{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001036833510459058,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010368335104590581,
      "grad_norm": 3.0146021842956543,
      "learning_rate": 2e-05,
      "loss": 4.447,
      "step": 1
    },
    {
      "epoch": 0.00010368335104590581,
      "eval_loss": 5.926819801330566,
      "eval_runtime": 128.2259,
      "eval_samples_per_second": 31.671,
      "eval_steps_per_second": 15.839,
      "step": 1
    },
    {
      "epoch": 0.00020736670209181162,
      "grad_norm": 2.991119861602783,
      "learning_rate": 4e-05,
      "loss": 4.0703,
      "step": 2
    },
    {
      "epoch": 0.0003110500531377174,
      "grad_norm": 5.3986358642578125,
      "learning_rate": 6e-05,
      "loss": 6.7141,
      "step": 3
    },
    {
      "epoch": 0.0003110500531377174,
      "eval_loss": 5.904901504516602,
      "eval_runtime": 126.5778,
      "eval_samples_per_second": 32.083,
      "eval_steps_per_second": 16.045,
      "step": 3
    },
    {
      "epoch": 0.00041473340418362323,
      "grad_norm": 5.413496494293213,
      "learning_rate": 8e-05,
      "loss": 7.6944,
      "step": 4
    },
    {
      "epoch": 0.000518416755229529,
      "grad_norm": 5.264546871185303,
      "learning_rate": 0.0001,
      "loss": 6.1945,
      "step": 5
    },
    {
      "epoch": 0.0006221001062754348,
      "grad_norm": 5.025759696960449,
      "learning_rate": 0.00012,
      "loss": 4.8205,
      "step": 6
    },
    {
      "epoch": 0.0006221001062754348,
      "eval_loss": 5.456394195556641,
      "eval_runtime": 126.5948,
      "eval_samples_per_second": 32.079,
      "eval_steps_per_second": 16.043,
      "step": 6
    },
    {
      "epoch": 0.0007257834573213407,
      "grad_norm": 6.551008701324463,
      "learning_rate": 0.00014,
      "loss": 5.2372,
      "step": 7
    },
    {
      "epoch": 0.0008294668083672465,
      "grad_norm": 6.6202521324157715,
      "learning_rate": 0.00016,
      "loss": 4.5064,
      "step": 8
    },
    {
      "epoch": 0.0009331501594131523,
      "grad_norm": 9.594223022460938,
      "learning_rate": 0.00018,
      "loss": 4.7458,
      "step": 9
    },
    {
      "epoch": 0.0009331501594131523,
      "eval_loss": 3.6891896724700928,
      "eval_runtime": 126.5673,
      "eval_samples_per_second": 32.086,
      "eval_steps_per_second": 16.047,
      "step": 9
    },
    {
      "epoch": 0.001036833510459058,
      "grad_norm": 8.852412223815918,
      "learning_rate": 0.0002,
      "loss": 3.6755,
      "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": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}