{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010077851402081077,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0155702804162153e-05,
      "eval_loss": 1.8410059213638306,
      "eval_runtime": 1881.0496,
      "eval_samples_per_second": 11.106,
      "eval_steps_per_second": 5.553,
      "step": 1
    },
    {
      "epoch": 0.00010077851402081077,
      "grad_norm": 1.8387056589126587,
      "learning_rate": 5e-05,
      "loss": 1.8501,
      "step": 5
    },
    {
      "epoch": 0.00020155702804162154,
      "grad_norm": 1.1357821226119995,
      "learning_rate": 0.0001,
      "loss": 1.6593,
      "step": 10
    },
    {
      "epoch": 0.00020155702804162154,
      "eval_loss": 1.46839439868927,
      "eval_runtime": 1881.3223,
      "eval_samples_per_second": 11.104,
      "eval_steps_per_second": 5.552,
      "step": 10
    },
    {
      "epoch": 0.0003023355420624323,
      "grad_norm": 1.3025918006896973,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.166,
      "step": 15
    },
    {
      "epoch": 0.0004031140560832431,
      "grad_norm": 0.7983736395835876,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3881,
      "step": 20
    },
    {
      "epoch": 0.0004031140560832431,
      "eval_loss": 1.1858701705932617,
      "eval_runtime": 1883.6837,
      "eval_samples_per_second": 11.09,
      "eval_steps_per_second": 5.545,
      "step": 20
    },
    {
      "epoch": 0.0005038925701040538,
      "grad_norm": 1.699404239654541,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.32,
      "step": 25
    },
    {
      "epoch": 0.0006046710841248646,
      "grad_norm": 1.0257610082626343,
      "learning_rate": 5e-05,
      "loss": 1.1806,
      "step": 30
    },
    {
      "epoch": 0.0006046710841248646,
      "eval_loss": 1.1275124549865723,
      "eval_runtime": 1879.839,
      "eval_samples_per_second": 11.113,
      "eval_steps_per_second": 5.556,
      "step": 30
    },
    {
      "epoch": 0.0007054495981456754,
      "grad_norm": 0.6786960363388062,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.3336,
      "step": 35
    },
    {
      "epoch": 0.0008062281121664861,
      "grad_norm": 1.3598406314849854,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8859,
      "step": 40
    },
    {
      "epoch": 0.0008062281121664861,
      "eval_loss": 1.1031326055526733,
      "eval_runtime": 1874.0191,
      "eval_samples_per_second": 11.147,
      "eval_steps_per_second": 5.574,
      "step": 40
    },
    {
      "epoch": 0.0009070066261872969,
      "grad_norm": 0.7752267718315125,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.102,
      "step": 45
    },
    {
      "epoch": 0.0010077851402081077,
      "grad_norm": 1.247992992401123,
      "learning_rate": 0.0,
      "loss": 1.1284,
      "step": 50
    },
    {
      "epoch": 0.0010077851402081077,
      "eval_loss": 1.0990670919418335,
      "eval_runtime": 1877.0542,
      "eval_samples_per_second": 11.129,
      "eval_steps_per_second": 5.565,
      "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": 1.2761993312206848e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}