{
  "best_metric": 0.27326497435569763,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.17834849295523453,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003566969859104691,
      "eval_loss": 1.6572248935699463,
      "eval_runtime": 126.1616,
      "eval_samples_per_second": 9.361,
      "eval_steps_per_second": 2.346,
      "step": 1
    },
    {
      "epoch": 0.0035669698591046907,
      "grad_norm": 2.7096357345581055,
      "learning_rate": 4.34e-05,
      "loss": 0.9751,
      "step": 10
    },
    {
      "epoch": 0.0071339397182093815,
      "grad_norm": 10.129169464111328,
      "learning_rate": 8.68e-05,
      "loss": 0.6725,
      "step": 20
    },
    {
      "epoch": 0.010700909577314071,
      "grad_norm": 1.403724193572998,
      "learning_rate": 0.0001302,
      "loss": 0.4999,
      "step": 30
    },
    {
      "epoch": 0.014267879436418763,
      "grad_norm": 1.566288948059082,
      "learning_rate": 0.0001736,
      "loss": 0.5148,
      "step": 40
    },
    {
      "epoch": 0.017834849295523453,
      "grad_norm": 1.1698219776153564,
      "learning_rate": 0.000217,
      "loss": 0.3887,
      "step": 50
    },
    {
      "epoch": 0.017834849295523453,
      "eval_loss": 0.5776557326316833,
      "eval_runtime": 126.4119,
      "eval_samples_per_second": 9.342,
      "eval_steps_per_second": 2.342,
      "step": 50
    },
    {
      "epoch": 0.021401819154628143,
      "grad_norm": 1.3930236101150513,
      "learning_rate": 0.00021673569945319091,
      "loss": 0.5755,
      "step": 60
    },
    {
      "epoch": 0.024968789013732832,
      "grad_norm": 0.9935230612754822,
      "learning_rate": 0.00021594408545846038,
      "loss": 0.4614,
      "step": 70
    },
    {
      "epoch": 0.028535758872837526,
      "grad_norm": 1.562578558921814,
      "learning_rate": 0.0002146290146796179,
      "loss": 0.4925,
      "step": 80
    },
    {
      "epoch": 0.03210272873194221,
      "grad_norm": 1.2459532022476196,
      "learning_rate": 0.0002127968940093076,
      "loss": 0.3117,
      "step": 90
    },
    {
      "epoch": 0.035669698591046906,
      "grad_norm": 1.4213972091674805,
      "learning_rate": 0.00021045664935527106,
      "loss": 0.4069,
      "step": 100
    },
    {
      "epoch": 0.035669698591046906,
      "eval_loss": 0.6545668840408325,
      "eval_runtime": 126.3911,
      "eval_samples_per_second": 9.344,
      "eval_steps_per_second": 2.342,
      "step": 100
    },
    {
      "epoch": 0.0392366684501516,
      "grad_norm": 1.6053053140640259,
      "learning_rate": 0.00020761968215422217,
      "loss": 0.6128,
      "step": 110
    },
    {
      "epoch": 0.042803638309256285,
      "grad_norm": 1.4004822969436646,
      "learning_rate": 0.00020429981382519356,
      "loss": 0.5975,
      "step": 120
    },
    {
      "epoch": 0.04637060816836098,
      "grad_norm": 1.241351842880249,
      "learning_rate": 0.00020051321843297219,
      "loss": 0.4978,
      "step": 130
    },
    {
      "epoch": 0.049937578027465665,
      "grad_norm": 5.282879829406738,
      "learning_rate": 0.0001962783438896818,
      "loss": 0.4208,
      "step": 140
    },
    {
      "epoch": 0.05350454788657036,
      "grad_norm": 2.913874864578247,
      "learning_rate": 0.0001916158220784091,
      "loss": 0.3688,
      "step": 150
    },
    {
      "epoch": 0.05350454788657036,
      "eval_loss": 0.5131043791770935,
      "eval_runtime": 126.3713,
      "eval_samples_per_second": 9.345,
      "eval_steps_per_second": 2.342,
      "step": 150
    },
    {
      "epoch": 0.05707151774567505,
      "grad_norm": 1.2657321691513062,
      "learning_rate": 0.00018654836833674362,
      "loss": 0.6035,
      "step": 160
    },
    {
      "epoch": 0.06063848760477974,
      "grad_norm": 1.2073376178741455,
      "learning_rate": 0.0001811006707899361,
      "loss": 0.3707,
      "step": 170
    },
    {
      "epoch": 0.06420545746388442,
      "grad_norm": 1.2466622591018677,
      "learning_rate": 0.0001752992700728339,
      "loss": 0.4732,
      "step": 180
    },
    {
      "epoch": 0.06777242732298912,
      "grad_norm": 1.2483686208724976,
      "learning_rate": 0.00016917243002657602,
      "loss": 0.3561,
      "step": 190
    },
    {
      "epoch": 0.07133939718209381,
      "grad_norm": 1.5653057098388672,
      "learning_rate": 0.00016275,
      "loss": 0.4015,
      "step": 200
    },
    {
      "epoch": 0.07133939718209381,
      "eval_loss": 0.5132488012313843,
      "eval_runtime": 126.2518,
      "eval_samples_per_second": 9.354,
      "eval_steps_per_second": 2.345,
      "step": 200
    },
    {
      "epoch": 0.0749063670411985,
      "grad_norm": 1.5472954511642456,
      "learning_rate": 0.0001560632694266149,
      "loss": 0.5455,
      "step": 210
    },
    {
      "epoch": 0.0784733369003032,
      "grad_norm": 1.3301926851272583,
      "learning_rate": 0.00014914481538562646,
      "loss": 0.4256,
      "step": 220
    },
    {
      "epoch": 0.08204030675940788,
      "grad_norm": 1.182495355606079,
      "learning_rate": 0.0001420283438896818,
      "loss": 0.3823,
      "step": 230
    },
    {
      "epoch": 0.08560727661851257,
      "grad_norm": 1.007603645324707,
      "learning_rate": 0.00013474852567256393,
      "loss": 0.275,
      "step": 240
    },
    {
      "epoch": 0.08917424647761726,
      "grad_norm": 1.2171993255615234,
      "learning_rate": 0.00012734082727686196,
      "loss": 0.2953,
      "step": 250
    },
    {
      "epoch": 0.08917424647761726,
      "eval_loss": 0.47643429040908813,
      "eval_runtime": 126.4327,
      "eval_samples_per_second": 9.341,
      "eval_steps_per_second": 2.341,
      "step": 250
    },
    {
      "epoch": 0.09274121633672196,
      "grad_norm": 1.6132450103759766,
      "learning_rate": 0.0001198413382645404,
      "loss": 0.5383,
      "step": 260
    },
    {
      "epoch": 0.09630818619582665,
      "grad_norm": 1.4011763334274292,
      "learning_rate": 0.00011228659539222137,
      "loss": 0.3738,
      "step": 270
    },
    {
      "epoch": 0.09987515605493133,
      "grad_norm": 1.091366171836853,
      "learning_rate": 0.00010471340460777866,
      "loss": 0.3487,
      "step": 280
    },
    {
      "epoch": 0.10344212591403602,
      "grad_norm": 1.5295441150665283,
      "learning_rate": 9.715866173545961e-05,
      "loss": 0.3104,
      "step": 290
    },
    {
      "epoch": 0.10700909577314072,
      "grad_norm": 0.5504244565963745,
      "learning_rate": 8.965917272313806e-05,
      "loss": 0.2395,
      "step": 300
    },
    {
      "epoch": 0.10700909577314072,
      "eval_loss": 0.3887171447277069,
      "eval_runtime": 126.4389,
      "eval_samples_per_second": 9.34,
      "eval_steps_per_second": 2.341,
      "step": 300
    },
    {
      "epoch": 0.11057606563224541,
      "grad_norm": 1.032090425491333,
      "learning_rate": 8.225147432743606e-05,
      "loss": 0.5718,
      "step": 310
    },
    {
      "epoch": 0.1141430354913501,
      "grad_norm": 0.9163453578948975,
      "learning_rate": 7.497165611031821e-05,
      "loss": 0.3106,
      "step": 320
    },
    {
      "epoch": 0.11771000535045478,
      "grad_norm": 0.7260503172874451,
      "learning_rate": 6.785518461437353e-05,
      "loss": 0.3202,
      "step": 330
    },
    {
      "epoch": 0.12127697520955948,
      "grad_norm": 0.6277322173118591,
      "learning_rate": 6.093673057338509e-05,
      "loss": 0.2855,
      "step": 340
    },
    {
      "epoch": 0.12484394506866417,
      "grad_norm": 1.2401589155197144,
      "learning_rate": 5.4250000000000024e-05,
      "loss": 0.2984,
      "step": 350
    },
    {
      "epoch": 0.12484394506866417,
      "eval_loss": 0.35979732871055603,
      "eval_runtime": 126.6911,
      "eval_samples_per_second": 9.322,
      "eval_steps_per_second": 2.336,
      "step": 350
    },
    {
      "epoch": 0.12841091492776885,
      "grad_norm": 1.1920021772384644,
      "learning_rate": 4.782756997342398e-05,
      "loss": 0.4701,
      "step": 360
    },
    {
      "epoch": 0.13197788478687356,
      "grad_norm": 1.140146255493164,
      "learning_rate": 4.170072992716607e-05,
      "loss": 0.3846,
      "step": 370
    },
    {
      "epoch": 0.13554485464597824,
      "grad_norm": 0.6016573309898376,
      "learning_rate": 3.5899329210063916e-05,
      "loss": 0.2747,
      "step": 380
    },
    {
      "epoch": 0.13911182450508294,
      "grad_norm": 0.7130181193351746,
      "learning_rate": 3.045163166325637e-05,
      "loss": 0.2489,
      "step": 390
    },
    {
      "epoch": 0.14267879436418762,
      "grad_norm": 0.7759641408920288,
      "learning_rate": 2.5384177921590895e-05,
      "loss": 0.1899,
      "step": 400
    },
    {
      "epoch": 0.14267879436418762,
      "eval_loss": 0.3352268934249878,
      "eval_runtime": 126.4127,
      "eval_samples_per_second": 9.342,
      "eval_steps_per_second": 2.342,
      "step": 400
    },
    {
      "epoch": 0.1462457642232923,
      "grad_norm": 1.3363033533096313,
      "learning_rate": 2.0721656110318213e-05,
      "loss": 0.5647,
      "step": 410
    },
    {
      "epoch": 0.149812734082397,
      "grad_norm": 0.7996323704719543,
      "learning_rate": 1.6486781567027783e-05,
      "loss": 0.276,
      "step": 420
    },
    {
      "epoch": 0.1533797039415017,
      "grad_norm": 0.8417302966117859,
      "learning_rate": 1.2700186174806422e-05,
      "loss": 0.3509,
      "step": 430
    },
    {
      "epoch": 0.1569466738006064,
      "grad_norm": 0.6128970384597778,
      "learning_rate": 9.380317845777794e-06,
      "loss": 0.2575,
      "step": 440
    },
    {
      "epoch": 0.16051364365971107,
      "grad_norm": 0.5301075577735901,
      "learning_rate": 6.543350644728947e-06,
      "loss": 0.1957,
      "step": 450
    },
    {
      "epoch": 0.16051364365971107,
      "eval_loss": 0.27697739005088806,
      "eval_runtime": 126.4761,
      "eval_samples_per_second": 9.338,
      "eval_steps_per_second": 2.34,
      "step": 450
    },
    {
      "epoch": 0.16408061351881575,
      "grad_norm": 0.767898678779602,
      "learning_rate": 4.2031059906924e-06,
      "loss": 0.4768,
      "step": 460
    },
    {
      "epoch": 0.16764758337792046,
      "grad_norm": 0.8965118527412415,
      "learning_rate": 2.3709853203820825e-06,
      "loss": 0.3135,
      "step": 470
    },
    {
      "epoch": 0.17121455323702514,
      "grad_norm": 0.7519134283065796,
      "learning_rate": 1.0559145415396157e-06,
      "loss": 0.2856,
      "step": 480
    },
    {
      "epoch": 0.17478152309612985,
      "grad_norm": 0.5825276374816895,
      "learning_rate": 2.643005468090745e-07,
      "loss": 0.2907,
      "step": 490
    },
    {
      "epoch": 0.17834849295523453,
      "grad_norm": 0.5771666169166565,
      "learning_rate": 0.0,
      "loss": 0.1991,
      "step": 500
    },
    {
      "epoch": 0.17834849295523453,
      "eval_loss": 0.27326497435569763,
      "eval_runtime": 126.8529,
      "eval_samples_per_second": 9.31,
      "eval_steps_per_second": 2.333,
      "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": 1.7989024426544333e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}