{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0050729232720355105,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001690974424011837,
      "eval_loss": 0.8131918907165527,
      "eval_runtime": 332.6955,
      "eval_samples_per_second": 7.484,
      "eval_steps_per_second": 3.742,
      "step": 1
    },
    {
      "epoch": 0.000507292327203551,
      "grad_norm": 0.23843888938426971,
      "learning_rate": 6e-05,
      "loss": 0.7429,
      "step": 3
    },
    {
      "epoch": 0.001014584654407102,
      "grad_norm": 0.25359129905700684,
      "learning_rate": 0.00012,
      "loss": 0.7015,
      "step": 6
    },
    {
      "epoch": 0.0013527795392094695,
      "eval_loss": 0.735551118850708,
      "eval_runtime": 335.9095,
      "eval_samples_per_second": 7.413,
      "eval_steps_per_second": 3.706,
      "step": 8
    },
    {
      "epoch": 0.0015218769816106531,
      "grad_norm": 0.315972238779068,
      "learning_rate": 0.00018,
      "loss": 0.717,
      "step": 9
    },
    {
      "epoch": 0.002029169308814204,
      "grad_norm": 0.3717198073863983,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.7273,
      "step": 12
    },
    {
      "epoch": 0.0025364616360177552,
      "grad_norm": 0.26527586579322815,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.6523,
      "step": 15
    },
    {
      "epoch": 0.002705559078418939,
      "eval_loss": 0.6464331746101379,
      "eval_runtime": 335.14,
      "eval_samples_per_second": 7.43,
      "eval_steps_per_second": 3.715,
      "step": 16
    },
    {
      "epoch": 0.0030437539632213063,
      "grad_norm": 0.379140168428421,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.723,
      "step": 18
    },
    {
      "epoch": 0.0035510462904248573,
      "grad_norm": 0.3034185469150543,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.6186,
      "step": 21
    },
    {
      "epoch": 0.004058338617628408,
      "grad_norm": 0.2614850103855133,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.6128,
      "step": 24
    },
    {
      "epoch": 0.004058338617628408,
      "eval_loss": 0.6241685748100281,
      "eval_runtime": 335.2606,
      "eval_samples_per_second": 7.427,
      "eval_steps_per_second": 3.714,
      "step": 24
    },
    {
      "epoch": 0.004565630944831959,
      "grad_norm": 0.2510441243648529,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.5886,
      "step": 27
    },
    {
      "epoch": 0.0050729232720355105,
      "grad_norm": 0.30792003870010376,
      "learning_rate": 0.0,
      "loss": 0.6102,
      "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": 1.0863742606639104e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}