{
  "best_metric": 3.1905126571655273,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.4317789291882556,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008635578583765112,
      "eval_loss": 4.056301116943359,
      "eval_runtime": 6.6134,
      "eval_samples_per_second": 73.789,
      "eval_steps_per_second": 18.447,
      "step": 1
    },
    {
      "epoch": 0.008635578583765112,
      "grad_norm": 75.20758056640625,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 7.2673,
      "step": 10
    },
    {
      "epoch": 0.017271157167530225,
      "grad_norm": 82.5886001586914,
      "learning_rate": 8.400000000000001e-05,
      "loss": 6.9928,
      "step": 20
    },
    {
      "epoch": 0.025906735751295335,
      "grad_norm": 934.9874877929688,
      "learning_rate": 0.000126,
      "loss": 7.1944,
      "step": 30
    },
    {
      "epoch": 0.03454231433506045,
      "grad_norm": 220.6071319580078,
      "learning_rate": 0.00016800000000000002,
      "loss": 7.0499,
      "step": 40
    },
    {
      "epoch": 0.04317789291882556,
      "grad_norm": 720.1281127929688,
      "learning_rate": 0.00021,
      "loss": 8.7892,
      "step": 50
    },
    {
      "epoch": 0.04317789291882556,
      "eval_loss": 5.3484110832214355,
      "eval_runtime": 6.7066,
      "eval_samples_per_second": 72.764,
      "eval_steps_per_second": 18.191,
      "step": 50
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 62.76759719848633,
      "learning_rate": 0.00020974422527728155,
      "loss": 13.9468,
      "step": 60
    },
    {
      "epoch": 0.06044905008635579,
      "grad_norm": 154.0032501220703,
      "learning_rate": 0.0002089781472178649,
      "loss": 10.8076,
      "step": 70
    },
    {
      "epoch": 0.0690846286701209,
      "grad_norm": 666.8218994140625,
      "learning_rate": 0.0002077054980770496,
      "loss": 7.8264,
      "step": 80
    },
    {
      "epoch": 0.07772020725388601,
      "grad_norm": 109.74002838134766,
      "learning_rate": 0.00020593247807352348,
      "loss": 9.7935,
      "step": 90
    },
    {
      "epoch": 0.08635578583765112,
      "grad_norm": 324.6034851074219,
      "learning_rate": 0.00020366772518252038,
      "loss": 9.2869,
      "step": 100
    },
    {
      "epoch": 0.08635578583765112,
      "eval_loss": 4.111455917358398,
      "eval_runtime": 6.6401,
      "eval_samples_per_second": 73.493,
      "eval_steps_per_second": 18.373,
      "step": 100
    },
    {
      "epoch": 0.09499136442141623,
      "grad_norm": 116.87757110595703,
      "learning_rate": 0.0002009222730524731,
      "loss": 9.3815,
      "step": 110
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 203.64956665039062,
      "learning_rate": 0.00019770949725018733,
      "loss": 8.3639,
      "step": 120
    },
    {
      "epoch": 0.11226252158894647,
      "grad_norm": 709.5479736328125,
      "learning_rate": 0.00019404505009642473,
      "loss": 9.0807,
      "step": 130
    },
    {
      "epoch": 0.12089810017271158,
      "grad_norm": 485.1632385253906,
      "learning_rate": 0.0001899467844093695,
      "loss": 9.3948,
      "step": 140
    },
    {
      "epoch": 0.12953367875647667,
      "grad_norm": 68.30054473876953,
      "learning_rate": 0.00018543466652749268,
      "loss": 9.8128,
      "step": 150
    },
    {
      "epoch": 0.12953367875647667,
      "eval_loss": 4.509408950805664,
      "eval_runtime": 6.6584,
      "eval_samples_per_second": 73.291,
      "eval_steps_per_second": 18.323,
      "step": 150
    },
    {
      "epoch": 0.1381692573402418,
      "grad_norm": 49.328487396240234,
      "learning_rate": 0.00018053067903555837,
      "loss": 8.1567,
      "step": 160
    },
    {
      "epoch": 0.14680483592400692,
      "grad_norm": 51.78285598754883,
      "learning_rate": 0.00017525871366768012,
      "loss": 6.7827,
      "step": 170
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 26.78425407409668,
      "learning_rate": 0.00016964445490919413,
      "loss": 6.8905,
      "step": 180
    },
    {
      "epoch": 0.16407599309153714,
      "grad_norm": 114.72111511230469,
      "learning_rate": 0.00016371525486442843,
      "loss": 6.8923,
      "step": 190
    },
    {
      "epoch": 0.17271157167530224,
      "grad_norm": 136.30235290527344,
      "learning_rate": 0.0001575,
      "loss": 6.9788,
      "step": 200
    },
    {
      "epoch": 0.17271157167530224,
      "eval_loss": 3.53438401222229,
      "eval_runtime": 6.669,
      "eval_samples_per_second": 73.175,
      "eval_steps_per_second": 18.294,
      "step": 200
    },
    {
      "epoch": 0.18134715025906736,
      "grad_norm": 531.1268920898438,
      "learning_rate": 0.00015102897041285315,
      "loss": 7.6385,
      "step": 210
    },
    {
      "epoch": 0.18998272884283246,
      "grad_norm": 769.6386108398438,
      "learning_rate": 0.00014433369230867077,
      "loss": 9.0432,
      "step": 220
    },
    {
      "epoch": 0.19861830742659758,
      "grad_norm": 86.73228454589844,
      "learning_rate": 0.0001374467844093695,
      "loss": 8.1367,
      "step": 230
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 71.22868347167969,
      "learning_rate": 0.0001304017990379651,
      "loss": 7.3369,
      "step": 240
    },
    {
      "epoch": 0.2158894645941278,
      "grad_norm": 92.49053192138672,
      "learning_rate": 0.0001232330586550277,
      "loss": 6.71,
      "step": 250
    },
    {
      "epoch": 0.2158894645941278,
      "eval_loss": 3.505357503890991,
      "eval_runtime": 6.6649,
      "eval_samples_per_second": 73.219,
      "eval_steps_per_second": 18.305,
      "step": 250
    },
    {
      "epoch": 0.22452504317789293,
      "grad_norm": 113.52294158935547,
      "learning_rate": 0.00011597548864310363,
      "loss": 6.9686,
      "step": 260
    },
    {
      "epoch": 0.23316062176165803,
      "grad_norm": 181.00125122070312,
      "learning_rate": 0.00010866444715376263,
      "loss": 6.5956,
      "step": 270
    },
    {
      "epoch": 0.24179620034542315,
      "grad_norm": 295.9447326660156,
      "learning_rate": 0.00010133555284623744,
      "loss": 6.5293,
      "step": 280
    },
    {
      "epoch": 0.2504317789291883,
      "grad_norm": 189.24530029296875,
      "learning_rate": 9.402451135689641e-05,
      "loss": 6.727,
      "step": 290
    },
    {
      "epoch": 0.25906735751295334,
      "grad_norm": 142.2465362548828,
      "learning_rate": 8.676694134497232e-05,
      "loss": 6.7211,
      "step": 300
    },
    {
      "epoch": 0.25906735751295334,
      "eval_loss": 3.346792221069336,
      "eval_runtime": 6.6861,
      "eval_samples_per_second": 72.987,
      "eval_steps_per_second": 18.247,
      "step": 300
    },
    {
      "epoch": 0.26770293609671847,
      "grad_norm": 250.88473510742188,
      "learning_rate": 7.95982009620349e-05,
      "loss": 6.4387,
      "step": 310
    },
    {
      "epoch": 0.2763385146804836,
      "grad_norm": 167.4871368408203,
      "learning_rate": 7.255321559063053e-05,
      "loss": 6.3941,
      "step": 320
    },
    {
      "epoch": 0.2849740932642487,
      "grad_norm": 257.501220703125,
      "learning_rate": 6.566630769132923e-05,
      "loss": 6.8217,
      "step": 330
    },
    {
      "epoch": 0.29360967184801384,
      "grad_norm": 157.9259033203125,
      "learning_rate": 5.897102958714686e-05,
      "loss": 6.7069,
      "step": 340
    },
    {
      "epoch": 0.3022452504317789,
      "grad_norm": 94.20719909667969,
      "learning_rate": 5.250000000000002e-05,
      "loss": 6.9331,
      "step": 350
    },
    {
      "epoch": 0.3022452504317789,
      "eval_loss": 3.275651454925537,
      "eval_runtime": 6.7141,
      "eval_samples_per_second": 72.683,
      "eval_steps_per_second": 18.171,
      "step": 350
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 112.30079650878906,
      "learning_rate": 4.62847451355716e-05,
      "loss": 7.1002,
      "step": 360
    },
    {
      "epoch": 0.31951640759930916,
      "grad_norm": 145.58631896972656,
      "learning_rate": 4.035554509080588e-05,
      "loss": 6.4866,
      "step": 370
    },
    {
      "epoch": 0.3281519861830743,
      "grad_norm": 114.67252349853516,
      "learning_rate": 3.474128633231992e-05,
      "loss": 6.2346,
      "step": 380
    },
    {
      "epoch": 0.33678756476683935,
      "grad_norm": 68.26001739501953,
      "learning_rate": 2.946932096444165e-05,
      "loss": 5.992,
      "step": 390
    },
    {
      "epoch": 0.3454231433506045,
      "grad_norm": 128.07357788085938,
      "learning_rate": 2.456533347250732e-05,
      "loss": 6.4847,
      "step": 400
    },
    {
      "epoch": 0.3454231433506045,
      "eval_loss": 3.2016987800598145,
      "eval_runtime": 6.6861,
      "eval_samples_per_second": 72.987,
      "eval_steps_per_second": 18.247,
      "step": 400
    },
    {
      "epoch": 0.3540587219343696,
      "grad_norm": 95.15899658203125,
      "learning_rate": 2.005321559063053e-05,
      "loss": 6.611,
      "step": 410
    },
    {
      "epoch": 0.3626943005181347,
      "grad_norm": 90.93391418457031,
      "learning_rate": 1.5954949903575276e-05,
      "loss": 6.4129,
      "step": 420
    },
    {
      "epoch": 0.37132987910189985,
      "grad_norm": 197.74005126953125,
      "learning_rate": 1.2290502749812666e-05,
      "loss": 6.6629,
      "step": 430
    },
    {
      "epoch": 0.3799654576856649,
      "grad_norm": 122.5657730102539,
      "learning_rate": 9.077726947526898e-06,
      "loss": 6.6915,
      "step": 440
    },
    {
      "epoch": 0.38860103626943004,
      "grad_norm": 114.84415435791016,
      "learning_rate": 6.332274817479627e-06,
      "loss": 6.6208,
      "step": 450
    },
    {
      "epoch": 0.38860103626943004,
      "eval_loss": 3.2092630863189697,
      "eval_runtime": 6.7137,
      "eval_samples_per_second": 72.687,
      "eval_steps_per_second": 18.172,
      "step": 450
    },
    {
      "epoch": 0.39723661485319517,
      "grad_norm": 135.63075256347656,
      "learning_rate": 4.067521926476516e-06,
      "loss": 6.3582,
      "step": 460
    },
    {
      "epoch": 0.4058721934369603,
      "grad_norm": 60.413612365722656,
      "learning_rate": 2.294501922950403e-06,
      "loss": 6.2606,
      "step": 470
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 293.9761962890625,
      "learning_rate": 1.021852782135112e-06,
      "loss": 6.8701,
      "step": 480
    },
    {
      "epoch": 0.4231433506044905,
      "grad_norm": 201.35853576660156,
      "learning_rate": 2.5577472271845927e-07,
      "loss": 6.5198,
      "step": 490
    },
    {
      "epoch": 0.4317789291882556,
      "grad_norm": 332.1162414550781,
      "learning_rate": 0.0,
      "loss": 6.4061,
      "step": 500
    },
    {
      "epoch": 0.4317789291882556,
      "eval_loss": 3.1905126571655273,
      "eval_runtime": 6.702,
      "eval_samples_per_second": 72.814,
      "eval_steps_per_second": 18.203,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 4657011228672000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}