{
  "best_metric": 1.9761757850646973,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.35587188612099646,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014234875444839857,
      "grad_norm": 3.987726926803589,
      "learning_rate": 5e-05,
      "loss": 4.7109,
      "step": 1
    },
    {
      "epoch": 0.014234875444839857,
      "eval_loss": 5.259206295013428,
      "eval_runtime": 22.4487,
      "eval_samples_per_second": 21.07,
      "eval_steps_per_second": 2.673,
      "step": 1
    },
    {
      "epoch": 0.028469750889679714,
      "grad_norm": 4.957414627075195,
      "learning_rate": 0.0001,
      "loss": 4.7682,
      "step": 2
    },
    {
      "epoch": 0.042704626334519574,
      "grad_norm": 7.8210248947143555,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.6014,
      "step": 3
    },
    {
      "epoch": 0.05693950177935943,
      "grad_norm": 3.681251287460327,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.3953,
      "step": 4
    },
    {
      "epoch": 0.0711743772241993,
      "grad_norm": 3.565408706665039,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.7114,
      "step": 5
    },
    {
      "epoch": 0.08540925266903915,
      "grad_norm": 3.3629918098449707,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.9721,
      "step": 6
    },
    {
      "epoch": 0.099644128113879,
      "grad_norm": 2.452725648880005,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.6223,
      "step": 7
    },
    {
      "epoch": 0.11387900355871886,
      "grad_norm": 1.597943902015686,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.3872,
      "step": 8
    },
    {
      "epoch": 0.12811387900355872,
      "grad_norm": 1.974350094795227,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.3364,
      "step": 9
    },
    {
      "epoch": 0.1423487544483986,
      "grad_norm": 1.6135342121124268,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.2104,
      "step": 10
    },
    {
      "epoch": 0.15658362989323843,
      "grad_norm": 1.2702614068984985,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.1566,
      "step": 11
    },
    {
      "epoch": 0.1708185053380783,
      "grad_norm": 1.438144564628601,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.2743,
      "step": 12
    },
    {
      "epoch": 0.18505338078291814,
      "grad_norm": 1.0113654136657715,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.0603,
      "step": 13
    },
    {
      "epoch": 0.199288256227758,
      "grad_norm": 1.0551536083221436,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8847,
      "step": 14
    },
    {
      "epoch": 0.21352313167259787,
      "grad_norm": 0.9735572338104248,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.7829,
      "step": 15
    },
    {
      "epoch": 0.2277580071174377,
      "grad_norm": 0.8158897757530212,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.7687,
      "step": 16
    },
    {
      "epoch": 0.24199288256227758,
      "grad_norm": 0.8722501993179321,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.8711,
      "step": 17
    },
    {
      "epoch": 0.25622775800711745,
      "grad_norm": 0.8626693487167358,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.924,
      "step": 18
    },
    {
      "epoch": 0.2704626334519573,
      "grad_norm": 1.0108652114868164,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.0751,
      "step": 19
    },
    {
      "epoch": 0.2846975088967972,
      "grad_norm": 1.1322764158248901,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.1195,
      "step": 20
    },
    {
      "epoch": 0.298932384341637,
      "grad_norm": 0.7352483868598938,
      "learning_rate": 6.607197326515808e-05,
      "loss": 2.0273,
      "step": 21
    },
    {
      "epoch": 0.31316725978647686,
      "grad_norm": 0.8529086112976074,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.0648,
      "step": 22
    },
    {
      "epoch": 0.3274021352313167,
      "grad_norm": 0.8490323424339294,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 2.0244,
      "step": 23
    },
    {
      "epoch": 0.3416370106761566,
      "grad_norm": 0.8629425764083862,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.0,
      "step": 24
    },
    {
      "epoch": 0.35587188612099646,
      "grad_norm": 0.9219096899032593,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.3233,
      "step": 25
    },
    {
      "epoch": 0.35587188612099646,
      "eval_loss": 1.9761757850646973,
      "eval_runtime": 22.5157,
      "eval_samples_per_second": 21.008,
      "eval_steps_per_second": 2.665,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.114180768104448e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}