{
  "best_metric": 1.4907110929489136,
  "best_model_checkpoint": "checkpoints/Llama-3.1-8B-Instruct/hatedemics_rag-0402-custom_loss/checkpoint-150",
  "epoch": 0.43509789702683105,
  "eval_steps": 10,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029006526468455404,
      "eval_loss": 2.542835235595703,
      "eval_runtime": 2442.4047,
      "eval_samples_per_second": 0.564,
      "eval_steps_per_second": 0.141,
      "step": 10
    },
    {
      "epoch": 0.05801305293691081,
      "grad_norm": 0.5312708616256714,
      "learning_rate": 1.153846153846154e-05,
      "loss": 2.4943,
      "step": 20
    },
    {
      "epoch": 0.05801305293691081,
      "eval_loss": 2.384974718093872,
      "eval_runtime": 2440.2318,
      "eval_samples_per_second": 0.565,
      "eval_steps_per_second": 0.141,
      "step": 20
    },
    {
      "epoch": 0.08701957940536621,
      "eval_loss": 2.191277027130127,
      "eval_runtime": 2442.7783,
      "eval_samples_per_second": 0.564,
      "eval_steps_per_second": 0.141,
      "step": 30
    },
    {
      "epoch": 0.11602610587382162,
      "grad_norm": 0.5317983031272888,
      "learning_rate": 2.307692307692308e-05,
      "loss": 2.2195,
      "step": 40
    },
    {
      "epoch": 0.11602610587382162,
      "eval_loss": 1.9987460374832153,
      "eval_runtime": 2442.7258,
      "eval_samples_per_second": 0.564,
      "eval_steps_per_second": 0.141,
      "step": 40
    },
    {
      "epoch": 0.145032632342277,
      "eval_loss": 1.7984939813613892,
      "eval_runtime": 2437.4111,
      "eval_samples_per_second": 0.565,
      "eval_steps_per_second": 0.142,
      "step": 50
    },
    {
      "epoch": 0.17403915881073242,
      "grad_norm": 0.5333729386329651,
      "learning_rate": 2.999829729005125e-05,
      "loss": 1.8587,
      "step": 60
    },
    {
      "epoch": 0.17403915881073242,
      "eval_loss": 1.639336109161377,
      "eval_runtime": 2434.3583,
      "eval_samples_per_second": 0.566,
      "eval_steps_per_second": 0.142,
      "step": 60
    },
    {
      "epoch": 0.20304568527918782,
      "eval_loss": 1.5912648439407349,
      "eval_runtime": 2435.7205,
      "eval_samples_per_second": 0.566,
      "eval_steps_per_second": 0.142,
      "step": 70
    },
    {
      "epoch": 0.23205221174764323,
      "grad_norm": 0.43636104464530945,
      "learning_rate": 2.9979146242283087e-05,
      "loss": 1.6584,
      "step": 80
    },
    {
      "epoch": 0.23205221174764323,
      "eval_loss": 1.567818522453308,
      "eval_runtime": 2435.2495,
      "eval_samples_per_second": 0.566,
      "eval_steps_per_second": 0.142,
      "step": 80
    },
    {
      "epoch": 0.2610587382160986,
      "eval_loss": 1.549891471862793,
      "eval_runtime": 2435.1297,
      "eval_samples_per_second": 0.566,
      "eval_steps_per_second": 0.142,
      "step": 90
    },
    {
      "epoch": 0.290065264684554,
      "grad_norm": 0.3220229148864746,
      "learning_rate": 2.9938743021113326e-05,
      "loss": 1.5901,
      "step": 100
    },
    {
      "epoch": 0.290065264684554,
      "eval_loss": 1.5360591411590576,
      "eval_runtime": 2434.2214,
      "eval_samples_per_second": 0.566,
      "eval_steps_per_second": 0.142,
      "step": 100
    },
    {
      "epoch": 0.31907179115300943,
      "eval_loss": 1.5227614641189575,
      "eval_runtime": 2432.2291,
      "eval_samples_per_second": 0.567,
      "eval_steps_per_second": 0.142,
      "step": 110
    },
    {
      "epoch": 0.34807831762146485,
      "grad_norm": 0.3948887586593628,
      "learning_rate": 2.987714494998674e-05,
      "loss": 1.557,
      "step": 120
    },
    {
      "epoch": 0.34807831762146485,
      "eval_loss": 1.511211633682251,
      "eval_runtime": 2432.4757,
      "eval_samples_per_second": 0.567,
      "eval_steps_per_second": 0.142,
      "step": 120
    },
    {
      "epoch": 0.3770848440899202,
      "eval_loss": 1.5033425092697144,
      "eval_runtime": 2433.8386,
      "eval_samples_per_second": 0.566,
      "eval_steps_per_second": 0.142,
      "step": 130
    },
    {
      "epoch": 0.40609137055837563,
      "grad_norm": 0.5044500231742859,
      "learning_rate": 2.9794439423262625e-05,
      "loss": 1.4977,
      "step": 140
    },
    {
      "epoch": 0.40609137055837563,
      "eval_loss": 1.4966373443603516,
      "eval_runtime": 2433.7306,
      "eval_samples_per_second": 0.566,
      "eval_steps_per_second": 0.142,
      "step": 140
    },
    {
      "epoch": 0.43509789702683105,
      "eval_loss": 1.4907110929489136,
      "eval_runtime": 2434.4621,
      "eval_samples_per_second": 0.566,
      "eval_steps_per_second": 0.142,
      "step": 150
    }
  ],
  "logging_steps": 20,
  "max_steps": 1720,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 10,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3876451196928e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}