trainer_state.json

{
  "best_metric": 0.5988090634346008,
  "best_model_checkpoint": "model/run-v9tx3vp4/checkpoint-22",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 22,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.610965371131897,
      "eval_runtime": 1.2943,
      "eval_samples_per_second": 440.398,
      "eval_steps_per_second": 18.543,
      "step": 11
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5988090634346008,
      "eval_runtime": 1.2474,
      "eval_samples_per_second": 456.952,
      "eval_steps_per_second": 19.24,
      "step": 22
    }
  ],
  "logging_steps": 500,
  "max_steps": 22,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0,
  "train_batch_size": 384,
  "trial_name": null,
  "trial_params": {
    "_wandb": {},
    "assignments": {},
    "learning_rate": 8.471245067545569e-05,
    "metric": "eval/loss",
    "num_train_epochs": 2.9972661019913396,
    "optim": "adamw_torch",
    "per_device_train_batch_size": 128
  }
}