run-0/checkpoint-1500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.716981132075472,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.584516129032258,
      "eval_loss": 0.21347010135650635,
      "eval_runtime": 5.5258,
      "eval_samples_per_second": 561.004,
      "eval_steps_per_second": 11.763,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.5506463050842285,
      "learning_rate": 1.4758909853249476e-05,
      "loss": 0.3376,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8151612903225807,
      "eval_loss": 0.10622444748878479,
      "eval_runtime": 5.553,
      "eval_samples_per_second": 558.259,
      "eval_steps_per_second": 11.705,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8722580645161291,
      "eval_loss": 0.07321830838918686,
      "eval_runtime": 5.2823,
      "eval_samples_per_second": 586.866,
      "eval_steps_per_second": 12.305,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.4782344400882721,
      "learning_rate": 9.517819706498952e-06,
      "loss": 0.1229,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.892258064516129,
      "eval_loss": 0.059067677706480026,
      "eval_runtime": 5.4003,
      "eval_samples_per_second": 574.047,
      "eval_steps_per_second": 12.036,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.34752407670021057,
      "learning_rate": 4.276729559748428e-06,
      "loss": 0.0832,
      "step": 1500
    }
  ],
  "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": 391368939443328.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.025340185433372686,
    "num_train_epochs": 6,
    "temperature": 8
  }
}