last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.025789813023855575,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010315925209542231,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0010315925209542231,
      "eval_loss": NaN,
      "eval_runtime": 87.2879,
      "eval_samples_per_second": 9.36,
      "eval_steps_per_second": 4.686,
      "step": 1
    },
    {
      "epoch": 0.0020631850419084463,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.003094777562862669,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0041263700838168925,
      "grad_norm": NaN,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0051579626047711154,
      "grad_norm": NaN,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.006189555125725338,
      "grad_norm": NaN,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.007221147646679561,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.008252740167633785,
      "grad_norm": NaN,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.009284332688588007,
      "grad_norm": NaN,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.010315925209542231,
      "grad_norm": NaN,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.011347517730496455,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.012379110251450677,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0134107027724049,
      "grad_norm": NaN,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.014442295293359123,
      "grad_norm": NaN,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.015473887814313346,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.01650548033526757,
      "grad_norm": NaN,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.017537072856221792,
      "grad_norm": NaN,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.018568665377176014,
      "grad_norm": NaN,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.01960025789813024,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.020631850419084462,
      "grad_norm": NaN,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.021663442940038684,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.02269503546099291,
      "grad_norm": NaN,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.02372662798194713,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.024758220502901353,
      "grad_norm": NaN,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.025789813023855575,
      "grad_norm": NaN,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.025789813023855575,
      "eval_loss": NaN,
      "eval_runtime": 86.4085,
      "eval_samples_per_second": 9.455,
      "eval_steps_per_second": 4.733,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.53626736295936e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}