checkpoint-55/trainer_state.json

{
  "best_metric": 0.28,
  "best_model_checkpoint": "./trainer_test_checkpoint/checkpoint-55",
  "epoch": 1.1,
  "global_step": 55,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "eval_accuracy": 0.17,
      "eval_loss": 1.7631263732910156,
      "eval_runtime": 3.5157,
      "eval_samples_per_second": 28.444,
      "eval_steps_per_second": 14.222,
      "step": 5
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.25,
      "eval_loss": 1.7874902486801147,
      "eval_runtime": 3.5523,
      "eval_samples_per_second": 28.15,
      "eval_steps_per_second": 14.075,
      "step": 10
    },
    {
      "epoch": 0.3,
      "eval_accuracy": 0.2,
      "eval_loss": 1.7714591026306152,
      "eval_runtime": 5.4717,
      "eval_samples_per_second": 18.276,
      "eval_steps_per_second": 9.138,
      "step": 15
    },
    {
      "epoch": 0.4,
      "eval_accuracy": 0.2,
      "eval_loss": 1.7414228916168213,
      "eval_runtime": 3.5124,
      "eval_samples_per_second": 28.47,
      "eval_steps_per_second": 14.235,
      "step": 20
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.2,
      "eval_loss": 1.6978241205215454,
      "eval_runtime": 3.6422,
      "eval_samples_per_second": 27.456,
      "eval_steps_per_second": 13.728,
      "step": 25
    },
    {
      "epoch": 0.6,
      "eval_accuracy": 0.2,
      "eval_loss": 1.676612138748169,
      "eval_runtime": 8.5564,
      "eval_samples_per_second": 11.687,
      "eval_steps_per_second": 5.844,
      "step": 30
    },
    {
      "epoch": 0.7,
      "eval_accuracy": 0.2,
      "eval_loss": 1.634315848350525,
      "eval_runtime": 4.8041,
      "eval_samples_per_second": 20.815,
      "eval_steps_per_second": 10.408,
      "step": 35
    },
    {
      "epoch": 0.8,
      "eval_accuracy": 0.19,
      "eval_loss": 1.6438544988632202,
      "eval_runtime": 3.7224,
      "eval_samples_per_second": 26.865,
      "eval_steps_per_second": 13.432,
      "step": 40
    },
    {
      "epoch": 0.9,
      "eval_accuracy": 0.19,
      "eval_loss": 1.6235827207565308,
      "eval_runtime": 4.875,
      "eval_samples_per_second": 20.513,
      "eval_steps_per_second": 10.256,
      "step": 45
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19,
      "eval_loss": 1.6140121221542358,
      "eval_runtime": 4.2264,
      "eval_samples_per_second": 23.661,
      "eval_steps_per_second": 11.83,
      "step": 50
    },
    {
      "epoch": 1.1,
      "eval_accuracy": 0.28,
      "eval_loss": 1.6068944931030273,
      "eval_runtime": 3.6567,
      "eval_samples_per_second": 27.347,
      "eval_steps_per_second": 13.673,
      "step": 55
    }
  ],
  "max_steps": 100,
  "num_train_epochs": 2,
  "total_flos": 28942995671040.0,
  "trial_name": null,
  "trial_params": null
}