{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04094165813715456,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001364721937905152,
      "eval_loss": 11.113584518432617,
      "eval_runtime": 2.2913,
      "eval_samples_per_second": 134.857,
      "eval_steps_per_second": 67.647,
      "step": 1
    },
    {
      "epoch": 0.0040941658137154556,
      "grad_norm": 1.9208190441131592,
      "learning_rate": 6e-05,
      "loss": 44.4814,
      "step": 3
    },
    {
      "epoch": 0.008188331627430911,
      "grad_norm": 1.8466147184371948,
      "learning_rate": 0.00012,
      "loss": 44.4149,
      "step": 6
    },
    {
      "epoch": 0.010917775503241215,
      "eval_loss": 11.091691017150879,
      "eval_runtime": 1.1447,
      "eval_samples_per_second": 269.934,
      "eval_steps_per_second": 135.404,
      "step": 8
    },
    {
      "epoch": 0.012282497441146366,
      "grad_norm": 1.8949085474014282,
      "learning_rate": 0.00018,
      "loss": 44.3801,
      "step": 9
    },
    {
      "epoch": 0.016376663254861822,
      "grad_norm": 1.9843776226043701,
      "learning_rate": 0.00019510565162951537,
      "loss": 44.3308,
      "step": 12
    },
    {
      "epoch": 0.02047082906857728,
      "grad_norm": 2.286764621734619,
      "learning_rate": 0.00017071067811865476,
      "loss": 44.1818,
      "step": 15
    },
    {
      "epoch": 0.02183555100648243,
      "eval_loss": 11.02480411529541,
      "eval_runtime": 1.1864,
      "eval_samples_per_second": 260.46,
      "eval_steps_per_second": 130.652,
      "step": 16
    },
    {
      "epoch": 0.02456499488229273,
      "grad_norm": 2.0422329902648926,
      "learning_rate": 0.00013090169943749476,
      "loss": 44.0678,
      "step": 18
    },
    {
      "epoch": 0.028659160696008188,
      "grad_norm": 2.2774696350097656,
      "learning_rate": 8.435655349597689e-05,
      "loss": 43.9817,
      "step": 21
    },
    {
      "epoch": 0.032753326509723645,
      "grad_norm": 2.248439073562622,
      "learning_rate": 4.12214747707527e-05,
      "loss": 43.9821,
      "step": 24
    },
    {
      "epoch": 0.032753326509723645,
      "eval_loss": 10.980461120605469,
      "eval_runtime": 1.1906,
      "eval_samples_per_second": 259.526,
      "eval_steps_per_second": 130.183,
      "step": 24
    },
    {
      "epoch": 0.0368474923234391,
      "grad_norm": 2.1170878410339355,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 43.8709,
      "step": 27
    },
    {
      "epoch": 0.04094165813715456,
      "grad_norm": 2.1071853637695312,
      "learning_rate": 0.0,
      "loss": 43.9185,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 623986606080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}