{
  "best_metric": 2.035742998123169,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.1804077214504781,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036081544290095615,
      "eval_loss": 2.921983242034912,
      "eval_runtime": 73.4498,
      "eval_samples_per_second": 15.888,
      "eval_steps_per_second": 3.976,
      "step": 1
    },
    {
      "epoch": 0.0036081544290095615,
      "grad_norm": 1.535165548324585,
      "learning_rate": 4.36e-05,
      "loss": 2.4652,
      "step": 10
    },
    {
      "epoch": 0.007216308858019123,
      "grad_norm": 1.88742196559906,
      "learning_rate": 8.72e-05,
      "loss": 2.3561,
      "step": 20
    },
    {
      "epoch": 0.010824463287028685,
      "grad_norm": 1.9067068099975586,
      "learning_rate": 0.0001308,
      "loss": 2.2395,
      "step": 30
    },
    {
      "epoch": 0.014432617716038246,
      "grad_norm": 2.238699436187744,
      "learning_rate": 0.0001744,
      "loss": 2.1678,
      "step": 40
    },
    {
      "epoch": 0.018040772145047807,
      "grad_norm": 4.385190963745117,
      "learning_rate": 0.000218,
      "loss": 2.1124,
      "step": 50
    },
    {
      "epoch": 0.018040772145047807,
      "eval_loss": 2.351407289505005,
      "eval_runtime": 73.4767,
      "eval_samples_per_second": 15.883,
      "eval_steps_per_second": 3.974,
      "step": 50
    },
    {
      "epoch": 0.02164892657405737,
      "grad_norm": 1.5297818183898926,
      "learning_rate": 0.00021773448147832086,
      "loss": 2.0854,
      "step": 60
    },
    {
      "epoch": 0.025257081003066933,
      "grad_norm": 1.3838398456573486,
      "learning_rate": 0.0002169392194928312,
      "loss": 2.0998,
      "step": 70
    },
    {
      "epoch": 0.028865235432076492,
      "grad_norm": 2.074045181274414,
      "learning_rate": 0.00021561808847998484,
      "loss": 2.2113,
      "step": 80
    },
    {
      "epoch": 0.032473389861086055,
      "grad_norm": 2.1741549968719482,
      "learning_rate": 0.00021377752485727676,
      "loss": 2.1485,
      "step": 90
    },
    {
      "epoch": 0.036081544290095614,
      "grad_norm": 6.557363986968994,
      "learning_rate": 0.00021142649566566402,
      "loss": 2.1276,
      "step": 100
    },
    {
      "epoch": 0.036081544290095614,
      "eval_loss": 2.3574182987213135,
      "eval_runtime": 73.3643,
      "eval_samples_per_second": 15.907,
      "eval_steps_per_second": 3.98,
      "step": 100
    },
    {
      "epoch": 0.03968969871910518,
      "grad_norm": 1.5597459077835083,
      "learning_rate": 0.0002085764548830435,
      "loss": 2.2556,
      "step": 110
    },
    {
      "epoch": 0.04329785314811474,
      "grad_norm": 1.775914192199707,
      "learning_rate": 0.00020524128762162305,
      "loss": 2.3104,
      "step": 120
    },
    {
      "epoch": 0.0469060075771243,
      "grad_norm": 1.6727547645568848,
      "learning_rate": 0.00020143724248105043,
      "loss": 2.1549,
      "step": 130
    },
    {
      "epoch": 0.050514162006133866,
      "grad_norm": 2.4896557331085205,
      "learning_rate": 0.0001971828523868693,
      "loss": 2.1205,
      "step": 140
    },
    {
      "epoch": 0.054122316435143425,
      "grad_norm": 4.250438213348389,
      "learning_rate": 0.0001924988442999686,
      "loss": 2.0478,
      "step": 150
    },
    {
      "epoch": 0.054122316435143425,
      "eval_loss": 2.2884583473205566,
      "eval_runtime": 73.1329,
      "eval_samples_per_second": 15.957,
      "eval_steps_per_second": 3.993,
      "step": 150
    },
    {
      "epoch": 0.057730470864152984,
      "grad_norm": 1.366658329963684,
      "learning_rate": 0.00018740803823691298,
      "loss": 2.172,
      "step": 160
    },
    {
      "epoch": 0.06133862529316255,
      "grad_norm": 1.5560624599456787,
      "learning_rate": 0.00018193523609311556,
      "loss": 2.3027,
      "step": 170
    },
    {
      "epoch": 0.06494677972217211,
      "grad_norm": 1.9186638593673706,
      "learning_rate": 0.00017610710081049675,
      "loss": 2.1255,
      "step": 180
    },
    {
      "epoch": 0.06855493415118168,
      "grad_norm": 2.413241386413574,
      "learning_rate": 0.00016995202647831142,
      "loss": 2.1701,
      "step": 190
    },
    {
      "epoch": 0.07216308858019123,
      "grad_norm": 4.694942474365234,
      "learning_rate": 0.00016350000000000002,
      "loss": 2.0427,
      "step": 200
    },
    {
      "epoch": 0.07216308858019123,
      "eval_loss": 2.2128450870513916,
      "eval_runtime": 73.3767,
      "eval_samples_per_second": 15.904,
      "eval_steps_per_second": 3.979,
      "step": 200
    },
    {
      "epoch": 0.0757712430092008,
      "grad_norm": 1.2760608196258545,
      "learning_rate": 0.00015678245500000943,
      "loss": 2.2211,
      "step": 210
    },
    {
      "epoch": 0.07937939743821036,
      "grad_norm": 1.7979975938796997,
      "learning_rate": 0.00014983211868233444,
      "loss": 2.3215,
      "step": 220
    },
    {
      "epoch": 0.08298755186721991,
      "grad_norm": 2.1475672721862793,
      "learning_rate": 0.00014268285238686927,
      "loss": 2.1729,
      "step": 230
    },
    {
      "epoch": 0.08659570629622948,
      "grad_norm": 2.0573699474334717,
      "learning_rate": 0.00013536948662036378,
      "loss": 2.0533,
      "step": 240
    },
    {
      "epoch": 0.09020386072523905,
      "grad_norm": 5.545847415924072,
      "learning_rate": 0.00012792765136569544,
      "loss": 2.0229,
      "step": 250
    },
    {
      "epoch": 0.09020386072523905,
      "eval_loss": 2.196916341781616,
      "eval_runtime": 73.0911,
      "eval_samples_per_second": 15.966,
      "eval_steps_per_second": 3.995,
      "step": 250
    },
    {
      "epoch": 0.0938120151542486,
      "grad_norm": 1.4615882635116577,
      "learning_rate": 0.00012039360249617425,
      "loss": 2.2424,
      "step": 260
    },
    {
      "epoch": 0.09742016958325816,
      "grad_norm": 1.7726435661315918,
      "learning_rate": 0.00011280404514057264,
      "loss": 2.147,
      "step": 270
    },
    {
      "epoch": 0.10102832401226773,
      "grad_norm": 1.9420199394226074,
      "learning_rate": 0.00010519595485942743,
      "loss": 2.157,
      "step": 280
    },
    {
      "epoch": 0.10463647844127728,
      "grad_norm": 2.1413962841033936,
      "learning_rate": 9.76063975038258e-05,
      "loss": 1.9894,
      "step": 290
    },
    {
      "epoch": 0.10824463287028685,
      "grad_norm": 5.385281562805176,
      "learning_rate": 9.00723486343046e-05,
      "loss": 2.0386,
      "step": 300
    },
    {
      "epoch": 0.10824463287028685,
      "eval_loss": 2.1419291496276855,
      "eval_runtime": 73.4196,
      "eval_samples_per_second": 15.895,
      "eval_steps_per_second": 3.977,
      "step": 300
    },
    {
      "epoch": 0.11185278729929642,
      "grad_norm": 1.4185280799865723,
      "learning_rate": 8.263051337963623e-05,
      "loss": 2.2137,
      "step": 310
    },
    {
      "epoch": 0.11546094172830597,
      "grad_norm": 1.4617102146148682,
      "learning_rate": 7.531714761313074e-05,
      "loss": 2.1878,
      "step": 320
    },
    {
      "epoch": 0.11906909615731553,
      "grad_norm": 1.7664028406143188,
      "learning_rate": 6.816788131766559e-05,
      "loss": 2.0554,
      "step": 330
    },
    {
      "epoch": 0.1226772505863251,
      "grad_norm": 2.4227097034454346,
      "learning_rate": 6.121754499999055e-05,
      "loss": 2.0241,
      "step": 340
    },
    {
      "epoch": 0.12628540501533467,
      "grad_norm": 4.657759189605713,
      "learning_rate": 5.450000000000003e-05,
      "loss": 2.0051,
      "step": 350
    },
    {
      "epoch": 0.12628540501533467,
      "eval_loss": 2.0811328887939453,
      "eval_runtime": 73.35,
      "eval_samples_per_second": 15.91,
      "eval_steps_per_second": 3.981,
      "step": 350
    },
    {
      "epoch": 0.12989355944434422,
      "grad_norm": 1.0652941465377808,
      "learning_rate": 4.804797352168861e-05,
      "loss": 2.1246,
      "step": 360
    },
    {
      "epoch": 0.13350171387335377,
      "grad_norm": 1.3440688848495483,
      "learning_rate": 4.189289918950325e-05,
      "loss": 2.0742,
      "step": 370
    },
    {
      "epoch": 0.13710986830236335,
      "grad_norm": 1.5741288661956787,
      "learning_rate": 3.606476390688449e-05,
      "loss": 2.0424,
      "step": 380
    },
    {
      "epoch": 0.1407180227313729,
      "grad_norm": 1.601135492324829,
      "learning_rate": 3.0591961763087043e-05,
      "loss": 2.0331,
      "step": 390
    },
    {
      "epoch": 0.14432617716038246,
      "grad_norm": 4.815340518951416,
      "learning_rate": 2.550115570003141e-05,
      "loss": 2.0085,
      "step": 400
    },
    {
      "epoch": 0.14432617716038246,
      "eval_loss": 2.0443766117095947,
      "eval_runtime": 73.424,
      "eval_samples_per_second": 15.894,
      "eval_steps_per_second": 3.977,
      "step": 400
    },
    {
      "epoch": 0.14793433158939204,
      "grad_norm": 1.3404114246368408,
      "learning_rate": 2.081714761313074e-05,
      "loss": 2.2207,
      "step": 410
    },
    {
      "epoch": 0.1515424860184016,
      "grad_norm": 1.5793532133102417,
      "learning_rate": 1.656275751894957e-05,
      "loss": 2.0376,
      "step": 420
    },
    {
      "epoch": 0.15515064044741114,
      "grad_norm": 1.5471128225326538,
      "learning_rate": 1.275871237837696e-05,
      "loss": 2.1071,
      "step": 430
    },
    {
      "epoch": 0.15875879487642072,
      "grad_norm": 2.025006055831909,
      "learning_rate": 9.423545116956494e-06,
      "loss": 1.9576,
      "step": 440
    },
    {
      "epoch": 0.16236694930543027,
      "grad_norm": 3.5461795330047607,
      "learning_rate": 6.573504334335994e-06,
      "loss": 1.9234,
      "step": 450
    },
    {
      "epoch": 0.16236694930543027,
      "eval_loss": 2.035742998123169,
      "eval_runtime": 73.4959,
      "eval_samples_per_second": 15.878,
      "eval_steps_per_second": 3.973,
      "step": 450
    },
    {
      "epoch": 0.16597510373443983,
      "grad_norm": 1.0669924020767212,
      "learning_rate": 4.22247514272324e-06,
      "loss": 2.0513,
      "step": 460
    },
    {
      "epoch": 0.1695832581634494,
      "grad_norm": 1.5129503011703491,
      "learning_rate": 2.38191152001518e-06,
      "loss": 2.0959,
      "step": 470
    },
    {
      "epoch": 0.17319141259245896,
      "grad_norm": 1.5468735694885254,
      "learning_rate": 1.0607805071688306e-06,
      "loss": 2.1127,
      "step": 480
    },
    {
      "epoch": 0.1767995670214685,
      "grad_norm": 1.8866146802902222,
      "learning_rate": 2.655185216791625e-07,
      "loss": 2.0466,
      "step": 490
    },
    {
      "epoch": 0.1804077214504781,
      "grad_norm": 4.180663108825684,
      "learning_rate": 0.0,
      "loss": 1.813,
      "step": 500
    },
    {
      "epoch": 0.1804077214504781,
      "eval_loss": 2.0386555194854736,
      "eval_runtime": 73.3404,
      "eval_samples_per_second": 15.912,
      "eval_steps_per_second": 3.981,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.72048437304361e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}