checkpoint-235/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 235,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.77,
      "learning_rate": 0.0005454545454545455,
      "loss": 1.1356,
      "step": 9
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.001090909090909091,
      "loss": 0.707,
      "step": 18
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0016363636363636365,
      "loss": 0.4786,
      "step": 27
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.00197979797979798,
      "loss": 0.3701,
      "step": 36
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0019191919191919192,
      "loss": 0.3513,
      "step": 45
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0018585858585858585,
      "loss": 0.2933,
      "step": 54
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.001797979797979798,
      "loss": 0.2733,
      "step": 63
    },
    {
      "epoch": 6.13,
      "learning_rate": 0.0017373737373737375,
      "loss": 0.2281,
      "step": 72
    },
    {
      "epoch": 6.89,
      "learning_rate": 0.0016767676767676766,
      "loss": 0.1794,
      "step": 81
    },
    {
      "epoch": 7.66,
      "learning_rate": 0.0016161616161616162,
      "loss": 0.15,
      "step": 90
    },
    {
      "epoch": 8.43,
      "learning_rate": 0.0015555555555555557,
      "loss": 0.1268,
      "step": 99
    },
    {
      "epoch": 9.19,
      "learning_rate": 0.001494949494949495,
      "loss": 0.1058,
      "step": 108
    },
    {
      "epoch": 9.96,
      "learning_rate": 0.0014343434343434343,
      "loss": 0.091,
      "step": 117
    },
    {
      "epoch": 10.72,
      "learning_rate": 0.0013737373737373738,
      "loss": 0.0752,
      "step": 126
    },
    {
      "epoch": 11.49,
      "learning_rate": 0.0013131313131313131,
      "loss": 0.07,
      "step": 135
    },
    {
      "epoch": 12.26,
      "learning_rate": 0.0012525252525252527,
      "loss": 0.0628,
      "step": 144
    },
    {
      "epoch": 13.02,
      "learning_rate": 0.0011919191919191917,
      "loss": 0.0569,
      "step": 153
    },
    {
      "epoch": 13.79,
      "learning_rate": 0.0011313131313131313,
      "loss": 0.0447,
      "step": 162
    },
    {
      "epoch": 14.55,
      "learning_rate": 0.0010707070707070708,
      "loss": 0.0399,
      "step": 171
    },
    {
      "epoch": 15.32,
      "learning_rate": 0.00101010101010101,
      "loss": 0.0355,
      "step": 180
    },
    {
      "epoch": 16.09,
      "learning_rate": 0.0009494949494949495,
      "loss": 0.0307,
      "step": 189
    },
    {
      "epoch": 16.85,
      "learning_rate": 0.0008888888888888888,
      "loss": 0.0253,
      "step": 198
    },
    {
      "epoch": 17.62,
      "learning_rate": 0.0008282828282828283,
      "loss": 0.021,
      "step": 207
    },
    {
      "epoch": 18.38,
      "learning_rate": 0.0007676767676767677,
      "loss": 0.0187,
      "step": 216
    },
    {
      "epoch": 19.15,
      "learning_rate": 0.0007070707070707071,
      "loss": 0.0157,
      "step": 225
    },
    {
      "epoch": 19.91,
      "learning_rate": 0.0006464646464646465,
      "loss": 0.013,
      "step": 234
    }
  ],
  "logging_steps": 9,
  "max_steps": 330,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 6.559465734144e+17,
  "trial_name": null,
  "trial_params": null
}