{
  "best_metric": 2.243114471435547,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.07436787307882994,
  "eval_steps": 50,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016526194017517766,
      "eval_loss": 3.1149251461029053,
      "eval_runtime": 43.6347,
      "eval_samples_per_second": 58.394,
      "eval_steps_per_second": 14.598,
      "step": 1
    },
    {
      "epoch": 0.0016526194017517765,
      "grad_norm": 2.4044153690338135,
      "learning_rate": 4.36e-05,
      "loss": 2.4216,
      "step": 10
    },
    {
      "epoch": 0.003305238803503553,
      "grad_norm": 3.2215139865875244,
      "learning_rate": 8.72e-05,
      "loss": 2.2895,
      "step": 20
    },
    {
      "epoch": 0.00495785820525533,
      "grad_norm": 4.437511444091797,
      "learning_rate": 0.0001308,
      "loss": 2.2952,
      "step": 30
    },
    {
      "epoch": 0.006610477607007106,
      "grad_norm": 6.676159381866455,
      "learning_rate": 0.0001744,
      "loss": 2.2616,
      "step": 40
    },
    {
      "epoch": 0.008263097008758883,
      "grad_norm": 22.480907440185547,
      "learning_rate": 0.000218,
      "loss": 2.7042,
      "step": 50
    },
    {
      "epoch": 0.008263097008758883,
      "eval_loss": 2.7512803077697754,
      "eval_runtime": 43.5634,
      "eval_samples_per_second": 58.489,
      "eval_steps_per_second": 14.622,
      "step": 50
    },
    {
      "epoch": 0.00991571641051066,
      "grad_norm": 2.332223415374756,
      "learning_rate": 0.00021773448147832086,
      "loss": 2.3331,
      "step": 60
    },
    {
      "epoch": 0.011568335812262435,
      "grad_norm": 2.4621620178222656,
      "learning_rate": 0.0002169392194928312,
      "loss": 2.3293,
      "step": 70
    },
    {
      "epoch": 0.013220955214014212,
      "grad_norm": 3.450859546661377,
      "learning_rate": 0.00021561808847998484,
      "loss": 2.1836,
      "step": 80
    },
    {
      "epoch": 0.014873574615765989,
      "grad_norm": 7.603415489196777,
      "learning_rate": 0.00021377752485727676,
      "loss": 2.2165,
      "step": 90
    },
    {
      "epoch": 0.016526194017517766,
      "grad_norm": 19.09664535522461,
      "learning_rate": 0.00021142649566566402,
      "loss": 3.0109,
      "step": 100
    },
    {
      "epoch": 0.016526194017517766,
      "eval_loss": 2.7991316318511963,
      "eval_runtime": 43.5731,
      "eval_samples_per_second": 58.476,
      "eval_steps_per_second": 14.619,
      "step": 100
    },
    {
      "epoch": 0.01817881341926954,
      "grad_norm": 2.182637929916382,
      "learning_rate": 0.0002085764548830435,
      "loss": 2.4546,
      "step": 110
    },
    {
      "epoch": 0.01983143282102132,
      "grad_norm": 2.9767863750457764,
      "learning_rate": 0.00020524128762162305,
      "loss": 2.252,
      "step": 120
    },
    {
      "epoch": 0.021484052222773095,
      "grad_norm": 4.451344966888428,
      "learning_rate": 0.00020143724248105043,
      "loss": 2.1921,
      "step": 130
    },
    {
      "epoch": 0.02313667162452487,
      "grad_norm": 5.990928649902344,
      "learning_rate": 0.0001971828523868693,
      "loss": 2.0887,
      "step": 140
    },
    {
      "epoch": 0.02478929102627665,
      "grad_norm": 19.66733741760254,
      "learning_rate": 0.0001924988442999686,
      "loss": 2.5636,
      "step": 150
    },
    {
      "epoch": 0.02478929102627665,
      "eval_loss": 2.7373805046081543,
      "eval_runtime": 43.5877,
      "eval_samples_per_second": 58.457,
      "eval_steps_per_second": 14.614,
      "step": 150
    },
    {
      "epoch": 0.026441910428028424,
      "grad_norm": 2.0548884868621826,
      "learning_rate": 0.00018740803823691298,
      "loss": 2.4033,
      "step": 160
    },
    {
      "epoch": 0.028094529829780203,
      "grad_norm": 2.9234230518341064,
      "learning_rate": 0.00018193523609311556,
      "loss": 2.2948,
      "step": 170
    },
    {
      "epoch": 0.029747149231531978,
      "grad_norm": 3.7016618251800537,
      "learning_rate": 0.00017610710081049675,
      "loss": 2.3234,
      "step": 180
    },
    {
      "epoch": 0.03139976863328375,
      "grad_norm": 5.965432643890381,
      "learning_rate": 0.00016995202647831142,
      "loss": 2.2832,
      "step": 190
    },
    {
      "epoch": 0.03305238803503553,
      "grad_norm": 17.460437774658203,
      "learning_rate": 0.00016350000000000002,
      "loss": 3.0321,
      "step": 200
    },
    {
      "epoch": 0.03305238803503553,
      "eval_loss": 2.5573222637176514,
      "eval_runtime": 43.5955,
      "eval_samples_per_second": 58.446,
      "eval_steps_per_second": 14.612,
      "step": 200
    },
    {
      "epoch": 0.03470500743678731,
      "grad_norm": 2.2317683696746826,
      "learning_rate": 0.00015678245500000943,
      "loss": 2.3917,
      "step": 210
    },
    {
      "epoch": 0.03635762683853908,
      "grad_norm": 2.6078310012817383,
      "learning_rate": 0.00014983211868233444,
      "loss": 2.3408,
      "step": 220
    },
    {
      "epoch": 0.03801024624029086,
      "grad_norm": 4.730777263641357,
      "learning_rate": 0.00014268285238686927,
      "loss": 2.2385,
      "step": 230
    },
    {
      "epoch": 0.03966286564204264,
      "grad_norm": 5.267191410064697,
      "learning_rate": 0.00013536948662036378,
      "loss": 2.4694,
      "step": 240
    },
    {
      "epoch": 0.04131548504379441,
      "grad_norm": 14.102747917175293,
      "learning_rate": 0.00012792765136569544,
      "loss": 2.8198,
      "step": 250
    },
    {
      "epoch": 0.04131548504379441,
      "eval_loss": 2.482667922973633,
      "eval_runtime": 43.6594,
      "eval_samples_per_second": 58.361,
      "eval_steps_per_second": 14.59,
      "step": 250
    },
    {
      "epoch": 0.04296810444554619,
      "grad_norm": 2.223804473876953,
      "learning_rate": 0.00012039360249617425,
      "loss": 2.3776,
      "step": 260
    },
    {
      "epoch": 0.04462072384729797,
      "grad_norm": 2.835205078125,
      "learning_rate": 0.00011280404514057264,
      "loss": 2.2912,
      "step": 270
    },
    {
      "epoch": 0.04627334324904974,
      "grad_norm": 4.878274917602539,
      "learning_rate": 0.00010519595485942743,
      "loss": 2.1857,
      "step": 280
    },
    {
      "epoch": 0.04792596265080152,
      "grad_norm": 5.728613376617432,
      "learning_rate": 9.76063975038258e-05,
      "loss": 2.2346,
      "step": 290
    },
    {
      "epoch": 0.0495785820525533,
      "grad_norm": 16.714305877685547,
      "learning_rate": 9.00723486343046e-05,
      "loss": 2.2206,
      "step": 300
    },
    {
      "epoch": 0.0495785820525533,
      "eval_loss": 2.4008781909942627,
      "eval_runtime": 43.6638,
      "eval_samples_per_second": 58.355,
      "eval_steps_per_second": 14.589,
      "step": 300
    },
    {
      "epoch": 0.05123120145430508,
      "grad_norm": 2.1384823322296143,
      "learning_rate": 8.263051337963623e-05,
      "loss": 2.2682,
      "step": 310
    },
    {
      "epoch": 0.05288382085605685,
      "grad_norm": 2.6786699295043945,
      "learning_rate": 7.531714761313074e-05,
      "loss": 2.1271,
      "step": 320
    },
    {
      "epoch": 0.05453644025780863,
      "grad_norm": 4.25484037399292,
      "learning_rate": 6.816788131766559e-05,
      "loss": 2.3849,
      "step": 330
    },
    {
      "epoch": 0.056189059659560406,
      "grad_norm": 4.951492786407471,
      "learning_rate": 6.121754499999055e-05,
      "loss": 2.1332,
      "step": 340
    },
    {
      "epoch": 0.05784167906131218,
      "grad_norm": 14.745146751403809,
      "learning_rate": 5.450000000000003e-05,
      "loss": 2.9364,
      "step": 350
    },
    {
      "epoch": 0.05784167906131218,
      "eval_loss": 2.2891488075256348,
      "eval_runtime": 43.6713,
      "eval_samples_per_second": 58.345,
      "eval_steps_per_second": 14.586,
      "step": 350
    },
    {
      "epoch": 0.059494298463063956,
      "grad_norm": 1.9254217147827148,
      "learning_rate": 4.804797352168861e-05,
      "loss": 2.1897,
      "step": 360
    },
    {
      "epoch": 0.061146917864815735,
      "grad_norm": 2.3489015102386475,
      "learning_rate": 4.189289918950325e-05,
      "loss": 2.2346,
      "step": 370
    },
    {
      "epoch": 0.0627995372665675,
      "grad_norm": 3.7030725479125977,
      "learning_rate": 3.606476390688449e-05,
      "loss": 2.2318,
      "step": 380
    },
    {
      "epoch": 0.06445215666831929,
      "grad_norm": 5.087347507476807,
      "learning_rate": 3.0591961763087043e-05,
      "loss": 2.2742,
      "step": 390
    },
    {
      "epoch": 0.06610477607007106,
      "grad_norm": 16.04279899597168,
      "learning_rate": 2.550115570003141e-05,
      "loss": 2.5913,
      "step": 400
    },
    {
      "epoch": 0.06610477607007106,
      "eval_loss": 2.2623276710510254,
      "eval_runtime": 43.6913,
      "eval_samples_per_second": 58.318,
      "eval_steps_per_second": 14.58,
      "step": 400
    },
    {
      "epoch": 0.06775739547182284,
      "grad_norm": 2.179595470428467,
      "learning_rate": 2.081714761313074e-05,
      "loss": 2.2334,
      "step": 410
    },
    {
      "epoch": 0.06941001487357462,
      "grad_norm": 2.5870578289031982,
      "learning_rate": 1.656275751894957e-05,
      "loss": 2.1487,
      "step": 420
    },
    {
      "epoch": 0.07106263427532639,
      "grad_norm": 3.1885182857513428,
      "learning_rate": 1.275871237837696e-05,
      "loss": 2.0605,
      "step": 430
    },
    {
      "epoch": 0.07271525367707816,
      "grad_norm": 5.060018539428711,
      "learning_rate": 9.423545116956494e-06,
      "loss": 2.3016,
      "step": 440
    },
    {
      "epoch": 0.07436787307882994,
      "grad_norm": 12.431950569152832,
      "learning_rate": 6.573504334335994e-06,
      "loss": 2.5269,
      "step": 450
    },
    {
      "epoch": 0.07436787307882994,
      "eval_loss": 2.243114471435547,
      "eval_runtime": 43.9155,
      "eval_samples_per_second": 58.021,
      "eval_steps_per_second": 14.505,
      "step": 450
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.13234235359232e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}