{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010551305724083356,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.110261144816671e-05,
      "eval_loss": 4.271842956542969,
      "eval_runtime": 1834.5182,
      "eval_samples_per_second": 10.876,
      "eval_steps_per_second": 5.438,
      "step": 1
    },
    {
      "epoch": 0.00010551305724083355,
      "grad_norm": 2.6179606914520264,
      "learning_rate": 5e-05,
      "loss": 3.6149,
      "step": 5
    },
    {
      "epoch": 0.0002110261144816671,
      "grad_norm": 5.768125534057617,
      "learning_rate": 0.0001,
      "loss": 3.2024,
      "step": 10
    },
    {
      "epoch": 0.0002110261144816671,
      "eval_loss": 3.907235622406006,
      "eval_runtime": 1823.8226,
      "eval_samples_per_second": 10.94,
      "eval_steps_per_second": 5.47,
      "step": 10
    },
    {
      "epoch": 0.00031653917172250065,
      "grad_norm": 2.441521167755127,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.0431,
      "step": 15
    },
    {
      "epoch": 0.0004220522289633342,
      "grad_norm": 1.7382241487503052,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.7075,
      "step": 20
    },
    {
      "epoch": 0.0004220522289633342,
      "eval_loss": 2.8955235481262207,
      "eval_runtime": 1828.307,
      "eval_samples_per_second": 10.913,
      "eval_steps_per_second": 5.457,
      "step": 20
    },
    {
      "epoch": 0.0005275652862041678,
      "grad_norm": 1.8373712301254272,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.8294,
      "step": 25
    },
    {
      "epoch": 0.0006330783434450013,
      "grad_norm": 3.486210584640503,
      "learning_rate": 5e-05,
      "loss": 2.3964,
      "step": 30
    },
    {
      "epoch": 0.0006330783434450013,
      "eval_loss": 2.731161117553711,
      "eval_runtime": 1833.0819,
      "eval_samples_per_second": 10.885,
      "eval_steps_per_second": 5.443,
      "step": 30
    },
    {
      "epoch": 0.0007385914006858349,
      "grad_norm": 2.5775156021118164,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.8234,
      "step": 35
    },
    {
      "epoch": 0.0008441044579266684,
      "grad_norm": 2.7716472148895264,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.1688,
      "step": 40
    },
    {
      "epoch": 0.0008441044579266684,
      "eval_loss": 2.6252567768096924,
      "eval_runtime": 1833.3516,
      "eval_samples_per_second": 10.883,
      "eval_steps_per_second": 5.442,
      "step": 40
    },
    {
      "epoch": 0.000949617515167502,
      "grad_norm": 3.8267385959625244,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.2435,
      "step": 45
    },
    {
      "epoch": 0.0010551305724083356,
      "grad_norm": 3.116450071334839,
      "learning_rate": 0.0,
      "loss": 2.327,
      "step": 50
    },
    {
      "epoch": 0.0010551305724083356,
      "eval_loss": 2.614342212677002,
      "eval_runtime": 1830.2418,
      "eval_samples_per_second": 10.902,
      "eval_steps_per_second": 5.451,
      "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": 1.2623275993595904e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}