{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.037993920972644375,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007598784194528875,
      "eval_loss": 8.610437393188477,
      "eval_runtime": 7.5213,
      "eval_samples_per_second": 73.791,
      "eval_steps_per_second": 36.962,
      "step": 1
    },
    {
      "epoch": 0.003799392097264438,
      "grad_norm": 3.1603012084960938,
      "learning_rate": 5e-05,
      "loss": 8.5891,
      "step": 5
    },
    {
      "epoch": 0.007598784194528876,
      "grad_norm": 2.109530448913574,
      "learning_rate": 0.0001,
      "loss": 8.2812,
      "step": 10
    },
    {
      "epoch": 0.007598784194528876,
      "eval_loss": 8.542115211486816,
      "eval_runtime": 7.519,
      "eval_samples_per_second": 73.813,
      "eval_steps_per_second": 36.973,
      "step": 10
    },
    {
      "epoch": 0.011398176291793313,
      "grad_norm": 2.883855104446411,
      "learning_rate": 9.619397662556435e-05,
      "loss": 8.3708,
      "step": 15
    },
    {
      "epoch": 0.015197568389057751,
      "grad_norm": 2.5980207920074463,
      "learning_rate": 8.535533905932738e-05,
      "loss": 8.1666,
      "step": 20
    },
    {
      "epoch": 0.015197568389057751,
      "eval_loss": 8.359399795532227,
      "eval_runtime": 7.655,
      "eval_samples_per_second": 72.502,
      "eval_steps_per_second": 36.316,
      "step": 20
    },
    {
      "epoch": 0.018996960486322188,
      "grad_norm": 3.1167116165161133,
      "learning_rate": 6.91341716182545e-05,
      "loss": 8.095,
      "step": 25
    },
    {
      "epoch": 0.022796352583586626,
      "grad_norm": 2.891735792160034,
      "learning_rate": 5e-05,
      "loss": 8.1248,
      "step": 30
    },
    {
      "epoch": 0.022796352583586626,
      "eval_loss": 8.240621566772461,
      "eval_runtime": 7.7515,
      "eval_samples_per_second": 71.599,
      "eval_steps_per_second": 35.864,
      "step": 30
    },
    {
      "epoch": 0.026595744680851064,
      "grad_norm": 2.1788597106933594,
      "learning_rate": 3.086582838174551e-05,
      "loss": 7.9935,
      "step": 35
    },
    {
      "epoch": 0.030395136778115502,
      "grad_norm": 2.944188356399536,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 8.1376,
      "step": 40
    },
    {
      "epoch": 0.030395136778115502,
      "eval_loss": 8.18637752532959,
      "eval_runtime": 7.9085,
      "eval_samples_per_second": 70.177,
      "eval_steps_per_second": 35.152,
      "step": 40
    },
    {
      "epoch": 0.03419452887537994,
      "grad_norm": 2.2056612968444824,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 8.1537,
      "step": 45
    },
    {
      "epoch": 0.037993920972644375,
      "grad_norm": 2.681415319442749,
      "learning_rate": 0.0,
      "loss": 8.181,
      "step": 50
    },
    {
      "epoch": 0.037993920972644375,
      "eval_loss": 8.177650451660156,
      "eval_runtime": 7.6687,
      "eval_samples_per_second": 72.372,
      "eval_steps_per_second": 36.251,
      "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": 6178892808192.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}