{
  "best_metric": 1.7377251386642456,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.18509949097639983,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009254974548819991,
      "eval_loss": 2.0847232341766357,
      "eval_runtime": 162.4017,
      "eval_samples_per_second": 11.207,
      "eval_steps_per_second": 2.802,
      "step": 1
    },
    {
      "epoch": 0.00925497454881999,
      "grad_norm": 0.5288553833961487,
      "learning_rate": 5e-05,
      "loss": 1.9788,
      "step": 10
    },
    {
      "epoch": 0.01850994909763998,
      "grad_norm": 0.2687051594257355,
      "learning_rate": 0.0001,
      "loss": 1.8967,
      "step": 20
    },
    {
      "epoch": 0.027764923646459973,
      "grad_norm": 0.285468190908432,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.8612,
      "step": 30
    },
    {
      "epoch": 0.03701989819527996,
      "grad_norm": 0.3615187406539917,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.8278,
      "step": 40
    },
    {
      "epoch": 0.04627487274409996,
      "grad_norm": 0.8302805423736572,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.7995,
      "step": 50
    },
    {
      "epoch": 0.04627487274409996,
      "eval_loss": 1.8223581314086914,
      "eval_runtime": 164.1133,
      "eval_samples_per_second": 11.09,
      "eval_steps_per_second": 2.772,
      "step": 50
    },
    {
      "epoch": 0.055529847292919945,
      "grad_norm": 0.2162926346063614,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.8218,
      "step": 60
    },
    {
      "epoch": 0.06478482184173993,
      "grad_norm": 0.22706399857997894,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.7809,
      "step": 70
    },
    {
      "epoch": 0.07403979639055992,
      "grad_norm": 0.26259857416152954,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.775,
      "step": 80
    },
    {
      "epoch": 0.08329477093937991,
      "grad_norm": 0.33791765570640564,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.7634,
      "step": 90
    },
    {
      "epoch": 0.09254974548819991,
      "grad_norm": 0.899003267288208,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.7645,
      "step": 100
    },
    {
      "epoch": 0.09254974548819991,
      "eval_loss": 1.7726473808288574,
      "eval_runtime": 164.1416,
      "eval_samples_per_second": 11.088,
      "eval_steps_per_second": 2.772,
      "step": 100
    },
    {
      "epoch": 0.1018047200370199,
      "grad_norm": 0.21113358438014984,
      "learning_rate": 5e-05,
      "loss": 1.7978,
      "step": 110
    },
    {
      "epoch": 0.11105969458583989,
      "grad_norm": 0.23512417078018188,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.7734,
      "step": 120
    },
    {
      "epoch": 0.12031466913465988,
      "grad_norm": 0.28493714332580566,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.7711,
      "step": 130
    },
    {
      "epoch": 0.12956964368347987,
      "grad_norm": 0.33335134387016296,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.7619,
      "step": 140
    },
    {
      "epoch": 0.13882461823229986,
      "grad_norm": 0.7424925565719604,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.7731,
      "step": 150
    },
    {
      "epoch": 0.13882461823229986,
      "eval_loss": 1.7417677640914917,
      "eval_runtime": 164.0774,
      "eval_samples_per_second": 11.092,
      "eval_steps_per_second": 2.773,
      "step": 150
    },
    {
      "epoch": 0.14807959278111985,
      "grad_norm": 0.22447636723518372,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.7912,
      "step": 160
    },
    {
      "epoch": 0.15733456732993983,
      "grad_norm": 0.23410490155220032,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.7734,
      "step": 170
    },
    {
      "epoch": 0.16658954187875982,
      "grad_norm": 0.2778407037258148,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.7592,
      "step": 180
    },
    {
      "epoch": 0.1758445164275798,
      "grad_norm": 0.3438330888748169,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.7603,
      "step": 190
    },
    {
      "epoch": 0.18509949097639983,
      "grad_norm": 0.7146674394607544,
      "learning_rate": 0.0,
      "loss": 1.7467,
      "step": 200
    },
    {
      "epoch": 0.18509949097639983,
      "eval_loss": 1.7377251386642456,
      "eval_runtime": 163.7691,
      "eval_samples_per_second": 11.113,
      "eval_steps_per_second": 2.778,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5796047653502976e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}