{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04926108374384237,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0049261083743842365,
      "grad_norm": 30.4012393951416,
      "learning_rate": 2e-05,
      "loss": 16.8732,
      "step": 1
    },
    {
      "epoch": 0.0049261083743842365,
      "eval_loss": 15.000287055969238,
      "eval_runtime": 18.9652,
      "eval_samples_per_second": 4.535,
      "eval_steps_per_second": 2.267,
      "step": 1
    },
    {
      "epoch": 0.009852216748768473,
      "grad_norm": 33.68854522705078,
      "learning_rate": 4e-05,
      "loss": 12.3989,
      "step": 2
    },
    {
      "epoch": 0.014778325123152709,
      "grad_norm": 21.5296630859375,
      "learning_rate": 6e-05,
      "loss": 14.2884,
      "step": 3
    },
    {
      "epoch": 0.014778325123152709,
      "eval_loss": 14.733838081359863,
      "eval_runtime": 19.512,
      "eval_samples_per_second": 4.408,
      "eval_steps_per_second": 2.204,
      "step": 3
    },
    {
      "epoch": 0.019704433497536946,
      "grad_norm": 36.899383544921875,
      "learning_rate": 8e-05,
      "loss": 16.5783,
      "step": 4
    },
    {
      "epoch": 0.024630541871921183,
      "grad_norm": 28.822200775146484,
      "learning_rate": 0.0001,
      "loss": 14.9728,
      "step": 5
    },
    {
      "epoch": 0.029556650246305417,
      "grad_norm": 290.9329833984375,
      "learning_rate": 0.00012,
      "loss": 11.4899,
      "step": 6
    },
    {
      "epoch": 0.029556650246305417,
      "eval_loss": 9.435476303100586,
      "eval_runtime": 19.9616,
      "eval_samples_per_second": 4.308,
      "eval_steps_per_second": 2.154,
      "step": 6
    },
    {
      "epoch": 0.034482758620689655,
      "grad_norm": 33.94437789916992,
      "learning_rate": 0.00014,
      "loss": 8.6181,
      "step": 7
    },
    {
      "epoch": 0.03940886699507389,
      "grad_norm": 37.8486442565918,
      "learning_rate": 0.00016,
      "loss": 5.4599,
      "step": 8
    },
    {
      "epoch": 0.04433497536945813,
      "grad_norm": 33.13700485229492,
      "learning_rate": 0.00018,
      "loss": 3.997,
      "step": 9
    },
    {
      "epoch": 0.04433497536945813,
      "eval_loss": 2.348573684692383,
      "eval_runtime": 19.9544,
      "eval_samples_per_second": 4.31,
      "eval_steps_per_second": 2.155,
      "step": 9
    },
    {
      "epoch": 0.04926108374384237,
      "grad_norm": 14.288877487182617,
      "learning_rate": 0.0002,
      "loss": 2.7361,
      "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": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}