{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0030440473653770054,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.08809473075401e-05,
      "eval_loss": 6.931131362915039,
      "eval_runtime": 656.8644,
      "eval_samples_per_second": 10.529,
      "eval_steps_per_second": 5.264,
      "step": 1
    },
    {
      "epoch": 0.00030440473653770055,
      "grad_norm": 45.05469512939453,
      "learning_rate": 5e-05,
      "loss": 27.2097,
      "step": 5
    },
    {
      "epoch": 0.0006088094730754011,
      "grad_norm": 40.21764373779297,
      "learning_rate": 0.0001,
      "loss": 19.0893,
      "step": 10
    },
    {
      "epoch": 0.0006088094730754011,
      "eval_loss": 2.306489944458008,
      "eval_runtime": 658.2084,
      "eval_samples_per_second": 10.507,
      "eval_steps_per_second": 5.254,
      "step": 10
    },
    {
      "epoch": 0.0009132142096131016,
      "grad_norm": 13.2877779006958,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.675,
      "step": 15
    },
    {
      "epoch": 0.0012176189461508022,
      "grad_norm": 7.806561470031738,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.4316,
      "step": 20
    },
    {
      "epoch": 0.0012176189461508022,
      "eval_loss": 0.07837376743555069,
      "eval_runtime": 656.503,
      "eval_samples_per_second": 10.535,
      "eval_steps_per_second": 5.267,
      "step": 20
    },
    {
      "epoch": 0.0015220236826885027,
      "grad_norm": 2.9194090366363525,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9073,
      "step": 25
    },
    {
      "epoch": 0.0018264284192262032,
      "grad_norm": 23.289958953857422,
      "learning_rate": 5e-05,
      "loss": 0.6673,
      "step": 30
    },
    {
      "epoch": 0.0018264284192262032,
      "eval_loss": 0.07907278090715408,
      "eval_runtime": 658.9663,
      "eval_samples_per_second": 10.495,
      "eval_steps_per_second": 5.248,
      "step": 30
    },
    {
      "epoch": 0.002130833155763904,
      "grad_norm": 13.350411415100098,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.3659,
      "step": 35
    },
    {
      "epoch": 0.0024352378923016044,
      "grad_norm": 2.5347867012023926,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2356,
      "step": 40
    },
    {
      "epoch": 0.0024352378923016044,
      "eval_loss": 0.0975862666964531,
      "eval_runtime": 658.7808,
      "eval_samples_per_second": 10.498,
      "eval_steps_per_second": 5.249,
      "step": 40
    },
    {
      "epoch": 0.002739642628839305,
      "grad_norm": 1.3288694620132446,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.2834,
      "step": 45
    },
    {
      "epoch": 0.0030440473653770054,
      "grad_norm": 12.975996971130371,
      "learning_rate": 0.0,
      "loss": 0.3669,
      "step": 50
    },
    {
      "epoch": 0.0030440473653770054,
      "eval_loss": 0.07795499265193939,
      "eval_runtime": 657.4379,
      "eval_samples_per_second": 10.52,
      "eval_steps_per_second": 5.26,
      "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": 1.4260472119296e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}