{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02661343978709248,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008871146595697493,
      "eval_loss": 10.382826805114746,
      "eval_runtime": 1.6561,
      "eval_samples_per_second": 286.82,
      "eval_steps_per_second": 143.712,
      "step": 1
    },
    {
      "epoch": 0.0026613439787092482,
      "grad_norm": 0.09095119684934616,
      "learning_rate": 6e-05,
      "loss": 10.3843,
      "step": 3
    },
    {
      "epoch": 0.0053226879574184965,
      "grad_norm": 0.11315666884183884,
      "learning_rate": 0.00012,
      "loss": 10.3862,
      "step": 6
    },
    {
      "epoch": 0.007096917276557995,
      "eval_loss": 10.38138198852539,
      "eval_runtime": 1.6844,
      "eval_samples_per_second": 281.997,
      "eval_steps_per_second": 141.295,
      "step": 8
    },
    {
      "epoch": 0.007984031936127744,
      "grad_norm": 0.09687285125255585,
      "learning_rate": 0.00018,
      "loss": 10.3803,
      "step": 9
    },
    {
      "epoch": 0.010645375914836993,
      "grad_norm": 0.11813008040189743,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.379,
      "step": 12
    },
    {
      "epoch": 0.01330671989354624,
      "grad_norm": 0.11643451452255249,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.3807,
      "step": 15
    },
    {
      "epoch": 0.01419383455311599,
      "eval_loss": 10.377161026000977,
      "eval_runtime": 1.681,
      "eval_samples_per_second": 282.569,
      "eval_steps_per_second": 141.582,
      "step": 16
    },
    {
      "epoch": 0.015968063872255488,
      "grad_norm": 0.15684852004051208,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.3753,
      "step": 18
    },
    {
      "epoch": 0.018629407850964737,
      "grad_norm": 0.13412253558635712,
      "learning_rate": 8.435655349597689e-05,
      "loss": 10.3734,
      "step": 21
    },
    {
      "epoch": 0.021290751829673986,
      "grad_norm": 0.09824293106794357,
      "learning_rate": 4.12214747707527e-05,
      "loss": 10.372,
      "step": 24
    },
    {
      "epoch": 0.021290751829673986,
      "eval_loss": 10.374128341674805,
      "eval_runtime": 1.6832,
      "eval_samples_per_second": 282.207,
      "eval_steps_per_second": 141.4,
      "step": 24
    },
    {
      "epoch": 0.023952095808383235,
      "grad_norm": 0.1290944665670395,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 10.3796,
      "step": 27
    },
    {
      "epoch": 0.02661343978709248,
      "grad_norm": 0.15242111682891846,
      "learning_rate": 0.0,
      "loss": 10.3769,
      "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": 1000284291072.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}