{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 249,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.5029889345169067,
      "learning_rate": 7.2e-05,
      "loss": 1.6248924255371093,
      "step": 10
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.5242133736610413,
      "learning_rate": 0.000152,
      "loss": 0.9626120567321778,
      "step": 20
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.37232705950737,
      "learning_rate": 0.00019984268150178167,
      "loss": 0.3878004550933838,
      "step": 30
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.3485192060470581,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.2589367151260376,
      "step": 40
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.39318668842315674,
      "learning_rate": 0.00019438833303083678,
      "loss": 0.22383544445037842,
      "step": 50
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.32316797971725464,
      "learning_rate": 0.00018884456359788724,
      "loss": 0.2246922254562378,
      "step": 60
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.30077946186065674,
      "learning_rate": 0.00018155608689592604,
      "loss": 0.19630048274993897,
      "step": 70
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.29323890805244446,
      "learning_rate": 0.0001726660322034027,
      "loss": 0.190514874458313,
      "step": 80
    },
    {
      "epoch": 1.084848484848485,
      "grad_norm": 0.25198444724082947,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.1462882399559021,
      "step": 90
    },
    {
      "epoch": 1.206060606060606,
      "grad_norm": 0.3029341697692871,
      "learning_rate": 0.00015080753452465296,
      "loss": 0.14055825471878053,
      "step": 100
    },
    {
      "epoch": 1.206060606060606,
      "eval_loss": 0.1648179292678833,
      "eval_runtime": 26.3797,
      "eval_samples_per_second": 1.403,
      "eval_steps_per_second": 1.403,
      "step": 100
    },
    {
      "epoch": 1.3272727272727272,
      "grad_norm": 0.31430932879447937,
      "learning_rate": 0.000138268343236509,
      "loss": 0.13582674264907837,
      "step": 110
    },
    {
      "epoch": 1.4484848484848485,
      "grad_norm": 0.4176490008831024,
      "learning_rate": 0.0001249776478167227,
      "loss": 0.1242327094078064,
      "step": 120
    },
    {
      "epoch": 1.5696969696969698,
      "grad_norm": 0.30500853061676025,
      "learning_rate": 0.00011119644761033078,
      "loss": 0.12956202030181885,
      "step": 130
    },
    {
      "epoch": 1.690909090909091,
      "grad_norm": 0.32470235228538513,
      "learning_rate": 9.719537437241312e-05,
      "loss": 0.11253986358642579,
      "step": 140
    },
    {
      "epoch": 1.812121212121212,
      "grad_norm": 0.2475222647190094,
      "learning_rate": 8.324937766952638e-05,
      "loss": 0.13103077411651612,
      "step": 150
    },
    {
      "epoch": 1.9333333333333333,
      "grad_norm": 0.29638567566871643,
      "learning_rate": 6.963232548903853e-05,
      "loss": 0.11490601301193237,
      "step": 160
    },
    {
      "epoch": 2.0484848484848484,
      "grad_norm": 0.283840537071228,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.10299185514450074,
      "step": 170
    },
    {
      "epoch": 2.16969696969697,
      "grad_norm": 0.2592798173427582,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.06464942693710327,
      "step": 180
    },
    {
      "epoch": 2.290909090909091,
      "grad_norm": 0.43967875838279724,
      "learning_rate": 3.336534220479961e-05,
      "loss": 0.07628917694091797,
      "step": 190
    },
    {
      "epoch": 2.412121212121212,
      "grad_norm": 0.2669766843318939,
      "learning_rate": 2.3596262417839255e-05,
      "loss": 0.06493941545486451,
      "step": 200
    },
    {
      "epoch": 2.412121212121212,
      "eval_loss": 0.14370080828666687,
      "eval_runtime": 26.392,
      "eval_samples_per_second": 1.402,
      "eval_steps_per_second": 1.402,
      "step": 200
    },
    {
      "epoch": 2.533333333333333,
      "grad_norm": 0.3065372109413147,
      "learning_rate": 1.5327580077171587e-05,
      "loss": 0.06551741957664489,
      "step": 210
    },
    {
      "epoch": 2.6545454545454543,
      "grad_norm": 0.2930675148963928,
      "learning_rate": 8.72167349386811e-06,
      "loss": 0.06805793642997741,
      "step": 220
    },
    {
      "epoch": 2.775757575757576,
      "grad_norm": 0.3214111924171448,
      "learning_rate": 3.908267805490051e-06,
      "loss": 0.0629807949066162,
      "step": 230
    },
    {
      "epoch": 2.896969696969697,
      "grad_norm": 0.3266196548938751,
      "learning_rate": 9.818874663554357e-07,
      "loss": 0.062103265523910524,
      "step": 240
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.1428956389427185,
      "eval_runtime": 26.3609,
      "eval_samples_per_second": 1.404,
      "eval_steps_per_second": 1.404,
      "step": 249
    },
    {
      "epoch": 3.0,
      "step": 249,
      "total_flos": 2.043548997493248e+16,
      "train_loss": 0.2298657032380621,
      "train_runtime": 2123.2392,
      "train_samples_per_second": 0.466,
      "train_steps_per_second": 0.117
    }
  ],
  "logging_steps": 10,
  "max_steps": 249,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.043548997493248e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}