{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.9184845005740528,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03673938002296211,
      "grad_norm": 0.9278978109359741,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.6167,
      "step": 1
    },
    {
      "epoch": 0.03673938002296211,
      "eval_loss": NaN,
      "eval_runtime": 1.5629,
      "eval_samples_per_second": 31.991,
      "eval_steps_per_second": 8.318,
      "step": 1
    },
    {
      "epoch": 0.07347876004592423,
      "grad_norm": 0.9947828650474548,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.5255,
      "step": 2
    },
    {
      "epoch": 0.11021814006888633,
      "grad_norm": 1.719213604927063,
      "learning_rate": 0.0001,
      "loss": 3.392,
      "step": 3
    },
    {
      "epoch": 0.14695752009184845,
      "grad_norm": 1.7546511888504028,
      "learning_rate": 9.99571699711836e-05,
      "loss": 3.5766,
      "step": 4
    },
    {
      "epoch": 0.18369690011481057,
      "grad_norm": 1.9130165576934814,
      "learning_rate": 9.982876141412856e-05,
      "loss": 2.7926,
      "step": 5
    },
    {
      "epoch": 0.22043628013777267,
      "grad_norm": 3.421264410018921,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.9667,
      "step": 6
    },
    {
      "epoch": 0.2571756601607348,
      "grad_norm": 2.740537643432617,
      "learning_rate": 9.931634888554937e-05,
      "loss": 2.596,
      "step": 7
    },
    {
      "epoch": 0.2939150401836969,
      "grad_norm": 2.477086305618286,
      "learning_rate": 9.893332032039701e-05,
      "loss": 2.3228,
      "step": 8
    },
    {
      "epoch": 0.330654420206659,
      "grad_norm": 1.5250732898712158,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.1207,
      "step": 9
    },
    {
      "epoch": 0.36739380022962115,
      "grad_norm": 1.927494764328003,
      "learning_rate": 9.791726278367022e-05,
      "loss": 2.6965,
      "step": 10
    },
    {
      "epoch": 0.4041331802525832,
      "grad_norm": 1.0458897352218628,
      "learning_rate": 9.728616793536588e-05,
      "loss": 2.1316,
      "step": 11
    },
    {
      "epoch": 0.44087256027554533,
      "grad_norm": 1.563544750213623,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.9629,
      "step": 12
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 1.739471197128296,
      "learning_rate": 9.578385041664925e-05,
      "loss": 1.9402,
      "step": 13
    },
    {
      "epoch": 0.5143513203214696,
      "grad_norm": 0.9345394372940063,
      "learning_rate": 9.491548749301997e-05,
      "loss": 2.2439,
      "step": 14
    },
    {
      "epoch": 0.5510907003444316,
      "grad_norm": 0.8077870011329651,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.0604,
      "step": 15
    },
    {
      "epoch": 0.5878300803673938,
      "grad_norm": 1.165358304977417,
      "learning_rate": 9.295261506157986e-05,
      "loss": 1.8347,
      "step": 16
    },
    {
      "epoch": 0.6245694603903559,
      "grad_norm": 1.2270612716674805,
      "learning_rate": 9.186184199300464e-05,
      "loss": 2.3273,
      "step": 17
    },
    {
      "epoch": 0.661308840413318,
      "grad_norm": 1.1496846675872803,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.9949,
      "step": 18
    },
    {
      "epoch": 0.6980482204362801,
      "grad_norm": 1.7061587572097778,
      "learning_rate": 8.947199994035401e-05,
      "loss": 1.4995,
      "step": 19
    },
    {
      "epoch": 0.7347876004592423,
      "grad_norm": 1.7375099658966064,
      "learning_rate": 8.817748015645558e-05,
      "loss": 1.4207,
      "step": 20
    },
    {
      "epoch": 0.7715269804822044,
      "grad_norm": 0.8804224729537964,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.0821,
      "step": 21
    },
    {
      "epoch": 0.8082663605051664,
      "grad_norm": 0.94223952293396,
      "learning_rate": 8.540155934270471e-05,
      "loss": 1.8211,
      "step": 22
    },
    {
      "epoch": 0.8450057405281286,
      "grad_norm": 1.558922290802002,
      "learning_rate": 8.392544243589427e-05,
      "loss": 1.9614,
      "step": 23
    },
    {
      "epoch": 0.8817451205510907,
      "grad_norm": 1.367186188697815,
      "learning_rate": 8.239426430539243e-05,
      "loss": 2.0158,
      "step": 24
    },
    {
      "epoch": 0.9184845005740528,
      "grad_norm": 1.1374205350875854,
      "learning_rate": 8.081093963579707e-05,
      "loss": 1.5267,
      "step": 25
    },
    {
      "epoch": 0.9184845005740528,
      "eval_loss": NaN,
      "eval_runtime": 1.5676,
      "eval_samples_per_second": 31.897,
      "eval_steps_per_second": 8.293,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.984041808658432e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}