{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008429393294417634,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.429393294417634e-05,
      "grad_norm": 1.0564179420471191,
      "learning_rate": 2e-05,
      "loss": 2.5552,
      "step": 1
    },
    {
      "epoch": 8.429393294417634e-05,
      "eval_loss": 2.3914594650268555,
      "eval_runtime": 323.4866,
      "eval_samples_per_second": 15.441,
      "eval_steps_per_second": 7.722,
      "step": 1
    },
    {
      "epoch": 0.00016858786588835268,
      "grad_norm": 0.9427396655082703,
      "learning_rate": 4e-05,
      "loss": 2.0446,
      "step": 2
    },
    {
      "epoch": 0.00025288179883252904,
      "grad_norm": 0.834418773651123,
      "learning_rate": 6e-05,
      "loss": 2.331,
      "step": 3
    },
    {
      "epoch": 0.00025288179883252904,
      "eval_loss": 2.3892970085144043,
      "eval_runtime": 296.7845,
      "eval_samples_per_second": 16.83,
      "eval_steps_per_second": 8.417,
      "step": 3
    },
    {
      "epoch": 0.00033717573177670536,
      "grad_norm": 0.7369904518127441,
      "learning_rate": 8e-05,
      "loss": 2.0951,
      "step": 4
    },
    {
      "epoch": 0.0004214696647208817,
      "grad_norm": 0.8369784355163574,
      "learning_rate": 0.0001,
      "loss": 2.3672,
      "step": 5
    },
    {
      "epoch": 0.0005057635976650581,
      "grad_norm": 0.9448137283325195,
      "learning_rate": 0.00012,
      "loss": 1.8704,
      "step": 6
    },
    {
      "epoch": 0.0005057635976650581,
      "eval_loss": 2.316589593887329,
      "eval_runtime": 317.5688,
      "eval_samples_per_second": 15.729,
      "eval_steps_per_second": 7.866,
      "step": 6
    },
    {
      "epoch": 0.0005900575306092345,
      "grad_norm": 1.3330564498901367,
      "learning_rate": 0.00014,
      "loss": 2.7357,
      "step": 7
    },
    {
      "epoch": 0.0006743514635534107,
      "grad_norm": 1.364074468612671,
      "learning_rate": 0.00016,
      "loss": 1.8772,
      "step": 8
    },
    {
      "epoch": 0.0007586453964975871,
      "grad_norm": 1.657910943031311,
      "learning_rate": 0.00018,
      "loss": 2.183,
      "step": 9
    },
    {
      "epoch": 0.0007586453964975871,
      "eval_loss": 1.8471567630767822,
      "eval_runtime": 297.6329,
      "eval_samples_per_second": 16.782,
      "eval_steps_per_second": 8.393,
      "step": 9
    },
    {
      "epoch": 0.0008429393294417634,
      "grad_norm": 1.7984774112701416,
      "learning_rate": 0.0002,
      "loss": 2.0832,
      "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": 1742636046090240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}