trainer_outputs/checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1156136192843517,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 1.0185,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 0.8649,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012,
      "loss": 0.7784,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016,
      "loss": 0.7386,
      "step": 80
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7037,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001990530303030303,
      "loss": 0.7019,
      "step": 120
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001981060606060606,
      "loss": 0.7117,
      "step": 140
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019715909090909094,
      "loss": 0.672,
      "step": 160
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019621212121212123,
      "loss": 0.664,
      "step": 180
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019526515151515152,
      "loss": 0.6666,
      "step": 200
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001943181818181818,
      "loss": 0.6685,
      "step": 220
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019337121212121213,
      "loss": 0.6788,
      "step": 240
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019242424242424245,
      "loss": 0.6673,
      "step": 260
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019147727272727274,
      "loss": 0.6628,
      "step": 280
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019053030303030303,
      "loss": 0.6643,
      "step": 300
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018958333333333332,
      "loss": 0.6607,
      "step": 320
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018863636363636364,
      "loss": 0.6706,
      "step": 340
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018768939393939396,
      "loss": 0.6709,
      "step": 360
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018674242424242425,
      "loss": 0.6616,
      "step": 380
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018579545454545454,
      "loss": 0.6566,
      "step": 400
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00018484848484848484,
      "loss": 0.6513,
      "step": 420
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00018390151515151518,
      "loss": 0.6797,
      "step": 440
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00018295454545454547,
      "loss": 0.6599,
      "step": 460
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00018200757575757577,
      "loss": 0.6561,
      "step": 480
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00018106060606060606,
      "loss": 0.662,
      "step": 500
    }
  ],
  "logging_steps": 20,
  "max_steps": 4324,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 7.92890273426473e+16,
  "trial_name": null,
  "trial_params": null
}