{
  "best_metric": 1.208978295326233,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.03390405153415833,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013561620613663332,
      "grad_norm": 2.852473735809326,
      "learning_rate": 5e-05,
      "loss": 1.8006,
      "step": 1
    },
    {
      "epoch": 0.0013561620613663332,
      "eval_loss": 1.861175537109375,
      "eval_runtime": 82.7696,
      "eval_samples_per_second": 60.022,
      "eval_steps_per_second": 7.503,
      "step": 1
    },
    {
      "epoch": 0.0027123241227326664,
      "grad_norm": 2.986945390701294,
      "learning_rate": 0.0001,
      "loss": 1.8261,
      "step": 2
    },
    {
      "epoch": 0.0040684861840989996,
      "grad_norm": 1.968458652496338,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.6889,
      "step": 3
    },
    {
      "epoch": 0.005424648245465333,
      "grad_norm": 2.078989028930664,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.5043,
      "step": 4
    },
    {
      "epoch": 0.006780810306831667,
      "grad_norm": 1.3944963216781616,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.4348,
      "step": 5
    },
    {
      "epoch": 0.008136972368197999,
      "grad_norm": 1.0220277309417725,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.3875,
      "step": 6
    },
    {
      "epoch": 0.009493134429564332,
      "grad_norm": 0.6817047595977783,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.2852,
      "step": 7
    },
    {
      "epoch": 0.010849296490930666,
      "grad_norm": 0.674114465713501,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.2928,
      "step": 8
    },
    {
      "epoch": 0.012205458552296999,
      "grad_norm": 0.6182920336723328,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.2517,
      "step": 9
    },
    {
      "epoch": 0.013561620613663334,
      "grad_norm": 0.5390492677688599,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.2533,
      "step": 10
    },
    {
      "epoch": 0.014917782675029667,
      "grad_norm": 0.4900094270706177,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.2403,
      "step": 11
    },
    {
      "epoch": 0.016273944736395998,
      "grad_norm": 0.510083019733429,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.2955,
      "step": 12
    },
    {
      "epoch": 0.01763010679776233,
      "grad_norm": 0.486646831035614,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.3456,
      "step": 13
    },
    {
      "epoch": 0.018986268859128665,
      "grad_norm": 0.440630704164505,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.2407,
      "step": 14
    },
    {
      "epoch": 0.020342430920494998,
      "grad_norm": 0.42777761816978455,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.261,
      "step": 15
    },
    {
      "epoch": 0.02169859298186133,
      "grad_norm": 0.4407661259174347,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.2406,
      "step": 16
    },
    {
      "epoch": 0.023054755043227664,
      "grad_norm": 0.44828706979751587,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.2327,
      "step": 17
    },
    {
      "epoch": 0.024410917104593997,
      "grad_norm": 0.4163109064102173,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2363,
      "step": 18
    },
    {
      "epoch": 0.02576707916596033,
      "grad_norm": 0.4135110676288605,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.2585,
      "step": 19
    },
    {
      "epoch": 0.027123241227326667,
      "grad_norm": 0.4255843162536621,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2716,
      "step": 20
    },
    {
      "epoch": 0.028479403288693,
      "grad_norm": 0.3930562734603882,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.2165,
      "step": 21
    },
    {
      "epoch": 0.029835565350059334,
      "grad_norm": 0.3968987762928009,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.2606,
      "step": 22
    },
    {
      "epoch": 0.031191727411425667,
      "grad_norm": 0.40137743949890137,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.2374,
      "step": 23
    },
    {
      "epoch": 0.032547889472791997,
      "grad_norm": 0.3884185254573822,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.2152,
      "step": 24
    },
    {
      "epoch": 0.03390405153415833,
      "grad_norm": 0.43205586075782776,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.2734,
      "step": 25
    },
    {
      "epoch": 0.03390405153415833,
      "eval_loss": 1.208978295326233,
      "eval_runtime": 82.6548,
      "eval_samples_per_second": 60.105,
      "eval_steps_per_second": 7.513,
      "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": 8.1240447254528e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}