{
  "best_metric": 0.25296375155448914,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.013832693571255663,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013832693571255662,
      "grad_norm": 0.5414836406707764,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 0.2862,
      "step": 1
    },
    {
      "epoch": 0.00013832693571255662,
      "eval_loss": 0.32557761669158936,
      "eval_runtime": 864.4397,
      "eval_samples_per_second": 14.085,
      "eval_steps_per_second": 1.761,
      "step": 1
    },
    {
      "epoch": 0.00027665387142511324,
      "grad_norm": 0.5004603266716003,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.3187,
      "step": 2
    },
    {
      "epoch": 0.00041498080713766987,
      "grad_norm": 0.6289068460464478,
      "learning_rate": 4.5e-07,
      "loss": 0.3039,
      "step": 3
    },
    {
      "epoch": 0.0005533077428502265,
      "grad_norm": 0.5262965559959412,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.3065,
      "step": 4
    },
    {
      "epoch": 0.0006916346785627831,
      "grad_norm": 0.6534644365310669,
      "learning_rate": 7.5e-07,
      "loss": 0.3509,
      "step": 5
    },
    {
      "epoch": 0.0008299616142753397,
      "grad_norm": 0.7118496894836426,
      "learning_rate": 9e-07,
      "loss": 0.3991,
      "step": 6
    },
    {
      "epoch": 0.0009682885499878964,
      "grad_norm": 0.4656999707221985,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 0.2937,
      "step": 7
    },
    {
      "epoch": 0.001106615485700453,
      "grad_norm": 0.451833575963974,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.2822,
      "step": 8
    },
    {
      "epoch": 0.0012449424214130097,
      "grad_norm": 0.5716612935066223,
      "learning_rate": 1.35e-06,
      "loss": 0.3687,
      "step": 9
    },
    {
      "epoch": 0.0013832693571255662,
      "grad_norm": 0.5744236707687378,
      "learning_rate": 1.5e-06,
      "loss": 0.3069,
      "step": 10
    },
    {
      "epoch": 0.001521596292838123,
      "grad_norm": 0.6165915727615356,
      "learning_rate": 1.65e-06,
      "loss": 0.4473,
      "step": 11
    },
    {
      "epoch": 0.0016599232285506795,
      "grad_norm": 0.5897412300109863,
      "learning_rate": 1.8e-06,
      "loss": 0.304,
      "step": 12
    },
    {
      "epoch": 0.0017982501642632362,
      "grad_norm": 0.5174123048782349,
      "learning_rate": 1.95e-06,
      "loss": 0.3018,
      "step": 13
    },
    {
      "epoch": 0.0019365770999757927,
      "grad_norm": 0.5476775765419006,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.411,
      "step": 14
    },
    {
      "epoch": 0.0020749040356883492,
      "grad_norm": 0.5217826962471008,
      "learning_rate": 2.25e-06,
      "loss": 0.2919,
      "step": 15
    },
    {
      "epoch": 0.002213230971400906,
      "grad_norm": 0.450664758682251,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.292,
      "step": 16
    },
    {
      "epoch": 0.0023515579071134627,
      "grad_norm": 0.47869348526000977,
      "learning_rate": 2.55e-06,
      "loss": 0.3593,
      "step": 17
    },
    {
      "epoch": 0.0024898848428260194,
      "grad_norm": 0.5078862905502319,
      "learning_rate": 2.7e-06,
      "loss": 0.3426,
      "step": 18
    },
    {
      "epoch": 0.0026282117785385757,
      "grad_norm": 0.5059868693351746,
      "learning_rate": 2.8500000000000002e-06,
      "loss": 0.302,
      "step": 19
    },
    {
      "epoch": 0.0027665387142511324,
      "grad_norm": 0.38030219078063965,
      "learning_rate": 3e-06,
      "loss": 0.2697,
      "step": 20
    },
    {
      "epoch": 0.002904865649963689,
      "grad_norm": 0.5299117565155029,
      "learning_rate": 3.15e-06,
      "loss": 0.309,
      "step": 21
    },
    {
      "epoch": 0.003043192585676246,
      "grad_norm": 0.4995821416378021,
      "learning_rate": 3.3e-06,
      "loss": 0.3418,
      "step": 22
    },
    {
      "epoch": 0.0031815195213888026,
      "grad_norm": 0.4045211970806122,
      "learning_rate": 3.4500000000000004e-06,
      "loss": 0.3161,
      "step": 23
    },
    {
      "epoch": 0.003319846457101359,
      "grad_norm": 0.4190620183944702,
      "learning_rate": 3.6e-06,
      "loss": 0.3402,
      "step": 24
    },
    {
      "epoch": 0.0034581733928139157,
      "grad_norm": 0.40234580636024475,
      "learning_rate": 3.75e-06,
      "loss": 0.3907,
      "step": 25
    },
    {
      "epoch": 0.0035965003285264724,
      "grad_norm": 0.4151726961135864,
      "learning_rate": 3.9e-06,
      "loss": 0.3512,
      "step": 26
    },
    {
      "epoch": 0.003734827264239029,
      "grad_norm": 0.4049225449562073,
      "learning_rate": 4.05e-06,
      "loss": 0.316,
      "step": 27
    },
    {
      "epoch": 0.0038731541999515854,
      "grad_norm": 0.4368723928928375,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.2541,
      "step": 28
    },
    {
      "epoch": 0.004011481135664142,
      "grad_norm": 0.44128212332725525,
      "learning_rate": 4.35e-06,
      "loss": 0.3171,
      "step": 29
    },
    {
      "epoch": 0.0041498080713766984,
      "grad_norm": 0.32956743240356445,
      "learning_rate": 4.5e-06,
      "loss": 0.3075,
      "step": 30
    },
    {
      "epoch": 0.004288135007089256,
      "grad_norm": 0.3135199248790741,
      "learning_rate": 4.65e-06,
      "loss": 0.3135,
      "step": 31
    },
    {
      "epoch": 0.004426461942801812,
      "grad_norm": 0.263225793838501,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.2816,
      "step": 32
    },
    {
      "epoch": 0.004564788878514369,
      "grad_norm": 0.2696998417377472,
      "learning_rate": 4.95e-06,
      "loss": 0.2978,
      "step": 33
    },
    {
      "epoch": 0.004703115814226925,
      "grad_norm": 0.22326156497001648,
      "learning_rate": 5.1e-06,
      "loss": 0.2716,
      "step": 34
    },
    {
      "epoch": 0.004841442749939482,
      "grad_norm": 0.2183511108160019,
      "learning_rate": 5.25e-06,
      "loss": 0.267,
      "step": 35
    },
    {
      "epoch": 0.004979769685652039,
      "grad_norm": 0.23443461954593658,
      "learning_rate": 5.4e-06,
      "loss": 0.306,
      "step": 36
    },
    {
      "epoch": 0.005118096621364595,
      "grad_norm": 0.2592571973800659,
      "learning_rate": 5.55e-06,
      "loss": 0.3548,
      "step": 37
    },
    {
      "epoch": 0.005256423557077151,
      "grad_norm": 0.2267267256975174,
      "learning_rate": 5.7000000000000005e-06,
      "loss": 0.3722,
      "step": 38
    },
    {
      "epoch": 0.005394750492789709,
      "grad_norm": 0.20199447870254517,
      "learning_rate": 5.850000000000001e-06,
      "loss": 0.2761,
      "step": 39
    },
    {
      "epoch": 0.005533077428502265,
      "grad_norm": 0.20377960801124573,
      "learning_rate": 6e-06,
      "loss": 0.2585,
      "step": 40
    },
    {
      "epoch": 0.005671404364214822,
      "grad_norm": 0.19677956402301788,
      "learning_rate": 6.1499999999999996e-06,
      "loss": 0.3644,
      "step": 41
    },
    {
      "epoch": 0.005809731299927378,
      "grad_norm": 0.18353554606437683,
      "learning_rate": 6.3e-06,
      "loss": 0.3253,
      "step": 42
    },
    {
      "epoch": 0.005948058235639935,
      "grad_norm": 0.18772590160369873,
      "learning_rate": 6.45e-06,
      "loss": 0.2842,
      "step": 43
    },
    {
      "epoch": 0.006086385171352492,
      "grad_norm": 0.18426308035850525,
      "learning_rate": 6.6e-06,
      "loss": 0.3357,
      "step": 44
    },
    {
      "epoch": 0.006224712107065048,
      "grad_norm": 0.18350034952163696,
      "learning_rate": 6.750000000000001e-06,
      "loss": 0.2412,
      "step": 45
    },
    {
      "epoch": 0.006363039042777605,
      "grad_norm": 0.18429340422153473,
      "learning_rate": 6.900000000000001e-06,
      "loss": 0.2598,
      "step": 46
    },
    {
      "epoch": 0.0065013659784901616,
      "grad_norm": 0.16520313918590546,
      "learning_rate": 7.049999999999999e-06,
      "loss": 0.2797,
      "step": 47
    },
    {
      "epoch": 0.006639692914202718,
      "grad_norm": 0.1929628700017929,
      "learning_rate": 7.2e-06,
      "loss": 0.3005,
      "step": 48
    },
    {
      "epoch": 0.006778019849915275,
      "grad_norm": 0.1845887005329132,
      "learning_rate": 7.35e-06,
      "loss": 0.2614,
      "step": 49
    },
    {
      "epoch": 0.006916346785627831,
      "grad_norm": 0.1492261290550232,
      "learning_rate": 7.5e-06,
      "loss": 0.2698,
      "step": 50
    },
    {
      "epoch": 0.006916346785627831,
      "eval_loss": 0.2843204140663147,
      "eval_runtime": 886.4909,
      "eval_samples_per_second": 13.735,
      "eval_steps_per_second": 1.717,
      "step": 50
    },
    {
      "epoch": 0.007054673721340388,
      "grad_norm": 0.17172540724277496,
      "learning_rate": 7.65e-06,
      "loss": 0.2737,
      "step": 51
    },
    {
      "epoch": 0.007193000657052945,
      "grad_norm": 0.18842163681983948,
      "learning_rate": 7.8e-06,
      "loss": 0.2943,
      "step": 52
    },
    {
      "epoch": 0.007331327592765501,
      "grad_norm": 0.18067596852779388,
      "learning_rate": 7.95e-06,
      "loss": 0.308,
      "step": 53
    },
    {
      "epoch": 0.007469654528478058,
      "grad_norm": 0.16696469485759735,
      "learning_rate": 8.1e-06,
      "loss": 0.2641,
      "step": 54
    },
    {
      "epoch": 0.0076079814641906145,
      "grad_norm": 0.15525111556053162,
      "learning_rate": 8.25e-06,
      "loss": 0.2417,
      "step": 55
    },
    {
      "epoch": 0.007746308399903171,
      "grad_norm": 0.17325535416603088,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.3275,
      "step": 56
    },
    {
      "epoch": 0.007884635335615727,
      "grad_norm": 0.1737009733915329,
      "learning_rate": 8.55e-06,
      "loss": 0.3544,
      "step": 57
    },
    {
      "epoch": 0.008022962271328284,
      "grad_norm": 0.16440212726593018,
      "learning_rate": 8.7e-06,
      "loss": 0.3049,
      "step": 58
    },
    {
      "epoch": 0.008161289207040841,
      "grad_norm": 0.15149055421352386,
      "learning_rate": 8.85e-06,
      "loss": 0.2669,
      "step": 59
    },
    {
      "epoch": 0.008299616142753397,
      "grad_norm": 0.15021531283855438,
      "learning_rate": 9e-06,
      "loss": 0.2852,
      "step": 60
    },
    {
      "epoch": 0.008437943078465954,
      "grad_norm": 0.14351071417331696,
      "learning_rate": 9.15e-06,
      "loss": 0.2018,
      "step": 61
    },
    {
      "epoch": 0.008576270014178511,
      "grad_norm": 0.12986423075199127,
      "learning_rate": 9.3e-06,
      "loss": 0.2416,
      "step": 62
    },
    {
      "epoch": 0.008714596949891068,
      "grad_norm": 0.1482655256986618,
      "learning_rate": 9.450000000000001e-06,
      "loss": 0.2492,
      "step": 63
    },
    {
      "epoch": 0.008852923885603624,
      "grad_norm": 0.14514705538749695,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.2925,
      "step": 64
    },
    {
      "epoch": 0.008991250821316181,
      "grad_norm": 0.15891727805137634,
      "learning_rate": 9.75e-06,
      "loss": 0.234,
      "step": 65
    },
    {
      "epoch": 0.009129577757028738,
      "grad_norm": 0.12783700227737427,
      "learning_rate": 9.9e-06,
      "loss": 0.2144,
      "step": 66
    },
    {
      "epoch": 0.009267904692741294,
      "grad_norm": 0.11698262393474579,
      "learning_rate": 1.005e-05,
      "loss": 0.2107,
      "step": 67
    },
    {
      "epoch": 0.00940623162845385,
      "grad_norm": 0.14814496040344238,
      "learning_rate": 1.02e-05,
      "loss": 0.296,
      "step": 68
    },
    {
      "epoch": 0.009544558564166408,
      "grad_norm": 0.1301187127828598,
      "learning_rate": 1.035e-05,
      "loss": 0.1869,
      "step": 69
    },
    {
      "epoch": 0.009682885499878963,
      "grad_norm": 0.17036621272563934,
      "learning_rate": 1.05e-05,
      "loss": 0.3304,
      "step": 70
    },
    {
      "epoch": 0.00982121243559152,
      "grad_norm": 0.12910433113574982,
      "learning_rate": 1.065e-05,
      "loss": 0.2495,
      "step": 71
    },
    {
      "epoch": 0.009959539371304078,
      "grad_norm": 0.14236624538898468,
      "learning_rate": 1.08e-05,
      "loss": 0.2275,
      "step": 72
    },
    {
      "epoch": 0.010097866307016633,
      "grad_norm": 0.15861648321151733,
      "learning_rate": 1.095e-05,
      "loss": 0.3031,
      "step": 73
    },
    {
      "epoch": 0.01023619324272919,
      "grad_norm": 0.1290421336889267,
      "learning_rate": 1.11e-05,
      "loss": 0.2598,
      "step": 74
    },
    {
      "epoch": 0.010374520178441747,
      "grad_norm": 0.13748377561569214,
      "learning_rate": 1.125e-05,
      "loss": 0.2692,
      "step": 75
    },
    {
      "epoch": 0.010512847114154303,
      "grad_norm": 0.1323186159133911,
      "learning_rate": 1.1400000000000001e-05,
      "loss": 0.2333,
      "step": 76
    },
    {
      "epoch": 0.01065117404986686,
      "grad_norm": 0.14683866500854492,
      "learning_rate": 1.1550000000000001e-05,
      "loss": 0.2783,
      "step": 77
    },
    {
      "epoch": 0.010789500985579417,
      "grad_norm": 0.14012585580348969,
      "learning_rate": 1.1700000000000001e-05,
      "loss": 0.3069,
      "step": 78
    },
    {
      "epoch": 0.010927827921291974,
      "grad_norm": 0.14110729098320007,
      "learning_rate": 1.185e-05,
      "loss": 0.3,
      "step": 79
    },
    {
      "epoch": 0.01106615485700453,
      "grad_norm": 0.15559019148349762,
      "learning_rate": 1.2e-05,
      "loss": 0.3066,
      "step": 80
    },
    {
      "epoch": 0.011204481792717087,
      "grad_norm": 0.11998707801103592,
      "learning_rate": 1.215e-05,
      "loss": 0.2358,
      "step": 81
    },
    {
      "epoch": 0.011342808728429644,
      "grad_norm": 0.1280561089515686,
      "learning_rate": 1.2299999999999999e-05,
      "loss": 0.2721,
      "step": 82
    },
    {
      "epoch": 0.0114811356641422,
      "grad_norm": 0.14386573433876038,
      "learning_rate": 1.245e-05,
      "loss": 0.2976,
      "step": 83
    },
    {
      "epoch": 0.011619462599854757,
      "grad_norm": 0.1161927729845047,
      "learning_rate": 1.26e-05,
      "loss": 0.2059,
      "step": 84
    },
    {
      "epoch": 0.011757789535567314,
      "grad_norm": 0.1201709434390068,
      "learning_rate": 1.275e-05,
      "loss": 0.2446,
      "step": 85
    },
    {
      "epoch": 0.01189611647127987,
      "grad_norm": 0.1458764672279358,
      "learning_rate": 1.29e-05,
      "loss": 0.2376,
      "step": 86
    },
    {
      "epoch": 0.012034443406992426,
      "grad_norm": 0.13553838431835175,
      "learning_rate": 1.305e-05,
      "loss": 0.2875,
      "step": 87
    },
    {
      "epoch": 0.012172770342704984,
      "grad_norm": 0.13249175250530243,
      "learning_rate": 1.32e-05,
      "loss": 0.2974,
      "step": 88
    },
    {
      "epoch": 0.012311097278417539,
      "grad_norm": 0.15065519511699677,
      "learning_rate": 1.3350000000000001e-05,
      "loss": 0.2945,
      "step": 89
    },
    {
      "epoch": 0.012449424214130096,
      "grad_norm": 0.1529104858636856,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 0.2972,
      "step": 90
    },
    {
      "epoch": 0.012587751149842653,
      "grad_norm": 0.1217237114906311,
      "learning_rate": 1.3650000000000001e-05,
      "loss": 0.2322,
      "step": 91
    },
    {
      "epoch": 0.01272607808555521,
      "grad_norm": 0.13060763478279114,
      "learning_rate": 1.3800000000000002e-05,
      "loss": 0.2931,
      "step": 92
    },
    {
      "epoch": 0.012864405021267766,
      "grad_norm": 0.1278468370437622,
      "learning_rate": 1.395e-05,
      "loss": 0.245,
      "step": 93
    },
    {
      "epoch": 0.013002731956980323,
      "grad_norm": 0.11934634298086166,
      "learning_rate": 1.4099999999999999e-05,
      "loss": 0.2238,
      "step": 94
    },
    {
      "epoch": 0.01314105889269288,
      "grad_norm": 0.13119642436504364,
      "learning_rate": 1.4249999999999999e-05,
      "loss": 0.2394,
      "step": 95
    },
    {
      "epoch": 0.013279385828405436,
      "grad_norm": 0.13287314772605896,
      "learning_rate": 1.44e-05,
      "loss": 0.2134,
      "step": 96
    },
    {
      "epoch": 0.013417712764117993,
      "grad_norm": 0.13096174597740173,
      "learning_rate": 1.455e-05,
      "loss": 0.2449,
      "step": 97
    },
    {
      "epoch": 0.01355603969983055,
      "grad_norm": 0.1295308768749237,
      "learning_rate": 1.47e-05,
      "loss": 0.2517,
      "step": 98
    },
    {
      "epoch": 0.013694366635543105,
      "grad_norm": 0.1313454955816269,
      "learning_rate": 1.485e-05,
      "loss": 0.2596,
      "step": 99
    },
    {
      "epoch": 0.013832693571255663,
      "grad_norm": 0.12004859000444412,
      "learning_rate": 1.5e-05,
      "loss": 0.2258,
      "step": 100
    },
    {
      "epoch": 0.013832693571255663,
      "eval_loss": 0.25296375155448914,
      "eval_runtime": 873.1576,
      "eval_samples_per_second": 13.945,
      "eval_steps_per_second": 1.743,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 3.0372935956955136e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}