.ipynb_checkpoints/trainer_state-checkpoint.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9166666666666665,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.42,
      "learning_rate": 8.611111111111112e-05,
      "loss": 1.4322,
      "step": 10
    },
    {
      "epoch": 0.42,
      "eval_accuracy": 0.3125,
      "eval_loss": 1.3030599355697632,
      "eval_runtime": 9.8316,
      "eval_samples_per_second": 4.882,
      "eval_steps_per_second": 1.221,
      "step": 10
    },
    {
      "epoch": 0.83,
      "learning_rate": 7.222222222222222e-05,
      "loss": 1.2975,
      "step": 20
    },
    {
      "epoch": 0.83,
      "eval_accuracy": 0.3541666567325592,
      "eval_loss": 1.2456461191177368,
      "eval_runtime": 12.762,
      "eval_samples_per_second": 3.761,
      "eval_steps_per_second": 0.94,
      "step": 20
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.833333333333334e-05,
      "loss": 1.3053,
      "step": 30
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 0.375,
      "eval_loss": 1.235076904296875,
      "eval_runtime": 9.8907,
      "eval_samples_per_second": 4.853,
      "eval_steps_per_second": 1.213,
      "step": 30
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.2042,
      "step": 40
    },
    {
      "epoch": 1.67,
      "eval_accuracy": 0.375,
      "eval_loss": 1.1900380849838257,
      "eval_runtime": 12.1455,
      "eval_samples_per_second": 3.952,
      "eval_steps_per_second": 0.988,
      "step": 40
    },
    {
      "epoch": 2.08,
      "learning_rate": 3.055555555555556e-05,
      "loss": 1.0192,
      "step": 50
    },
    {
      "epoch": 2.08,
      "eval_accuracy": 0.5416666865348816,
      "eval_loss": 1.006090760231018,
      "eval_runtime": 9.9246,
      "eval_samples_per_second": 4.836,
      "eval_steps_per_second": 1.209,
      "step": 50
    },
    {
      "epoch": 2.5,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.8874,
      "step": 60
    },
    {
      "epoch": 2.5,
      "eval_accuracy": 0.625,
      "eval_loss": 0.8699900507926941,
      "eval_runtime": 11.1183,
      "eval_samples_per_second": 4.317,
      "eval_steps_per_second": 1.079,
      "step": 60
    },
    {
      "epoch": 2.92,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.855,
      "step": 70
    },
    {
      "epoch": 2.92,
      "eval_accuracy": 0.5833333134651184,
      "eval_loss": 0.9461669921875,
      "eval_runtime": 9.9807,
      "eval_samples_per_second": 4.809,
      "eval_steps_per_second": 1.202,
      "step": 70
    }
  ],
  "max_steps": 72,
  "num_train_epochs": 3,
  "total_flos": 2.022508856471088e+17,
  "trial_name": null,
  "trial_params": null
}