{
  "best_global_step": 120,
  "best_metric": 0.7121169378526554,
  "best_model_checkpoint": "/content/gemma_lora_imb/checkpoint-120",
  "epoch": 1.912,
  "eval_steps": 20,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32,
      "grad_norm": 428.16009521484375,
      "learning_rate": 8.492063492063492e-06,
      "loss": 10.2541,
      "step": 20
    },
    {
      "epoch": 0.32,
      "eval_f1_macro": 0.30367703103162375,
      "eval_loss": 2.0160138607025146,
      "eval_runtime": 42.6744,
      "eval_samples_per_second": 46.867,
      "eval_steps_per_second": 5.858,
      "step": 20
    },
    {
      "epoch": 0.64,
      "grad_norm": 46.26844024658203,
      "learning_rate": 6.9047619047619055e-06,
      "loss": 5.1249,
      "step": 40
    },
    {
      "epoch": 0.64,
      "eval_f1_macro": 0.48650808108472904,
      "eval_loss": 1.5075854063034058,
      "eval_runtime": 42.3883,
      "eval_samples_per_second": 47.183,
      "eval_steps_per_second": 5.898,
      "step": 40
    },
    {
      "epoch": 0.96,
      "grad_norm": 684.8424072265625,
      "learning_rate": 5.317460317460318e-06,
      "loss": 3.7901,
      "step": 60
    },
    {
      "epoch": 0.96,
      "eval_f1_macro": 0.5956481908520431,
      "eval_loss": 1.541353702545166,
      "eval_runtime": 42.505,
      "eval_samples_per_second": 47.053,
      "eval_steps_per_second": 5.882,
      "step": 60
    },
    {
      "epoch": 1.272,
      "grad_norm": 23.575862884521484,
      "learning_rate": 3.7301587301587305e-06,
      "loss": 1.4486,
      "step": 80
    },
    {
      "epoch": 1.272,
      "eval_f1_macro": 0.6662347432713018,
      "eval_loss": 1.373887062072754,
      "eval_runtime": 42.5186,
      "eval_samples_per_second": 47.038,
      "eval_steps_per_second": 5.88,
      "step": 80
    },
    {
      "epoch": 1.592,
      "grad_norm": 40.776390075683594,
      "learning_rate": 2.1428571428571427e-06,
      "loss": 1.6294,
      "step": 100
    },
    {
      "epoch": 1.592,
      "eval_f1_macro": 0.7040549462194111,
      "eval_loss": 0.9468446373939514,
      "eval_runtime": 42.5061,
      "eval_samples_per_second": 47.052,
      "eval_steps_per_second": 5.882,
      "step": 100
    },
    {
      "epoch": 1.912,
      "grad_norm": 30.759462356567383,
      "learning_rate": 5.555555555555555e-07,
      "loss": 1.054,
      "step": 120
    },
    {
      "epoch": 1.912,
      "eval_f1_macro": 0.7121169378526554,
      "eval_loss": 0.9425287246704102,
      "eval_runtime": 42.6742,
      "eval_samples_per_second": 46.867,
      "eval_steps_per_second": 5.858,
      "step": 120
    }
  ],
  "logging_steps": 20,
  "max_steps": 126,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9149081621848064e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}