{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0019913376810872705,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019913376810872703,
      "grad_norm": 2.1729846000671387,
      "learning_rate": 2e-05,
      "loss": 0.8296,
      "step": 1
    },
    {
      "epoch": 0.00019913376810872703,
      "eval_loss": 0.9083439111709595,
      "eval_runtime": 248.3021,
      "eval_samples_per_second": 4.261,
      "eval_steps_per_second": 4.261,
      "step": 1
    },
    {
      "epoch": 0.00039826753621745407,
      "grad_norm": 3.0502281188964844,
      "learning_rate": 4e-05,
      "loss": 1.104,
      "step": 2
    },
    {
      "epoch": 0.0005974013043261811,
      "grad_norm": 1.9752157926559448,
      "learning_rate": 6e-05,
      "loss": 0.4881,
      "step": 3
    },
    {
      "epoch": 0.0005974013043261811,
      "eval_loss": 0.817756175994873,
      "eval_runtime": 248.5437,
      "eval_samples_per_second": 4.257,
      "eval_steps_per_second": 4.257,
      "step": 3
    },
    {
      "epoch": 0.0007965350724349081,
      "grad_norm": 1.9458492994308472,
      "learning_rate": 8e-05,
      "loss": 0.6913,
      "step": 4
    },
    {
      "epoch": 0.0009956688405436352,
      "grad_norm": 1.7831168174743652,
      "learning_rate": 0.0001,
      "loss": 0.6136,
      "step": 5
    },
    {
      "epoch": 0.0011948026086523623,
      "grad_norm": 2.603858470916748,
      "learning_rate": 0.00012,
      "loss": 0.5703,
      "step": 6
    },
    {
      "epoch": 0.0011948026086523623,
      "eval_loss": 0.526261031627655,
      "eval_runtime": 248.6726,
      "eval_samples_per_second": 4.255,
      "eval_steps_per_second": 4.255,
      "step": 6
    },
    {
      "epoch": 0.0013939363767610893,
      "grad_norm": 2.7793145179748535,
      "learning_rate": 0.00014,
      "loss": 0.4502,
      "step": 7
    },
    {
      "epoch": 0.0015930701448698163,
      "grad_norm": 1.5942715406417847,
      "learning_rate": 0.00016,
      "loss": 0.3581,
      "step": 8
    },
    {
      "epoch": 0.0017922039129785433,
      "grad_norm": 2.2092483043670654,
      "learning_rate": 0.00018,
      "loss": 0.3398,
      "step": 9
    },
    {
      "epoch": 0.0017922039129785433,
      "eval_loss": 0.41140756011009216,
      "eval_runtime": 248.3936,
      "eval_samples_per_second": 4.259,
      "eval_steps_per_second": 4.259,
      "step": 9
    },
    {
      "epoch": 0.0019913376810872705,
      "grad_norm": 1.9128527641296387,
      "learning_rate": 0.0002,
      "loss": 0.4628,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7668943615426560.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}