{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10230179028132992,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010230179028132993,
      "grad_norm": 2.7847933769226074,
      "learning_rate": 2e-05,
      "loss": 5.6948,
      "step": 1
    },
    {
      "epoch": 0.010230179028132993,
      "eval_loss": 1.5982179641723633,
      "eval_runtime": 1.2155,
      "eval_samples_per_second": 34.554,
      "eval_steps_per_second": 17.277,
      "step": 1
    },
    {
      "epoch": 0.020460358056265986,
      "grad_norm": 2.1262452602386475,
      "learning_rate": 4e-05,
      "loss": 4.845,
      "step": 2
    },
    {
      "epoch": 0.030690537084398978,
      "grad_norm": 4.10209846496582,
      "learning_rate": 6e-05,
      "loss": 7.2068,
      "step": 3
    },
    {
      "epoch": 0.030690537084398978,
      "eval_loss": 1.5947189331054688,
      "eval_runtime": 1.2162,
      "eval_samples_per_second": 34.533,
      "eval_steps_per_second": 17.266,
      "step": 3
    },
    {
      "epoch": 0.04092071611253197,
      "grad_norm": 3.0207631587982178,
      "learning_rate": 8e-05,
      "loss": 6.4761,
      "step": 4
    },
    {
      "epoch": 0.05115089514066496,
      "grad_norm": 3.253593921661377,
      "learning_rate": 0.0001,
      "loss": 7.345,
      "step": 5
    },
    {
      "epoch": 0.061381074168797956,
      "grad_norm": 2.768976926803589,
      "learning_rate": 0.00012,
      "loss": 6.8946,
      "step": 6
    },
    {
      "epoch": 0.061381074168797956,
      "eval_loss": 1.5658289194107056,
      "eval_runtime": 1.2233,
      "eval_samples_per_second": 34.333,
      "eval_steps_per_second": 17.167,
      "step": 6
    },
    {
      "epoch": 0.07161125319693094,
      "grad_norm": 4.019915580749512,
      "learning_rate": 0.00014,
      "loss": 6.9505,
      "step": 7
    },
    {
      "epoch": 0.08184143222506395,
      "grad_norm": 3.614354133605957,
      "learning_rate": 0.00016,
      "loss": 4.8266,
      "step": 8
    },
    {
      "epoch": 0.09207161125319693,
      "grad_norm": 3.3476078510284424,
      "learning_rate": 0.00018,
      "loss": 6.4537,
      "step": 9
    },
    {
      "epoch": 0.09207161125319693,
      "eval_loss": 1.4482439756393433,
      "eval_runtime": 1.2516,
      "eval_samples_per_second": 33.557,
      "eval_steps_per_second": 16.779,
      "step": 9
    },
    {
      "epoch": 0.10230179028132992,
      "grad_norm": 2.8636763095855713,
      "learning_rate": 0.0002,
      "loss": 5.1632,
      "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": 917953377730560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}