{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21052631578947367,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004210526315789474,
      "eval_loss": 2.6562552452087402,
      "eval_runtime": 4.4287,
      "eval_samples_per_second": 22.58,
      "eval_steps_per_second": 11.29,
      "step": 1
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 0.8043078184127808,
      "learning_rate": 5e-05,
      "loss": 2.8372,
      "step": 5
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.45552536845207214,
      "learning_rate": 0.0001,
      "loss": 2.2991,
      "step": 10
    },
    {
      "epoch": 0.042105263157894736,
      "eval_loss": 2.550579786300659,
      "eval_runtime": 3.9155,
      "eval_samples_per_second": 25.54,
      "eval_steps_per_second": 12.77,
      "step": 10
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 0.5643782019615173,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.8841,
      "step": 15
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.4963832199573517,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8898,
      "step": 20
    },
    {
      "epoch": 0.08421052631578947,
      "eval_loss": 2.216585159301758,
      "eval_runtime": 4.031,
      "eval_samples_per_second": 24.808,
      "eval_steps_per_second": 12.404,
      "step": 20
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.5257603526115417,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8998,
      "step": 25
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 0.8485556244850159,
      "learning_rate": 5e-05,
      "loss": 1.6415,
      "step": 30
    },
    {
      "epoch": 0.12631578947368421,
      "eval_loss": 2.0503528118133545,
      "eval_runtime": 3.965,
      "eval_samples_per_second": 25.221,
      "eval_steps_per_second": 12.61,
      "step": 30
    },
    {
      "epoch": 0.14736842105263157,
      "grad_norm": 1.2867674827575684,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.6452,
      "step": 35
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.47658050060272217,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.8139,
      "step": 40
    },
    {
      "epoch": 0.16842105263157894,
      "eval_loss": 1.9745097160339355,
      "eval_runtime": 3.9944,
      "eval_samples_per_second": 25.035,
      "eval_steps_per_second": 12.517,
      "step": 40
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 1.0479307174682617,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.7238,
      "step": 45
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.6328036785125732,
      "learning_rate": 0.0,
      "loss": 1.7828,
      "step": 50
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 1.9637155532836914,
      "eval_runtime": 3.8584,
      "eval_samples_per_second": 25.918,
      "eval_steps_per_second": 12.959,
      "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": 1751210595975168.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}