{
  "best_metric": 1.8950231075286865,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.8298755186721992,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03319502074688797,
      "grad_norm": 1.3888013362884521,
      "learning_rate": 5e-05,
      "loss": 2.6549,
      "step": 1
    },
    {
      "epoch": 0.03319502074688797,
      "eval_loss": 3.3357467651367188,
      "eval_runtime": 13.4264,
      "eval_samples_per_second": 15.119,
      "eval_steps_per_second": 1.936,
      "step": 1
    },
    {
      "epoch": 0.06639004149377593,
      "grad_norm": 1.8296154737472534,
      "learning_rate": 0.0001,
      "loss": 2.8439,
      "step": 2
    },
    {
      "epoch": 0.0995850622406639,
      "grad_norm": 2.0284576416015625,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.9364,
      "step": 3
    },
    {
      "epoch": 0.13278008298755187,
      "grad_norm": 1.11079740524292,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.9005,
      "step": 4
    },
    {
      "epoch": 0.16597510373443983,
      "grad_norm": 1.8842670917510986,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.9907,
      "step": 5
    },
    {
      "epoch": 0.1991701244813278,
      "grad_norm": 3.5251011848449707,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.4015,
      "step": 6
    },
    {
      "epoch": 0.23236514522821577,
      "grad_norm": 7.950530052185059,
      "learning_rate": 9.73465064747553e-05,
      "loss": 3.4811,
      "step": 7
    },
    {
      "epoch": 0.26556016597510373,
      "grad_norm": 1.74943208694458,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.5328,
      "step": 8
    },
    {
      "epoch": 0.2987551867219917,
      "grad_norm": 1.263008952140808,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.4674,
      "step": 9
    },
    {
      "epoch": 0.33195020746887965,
      "grad_norm": 0.8815121054649353,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.3436,
      "step": 10
    },
    {
      "epoch": 0.3651452282157676,
      "grad_norm": 1.1149423122406006,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.3617,
      "step": 11
    },
    {
      "epoch": 0.3983402489626556,
      "grad_norm": 1.4619115591049194,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.3046,
      "step": 12
    },
    {
      "epoch": 0.4315352697095436,
      "grad_norm": 1.623265027999878,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.3843,
      "step": 13
    },
    {
      "epoch": 0.46473029045643155,
      "grad_norm": 2.030881404876709,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.2864,
      "step": 14
    },
    {
      "epoch": 0.4979253112033195,
      "grad_norm": 3.0583701133728027,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.234,
      "step": 15
    },
    {
      "epoch": 0.5311203319502075,
      "grad_norm": 3.715399742126465,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.3731,
      "step": 16
    },
    {
      "epoch": 0.5643153526970954,
      "grad_norm": 3.8472068309783936,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.3049,
      "step": 17
    },
    {
      "epoch": 0.5975103734439834,
      "grad_norm": 3.441741466522217,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2444,
      "step": 18
    },
    {
      "epoch": 0.6307053941908713,
      "grad_norm": 3.601855516433716,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.1137,
      "step": 19
    },
    {
      "epoch": 0.6639004149377593,
      "grad_norm": 4.1452813148498535,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.2233,
      "step": 20
    },
    {
      "epoch": 0.6970954356846473,
      "grad_norm": 3.2563297748565674,
      "learning_rate": 6.607197326515808e-05,
      "loss": 2.1183,
      "step": 21
    },
    {
      "epoch": 0.7302904564315352,
      "grad_norm": 3.6426761150360107,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.9478,
      "step": 22
    },
    {
      "epoch": 0.7634854771784232,
      "grad_norm": 1.054520606994629,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 2.057,
      "step": 23
    },
    {
      "epoch": 0.7966804979253111,
      "grad_norm": 0.8895332217216492,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.0793,
      "step": 24
    },
    {
      "epoch": 0.8298755186721992,
      "grad_norm": 0.7986735105514526,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.0316,
      "step": 25
    },
    {
      "epoch": 0.8298755186721992,
      "eval_loss": 1.8950231075286865,
      "eval_runtime": 13.3773,
      "eval_samples_per_second": 15.175,
      "eval_steps_per_second": 1.944,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.652642132099072e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}