{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.424778761061947,
  "eval_steps": 500,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1415929203539823,
      "grad_norm": 24.470975522359446,
      "learning_rate": 4.989935734988098e-06,
      "loss": 0.9931,
      "step": 1
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 3.847836197185543,
      "learning_rate": 4.752422169756048e-06,
      "loss": 0.4145,
      "step": 5
    },
    {
      "epoch": 1.2831858407079646,
      "grad_norm": 1.207884724512833,
      "learning_rate": 4.058724504646834e-06,
      "loss": 0.2296,
      "step": 10
    },
    {
      "epoch": 1.991150442477876,
      "grad_norm": 1.0758073140672315,
      "learning_rate": 3.056302334890786e-06,
      "loss": 0.186,
      "step": 15
    },
    {
      "epoch": 2.566371681415929,
      "grad_norm": 0.8999666026080211,
      "learning_rate": 1.9436976651092143e-06,
      "loss": 0.1425,
      "step": 20
    },
    {
      "epoch": 3.1415929203539825,
      "grad_norm": 2.8544359868742033,
      "learning_rate": 9.412754953531664e-07,
      "loss": 0.122,
      "step": 25
    },
    {
      "epoch": 3.849557522123894,
      "grad_norm": 0.7058083901125113,
      "learning_rate": 2.4757783024395244e-07,
      "loss": 0.1027,
      "step": 30
    },
    {
      "epoch": 4.424778761061947,
      "grad_norm": 0.6362906534577231,
      "learning_rate": 0.0,
      "loss": 0.0949,
      "step": 35
    },
    {
      "epoch": 4.424778761061947,
      "step": 35,
      "total_flos": 2.3903983761149133e+17,
      "train_loss": 0.20112226009368897,
      "train_runtime": 2982.668,
      "train_samples_per_second": 1.505,
      "train_steps_per_second": 0.012
    }
  ],
  "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": 2.3903983761149133e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}