{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008389965601141035,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7966552003803452e-05,
      "eval_loss": 1.7269418239593506,
      "eval_runtime": 1831.0295,
      "eval_samples_per_second": 8.223,
      "eval_steps_per_second": 4.111,
      "step": 1
    },
    {
      "epoch": 8.389965601141036e-05,
      "grad_norm": 0.8598058819770813,
      "learning_rate": 6e-05,
      "loss": 1.6654,
      "step": 3
    },
    {
      "epoch": 0.00013983276001901726,
      "eval_loss": 1.605461835861206,
      "eval_runtime": 1842.0391,
      "eval_samples_per_second": 8.174,
      "eval_steps_per_second": 4.087,
      "step": 5
    },
    {
      "epoch": 0.00016779931202282072,
      "grad_norm": 0.9945847392082214,
      "learning_rate": 0.00012,
      "loss": 1.6924,
      "step": 6
    },
    {
      "epoch": 0.0002516989680342311,
      "grad_norm": 0.5602508187294006,
      "learning_rate": 0.00018,
      "loss": 1.4559,
      "step": 9
    },
    {
      "epoch": 0.0002796655200380345,
      "eval_loss": 1.327162504196167,
      "eval_runtime": 1838.8693,
      "eval_samples_per_second": 8.188,
      "eval_steps_per_second": 4.094,
      "step": 10
    },
    {
      "epoch": 0.00033559862404564144,
      "grad_norm": 0.8673509955406189,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3144,
      "step": 12
    },
    {
      "epoch": 0.00041949828005705174,
      "grad_norm": 0.7220252752304077,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.2095,
      "step": 15
    },
    {
      "epoch": 0.00041949828005705174,
      "eval_loss": 1.233842372894287,
      "eval_runtime": 1838.0633,
      "eval_samples_per_second": 8.191,
      "eval_steps_per_second": 4.096,
      "step": 15
    },
    {
      "epoch": 0.0005033979360684622,
      "grad_norm": 0.5835627913475037,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2566,
      "step": 18
    },
    {
      "epoch": 0.000559331040076069,
      "eval_loss": 1.2087029218673706,
      "eval_runtime": 1834.2779,
      "eval_samples_per_second": 8.208,
      "eval_steps_per_second": 4.104,
      "step": 20
    },
    {
      "epoch": 0.0005872975920798725,
      "grad_norm": 0.5474965572357178,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.1812,
      "step": 21
    },
    {
      "epoch": 0.0006711972480912829,
      "grad_norm": 0.45622146129608154,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.1839,
      "step": 24
    },
    {
      "epoch": 0.0006991638000950863,
      "eval_loss": 1.191240668296814,
      "eval_runtime": 1835.1225,
      "eval_samples_per_second": 8.204,
      "eval_steps_per_second": 4.102,
      "step": 25
    },
    {
      "epoch": 0.0007550969041026932,
      "grad_norm": 0.4854365885257721,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.1041,
      "step": 27
    },
    {
      "epoch": 0.0008389965601141035,
      "grad_norm": 0.43934768438339233,
      "learning_rate": 0.0,
      "loss": 1.1416,
      "step": 30
    },
    {
      "epoch": 0.0008389965601141035,
      "eval_loss": 1.188349962234497,
      "eval_runtime": 1836.1198,
      "eval_samples_per_second": 8.2,
      "eval_steps_per_second": 4.1,
      "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": 9916411753267200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}