{
  "best_metric": 0.16797423362731934,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.2403846153846154,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002403846153846154,
      "grad_norm": 1.1882891654968262,
      "learning_rate": 1e-06,
      "loss": 0.5942,
      "step": 1
    },
    {
      "epoch": 0.002403846153846154,
      "eval_loss": 1.188090205192566,
      "eval_runtime": 12.7193,
      "eval_samples_per_second": 13.837,
      "eval_steps_per_second": 3.459,
      "step": 1
    },
    {
      "epoch": 0.004807692307692308,
      "grad_norm": 1.4247385263442993,
      "learning_rate": 2e-06,
      "loss": 0.7545,
      "step": 2
    },
    {
      "epoch": 0.007211538461538462,
      "grad_norm": 1.461084246635437,
      "learning_rate": 3e-06,
      "loss": 0.6679,
      "step": 3
    },
    {
      "epoch": 0.009615384615384616,
      "grad_norm": 1.4952707290649414,
      "learning_rate": 4e-06,
      "loss": 0.7754,
      "step": 4
    },
    {
      "epoch": 0.01201923076923077,
      "grad_norm": 1.8526206016540527,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 0.9569,
      "step": 5
    },
    {
      "epoch": 0.014423076923076924,
      "grad_norm": 1.8152567148208618,
      "learning_rate": 6e-06,
      "loss": 0.7717,
      "step": 6
    },
    {
      "epoch": 0.016826923076923076,
      "grad_norm": 1.7006921768188477,
      "learning_rate": 7e-06,
      "loss": 0.6765,
      "step": 7
    },
    {
      "epoch": 0.019230769230769232,
      "grad_norm": 1.8837177753448486,
      "learning_rate": 8e-06,
      "loss": 0.8482,
      "step": 8
    },
    {
      "epoch": 0.021634615384615384,
      "grad_norm": 2.074211835861206,
      "learning_rate": 9e-06,
      "loss": 0.7892,
      "step": 9
    },
    {
      "epoch": 0.02403846153846154,
      "grad_norm": 2.25862193107605,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.8246,
      "step": 10
    },
    {
      "epoch": 0.026442307692307692,
      "grad_norm": 1.8513481616973877,
      "learning_rate": 1.1e-05,
      "loss": 0.6972,
      "step": 11
    },
    {
      "epoch": 0.028846153846153848,
      "grad_norm": 2.120839834213257,
      "learning_rate": 1.2e-05,
      "loss": 0.8297,
      "step": 12
    },
    {
      "epoch": 0.03125,
      "grad_norm": 1.88652503490448,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.6692,
      "step": 13
    },
    {
      "epoch": 0.03365384615384615,
      "grad_norm": 2.3837525844573975,
      "learning_rate": 1.4e-05,
      "loss": 0.6891,
      "step": 14
    },
    {
      "epoch": 0.036057692307692304,
      "grad_norm": 1.9358539581298828,
      "learning_rate": 1.5e-05,
      "loss": 0.5881,
      "step": 15
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 1.9593491554260254,
      "learning_rate": 1.6e-05,
      "loss": 0.7997,
      "step": 16
    },
    {
      "epoch": 0.040865384615384616,
      "grad_norm": 1.5227642059326172,
      "learning_rate": 1.7e-05,
      "loss": 0.3436,
      "step": 17
    },
    {
      "epoch": 0.04326923076923077,
      "grad_norm": 1.8325457572937012,
      "learning_rate": 1.8e-05,
      "loss": 0.5188,
      "step": 18
    },
    {
      "epoch": 0.04567307692307692,
      "grad_norm": 1.695982813835144,
      "learning_rate": 1.9e-05,
      "loss": 0.5362,
      "step": 19
    },
    {
      "epoch": 0.04807692307692308,
      "grad_norm": 1.1321346759796143,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.4427,
      "step": 20
    },
    {
      "epoch": 0.05048076923076923,
      "grad_norm": 1.1562103033065796,
      "learning_rate": 2.1e-05,
      "loss": 0.2424,
      "step": 21
    },
    {
      "epoch": 0.052884615384615384,
      "grad_norm": 1.7005853652954102,
      "learning_rate": 2.2e-05,
      "loss": 0.5071,
      "step": 22
    },
    {
      "epoch": 0.055288461538461536,
      "grad_norm": 1.26986563205719,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.2622,
      "step": 23
    },
    {
      "epoch": 0.057692307692307696,
      "grad_norm": 2.2647178173065186,
      "learning_rate": 2.4e-05,
      "loss": 0.3827,
      "step": 24
    },
    {
      "epoch": 0.06009615384615385,
      "grad_norm": 1.5839488506317139,
      "learning_rate": 2.5e-05,
      "loss": 0.3306,
      "step": 25
    },
    {
      "epoch": 0.0625,
      "grad_norm": 1.6258400678634644,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.3544,
      "step": 26
    },
    {
      "epoch": 0.06490384615384616,
      "grad_norm": 1.2185949087142944,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.2697,
      "step": 27
    },
    {
      "epoch": 0.0673076923076923,
      "grad_norm": 0.9912201166152954,
      "learning_rate": 2.8e-05,
      "loss": 0.1179,
      "step": 28
    },
    {
      "epoch": 0.06971153846153846,
      "grad_norm": 1.4945157766342163,
      "learning_rate": 2.9e-05,
      "loss": 0.3554,
      "step": 29
    },
    {
      "epoch": 0.07211538461538461,
      "grad_norm": 2.056633234024048,
      "learning_rate": 3e-05,
      "loss": 0.4481,
      "step": 30
    },
    {
      "epoch": 0.07451923076923077,
      "grad_norm": 1.86720871925354,
      "learning_rate": 2.9984895998119723e-05,
      "loss": 0.4367,
      "step": 31
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 1.968263030052185,
      "learning_rate": 2.993961440992859e-05,
      "loss": 0.3615,
      "step": 32
    },
    {
      "epoch": 0.07932692307692307,
      "grad_norm": 1.6691246032714844,
      "learning_rate": 2.9864246426519023e-05,
      "loss": 0.2089,
      "step": 33
    },
    {
      "epoch": 0.08173076923076923,
      "grad_norm": 1.6768012046813965,
      "learning_rate": 2.9758943828979444e-05,
      "loss": 0.2026,
      "step": 34
    },
    {
      "epoch": 0.08413461538461539,
      "grad_norm": 2.3216371536254883,
      "learning_rate": 2.9623918682727355e-05,
      "loss": 0.2482,
      "step": 35
    },
    {
      "epoch": 0.08653846153846154,
      "grad_norm": 1.615944743156433,
      "learning_rate": 2.9459442910437798e-05,
      "loss": 0.2615,
      "step": 36
    },
    {
      "epoch": 0.0889423076923077,
      "grad_norm": 1.0830882787704468,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 0.0836,
      "step": 37
    },
    {
      "epoch": 0.09134615384615384,
      "grad_norm": 1.4945337772369385,
      "learning_rate": 2.904352305959606e-05,
      "loss": 0.1732,
      "step": 38
    },
    {
      "epoch": 0.09375,
      "grad_norm": 1.4487866163253784,
      "learning_rate": 2.8792916588271762e-05,
      "loss": 0.1766,
      "step": 39
    },
    {
      "epoch": 0.09615384615384616,
      "grad_norm": 0.9886900186538696,
      "learning_rate": 2.8514533018536286e-05,
      "loss": 0.0904,
      "step": 40
    },
    {
      "epoch": 0.0985576923076923,
      "grad_norm": 0.6899282336235046,
      "learning_rate": 2.820893297785107e-05,
      "loss": 0.0604,
      "step": 41
    },
    {
      "epoch": 0.10096153846153846,
      "grad_norm": 1.313900351524353,
      "learning_rate": 2.7876731904027994e-05,
      "loss": 0.0951,
      "step": 42
    },
    {
      "epoch": 0.10336538461538461,
      "grad_norm": 1.0713980197906494,
      "learning_rate": 2.7518598805819542e-05,
      "loss": 0.1309,
      "step": 43
    },
    {
      "epoch": 0.10576923076923077,
      "grad_norm": 0.9497880935668945,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.0521,
      "step": 44
    },
    {
      "epoch": 0.10817307692307693,
      "grad_norm": 1.0702611207962036,
      "learning_rate": 2.672747223702045e-05,
      "loss": 0.1382,
      "step": 45
    },
    {
      "epoch": 0.11057692307692307,
      "grad_norm": 1.6158556938171387,
      "learning_rate": 2.6296071990054167e-05,
      "loss": 0.2278,
      "step": 46
    },
    {
      "epoch": 0.11298076923076923,
      "grad_norm": 1.1326674222946167,
      "learning_rate": 2.5841922957410875e-05,
      "loss": 0.0456,
      "step": 47
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 0.6065059900283813,
      "learning_rate": 2.5365939734802973e-05,
      "loss": 0.0309,
      "step": 48
    },
    {
      "epoch": 0.11778846153846154,
      "grad_norm": 1.3793675899505615,
      "learning_rate": 2.4869080889095693e-05,
      "loss": 0.1734,
      "step": 49
    },
    {
      "epoch": 0.1201923076923077,
      "grad_norm": 1.3287246227264404,
      "learning_rate": 2.4352347027881003e-05,
      "loss": 0.0988,
      "step": 50
    },
    {
      "epoch": 0.1201923076923077,
      "eval_loss": 0.2722248136997223,
      "eval_runtime": 12.9944,
      "eval_samples_per_second": 13.544,
      "eval_steps_per_second": 3.386,
      "step": 50
    },
    {
      "epoch": 0.12259615384615384,
      "grad_norm": 1.4362388849258423,
      "learning_rate": 2.3816778784387097e-05,
      "loss": 0.3142,
      "step": 51
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.860426902770996,
      "learning_rate": 2.3263454721781537e-05,
      "loss": 0.3385,
      "step": 52
    },
    {
      "epoch": 0.12740384615384615,
      "grad_norm": 1.6274983882904053,
      "learning_rate": 2.2693489161088592e-05,
      "loss": 0.3687,
      "step": 53
    },
    {
      "epoch": 0.12980769230769232,
      "grad_norm": 1.2778645753860474,
      "learning_rate": 2.210802993709498e-05,
      "loss": 0.2203,
      "step": 54
    },
    {
      "epoch": 0.13221153846153846,
      "grad_norm": 0.6512196063995361,
      "learning_rate": 2.1508256086763372e-05,
      "loss": 0.1032,
      "step": 55
    },
    {
      "epoch": 0.1346153846153846,
      "grad_norm": 0.9451633095741272,
      "learning_rate": 2.0895375474808857e-05,
      "loss": 0.2004,
      "step": 56
    },
    {
      "epoch": 0.13701923076923078,
      "grad_norm": 0.9968198537826538,
      "learning_rate": 2.0270622361220143e-05,
      "loss": 0.1885,
      "step": 57
    },
    {
      "epoch": 0.13942307692307693,
      "grad_norm": 1.0050638914108276,
      "learning_rate": 1.963525491562421e-05,
      "loss": 0.2024,
      "step": 58
    },
    {
      "epoch": 0.14182692307692307,
      "grad_norm": 1.0530974864959717,
      "learning_rate": 1.8990552683500128e-05,
      "loss": 0.2574,
      "step": 59
    },
    {
      "epoch": 0.14423076923076922,
      "grad_norm": 1.152009129524231,
      "learning_rate": 1.8337814009344716e-05,
      "loss": 0.2027,
      "step": 60
    },
    {
      "epoch": 0.1466346153846154,
      "grad_norm": 1.23932683467865,
      "learning_rate": 1.767835342197955e-05,
      "loss": 0.3122,
      "step": 61
    },
    {
      "epoch": 0.14903846153846154,
      "grad_norm": 1.4331951141357422,
      "learning_rate": 1.7013498987264832e-05,
      "loss": 0.2927,
      "step": 62
    },
    {
      "epoch": 0.15144230769230768,
      "grad_norm": 1.1172962188720703,
      "learning_rate": 1.6344589633551502e-05,
      "loss": 0.1881,
      "step": 63
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 1.538137674331665,
      "learning_rate": 1.5672972455257726e-05,
      "loss": 0.3572,
      "step": 64
    },
    {
      "epoch": 0.15625,
      "grad_norm": 1.3856353759765625,
      "learning_rate": 1.5e-05,
      "loss": 0.2622,
      "step": 65
    },
    {
      "epoch": 0.15865384615384615,
      "grad_norm": 1.19050133228302,
      "learning_rate": 1.4327027544742281e-05,
      "loss": 0.1605,
      "step": 66
    },
    {
      "epoch": 0.16105769230769232,
      "grad_norm": 1.642045021057129,
      "learning_rate": 1.36554103664485e-05,
      "loss": 0.2095,
      "step": 67
    },
    {
      "epoch": 0.16346153846153846,
      "grad_norm": 0.8812408447265625,
      "learning_rate": 1.2986501012735174e-05,
      "loss": 0.2378,
      "step": 68
    },
    {
      "epoch": 0.1658653846153846,
      "grad_norm": 1.209253191947937,
      "learning_rate": 1.2321646578020452e-05,
      "loss": 0.2468,
      "step": 69
    },
    {
      "epoch": 0.16826923076923078,
      "grad_norm": 0.7078008055686951,
      "learning_rate": 1.1662185990655285e-05,
      "loss": 0.1156,
      "step": 70
    },
    {
      "epoch": 0.17067307692307693,
      "grad_norm": 1.1781238317489624,
      "learning_rate": 1.1009447316499875e-05,
      "loss": 0.2665,
      "step": 71
    },
    {
      "epoch": 0.17307692307692307,
      "grad_norm": 0.9855147004127502,
      "learning_rate": 1.036474508437579e-05,
      "loss": 0.1571,
      "step": 72
    },
    {
      "epoch": 0.17548076923076922,
      "grad_norm": 0.9759849309921265,
      "learning_rate": 9.729377638779859e-06,
      "loss": 0.1611,
      "step": 73
    },
    {
      "epoch": 0.1778846153846154,
      "grad_norm": 1.0247809886932373,
      "learning_rate": 9.104624525191147e-06,
      "loss": 0.1715,
      "step": 74
    },
    {
      "epoch": 0.18028846153846154,
      "grad_norm": 0.8398781418800354,
      "learning_rate": 8.491743913236629e-06,
      "loss": 0.1215,
      "step": 75
    },
    {
      "epoch": 0.18269230769230768,
      "grad_norm": 1.200787901878357,
      "learning_rate": 7.89197006290502e-06,
      "loss": 0.1345,
      "step": 76
    },
    {
      "epoch": 0.18509615384615385,
      "grad_norm": 1.2606765031814575,
      "learning_rate": 7.30651083891141e-06,
      "loss": 0.2015,
      "step": 77
    },
    {
      "epoch": 0.1875,
      "grad_norm": 1.226075530052185,
      "learning_rate": 6.736545278218464e-06,
      "loss": 0.1495,
      "step": 78
    },
    {
      "epoch": 0.18990384615384615,
      "grad_norm": 1.6568992137908936,
      "learning_rate": 6.1832212156129045e-06,
      "loss": 0.3211,
      "step": 79
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 0.7081555724143982,
      "learning_rate": 5.647652972118998e-06,
      "loss": 0.0899,
      "step": 80
    },
    {
      "epoch": 0.19471153846153846,
      "grad_norm": 0.7544460296630859,
      "learning_rate": 5.130919110904311e-06,
      "loss": 0.0897,
      "step": 81
    },
    {
      "epoch": 0.1971153846153846,
      "grad_norm": 2.0655691623687744,
      "learning_rate": 4.6340602651970304e-06,
      "loss": 0.3054,
      "step": 82
    },
    {
      "epoch": 0.19951923076923078,
      "grad_norm": 0.9946995973587036,
      "learning_rate": 4.158077042589129e-06,
      "loss": 0.1079,
      "step": 83
    },
    {
      "epoch": 0.20192307692307693,
      "grad_norm": 0.7628113627433777,
      "learning_rate": 3.7039280099458373e-06,
      "loss": 0.0829,
      "step": 84
    },
    {
      "epoch": 0.20432692307692307,
      "grad_norm": 1.402290940284729,
      "learning_rate": 3.272527762979553e-06,
      "loss": 0.3208,
      "step": 85
    },
    {
      "epoch": 0.20673076923076922,
      "grad_norm": 1.0061466693878174,
      "learning_rate": 2.86474508437579e-06,
      "loss": 0.1289,
      "step": 86
    },
    {
      "epoch": 0.2091346153846154,
      "grad_norm": 1.5119874477386475,
      "learning_rate": 2.4814011941804603e-06,
      "loss": 0.1942,
      "step": 87
    },
    {
      "epoch": 0.21153846153846154,
      "grad_norm": 1.1907665729522705,
      "learning_rate": 2.1232680959720085e-06,
      "loss": 0.1552,
      "step": 88
    },
    {
      "epoch": 0.21394230769230768,
      "grad_norm": 1.051279067993164,
      "learning_rate": 1.79106702214893e-06,
      "loss": 0.1246,
      "step": 89
    },
    {
      "epoch": 0.21634615384615385,
      "grad_norm": 0.5934176445007324,
      "learning_rate": 1.4854669814637145e-06,
      "loss": 0.039,
      "step": 90
    },
    {
      "epoch": 0.21875,
      "grad_norm": 1.1616430282592773,
      "learning_rate": 1.2070834117282414e-06,
      "loss": 0.1305,
      "step": 91
    },
    {
      "epoch": 0.22115384615384615,
      "grad_norm": 1.1014513969421387,
      "learning_rate": 9.56476940403942e-07,
      "loss": 0.1512,
      "step": 92
    },
    {
      "epoch": 0.22355769230769232,
      "grad_norm": 0.7917444705963135,
      "learning_rate": 7.341522555726971e-07,
      "loss": 0.0913,
      "step": 93
    },
    {
      "epoch": 0.22596153846153846,
      "grad_norm": 1.2249654531478882,
      "learning_rate": 5.405570895622014e-07,
      "loss": 0.1222,
      "step": 94
    },
    {
      "epoch": 0.2283653846153846,
      "grad_norm": 0.6707494854927063,
      "learning_rate": 3.760813172726457e-07,
      "loss": 0.0606,
      "step": 95
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.6507337093353271,
      "learning_rate": 2.41056171020555e-07,
      "loss": 0.0762,
      "step": 96
    },
    {
      "epoch": 0.23317307692307693,
      "grad_norm": 0.5566867589950562,
      "learning_rate": 1.357535734809795e-07,
      "loss": 0.0479,
      "step": 97
    },
    {
      "epoch": 0.23557692307692307,
      "grad_norm": 0.8109729290008545,
      "learning_rate": 6.038559007141397e-08,
      "loss": 0.1004,
      "step": 98
    },
    {
      "epoch": 0.23798076923076922,
      "grad_norm": 0.40619972348213196,
      "learning_rate": 1.510400188028116e-08,
      "loss": 0.0221,
      "step": 99
    },
    {
      "epoch": 0.2403846153846154,
      "grad_norm": 0.7692926526069641,
      "learning_rate": 0.0,
      "loss": 0.0592,
      "step": 100
    },
    {
      "epoch": 0.2403846153846154,
      "eval_loss": 0.16797423362731934,
      "eval_runtime": 13.0043,
      "eval_samples_per_second": 13.534,
      "eval_steps_per_second": 3.383,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5547217133568e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}