trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.987012987012987,
  "eval_steps": 500,
  "global_step": 19,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 0.17318853735923767,
      "learning_rate": 9.931806517013612e-06,
      "loss": 0.2793,
      "step": 1
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 0.16861183941364288,
      "learning_rate": 9.729086208503174e-06,
      "loss": 0.2526,
      "step": 2
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 0.20030151307582855,
      "learning_rate": 9.397368756032445e-06,
      "loss": 0.314,
      "step": 3
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 0.1905766725540161,
      "learning_rate": 8.94570254698197e-06,
      "loss": 0.3651,
      "step": 4
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 0.18305057287216187,
      "learning_rate": 8.386407858128707e-06,
      "loss": 0.2511,
      "step": 5
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 0.1884309947490692,
      "learning_rate": 7.734740790612137e-06,
      "loss": 0.3179,
      "step": 6
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.197285994887352,
      "learning_rate": 7.008477123264849e-06,
      "loss": 0.3045,
      "step": 7
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.2820747494697571,
      "learning_rate": 6.227427435703997e-06,
      "loss": 0.2897,
      "step": 8
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 0.17939220368862152,
      "learning_rate": 5.412896727361663e-06,
      "loss": 0.3061,
      "step": 9
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.18881358206272125,
      "learning_rate": 4.587103272638339e-06,
      "loss": 0.2938,
      "step": 10
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.18471910059452057,
      "learning_rate": 3.7725725642960047e-06,
      "loss": 0.2933,
      "step": 11
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 0.16619093716144562,
      "learning_rate": 2.991522876735154e-06,
      "loss": 0.2563,
      "step": 12
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 0.17355136573314667,
      "learning_rate": 2.265259209387867e-06,
      "loss": 0.2928,
      "step": 13
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.1705784648656845,
      "learning_rate": 1.6135921418712959e-06,
      "loss": 0.3275,
      "step": 14
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 0.16323448717594147,
      "learning_rate": 1.0542974530180327e-06,
      "loss": 0.2644,
      "step": 15
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 0.17525160312652588,
      "learning_rate": 6.026312439675553e-07,
      "loss": 0.2977,
      "step": 16
    },
    {
      "epoch": 0.8831168831168831,
      "grad_norm": 0.1585198938846588,
      "learning_rate": 2.7091379149682683e-07,
      "loss": 0.2762,
      "step": 17
    },
    {
      "epoch": 0.935064935064935,
      "grad_norm": 0.16804182529449463,
      "learning_rate": 6.819348298638839e-08,
      "loss": 0.3112,
      "step": 18
    },
    {
      "epoch": 0.987012987012987,
      "grad_norm": 0.1660885363817215,
      "learning_rate": 0.0,
      "loss": 0.3045,
      "step": 19
    }
  ],
  "logging_steps": 1,
  "max_steps": 19,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8521915203190784e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}