{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011927836588638736,
  "eval_steps": 2,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005963918294319368,
      "grad_norm": 1.5163764953613281,
      "learning_rate": 2e-05,
      "loss": 0.9264,
      "step": 1
    },
    {
      "epoch": 0.0005963918294319368,
      "eval_loss": 0.988461434841156,
      "eval_runtime": 77.0662,
      "eval_samples_per_second": 9.161,
      "eval_steps_per_second": 4.58,
      "step": 1
    },
    {
      "epoch": 0.0011927836588638736,
      "grad_norm": 1.2068827152252197,
      "learning_rate": 4e-05,
      "loss": 0.8253,
      "step": 2
    },
    {
      "epoch": 0.0011927836588638736,
      "eval_loss": 0.9857558012008667,
      "eval_runtime": 76.5737,
      "eval_samples_per_second": 9.22,
      "eval_steps_per_second": 4.61,
      "step": 2
    },
    {
      "epoch": 0.0017891754882958103,
      "grad_norm": 1.454573631286621,
      "learning_rate": 6e-05,
      "loss": 0.901,
      "step": 3
    },
    {
      "epoch": 0.0023855673177277472,
      "grad_norm": 1.681971788406372,
      "learning_rate": 8e-05,
      "loss": 1.0454,
      "step": 4
    },
    {
      "epoch": 0.0023855673177277472,
      "eval_loss": 0.9374808073043823,
      "eval_runtime": 76.5425,
      "eval_samples_per_second": 9.224,
      "eval_steps_per_second": 4.612,
      "step": 4
    },
    {
      "epoch": 0.002981959147159684,
      "grad_norm": 1.7881622314453125,
      "learning_rate": 0.0001,
      "loss": 0.8865,
      "step": 5
    },
    {
      "epoch": 0.0035783509765916206,
      "grad_norm": 1.8039438724517822,
      "learning_rate": 0.00012,
      "loss": 0.8906,
      "step": 6
    },
    {
      "epoch": 0.0035783509765916206,
      "eval_loss": 0.7199013829231262,
      "eval_runtime": 76.5601,
      "eval_samples_per_second": 9.222,
      "eval_steps_per_second": 4.611,
      "step": 6
    },
    {
      "epoch": 0.004174742806023557,
      "grad_norm": 1.78489351272583,
      "learning_rate": 0.00014,
      "loss": 0.8658,
      "step": 7
    },
    {
      "epoch": 0.0047711346354554944,
      "grad_norm": 1.3335764408111572,
      "learning_rate": 0.00016,
      "loss": 0.5989,
      "step": 8
    },
    {
      "epoch": 0.0047711346354554944,
      "eval_loss": 0.45117324590682983,
      "eval_runtime": 76.584,
      "eval_samples_per_second": 9.219,
      "eval_steps_per_second": 4.609,
      "step": 8
    },
    {
      "epoch": 0.005367526464887431,
      "grad_norm": 1.000693440437317,
      "learning_rate": 0.00018,
      "loss": 0.4353,
      "step": 9
    },
    {
      "epoch": 0.005963918294319368,
      "grad_norm": 0.9320959448814392,
      "learning_rate": 0.0002,
      "loss": 0.4002,
      "step": 10
    },
    {
      "epoch": 0.005963918294319368,
      "eval_loss": 0.33094078302383423,
      "eval_runtime": 76.5684,
      "eval_samples_per_second": 9.221,
      "eval_steps_per_second": 4.61,
      "step": 10
    },
    {
      "epoch": 0.006560310123751305,
      "grad_norm": 1.0968209505081177,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.5539,
      "step": 11
    },
    {
      "epoch": 0.007156701953183241,
      "grad_norm": 0.8019706010818481,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.2537,
      "step": 12
    },
    {
      "epoch": 0.007156701953183241,
      "eval_loss": 0.24521681666374207,
      "eval_runtime": 76.5378,
      "eval_samples_per_second": 9.224,
      "eval_steps_per_second": 4.612,
      "step": 12
    },
    {
      "epoch": 0.007753093782615178,
      "grad_norm": 0.8972131609916687,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.188,
      "step": 13
    },
    {
      "epoch": 0.008349485612047115,
      "grad_norm": 1.388610601425171,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.2539,
      "step": 14
    },
    {
      "epoch": 0.008349485612047115,
      "eval_loss": 0.20003721117973328,
      "eval_runtime": 76.5695,
      "eval_samples_per_second": 9.22,
      "eval_steps_per_second": 4.61,
      "step": 14
    },
    {
      "epoch": 0.008945877441479051,
      "grad_norm": 1.2546236515045166,
      "learning_rate": 0.0001,
      "loss": 0.2859,
      "step": 15
    },
    {
      "epoch": 0.009542269270910989,
      "grad_norm": 1.2586054801940918,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.2893,
      "step": 16
    },
    {
      "epoch": 0.009542269270910989,
      "eval_loss": 0.17982345819473267,
      "eval_runtime": 76.5392,
      "eval_samples_per_second": 9.224,
      "eval_steps_per_second": 4.612,
      "step": 16
    },
    {
      "epoch": 0.010138661100342925,
      "grad_norm": 1.4489102363586426,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.1875,
      "step": 17
    },
    {
      "epoch": 0.010735052929774861,
      "grad_norm": 1.0019066333770752,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0675,
      "step": 18
    },
    {
      "epoch": 0.010735052929774861,
      "eval_loss": 0.15851947665214539,
      "eval_runtime": 76.5776,
      "eval_samples_per_second": 9.219,
      "eval_steps_per_second": 4.61,
      "step": 18
    },
    {
      "epoch": 0.0113314447592068,
      "grad_norm": 0.7860324382781982,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.1514,
      "step": 19
    },
    {
      "epoch": 0.011927836588638736,
      "grad_norm": 0.9038301110267639,
      "learning_rate": 0.0,
      "loss": 0.178,
      "step": 20
    },
    {
      "epoch": 0.011927836588638736,
      "eval_loss": 0.1537449210882187,
      "eval_runtime": 76.5787,
      "eval_samples_per_second": 9.219,
      "eval_steps_per_second": 4.61,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.31825833869312e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}