{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 11.764705882352942,
  "eval_steps": 20,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.058823529411764705,
      "eval_loss": 2.5443625450134277,
      "eval_runtime": 14.3878,
      "eval_samples_per_second": 104.324,
      "eval_steps_per_second": 2.433,
      "step": 1
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 2.671875,
      "learning_rate": 0.0001,
      "loss": 2.2541,
      "step": 10
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 3.65625,
      "learning_rate": 0.0002,
      "loss": 2.0275,
      "step": 20
    },
    {
      "epoch": 1.1764705882352942,
      "eval_loss": 2.187530517578125,
      "eval_runtime": 13.8986,
      "eval_samples_per_second": 107.996,
      "eval_steps_per_second": 2.518,
      "step": 20
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 2.15625,
      "learning_rate": 0.000199658449300667,
      "loss": 1.5265,
      "step": 30
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 2.40625,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.1034,
      "step": 40
    },
    {
      "epoch": 2.3529411764705883,
      "eval_loss": 2.58608341217041,
      "eval_runtime": 14.5728,
      "eval_samples_per_second": 103.0,
      "eval_steps_per_second": 2.402,
      "step": 40
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 3.078125,
      "learning_rate": 0.00019694002659393305,
      "loss": 0.8112,
      "step": 50
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 3.6875,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.3839,
      "step": 60
    },
    {
      "epoch": 3.5294117647058822,
      "eval_loss": 2.9881904125213623,
      "eval_runtime": 15.7638,
      "eval_samples_per_second": 95.218,
      "eval_steps_per_second": 2.22,
      "step": 60
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 1.3125,
      "learning_rate": 0.00019157733266550575,
      "loss": 0.3102,
      "step": 70
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 1.6171875,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.1897,
      "step": 80
    },
    {
      "epoch": 4.705882352941177,
      "eval_loss": 3.129960536956787,
      "eval_runtime": 14.6965,
      "eval_samples_per_second": 102.133,
      "eval_steps_per_second": 2.382,
      "step": 80
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 1.25,
      "learning_rate": 0.00018371664782625287,
      "loss": 0.1821,
      "step": 90
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 1.3828125,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.1432,
      "step": 100
    },
    {
      "epoch": 5.882352941176471,
      "eval_loss": 3.274164915084839,
      "eval_runtime": 15.1902,
      "eval_samples_per_second": 98.814,
      "eval_steps_per_second": 2.304,
      "step": 100
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00017357239106731317,
      "loss": 0.1188,
      "step": 110
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.78125,
      "learning_rate": 0.00016772815716257412,
      "loss": 0.1193,
      "step": 120
    },
    {
      "epoch": 7.0588235294117645,
      "eval_loss": 3.397793769836426,
      "eval_runtime": 14.573,
      "eval_samples_per_second": 102.998,
      "eval_steps_per_second": 2.402,
      "step": 120
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 1.0546875,
      "learning_rate": 0.0001614212712689668,
      "loss": 0.0733,
      "step": 130
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 0.69921875,
      "learning_rate": 0.00015469481581224272,
      "loss": 0.0776,
      "step": 140
    },
    {
      "epoch": 8.235294117647058,
      "eval_loss": 3.6323835849761963,
      "eval_runtime": 14.197,
      "eval_samples_per_second": 105.726,
      "eval_steps_per_second": 2.465,
      "step": 140
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 0.76171875,
      "learning_rate": 0.00014759473930370736,
      "loss": 0.0647,
      "step": 150
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 0.67578125,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.0456,
      "step": 160
    },
    {
      "epoch": 9.411764705882353,
      "eval_loss": 3.7919914722442627,
      "eval_runtime": 15.5596,
      "eval_samples_per_second": 96.468,
      "eval_steps_per_second": 2.249,
      "step": 160
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.62109375,
      "learning_rate": 0.00013246994692046836,
      "loss": 0.0373,
      "step": 170
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 0.349609375,
      "learning_rate": 0.00012454854871407994,
      "loss": 0.0152,
      "step": 180
    },
    {
      "epoch": 10.588235294117647,
      "eval_loss": 3.9090092182159424,
      "eval_runtime": 15.4377,
      "eval_samples_per_second": 97.23,
      "eval_steps_per_second": 2.267,
      "step": 180
    },
    {
      "epoch": 11.176470588235293,
      "grad_norm": 0.134765625,
      "learning_rate": 0.00011645945902807341,
      "loss": 0.0121,
      "step": 190
    },
    {
      "epoch": 11.764705882352942,
      "grad_norm": 0.1884765625,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.0051,
      "step": 200
    },
    {
      "epoch": 11.764705882352942,
      "eval_loss": 4.041390419006348,
      "eval_runtime": 14.6874,
      "eval_samples_per_second": 102.197,
      "eval_steps_per_second": 2.383,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 24,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0433372297468314e+17,
  "train_batch_size": 11,
  "trial_name": null,
  "trial_params": null
}