{
  "best_metric": 0.0015228495467454195,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06685609226140732,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013371218452281465,
      "grad_norm": 1.1056793928146362,
      "learning_rate": 5e-05,
      "loss": 0.2763,
      "step": 1
    },
    {
      "epoch": 0.0013371218452281465,
      "eval_loss": 1.0053369998931885,
      "eval_runtime": 102.5788,
      "eval_samples_per_second": 49.113,
      "eval_steps_per_second": 6.142,
      "step": 1
    },
    {
      "epoch": 0.002674243690456293,
      "grad_norm": 1.2596580982208252,
      "learning_rate": 0.0001,
      "loss": 0.3303,
      "step": 2
    },
    {
      "epoch": 0.004011365535684439,
      "grad_norm": 1.2573037147521973,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.3415,
      "step": 3
    },
    {
      "epoch": 0.005348487380912586,
      "grad_norm": 0.8383220434188843,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.2071,
      "step": 4
    },
    {
      "epoch": 0.006685609226140732,
      "grad_norm": 0.8991056680679321,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1315,
      "step": 5
    },
    {
      "epoch": 0.008022731071368878,
      "grad_norm": 0.4017704725265503,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0852,
      "step": 6
    },
    {
      "epoch": 0.009359852916597024,
      "grad_norm": 1.087311029434204,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0858,
      "step": 7
    },
    {
      "epoch": 0.010696974761825172,
      "grad_norm": 0.6217412948608398,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0506,
      "step": 8
    },
    {
      "epoch": 0.012034096607053318,
      "grad_norm": 0.3295789957046509,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0448,
      "step": 9
    },
    {
      "epoch": 0.013371218452281465,
      "grad_norm": 0.7376157641410828,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0421,
      "step": 10
    },
    {
      "epoch": 0.014708340297509611,
      "grad_norm": 0.31833508610725403,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0229,
      "step": 11
    },
    {
      "epoch": 0.016045462142737756,
      "grad_norm": 0.20964288711547852,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0088,
      "step": 12
    },
    {
      "epoch": 0.017382583987965904,
      "grad_norm": 0.3452492356300354,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0259,
      "step": 13
    },
    {
      "epoch": 0.018719705833194048,
      "grad_norm": 0.25383225083351135,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0198,
      "step": 14
    },
    {
      "epoch": 0.020056827678422196,
      "grad_norm": 0.23373889923095703,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0114,
      "step": 15
    },
    {
      "epoch": 0.021393949523650344,
      "grad_norm": 0.17382249236106873,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.003,
      "step": 16
    },
    {
      "epoch": 0.02273107136887849,
      "grad_norm": 0.10434332489967346,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0052,
      "step": 17
    },
    {
      "epoch": 0.024068193214106637,
      "grad_norm": 0.050614554435014725,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0018,
      "step": 18
    },
    {
      "epoch": 0.02540531505933478,
      "grad_norm": 0.1752793937921524,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0024,
      "step": 19
    },
    {
      "epoch": 0.02674243690456293,
      "grad_norm": 0.0631827861070633,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0017,
      "step": 20
    },
    {
      "epoch": 0.028079558749791074,
      "grad_norm": 0.044013332575559616,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0013,
      "step": 21
    },
    {
      "epoch": 0.029416680595019222,
      "grad_norm": 0.24050629138946533,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0045,
      "step": 22
    },
    {
      "epoch": 0.030753802440247367,
      "grad_norm": 0.054780010133981705,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0008,
      "step": 23
    },
    {
      "epoch": 0.03209092428547551,
      "grad_norm": 0.06880411505699158,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0017,
      "step": 24
    },
    {
      "epoch": 0.03342804613070366,
      "grad_norm": 0.30958375334739685,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0058,
      "step": 25
    },
    {
      "epoch": 0.03342804613070366,
      "eval_loss": 0.0024255544412881136,
      "eval_runtime": 102.7012,
      "eval_samples_per_second": 49.055,
      "eval_steps_per_second": 6.134,
      "step": 25
    },
    {
      "epoch": 0.03476516797593181,
      "grad_norm": 0.10596287250518799,
      "learning_rate": 5e-05,
      "loss": 0.0042,
      "step": 26
    },
    {
      "epoch": 0.036102289821159955,
      "grad_norm": 0.05240289866924286,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0029,
      "step": 27
    },
    {
      "epoch": 0.037439411666388096,
      "grad_norm": 0.04171014577150345,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0006,
      "step": 28
    },
    {
      "epoch": 0.038776533511616244,
      "grad_norm": 0.019574448466300964,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0013,
      "step": 29
    },
    {
      "epoch": 0.04011365535684439,
      "grad_norm": 0.03698131442070007,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.001,
      "step": 30
    },
    {
      "epoch": 0.04145077720207254,
      "grad_norm": 0.10602346807718277,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0017,
      "step": 31
    },
    {
      "epoch": 0.04278789904730069,
      "grad_norm": 0.049237657338380814,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0009,
      "step": 32
    },
    {
      "epoch": 0.04412502089252883,
      "grad_norm": 0.020352071151137352,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0004,
      "step": 33
    },
    {
      "epoch": 0.04546214273775698,
      "grad_norm": 0.02474248968064785,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0005,
      "step": 34
    },
    {
      "epoch": 0.046799264582985126,
      "grad_norm": 0.20188511908054352,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0029,
      "step": 35
    },
    {
      "epoch": 0.048136386428213274,
      "grad_norm": 0.01786266639828682,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0002,
      "step": 36
    },
    {
      "epoch": 0.049473508273441415,
      "grad_norm": 0.06426721066236496,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0015,
      "step": 37
    },
    {
      "epoch": 0.05081063011866956,
      "grad_norm": 0.0700186938047409,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0039,
      "step": 38
    },
    {
      "epoch": 0.05214775196389771,
      "grad_norm": 0.06131847947835922,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0025,
      "step": 39
    },
    {
      "epoch": 0.05348487380912586,
      "grad_norm": 0.021232590079307556,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0006,
      "step": 40
    },
    {
      "epoch": 0.054821995654354,
      "grad_norm": 0.03514159843325615,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0013,
      "step": 41
    },
    {
      "epoch": 0.05615911749958215,
      "grad_norm": 0.040575020015239716,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.001,
      "step": 42
    },
    {
      "epoch": 0.057496239344810296,
      "grad_norm": 0.029789714142680168,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0011,
      "step": 43
    },
    {
      "epoch": 0.058833361190038444,
      "grad_norm": 0.01341679971665144,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0002,
      "step": 44
    },
    {
      "epoch": 0.06017048303526659,
      "grad_norm": 0.023356175050139427,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0006,
      "step": 45
    },
    {
      "epoch": 0.06150760488049473,
      "grad_norm": 0.002739351475611329,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0001,
      "step": 46
    },
    {
      "epoch": 0.06284472672572289,
      "grad_norm": 0.007518163416534662,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0002,
      "step": 47
    },
    {
      "epoch": 0.06418184857095102,
      "grad_norm": 0.11280187219381332,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0007,
      "step": 48
    },
    {
      "epoch": 0.06551897041617917,
      "grad_norm": 0.1114940270781517,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0036,
      "step": 49
    },
    {
      "epoch": 0.06685609226140732,
      "grad_norm": 0.07846508920192719,
      "learning_rate": 0.0,
      "loss": 0.0012,
      "step": 50
    },
    {
      "epoch": 0.06685609226140732,
      "eval_loss": 0.0015228495467454195,
      "eval_runtime": 102.6882,
      "eval_samples_per_second": 49.061,
      "eval_steps_per_second": 6.135,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.62480894509056e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}