last-checkpoint/trainer_state.json

{
  "best_metric": 1.0106526613235474,
  "best_model_checkpoint": "./opt_trained/checkpoint-402",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 402,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.0177865028381348,
      "eval_runtime": 77.0752,
      "eval_samples_per_second": 37.055,
      "eval_steps_per_second": 9.264,
      "step": 201
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0106526613235474,
      "eval_runtime": 77.338,
      "eval_samples_per_second": 36.929,
      "eval_steps_per_second": 9.232,
      "step": 402
    }
  ],
  "logging_steps": 500,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.353270219264e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}