checkpoint-7462/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 26.0,
  "eval_steps": 500,
  "global_step": 7462,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.000484375,
      "loss": 2.8375,
      "step": 287
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00046875,
      "loss": 2.4263,
      "step": 574
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.000453125,
      "loss": 2.2043,
      "step": 861
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0004375,
      "loss": 2.0835,
      "step": 1148
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.000421875,
      "loss": 2.0225,
      "step": 1435
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00040625000000000004,
      "loss": 1.9901,
      "step": 1722
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.000390625,
      "loss": 1.9992,
      "step": 2009
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.000375,
      "loss": 1.9665,
      "step": 2296
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.000359375,
      "loss": 1.943,
      "step": 2583
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.00034375,
      "loss": 1.9327,
      "step": 2870
    },
    {
      "epoch": 11.0,
      "learning_rate": 0.000328125,
      "loss": 1.9184,
      "step": 3157
    },
    {
      "epoch": 12.0,
      "learning_rate": 0.0003125,
      "loss": 1.9191,
      "step": 3444
    },
    {
      "epoch": 13.0,
      "learning_rate": 0.000296875,
      "loss": 1.9074,
      "step": 3731
    },
    {
      "epoch": 14.0,
      "learning_rate": 0.00028125000000000003,
      "loss": 1.9066,
      "step": 4018
    },
    {
      "epoch": 15.0,
      "learning_rate": 0.000265625,
      "loss": 1.9053,
      "step": 4305
    },
    {
      "epoch": 16.0,
      "learning_rate": 0.00025,
      "loss": 1.8906,
      "step": 4592
    },
    {
      "epoch": 17.0,
      "learning_rate": 0.000234375,
      "loss": 1.8876,
      "step": 4879
    },
    {
      "epoch": 18.0,
      "learning_rate": 0.00021875,
      "loss": 1.8837,
      "step": 5166
    },
    {
      "epoch": 19.0,
      "learning_rate": 0.00020312500000000002,
      "loss": 1.8766,
      "step": 5453
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.0001875,
      "loss": 1.8701,
      "step": 5740
    },
    {
      "epoch": 21.0,
      "learning_rate": 0.000171875,
      "loss": 1.8698,
      "step": 6027
    },
    {
      "epoch": 22.0,
      "learning_rate": 0.00015625,
      "loss": 1.8713,
      "step": 6314
    },
    {
      "epoch": 23.0,
      "learning_rate": 0.00014062500000000002,
      "loss": 1.8756,
      "step": 6601
    },
    {
      "epoch": 24.0,
      "learning_rate": 0.000125,
      "loss": 1.8628,
      "step": 6888
    },
    {
      "epoch": 25.0,
      "learning_rate": 0.000109375,
      "loss": 1.8646,
      "step": 7175
    },
    {
      "epoch": 26.0,
      "learning_rate": 9.375e-05,
      "loss": 1.8658,
      "step": 7462
    }
  ],
  "logging_steps": 500,
  "max_steps": 9184,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 32,
  "save_steps": 500,
  "total_flos": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}