{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00880410858400587,
  "eval_steps": 42,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002096216329525207,
      "eval_loss": 1.4208108186721802,
      "eval_runtime": 163.5996,
      "eval_samples_per_second": 49.114,
      "eval_steps_per_second": 6.143,
      "step": 1
    },
    {
      "epoch": 0.0006288648988575621,
      "grad_norm": 0.39683395624160767,
      "learning_rate": 3e-05,
      "loss": 1.4354,
      "step": 3
    },
    {
      "epoch": 0.0012577297977151242,
      "grad_norm": 0.4367702305316925,
      "learning_rate": 6e-05,
      "loss": 1.4342,
      "step": 6
    },
    {
      "epoch": 0.0018865946965726864,
      "grad_norm": 0.37110769748687744,
      "learning_rate": 9e-05,
      "loss": 1.3479,
      "step": 9
    },
    {
      "epoch": 0.0025154595954302483,
      "grad_norm": 0.36730247735977173,
      "learning_rate": 9.999588943391597e-05,
      "loss": 1.361,
      "step": 12
    },
    {
      "epoch": 0.0031443244942878103,
      "grad_norm": 0.35089993476867676,
      "learning_rate": 9.99743108100344e-05,
      "loss": 1.2814,
      "step": 15
    },
    {
      "epoch": 0.0037731893931453727,
      "grad_norm": 0.38672298192977905,
      "learning_rate": 9.993424445916923e-05,
      "loss": 1.3016,
      "step": 18
    },
    {
      "epoch": 0.004402054292002935,
      "grad_norm": 0.321205198764801,
      "learning_rate": 9.987570520365104e-05,
      "loss": 1.2163,
      "step": 21
    },
    {
      "epoch": 0.005030919190860497,
      "grad_norm": 0.3282659649848938,
      "learning_rate": 9.979871469976196e-05,
      "loss": 1.2312,
      "step": 24
    },
    {
      "epoch": 0.005659784089718059,
      "grad_norm": 0.3265891373157501,
      "learning_rate": 9.970330142972401e-05,
      "loss": 1.2505,
      "step": 27
    },
    {
      "epoch": 0.006288648988575621,
      "grad_norm": 0.3450949192047119,
      "learning_rate": 9.95895006911623e-05,
      "loss": 1.1982,
      "step": 30
    },
    {
      "epoch": 0.0069175138874331835,
      "grad_norm": 0.3153296411037445,
      "learning_rate": 9.945735458404681e-05,
      "loss": 1.1669,
      "step": 33
    },
    {
      "epoch": 0.0075463787862907455,
      "grad_norm": 0.3419332802295685,
      "learning_rate": 9.930691199511775e-05,
      "loss": 1.2492,
      "step": 36
    },
    {
      "epoch": 0.008175243685148307,
      "grad_norm": 0.2867058515548706,
      "learning_rate": 9.91382285798002e-05,
      "loss": 1.1652,
      "step": 39
    },
    {
      "epoch": 0.00880410858400587,
      "grad_norm": 0.3220820426940918,
      "learning_rate": 9.895136674161465e-05,
      "loss": 1.1996,
      "step": 42
    },
    {
      "epoch": 0.00880410858400587,
      "eval_loss": 1.1905547380447388,
      "eval_runtime": 165.0006,
      "eval_samples_per_second": 48.697,
      "eval_steps_per_second": 6.091,
      "step": 42
    }
  ],
  "logging_steps": 3,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 42,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8959220980383744.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}