{
  "best_global_step": 240,
  "best_metric": 2.09912371635437,
  "best_model_checkpoint": "./mt5_summary_model\\checkpoint-240",
  "epoch": 3.0,
  "eval_steps": 40,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.125,
      "grad_norm": 41460.79296875,
      "learning_rate": 1.955e-05,
      "loss": 15.9769,
      "step": 10
    },
    {
      "epoch": 0.25,
      "grad_norm": 7548.4443359375,
      "learning_rate": 1.9050000000000002e-05,
      "loss": 14.8679,
      "step": 20
    },
    {
      "epoch": 0.375,
      "grad_norm": 6171.39013671875,
      "learning_rate": 1.855e-05,
      "loss": 14.4649,
      "step": 30
    },
    {
      "epoch": 0.5,
      "grad_norm": 3173.07275390625,
      "learning_rate": 1.805e-05,
      "loss": 12.9826,
      "step": 40
    },
    {
      "epoch": 0.5,
      "eval_loss": 7.740403175354004,
      "eval_runtime": 45.4998,
      "eval_samples_per_second": 1.582,
      "eval_steps_per_second": 0.198,
      "step": 40
    },
    {
      "epoch": 0.625,
      "grad_norm": 3397.85302734375,
      "learning_rate": 1.755e-05,
      "loss": 11.9366,
      "step": 50
    },
    {
      "epoch": 0.75,
      "grad_norm": 6715.337890625,
      "learning_rate": 1.705e-05,
      "loss": 11.328,
      "step": 60
    },
    {
      "epoch": 0.875,
      "grad_norm": 4861.546875,
      "learning_rate": 1.6550000000000002e-05,
      "loss": 11.3735,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 12531.2421875,
      "learning_rate": 1.605e-05,
      "loss": 10.5015,
      "step": 80
    },
    {
      "epoch": 1.0,
      "eval_loss": 5.373843669891357,
      "eval_runtime": 172.11,
      "eval_samples_per_second": 0.418,
      "eval_steps_per_second": 0.052,
      "step": 80
    },
    {
      "epoch": 1.125,
      "grad_norm": 1363.3099365234375,
      "learning_rate": 1.5550000000000002e-05,
      "loss": 9.7802,
      "step": 90
    },
    {
      "epoch": 1.25,
      "grad_norm": 3557.00537109375,
      "learning_rate": 1.505e-05,
      "loss": 9.3325,
      "step": 100
    },
    {
      "epoch": 1.375,
      "grad_norm": 448.0030517578125,
      "learning_rate": 1.4550000000000001e-05,
      "loss": 8.1717,
      "step": 110
    },
    {
      "epoch": 1.5,
      "grad_norm": 845.931640625,
      "learning_rate": 1.4050000000000001e-05,
      "loss": 7.581,
      "step": 120
    },
    {
      "epoch": 1.5,
      "eval_loss": 3.380208969116211,
      "eval_runtime": 172.0401,
      "eval_samples_per_second": 0.419,
      "eval_steps_per_second": 0.052,
      "step": 120
    },
    {
      "epoch": 1.625,
      "grad_norm": 1770.1221923828125,
      "learning_rate": 1.355e-05,
      "loss": 7.053,
      "step": 130
    },
    {
      "epoch": 1.75,
      "grad_norm": 38.347225189208984,
      "learning_rate": 1.305e-05,
      "loss": 6.2872,
      "step": 140
    },
    {
      "epoch": 1.875,
      "grad_norm": 139.71669006347656,
      "learning_rate": 1.255e-05,
      "loss": 5.6765,
      "step": 150
    },
    {
      "epoch": 2.0,
      "grad_norm": 67.0308837890625,
      "learning_rate": 1.2050000000000002e-05,
      "loss": 4.9915,
      "step": 160
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.404210329055786,
      "eval_runtime": 172.0874,
      "eval_samples_per_second": 0.418,
      "eval_steps_per_second": 0.052,
      "step": 160
    },
    {
      "epoch": 2.125,
      "grad_norm": 73.80687713623047,
      "learning_rate": 1.1550000000000001e-05,
      "loss": 4.6035,
      "step": 170
    },
    {
      "epoch": 2.25,
      "grad_norm": 14.295919418334961,
      "learning_rate": 1.1050000000000001e-05,
      "loss": 4.4453,
      "step": 180
    },
    {
      "epoch": 2.375,
      "grad_norm": 18.72945785522461,
      "learning_rate": 1.055e-05,
      "loss": 3.8718,
      "step": 190
    },
    {
      "epoch": 2.5,
      "grad_norm": 132.57345581054688,
      "learning_rate": 1.005e-05,
      "loss": 3.8554,
      "step": 200
    },
    {
      "epoch": 2.5,
      "eval_loss": 2.212625741958618,
      "eval_runtime": 172.1408,
      "eval_samples_per_second": 0.418,
      "eval_steps_per_second": 0.052,
      "step": 200
    },
    {
      "epoch": 2.625,
      "grad_norm": 6.234254360198975,
      "learning_rate": 9.55e-06,
      "loss": 3.481,
      "step": 210
    },
    {
      "epoch": 2.75,
      "grad_norm": 5.568007946014404,
      "learning_rate": 9.050000000000001e-06,
      "loss": 3.4293,
      "step": 220
    },
    {
      "epoch": 2.875,
      "grad_norm": 6.030545234680176,
      "learning_rate": 8.550000000000001e-06,
      "loss": 3.2727,
      "step": 230
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.541934013366699,
      "learning_rate": 8.050000000000001e-06,
      "loss": 3.2418,
      "step": 240
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.09912371635437,
      "eval_runtime": 172.0066,
      "eval_samples_per_second": 0.419,
      "eval_steps_per_second": 0.052,
      "step": 240
    }
  ],
  "logging_steps": 10,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 40,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 4604337145774080.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}