trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23262576330328583,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "eval_accuracy": 0.9866142691167129,
      "eval_loss": 0.07293701171875,
      "eval_runtime": 192.7185,
      "eval_samples_per_second": 60.103,
      "eval_steps_per_second": 1.878,
      "step": 100
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.9868109877885048,
      "eval_loss": 0.07159423828125,
      "eval_runtime": 192.6928,
      "eval_samples_per_second": 60.111,
      "eval_steps_per_second": 1.879,
      "step": 200
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.9869265209767002,
      "eval_loss": 0.07049560546875,
      "eval_runtime": 193.5043,
      "eval_samples_per_second": 59.859,
      "eval_steps_per_second": 1.871,
      "step": 300
    },
    {
      "epoch": 0.23,
      "eval_accuracy": 0.986989308918276,
      "eval_loss": 0.0699462890625,
      "eval_runtime": 192.6707,
      "eval_samples_per_second": 60.118,
      "eval_steps_per_second": 1.879,
      "step": 400
    },
    {
      "epoch": 0.23,
      "step": 400,
      "total_flos": 4.12601633927594e+17,
      "train_loss": 0.12210027694702148,
      "train_runtime": 1976.8574,
      "train_samples_per_second": 25.9,
      "train_steps_per_second": 0.202
    }
  ],
  "max_steps": 400,
  "num_train_epochs": 1,
  "total_flos": 4.12601633927594e+17,
  "trial_name": null,
  "trial_params": null
}