checkpoint-300/trainer_state.json

{
  "best_metric": 0.5629389882087708,
  "best_model_checkpoint": "/kaggle/output/checkpoint-300",
  "epoch": 0.6198347107438017,
  "eval_steps": 50,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.777777777777778e-07,
      "loss": 0.664,
      "step": 1
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.75,
      "eval_loss": 0.5625454783439636,
      "eval_runtime": 28.0598,
      "eval_samples_per_second": 42.196,
      "eval_steps_per_second": 21.098,
      "step": 50
    },
    {
      "epoch": 0.21,
      "eval_accuracy": 0.75,
      "eval_loss": 0.5684965252876282,
      "eval_runtime": 27.869,
      "eval_samples_per_second": 42.485,
      "eval_steps_per_second": 21.242,
      "step": 100
    },
    {
      "epoch": 0.31,
      "eval_accuracy": 0.75,
      "eval_loss": 0.5661544799804688,
      "eval_runtime": 29.0027,
      "eval_samples_per_second": 40.824,
      "eval_steps_per_second": 20.412,
      "step": 150
    },
    {
      "epoch": 0.41,
      "eval_accuracy": 0.75,
      "eval_loss": 0.5637454986572266,
      "eval_runtime": 27.8992,
      "eval_samples_per_second": 42.439,
      "eval_steps_per_second": 21.219,
      "step": 200
    },
    {
      "epoch": 0.52,
      "eval_accuracy": 0.75,
      "eval_loss": 0.575886607170105,
      "eval_runtime": 28.6519,
      "eval_samples_per_second": 41.324,
      "eval_steps_per_second": 20.662,
      "step": 250
    },
    {
      "epoch": 0.62,
      "eval_accuracy": 0.75,
      "eval_loss": 0.5629389882087708,
      "eval_runtime": 27.9424,
      "eval_samples_per_second": 42.373,
      "eval_steps_per_second": 21.186,
      "step": 300
    }
  ],
  "logging_steps": 1000,
  "max_steps": 1000,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 942109667942952.0,
  "trial_name": null,
  "trial_params": null
}