{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2616516762060507,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013082583810302535,
      "grad_norm": 1.9874714612960815,
      "learning_rate": 1e-05,
      "loss": 2.9985,
      "step": 1
    },
    {
      "epoch": 0.013082583810302535,
      "eval_loss": 2.9726431369781494,
      "eval_runtime": 175.3943,
      "eval_samples_per_second": 0.735,
      "eval_steps_per_second": 0.371,
      "step": 1
    },
    {
      "epoch": 0.02616516762060507,
      "grad_norm": 2.1006743907928467,
      "learning_rate": 2e-05,
      "loss": 2.9909,
      "step": 2
    },
    {
      "epoch": 0.039247751430907606,
      "grad_norm": 1.9560920000076294,
      "learning_rate": 3e-05,
      "loss": 2.9575,
      "step": 3
    },
    {
      "epoch": 0.05233033524121014,
      "grad_norm": 1.8804231882095337,
      "learning_rate": 4e-05,
      "loss": 2.7084,
      "step": 4
    },
    {
      "epoch": 0.06541291905151267,
      "grad_norm": 2.027716875076294,
      "learning_rate": 5e-05,
      "loss": 2.9643,
      "step": 5
    },
    {
      "epoch": 0.06541291905151267,
      "eval_loss": 2.8290839195251465,
      "eval_runtime": 12.1145,
      "eval_samples_per_second": 10.648,
      "eval_steps_per_second": 5.365,
      "step": 5
    },
    {
      "epoch": 0.07849550286181521,
      "grad_norm": 2.079145908355713,
      "learning_rate": 6e-05,
      "loss": 2.8166,
      "step": 6
    },
    {
      "epoch": 0.09157808667211774,
      "grad_norm": 2.0956904888153076,
      "learning_rate": 7e-05,
      "loss": 2.8296,
      "step": 7
    },
    {
      "epoch": 0.10466067048242028,
      "grad_norm": 2.202118158340454,
      "learning_rate": 8e-05,
      "loss": 2.4754,
      "step": 8
    },
    {
      "epoch": 0.11774325429272281,
      "grad_norm": 2.1167402267456055,
      "learning_rate": 9e-05,
      "loss": 2.5891,
      "step": 9
    },
    {
      "epoch": 0.13082583810302534,
      "grad_norm": 1.9512401819229126,
      "learning_rate": 0.0001,
      "loss": 2.1561,
      "step": 10
    },
    {
      "epoch": 0.13082583810302534,
      "eval_loss": 2.1229875087738037,
      "eval_runtime": 12.1118,
      "eval_samples_per_second": 10.651,
      "eval_steps_per_second": 5.367,
      "step": 10
    },
    {
      "epoch": 0.1439084219133279,
      "grad_norm": 2.0281834602355957,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1318,
      "step": 11
    },
    {
      "epoch": 0.15699100572363042,
      "grad_norm": 1.735203742980957,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.9844,
      "step": 12
    },
    {
      "epoch": 0.17007358953393295,
      "grad_norm": 1.8242249488830566,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.7185,
      "step": 13
    },
    {
      "epoch": 0.18315617334423548,
      "grad_norm": 1.972509741783142,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9075,
      "step": 14
    },
    {
      "epoch": 0.19623875715453803,
      "grad_norm": 1.6755626201629639,
      "learning_rate": 5e-05,
      "loss": 1.6003,
      "step": 15
    },
    {
      "epoch": 0.19623875715453803,
      "eval_loss": 1.6906676292419434,
      "eval_runtime": 12.112,
      "eval_samples_per_second": 10.651,
      "eval_steps_per_second": 5.367,
      "step": 15
    },
    {
      "epoch": 0.20932134096484056,
      "grad_norm": 1.9911706447601318,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.7984,
      "step": 16
    },
    {
      "epoch": 0.2224039247751431,
      "grad_norm": 2.5861637592315674,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.8082,
      "step": 17
    },
    {
      "epoch": 0.23548650858544562,
      "grad_norm": 1.678914189338684,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.6282,
      "step": 18
    },
    {
      "epoch": 0.24856909239574815,
      "grad_norm": 1.5788204669952393,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.6303,
      "step": 19
    },
    {
      "epoch": 0.2616516762060507,
      "grad_norm": 1.6771125793457031,
      "learning_rate": 0.0,
      "loss": 1.8161,
      "step": 20
    },
    {
      "epoch": 0.2616516762060507,
      "eval_loss": 1.6098642349243164,
      "eval_runtime": 11.7603,
      "eval_samples_per_second": 10.969,
      "eval_steps_per_second": 5.527,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.641914893860864e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}