{
  "best_metric": 0.29123440384864807,
  "best_model_checkpoint": "saves/Llama-3.1-8B-Instruct/lora/sft-200/checkpoint-100",
  "epoch": 9.777777777777779,
  "eval_steps": 50,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 7.0752716064453125,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 1.6893,
      "step": 10
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 3.9827725887298584,
      "learning_rate": 4.938574467213519e-06,
      "loss": 1.4995,
      "step": 20
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 3.5237555503845215,
      "learning_rate": 4.644958533087443e-06,
      "loss": 1.2725,
      "step": 30
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 2.8591604232788086,
      "learning_rate": 4.137151834863213e-06,
      "loss": 0.9973,
      "step": 40
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 3.0029361248016357,
      "learning_rate": 3.4658628142328215e-06,
      "loss": 0.7576,
      "step": 50
    },
    {
      "epoch": 4.444444444444445,
      "eval_loss": 0.6173266172409058,
      "eval_runtime": 0.5267,
      "eval_samples_per_second": 37.97,
      "eval_steps_per_second": 18.985,
      "step": 50
    },
    {
      "epoch": 5.333333333333333,
      "grad_norm": 3.8220601081848145,
      "learning_rate": 2.6981248921419713e-06,
      "loss": 0.6908,
      "step": 60
    },
    {
      "epoch": 6.222222222222222,
      "grad_norm": 3.00999116897583,
      "learning_rate": 1.9106026612264316e-06,
      "loss": 0.5395,
      "step": 70
    },
    {
      "epoch": 7.111111111111111,
      "grad_norm": 2.473998546600342,
      "learning_rate": 1.181936330973744e-06,
      "loss": 0.4238,
      "step": 80
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.002608060836792,
      "learning_rate": 5.848888922025553e-07,
      "loss": 0.3945,
      "step": 90
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 2.675635576248169,
      "learning_rate": 1.790801674598186e-07,
      "loss": 0.3664,
      "step": 100
    },
    {
      "epoch": 8.88888888888889,
      "eval_loss": 0.29123440384864807,
      "eval_runtime": 0.5321,
      "eval_samples_per_second": 37.586,
      "eval_steps_per_second": 18.793,
      "step": 100
    },
    {
      "epoch": 9.777777777777779,
      "grad_norm": 2.5628325939178467,
      "learning_rate": 5.033308820289185e-09,
      "loss": 0.3717,
      "step": 110
    },
    {
      "epoch": 9.777777777777779,
      "step": 110,
      "total_flos": 1.002088129757184e+16,
      "train_loss": 0.8184320038015193,
      "train_runtime": 152.2376,
      "train_samples_per_second": 11.824,
      "train_steps_per_second": 0.723
    }
  ],
  "logging_steps": 10,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.002088129757184e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}