{
  "best_metric": 1.6387317180633545,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.6514657980456026,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013029315960912053,
      "grad_norm": 4.033048629760742,
      "learning_rate": 5e-05,
      "loss": 4.4207,
      "step": 1
    },
    {
      "epoch": 0.013029315960912053,
      "eval_loss": 6.510675430297852,
      "eval_runtime": 15.7339,
      "eval_samples_per_second": 32.859,
      "eval_steps_per_second": 4.131,
      "step": 1
    },
    {
      "epoch": 0.026058631921824105,
      "grad_norm": 4.561133861541748,
      "learning_rate": 0.0001,
      "loss": 4.8966,
      "step": 2
    },
    {
      "epoch": 0.03908794788273615,
      "grad_norm": 5.338207244873047,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.8076,
      "step": 3
    },
    {
      "epoch": 0.05211726384364821,
      "grad_norm": 4.561549186706543,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.1035,
      "step": 4
    },
    {
      "epoch": 0.06514657980456026,
      "grad_norm": 4.916613578796387,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.256,
      "step": 5
    },
    {
      "epoch": 0.0781758957654723,
      "grad_norm": 3.6213910579681396,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.7378,
      "step": 6
    },
    {
      "epoch": 0.09120521172638436,
      "grad_norm": 3.188063859939575,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.7365,
      "step": 7
    },
    {
      "epoch": 0.10423452768729642,
      "grad_norm": 3.4584438800811768,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.453,
      "step": 8
    },
    {
      "epoch": 0.11726384364820847,
      "grad_norm": 3.692514181137085,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.2256,
      "step": 9
    },
    {
      "epoch": 0.13029315960912052,
      "grad_norm": 2.7663116455078125,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.1805,
      "step": 10
    },
    {
      "epoch": 0.14332247557003258,
      "grad_norm": 3.047680139541626,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8794,
      "step": 11
    },
    {
      "epoch": 0.1563517915309446,
      "grad_norm": 6.86872673034668,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.5884,
      "step": 12
    },
    {
      "epoch": 0.16938110749185667,
      "grad_norm": 9.102276802062988,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.9419,
      "step": 13
    },
    {
      "epoch": 0.18241042345276873,
      "grad_norm": 7.11753511428833,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.6921,
      "step": 14
    },
    {
      "epoch": 0.19543973941368079,
      "grad_norm": 3.8425393104553223,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.3199,
      "step": 15
    },
    {
      "epoch": 0.20846905537459284,
      "grad_norm": 2.036224126815796,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.3416,
      "step": 16
    },
    {
      "epoch": 0.22149837133550487,
      "grad_norm": 1.965226173400879,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.149,
      "step": 17
    },
    {
      "epoch": 0.23452768729641693,
      "grad_norm": 2.1932334899902344,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0797,
      "step": 18
    },
    {
      "epoch": 0.247557003257329,
      "grad_norm": 2.3755345344543457,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.1096,
      "step": 19
    },
    {
      "epoch": 0.26058631921824105,
      "grad_norm": 2.250009775161743,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0224,
      "step": 20
    },
    {
      "epoch": 0.2736156351791531,
      "grad_norm": 1.7564245462417603,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.8868,
      "step": 21
    },
    {
      "epoch": 0.28664495114006516,
      "grad_norm": 1.8922572135925293,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.879,
      "step": 22
    },
    {
      "epoch": 0.2996742671009772,
      "grad_norm": 1.9456310272216797,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.4581,
      "step": 23
    },
    {
      "epoch": 0.3127035830618892,
      "grad_norm": 1.9163482189178467,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.2085,
      "step": 24
    },
    {
      "epoch": 0.3257328990228013,
      "grad_norm": 7.9290947914123535,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.5958,
      "step": 25
    },
    {
      "epoch": 0.3257328990228013,
      "eval_loss": 1.8510099649429321,
      "eval_runtime": 15.7107,
      "eval_samples_per_second": 32.907,
      "eval_steps_per_second": 4.137,
      "step": 25
    },
    {
      "epoch": 0.33876221498371334,
      "grad_norm": 2.9749815464019775,
      "learning_rate": 5e-05,
      "loss": 2.3222,
      "step": 26
    },
    {
      "epoch": 0.3517915309446254,
      "grad_norm": 2.7900686264038086,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 2.2201,
      "step": 27
    },
    {
      "epoch": 0.36482084690553745,
      "grad_norm": 2.3980400562286377,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.9729,
      "step": 28
    },
    {
      "epoch": 0.3778501628664495,
      "grad_norm": 2.311643123626709,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 2.0899,
      "step": 29
    },
    {
      "epoch": 0.39087947882736157,
      "grad_norm": 1.716529369354248,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.7145,
      "step": 30
    },
    {
      "epoch": 0.40390879478827363,
      "grad_norm": 1.4827934503555298,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.8561,
      "step": 31
    },
    {
      "epoch": 0.4169381107491857,
      "grad_norm": 1.62079918384552,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.8233,
      "step": 32
    },
    {
      "epoch": 0.42996742671009774,
      "grad_norm": 1.744267225265503,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.8271,
      "step": 33
    },
    {
      "epoch": 0.44299674267100975,
      "grad_norm": 1.6195056438446045,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.6763,
      "step": 34
    },
    {
      "epoch": 0.4560260586319218,
      "grad_norm": 1.8608180284500122,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.5281,
      "step": 35
    },
    {
      "epoch": 0.46905537459283386,
      "grad_norm": 2.0520479679107666,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.4334,
      "step": 36
    },
    {
      "epoch": 0.4820846905537459,
      "grad_norm": 2.6401760578155518,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.1135,
      "step": 37
    },
    {
      "epoch": 0.495114006514658,
      "grad_norm": 1.7265050411224365,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.8908,
      "step": 38
    },
    {
      "epoch": 0.50814332247557,
      "grad_norm": 1.504112720489502,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.9997,
      "step": 39
    },
    {
      "epoch": 0.5211726384364821,
      "grad_norm": 1.5612125396728516,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.9431,
      "step": 40
    },
    {
      "epoch": 0.5342019543973942,
      "grad_norm": 1.5212734937667847,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.854,
      "step": 41
    },
    {
      "epoch": 0.5472312703583062,
      "grad_norm": 1.4431742429733276,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.8395,
      "step": 42
    },
    {
      "epoch": 0.5602605863192183,
      "grad_norm": 1.4133102893829346,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.8975,
      "step": 43
    },
    {
      "epoch": 0.5732899022801303,
      "grad_norm": 1.4782320261001587,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.7064,
      "step": 44
    },
    {
      "epoch": 0.5863192182410424,
      "grad_norm": 1.3608444929122925,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.5539,
      "step": 45
    },
    {
      "epoch": 0.5993485342019544,
      "grad_norm": 1.5868359804153442,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.6155,
      "step": 46
    },
    {
      "epoch": 0.6123778501628665,
      "grad_norm": 1.7289336919784546,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.7781,
      "step": 47
    },
    {
      "epoch": 0.6254071661237784,
      "grad_norm": 1.669608235359192,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.3571,
      "step": 48
    },
    {
      "epoch": 0.6384364820846905,
      "grad_norm": 1.7300235033035278,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.1766,
      "step": 49
    },
    {
      "epoch": 0.6514657980456026,
      "grad_norm": 2.4439947605133057,
      "learning_rate": 0.0,
      "loss": 0.5083,
      "step": 50
    },
    {
      "epoch": 0.6514657980456026,
      "eval_loss": 1.6387317180633545,
      "eval_runtime": 15.9992,
      "eval_samples_per_second": 32.314,
      "eval_steps_per_second": 4.063,
      "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": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}