trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "global_step": 508,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.01,
      "learning_rate": 3.740157480314961e-05,
      "loss": 2.7781,
      "step": 128
    },
    {
      "epoch": 1.01,
      "eval_accuracy": 0.4874660477958952,
      "eval_loss": 2.6284313201904297,
      "eval_runtime": 69.4322,
      "eval_samples_per_second": 14.705,
      "eval_steps_per_second": 1.844,
      "step": 128
    },
    {
      "epoch": 2.02,
      "learning_rate": 2.4803149606299215e-05,
      "loss": 2.6217,
      "step": 256
    },
    {
      "epoch": 2.02,
      "eval_accuracy": 0.49078252111331633,
      "eval_loss": 2.6022448539733887,
      "eval_runtime": 70.8747,
      "eval_samples_per_second": 14.406,
      "eval_steps_per_second": 1.806,
      "step": 256
    },
    {
      "epoch": 3.02,
      "learning_rate": 1.220472440944882e-05,
      "loss": 2.569,
      "step": 384
    },
    {
      "epoch": 3.02,
      "eval_accuracy": 0.49170738058924846,
      "eval_loss": 2.5927629470825195,
      "eval_runtime": 76.8807,
      "eval_samples_per_second": 13.28,
      "eval_steps_per_second": 1.665,
      "step": 384
    },
    {
      "epoch": 4.0,
      "step": 508,
      "total_flos": 3.0193916980494336e+16,
      "train_loss": 2.6286109864242433,
      "train_runtime": 3384.5609,
      "train_samples_per_second": 4.803,
      "train_steps_per_second": 0.15
    }
  ],
  "max_steps": 508,
  "num_train_epochs": 4,
  "total_flos": 3.0193916980494336e+16,
  "trial_name": null,
  "trial_params": null
}