{
  "best_metric": 0.3089325428009033,
  "best_model_checkpoint": "./xlam_lora_new_ete_over_size_3epoch_multi_mix/checkpoint-205",
  "epoch": 0.33372335554764204,
  "eval_steps": 205,
  "global_step": 205,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016279188075494735,
      "grad_norm": 0.7572630643844604,
      "learning_rate": 2.688172043010753e-06,
      "loss": 0.5223,
      "step": 10
    },
    {
      "epoch": 0.03255837615098947,
      "grad_norm": 0.417061984539032,
      "learning_rate": 5.376344086021506e-06,
      "loss": 0.4858,
      "step": 20
    },
    {
      "epoch": 0.048837564226484206,
      "grad_norm": 0.3718095123767853,
      "learning_rate": 8.064516129032258e-06,
      "loss": 0.4246,
      "step": 30
    },
    {
      "epoch": 0.06511675230197894,
      "grad_norm": 0.2949349582195282,
      "learning_rate": 1.0752688172043012e-05,
      "loss": 0.4405,
      "step": 40
    },
    {
      "epoch": 0.08139594037747368,
      "grad_norm": 0.3159159719944,
      "learning_rate": 1.3440860215053763e-05,
      "loss": 0.4148,
      "step": 50
    },
    {
      "epoch": 0.09767512845296841,
      "grad_norm": 0.4167034327983856,
      "learning_rate": 1.6129032258064517e-05,
      "loss": 0.3393,
      "step": 60
    },
    {
      "epoch": 0.11395431652846315,
      "grad_norm": 0.39410400390625,
      "learning_rate": 1.881720430107527e-05,
      "loss": 0.2464,
      "step": 70
    },
    {
      "epoch": 0.13023350460395788,
      "grad_norm": 0.3644021153450012,
      "learning_rate": 2.1505376344086024e-05,
      "loss": 0.2294,
      "step": 80
    },
    {
      "epoch": 0.1465126926794526,
      "grad_norm": 0.30372634530067444,
      "learning_rate": 2.4193548387096777e-05,
      "loss": 0.2315,
      "step": 90
    },
    {
      "epoch": 0.16279188075494735,
      "grad_norm": 0.2586315870285034,
      "learning_rate": 2.4999011923655086e-05,
      "loss": 0.1932,
      "step": 100
    },
    {
      "epoch": 0.17907106883044208,
      "grad_norm": 0.37825971841812134,
      "learning_rate": 2.4994172742085852e-05,
      "loss": 0.2204,
      "step": 110
    },
    {
      "epoch": 0.19535025690593683,
      "grad_norm": 0.21422357857227325,
      "learning_rate": 2.4985302531208654e-05,
      "loss": 0.1795,
      "step": 120
    },
    {
      "epoch": 0.21162944498143155,
      "grad_norm": 0.2566869854927063,
      "learning_rate": 2.4972404152844008e-05,
      "loss": 0.1668,
      "step": 130
    },
    {
      "epoch": 0.2279086330569263,
      "grad_norm": 0.28194501996040344,
      "learning_rate": 2.49554817684312e-05,
      "loss": 0.1476,
      "step": 140
    },
    {
      "epoch": 0.24418782113242102,
      "grad_norm": 0.24139340221881866,
      "learning_rate": 2.4934540837685647e-05,
      "loss": 0.1609,
      "step": 150
    },
    {
      "epoch": 0.26046700920791577,
      "grad_norm": 0.3306334614753723,
      "learning_rate": 2.490958811683741e-05,
      "loss": 0.1638,
      "step": 160
    },
    {
      "epoch": 0.2767461972834105,
      "grad_norm": 0.27301114797592163,
      "learning_rate": 2.4880631656451447e-05,
      "loss": 0.1494,
      "step": 170
    },
    {
      "epoch": 0.2930253853589052,
      "grad_norm": 0.34037259221076965,
      "learning_rate": 2.484768079883018e-05,
      "loss": 0.1534,
      "step": 180
    },
    {
      "epoch": 0.30930457343439993,
      "grad_norm": 0.2306762933731079,
      "learning_rate": 2.4810746174999418e-05,
      "loss": 0.1749,
      "step": 190
    },
    {
      "epoch": 0.3255837615098947,
      "grad_norm": 0.3183388113975525,
      "learning_rate": 2.476983970127841e-05,
      "loss": 0.1482,
      "step": 200
    },
    {
      "epoch": 0.33372335554764204,
      "eval_loss": 0.3089325428009033,
      "eval_runtime": 34.8769,
      "eval_samples_per_second": 5.419,
      "eval_steps_per_second": 5.419,
      "step": 205
    }
  ],
  "logging_steps": 10,
  "max_steps": 1842,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 205,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7404062066376704e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}