run-3/checkpoint-1650/trainer_state.json

{
  "best_metric": 0.3877551020408163,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-3\\checkpoint-550",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1650,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.91,
      "learning_rate": 1.3662899505209146e-06,
      "loss": 2.35,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3877551020408163,
      "eval_loss": 2.2825658321380615,
      "eval_runtime": 1.1797,
      "eval_samples_per_second": 207.683,
      "eval_steps_per_second": 13.563,
      "step": 550
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.722508415987777e-07,
      "loss": 2.2529,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3795918367346939,
      "eval_loss": 2.1926839351654053,
      "eval_runtime": 1.103,
      "eval_samples_per_second": 222.122,
      "eval_steps_per_second": 14.506,
      "step": 1100
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.7821173267664104e-07,
      "loss": 2.1925,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.37551020408163266,
      "eval_loss": 2.160534143447876,
      "eval_runtime": 1.431,
      "eval_samples_per_second": 171.209,
      "eval_steps_per_second": 11.181,
      "step": 1650
    }
  ],
  "logging_steps": 500,
  "max_steps": 1650,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2885602679400.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.9603290594430513e-06,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 4,
    "seed": 40
  }
}