{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.82648401826484,
  "eval_steps": 0,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.182648401826484,
      "grad_norm": 0.04941319301724434,
      "learning_rate": 4.591836734693878e-05,
      "loss": 2.1023,
      "step": 100
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 0.08505821973085403,
      "learning_rate": 4.0816326530612245e-05,
      "loss": 0.005,
      "step": 200
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.010337394662201405,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.0029,
      "step": 300
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 0.008043269626796246,
      "learning_rate": 3.061224489795919e-05,
      "loss": 0.0025,
      "step": 400
    },
    {
      "epoch": 0.91324200913242,
      "grad_norm": 0.00774584524333477,
      "learning_rate": 2.5510204081632654e-05,
      "loss": 0.0025,
      "step": 500
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 0.007855338044464588,
      "learning_rate": 2.0408163265306123e-05,
      "loss": 0.0023,
      "step": 600
    },
    {
      "epoch": 1.278538812785388,
      "grad_norm": 0.008511941879987717,
      "learning_rate": 1.5306122448979594e-05,
      "loss": 0.0022,
      "step": 700
    },
    {
      "epoch": 1.461187214611872,
      "grad_norm": 0.007371000479906797,
      "learning_rate": 1.0204081632653061e-05,
      "loss": 0.0021,
      "step": 800
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 0.008065593428909779,
      "learning_rate": 5.102040816326531e-06,
      "loss": 0.0021,
      "step": 900
    },
    {
      "epoch": 1.82648401826484,
      "grad_norm": 0.006567740812897682,
      "learning_rate": 0.0,
      "loss": 0.0021,
      "step": 1000
    },
    {
      "epoch": 1.82648401826484,
      "step": 1000,
      "total_flos": 1.5310362798718976e+16,
      "train_loss": 0.2125894913226366,
      "train_runtime": 43501.0411,
      "train_samples_per_second": 3.678,
      "train_steps_per_second": 0.023
    }
  ],
  "logging_steps": 100,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5310362798718976e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}