{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012391573729863693,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012391573729863693,
      "grad_norm": 2.0740199089050293,
      "learning_rate": 2e-05,
      "loss": 1.2225,
      "step": 1
    },
    {
      "epoch": 0.0012391573729863693,
      "eval_loss": 1.1873403787612915,
      "eval_runtime": 14.6162,
      "eval_samples_per_second": 23.262,
      "eval_steps_per_second": 11.631,
      "step": 1
    },
    {
      "epoch": 0.0024783147459727386,
      "grad_norm": 1.9419535398483276,
      "learning_rate": 4e-05,
      "loss": 1.1186,
      "step": 2
    },
    {
      "epoch": 0.0037174721189591076,
      "grad_norm": 1.8858602046966553,
      "learning_rate": 6e-05,
      "loss": 1.0949,
      "step": 3
    },
    {
      "epoch": 0.0037174721189591076,
      "eval_loss": 1.1718430519104004,
      "eval_runtime": 13.4878,
      "eval_samples_per_second": 25.208,
      "eval_steps_per_second": 12.604,
      "step": 3
    },
    {
      "epoch": 0.004956629491945477,
      "grad_norm": 2.060594320297241,
      "learning_rate": 8e-05,
      "loss": 1.1871,
      "step": 4
    },
    {
      "epoch": 0.006195786864931847,
      "grad_norm": 1.6668012142181396,
      "learning_rate": 0.0001,
      "loss": 1.1095,
      "step": 5
    },
    {
      "epoch": 0.007434944237918215,
      "grad_norm": 1.9496322870254517,
      "learning_rate": 0.00012,
      "loss": 1.0091,
      "step": 6
    },
    {
      "epoch": 0.007434944237918215,
      "eval_loss": 0.9973742961883545,
      "eval_runtime": 13.6122,
      "eval_samples_per_second": 24.978,
      "eval_steps_per_second": 12.489,
      "step": 6
    },
    {
      "epoch": 0.008674101610904586,
      "grad_norm": 1.8269734382629395,
      "learning_rate": 0.00014,
      "loss": 0.926,
      "step": 7
    },
    {
      "epoch": 0.009913258983890954,
      "grad_norm": 2.080160140991211,
      "learning_rate": 0.00016,
      "loss": 0.8306,
      "step": 8
    },
    {
      "epoch": 0.011152416356877323,
      "grad_norm": 1.5973968505859375,
      "learning_rate": 0.00018,
      "loss": 1.0558,
      "step": 9
    },
    {
      "epoch": 0.011152416356877323,
      "eval_loss": 0.8688002824783325,
      "eval_runtime": 13.6495,
      "eval_samples_per_second": 24.909,
      "eval_steps_per_second": 12.455,
      "step": 9
    },
    {
      "epoch": 0.012391573729863693,
      "grad_norm": 1.6963117122650146,
      "learning_rate": 0.0002,
      "loss": 0.8643,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2112182707814400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}