{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002190412564206468,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.380825128412937e-05,
      "eval_loss": 1.3511103391647339,
      "eval_runtime": 875.792,
      "eval_samples_per_second": 10.975,
      "eval_steps_per_second": 5.488,
      "step": 1
    },
    {
      "epoch": 0.00021904125642064682,
      "grad_norm": 0.9839276671409607,
      "learning_rate": 5e-05,
      "loss": 1.3691,
      "step": 5
    },
    {
      "epoch": 0.00043808251284129364,
      "grad_norm": 0.8648563027381897,
      "learning_rate": 0.0001,
      "loss": 1.2625,
      "step": 10
    },
    {
      "epoch": 0.00043808251284129364,
      "eval_loss": 1.1627215147018433,
      "eval_runtime": 879.1475,
      "eval_samples_per_second": 10.933,
      "eval_steps_per_second": 5.467,
      "step": 10
    },
    {
      "epoch": 0.0006571237692619405,
      "grad_norm": 0.8831146359443665,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1129,
      "step": 15
    },
    {
      "epoch": 0.0008761650256825873,
      "grad_norm": 0.6764513850212097,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8807,
      "step": 20
    },
    {
      "epoch": 0.0008761650256825873,
      "eval_loss": 0.9764151573181152,
      "eval_runtime": 876.6149,
      "eval_samples_per_second": 10.965,
      "eval_steps_per_second": 5.482,
      "step": 20
    },
    {
      "epoch": 0.001095206282103234,
      "grad_norm": 0.7300176024436951,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9643,
      "step": 25
    },
    {
      "epoch": 0.001314247538523881,
      "grad_norm": 0.6463407874107361,
      "learning_rate": 5e-05,
      "loss": 0.9152,
      "step": 30
    },
    {
      "epoch": 0.001314247538523881,
      "eval_loss": 0.8988265991210938,
      "eval_runtime": 876.9987,
      "eval_samples_per_second": 10.96,
      "eval_steps_per_second": 5.48,
      "step": 30
    },
    {
      "epoch": 0.0015332887949445278,
      "grad_norm": 0.7085407972335815,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.9022,
      "step": 35
    },
    {
      "epoch": 0.0017523300513651746,
      "grad_norm": 1.578107476234436,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8584,
      "step": 40
    },
    {
      "epoch": 0.0017523300513651746,
      "eval_loss": 0.8682357668876648,
      "eval_runtime": 876.1164,
      "eval_samples_per_second": 10.971,
      "eval_steps_per_second": 5.486,
      "step": 40
    },
    {
      "epoch": 0.0019713713077858215,
      "grad_norm": 0.7002089023590088,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.882,
      "step": 45
    },
    {
      "epoch": 0.002190412564206468,
      "grad_norm": 0.7077807784080505,
      "learning_rate": 0.0,
      "loss": 0.8292,
      "step": 50
    },
    {
      "epoch": 0.002190412564206468,
      "eval_loss": 0.8632972240447998,
      "eval_runtime": 876.6962,
      "eval_samples_per_second": 10.964,
      "eval_steps_per_second": 5.482,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2808232418410496e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}