{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.20013743343068202,
  "eval_steps": 500,
  "global_step": 1165,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08589589417625837,
      "grad_norm": 303.1338195800781,
      "learning_rate": 6.345419847328245e-06,
      "loss": 23.7695,
      "step": 500
    },
    {
      "epoch": 0.08589589417625837,
      "eval_loss": 551.8925170898438,
      "eval_runtime": 125.7319,
      "eval_samples_per_second": 41.445,
      "eval_steps_per_second": 5.186,
      "step": 500
    },
    {
      "epoch": 0.17179178835251674,
      "grad_norm": 176.70028686523438,
      "learning_rate": 1.5744274809160306e-06,
      "loss": 13.8972,
      "step": 1000
    },
    {
      "epoch": 0.17179178835251674,
      "eval_loss": 467.1653137207031,
      "eval_runtime": 125.8528,
      "eval_samples_per_second": 41.406,
      "eval_steps_per_second": 5.181,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1165,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}