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 2.3378214836120605,
      "learning_rate": 9.792499064044342e-05,
      "loss": 2.5139,
      "step": 25
    },
    {
      "epoch": 0.45021645021645024,
      "grad_norm": 2.4948999881744385,
      "learning_rate": 9.764136834878986e-05,
      "loss": 2.5467,
      "step": 26
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 2.667940139770508,
      "learning_rate": 9.734004923364257e-05,
      "loss": 2.4101,
      "step": 27
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 5.119446277618408,
      "learning_rate": 9.702114522275216e-05,
      "loss": 3.1252,
      "step": 28
    },
    {
      "epoch": 0.5021645021645021,
      "grad_norm": 1.3318713903427124,
      "learning_rate": 9.66847747759402e-05,
      "loss": 1.6226,
      "step": 29
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 2.2476823329925537,
      "learning_rate": 9.63310628410961e-05,
      "loss": 2.2634,
      "step": 30
    },
    {
      "epoch": 0.5367965367965368,
      "grad_norm": 1.6670700311660767,
      "learning_rate": 9.596014080776423e-05,
      "loss": 2.0752,
      "step": 31
    },
    {
      "epoch": 0.5541125541125541,
      "grad_norm": 1.5613207817077637,
      "learning_rate": 9.557214645833792e-05,
      "loss": 2.0647,
      "step": 32
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.5586175918579102,
      "learning_rate": 9.516722391687902e-05,
      "loss": 2.0191,
      "step": 33
    },
    {
      "epoch": 0.5887445887445888,
      "grad_norm": 1.7481515407562256,
      "learning_rate": 9.474552359558166e-05,
      "loss": 2.0408,
      "step": 34
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.908803939819336,
      "learning_rate": 9.43072021389003e-05,
      "loss": 2.251,
      "step": 35
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 1.9676694869995117,
      "learning_rate": 9.38524223653626e-05,
      "loss": 2.1518,
      "step": 36
    },
    {
      "epoch": 0.6406926406926406,
      "grad_norm": 2.245049238204956,
      "learning_rate": 9.338135320708911e-05,
      "loss": 2.3752,
      "step": 37
    },
    {
      "epoch": 0.658008658008658,
      "grad_norm": 2.3313148021698,
      "learning_rate": 9.289416964704185e-05,
      "loss": 2.6293,
      "step": 38
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 2.3561019897460938,
      "learning_rate": 9.239105265402525e-05,
      "loss": 2.3578,
      "step": 39
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 2.4642536640167236,
      "learning_rate": 9.187218911546362e-05,
      "loss": 2.3347,
      "step": 40
    },
    {
      "epoch": 0.70995670995671,
      "grad_norm": 2.577402353286743,
      "learning_rate": 9.133777176798013e-05,
      "loss": 2.3815,
      "step": 41
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 4.283364772796631,
      "learning_rate": 9.078799912580304e-05,
      "loss": 2.3154,
      "step": 42
    },
    {
      "epoch": 0.7445887445887446,
      "grad_norm": 1.0042027235031128,
      "learning_rate": 9.022307540702576e-05,
      "loss": 1.7462,
      "step": 43
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.7617307901382446,
      "learning_rate": 8.964321045774807e-05,
      "loss": 2.0569,
      "step": 44
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 1.7388392686843872,
      "learning_rate": 8.904861967412703e-05,
      "loss": 2.0223,
      "step": 45
    },
    {
      "epoch": 0.7965367965367965,
      "grad_norm": 1.6279188394546509,
      "learning_rate": 8.843952392236594e-05,
      "loss": 1.8667,
      "step": 46
    },
    {
      "epoch": 0.8138528138528138,
      "grad_norm": 1.613118290901184,
      "learning_rate": 8.781614945667169e-05,
      "loss": 2.1793,
      "step": 47
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 1.5092192888259888,
      "learning_rate": 8.717872783521047e-05,
      "loss": 2.0122,
      "step": 48
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 1.6618455648422241,
      "learning_rate": 8.65274958340934e-05,
      "loss": 1.8772,
      "step": 49
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 1.820896863937378,
      "learning_rate": 8.586269535942385e-05,
      "loss": 2.1534,
      "step": 50
    },
    {
      "epoch": 0.8658008658008658,
      "eval_loss": 2.2589545249938965,
      "eval_runtime": 4.4124,
      "eval_samples_per_second": 22.21,
      "eval_steps_per_second": 5.666,
      "step": 50
    },
    {
      "epoch": 0.8831168831168831,
      "grad_norm": 2.0972702503204346,
      "learning_rate": 8.518457335743926e-05,
      "loss": 2.3293,
      "step": 51
    },
    {
      "epoch": 0.9004329004329005,
      "grad_norm": 2.350532293319702,
      "learning_rate": 8.449338172278059e-05,
      "loss": 2.4826,
      "step": 52
    },
    {
      "epoch": 0.9177489177489178,
      "grad_norm": 2.3178534507751465,
      "learning_rate": 8.378937720492384e-05,
      "loss": 2.2085,
      "step": 53
    },
    {
      "epoch": 0.935064935064935,
      "grad_norm": 2.572354793548584,
      "learning_rate": 8.307282131280804e-05,
      "loss": 2.2593,
      "step": 54
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 2.8676466941833496,
      "learning_rate": 8.23439802176954e-05,
      "loss": 2.401,
      "step": 55
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 5.183324813842773,
      "learning_rate": 8.160312465429952e-05,
      "loss": 2.8153,
      "step": 56
    },
    {
      "epoch": 0.987012987012987,
      "grad_norm": 1.302344560623169,
      "learning_rate": 8.085052982021847e-05,
      "loss": 1.8029,
      "step": 57
    },
    {
      "epoch": 1.0043290043290043,
      "grad_norm": 3.5733864307403564,
      "learning_rate": 8.008647527371023e-05,
      "loss": 2.9339,
      "step": 58
    },
    {
      "epoch": 1.0216450216450217,
      "grad_norm": 0.99031662940979,
      "learning_rate": 7.931124482984802e-05,
      "loss": 1.6368,
      "step": 59
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 1.045397162437439,
      "learning_rate": 7.85251264550948e-05,
      "loss": 1.7296,
      "step": 60
    },
    {
      "epoch": 1.0562770562770563,
      "grad_norm": 1.1642181873321533,
      "learning_rate": 7.772841216033533e-05,
      "loss": 1.7076,
      "step": 61
    },
    {
      "epoch": 1.0735930735930737,
      "grad_norm": 1.2963627576828003,
      "learning_rate": 7.692139789240611e-05,
      "loss": 1.6386,
      "step": 62
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.37860107421875,
      "learning_rate": 7.610438342416319e-05,
      "loss": 1.5183,
      "step": 63
    },
    {
      "epoch": 1.1082251082251082,
      "grad_norm": 1.6060508489608765,
      "learning_rate": 7.527767224312883e-05,
      "loss": 1.8744,
      "step": 64
    },
    {
      "epoch": 1.1255411255411256,
      "grad_norm": 1.3911950588226318,
      "learning_rate": 7.44415714387582e-05,
      "loss": 1.4808,
      "step": 65
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.5222082138061523,
      "learning_rate": 7.359639158836828e-05,
      "loss": 1.7056,
      "step": 66
    },
    {
      "epoch": 1.1601731601731602,
      "grad_norm": 1.7811347246170044,
      "learning_rate": 7.274244664177097e-05,
      "loss": 1.8924,
      "step": 67
    },
    {
      "epoch": 1.1774891774891776,
      "grad_norm": 1.972655177116394,
      "learning_rate": 7.188005380465364e-05,
      "loss": 1.7403,
      "step": 68
    },
    {
      "epoch": 1.1948051948051948,
      "grad_norm": 2.413468837738037,
      "learning_rate": 7.10095334207501e-05,
      "loss": 1.7472,
      "step": 69
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 2.587477207183838,
      "learning_rate": 7.013120885284598e-05,
      "loss": 1.9488,
      "step": 70
    },
    {
      "epoch": 1.2294372294372296,
      "grad_norm": 2.9659059047698975,
      "learning_rate": 6.924540636266272e-05,
      "loss": 1.7928,
      "step": 71
    },
    {
      "epoch": 1.2467532467532467,
      "grad_norm": 3.635132074356079,
      "learning_rate": 6.835245498966461e-05,
      "loss": 1.8512,
      "step": 72
    },
    {
      "epoch": 1.2640692640692641,
      "grad_norm": 1.1850864887237549,
      "learning_rate": 6.745268642883404e-05,
      "loss": 1.3889,
      "step": 73
    },
    {
      "epoch": 1.2813852813852815,
      "grad_norm": 1.5134196281433105,
      "learning_rate": 6.654643490746042e-05,
      "loss": 1.8089,
      "step": 74
    },
    {
      "epoch": 1.2987012987012987,
      "grad_norm": 1.5268129110336304,
      "learning_rate": 6.563403706098833e-05,
      "loss": 1.913,
      "step": 75
    },
    {
      "epoch": 1.316017316017316,
      "grad_norm": 1.3524274826049805,
      "learning_rate": 6.471583180797121e-05,
      "loss": 1.317,
      "step": 76
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.6053553819656372,
      "learning_rate": 6.379216022417696e-05,
      "loss": 1.7508,
      "step": 77
    },
    {
      "epoch": 1.3506493506493507,
      "grad_norm": 1.6736403703689575,
      "learning_rate": 6.286336541589224e-05,
      "loss": 1.6712,
      "step": 78
    },
    {
      "epoch": 1.3679653679653678,
      "grad_norm": 1.6220240592956543,
      "learning_rate": 6.192979239247243e-05,
      "loss": 1.5654,
      "step": 79
    },
    {
      "epoch": 1.3852813852813852,
      "grad_norm": 1.7063477039337158,
      "learning_rate": 6.0991787938184784e-05,
      "loss": 1.7755,
      "step": 80
    },
    {
      "epoch": 1.4025974025974026,
      "grad_norm": 1.7277164459228516,
      "learning_rate": 6.004970048339226e-05,
      "loss": 1.5972,
      "step": 81
    },
    {
      "epoch": 1.4199134199134198,
      "grad_norm": 1.855843186378479,
      "learning_rate": 5.910387997512573e-05,
      "loss": 1.7611,
      "step": 82
    },
    {
      "epoch": 1.4372294372294372,
      "grad_norm": 2.0694801807403564,
      "learning_rate": 5.8154677747093134e-05,
      "loss": 1.6634,
      "step": 83
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 2.3597748279571533,
      "learning_rate": 5.7202446389173223e-05,
      "loss": 1.9045,
      "step": 84
    },
    {
      "epoch": 1.4718614718614718,
      "grad_norm": 2.8176522254943848,
      "learning_rate": 5.624753961644281e-05,
      "loss": 1.6573,
      "step": 85
    },
    {
      "epoch": 1.4891774891774892,
      "grad_norm": 2.932007312774658,
      "learning_rate": 5.5290312137786146e-05,
      "loss": 1.5173,
      "step": 86
    },
    {
      "epoch": 1.5064935064935066,
      "grad_norm": 0.9135814905166626,
      "learning_rate": 5.433111952413495e-05,
      "loss": 1.4504,
      "step": 87
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 1.2319753170013428,
      "learning_rate": 5.33703180763884e-05,
      "loss": 1.8403,
      "step": 88
    },
    {
      "epoch": 1.5411255411255411,
      "grad_norm": 1.2729883193969727,
      "learning_rate": 5.240826469306187e-05,
      "loss": 1.6524,
      "step": 89
    },
    {
      "epoch": 1.5584415584415585,
      "grad_norm": 1.4365655183792114,
      "learning_rate": 5.144531673771363e-05,
      "loss": 1.4742,
      "step": 90
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 1.4098918437957764,
      "learning_rate": 5.048183190619904e-05,
      "loss": 1.5275,
      "step": 91
    },
    {
      "epoch": 1.593073593073593,
      "grad_norm": 1.5895005464553833,
      "learning_rate": 4.951816809380097e-05,
      "loss": 1.5147,
      "step": 92
    },
    {
      "epoch": 1.6103896103896105,
      "grad_norm": 1.71897292137146,
      "learning_rate": 4.855468326228638e-05,
      "loss": 1.5553,
      "step": 93
    },
    {
      "epoch": 1.6277056277056277,
      "grad_norm": 1.8746683597564697,
      "learning_rate": 4.759173530693814e-05,
      "loss": 1.6687,
      "step": 94
    },
    {
      "epoch": 1.645021645021645,
      "grad_norm": 2.1632306575775146,
      "learning_rate": 4.6629681923611603e-05,
      "loss": 1.7037,
      "step": 95
    },
    {
      "epoch": 1.6623376623376624,
      "grad_norm": 2.1969408988952637,
      "learning_rate": 4.566888047586507e-05,
      "loss": 1.8775,
      "step": 96
    },
    {
      "epoch": 1.6796536796536796,
      "grad_norm": 2.26798152923584,
      "learning_rate": 4.4709687862213866e-05,
      "loss": 1.6915,
      "step": 97
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 2.2888317108154297,
      "learning_rate": 4.3752460383557195e-05,
      "loss": 1.7374,
      "step": 98
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 3.2511236667633057,
      "learning_rate": 4.27975536108268e-05,
      "loss": 1.8612,
      "step": 99
    },
    {
      "epoch": 1.7316017316017316,
      "grad_norm": 3.068394899368286,
      "learning_rate": 4.1845322252906864e-05,
      "loss": 1.4067,
      "step": 100
    },
    {
      "epoch": 1.7316017316017316,
      "eval_loss": 2.1530466079711914,
      "eval_runtime": 4.4162,
      "eval_samples_per_second": 22.191,
      "eval_steps_per_second": 5.661,
      "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
}