checkpoint-2472/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 96.0,
  "eval_steps": 500,
  "global_step": 2472,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.15,
      "learning_rate": 0.000324,
      "loss": 1.6248,
      "step": 81
    },
    {
      "epoch": 6.29,
      "learning_rate": 0.000648,
      "loss": 1.5109,
      "step": 162
    },
    {
      "epoch": 9.44,
      "learning_rate": 0.000972,
      "loss": 1.4155,
      "step": 243
    },
    {
      "epoch": 12.58,
      "learning_rate": 0.0009671111111111112,
      "loss": 1.328,
      "step": 324
    },
    {
      "epoch": 15.73,
      "learning_rate": 0.0009311111111111112,
      "loss": 1.2665,
      "step": 405
    },
    {
      "epoch": 18.87,
      "learning_rate": 0.0008951111111111111,
      "loss": 1.2178,
      "step": 486
    },
    {
      "epoch": 22.02,
      "learning_rate": 0.0008591111111111112,
      "loss": 1.1829,
      "step": 567
    },
    {
      "epoch": 25.17,
      "learning_rate": 0.0008231111111111112,
      "loss": 1.1523,
      "step": 648
    },
    {
      "epoch": 28.31,
      "learning_rate": 0.0007871111111111111,
      "loss": 1.1296,
      "step": 729
    },
    {
      "epoch": 31.46,
      "learning_rate": 0.000751111111111111,
      "loss": 1.1084,
      "step": 810
    },
    {
      "epoch": 34.6,
      "learning_rate": 0.0007151111111111111,
      "loss": 1.0855,
      "step": 891
    },
    {
      "epoch": 37.75,
      "learning_rate": 0.0006791111111111111,
      "loss": 1.0708,
      "step": 972
    },
    {
      "epoch": 40.89,
      "learning_rate": 0.0006431111111111111,
      "loss": 1.0536,
      "step": 1053
    },
    {
      "epoch": 44.04,
      "learning_rate": 0.0006071111111111112,
      "loss": 1.0359,
      "step": 1134
    },
    {
      "epoch": 47.18,
      "learning_rate": 0.0005711111111111111,
      "loss": 1.0246,
      "step": 1215
    },
    {
      "epoch": 50.33,
      "learning_rate": 0.0005351111111111111,
      "loss": 1.0132,
      "step": 1296
    },
    {
      "epoch": 53.48,
      "learning_rate": 0.0004991111111111111,
      "loss": 1.0013,
      "step": 1377
    },
    {
      "epoch": 56.62,
      "learning_rate": 0.0004631111111111111,
      "loss": 0.9878,
      "step": 1458
    },
    {
      "epoch": 59.77,
      "learning_rate": 0.0004271111111111111,
      "loss": 0.9766,
      "step": 1539
    },
    {
      "epoch": 62.91,
      "learning_rate": 0.0003911111111111111,
      "loss": 0.9643,
      "step": 1620
    },
    {
      "epoch": 66.06,
      "learning_rate": 0.0003551111111111111,
      "loss": 0.9538,
      "step": 1701
    },
    {
      "epoch": 69.2,
      "learning_rate": 0.0003191111111111111,
      "loss": 0.9486,
      "step": 1782
    },
    {
      "epoch": 72.35,
      "learning_rate": 0.0002831111111111111,
      "loss": 0.9382,
      "step": 1863
    },
    {
      "epoch": 75.5,
      "learning_rate": 0.00024711111111111114,
      "loss": 0.9255,
      "step": 1944
    },
    {
      "epoch": 78.64,
      "learning_rate": 0.0002111111111111111,
      "loss": 0.9153,
      "step": 2025
    },
    {
      "epoch": 81.79,
      "learning_rate": 0.0001751111111111111,
      "loss": 0.9069,
      "step": 2106
    },
    {
      "epoch": 84.93,
      "learning_rate": 0.0001391111111111111,
      "loss": 0.8996,
      "step": 2187
    },
    {
      "epoch": 88.08,
      "learning_rate": 0.00010311111111111111,
      "loss": 0.888,
      "step": 2268
    },
    {
      "epoch": 91.22,
      "learning_rate": 6.71111111111111e-05,
      "loss": 0.8791,
      "step": 2349
    },
    {
      "epoch": 94.37,
      "learning_rate": 3.111111111111111e-05,
      "loss": 0.8721,
      "step": 2430
    }
  ],
  "logging_steps": 81,
  "max_steps": 2500,
  "num_train_epochs": 100,
  "save_steps": 500,
  "total_flos": 2.7673599172275077e+19,
  "trial_name": null,
  "trial_params": null
}