trainer_state.json

{
  "best_metric": 0.9398584510113038,
  "best_model_checkpoint": "model_saves/xlnet-large_lemon_10k_2_p3/checkpoint-536",
  "epoch": 5.0,
  "global_step": 1340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9397857757801407,
      "eval_loss": 0.45327770709991455,
      "eval_runtime": 4.8067,
      "eval_samples_per_second": 911.641,
      "eval_steps_per_second": 7.281,
      "step": 268
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9398584510113038,
      "eval_loss": 0.4725741744041443,
      "eval_runtime": 4.8269,
      "eval_samples_per_second": 907.821,
      "eval_steps_per_second": 7.251,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9392938203691902,
      "eval_loss": 0.5044676065444946,
      "eval_runtime": 4.7501,
      "eval_samples_per_second": 922.516,
      "eval_steps_per_second": 7.368,
      "step": 804
    },
    {
      "epoch": 3.73,
      "learning_rate": 1e-05,
      "loss": 0.2939,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9389695770301546,
      "eval_loss": 0.5532529950141907,
      "eval_runtime": 4.7832,
      "eval_samples_per_second": 916.116,
      "eval_steps_per_second": 7.317,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9388354073726227,
      "eval_loss": 0.6085860133171082,
      "eval_runtime": 4.8148,
      "eval_samples_per_second": 910.113,
      "eval_steps_per_second": 7.269,
      "step": 1340
    },
    {
      "epoch": 5.0,
      "step": 1340,
      "total_flos": 2.1579393029636096e+16,
      "train_loss": 0.26621628946332787,
      "train_runtime": 557.1132,
      "train_samples_per_second": 923.618,
      "train_steps_per_second": 7.216
    }
  ],
  "max_steps": 4020,
  "num_train_epochs": 15,
  "total_flos": 2.1579393029636096e+16,
  "trial_name": null,
  "trial_params": null
}