trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06474820143884892,
  "eval_steps": 500,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.5345,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018947368421052632,
      "loss": 1.3349,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00017894736842105264,
      "loss": 1.1777,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016842105263157895,
      "loss": 1.4423,
      "step": 4
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00015789473684210527,
      "loss": 1.608,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00014736842105263158,
      "loss": 1.2715,
      "step": 6
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001368421052631579,
      "loss": 1.2625,
      "step": 7
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001263157894736842,
      "loss": 1.2287,
      "step": 8
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011578947368421053,
      "loss": 1.1866,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_train_epochs": 1,
  "save_steps": 1,
  "total_flos": 551832832696320.0,
  "trial_name": null,
  "trial_params": null
}