{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.1423487544483986,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011387900355871887,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000001e-07,
      "loss": 16.0597,
      "step": 1
    },
    {
      "epoch": 0.011387900355871887,
      "eval_loss": NaN,
      "eval_runtime": 41.5977,
      "eval_samples_per_second": 14.232,
      "eval_steps_per_second": 1.779,
      "step": 1
    },
    {
      "epoch": 0.022775800711743774,
      "grad_norm": NaN,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.03416370106761566,
      "grad_norm": NaN,
      "learning_rate": 1.5e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.04555160142348755,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.05693950177935943,
      "grad_norm": NaN,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.06832740213523132,
      "grad_norm": NaN,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0797153024911032,
      "grad_norm": NaN,
      "learning_rate": 3.5e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0911032028469751,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.10249110320284698,
      "grad_norm": NaN,
      "learning_rate": 4.5e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.11387900355871886,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.12526690391459075,
      "grad_norm": NaN,
      "learning_rate": 4.99847706754774e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.13665480427046264,
      "grad_norm": NaN,
      "learning_rate": 4.993910125649561e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.1480427046263345,
      "grad_norm": NaN,
      "learning_rate": 4.986304738420684e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.1594306049822064,
      "grad_norm": NaN,
      "learning_rate": 4.975670171853926e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.1708185053380783,
      "grad_norm": NaN,
      "learning_rate": 4.962019382530521e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.1822064056939502,
      "grad_norm": NaN,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.19359430604982206,
      "grad_norm": NaN,
      "learning_rate": 4.925739315689991e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.20498220640569395,
      "grad_norm": NaN,
      "learning_rate": 4.903154239845798e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.21637010676156584,
      "grad_norm": NaN,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.2277580071174377,
      "grad_norm": NaN,
      "learning_rate": 4.849231551964771e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.2391459074733096,
      "grad_norm": NaN,
      "learning_rate": 4.817959636416969e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.2505338078291815,
      "grad_norm": NaN,
      "learning_rate": 4.783863644106502e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.2619217081850534,
      "grad_norm": NaN,
      "learning_rate": 4.746985115747918e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.2733096085409253,
      "grad_norm": NaN,
      "learning_rate": 4.707368982147318e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.2846975088967972,
      "grad_norm": NaN,
      "learning_rate": 4.665063509461098e-06,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.296085409252669,
      "grad_norm": NaN,
      "learning_rate": 4.620120240391065e-06,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.3074733096085409,
      "grad_norm": NaN,
      "learning_rate": 4.572593931387604e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.3188612099644128,
      "grad_norm": NaN,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.3302491103202847,
      "grad_norm": NaN,
      "learning_rate": 4.470026884016805e-06,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.3416370106761566,
      "grad_norm": NaN,
      "learning_rate": 4.415111107797445e-06,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.3530249110320285,
      "grad_norm": NaN,
      "learning_rate": 4.357862063693486e-06,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.3644128113879004,
      "grad_norm": NaN,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.3758007117437722,
      "grad_norm": NaN,
      "learning_rate": 4.236645926147493e-06,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.3871886120996441,
      "grad_norm": NaN,
      "learning_rate": 4.172826515897146e-06,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.398576512455516,
      "grad_norm": NaN,
      "learning_rate": 4.106969024216348e-06,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.4099644128113879,
      "grad_norm": NaN,
      "learning_rate": 4.039153688314146e-06,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.4213523131672598,
      "grad_norm": NaN,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.4327402135231317,
      "grad_norm": NaN,
      "learning_rate": 3.897982258676867e-06,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.4441281138790036,
      "grad_norm": NaN,
      "learning_rate": 3.824798160583012e-06,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.4555160142348754,
      "grad_norm": NaN,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.4669039145907473,
      "grad_norm": NaN,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.4782918149466192,
      "grad_norm": NaN,
      "learning_rate": 3.595927866972694e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.4896797153024911,
      "grad_norm": NaN,
      "learning_rate": 3.516841607689501e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.501067615658363,
      "grad_norm": NaN,
      "learning_rate": 3.436516483539781e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.5124555160142349,
      "grad_norm": NaN,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.5238434163701068,
      "grad_norm": NaN,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.5352313167259787,
      "grad_norm": NaN,
      "learning_rate": 3.189093389542498e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.5466192170818506,
      "grad_norm": NaN,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.5580071174377225,
      "grad_norm": NaN,
      "learning_rate": 3.019779227044398e-06,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.5693950177935944,
      "grad_norm": NaN,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.5693950177935944,
      "eval_loss": NaN,
      "eval_runtime": 42.4689,
      "eval_samples_per_second": 13.94,
      "eval_steps_per_second": 1.742,
      "step": 50
    },
    {
      "epoch": 0.5807829181494661,
      "grad_norm": NaN,
      "learning_rate": 2.847932752400164e-06,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.592170818505338,
      "grad_norm": NaN,
      "learning_rate": 2.761321158169134e-06,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.6035587188612099,
      "grad_norm": NaN,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.6149466192170818,
      "grad_norm": NaN,
      "learning_rate": 2.587248741756253e-06,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.6263345195729537,
      "grad_norm": NaN,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.6377224199288256,
      "grad_norm": NaN,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.6491103202846975,
      "grad_norm": NaN,
      "learning_rate": 2.325608815639687e-06,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.6604982206405694,
      "grad_norm": NaN,
      "learning_rate": 2.238678841830867e-06,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.6718861209964413,
      "grad_norm": NaN,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.6832740213523132,
      "grad_norm": NaN,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.6946619217081851,
      "grad_norm": NaN,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.706049822064057,
      "grad_norm": NaN,
      "learning_rate": 1.895195261000831e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.7174377224199289,
      "grad_norm": NaN,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.7288256227758008,
      "grad_norm": NaN,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.7402135231316725,
      "grad_norm": NaN,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.7516014234875444,
      "grad_norm": NaN,
      "learning_rate": 1.56348351646022e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.7629893238434163,
      "grad_norm": NaN,
      "learning_rate": 1.4831583923105e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.7743772241992882,
      "grad_norm": NaN,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.7857651245551601,
      "grad_norm": NaN,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.797153024911032,
      "grad_norm": NaN,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.8085409252669039,
      "grad_norm": NaN,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.8199288256227758,
      "grad_norm": NaN,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.8313167259786477,
      "grad_norm": NaN,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.8427046263345196,
      "grad_norm": NaN,
      "learning_rate": 9.608463116858544e-07,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.8540925266903915,
      "grad_norm": NaN,
      "learning_rate": 8.930309757836517e-07,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.8654804270462634,
      "grad_norm": NaN,
      "learning_rate": 8.271734841028553e-07,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.8768683274021353,
      "grad_norm": NaN,
      "learning_rate": 7.633540738525066e-07,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.8882562277580072,
      "grad_norm": NaN,
      "learning_rate": 7.016504991533727e-07,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.899644128113879,
      "grad_norm": NaN,
      "learning_rate": 6.421379363065142e-07,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.9110320284697508,
      "grad_norm": NaN,
      "learning_rate": 5.848888922025553e-07,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.9224199288256227,
      "grad_norm": NaN,
      "learning_rate": 5.299731159831953e-07,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.9338078291814946,
      "grad_norm": NaN,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.9451957295373665,
      "grad_norm": NaN,
      "learning_rate": 4.27406068612396e-07,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.9565836298932384,
      "grad_norm": NaN,
      "learning_rate": 3.798797596089351e-07,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.9679715302491103,
      "grad_norm": NaN,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.9793594306049822,
      "grad_norm": NaN,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.9907473309608541,
      "grad_norm": NaN,
      "learning_rate": 2.53014884252083e-07,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 1.0056939501779358,
      "grad_norm": NaN,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 1.0170818505338077,
      "grad_norm": NaN,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 1.0284697508896796,
      "grad_norm": NaN,
      "learning_rate": 1.507684480352292e-07,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 1.0398576512455515,
      "grad_norm": NaN,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 1.0512455516014234,
      "grad_norm": NaN,
      "learning_rate": 9.684576015420277e-08,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 1.0626334519572953,
      "grad_norm": NaN,
      "learning_rate": 7.426068431000883e-08,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 1.0740213523131672,
      "grad_norm": NaN,
      "learning_rate": 5.463099816548578e-08,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 1.085409252669039,
      "grad_norm": NaN,
      "learning_rate": 3.798061746947995e-08,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 1.096797153024911,
      "grad_norm": NaN,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 1.1081850533807829,
      "grad_norm": NaN,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 1.1195729537366548,
      "grad_norm": NaN,
      "learning_rate": 6.089874350439507e-09,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 1.1309608540925267,
      "grad_norm": NaN,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 1.1423487544483986,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 1.1423487544483986,
      "eval_loss": NaN,
      "eval_runtime": 41.9113,
      "eval_samples_per_second": 14.125,
      "eval_steps_per_second": 1.766,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.79503076767957e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}