trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.4397693872451782,
      "eval_runtime": 0.1284,
      "eval_samples_per_second": 23.368,
      "eval_steps_per_second": 7.789,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.427268147468567,
      "eval_runtime": 0.1282,
      "eval_samples_per_second": 23.407,
      "eval_steps_per_second": 7.802,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.416739821434021,
      "eval_runtime": 0.1284,
      "eval_samples_per_second": 23.367,
      "eval_steps_per_second": 7.789,
      "step": 3
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.408455729484558,
      "eval_runtime": 0.1283,
      "eval_samples_per_second": 23.385,
      "eval_steps_per_second": 7.795,
      "step": 4
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.4030274152755737,
      "eval_runtime": 0.1281,
      "eval_samples_per_second": 23.417,
      "eval_steps_per_second": 7.806,
      "step": 5
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.3999160528182983,
      "eval_runtime": 0.1282,
      "eval_samples_per_second": 23.406,
      "eval_steps_per_second": 7.802,
      "step": 6
    }
  ],
  "logging_steps": 10,
  "max_steps": 6,
  "num_train_epochs": 6,
  "save_steps": 500,
  "total_flos": 1062700905922560.0,
  "trial_name": null,
  "trial_params": null
}