{
  "best_metric": 0.28519564867019653,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.015524816419045845,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.104963283809169e-05,
      "eval_loss": 3.72892689704895,
      "eval_runtime": 1163.8988,
      "eval_samples_per_second": 11.651,
      "eval_steps_per_second": 2.913,
      "step": 1
    },
    {
      "epoch": 0.0003104963283809169,
      "grad_norm": 3.2471072673797607,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 3.1999,
      "step": 10
    },
    {
      "epoch": 0.0006209926567618338,
      "grad_norm": 4.48224401473999,
      "learning_rate": 8.400000000000001e-05,
      "loss": 2.466,
      "step": 20
    },
    {
      "epoch": 0.0009314889851427506,
      "grad_norm": 4.198734283447266,
      "learning_rate": 0.000126,
      "loss": 0.818,
      "step": 30
    },
    {
      "epoch": 0.0012419853135236677,
      "grad_norm": 0.7716361284255981,
      "learning_rate": 0.00016800000000000002,
      "loss": 0.3401,
      "step": 40
    },
    {
      "epoch": 0.0015524816419045845,
      "grad_norm": 0.675552248954773,
      "learning_rate": 0.00021,
      "loss": 0.2693,
      "step": 50
    },
    {
      "epoch": 0.0015524816419045845,
      "eval_loss": 0.39680594205856323,
      "eval_runtime": 1162.3895,
      "eval_samples_per_second": 11.666,
      "eval_steps_per_second": 2.917,
      "step": 50
    },
    {
      "epoch": 0.0018629779702855013,
      "grad_norm": 1.1730502843856812,
      "learning_rate": 0.00020974422527728155,
      "loss": 0.3794,
      "step": 60
    },
    {
      "epoch": 0.0021734742986664183,
      "grad_norm": 2.169248580932617,
      "learning_rate": 0.0002089781472178649,
      "loss": 0.3869,
      "step": 70
    },
    {
      "epoch": 0.0024839706270473353,
      "grad_norm": 14.912446022033691,
      "learning_rate": 0.0002077054980770496,
      "loss": 0.3622,
      "step": 80
    },
    {
      "epoch": 0.002794466955428252,
      "grad_norm": 0.8610610961914062,
      "learning_rate": 0.00020593247807352348,
      "loss": 0.3092,
      "step": 90
    },
    {
      "epoch": 0.003104963283809169,
      "grad_norm": 0.7043868899345398,
      "learning_rate": 0.00020366772518252038,
      "loss": 0.3479,
      "step": 100
    },
    {
      "epoch": 0.003104963283809169,
      "eval_loss": 0.3086857795715332,
      "eval_runtime": 1161.3888,
      "eval_samples_per_second": 11.677,
      "eval_steps_per_second": 2.92,
      "step": 100
    },
    {
      "epoch": 0.003415459612190086,
      "grad_norm": 0.526524007320404,
      "learning_rate": 0.0002009222730524731,
      "loss": 0.2852,
      "step": 110
    },
    {
      "epoch": 0.0037259559405710026,
      "grad_norm": 2.453948974609375,
      "learning_rate": 0.00019770949725018733,
      "loss": 0.3807,
      "step": 120
    },
    {
      "epoch": 0.00403645226895192,
      "grad_norm": 1.1369106769561768,
      "learning_rate": 0.00019404505009642473,
      "loss": 0.4655,
      "step": 130
    },
    {
      "epoch": 0.004346948597332837,
      "grad_norm": 0.5654745101928711,
      "learning_rate": 0.0001899467844093695,
      "loss": 0.3161,
      "step": 140
    },
    {
      "epoch": 0.004657444925713753,
      "grad_norm": 0.7114362716674805,
      "learning_rate": 0.00018543466652749268,
      "loss": 0.2704,
      "step": 150
    },
    {
      "epoch": 0.004657444925713753,
      "eval_loss": 0.33749160170555115,
      "eval_runtime": 1163.9994,
      "eval_samples_per_second": 11.65,
      "eval_steps_per_second": 2.913,
      "step": 150
    },
    {
      "epoch": 0.004967941254094671,
      "grad_norm": 0.620780885219574,
      "learning_rate": 0.00018053067903555837,
      "loss": 0.333,
      "step": 160
    },
    {
      "epoch": 0.005278437582475587,
      "grad_norm": 14.071165084838867,
      "learning_rate": 0.00017525871366768012,
      "loss": 0.3744,
      "step": 170
    },
    {
      "epoch": 0.005588933910856504,
      "grad_norm": 0.7737940549850464,
      "learning_rate": 0.00016964445490919413,
      "loss": 0.3283,
      "step": 180
    },
    {
      "epoch": 0.005899430239237421,
      "grad_norm": 0.687343955039978,
      "learning_rate": 0.00016371525486442843,
      "loss": 0.3368,
      "step": 190
    },
    {
      "epoch": 0.006209926567618338,
      "grad_norm": 0.7471249103546143,
      "learning_rate": 0.0001575,
      "loss": 0.2711,
      "step": 200
    },
    {
      "epoch": 0.006209926567618338,
      "eval_loss": 0.3042045831680298,
      "eval_runtime": 1163.7747,
      "eval_samples_per_second": 11.653,
      "eval_steps_per_second": 2.914,
      "step": 200
    },
    {
      "epoch": 0.0065204228959992545,
      "grad_norm": 0.6126402616500854,
      "learning_rate": 0.00015102897041285315,
      "loss": 0.3165,
      "step": 210
    },
    {
      "epoch": 0.006830919224380172,
      "grad_norm": 3.4305641651153564,
      "learning_rate": 0.00014433369230867077,
      "loss": 0.2982,
      "step": 220
    },
    {
      "epoch": 0.0071414155527610886,
      "grad_norm": 4.1259589195251465,
      "learning_rate": 0.0001374467844093695,
      "loss": 0.4701,
      "step": 230
    },
    {
      "epoch": 0.007451911881142005,
      "grad_norm": 0.6386480331420898,
      "learning_rate": 0.0001304017990379651,
      "loss": 0.3251,
      "step": 240
    },
    {
      "epoch": 0.007762408209522923,
      "grad_norm": 0.4939100742340088,
      "learning_rate": 0.0001232330586550277,
      "loss": 0.2631,
      "step": 250
    },
    {
      "epoch": 0.007762408209522923,
      "eval_loss": 0.293373167514801,
      "eval_runtime": 1164.2178,
      "eval_samples_per_second": 11.648,
      "eval_steps_per_second": 2.913,
      "step": 250
    },
    {
      "epoch": 0.00807290453790384,
      "grad_norm": 0.7074109315872192,
      "learning_rate": 0.00011597548864310363,
      "loss": 0.2975,
      "step": 260
    },
    {
      "epoch": 0.008383400866284757,
      "grad_norm": 1.0438284873962402,
      "learning_rate": 0.00010866444715376263,
      "loss": 0.2717,
      "step": 270
    },
    {
      "epoch": 0.008693897194665673,
      "grad_norm": 0.7922680974006653,
      "learning_rate": 0.00010133555284623744,
      "loss": 0.4675,
      "step": 280
    },
    {
      "epoch": 0.00900439352304659,
      "grad_norm": 0.6056926846504211,
      "learning_rate": 9.402451135689641e-05,
      "loss": 0.314,
      "step": 290
    },
    {
      "epoch": 0.009314889851427506,
      "grad_norm": 1.8034029006958008,
      "learning_rate": 8.676694134497232e-05,
      "loss": 0.2882,
      "step": 300
    },
    {
      "epoch": 0.009314889851427506,
      "eval_loss": 0.29820531606674194,
      "eval_runtime": 1164.5486,
      "eval_samples_per_second": 11.645,
      "eval_steps_per_second": 2.912,
      "step": 300
    },
    {
      "epoch": 0.009625386179808423,
      "grad_norm": 0.48237577080726624,
      "learning_rate": 7.95982009620349e-05,
      "loss": 0.3016,
      "step": 310
    },
    {
      "epoch": 0.009935882508189341,
      "grad_norm": 0.5947824120521545,
      "learning_rate": 7.255321559063053e-05,
      "loss": 0.2607,
      "step": 320
    },
    {
      "epoch": 0.010246378836570258,
      "grad_norm": 1.112855076789856,
      "learning_rate": 6.566630769132923e-05,
      "loss": 0.4451,
      "step": 330
    },
    {
      "epoch": 0.010556875164951175,
      "grad_norm": 0.5384666919708252,
      "learning_rate": 5.897102958714686e-05,
      "loss": 0.2777,
      "step": 340
    },
    {
      "epoch": 0.010867371493332091,
      "grad_norm": 0.3258765935897827,
      "learning_rate": 5.250000000000002e-05,
      "loss": 0.2759,
      "step": 350
    },
    {
      "epoch": 0.010867371493332091,
      "eval_loss": 0.2902805805206299,
      "eval_runtime": 1164.9711,
      "eval_samples_per_second": 11.641,
      "eval_steps_per_second": 2.911,
      "step": 350
    },
    {
      "epoch": 0.011177867821713008,
      "grad_norm": 0.6546416282653809,
      "learning_rate": 4.62847451355716e-05,
      "loss": 0.3157,
      "step": 360
    },
    {
      "epoch": 0.011488364150093924,
      "grad_norm": 0.703099250793457,
      "learning_rate": 4.035554509080588e-05,
      "loss": 0.2672,
      "step": 370
    },
    {
      "epoch": 0.011798860478474843,
      "grad_norm": 1.0945324897766113,
      "learning_rate": 3.474128633231992e-05,
      "loss": 0.3675,
      "step": 380
    },
    {
      "epoch": 0.01210935680685576,
      "grad_norm": 0.3610471785068512,
      "learning_rate": 2.946932096444165e-05,
      "loss": 0.2548,
      "step": 390
    },
    {
      "epoch": 0.012419853135236676,
      "grad_norm": 0.3258683383464813,
      "learning_rate": 2.456533347250732e-05,
      "loss": 0.2487,
      "step": 400
    },
    {
      "epoch": 0.012419853135236676,
      "eval_loss": 0.2859453856945038,
      "eval_runtime": 1164.1855,
      "eval_samples_per_second": 11.648,
      "eval_steps_per_second": 2.913,
      "step": 400
    },
    {
      "epoch": 0.012730349463617592,
      "grad_norm": 0.45075902342796326,
      "learning_rate": 2.005321559063053e-05,
      "loss": 0.2686,
      "step": 410
    },
    {
      "epoch": 0.013040845791998509,
      "grad_norm": 0.568687379360199,
      "learning_rate": 1.5954949903575276e-05,
      "loss": 0.2879,
      "step": 420
    },
    {
      "epoch": 0.013351342120379427,
      "grad_norm": 1.1055338382720947,
      "learning_rate": 1.2290502749812666e-05,
      "loss": 0.3734,
      "step": 430
    },
    {
      "epoch": 0.013661838448760344,
      "grad_norm": 0.2285093367099762,
      "learning_rate": 9.077726947526898e-06,
      "loss": 0.2876,
      "step": 440
    },
    {
      "epoch": 0.01397233477714126,
      "grad_norm": 0.41890841722488403,
      "learning_rate": 6.332274817479627e-06,
      "loss": 0.2627,
      "step": 450
    },
    {
      "epoch": 0.01397233477714126,
      "eval_loss": 0.28539028763771057,
      "eval_runtime": 1163.9333,
      "eval_samples_per_second": 11.651,
      "eval_steps_per_second": 2.913,
      "step": 450
    },
    {
      "epoch": 0.014282831105522177,
      "grad_norm": 0.9566968083381653,
      "learning_rate": 4.067521926476516e-06,
      "loss": 0.291,
      "step": 460
    },
    {
      "epoch": 0.014593327433903094,
      "grad_norm": 0.5413401126861572,
      "learning_rate": 2.294501922950403e-06,
      "loss": 0.2643,
      "step": 470
    },
    {
      "epoch": 0.01490382376228401,
      "grad_norm": 0.8163195252418518,
      "learning_rate": 1.021852782135112e-06,
      "loss": 0.3415,
      "step": 480
    },
    {
      "epoch": 0.015214320090664929,
      "grad_norm": 0.27404096722602844,
      "learning_rate": 2.5577472271845927e-07,
      "loss": 0.295,
      "step": 490
    },
    {
      "epoch": 0.015524816419045845,
      "grad_norm": 0.3744218945503235,
      "learning_rate": 0.0,
      "loss": 0.2789,
      "step": 500
    },
    {
      "epoch": 0.015524816419045845,
      "eval_loss": 0.28519564867019653,
      "eval_runtime": 1163.2315,
      "eval_samples_per_second": 11.658,
      "eval_steps_per_second": 2.915,
      "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": 1.3972035882870374e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}