{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07259528130671507,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024198427102238356,
      "eval_loss": 2.8950273990631104,
      "eval_runtime": 4.3436,
      "eval_samples_per_second": 40.059,
      "eval_steps_per_second": 20.029,
      "step": 1
    },
    {
      "epoch": 0.007259528130671506,
      "grad_norm": 5.927088260650635,
      "learning_rate": 6e-05,
      "loss": 11.0453,
      "step": 3
    },
    {
      "epoch": 0.012099213551119177,
      "eval_loss": 2.774757146835327,
      "eval_runtime": 4.3101,
      "eval_samples_per_second": 40.37,
      "eval_steps_per_second": 20.185,
      "step": 5
    },
    {
      "epoch": 0.014519056261343012,
      "grad_norm": 3.2372381687164307,
      "learning_rate": 0.00012,
      "loss": 11.2996,
      "step": 6
    },
    {
      "epoch": 0.021778584392014518,
      "grad_norm": 4.715695381164551,
      "learning_rate": 0.00018,
      "loss": 10.1899,
      "step": 9
    },
    {
      "epoch": 0.024198427102238355,
      "eval_loss": 2.6026744842529297,
      "eval_runtime": 4.3152,
      "eval_samples_per_second": 40.323,
      "eval_steps_per_second": 20.161,
      "step": 10
    },
    {
      "epoch": 0.029038112522686024,
      "grad_norm": 3.3717691898345947,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.5228,
      "step": 12
    },
    {
      "epoch": 0.036297640653357534,
      "grad_norm": 6.051303863525391,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.1599,
      "step": 15
    },
    {
      "epoch": 0.036297640653357534,
      "eval_loss": 2.559455394744873,
      "eval_runtime": 4.216,
      "eval_samples_per_second": 41.271,
      "eval_steps_per_second": 20.636,
      "step": 15
    },
    {
      "epoch": 0.043557168784029036,
      "grad_norm": 4.3984150886535645,
      "learning_rate": 0.00013090169943749476,
      "loss": 9.7389,
      "step": 18
    },
    {
      "epoch": 0.04839685420447671,
      "eval_loss": 2.528050661087036,
      "eval_runtime": 4.2118,
      "eval_samples_per_second": 41.313,
      "eval_steps_per_second": 20.656,
      "step": 20
    },
    {
      "epoch": 0.050816696914700546,
      "grad_norm": 5.073339462280273,
      "learning_rate": 8.435655349597689e-05,
      "loss": 10.163,
      "step": 21
    },
    {
      "epoch": 0.05807622504537205,
      "grad_norm": 5.8750104904174805,
      "learning_rate": 4.12214747707527e-05,
      "loss": 10.431,
      "step": 24
    },
    {
      "epoch": 0.060496067755595885,
      "eval_loss": 2.518890619277954,
      "eval_runtime": 4.2166,
      "eval_samples_per_second": 41.265,
      "eval_steps_per_second": 20.633,
      "step": 25
    },
    {
      "epoch": 0.06533575317604355,
      "grad_norm": 6.0680460929870605,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 10.4286,
      "step": 27
    },
    {
      "epoch": 0.07259528130671507,
      "grad_norm": 6.099903106689453,
      "learning_rate": 0.0,
      "loss": 9.8809,
      "step": 30
    },
    {
      "epoch": 0.07259528130671507,
      "eval_loss": 2.5167429447174072,
      "eval_runtime": 4.2164,
      "eval_samples_per_second": 41.267,
      "eval_steps_per_second": 20.634,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1397468877029376.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}