{
  "best_metric": 6.1056413650512695,
  "best_model_checkpoint": "./opt_trained1/checkpoint-201",
  "epoch": 3.9956656346749226,
  "eval_steps": 500,
  "global_step": 804,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9956656346749226,
      "eval_loss": 6.1056413650512695,
      "eval_runtime": 155.9076,
      "eval_samples_per_second": 13.809,
      "eval_steps_per_second": 1.732,
      "step": 201
    },
    {
      "epoch": 1.9956656346749226,
      "eval_loss": 8.50473690032959,
      "eval_runtime": 155.7389,
      "eval_samples_per_second": 13.824,
      "eval_steps_per_second": 1.734,
      "step": 402
    },
    {
      "epoch": 2.485448916408669,
      "grad_norm": 283244.78125,
      "learning_rate": 8.756218905472637e-05,
      "loss": 3.2084,
      "step": 500
    },
    {
      "epoch": 2.9956656346749226,
      "eval_loss": 8.332228660583496,
      "eval_runtime": 155.8264,
      "eval_samples_per_second": 13.817,
      "eval_steps_per_second": 1.733,
      "step": 603
    },
    {
      "epoch": 3.9956656346749226,
      "eval_loss": 8.359700202941895,
      "eval_runtime": 155.7968,
      "eval_samples_per_second": 13.819,
      "eval_steps_per_second": 1.733,
      "step": 804
    }
  ],
  "logging_steps": 500,
  "max_steps": 4020,
  "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": 5.446962393985843e+16,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}