{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009978546125829467,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.978546125829467e-05,
      "grad_norm": 11569.4560546875,
      "learning_rate": 2e-05,
      "loss": 647.6416,
      "step": 1
    },
    {
      "epoch": 0.00019957092251658934,
      "grad_norm": 6468.01513671875,
      "learning_rate": 4e-05,
      "loss": 1051.7023,
      "step": 2
    },
    {
      "epoch": 0.000299356383774884,
      "grad_norm": 5256.70947265625,
      "learning_rate": 6e-05,
      "loss": 575.7077,
      "step": 3
    },
    {
      "epoch": 0.000299356383774884,
      "eval_loss": 182.73513793945312,
      "eval_runtime": 66.5171,
      "eval_samples_per_second": 63.442,
      "eval_steps_per_second": 31.721,
      "step": 3
    },
    {
      "epoch": 0.0003991418450331787,
      "grad_norm": 1647.935546875,
      "learning_rate": 8e-05,
      "loss": 771.6786,
      "step": 4
    },
    {
      "epoch": 0.0004989273062914733,
      "grad_norm": 3978.550048828125,
      "learning_rate": 0.0001,
      "loss": 1076.403,
      "step": 5
    },
    {
      "epoch": 0.000598712767549768,
      "grad_norm": 2238.62353515625,
      "learning_rate": 0.00012,
      "loss": 962.5692,
      "step": 6
    },
    {
      "epoch": 0.000598712767549768,
      "eval_loss": 182.6677703857422,
      "eval_runtime": 69.995,
      "eval_samples_per_second": 60.29,
      "eval_steps_per_second": 30.145,
      "step": 6
    },
    {
      "epoch": 0.0006984982288080626,
      "grad_norm": 1263.8529052734375,
      "learning_rate": 0.00014,
      "loss": 576.2386,
      "step": 7
    },
    {
      "epoch": 0.0007982836900663574,
      "grad_norm": 1995.560302734375,
      "learning_rate": 0.00016,
      "loss": 867.7949,
      "step": 8
    },
    {
      "epoch": 0.000898069151324652,
      "grad_norm": 1757.4945068359375,
      "learning_rate": 0.00018,
      "loss": 537.9006,
      "step": 9
    },
    {
      "epoch": 0.000898069151324652,
      "eval_loss": 182.59548950195312,
      "eval_runtime": 71.6127,
      "eval_samples_per_second": 58.928,
      "eval_steps_per_second": 29.464,
      "step": 9
    },
    {
      "epoch": 0.0009978546125829467,
      "grad_norm": 2451.3212890625,
      "learning_rate": 0.0002,
      "loss": 776.4106,
      "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": 11074975825920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}