{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09803921568627451,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032679738562091504,
      "eval_loss": 35.99869155883789,
      "eval_runtime": 1.3572,
      "eval_samples_per_second": 95.048,
      "eval_steps_per_second": 47.893,
      "step": 1
    },
    {
      "epoch": 0.00980392156862745,
      "grad_norm": 1269.3831787109375,
      "learning_rate": 6e-05,
      "loss": 153.7508,
      "step": 3
    },
    {
      "epoch": 0.0196078431372549,
      "grad_norm": 2242.561767578125,
      "learning_rate": 0.00012,
      "loss": 142.2784,
      "step": 6
    },
    {
      "epoch": 0.026143790849673203,
      "eval_loss": 35.76251220703125,
      "eval_runtime": 0.5664,
      "eval_samples_per_second": 227.765,
      "eval_steps_per_second": 114.765,
      "step": 8
    },
    {
      "epoch": 0.029411764705882353,
      "grad_norm": 1655.751220703125,
      "learning_rate": 0.00018,
      "loss": 157.3724,
      "step": 9
    },
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 1335.5296630859375,
      "learning_rate": 0.00019510565162951537,
      "loss": 147.3951,
      "step": 12
    },
    {
      "epoch": 0.049019607843137254,
      "grad_norm": 1890.16552734375,
      "learning_rate": 0.00017071067811865476,
      "loss": 139.4409,
      "step": 15
    },
    {
      "epoch": 0.05228758169934641,
      "eval_loss": 33.9350700378418,
      "eval_runtime": 0.5664,
      "eval_samples_per_second": 227.763,
      "eval_steps_per_second": 114.764,
      "step": 16
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 2073.57763671875,
      "learning_rate": 0.00013090169943749476,
      "loss": 141.3177,
      "step": 18
    },
    {
      "epoch": 0.06862745098039216,
      "grad_norm": 1190.1522216796875,
      "learning_rate": 8.435655349597689e-05,
      "loss": 127.6396,
      "step": 21
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 1978.2467041015625,
      "learning_rate": 4.12214747707527e-05,
      "loss": 110.43,
      "step": 24
    },
    {
      "epoch": 0.0784313725490196,
      "eval_loss": 27.576690673828125,
      "eval_runtime": 0.6158,
      "eval_samples_per_second": 209.468,
      "eval_steps_per_second": 105.546,
      "step": 24
    },
    {
      "epoch": 0.08823529411764706,
      "grad_norm": 2955.03564453125,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 85.8593,
      "step": 27
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 2815.968505859375,
      "learning_rate": 0.0,
      "loss": 102.8639,
      "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": 67029675540480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}