checkpoint-100/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.054303556882975834,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.404040404040404e-05,
      "loss": 2.0605,
      "step": 25
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.8682901859283447,
      "eval_runtime": 457.4343,
      "eval_samples_per_second": 1.788,
      "eval_steps_per_second": 0.225,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.287878787878788e-05,
      "loss": 1.8078,
      "step": 50
    },
    {
      "epoch": 0.03,
      "eval_loss": 1.77669095993042,
      "eval_runtime": 457.4484,
      "eval_samples_per_second": 1.788,
      "eval_steps_per_second": 0.225,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.1616161616161617e-05,
      "loss": 1.6867,
      "step": 75
    },
    {
      "epoch": 0.04,
      "eval_loss": 1.7253795862197876,
      "eval_runtime": 457.4598,
      "eval_samples_per_second": 1.788,
      "eval_steps_per_second": 0.225,
      "step": 75
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.0353535353535353e-05,
      "loss": 1.7026,
      "step": 100
    },
    {
      "epoch": 0.05,
      "eval_loss": 1.713043451309204,
      "eval_runtime": 457.4489,
      "eval_samples_per_second": 1.788,
      "eval_steps_per_second": 0.225,
      "step": 100
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_train_epochs": 1,
  "save_steps": 50,
  "total_flos": 8763703767859200.0,
  "trial_name": null,
  "trial_params": null
}