checkpoint-25/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 25.0,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.3065,
      "step": 1
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.3065,
      "step": 2
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0002,
      "loss": 0.3028,
      "step": 3
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.2954,
      "step": 4
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.2837,
      "step": 5
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00017272727272727275,
      "loss": 0.2706,
      "step": 6
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.2563,
      "step": 7
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.2414,
      "step": 8
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.2256,
      "step": 9
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.00013636363636363637,
      "loss": 0.2083,
      "step": 10
    },
    {
      "epoch": 11.0,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.1919,
      "step": 11
    },
    {
      "epoch": 12.0,
      "learning_rate": 0.0001181818181818182,
      "loss": 0.1825,
      "step": 12
    },
    {
      "epoch": 13.0,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.1766,
      "step": 13
    },
    {
      "epoch": 14.0,
      "learning_rate": 0.0001,
      "loss": 0.1706,
      "step": 14
    },
    {
      "epoch": 15.0,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.1648,
      "step": 15
    },
    {
      "epoch": 16.0,
      "learning_rate": 8.181818181818183e-05,
      "loss": 0.1591,
      "step": 16
    },
    {
      "epoch": 17.0,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.1541,
      "step": 17
    },
    {
      "epoch": 18.0,
      "learning_rate": 6.363636363636364e-05,
      "loss": 0.1492,
      "step": 18
    },
    {
      "epoch": 19.0,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.1448,
      "step": 19
    },
    {
      "epoch": 20.0,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.1407,
      "step": 20
    },
    {
      "epoch": 21.0,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.1373,
      "step": 21
    },
    {
      "epoch": 22.0,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.1343,
      "step": 22
    },
    {
      "epoch": 23.0,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.1319,
      "step": 23
    },
    {
      "epoch": 24.0,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.13,
      "step": 24
    },
    {
      "epoch": 25.0,
      "learning_rate": 0.0,
      "loss": 0.1287,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_train_epochs": 25,
  "save_steps": 500,
  "total_flos": 4064708395008000.0,
  "trial_name": null,
  "trial_params": null
}