{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.9079754601226995,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09815950920245399,
      "grad_norm": 22.079995941527155,
      "learning_rate": 4.9950668210706795e-06,
      "loss": 1.1476,
      "step": 1
    },
    {
      "epoch": 0.49079754601226994,
      "grad_norm": 28.798602514465546,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.6298,
      "step": 5
    },
    {
      "epoch": 0.9815950920245399,
      "grad_norm": 1.5828702193533934,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.3954,
      "step": 10
    },
    {
      "epoch": 1.4723926380368098,
      "grad_norm": 1.751452886574472,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.3763,
      "step": 15
    },
    {
      "epoch": 1.9631901840490797,
      "grad_norm": 1.5346301730102665,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.2938,
      "step": 20
    },
    {
      "epoch": 2.4539877300613497,
      "grad_norm": 1.77730409769221,
      "learning_rate": 2.5e-06,
      "loss": 0.2672,
      "step": 25
    },
    {
      "epoch": 2.9447852760736195,
      "grad_norm": 1.4804621454864022,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.2032,
      "step": 30
    },
    {
      "epoch": 3.4355828220858897,
      "grad_norm": 1.48905524222441,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.1838,
      "step": 35
    },
    {
      "epoch": 3.9263803680981595,
      "grad_norm": 1.547083449435107,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.1401,
      "step": 40
    },
    {
      "epoch": 4.41717791411043,
      "grad_norm": 1.2387253159564633,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.1385,
      "step": 45
    },
    {
      "epoch": 4.9079754601226995,
      "grad_norm": 1.412596844177546,
      "learning_rate": 0.0,
      "loss": 0.1175,
      "step": 50
    },
    {
      "epoch": 4.9079754601226995,
      "step": 50,
      "total_flos": 3402609524736.0,
      "train_loss": 0.28491151571273804,
      "train_runtime": 1069.0042,
      "train_samples_per_second": 3.04,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3402609524736.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}