{
  "best_metric": 1.2006784677505493,
  "best_model_checkpoint": "miner_id_24/checkpoint-550",
  "epoch": 0.3917727717923604,
  "eval_steps": 50,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000652954619653934,
      "eval_loss": 1.7593097686767578,
      "eval_runtime": 42.0818,
      "eval_samples_per_second": 61.285,
      "eval_steps_per_second": 15.327,
      "step": 1
    },
    {
      "epoch": 0.00652954619653934,
      "grad_norm": 0.1703435182571411,
      "learning_rate": 0.0002,
      "loss": 1.3545,
      "step": 10
    },
    {
      "epoch": 0.01305909239307868,
      "grad_norm": 0.10457056760787964,
      "learning_rate": 0.0001998582695676762,
      "loss": 1.3658,
      "step": 20
    },
    {
      "epoch": 0.019588638589618023,
      "grad_norm": 0.10769687592983246,
      "learning_rate": 0.00019943348002101371,
      "loss": 1.409,
      "step": 30
    },
    {
      "epoch": 0.02611818478615736,
      "grad_norm": 0.23312892019748688,
      "learning_rate": 0.00019872683547213446,
      "loss": 1.5118,
      "step": 40
    },
    {
      "epoch": 0.0326477309826967,
      "grad_norm": 0.8387290239334106,
      "learning_rate": 0.00019774033898178667,
      "loss": 1.6039,
      "step": 50
    },
    {
      "epoch": 0.0326477309826967,
      "eval_loss": 1.4602386951446533,
      "eval_runtime": 42.1985,
      "eval_samples_per_second": 61.116,
      "eval_steps_per_second": 15.285,
      "step": 50
    },
    {
      "epoch": 0.039177277179236046,
      "grad_norm": 0.09031832218170166,
      "learning_rate": 0.0001964767868814516,
      "loss": 1.2569,
      "step": 60
    },
    {
      "epoch": 0.045706823375775384,
      "grad_norm": 0.09168185293674469,
      "learning_rate": 0.00019493976084683813,
      "loss": 1.2857,
      "step": 70
    },
    {
      "epoch": 0.05223636957231472,
      "grad_norm": 0.1381785273551941,
      "learning_rate": 0.00019313361774523385,
      "loss": 1.3339,
      "step": 80
    },
    {
      "epoch": 0.058765915768854066,
      "grad_norm": 0.3087773323059082,
      "learning_rate": 0.00019106347728549135,
      "loss": 1.3948,
      "step": 90
    },
    {
      "epoch": 0.0652954619653934,
      "grad_norm": 0.6337625980377197,
      "learning_rate": 0.00018873520750565718,
      "loss": 1.3688,
      "step": 100
    },
    {
      "epoch": 0.0652954619653934,
      "eval_loss": 1.3073418140411377,
      "eval_runtime": 42.0855,
      "eval_samples_per_second": 61.28,
      "eval_steps_per_second": 15.326,
      "step": 100
    },
    {
      "epoch": 0.07182500816193274,
      "grad_norm": 0.15941736102104187,
      "learning_rate": 0.0001861554081393806,
      "loss": 1.2118,
      "step": 110
    },
    {
      "epoch": 0.07835455435847209,
      "grad_norm": 0.07974281907081604,
      "learning_rate": 0.0001833313919082515,
      "loss": 1.2545,
      "step": 120
    },
    {
      "epoch": 0.08488410055501143,
      "grad_norm": 0.14130432903766632,
      "learning_rate": 0.00018027116379309638,
      "loss": 1.3471,
      "step": 130
    },
    {
      "epoch": 0.09141364675155077,
      "grad_norm": 0.31553900241851807,
      "learning_rate": 0.00017698339834299061,
      "loss": 1.3692,
      "step": 140
    },
    {
      "epoch": 0.0979431929480901,
      "grad_norm": 0.9388893246650696,
      "learning_rate": 0.00017347741508630672,
      "loss": 1.4355,
      "step": 150
    },
    {
      "epoch": 0.0979431929480901,
      "eval_loss": 1.267966389656067,
      "eval_runtime": 42.2941,
      "eval_samples_per_second": 60.978,
      "eval_steps_per_second": 15.25,
      "step": 150
    },
    {
      "epoch": 0.10447273914462944,
      "grad_norm": 0.07010999321937561,
      "learning_rate": 0.0001697631521134985,
      "loss": 1.1417,
      "step": 160
    },
    {
      "epoch": 0.1110022853411688,
      "grad_norm": 0.10216495394706726,
      "learning_rate": 0.00016585113790650388,
      "loss": 1.238,
      "step": 170
    },
    {
      "epoch": 0.11753183153770813,
      "grad_norm": 0.12675678730010986,
      "learning_rate": 0.0001617524614946192,
      "loss": 1.3154,
      "step": 180
    },
    {
      "epoch": 0.12406137773424747,
      "grad_norm": 0.31328052282333374,
      "learning_rate": 0.0001574787410214407,
      "loss": 1.3155,
      "step": 190
    },
    {
      "epoch": 0.1305909239307868,
      "grad_norm": 1.081733226776123,
      "learning_rate": 0.00015304209081197425,
      "loss": 1.3807,
      "step": 200
    },
    {
      "epoch": 0.1305909239307868,
      "eval_loss": 1.2385743856430054,
      "eval_runtime": 42.1021,
      "eval_samples_per_second": 61.256,
      "eval_steps_per_second": 15.32,
      "step": 200
    },
    {
      "epoch": 0.13712047012732614,
      "grad_norm": 0.06139560416340828,
      "learning_rate": 0.00014845508703326504,
      "loss": 1.1561,
      "step": 210
    },
    {
      "epoch": 0.14365001632386548,
      "grad_norm": 0.07948515564203262,
      "learning_rate": 0.00014373073204588556,
      "loss": 1.2563,
      "step": 220
    },
    {
      "epoch": 0.15017956252040482,
      "grad_norm": 0.14629638195037842,
      "learning_rate": 0.00013888241754733208,
      "loss": 1.3074,
      "step": 230
    },
    {
      "epoch": 0.15670910871694418,
      "grad_norm": 0.3273250162601471,
      "learning_rate": 0.00013392388661180303,
      "loss": 1.288,
      "step": 240
    },
    {
      "epoch": 0.16323865491348352,
      "grad_norm": 1.0025297403335571,
      "learning_rate": 0.0001288691947339621,
      "loss": 1.242,
      "step": 250
    },
    {
      "epoch": 0.16323865491348352,
      "eval_loss": 1.2301549911499023,
      "eval_runtime": 41.9764,
      "eval_samples_per_second": 61.439,
      "eval_steps_per_second": 15.366,
      "step": 250
    },
    {
      "epoch": 0.16976820111002286,
      "grad_norm": 0.05828835442662239,
      "learning_rate": 0.0001237326699871115,
      "loss": 1.1586,
      "step": 260
    },
    {
      "epoch": 0.1762977473065622,
      "grad_norm": 0.09446071833372116,
      "learning_rate": 0.00011852887240871145,
      "loss": 1.2516,
      "step": 270
    },
    {
      "epoch": 0.18282729350310153,
      "grad_norm": 0.15607990324497223,
      "learning_rate": 0.00011327255272837221,
      "loss": 1.2933,
      "step": 280
    },
    {
      "epoch": 0.18935683969964087,
      "grad_norm": 0.35059285163879395,
      "learning_rate": 0.00010797861055530831,
      "loss": 1.2938,
      "step": 290
    },
    {
      "epoch": 0.1958863858961802,
      "grad_norm": 1.048234462738037,
      "learning_rate": 0.00010266205214377748,
      "loss": 1.1819,
      "step": 300
    },
    {
      "epoch": 0.1958863858961802,
      "eval_loss": 1.2161424160003662,
      "eval_runtime": 42.3336,
      "eval_samples_per_second": 60.921,
      "eval_steps_per_second": 15.236,
      "step": 300
    },
    {
      "epoch": 0.20241593209271955,
      "grad_norm": 0.058099668473005295,
      "learning_rate": 9.733794785622253e-05,
      "loss": 1.1525,
      "step": 310
    },
    {
      "epoch": 0.20894547828925888,
      "grad_norm": 0.09674125164747238,
      "learning_rate": 9.202138944469168e-05,
      "loss": 1.2296,
      "step": 320
    },
    {
      "epoch": 0.21547502448579825,
      "grad_norm": 0.15291635692119598,
      "learning_rate": 8.672744727162781e-05,
      "loss": 1.2739,
      "step": 330
    },
    {
      "epoch": 0.2220045706823376,
      "grad_norm": 0.2810160219669342,
      "learning_rate": 8.147112759128859e-05,
      "loss": 1.3062,
      "step": 340
    },
    {
      "epoch": 0.22853411687887693,
      "grad_norm": 0.978479266166687,
      "learning_rate": 7.626733001288851e-05,
      "loss": 1.3263,
      "step": 350
    },
    {
      "epoch": 0.22853411687887693,
      "eval_loss": 1.2151703834533691,
      "eval_runtime": 41.9719,
      "eval_samples_per_second": 61.446,
      "eval_steps_per_second": 15.367,
      "step": 350
    },
    {
      "epoch": 0.23506366307541626,
      "grad_norm": 0.054964158684015274,
      "learning_rate": 7.113080526603792e-05,
      "loss": 1.1284,
      "step": 360
    },
    {
      "epoch": 0.2415932092719556,
      "grad_norm": 0.07777497917413712,
      "learning_rate": 6.607611338819697e-05,
      "loss": 1.2268,
      "step": 370
    },
    {
      "epoch": 0.24812275546849494,
      "grad_norm": 0.1765056848526001,
      "learning_rate": 6.111758245266794e-05,
      "loss": 1.2698,
      "step": 380
    },
    {
      "epoch": 0.2546523016650343,
      "grad_norm": 0.33249780535697937,
      "learning_rate": 5.626926795411447e-05,
      "loss": 1.2465,
      "step": 390
    },
    {
      "epoch": 0.2611818478615736,
      "grad_norm": 0.7363329529762268,
      "learning_rate": 5.1544912966734994e-05,
      "loss": 1.1405,
      "step": 400
    },
    {
      "epoch": 0.2611818478615736,
      "eval_loss": 1.208735466003418,
      "eval_runtime": 41.7762,
      "eval_samples_per_second": 61.734,
      "eval_steps_per_second": 15.439,
      "step": 400
    },
    {
      "epoch": 0.26771139405811295,
      "grad_norm": 0.06299945712089539,
      "learning_rate": 4.695790918802576e-05,
      "loss": 1.1717,
      "step": 410
    },
    {
      "epoch": 0.2742409402546523,
      "grad_norm": 0.08601243048906326,
      "learning_rate": 4.252125897855932e-05,
      "loss": 1.2408,
      "step": 420
    },
    {
      "epoch": 0.2807704864511916,
      "grad_norm": 0.14494818449020386,
      "learning_rate": 3.824753850538082e-05,
      "loss": 1.2919,
      "step": 430
    },
    {
      "epoch": 0.28730003264773096,
      "grad_norm": 0.31678304076194763,
      "learning_rate": 3.414886209349615e-05,
      "loss": 1.239,
      "step": 440
    },
    {
      "epoch": 0.2938295788442703,
      "grad_norm": 1.0417225360870361,
      "learning_rate": 3.0236847886501542e-05,
      "loss": 1.1049,
      "step": 450
    },
    {
      "epoch": 0.2938295788442703,
      "eval_loss": 1.2068712711334229,
      "eval_runtime": 42.7188,
      "eval_samples_per_second": 60.372,
      "eval_steps_per_second": 15.099,
      "step": 450
    },
    {
      "epoch": 0.30035912504080964,
      "grad_norm": 0.054399143904447556,
      "learning_rate": 2.6522584913693294e-05,
      "loss": 1.1521,
      "step": 460
    },
    {
      "epoch": 0.30688867123734903,
      "grad_norm": 0.08509223908185959,
      "learning_rate": 2.301660165700936e-05,
      "loss": 1.2187,
      "step": 470
    },
    {
      "epoch": 0.31341821743388837,
      "grad_norm": 0.1509586125612259,
      "learning_rate": 1.9728836206903656e-05,
      "loss": 1.3379,
      "step": 480
    },
    {
      "epoch": 0.3199477636304277,
      "grad_norm": 0.3751097619533539,
      "learning_rate": 1.6668608091748495e-05,
      "loss": 1.3362,
      "step": 490
    },
    {
      "epoch": 0.32647730982696704,
      "grad_norm": 0.8351140022277832,
      "learning_rate": 1.3844591860619383e-05,
      "loss": 1.1598,
      "step": 500
    },
    {
      "epoch": 0.32647730982696704,
      "eval_loss": 1.2039023637771606,
      "eval_runtime": 42.6078,
      "eval_samples_per_second": 60.529,
      "eval_steps_per_second": 15.138,
      "step": 500
    },
    {
      "epoch": 0.3330068560235064,
      "grad_norm": 0.05650899186730385,
      "learning_rate": 1.1264792494342857e-05,
      "loss": 1.1749,
      "step": 510
    },
    {
      "epoch": 0.3395364022200457,
      "grad_norm": 0.0797816812992096,
      "learning_rate": 8.936522714508678e-06,
      "loss": 1.2085,
      "step": 520
    },
    {
      "epoch": 0.34606594841658506,
      "grad_norm": 0.14462202787399292,
      "learning_rate": 6.866382254766157e-06,
      "loss": 1.2441,
      "step": 530
    },
    {
      "epoch": 0.3525954946131244,
      "grad_norm": 0.30583634972572327,
      "learning_rate": 5.060239153161872e-06,
      "loss": 1.2586,
      "step": 540
    },
    {
      "epoch": 0.35912504080966373,
      "grad_norm": 0.7339666485786438,
      "learning_rate": 3.5232131185484076e-06,
      "loss": 1.1969,
      "step": 550
    },
    {
      "epoch": 0.35912504080966373,
      "eval_loss": 1.2006784677505493,
      "eval_runtime": 41.9627,
      "eval_samples_per_second": 61.459,
      "eval_steps_per_second": 15.371,
      "step": 550
    },
    {
      "epoch": 0.36565458700620307,
      "grad_norm": 0.05688609927892685,
      "learning_rate": 2.259661018213333e-06,
      "loss": 1.1429,
      "step": 560
    },
    {
      "epoch": 0.3721841332027424,
      "grad_norm": 0.08461929857730865,
      "learning_rate": 1.2731645278655445e-06,
      "loss": 1.2267,
      "step": 570
    },
    {
      "epoch": 0.37871367939928174,
      "grad_norm": 0.17034894227981567,
      "learning_rate": 5.665199789862907e-07,
      "loss": 1.2762,
      "step": 580
    },
    {
      "epoch": 0.3852432255958211,
      "grad_norm": 0.2856343984603882,
      "learning_rate": 1.4173043232380557e-07,
      "loss": 1.2923,
      "step": 590
    },
    {
      "epoch": 0.3917727717923604,
      "grad_norm": 0.926727831363678,
      "learning_rate": 0.0,
      "loss": 1.2127,
      "step": 600
    },
    {
      "epoch": 0.3917727717923604,
      "eval_loss": 1.2015607357025146,
      "eval_runtime": 42.3181,
      "eval_samples_per_second": 60.943,
      "eval_steps_per_second": 15.242,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 9.759171124867891e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}