{
  "best_metric": 3.924217939376831,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.1782001782001782,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002376002376002376,
      "grad_norm": 4.380615711212158,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 4.9543,
      "step": 1
    },
    {
      "epoch": 0.002376002376002376,
      "eval_loss": 5.8989152908325195,
      "eval_runtime": 0.4626,
      "eval_samples_per_second": 108.088,
      "eval_steps_per_second": 28.103,
      "step": 1
    },
    {
      "epoch": 0.004752004752004752,
      "grad_norm": 5.492649555206299,
      "learning_rate": 6.666666666666667e-05,
      "loss": 5.3281,
      "step": 2
    },
    {
      "epoch": 0.007128007128007128,
      "grad_norm": 5.611356258392334,
      "learning_rate": 0.0001,
      "loss": 5.5476,
      "step": 3
    },
    {
      "epoch": 0.009504009504009503,
      "grad_norm": 5.1926751136779785,
      "learning_rate": 9.99571699711836e-05,
      "loss": 5.4407,
      "step": 4
    },
    {
      "epoch": 0.01188001188001188,
      "grad_norm": 4.4678144454956055,
      "learning_rate": 9.982876141412856e-05,
      "loss": 4.9533,
      "step": 5
    },
    {
      "epoch": 0.014256014256014256,
      "grad_norm": 3.666590929031372,
      "learning_rate": 9.961501876182148e-05,
      "loss": 4.8957,
      "step": 6
    },
    {
      "epoch": 0.016632016632016633,
      "grad_norm": 2.9076924324035645,
      "learning_rate": 9.931634888554937e-05,
      "loss": 4.7412,
      "step": 7
    },
    {
      "epoch": 0.019008019008019007,
      "grad_norm": 3.1712443828582764,
      "learning_rate": 9.893332032039701e-05,
      "loss": 4.7591,
      "step": 8
    },
    {
      "epoch": 0.021384021384021384,
      "grad_norm": 3.3876755237579346,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.9002,
      "step": 9
    },
    {
      "epoch": 0.02376002376002376,
      "grad_norm": 3.2135019302368164,
      "learning_rate": 9.791726278367022e-05,
      "loss": 4.8693,
      "step": 10
    },
    {
      "epoch": 0.026136026136026135,
      "grad_norm": 3.6509037017822266,
      "learning_rate": 9.728616793536588e-05,
      "loss": 5.2601,
      "step": 11
    },
    {
      "epoch": 0.02851202851202851,
      "grad_norm": 4.232973575592041,
      "learning_rate": 9.657457896300791e-05,
      "loss": 5.1388,
      "step": 12
    },
    {
      "epoch": 0.03088803088803089,
      "grad_norm": 4.702571868896484,
      "learning_rate": 9.578385041664925e-05,
      "loss": 4.6445,
      "step": 13
    },
    {
      "epoch": 0.033264033264033266,
      "grad_norm": 5.038473606109619,
      "learning_rate": 9.491548749301997e-05,
      "loss": 4.1849,
      "step": 14
    },
    {
      "epoch": 0.03564003564003564,
      "grad_norm": 3.6792800426483154,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.1729,
      "step": 15
    },
    {
      "epoch": 0.03801603801603801,
      "grad_norm": 2.92476224899292,
      "learning_rate": 9.295261506157986e-05,
      "loss": 4.1779,
      "step": 16
    },
    {
      "epoch": 0.04039204039204039,
      "grad_norm": 2.7897653579711914,
      "learning_rate": 9.186184199300464e-05,
      "loss": 4.1821,
      "step": 17
    },
    {
      "epoch": 0.04276804276804277,
      "grad_norm": 3.0643630027770996,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.2447,
      "step": 18
    },
    {
      "epoch": 0.045144045144045145,
      "grad_norm": 3.3225109577178955,
      "learning_rate": 8.947199994035401e-05,
      "loss": 4.1242,
      "step": 19
    },
    {
      "epoch": 0.04752004752004752,
      "grad_norm": 3.201786994934082,
      "learning_rate": 8.817748015645558e-05,
      "loss": 4.3685,
      "step": 20
    },
    {
      "epoch": 0.0498960498960499,
      "grad_norm": 3.1338696479797363,
      "learning_rate": 8.681980515339464e-05,
      "loss": 4.2878,
      "step": 21
    },
    {
      "epoch": 0.05227205227205227,
      "grad_norm": 3.1590020656585693,
      "learning_rate": 8.540155934270471e-05,
      "loss": 4.497,
      "step": 22
    },
    {
      "epoch": 0.054648054648054646,
      "grad_norm": 2.928370714187622,
      "learning_rate": 8.392544243589427e-05,
      "loss": 4.542,
      "step": 23
    },
    {
      "epoch": 0.05702405702405702,
      "grad_norm": 3.1304128170013428,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.7395,
      "step": 24
    },
    {
      "epoch": 0.0594000594000594,
      "grad_norm": 3.5850155353546143,
      "learning_rate": 8.081093963579707e-05,
      "loss": 5.2024,
      "step": 25
    },
    {
      "epoch": 0.0594000594000594,
      "eval_loss": 4.197417736053467,
      "eval_runtime": 0.4632,
      "eval_samples_per_second": 107.934,
      "eval_steps_per_second": 28.063,
      "step": 25
    },
    {
      "epoch": 0.06177606177606178,
      "grad_norm": 5.812683582305908,
      "learning_rate": 7.917848237560709e-05,
      "loss": 3.9788,
      "step": 26
    },
    {
      "epoch": 0.06415206415206415,
      "grad_norm": 5.340697288513184,
      "learning_rate": 7.75e-05,
      "loss": 4.1852,
      "step": 27
    },
    {
      "epoch": 0.06652806652806653,
      "grad_norm": 5.233508586883545,
      "learning_rate": 7.577868759557654e-05,
      "loss": 4.0927,
      "step": 28
    },
    {
      "epoch": 0.0689040689040689,
      "grad_norm": 4.724637985229492,
      "learning_rate": 7.401782177833148e-05,
      "loss": 4.184,
      "step": 29
    },
    {
      "epoch": 0.07128007128007129,
      "grad_norm": 3.7798030376434326,
      "learning_rate": 7.222075445642904e-05,
      "loss": 3.9799,
      "step": 30
    },
    {
      "epoch": 0.07365607365607366,
      "grad_norm": 3.1549389362335205,
      "learning_rate": 7.03909064496551e-05,
      "loss": 4.0357,
      "step": 31
    },
    {
      "epoch": 0.07603207603207603,
      "grad_norm": 2.810375213623047,
      "learning_rate": 6.853176097769229e-05,
      "loss": 4.2323,
      "step": 32
    },
    {
      "epoch": 0.07840807840807841,
      "grad_norm": 2.2946324348449707,
      "learning_rate": 6.664685702961344e-05,
      "loss": 4.1228,
      "step": 33
    },
    {
      "epoch": 0.08078408078408078,
      "grad_norm": 2.794386386871338,
      "learning_rate": 6.473978262721463e-05,
      "loss": 4.3795,
      "step": 34
    },
    {
      "epoch": 0.08316008316008316,
      "grad_norm": 2.846055507659912,
      "learning_rate": 6.281416799501188e-05,
      "loss": 4.338,
      "step": 35
    },
    {
      "epoch": 0.08553608553608553,
      "grad_norm": 3.5053131580352783,
      "learning_rate": 6.087367864990233e-05,
      "loss": 4.6534,
      "step": 36
    },
    {
      "epoch": 0.08791208791208792,
      "grad_norm": 4.065090179443359,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 4.7563,
      "step": 37
    },
    {
      "epoch": 0.09028809028809029,
      "grad_norm": 2.289839744567871,
      "learning_rate": 5.696287243144013e-05,
      "loss": 4.1748,
      "step": 38
    },
    {
      "epoch": 0.09266409266409266,
      "grad_norm": 2.2016358375549316,
      "learning_rate": 5.500000000000001e-05,
      "loss": 3.8301,
      "step": 39
    },
    {
      "epoch": 0.09504009504009504,
      "grad_norm": 2.1572742462158203,
      "learning_rate": 5.303712756855988e-05,
      "loss": 3.8959,
      "step": 40
    },
    {
      "epoch": 0.09741609741609741,
      "grad_norm": 2.1548614501953125,
      "learning_rate": 5.107799157635538e-05,
      "loss": 4.0368,
      "step": 41
    },
    {
      "epoch": 0.0997920997920998,
      "grad_norm": 1.97099769115448,
      "learning_rate": 4.912632135009769e-05,
      "loss": 3.8731,
      "step": 42
    },
    {
      "epoch": 0.10216810216810217,
      "grad_norm": 1.972032904624939,
      "learning_rate": 4.718583200498814e-05,
      "loss": 4.0455,
      "step": 43
    },
    {
      "epoch": 0.10454410454410454,
      "grad_norm": 2.277165412902832,
      "learning_rate": 4.526021737278538e-05,
      "loss": 4.0799,
      "step": 44
    },
    {
      "epoch": 0.10692010692010692,
      "grad_norm": 2.229562997817993,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 4.2358,
      "step": 45
    },
    {
      "epoch": 0.10929610929610929,
      "grad_norm": 2.1845741271972656,
      "learning_rate": 4.146823902230772e-05,
      "loss": 4.1261,
      "step": 46
    },
    {
      "epoch": 0.11167211167211168,
      "grad_norm": 2.513690948486328,
      "learning_rate": 3.960909355034491e-05,
      "loss": 4.249,
      "step": 47
    },
    {
      "epoch": 0.11404811404811405,
      "grad_norm": 2.7216529846191406,
      "learning_rate": 3.777924554357096e-05,
      "loss": 4.3592,
      "step": 48
    },
    {
      "epoch": 0.11642411642411643,
      "grad_norm": 2.8171885013580322,
      "learning_rate": 3.598217822166854e-05,
      "loss": 4.59,
      "step": 49
    },
    {
      "epoch": 0.1188001188001188,
      "grad_norm": 4.377580165863037,
      "learning_rate": 3.422131240442349e-05,
      "loss": 5.0176,
      "step": 50
    },
    {
      "epoch": 0.1188001188001188,
      "eval_loss": 3.993185520172119,
      "eval_runtime": 0.463,
      "eval_samples_per_second": 107.981,
      "eval_steps_per_second": 28.075,
      "step": 50
    },
    {
      "epoch": 0.12117612117612117,
      "grad_norm": 2.3711788654327393,
      "learning_rate": 3.250000000000001e-05,
      "loss": 3.7217,
      "step": 51
    },
    {
      "epoch": 0.12355212355212356,
      "grad_norm": 2.324312686920166,
      "learning_rate": 3.082151762439293e-05,
      "loss": 3.7561,
      "step": 52
    },
    {
      "epoch": 0.12592812592812594,
      "grad_norm": 2.2597808837890625,
      "learning_rate": 2.9189060364202943e-05,
      "loss": 3.9246,
      "step": 53
    },
    {
      "epoch": 0.1283041283041283,
      "grad_norm": 2.233111619949341,
      "learning_rate": 2.760573569460757e-05,
      "loss": 3.9591,
      "step": 54
    },
    {
      "epoch": 0.13068013068013068,
      "grad_norm": 2.11525559425354,
      "learning_rate": 2.6074557564105727e-05,
      "loss": 4.0181,
      "step": 55
    },
    {
      "epoch": 0.13305613305613306,
      "grad_norm": 2.1554830074310303,
      "learning_rate": 2.459844065729529e-05,
      "loss": 4.0492,
      "step": 56
    },
    {
      "epoch": 0.13543213543213542,
      "grad_norm": 2.260748863220215,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 4.096,
      "step": 57
    },
    {
      "epoch": 0.1378081378081378,
      "grad_norm": 2.5770089626312256,
      "learning_rate": 2.1822519843544424e-05,
      "loss": 4.1185,
      "step": 58
    },
    {
      "epoch": 0.1401841401841402,
      "grad_norm": 2.5284464359283447,
      "learning_rate": 2.0528000059645997e-05,
      "loss": 4.2158,
      "step": 59
    },
    {
      "epoch": 0.14256014256014257,
      "grad_norm": 2.5339860916137695,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 4.3166,
      "step": 60
    },
    {
      "epoch": 0.14493614493614493,
      "grad_norm": 3.2956223487854004,
      "learning_rate": 1.8138158006995364e-05,
      "loss": 4.51,
      "step": 61
    },
    {
      "epoch": 0.1473121473121473,
      "grad_norm": 3.547050952911377,
      "learning_rate": 1.7047384938420154e-05,
      "loss": 4.6738,
      "step": 62
    },
    {
      "epoch": 0.1496881496881497,
      "grad_norm": 2.2729122638702393,
      "learning_rate": 1.602885682970026e-05,
      "loss": 4.1461,
      "step": 63
    },
    {
      "epoch": 0.15206415206415205,
      "grad_norm": 2.3304686546325684,
      "learning_rate": 1.5084512506980026e-05,
      "loss": 3.7979,
      "step": 64
    },
    {
      "epoch": 0.15444015444015444,
      "grad_norm": 2.1547152996063232,
      "learning_rate": 1.4216149583350754e-05,
      "loss": 3.7298,
      "step": 65
    },
    {
      "epoch": 0.15681615681615682,
      "grad_norm": 2.1138386726379395,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 3.9149,
      "step": 66
    },
    {
      "epoch": 0.1591921591921592,
      "grad_norm": 2.197359561920166,
      "learning_rate": 1.2713832064634126e-05,
      "loss": 3.9229,
      "step": 67
    },
    {
      "epoch": 0.16156816156816156,
      "grad_norm": 2.0438430309295654,
      "learning_rate": 1.2082737216329794e-05,
      "loss": 3.9128,
      "step": 68
    },
    {
      "epoch": 0.16394416394416395,
      "grad_norm": 2.085602045059204,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 4.0383,
      "step": 69
    },
    {
      "epoch": 0.16632016632016633,
      "grad_norm": 2.3776140213012695,
      "learning_rate": 1.1066679679603e-05,
      "loss": 3.9447,
      "step": 70
    },
    {
      "epoch": 0.16869616869616869,
      "grad_norm": 2.2178096771240234,
      "learning_rate": 1.0683651114450641e-05,
      "loss": 4.0903,
      "step": 71
    },
    {
      "epoch": 0.17107217107217107,
      "grad_norm": 2.8414366245269775,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 4.2017,
      "step": 72
    },
    {
      "epoch": 0.17344817344817345,
      "grad_norm": 2.834662914276123,
      "learning_rate": 1.017123858587145e-05,
      "loss": 4.3855,
      "step": 73
    },
    {
      "epoch": 0.17582417582417584,
      "grad_norm": 3.376075267791748,
      "learning_rate": 1.00428300288164e-05,
      "loss": 4.5297,
      "step": 74
    },
    {
      "epoch": 0.1782001782001782,
      "grad_norm": 4.6905436515808105,
      "learning_rate": 1e-05,
      "loss": 5.0961,
      "step": 75
    },
    {
      "epoch": 0.1782001782001782,
      "eval_loss": 3.924217939376831,
      "eval_runtime": 0.4633,
      "eval_samples_per_second": 107.912,
      "eval_steps_per_second": 28.057,
      "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": 1.174564302225408e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}