{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02002803925495694,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004005607850991388,
      "eval_loss": 2.8761134147644043,
      "eval_runtime": 88.4066,
      "eval_samples_per_second": 11.9,
      "eval_steps_per_second": 5.95,
      "step": 1
    },
    {
      "epoch": 0.002002803925495694,
      "grad_norm": 1.1965816020965576,
      "learning_rate": 5e-05,
      "loss": 3.1294,
      "step": 5
    },
    {
      "epoch": 0.004005607850991388,
      "grad_norm": 1.7420775890350342,
      "learning_rate": 0.0001,
      "loss": 2.8522,
      "step": 10
    },
    {
      "epoch": 0.004005607850991388,
      "eval_loss": 2.6015660762786865,
      "eval_runtime": 93.0323,
      "eval_samples_per_second": 11.308,
      "eval_steps_per_second": 5.654,
      "step": 10
    },
    {
      "epoch": 0.006008411776487082,
      "grad_norm": 1.9736239910125732,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.328,
      "step": 15
    },
    {
      "epoch": 0.008011215701982776,
      "grad_norm": 1.6762070655822754,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.2283,
      "step": 20
    },
    {
      "epoch": 0.008011215701982776,
      "eval_loss": 2.1456990242004395,
      "eval_runtime": 93.8832,
      "eval_samples_per_second": 11.205,
      "eval_steps_per_second": 5.603,
      "step": 20
    },
    {
      "epoch": 0.01001401962747847,
      "grad_norm": 0.9321993589401245,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.105,
      "step": 25
    },
    {
      "epoch": 0.012016823552974164,
      "grad_norm": 1.2267812490463257,
      "learning_rate": 5e-05,
      "loss": 2.0925,
      "step": 30
    },
    {
      "epoch": 0.012016823552974164,
      "eval_loss": 2.050027847290039,
      "eval_runtime": 93.9806,
      "eval_samples_per_second": 11.194,
      "eval_steps_per_second": 5.597,
      "step": 30
    },
    {
      "epoch": 0.014019627478469857,
      "grad_norm": 1.4538365602493286,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.1745,
      "step": 35
    },
    {
      "epoch": 0.016022431403965552,
      "grad_norm": 1.468965768814087,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.0499,
      "step": 40
    },
    {
      "epoch": 0.016022431403965552,
      "eval_loss": 2.015484571456909,
      "eval_runtime": 93.919,
      "eval_samples_per_second": 11.201,
      "eval_steps_per_second": 5.601,
      "step": 40
    },
    {
      "epoch": 0.018025235329461247,
      "grad_norm": 0.7921549677848816,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.2987,
      "step": 45
    },
    {
      "epoch": 0.02002803925495694,
      "grad_norm": 1.3731557130813599,
      "learning_rate": 0.0,
      "loss": 1.8412,
      "step": 50
    },
    {
      "epoch": 0.02002803925495694,
      "eval_loss": 2.0088131427764893,
      "eval_runtime": 94.1006,
      "eval_samples_per_second": 11.18,
      "eval_steps_per_second": 5.59,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9386538559340544.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}