run-1/checkpoint-1000/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.1446540880503147,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6532258064516129,
      "eval_loss": 0.3269854784011841,
      "eval_runtime": 5.4879,
      "eval_samples_per_second": 564.877,
      "eval_steps_per_second": 11.844,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.702914834022522,
      "learning_rate": 1.4758909853249476e-05,
      "loss": 0.5113,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.834516129032258,
      "eval_loss": 0.1344248652458191,
      "eval_runtime": 6.1387,
      "eval_samples_per_second": 504.993,
      "eval_steps_per_second": 10.589,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8861290322580645,
      "eval_loss": 0.07997074723243713,
      "eval_runtime": 5.5219,
      "eval_samples_per_second": 561.405,
      "eval_steps_per_second": 11.771,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.65141761302948,
      "learning_rate": 9.517819706498952e-06,
      "loss": 0.1574,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1908,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 260941334653608.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.4557079890699607,
    "num_train_epochs": 6.523070977322467,
    "temperature": 2.615438852816318
  }
}