{
  "best_metric": 3.0149381160736084,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.009938382031405287,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019876764062810574,
      "grad_norm": 0.08420488983392715,
      "learning_rate": 2e-05,
      "loss": 1.6777,
      "step": 1
    },
    {
      "epoch": 0.00019876764062810574,
      "eval_loss": 3.6612236499786377,
      "eval_runtime": 67.3581,
      "eval_samples_per_second": 125.805,
      "eval_steps_per_second": 15.737,
      "step": 1
    },
    {
      "epoch": 0.0003975352812562115,
      "grad_norm": 0.17416247725486755,
      "learning_rate": 4e-05,
      "loss": 2.4276,
      "step": 2
    },
    {
      "epoch": 0.0005963029218843172,
      "grad_norm": 0.21623319387435913,
      "learning_rate": 6e-05,
      "loss": 2.6007,
      "step": 3
    },
    {
      "epoch": 0.000795070562512423,
      "grad_norm": 0.15903286635875702,
      "learning_rate": 8e-05,
      "loss": 2.646,
      "step": 4
    },
    {
      "epoch": 0.0009938382031405286,
      "grad_norm": 0.1743364781141281,
      "learning_rate": 0.0001,
      "loss": 2.9006,
      "step": 5
    },
    {
      "epoch": 0.0011926058437686344,
      "grad_norm": 0.18579961359500885,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.7491,
      "step": 6
    },
    {
      "epoch": 0.0013913734843967402,
      "grad_norm": 0.19385971128940582,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.7176,
      "step": 7
    },
    {
      "epoch": 0.001590141125024846,
      "grad_norm": 0.20547613501548767,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.9435,
      "step": 8
    },
    {
      "epoch": 0.0017889087656529517,
      "grad_norm": 0.21542897820472717,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.9636,
      "step": 9
    },
    {
      "epoch": 0.0019876764062810573,
      "grad_norm": 0.20447668433189392,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.7969,
      "step": 10
    },
    {
      "epoch": 0.0021864440469091632,
      "grad_norm": 0.22560608386993408,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.3065,
      "step": 11
    },
    {
      "epoch": 0.002385211687537269,
      "grad_norm": 0.23869244754314423,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.1795,
      "step": 12
    },
    {
      "epoch": 0.002583979328165375,
      "grad_norm": 0.21942728757858276,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.9018,
      "step": 13
    },
    {
      "epoch": 0.0027827469687934803,
      "grad_norm": 0.24622339010238647,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.3347,
      "step": 14
    },
    {
      "epoch": 0.0029815146094215863,
      "grad_norm": 0.2358148694038391,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.2586,
      "step": 15
    },
    {
      "epoch": 0.003180282250049692,
      "grad_norm": 0.2474563717842102,
      "learning_rate": 8.596699001693255e-05,
      "loss": 3.2522,
      "step": 16
    },
    {
      "epoch": 0.003379049890677798,
      "grad_norm": 0.26249605417251587,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.0814,
      "step": 17
    },
    {
      "epoch": 0.0035778175313059034,
      "grad_norm": 0.27410539984703064,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.3012,
      "step": 18
    },
    {
      "epoch": 0.003776585171934009,
      "grad_norm": 0.25694385170936584,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.1564,
      "step": 19
    },
    {
      "epoch": 0.0039753528125621145,
      "grad_norm": 0.26552635431289673,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.2579,
      "step": 20
    },
    {
      "epoch": 0.0041741204531902205,
      "grad_norm": 0.25721579790115356,
      "learning_rate": 7.191855733945387e-05,
      "loss": 3.2505,
      "step": 21
    },
    {
      "epoch": 0.0043728880938183265,
      "grad_norm": 0.2668185234069824,
      "learning_rate": 6.873032967079561e-05,
      "loss": 3.0924,
      "step": 22
    },
    {
      "epoch": 0.0045716557344464325,
      "grad_norm": 0.26348620653152466,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.2819,
      "step": 23
    },
    {
      "epoch": 0.004770423375074538,
      "grad_norm": 0.26392704248428345,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.102,
      "step": 24
    },
    {
      "epoch": 0.004969191015702644,
      "grad_norm": 0.26735320687294006,
      "learning_rate": 5.868240888334653e-05,
      "loss": 3.1296,
      "step": 25
    },
    {
      "epoch": 0.004969191015702644,
      "eval_loss": 3.111262798309326,
      "eval_runtime": 67.118,
      "eval_samples_per_second": 126.255,
      "eval_steps_per_second": 15.793,
      "step": 25
    },
    {
      "epoch": 0.00516795865633075,
      "grad_norm": 0.3099224269390106,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.1568,
      "step": 26
    },
    {
      "epoch": 0.005366726296958855,
      "grad_norm": 0.2683943808078766,
      "learning_rate": 5.174497483512506e-05,
      "loss": 3.3075,
      "step": 27
    },
    {
      "epoch": 0.005565493937586961,
      "grad_norm": 0.290770560503006,
      "learning_rate": 4.825502516487497e-05,
      "loss": 3.1469,
      "step": 28
    },
    {
      "epoch": 0.005764261578215067,
      "grad_norm": 0.2689608931541443,
      "learning_rate": 4.477357683661734e-05,
      "loss": 3.1745,
      "step": 29
    },
    {
      "epoch": 0.005963029218843173,
      "grad_norm": 0.27947020530700684,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.1196,
      "step": 30
    },
    {
      "epoch": 0.006161796859471278,
      "grad_norm": 0.3059743344783783,
      "learning_rate": 3.790390522001662e-05,
      "loss": 3.2627,
      "step": 31
    },
    {
      "epoch": 0.006360564500099384,
      "grad_norm": 0.2834652066230774,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.0715,
      "step": 32
    },
    {
      "epoch": 0.00655933214072749,
      "grad_norm": 0.31416839361190796,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.1854,
      "step": 33
    },
    {
      "epoch": 0.006758099781355596,
      "grad_norm": 0.3347357213497162,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 3.1765,
      "step": 34
    },
    {
      "epoch": 0.006956867421983701,
      "grad_norm": 0.30826708674430847,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.223,
      "step": 35
    },
    {
      "epoch": 0.007155635062611807,
      "grad_norm": 0.32336822152137756,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 3.3838,
      "step": 36
    },
    {
      "epoch": 0.007354402703239913,
      "grad_norm": 0.3186890482902527,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 3.1607,
      "step": 37
    },
    {
      "epoch": 0.007553170343868018,
      "grad_norm": 0.330779105424881,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 3.2356,
      "step": 38
    },
    {
      "epoch": 0.007751937984496124,
      "grad_norm": 0.3563855290412903,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.1177,
      "step": 39
    },
    {
      "epoch": 0.007950705625124229,
      "grad_norm": 0.36722344160079956,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 3.0539,
      "step": 40
    },
    {
      "epoch": 0.008149473265752336,
      "grad_norm": 0.3383886516094208,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.2582,
      "step": 41
    },
    {
      "epoch": 0.008348240906380441,
      "grad_norm": 0.35494890809059143,
      "learning_rate": 7.597595192178702e-06,
      "loss": 3.0954,
      "step": 42
    },
    {
      "epoch": 0.008547008547008548,
      "grad_norm": 0.3515838086605072,
      "learning_rate": 5.852620357053651e-06,
      "loss": 3.3631,
      "step": 43
    },
    {
      "epoch": 0.008745776187636653,
      "grad_norm": 0.37979280948638916,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.3569,
      "step": 44
    },
    {
      "epoch": 0.008944543828264758,
      "grad_norm": 0.3924817144870758,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.2494,
      "step": 45
    },
    {
      "epoch": 0.009143311468892865,
      "grad_norm": 0.39909616112709045,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.3279,
      "step": 46
    },
    {
      "epoch": 0.00934207910952097,
      "grad_norm": 0.46893322467803955,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.1981,
      "step": 47
    },
    {
      "epoch": 0.009540846750149075,
      "grad_norm": 0.4818413555622101,
      "learning_rate": 4.865965629214819e-07,
      "loss": 3.4108,
      "step": 48
    },
    {
      "epoch": 0.009739614390777182,
      "grad_norm": 0.6217837333679199,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 3.674,
      "step": 49
    },
    {
      "epoch": 0.009938382031405287,
      "grad_norm": 0.9694095253944397,
      "learning_rate": 0.0,
      "loss": 4.1192,
      "step": 50
    },
    {
      "epoch": 0.009938382031405287,
      "eval_loss": 3.0149381160736084,
      "eval_runtime": 67.076,
      "eval_samples_per_second": 126.334,
      "eval_steps_per_second": 15.803,
      "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": 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": 1725805984481280.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}