{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06389776357827476,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002129925452609159,
      "eval_loss": 3.5438625812530518,
      "eval_runtime": 25.4787,
      "eval_samples_per_second": 7.771,
      "eval_steps_per_second": 3.886,
      "step": 1
    },
    {
      "epoch": 0.006389776357827476,
      "grad_norm": 2.2887728214263916,
      "learning_rate": 6e-05,
      "loss": 3.4855,
      "step": 3
    },
    {
      "epoch": 0.012779552715654952,
      "grad_norm": 2.4641361236572266,
      "learning_rate": 0.00012,
      "loss": 3.5091,
      "step": 6
    },
    {
      "epoch": 0.01703940362087327,
      "eval_loss": 2.8688793182373047,
      "eval_runtime": 25.4627,
      "eval_samples_per_second": 7.776,
      "eval_steps_per_second": 3.888,
      "step": 8
    },
    {
      "epoch": 0.019169329073482427,
      "grad_norm": 2.2242677211761475,
      "learning_rate": 0.00018,
      "loss": 2.8897,
      "step": 9
    },
    {
      "epoch": 0.025559105431309903,
      "grad_norm": 2.309509515762329,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.7125,
      "step": 12
    },
    {
      "epoch": 0.03194888178913738,
      "grad_norm": 2.2507786750793457,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.6185,
      "step": 15
    },
    {
      "epoch": 0.03407880724174654,
      "eval_loss": 2.331763505935669,
      "eval_runtime": 25.5887,
      "eval_samples_per_second": 7.738,
      "eval_steps_per_second": 3.869,
      "step": 16
    },
    {
      "epoch": 0.038338658146964855,
      "grad_norm": 1.899119257926941,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.4637,
      "step": 18
    },
    {
      "epoch": 0.04472843450479233,
      "grad_norm": 2.4376401901245117,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.9915,
      "step": 21
    },
    {
      "epoch": 0.051118210862619806,
      "grad_norm": 2.1409995555877686,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.3439,
      "step": 24
    },
    {
      "epoch": 0.051118210862619806,
      "eval_loss": 2.130235195159912,
      "eval_runtime": 25.6379,
      "eval_samples_per_second": 7.723,
      "eval_steps_per_second": 3.861,
      "step": 24
    },
    {
      "epoch": 0.05750798722044728,
      "grad_norm": 2.9437363147735596,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.297,
      "step": 27
    },
    {
      "epoch": 0.06389776357827476,
      "grad_norm": 2.069322347640991,
      "learning_rate": 0.0,
      "loss": 2.0593,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}