{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1271186440677966,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00423728813559322,
      "eval_loss": NaN,
      "eval_runtime": 6.277,
      "eval_samples_per_second": 15.931,
      "eval_steps_per_second": 7.966,
      "step": 1
    },
    {
      "epoch": 0.012711864406779662,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.025423728813559324,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.03389830508474576,
      "eval_loss": NaN,
      "eval_runtime": 5.2181,
      "eval_samples_per_second": 19.164,
      "eval_steps_per_second": 9.582,
      "step": 8
    },
    {
      "epoch": 0.038135593220338986,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.05084745762711865,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0635593220338983,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.06779661016949153,
      "eval_loss": NaN,
      "eval_runtime": 5.2385,
      "eval_samples_per_second": 19.089,
      "eval_steps_per_second": 9.545,
      "step": 16
    },
    {
      "epoch": 0.07627118644067797,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.08898305084745763,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.1016949152542373,
      "eval_loss": NaN,
      "eval_runtime": 5.2257,
      "eval_samples_per_second": 19.136,
      "eval_steps_per_second": 9.568,
      "step": 24
    },
    {
      "epoch": 0.11440677966101695,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.1271186440677966,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2601911907778560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}