{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016444934138038778,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.288986827607755e-05,
      "eval_loss": 2.7174880504608154,
      "eval_runtime": 2003.7503,
      "eval_samples_per_second": 6.389,
      "eval_steps_per_second": 3.195,
      "step": 1
    },
    {
      "epoch": 0.00016444934138038777,
      "grad_norm": 2.426621198654175,
      "learning_rate": 5e-05,
      "loss": 2.868,
      "step": 5
    },
    {
      "epoch": 0.00032889868276077554,
      "grad_norm": 2.9332046508789062,
      "learning_rate": 0.0001,
      "loss": 2.5314,
      "step": 10
    },
    {
      "epoch": 0.00032889868276077554,
      "eval_loss": 2.367553234100342,
      "eval_runtime": 2011.9959,
      "eval_samples_per_second": 6.363,
      "eval_steps_per_second": 3.181,
      "step": 10
    },
    {
      "epoch": 0.0004933480241411634,
      "grad_norm": 4.122739315032959,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1846,
      "step": 15
    },
    {
      "epoch": 0.0006577973655215511,
      "grad_norm": 3.268714666366577,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8726,
      "step": 20
    },
    {
      "epoch": 0.0006577973655215511,
      "eval_loss": 1.9326378107070923,
      "eval_runtime": 2011.5789,
      "eval_samples_per_second": 6.364,
      "eval_steps_per_second": 3.182,
      "step": 20
    },
    {
      "epoch": 0.0008222467069019389,
      "grad_norm": 3.4149394035339355,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8818,
      "step": 25
    },
    {
      "epoch": 0.0009866960482823267,
      "grad_norm": 3.685523509979248,
      "learning_rate": 5e-05,
      "loss": 1.9131,
      "step": 30
    },
    {
      "epoch": 0.0009866960482823267,
      "eval_loss": 1.8097310066223145,
      "eval_runtime": 2004.0665,
      "eval_samples_per_second": 6.388,
      "eval_steps_per_second": 3.194,
      "step": 30
    },
    {
      "epoch": 0.0011511453896627143,
      "grad_norm": 3.57448148727417,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.6267,
      "step": 35
    },
    {
      "epoch": 0.0013155947310431021,
      "grad_norm": 4.118277549743652,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.9963,
      "step": 40
    },
    {
      "epoch": 0.0013155947310431021,
      "eval_loss": 1.7459853887557983,
      "eval_runtime": 2010.8862,
      "eval_samples_per_second": 6.366,
      "eval_steps_per_second": 3.183,
      "step": 40
    },
    {
      "epoch": 0.00148004407242349,
      "grad_norm": 3.1414225101470947,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.8742,
      "step": 45
    },
    {
      "epoch": 0.0016444934138038778,
      "grad_norm": 4.184607028961182,
      "learning_rate": 0.0,
      "loss": 1.6942,
      "step": 50
    },
    {
      "epoch": 0.0016444934138038778,
      "eval_loss": 1.7354694604873657,
      "eval_runtime": 2007.8581,
      "eval_samples_per_second": 6.376,
      "eval_steps_per_second": 3.188,
      "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": 1.9110914162688e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}