{
  "best_metric": 0.03939060494303703,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.25157232704402516,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010062893081761006,
      "grad_norm": 0.3639535903930664,
      "learning_rate": 5e-05,
      "loss": 0.2333,
      "step": 1
    },
    {
      "epoch": 0.010062893081761006,
      "eval_loss": 0.4395422637462616,
      "eval_runtime": 30.7306,
      "eval_samples_per_second": 21.802,
      "eval_steps_per_second": 2.733,
      "step": 1
    },
    {
      "epoch": 0.02012578616352201,
      "grad_norm": 0.4397262632846832,
      "learning_rate": 0.0001,
      "loss": 0.2646,
      "step": 2
    },
    {
      "epoch": 0.03018867924528302,
      "grad_norm": 0.5376619696617126,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.2733,
      "step": 3
    },
    {
      "epoch": 0.04025157232704402,
      "grad_norm": 0.4236920475959778,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.2062,
      "step": 4
    },
    {
      "epoch": 0.050314465408805034,
      "grad_norm": 0.4180348813533783,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1301,
      "step": 5
    },
    {
      "epoch": 0.06037735849056604,
      "grad_norm": 0.24690310657024384,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0738,
      "step": 6
    },
    {
      "epoch": 0.07044025157232704,
      "grad_norm": 0.22631782293319702,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0576,
      "step": 7
    },
    {
      "epoch": 0.08050314465408805,
      "grad_norm": 0.2507324516773224,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0559,
      "step": 8
    },
    {
      "epoch": 0.09056603773584905,
      "grad_norm": 0.15755386650562286,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.036,
      "step": 9
    },
    {
      "epoch": 0.10062893081761007,
      "grad_norm": 0.1995922476053238,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0363,
      "step": 10
    },
    {
      "epoch": 0.11069182389937107,
      "grad_norm": 0.1199517473578453,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0254,
      "step": 11
    },
    {
      "epoch": 0.12075471698113208,
      "grad_norm": 0.12893110513687134,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0282,
      "step": 12
    },
    {
      "epoch": 0.13081761006289308,
      "grad_norm": 0.3422263264656067,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0821,
      "step": 13
    },
    {
      "epoch": 0.14088050314465408,
      "grad_norm": 0.2876516282558441,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0627,
      "step": 14
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 0.3431037366390228,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0537,
      "step": 15
    },
    {
      "epoch": 0.1610062893081761,
      "grad_norm": 0.24425195157527924,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0486,
      "step": 16
    },
    {
      "epoch": 0.1710691823899371,
      "grad_norm": 0.3430141806602478,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0428,
      "step": 17
    },
    {
      "epoch": 0.1811320754716981,
      "grad_norm": 0.13116921484470367,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0343,
      "step": 18
    },
    {
      "epoch": 0.19119496855345913,
      "grad_norm": 0.2921256124973297,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0277,
      "step": 19
    },
    {
      "epoch": 0.20125786163522014,
      "grad_norm": 0.09132912009954453,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.024,
      "step": 20
    },
    {
      "epoch": 0.21132075471698114,
      "grad_norm": 0.0867147147655487,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0217,
      "step": 21
    },
    {
      "epoch": 0.22138364779874214,
      "grad_norm": 0.10501576960086823,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0184,
      "step": 22
    },
    {
      "epoch": 0.23144654088050315,
      "grad_norm": 0.08421722054481506,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.013,
      "step": 23
    },
    {
      "epoch": 0.24150943396226415,
      "grad_norm": 0.08997359871864319,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0145,
      "step": 24
    },
    {
      "epoch": 0.25157232704402516,
      "grad_norm": 0.21365149319171906,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.023,
      "step": 25
    },
    {
      "epoch": 0.25157232704402516,
      "eval_loss": 0.03939060494303703,
      "eval_runtime": 30.8538,
      "eval_samples_per_second": 21.715,
      "eval_steps_per_second": 2.723,
      "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": 5.555785010511872e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}