{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.132890365448505,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004429678848283499,
      "eval_loss": 8.024643898010254,
      "eval_runtime": 9.0647,
      "eval_samples_per_second": 10.48,
      "eval_steps_per_second": 5.295,
      "step": 1
    },
    {
      "epoch": 0.013289036544850499,
      "grad_norm": 29.700767517089844,
      "learning_rate": 6e-05,
      "loss": 31.9959,
      "step": 3
    },
    {
      "epoch": 0.026578073089700997,
      "grad_norm": 32.594966888427734,
      "learning_rate": 0.00012,
      "loss": 30.0514,
      "step": 6
    },
    {
      "epoch": 0.035437430786267994,
      "eval_loss": 3.2749640941619873,
      "eval_runtime": 9.1032,
      "eval_samples_per_second": 10.436,
      "eval_steps_per_second": 5.273,
      "step": 8
    },
    {
      "epoch": 0.03986710963455149,
      "grad_norm": 28.02919578552246,
      "learning_rate": 0.00018,
      "loss": 17.1256,
      "step": 9
    },
    {
      "epoch": 0.053156146179401995,
      "grad_norm": 14.768317222595215,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.5283,
      "step": 12
    },
    {
      "epoch": 0.0664451827242525,
      "grad_norm": 1.5042724609375,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.8912,
      "step": 15
    },
    {
      "epoch": 0.07087486157253599,
      "eval_loss": 0.021139996126294136,
      "eval_runtime": 9.1503,
      "eval_samples_per_second": 10.382,
      "eval_steps_per_second": 5.246,
      "step": 16
    },
    {
      "epoch": 0.07973421926910298,
      "grad_norm": 0.0015086402418091893,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0001,
      "step": 18
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.0016459733014926314,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.10631229235880399,
      "grad_norm": 0.0002744944940786809,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.10631229235880399,
      "eval_loss": 1.489466626480862e-06,
      "eval_runtime": 9.1217,
      "eval_samples_per_second": 10.415,
      "eval_steps_per_second": 5.262,
      "step": 24
    },
    {
      "epoch": 0.11960132890365449,
      "grad_norm": 0.8000124096870422,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0016,
      "step": 27
    },
    {
      "epoch": 0.132890365448505,
      "grad_norm": 0.001092906342819333,
      "learning_rate": 0.0,
      "loss": 0.002,
      "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": 1.98368428032e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}