{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.026972353337828724,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026972353337828725,
      "grad_norm": 0.1639767289161682,
      "learning_rate": 2e-05,
      "loss": 1.237,
      "step": 1
    },
    {
      "epoch": 0.0026972353337828725,
      "eval_loss": 1.297181487083435,
      "eval_runtime": 5.8762,
      "eval_samples_per_second": 26.718,
      "eval_steps_per_second": 13.444,
      "step": 1
    },
    {
      "epoch": 0.005394470667565745,
      "grad_norm": 0.1925351768732071,
      "learning_rate": 4e-05,
      "loss": 1.2314,
      "step": 2
    },
    {
      "epoch": 0.008091706001348618,
      "grad_norm": 0.16352343559265137,
      "learning_rate": 6e-05,
      "loss": 0.9651,
      "step": 3
    },
    {
      "epoch": 0.008091706001348618,
      "eval_loss": 1.2972162961959839,
      "eval_runtime": 4.0439,
      "eval_samples_per_second": 38.824,
      "eval_steps_per_second": 19.535,
      "step": 3
    },
    {
      "epoch": 0.01078894133513149,
      "grad_norm": 0.23890061676502228,
      "learning_rate": 8e-05,
      "loss": 1.267,
      "step": 4
    },
    {
      "epoch": 0.013486176668914362,
      "grad_norm": 0.21312342584133148,
      "learning_rate": 0.0001,
      "loss": 1.2859,
      "step": 5
    },
    {
      "epoch": 0.016183412002697236,
      "grad_norm": 0.18828976154327393,
      "learning_rate": 0.00012,
      "loss": 1.2129,
      "step": 6
    },
    {
      "epoch": 0.016183412002697236,
      "eval_loss": 1.296493649482727,
      "eval_runtime": 4.0948,
      "eval_samples_per_second": 38.341,
      "eval_steps_per_second": 19.293,
      "step": 6
    },
    {
      "epoch": 0.018880647336480108,
      "grad_norm": 0.20136234164237976,
      "learning_rate": 0.00014,
      "loss": 1.1399,
      "step": 7
    },
    {
      "epoch": 0.02157788267026298,
      "grad_norm": 0.20706254243850708,
      "learning_rate": 0.00016,
      "loss": 1.1876,
      "step": 8
    },
    {
      "epoch": 0.024275118004045852,
      "grad_norm": 0.18600346148014069,
      "learning_rate": 0.00018,
      "loss": 1.1218,
      "step": 9
    },
    {
      "epoch": 0.024275118004045852,
      "eval_loss": 1.2926275730133057,
      "eval_runtime": 4.1348,
      "eval_samples_per_second": 37.971,
      "eval_steps_per_second": 19.106,
      "step": 9
    },
    {
      "epoch": 0.026972353337828724,
      "grad_norm": 0.18167784810066223,
      "learning_rate": 0.0002,
      "loss": 1.0861,
      "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": 632381604102144.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}