{
  "best_metric": 0.5911697745323181,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.6872852233676976,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003436426116838488,
      "eval_loss": 1.1602751016616821,
      "eval_runtime": 52.2233,
      "eval_samples_per_second": 9.383,
      "eval_steps_per_second": 2.355,
      "step": 1
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 1.157630205154419,
      "learning_rate": 3e-05,
      "loss": 2.4315,
      "step": 3
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 1.1563230752944946,
      "learning_rate": 6e-05,
      "loss": 3.724,
      "step": 6
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 0.9945737719535828,
      "learning_rate": 9e-05,
      "loss": 3.2789,
      "step": 9
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 1.7225005626678467,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.1255,
      "step": 12
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 1.2585349082946777,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.7899,
      "step": 15
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 0.8328224420547485,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.4667,
      "step": 18
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": 0.7277198433876038,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.5859,
      "step": 21
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.8099870085716248,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.6703,
      "step": 24
    },
    {
      "epoch": 0.09278350515463918,
      "grad_norm": 0.833128809928894,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.5984,
      "step": 27
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.9102660417556763,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.8384,
      "step": 30
    },
    {
      "epoch": 0.1134020618556701,
      "grad_norm": 0.9439516663551331,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.6385,
      "step": 33
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 1.1036616563796997,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.6881,
      "step": 36
    },
    {
      "epoch": 0.13402061855670103,
      "grad_norm": 1.217441201210022,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.5668,
      "step": 39
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 1.4947435855865479,
      "learning_rate": 9.316282404787871e-05,
      "loss": 3.2285,
      "step": 42
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 1.4794517755508423,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.0778,
      "step": 45
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 1.708467960357666,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.162,
      "step": 48
    },
    {
      "epoch": 0.1718213058419244,
      "eval_loss": 0.6368284821510315,
      "eval_runtime": 52.7352,
      "eval_samples_per_second": 9.292,
      "eval_steps_per_second": 2.332,
      "step": 50
    },
    {
      "epoch": 0.17525773195876287,
      "grad_norm": 0.49676239490509033,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.5583,
      "step": 51
    },
    {
      "epoch": 0.18556701030927836,
      "grad_norm": 0.6859402060508728,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.0706,
      "step": 54
    },
    {
      "epoch": 0.1958762886597938,
      "grad_norm": 0.522407054901123,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.8504,
      "step": 57
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.555097222328186,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.2681,
      "step": 60
    },
    {
      "epoch": 0.21649484536082475,
      "grad_norm": 0.573678731918335,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.2236,
      "step": 63
    },
    {
      "epoch": 0.2268041237113402,
      "grad_norm": 0.6186810731887817,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.2479,
      "step": 66
    },
    {
      "epoch": 0.23711340206185566,
      "grad_norm": 0.6820915341377258,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.3026,
      "step": 69
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.7188693284988403,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.2076,
      "step": 72
    },
    {
      "epoch": 0.25773195876288657,
      "grad_norm": 0.7415844202041626,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.3402,
      "step": 75
    },
    {
      "epoch": 0.26804123711340205,
      "grad_norm": 0.8060118556022644,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.3019,
      "step": 78
    },
    {
      "epoch": 0.27835051546391754,
      "grad_norm": 0.9178985953330994,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.6248,
      "step": 81
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 1.008913516998291,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.5083,
      "step": 84
    },
    {
      "epoch": 0.29896907216494845,
      "grad_norm": 1.0129549503326416,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.6237,
      "step": 87
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 1.1528254747390747,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.5261,
      "step": 90
    },
    {
      "epoch": 0.31958762886597936,
      "grad_norm": 1.2210513353347778,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.6408,
      "step": 93
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 1.4976028203964233,
      "learning_rate": 5.74131823855921e-05,
      "loss": 3.2657,
      "step": 96
    },
    {
      "epoch": 0.3402061855670103,
      "grad_norm": 1.8296886682510376,
      "learning_rate": 5.495227651252315e-05,
      "loss": 3.2903,
      "step": 99
    },
    {
      "epoch": 0.3436426116838488,
      "eval_loss": 0.6118174195289612,
      "eval_runtime": 52.7131,
      "eval_samples_per_second": 9.296,
      "eval_steps_per_second": 2.333,
      "step": 100
    },
    {
      "epoch": 0.35051546391752575,
      "grad_norm": 0.5407726764678955,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.8648,
      "step": 102
    },
    {
      "epoch": 0.36082474226804123,
      "grad_norm": 0.6459923386573792,
      "learning_rate": 5e-05,
      "loss": 2.4117,
      "step": 105
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 0.5058222413063049,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.2827,
      "step": 108
    },
    {
      "epoch": 0.38144329896907214,
      "grad_norm": 0.5394899249076843,
      "learning_rate": 4.504772348747687e-05,
      "loss": 2.1984,
      "step": 111
    },
    {
      "epoch": 0.3917525773195876,
      "grad_norm": 0.612091064453125,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 2.1348,
      "step": 114
    },
    {
      "epoch": 0.4020618556701031,
      "grad_norm": 0.6512736082077026,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 2.2831,
      "step": 117
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 0.6908525228500366,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.4022,
      "step": 120
    },
    {
      "epoch": 0.422680412371134,
      "grad_norm": 0.7587947845458984,
      "learning_rate": 3.533749813077677e-05,
      "loss": 2.3596,
      "step": 123
    },
    {
      "epoch": 0.4329896907216495,
      "grad_norm": 0.7948947548866272,
      "learning_rate": 3.298534127791785e-05,
      "loss": 2.3741,
      "step": 126
    },
    {
      "epoch": 0.44329896907216493,
      "grad_norm": 0.9440019726753235,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 2.5018,
      "step": 129
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 0.90851229429245,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.3247,
      "step": 132
    },
    {
      "epoch": 0.4639175257731959,
      "grad_norm": 1.0596612691879272,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.6448,
      "step": 135
    },
    {
      "epoch": 0.4742268041237113,
      "grad_norm": 1.383385181427002,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.8457,
      "step": 138
    },
    {
      "epoch": 0.4845360824742268,
      "grad_norm": 1.2124711275100708,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.7673,
      "step": 141
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 1.4068825244903564,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.7296,
      "step": 144
    },
    {
      "epoch": 0.5051546391752577,
      "grad_norm": 1.5321927070617676,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.9848,
      "step": 147
    },
    {
      "epoch": 0.5154639175257731,
      "grad_norm": 2.3313181400299072,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.5282,
      "step": 150
    },
    {
      "epoch": 0.5154639175257731,
      "eval_loss": 0.5927267074584961,
      "eval_runtime": 53.1413,
      "eval_samples_per_second": 9.221,
      "eval_steps_per_second": 2.315,
      "step": 150
    },
    {
      "epoch": 0.5257731958762887,
      "grad_norm": 0.4825039803981781,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.2003,
      "step": 153
    },
    {
      "epoch": 0.5360824742268041,
      "grad_norm": 0.5744404196739197,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 2.461,
      "step": 156
    },
    {
      "epoch": 0.5463917525773195,
      "grad_norm": 0.6095325350761414,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 2.5401,
      "step": 159
    },
    {
      "epoch": 0.5567010309278351,
      "grad_norm": 0.6706549525260925,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.2518,
      "step": 162
    },
    {
      "epoch": 0.5670103092783505,
      "grad_norm": 0.6379284262657166,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.214,
      "step": 165
    },
    {
      "epoch": 0.5773195876288659,
      "grad_norm": 0.7004604339599609,
      "learning_rate": 6.837175952121306e-06,
      "loss": 2.2514,
      "step": 168
    },
    {
      "epoch": 0.5876288659793815,
      "grad_norm": 0.6915513873100281,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 2.4767,
      "step": 171
    },
    {
      "epoch": 0.5979381443298969,
      "grad_norm": 0.7965708374977112,
      "learning_rate": 4.549673247541875e-06,
      "loss": 2.3281,
      "step": 174
    },
    {
      "epoch": 0.6082474226804123,
      "grad_norm": 0.8681992292404175,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 2.399,
      "step": 177
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 0.9099557995796204,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.2624,
      "step": 180
    },
    {
      "epoch": 0.6288659793814433,
      "grad_norm": 0.971269965171814,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.4042,
      "step": 183
    },
    {
      "epoch": 0.6391752577319587,
      "grad_norm": 1.0734204053878784,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.2968,
      "step": 186
    },
    {
      "epoch": 0.6494845360824743,
      "grad_norm": 1.0781867504119873,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.4744,
      "step": 189
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 1.2936267852783203,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.7197,
      "step": 192
    },
    {
      "epoch": 0.6701030927835051,
      "grad_norm": 1.4144686460494995,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.801,
      "step": 195
    },
    {
      "epoch": 0.6804123711340206,
      "grad_norm": 1.5016579627990723,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 3.0585,
      "step": 198
    },
    {
      "epoch": 0.6872852233676976,
      "eval_loss": 0.5911697745323181,
      "eval_runtime": 52.716,
      "eval_samples_per_second": 9.295,
      "eval_steps_per_second": 2.333,
      "step": 200
    }
  ],
  "logging_steps": 3,
  "max_steps": 200,
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6702813296130458e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}