{
  "best_metric": 0.13660724461078644,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.1739130434782608,
  "eval_steps": 25,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07729468599033816,
      "grad_norm": 0.43662938475608826,
      "learning_rate": 5e-05,
      "loss": 0.4704,
      "step": 1
    },
    {
      "epoch": 0.07729468599033816,
      "eval_loss": 0.5291202068328857,
      "eval_runtime": 1.828,
      "eval_samples_per_second": 27.352,
      "eval_steps_per_second": 7.111,
      "step": 1
    },
    {
      "epoch": 0.15458937198067632,
      "grad_norm": 0.5451412200927734,
      "learning_rate": 0.0001,
      "loss": 0.5141,
      "step": 2
    },
    {
      "epoch": 0.2318840579710145,
      "grad_norm": 0.6303209066390991,
      "learning_rate": 9.983788698441369e-05,
      "loss": 0.614,
      "step": 3
    },
    {
      "epoch": 0.30917874396135264,
      "grad_norm": 0.33306458592414856,
      "learning_rate": 9.935271596564688e-05,
      "loss": 0.4303,
      "step": 4
    },
    {
      "epoch": 0.3864734299516908,
      "grad_norm": 0.3506397306919098,
      "learning_rate": 9.854798261200746e-05,
      "loss": 0.3543,
      "step": 5
    },
    {
      "epoch": 0.463768115942029,
      "grad_norm": 0.4276319146156311,
      "learning_rate": 9.74294850457488e-05,
      "loss": 0.3801,
      "step": 6
    },
    {
      "epoch": 0.5410628019323671,
      "grad_norm": 0.22507691383361816,
      "learning_rate": 9.600528206746612e-05,
      "loss": 0.2902,
      "step": 7
    },
    {
      "epoch": 0.6183574879227053,
      "grad_norm": 0.24348624050617218,
      "learning_rate": 9.428563509225347e-05,
      "loss": 0.2535,
      "step": 8
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.4209447205066681,
      "learning_rate": 9.22829342159729e-05,
      "loss": 0.2811,
      "step": 9
    },
    {
      "epoch": 0.7729468599033816,
      "grad_norm": 0.24877655506134033,
      "learning_rate": 9.001160894432978e-05,
      "loss": 0.2272,
      "step": 10
    },
    {
      "epoch": 0.8502415458937198,
      "grad_norm": 0.520237147808075,
      "learning_rate": 8.74880242279536e-05,
      "loss": 0.2048,
      "step": 11
    },
    {
      "epoch": 0.927536231884058,
      "grad_norm": 0.9614755511283875,
      "learning_rate": 8.473036255255366e-05,
      "loss": 0.1937,
      "step": 12
    },
    {
      "epoch": 1.0579710144927537,
      "grad_norm": 0.8174208998680115,
      "learning_rate": 8.175849293369291e-05,
      "loss": 0.3853,
      "step": 13
    },
    {
      "epoch": 1.1352657004830917,
      "grad_norm": 0.21609851717948914,
      "learning_rate": 7.859382776007543e-05,
      "loss": 0.1514,
      "step": 14
    },
    {
      "epoch": 1.21256038647343,
      "grad_norm": 0.2834426462650299,
      "learning_rate": 7.525916851679529e-05,
      "loss": 0.151,
      "step": 15
    },
    {
      "epoch": 1.289855072463768,
      "grad_norm": 0.1985989809036255,
      "learning_rate": 7.177854150011389e-05,
      "loss": 0.1643,
      "step": 16
    },
    {
      "epoch": 1.3671497584541064,
      "grad_norm": 0.17753714323043823,
      "learning_rate": 6.817702470744477e-05,
      "loss": 0.1461,
      "step": 17
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.2179577499628067,
      "learning_rate": 6.448056714980767e-05,
      "loss": 0.1508,
      "step": 18
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 0.1527913361787796,
      "learning_rate": 6.071580188860955e-05,
      "loss": 0.2133,
      "step": 19
    },
    {
      "epoch": 1.5990338164251208,
      "grad_norm": 0.11120735108852386,
      "learning_rate": 5.690985414382668e-05,
      "loss": 0.1437,
      "step": 20
    },
    {
      "epoch": 1.6763285024154588,
      "grad_norm": 0.15228553116321564,
      "learning_rate": 5.3090145856173346e-05,
      "loss": 0.1414,
      "step": 21
    },
    {
      "epoch": 1.7536231884057971,
      "grad_norm": 0.11549022793769836,
      "learning_rate": 4.9284198111390456e-05,
      "loss": 0.2019,
      "step": 22
    },
    {
      "epoch": 1.8309178743961354,
      "grad_norm": 0.12989747524261475,
      "learning_rate": 4.551943285019234e-05,
      "loss": 0.137,
      "step": 23
    },
    {
      "epoch": 1.9082125603864735,
      "grad_norm": 0.10218170285224915,
      "learning_rate": 4.182297529255525e-05,
      "loss": 0.1316,
      "step": 24
    },
    {
      "epoch": 2.0386473429951693,
      "grad_norm": 0.2697076201438904,
      "learning_rate": 3.822145849988612e-05,
      "loss": 0.344,
      "step": 25
    },
    {
      "epoch": 2.0386473429951693,
      "eval_loss": 0.13660724461078644,
      "eval_runtime": 1.1451,
      "eval_samples_per_second": 43.663,
      "eval_steps_per_second": 11.352,
      "step": 25
    },
    {
      "epoch": 2.1159420289855073,
      "grad_norm": 0.1018509790301323,
      "learning_rate": 3.474083148320469e-05,
      "loss": 0.1343,
      "step": 26
    },
    {
      "epoch": 2.1932367149758454,
      "grad_norm": 0.12204479426145554,
      "learning_rate": 3.1406172239924584e-05,
      "loss": 0.1308,
      "step": 27
    },
    {
      "epoch": 2.2705314009661834,
      "grad_norm": 0.1276244819164276,
      "learning_rate": 2.8241507066307104e-05,
      "loss": 0.1798,
      "step": 28
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.07243148982524872,
      "learning_rate": 2.5269637447446348e-05,
      "loss": 0.1243,
      "step": 29
    },
    {
      "epoch": 2.42512077294686,
      "grad_norm": 0.12894168496131897,
      "learning_rate": 2.2511975772046403e-05,
      "loss": 0.1309,
      "step": 30
    },
    {
      "epoch": 2.502415458937198,
      "grad_norm": 0.09854254871606827,
      "learning_rate": 1.9988391055670233e-05,
      "loss": 0.1694,
      "step": 31
    },
    {
      "epoch": 2.579710144927536,
      "grad_norm": 0.08287820219993591,
      "learning_rate": 1.771706578402711e-05,
      "loss": 0.1285,
      "step": 32
    },
    {
      "epoch": 2.6570048309178746,
      "grad_norm": 0.10731519758701324,
      "learning_rate": 1.5714364907746536e-05,
      "loss": 0.1231,
      "step": 33
    },
    {
      "epoch": 2.7342995169082127,
      "grad_norm": 0.09050889313220978,
      "learning_rate": 1.3994717932533891e-05,
      "loss": 0.1906,
      "step": 34
    },
    {
      "epoch": 2.8115942028985508,
      "grad_norm": 0.10606944561004639,
      "learning_rate": 1.257051495425121e-05,
      "loss": 0.1276,
      "step": 35
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.0904989019036293,
      "learning_rate": 1.1452017387992552e-05,
      "loss": 0.1243,
      "step": 36
    },
    {
      "epoch": 3.0193236714975846,
      "grad_norm": 0.182935893535614,
      "learning_rate": 1.064728403435312e-05,
      "loss": 0.3068,
      "step": 37
    },
    {
      "epoch": 3.0966183574879227,
      "grad_norm": 0.11063341051340103,
      "learning_rate": 1.0162113015586309e-05,
      "loss": 0.1229,
      "step": 38
    },
    {
      "epoch": 3.1739130434782608,
      "grad_norm": 0.0827033594250679,
      "learning_rate": 1e-05,
      "loss": 0.1225,
      "step": 39
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 1.7527496374432563e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}