{
  "best_metric": 0.5745548592459963,
  "best_model_checkpoint": "/home/ruben/PT-Pump-Up/package-client/src/pt_pump_up/benchmarking/output/checkpoint-3217",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 6434,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 18.098752975463867,
      "learning_rate": 4.9222878458190864e-05,
      "loss": 0.393,
      "step": 500
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.4246498346328735,
      "learning_rate": 4.8445756916381726e-05,
      "loss": 0.3577,
      "step": 1000
    },
    {
      "epoch": 0.47,
      "grad_norm": 20.033092498779297,
      "learning_rate": 4.766863537457259e-05,
      "loss": 0.2749,
      "step": 1500
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.9361429214477539,
      "learning_rate": 4.689151383276344e-05,
      "loss": 0.2693,
      "step": 2000
    },
    {
      "epoch": 0.78,
      "grad_norm": 2.208453893661499,
      "learning_rate": 4.6114392290954305e-05,
      "loss": 0.2839,
      "step": 2500
    },
    {
      "epoch": 0.93,
      "grad_norm": 5.299256324768066,
      "learning_rate": 4.5337270749145166e-05,
      "loss": 0.3315,
      "step": 3000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6945,
      "eval_f1": 0.5745548592459963,
      "eval_loss": 0.5727517604827881,
      "eval_precision": 0.9459547985587946,
      "eval_recall": 0.4125714285714286,
      "eval_runtime": 971.5986,
      "eval_samples_per_second": 28.818,
      "eval_steps_per_second": 1.801,
      "step": 3217
    },
    {
      "epoch": 1.09,
      "grad_norm": 2.0671701431274414,
      "learning_rate": 4.456014920733603e-05,
      "loss": 0.5044,
      "step": 3500
    },
    {
      "epoch": 1.24,
      "grad_norm": 2.1807188987731934,
      "learning_rate": 4.378302766552689e-05,
      "loss": 0.6689,
      "step": 4000
    },
    {
      "epoch": 1.4,
      "grad_norm": 5.214261054992676,
      "learning_rate": 4.300590612371775e-05,
      "loss": 0.6711,
      "step": 4500
    },
    {
      "epoch": 1.55,
      "grad_norm": 4.0813446044921875,
      "learning_rate": 4.2228784581908613e-05,
      "loss": 0.69,
      "step": 5000
    },
    {
      "epoch": 1.71,
      "grad_norm": 14.689708709716797,
      "learning_rate": 4.1451663040099475e-05,
      "loss": 0.709,
      "step": 5500
    },
    {
      "epoch": 1.87,
      "grad_norm": 3.6824076175689697,
      "learning_rate": 4.067454149829034e-05,
      "loss": 0.6821,
      "step": 6000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5,
      "eval_f1": 0.0,
      "eval_loss": 0.685297429561615,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 964.7135,
      "eval_samples_per_second": 29.024,
      "eval_steps_per_second": 1.814,
      "step": 6434
    }
  ],
  "logging_steps": 500,
  "max_steps": 32170,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 3.215241835190381e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}