trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04576659038901602,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.00019292929292929293,
      "loss": 2.0259,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018282828282828283,
      "loss": 1.4961,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017272727272727275,
      "loss": 1.3953,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016262626262626264,
      "loss": 1.3234,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015252525252525253,
      "loss": 1.4601,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014242424242424243,
      "loss": 1.3362,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013232323232323235,
      "loss": 1.3905,
      "step": 70
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012222222222222224,
      "loss": 1.3132,
      "step": 80
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011212121212121212,
      "loss": 1.2767,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010202020202020202,
      "loss": 1.3303,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.191919191919192e-05,
      "loss": 1.3685,
      "step": 110
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.181818181818183e-05,
      "loss": 1.335,
      "step": 120
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.171717171717171e-05,
      "loss": 1.3122,
      "step": 130
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.161616161616162e-05,
      "loss": 1.2693,
      "step": 140
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.151515151515152e-05,
      "loss": 1.2069,
      "step": 150
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.141414141414142e-05,
      "loss": 1.2302,
      "step": 160
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.131313131313132e-05,
      "loss": 1.2451,
      "step": 170
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.1212121212121215e-05,
      "loss": 1.2993,
      "step": 180
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 1.2968,
      "step": 190
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.0101010101010103e-06,
      "loss": 1.2567,
      "step": 200
    },
    {
      "epoch": 0.05,
      "step": 200,
      "total_flos": 1428558744158208.0,
      "train_loss": 1.3583835124969483,
      "train_runtime": 1540.4432,
      "train_samples_per_second": 0.519,
      "train_steps_per_second": 0.13
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1428558744158208.0,
  "trial_name": null,
  "trial_params": null
}