checkpoint-30/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 29.333333333333332,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.33,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.4717,
      "step": 1
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.4717,
      "step": 2
    },
    {
      "epoch": 2.33,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.4497,
      "step": 3
    },
    {
      "epoch": 3.33,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.4049,
      "step": 4
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.00011111111111111112,
      "loss": 1.3354,
      "step": 5
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.2413,
      "step": 6
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.1378,
      "step": 7
    },
    {
      "epoch": 7.33,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.0309,
      "step": 8
    },
    {
      "epoch": 8.33,
      "learning_rate": 0.0002,
      "loss": 0.9263,
      "step": 9
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.00019753086419753085,
      "loss": 0.8314,
      "step": 10
    },
    {
      "epoch": 10.33,
      "learning_rate": 0.00019506172839506175,
      "loss": 0.7409,
      "step": 11
    },
    {
      "epoch": 11.33,
      "learning_rate": 0.0001925925925925926,
      "loss": 0.6599,
      "step": 12
    },
    {
      "epoch": 12.33,
      "learning_rate": 0.00019012345679012346,
      "loss": 0.581,
      "step": 13
    },
    {
      "epoch": 13.33,
      "learning_rate": 0.00018765432098765433,
      "loss": 0.4985,
      "step": 14
    },
    {
      "epoch": 14.33,
      "learning_rate": 0.0001851851851851852,
      "loss": 0.4184,
      "step": 15
    },
    {
      "epoch": 15.33,
      "learning_rate": 0.00018271604938271605,
      "loss": 0.3421,
      "step": 16
    },
    {
      "epoch": 16.33,
      "learning_rate": 0.00018024691358024692,
      "loss": 0.271,
      "step": 17
    },
    {
      "epoch": 17.33,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.2084,
      "step": 18
    },
    {
      "epoch": 18.33,
      "learning_rate": 0.00017530864197530866,
      "loss": 0.1555,
      "step": 19
    },
    {
      "epoch": 19.33,
      "learning_rate": 0.0001728395061728395,
      "loss": 0.1131,
      "step": 20
    },
    {
      "epoch": 20.33,
      "learning_rate": 0.00017037037037037037,
      "loss": 0.0872,
      "step": 21
    },
    {
      "epoch": 21.33,
      "learning_rate": 0.00016790123456790124,
      "loss": 0.0698,
      "step": 22
    },
    {
      "epoch": 22.33,
      "learning_rate": 0.0001654320987654321,
      "loss": 0.0578,
      "step": 23
    },
    {
      "epoch": 23.33,
      "learning_rate": 0.00016296296296296295,
      "loss": 0.0485,
      "step": 24
    },
    {
      "epoch": 24.33,
      "learning_rate": 0.00016049382716049385,
      "loss": 0.0412,
      "step": 25
    },
    {
      "epoch": 25.33,
      "learning_rate": 0.0001580246913580247,
      "loss": 0.0327,
      "step": 26
    },
    {
      "epoch": 26.33,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.0264,
      "step": 27
    },
    {
      "epoch": 27.33,
      "learning_rate": 0.0001530864197530864,
      "loss": 0.0202,
      "step": 28
    },
    {
      "epoch": 28.33,
      "learning_rate": 0.0001506172839506173,
      "loss": 0.0155,
      "step": 29
    },
    {
      "epoch": 29.33,
      "learning_rate": 0.00014814814814814815,
      "loss": 0.0137,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 90,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 2623786293657600.0,
  "trial_name": null,
  "trial_params": null
}