checkpoint-250/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14885382554331647,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.0759,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.7538,
      "step": 100
    },
    {
      "epoch": 0.09,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.68,
      "step": 150
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.6428,
      "step": 200
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0,
      "loss": 0.6344,
      "step": 250
    }
  ],
  "logging_steps": 50,
  "max_steps": 250,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 713584116301824.0,
  "trial_name": null,
  "trial_params": null
}