{
  "best_global_step": 708,
  "best_metric": 0.47357939458311205,
  "best_model_checkpoint": "./bert-lora-newsgroups/checkpoint-708",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 708,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14124293785310735,
      "grad_norm": 4.619589805603027,
      "learning_rate": 0.00019067796610169492,
      "loss": 2.9563,
      "step": 100
    },
    {
      "epoch": 0.2824858757062147,
      "grad_norm": 4.369770526885986,
      "learning_rate": 0.0001812617702448211,
      "loss": 2.4516,
      "step": 200
    },
    {
      "epoch": 0.423728813559322,
      "grad_norm": 4.454040050506592,
      "learning_rate": 0.00017184557438794729,
      "loss": 2.1271,
      "step": 300
    },
    {
      "epoch": 0.5649717514124294,
      "grad_norm": 5.155438423156738,
      "learning_rate": 0.00016242937853107344,
      "loss": 1.9125,
      "step": 400
    },
    {
      "epoch": 0.7062146892655368,
      "grad_norm": 4.892629623413086,
      "learning_rate": 0.00015301318267419963,
      "loss": 1.7896,
      "step": 500
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 4.983877658843994,
      "learning_rate": 0.0001435969868173258,
      "loss": 1.6968,
      "step": 600
    },
    {
      "epoch": 0.9887005649717514,
      "grad_norm": 8.334493637084961,
      "learning_rate": 0.00013418079096045197,
      "loss": 1.5862,
      "step": 700
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.47357939458311205,
      "eval_loss": 1.6120948791503906,
      "eval_runtime": 59.1685,
      "eval_samples_per_second": 127.297,
      "eval_steps_per_second": 7.96,
      "step": 708
    }
  ],
  "logging_steps": 100,
  "max_steps": 2124,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2844933635814144.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}