{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.869565217391305,
  "eval_steps": 500,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1391304347826087,
      "grad_norm": 13.294223572235921,
      "learning_rate": 4.989935734988098e-06,
      "loss": 0.8885,
      "step": 1
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 15.33785483230219,
      "learning_rate": 4.752422169756048e-06,
      "loss": 0.4795,
      "step": 5
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 1.4918982778387289,
      "learning_rate": 4.058724504646834e-06,
      "loss": 0.2303,
      "step": 10
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 2.503462735033531,
      "learning_rate": 3.056302334890786e-06,
      "loss": 0.1885,
      "step": 15
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.8730312782218441,
      "learning_rate": 1.9436976651092143e-06,
      "loss": 0.1404,
      "step": 20
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 0.8494147814314459,
      "learning_rate": 9.412754953531664e-07,
      "loss": 0.1453,
      "step": 25
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.7939119409213207,
      "learning_rate": 2.4757783024395244e-07,
      "loss": 0.1409,
      "step": 30
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.6288108195768021,
      "learning_rate": 0.0,
      "loss": 0.1111,
      "step": 35
    },
    {
      "epoch": 4.869565217391305,
      "step": 35,
      "total_flos": 5397230657536.0,
      "train_loss": 0.21683297497885567,
      "train_runtime": 752.3138,
      "train_samples_per_second": 3.037,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 5,
  "max_steps": 35,
  "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": 5397230657536.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}