{
  "best_global_step": 102,
  "best_metric": 0.334445595741272,
  "best_model_checkpoint": "/content/models/gemma_qlora_lmh_inst/checkpoint-102",
  "epoch": 2.0,
  "eval_steps": 20,
  "global_step": 102,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.0733081948012115,
      "epoch": 0.39408866995073893,
      "grad_norm": 0.80859375,
      "learning_rate": 8.137254901960784e-06,
      "loss": 1.8182489395141601,
      "mean_token_accuracy": 0.6859375,
      "num_tokens": 46761.0,
      "step": 20
    },
    {
      "epoch": 0.39408866995073893,
      "eval_entropy": 2.033581364388559,
      "eval_loss": 0.4592626392841339,
      "eval_mean_token_accuracy": 0.7745098039215687,
      "eval_num_tokens": 46761.0,
      "eval_runtime": 64.7147,
      "eval_samples_per_second": 3.137,
      "eval_steps_per_second": 1.576,
      "step": 20
    },
    {
      "entropy": 2.094073224067688,
      "epoch": 0.7881773399014779,
      "grad_norm": 0.55859375,
      "learning_rate": 6.176470588235295e-06,
      "loss": 0.37168567180633544,
      "mean_token_accuracy": 0.784375,
      "num_tokens": 95614.0,
      "step": 40
    },
    {
      "epoch": 0.7881773399014779,
      "eval_entropy": 2.047249140692692,
      "eval_loss": 0.35874781012535095,
      "eval_mean_token_accuracy": 0.7867647058823529,
      "eval_num_tokens": 95614.0,
      "eval_runtime": 64.7214,
      "eval_samples_per_second": 3.137,
      "eval_steps_per_second": 1.576,
      "step": 40
    },
    {
      "entropy": 2.1063496708115443,
      "epoch": 1.1773399014778325,
      "grad_norm": 0.3671875,
      "learning_rate": 4.215686274509805e-06,
      "loss": 0.3439093828201294,
      "mean_token_accuracy": 0.7887658227848101,
      "num_tokens": 143455.0,
      "step": 60
    },
    {
      "epoch": 1.1773399014778325,
      "eval_entropy": 2.0453919920266843,
      "eval_loss": 0.33736148476600647,
      "eval_mean_token_accuracy": 0.8014705882352942,
      "eval_num_tokens": 143455.0,
      "eval_runtime": 64.6714,
      "eval_samples_per_second": 3.139,
      "eval_steps_per_second": 1.577,
      "step": 60
    },
    {
      "entropy": 2.103617814555764,
      "epoch": 1.5714285714285714,
      "grad_norm": 0.2451171875,
      "learning_rate": 2.254901960784314e-06,
      "loss": 0.3234142065048218,
      "mean_token_accuracy": 0.81640625,
      "num_tokens": 192572.0,
      "step": 80
    },
    {
      "epoch": 1.5714285714285714,
      "eval_entropy": 2.0428848699027418,
      "eval_loss": 0.33574002981185913,
      "eval_mean_token_accuracy": 0.8014705882352942,
      "eval_num_tokens": 192572.0,
      "eval_runtime": 64.6733,
      "eval_samples_per_second": 3.139,
      "eval_steps_per_second": 1.577,
      "step": 80
    },
    {
      "entropy": 2.0937692623585464,
      "epoch": 1.9655172413793105,
      "grad_norm": 0.08203125,
      "learning_rate": 2.9411764705882356e-07,
      "loss": 0.33339247703552244,
      "mean_token_accuracy": 0.8078125,
      "num_tokens": 240555.0,
      "step": 100
    },
    {
      "epoch": 1.9655172413793105,
      "eval_entropy": 2.0438541921914792,
      "eval_loss": 0.3352242410182953,
      "eval_mean_token_accuracy": 0.7990196078431373,
      "eval_num_tokens": 240555.0,
      "eval_runtime": 64.6857,
      "eval_samples_per_second": 3.138,
      "eval_steps_per_second": 1.577,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_entropy": 2.0432825041752234,
      "eval_loss": 0.334445595741272,
      "eval_mean_token_accuracy": 0.8112745098039216,
      "eval_num_tokens": 244704.0,
      "eval_runtime": 64.7437,
      "eval_samples_per_second": 3.135,
      "eval_steps_per_second": 1.575,
      "step": 102
    }
  ],
  "logging_steps": 20,
  "max_steps": 102,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3629357536896000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}