{
  "best_metric": 0.575002133846283,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.46296296296296297,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 0.5474225282669067,
      "learning_rate": 5e-05,
      "loss": 1.097,
      "step": 1
    },
    {
      "epoch": 0.018518518518518517,
      "eval_loss": 1.6396740674972534,
      "eval_runtime": 4.0983,
      "eval_samples_per_second": 88.817,
      "eval_steps_per_second": 11.224,
      "step": 1
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.6814149618148804,
      "learning_rate": 0.0001,
      "loss": 1.2547,
      "step": 2
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.7163407802581787,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.2502,
      "step": 3
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.6404975056648254,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.2215,
      "step": 4
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.590765118598938,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.1955,
      "step": 5
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.5880994200706482,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.124,
      "step": 6
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 0.5782201886177063,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.086,
      "step": 7
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.5449230074882507,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.06,
      "step": 8
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.5347405076026917,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.9701,
      "step": 9
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.5817571878433228,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9558,
      "step": 10
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 0.543773889541626,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.9536,
      "step": 11
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.5493637919425964,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.9326,
      "step": 12
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 0.24274133145809174,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.6924,
      "step": 13
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.2198300063610077,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6801,
      "step": 14
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.21759666502475739,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.6965,
      "step": 15
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.23276081681251526,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.6476,
      "step": 16
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 0.24803251028060913,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.6523,
      "step": 17
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.24354369938373566,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.631,
      "step": 18
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 0.24335706233978271,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.6601,
      "step": 19
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.2604289948940277,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6603,
      "step": 20
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.26426175236701965,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.6111,
      "step": 21
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.2667665183544159,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.5973,
      "step": 22
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 0.28260642290115356,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.5798,
      "step": 23
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.3108558654785156,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.6035,
      "step": 24
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 0.3848308324813843,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.6114,
      "step": 25
    },
    {
      "epoch": 0.46296296296296297,
      "eval_loss": 0.575002133846283,
      "eval_runtime": 4.0913,
      "eval_samples_per_second": 88.969,
      "eval_steps_per_second": 11.243,
      "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": 5.29768176943104e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}