checkpoint-40/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 39.25,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.25,
      "learning_rate": 2.5e-05,
      "loss": 1.305,
      "step": 2
    },
    {
      "epoch": 3.25,
      "learning_rate": 5e-05,
      "loss": 1.2911,
      "step": 4
    },
    {
      "epoch": 5.25,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2513,
      "step": 6
    },
    {
      "epoch": 7.25,
      "learning_rate": 0.0001,
      "loss": 1.1854,
      "step": 8
    },
    {
      "epoch": 9.25,
      "learning_rate": 0.000125,
      "loss": 1.09,
      "step": 10
    },
    {
      "epoch": 11.25,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.9929,
      "step": 12
    },
    {
      "epoch": 13.25,
      "learning_rate": 0.000175,
      "loss": 0.9166,
      "step": 14
    },
    {
      "epoch": 15.25,
      "learning_rate": 0.0002,
      "loss": 0.8551,
      "step": 16
    },
    {
      "epoch": 17.25,
      "learning_rate": 0.00019722222222222225,
      "loss": 0.7925,
      "step": 18
    },
    {
      "epoch": 19.25,
      "learning_rate": 0.00019444444444444446,
      "loss": 0.7263,
      "step": 20
    },
    {
      "epoch": 21.25,
      "learning_rate": 0.00019166666666666667,
      "loss": 0.6448,
      "step": 22
    },
    {
      "epoch": 23.25,
      "learning_rate": 0.00018888888888888888,
      "loss": 0.5356,
      "step": 24
    },
    {
      "epoch": 25.25,
      "learning_rate": 0.00018611111111111112,
      "loss": 0.4362,
      "step": 26
    },
    {
      "epoch": 27.25,
      "learning_rate": 0.00018333333333333334,
      "loss": 0.3425,
      "step": 28
    },
    {
      "epoch": 29.25,
      "learning_rate": 0.00018055555555555557,
      "loss": 0.2636,
      "step": 30
    },
    {
      "epoch": 31.25,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.1984,
      "step": 32
    },
    {
      "epoch": 33.25,
      "learning_rate": 0.000175,
      "loss": 0.1303,
      "step": 34
    },
    {
      "epoch": 35.25,
      "learning_rate": 0.00017222222222222224,
      "loss": 0.081,
      "step": 36
    },
    {
      "epoch": 37.25,
      "learning_rate": 0.00016944444444444445,
      "loss": 0.0457,
      "step": 38
    },
    {
      "epoch": 39.25,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.0268,
      "step": 40
    }
  ],
  "logging_steps": 2,
  "max_steps": 160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 500,
  "total_flos": 3251764702740480.0,
  "trial_name": null,
  "trial_params": null
}