{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07654037504783773,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015308075009567547,
      "eval_loss": 11.930340766906738,
      "eval_runtime": 2.4639,
      "eval_samples_per_second": 111.612,
      "eval_steps_per_second": 56.009,
      "step": 1
    },
    {
      "epoch": 0.007654037504783774,
      "grad_norm": 0.0312897264957428,
      "learning_rate": 5e-05,
      "loss": 11.9322,
      "step": 5
    },
    {
      "epoch": 0.015308075009567547,
      "grad_norm": 0.039276644587516785,
      "learning_rate": 0.0001,
      "loss": 11.9333,
      "step": 10
    },
    {
      "epoch": 0.015308075009567547,
      "eval_loss": 11.930255889892578,
      "eval_runtime": 2.5279,
      "eval_samples_per_second": 108.786,
      "eval_steps_per_second": 54.591,
      "step": 10
    },
    {
      "epoch": 0.022962112514351322,
      "grad_norm": 0.02124314196407795,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9322,
      "step": 15
    },
    {
      "epoch": 0.030616150019135095,
      "grad_norm": 0.032384973019361496,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9338,
      "step": 20
    },
    {
      "epoch": 0.030616150019135095,
      "eval_loss": 11.930079460144043,
      "eval_runtime": 2.5894,
      "eval_samples_per_second": 106.202,
      "eval_steps_per_second": 53.294,
      "step": 20
    },
    {
      "epoch": 0.038270187523918864,
      "grad_norm": 0.039438918232917786,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9316,
      "step": 25
    },
    {
      "epoch": 0.045924225028702644,
      "grad_norm": 0.028815919533371925,
      "learning_rate": 5e-05,
      "loss": 11.9276,
      "step": 30
    },
    {
      "epoch": 0.045924225028702644,
      "eval_loss": 11.929950714111328,
      "eval_runtime": 2.6792,
      "eval_samples_per_second": 102.642,
      "eval_steps_per_second": 51.508,
      "step": 30
    },
    {
      "epoch": 0.053578262533486416,
      "grad_norm": 0.031004685908555984,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.9292,
      "step": 35
    },
    {
      "epoch": 0.06123230003827019,
      "grad_norm": 0.01803305745124817,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9333,
      "step": 40
    },
    {
      "epoch": 0.06123230003827019,
      "eval_loss": 11.92988395690918,
      "eval_runtime": 2.5801,
      "eval_samples_per_second": 106.584,
      "eval_steps_per_second": 53.486,
      "step": 40
    },
    {
      "epoch": 0.06888633754305395,
      "grad_norm": 0.030537074431777,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9303,
      "step": 45
    },
    {
      "epoch": 0.07654037504783773,
      "grad_norm": 0.03054003417491913,
      "learning_rate": 0.0,
      "loss": 11.9296,
      "step": 50
    },
    {
      "epoch": 0.07654037504783773,
      "eval_loss": 11.9298734664917,
      "eval_runtime": 2.5484,
      "eval_samples_per_second": 107.911,
      "eval_steps_per_second": 54.152,
      "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": 5908070400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}