checkpoint-9/trainer_state.json

{
  "best_metric": 2.420926094055176,
  "best_model_checkpoint": "shawgpt-ft-trial-0/checkpoint-9",
  "epoch": 2.88,
  "eval_steps": 500,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.96,
      "grad_norm": 1.081973671913147,
      "learning_rate": 0.00026388697902791035,
      "loss": 4.1859,
      "step": 3
    },
    {
      "epoch": 0.96,
      "eval_loss": 3.5218443870544434,
      "eval_runtime": 4.4578,
      "eval_samples_per_second": 2.019,
      "eval_steps_per_second": 1.122,
      "step": 3
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.1095596551895142,
      "learning_rate": 0.00021110958322232825,
      "loss": 3.3269,
      "step": 6
    },
    {
      "epoch": 1.92,
      "eval_loss": 2.843799114227295,
      "eval_runtime": 4.4972,
      "eval_samples_per_second": 2.001,
      "eval_steps_per_second": 1.112,
      "step": 6
    },
    {
      "epoch": 2.88,
      "grad_norm": 1.0787794589996338,
      "learning_rate": 0.0001583321874167462,
      "loss": 2.7223,
      "step": 9
    },
    {
      "epoch": 2.88,
      "eval_loss": 2.420926094055176,
      "eval_runtime": 4.4722,
      "eval_samples_per_second": 2.012,
      "eval_steps_per_second": 1.118,
      "step": 9
    }
  ],
  "logging_steps": 500,
  "max_steps": 18,
  "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": 28816710598656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}