{
  "best_metric": 4.168821811676025,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.4598540145985401,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.058394160583941604,
      "grad_norm": 1.2822612524032593,
      "learning_rate": 5e-05,
      "loss": 4.1834,
      "step": 1
    },
    {
      "epoch": 0.058394160583941604,
      "eval_loss": 5.098187446594238,
      "eval_runtime": 0.3396,
      "eval_samples_per_second": 341.606,
      "eval_steps_per_second": 44.173,
      "step": 1
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 2.569211006164551,
      "learning_rate": 0.0001,
      "loss": 4.8724,
      "step": 2
    },
    {
      "epoch": 0.17518248175182483,
      "grad_norm": 2.091531276702881,
      "learning_rate": 9.989294616193017e-05,
      "loss": 5.2191,
      "step": 3
    },
    {
      "epoch": 0.23357664233576642,
      "grad_norm": 1.7123160362243652,
      "learning_rate": 9.957224306869053e-05,
      "loss": 5.3955,
      "step": 4
    },
    {
      "epoch": 0.291970802919708,
      "grad_norm": 0.8882278203964233,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.055,
      "step": 5
    },
    {
      "epoch": 0.35036496350364965,
      "grad_norm": 0.8794437646865845,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.5183,
      "step": 6
    },
    {
      "epoch": 0.40875912408759124,
      "grad_norm": 1.4536943435668945,
      "learning_rate": 9.73465064747553e-05,
      "loss": 4.8049,
      "step": 7
    },
    {
      "epoch": 0.46715328467153283,
      "grad_norm": 2.662942886352539,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.0266,
      "step": 8
    },
    {
      "epoch": 0.5255474452554745,
      "grad_norm": 0.9087815880775452,
      "learning_rate": 9.484363707663442e-05,
      "loss": 3.9506,
      "step": 9
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 0.7557864189147949,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.2279,
      "step": 10
    },
    {
      "epoch": 0.6423357664233577,
      "grad_norm": 1.1979687213897705,
      "learning_rate": 9.157348061512727e-05,
      "loss": 4.4896,
      "step": 11
    },
    {
      "epoch": 0.7007299270072993,
      "grad_norm": 1.4247801303863525,
      "learning_rate": 8.966766701456177e-05,
      "loss": 4.7441,
      "step": 12
    },
    {
      "epoch": 0.7591240875912408,
      "grad_norm": 0.7902650833129883,
      "learning_rate": 8.759199037394887e-05,
      "loss": 4.0107,
      "step": 13
    },
    {
      "epoch": 0.8175182481751825,
      "grad_norm": 0.7168551087379456,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.0785,
      "step": 14
    },
    {
      "epoch": 0.8759124087591241,
      "grad_norm": 0.7550625801086426,
      "learning_rate": 8.296729075500344e-05,
      "loss": 4.272,
      "step": 15
    },
    {
      "epoch": 0.9343065693430657,
      "grad_norm": 1.0377146005630493,
      "learning_rate": 8.043807145043604e-05,
      "loss": 4.5471,
      "step": 16
    },
    {
      "epoch": 0.9927007299270073,
      "grad_norm": 1.4056518077850342,
      "learning_rate": 7.777851165098012e-05,
      "loss": 4.8509,
      "step": 17
    },
    {
      "epoch": 1.051094890510949,
      "grad_norm": 1.4291749000549316,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.0564,
      "step": 18
    },
    {
      "epoch": 1.1094890510948905,
      "grad_norm": 0.7004761099815369,
      "learning_rate": 7.211443451095007e-05,
      "loss": 4.0164,
      "step": 19
    },
    {
      "epoch": 1.167883211678832,
      "grad_norm": 0.9470470547676086,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.2587,
      "step": 20
    },
    {
      "epoch": 1.2262773722627738,
      "grad_norm": 1.1709222793579102,
      "learning_rate": 6.607197326515808e-05,
      "loss": 4.557,
      "step": 21
    },
    {
      "epoch": 1.2846715328467153,
      "grad_norm": 0.6594967246055603,
      "learning_rate": 6.294095225512603e-05,
      "loss": 3.7556,
      "step": 22
    },
    {
      "epoch": 1.343065693430657,
      "grad_norm": 0.6004905700683594,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.9757,
      "step": 23
    },
    {
      "epoch": 1.4014598540145986,
      "grad_norm": 0.865336537361145,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 4.224,
      "step": 24
    },
    {
      "epoch": 1.4598540145985401,
      "grad_norm": 1.046862006187439,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.2923,
      "step": 25
    },
    {
      "epoch": 1.4598540145985401,
      "eval_loss": 4.168821811676025,
      "eval_runtime": 0.3358,
      "eval_samples_per_second": 345.484,
      "eval_steps_per_second": 44.675,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 5686862177894400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}