trainer_state.json

{
  "best_metric": 0.4,
  "best_model_checkpoint": "finetuned-Accident-MultipleLabels-Others/checkpoint-10",
  "epoch": 3.25,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "eval_accuracy": 0.2857142857142857,
      "eval_loss": 1.8386245965957642,
      "eval_runtime": 190.3814,
      "eval_samples_per_second": 0.552,
      "eval_steps_per_second": 0.142,
      "step": 5
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.777777777777778e-05,
      "loss": 1.9251,
      "step": 10
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 0.4,
      "eval_loss": 1.7163732051849365,
      "eval_runtime": 189.1798,
      "eval_samples_per_second": 0.555,
      "eval_steps_per_second": 0.143,
      "step": 10
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 0.2571428571428571,
      "eval_loss": 1.7366632223129272,
      "eval_runtime": 188.863,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.143,
      "step": 15
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0,
      "loss": 1.5856,
      "step": 20
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.11428571428571428,
      "eval_loss": 1.7862908840179443,
      "eval_runtime": 188.0873,
      "eval_samples_per_second": 0.558,
      "eval_steps_per_second": 0.144,
      "step": 20
    },
    {
      "epoch": 3.25,
      "step": 20,
      "total_flos": 3.887929546632069e+17,
      "train_loss": 1.755351448059082,
      "train_runtime": 1490.9129,
      "train_samples_per_second": 0.215,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 10,
  "max_steps": 20,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 3.887929546632069e+17,
  "trial_name": null,
  "trial_params": null
}