{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04363636363636364,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014545454545454545,
      "eval_loss": 0.405824214220047,
      "eval_runtime": 37.2045,
      "eval_samples_per_second": 7.795,
      "eval_steps_per_second": 3.897,
      "step": 1
    },
    {
      "epoch": 0.004363636363636364,
      "grad_norm": 0.4422492980957031,
      "learning_rate": 6e-05,
      "loss": 0.3811,
      "step": 3
    },
    {
      "epoch": 0.008727272727272728,
      "grad_norm": 0.5055964589118958,
      "learning_rate": 0.00012,
      "loss": 0.237,
      "step": 6
    },
    {
      "epoch": 0.011636363636363636,
      "eval_loss": 0.154419407248497,
      "eval_runtime": 37.2223,
      "eval_samples_per_second": 7.791,
      "eval_steps_per_second": 3.896,
      "step": 8
    },
    {
      "epoch": 0.01309090909090909,
      "grad_norm": 0.9195519089698792,
      "learning_rate": 0.00018,
      "loss": 0.2196,
      "step": 9
    },
    {
      "epoch": 0.017454545454545455,
      "grad_norm": 0.9977229833602905,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0874,
      "step": 12
    },
    {
      "epoch": 0.02181818181818182,
      "grad_norm": 0.52955162525177,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.075,
      "step": 15
    },
    {
      "epoch": 0.02327272727272727,
      "eval_loss": 0.07141619920730591,
      "eval_runtime": 37.4915,
      "eval_samples_per_second": 7.735,
      "eval_steps_per_second": 3.868,
      "step": 16
    },
    {
      "epoch": 0.02618181818181818,
      "grad_norm": 0.4917963147163391,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0604,
      "step": 18
    },
    {
      "epoch": 0.030545454545454546,
      "grad_norm": 0.5574419498443604,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0659,
      "step": 21
    },
    {
      "epoch": 0.03490909090909091,
      "grad_norm": 0.3288589119911194,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0638,
      "step": 24
    },
    {
      "epoch": 0.03490909090909091,
      "eval_loss": 0.05812034755945206,
      "eval_runtime": 37.5038,
      "eval_samples_per_second": 7.733,
      "eval_steps_per_second": 3.866,
      "step": 24
    },
    {
      "epoch": 0.03927272727272727,
      "grad_norm": 0.7242821455001831,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0807,
      "step": 27
    },
    {
      "epoch": 0.04363636363636364,
      "grad_norm": 0.5137593746185303,
      "learning_rate": 0.0,
      "loss": 0.0329,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}