checkpoint-250/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13572204125950055,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.00013564118787132506,
      "loss": 1.9249,
      "step": 100
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.37557488988552e-05,
      "loss": 1.774,
      "step": 200
    }
  ],
  "logging_steps": 100,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 3.424280260411392e+16,
  "trial_name": null,
  "trial_params": null
}