{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008592910848549946,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "grad_norm": 0.399495393037796,
      "learning_rate": 2e-05,
      "loss": 41.4955,
      "step": 1
    },
    {
      "epoch": 0.0017185821697099893,
      "grad_norm": 0.365960031747818,
      "learning_rate": 4e-05,
      "loss": 41.5073,
      "step": 2
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 0.6799790263175964,
      "learning_rate": 6e-05,
      "loss": 41.5244,
      "step": 3
    },
    {
      "epoch": 0.0025778732545649837,
      "eval_loss": 10.379504203796387,
      "eval_runtime": 6.1326,
      "eval_samples_per_second": 79.9,
      "eval_steps_per_second": 39.95,
      "step": 3
    },
    {
      "epoch": 0.0034371643394199786,
      "grad_norm": 0.4746178388595581,
      "learning_rate": 8e-05,
      "loss": 41.5519,
      "step": 4
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 0.5340287089347839,
      "learning_rate": 0.0001,
      "loss": 41.4976,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 0.3955802619457245,
      "learning_rate": 0.00012,
      "loss": 41.527,
      "step": 6
    },
    {
      "epoch": 0.0051557465091299675,
      "eval_loss": 10.379013061523438,
      "eval_runtime": 7.4038,
      "eval_samples_per_second": 66.182,
      "eval_steps_per_second": 33.091,
      "step": 6
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": 0.697852611541748,
      "learning_rate": 0.00014,
      "loss": 41.5214,
      "step": 7
    },
    {
      "epoch": 0.006874328678839957,
      "grad_norm": 0.40399518609046936,
      "learning_rate": 0.00016,
      "loss": 41.4978,
      "step": 8
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 0.5647799968719482,
      "learning_rate": 0.00018,
      "loss": 41.5329,
      "step": 9
    },
    {
      "epoch": 0.007733619763694952,
      "eval_loss": 10.37820053100586,
      "eval_runtime": 6.0646,
      "eval_samples_per_second": 80.797,
      "eval_steps_per_second": 40.399,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 0.5523791909217834,
      "learning_rate": 0.0002,
      "loss": 41.4634,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 391388430336.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}