{
  "best_metric": 0.021110303699970245,
  "best_model_checkpoint": "/kaggle/working/output/checkpoint-56",
  "epoch": 20.857142857142858,
  "eval_steps": 500,
  "global_step": 73,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8571428571428571,
      "eval_LCC": 0.19761129838843355,
      "eval_SROCC": 0.1086674669867947,
      "eval_loss": 0.17467159032821655,
      "eval_runtime": 35.5195,
      "eval_samples_per_second": 1.408,
      "eval_steps_per_second": 0.056,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_LCC": 0.1898407031739211,
      "eval_SROCC": 0.10424969987995197,
      "eval_loss": 0.056969162076711655,
      "eval_runtime": 35.417,
      "eval_samples_per_second": 1.412,
      "eval_steps_per_second": 0.056,
      "step": 7
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 3.666994094848633,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1599,
      "step": 10
    },
    {
      "epoch": 2.857142857142857,
      "eval_LCC": 0.1686459812348507,
      "eval_SROCC": 0.11260504201680673,
      "eval_loss": 0.031988270580768585,
      "eval_runtime": 35.3188,
      "eval_samples_per_second": 1.416,
      "eval_steps_per_second": 0.057,
      "step": 10
    },
    {
      "epoch": 4.0,
      "eval_LCC": 0.12351226835758868,
      "eval_SROCC": 0.02645858343337335,
      "eval_loss": 0.0510590560734272,
      "eval_runtime": 35.2516,
      "eval_samples_per_second": 1.418,
      "eval_steps_per_second": 0.057,
      "step": 14
    },
    {
      "epoch": 4.857142857142857,
      "eval_LCC": 0.1029176675867897,
      "eval_SROCC": -0.00043217286914765904,
      "eval_loss": 0.02736870013177395,
      "eval_runtime": 35.3522,
      "eval_samples_per_second": 1.414,
      "eval_steps_per_second": 0.057,
      "step": 17
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 2.3310303688049316,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.0602,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_LCC": 0.08996101890143099,
      "eval_SROCC": -0.04057623049219687,
      "eval_loss": 0.03745032474398613,
      "eval_runtime": 35.2712,
      "eval_samples_per_second": 1.418,
      "eval_steps_per_second": 0.057,
      "step": 21
    },
    {
      "epoch": 6.857142857142857,
      "eval_LCC": 0.08304152415159055,
      "eval_SROCC": -0.05334933973589436,
      "eval_loss": 0.03062591142952442,
      "eval_runtime": 35.089,
      "eval_samples_per_second": 1.425,
      "eval_steps_per_second": 0.057,
      "step": 24
    },
    {
      "epoch": 8.0,
      "eval_LCC": 0.07141231150294015,
      "eval_SROCC": -0.07255702280912364,
      "eval_loss": 0.02552003413438797,
      "eval_runtime": 35.0759,
      "eval_samples_per_second": 1.425,
      "eval_steps_per_second": 0.057,
      "step": 28
    },
    {
      "epoch": 8.571428571428571,
      "grad_norm": 1.1723262071609497,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.029,
      "step": 30
    },
    {
      "epoch": 8.857142857142858,
      "eval_LCC": 0.07341013768251957,
      "eval_SROCC": -0.056806722689075634,
      "eval_loss": 0.024663101881742477,
      "eval_runtime": 35.4424,
      "eval_samples_per_second": 1.411,
      "eval_steps_per_second": 0.056,
      "step": 31
    },
    {
      "epoch": 10.0,
      "eval_LCC": 0.09004418149637736,
      "eval_SROCC": -0.042881152460984395,
      "eval_loss": 0.02926880680024624,
      "eval_runtime": 35.3398,
      "eval_samples_per_second": 1.415,
      "eval_steps_per_second": 0.057,
      "step": 35
    },
    {
      "epoch": 10.857142857142858,
      "eval_LCC": 0.09815228490732507,
      "eval_SROCC": -0.03174069627851141,
      "eval_loss": 0.025934694334864616,
      "eval_runtime": 35.299,
      "eval_samples_per_second": 1.416,
      "eval_steps_per_second": 0.057,
      "step": 38
    },
    {
      "epoch": 11.428571428571429,
      "grad_norm": 0.726739764213562,
      "learning_rate": 9.177439057064684e-06,
      "loss": 0.0199,
      "step": 40
    },
    {
      "epoch": 12.0,
      "eval_LCC": 0.12879803314702723,
      "eval_SROCC": -0.007250900360144057,
      "eval_loss": 0.02379768155515194,
      "eval_runtime": 35.6028,
      "eval_samples_per_second": 1.404,
      "eval_steps_per_second": 0.056,
      "step": 42
    },
    {
      "epoch": 12.857142857142858,
      "eval_LCC": 0.15936463360358263,
      "eval_SROCC": 0.02156062424969988,
      "eval_loss": 0.02426682412624359,
      "eval_runtime": 35.4009,
      "eval_samples_per_second": 1.412,
      "eval_steps_per_second": 0.056,
      "step": 45
    },
    {
      "epoch": 14.0,
      "eval_LCC": 0.18103273074335755,
      "eval_SROCC": 0.0453781512605042,
      "eval_loss": 0.02589680254459381,
      "eval_runtime": 35.429,
      "eval_samples_per_second": 1.411,
      "eval_steps_per_second": 0.056,
      "step": 49
    },
    {
      "epoch": 14.285714285714286,
      "grad_norm": 0.8898158669471741,
      "learning_rate": 8.43120818934367e-06,
      "loss": 0.0161,
      "step": 50
    },
    {
      "epoch": 14.857142857142858,
      "eval_LCC": 0.1954172655149359,
      "eval_SROCC": 0.056806722689075634,
      "eval_loss": 0.02237752452492714,
      "eval_runtime": 35.3401,
      "eval_samples_per_second": 1.415,
      "eval_steps_per_second": 0.057,
      "step": 52
    },
    {
      "epoch": 16.0,
      "eval_LCC": 0.23162353354414347,
      "eval_SROCC": 0.08955582232893158,
      "eval_loss": 0.021110303699970245,
      "eval_runtime": 35.3825,
      "eval_samples_per_second": 1.413,
      "eval_steps_per_second": 0.057,
      "step": 56
    },
    {
      "epoch": 16.857142857142858,
      "eval_LCC": 0.25437943511040334,
      "eval_SROCC": 0.10012004801920767,
      "eval_loss": 0.02233021892607212,
      "eval_runtime": 35.3868,
      "eval_samples_per_second": 1.413,
      "eval_steps_per_second": 0.057,
      "step": 59
    },
    {
      "epoch": 17.142857142857142,
      "grad_norm": 1.1253899335861206,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.0132,
      "step": 60
    },
    {
      "epoch": 18.0,
      "eval_LCC": 0.2680706396992355,
      "eval_SROCC": 0.0981032412965186,
      "eval_loss": 0.02166852541267872,
      "eval_runtime": 35.412,
      "eval_samples_per_second": 1.412,
      "eval_steps_per_second": 0.056,
      "step": 63
    },
    {
      "epoch": 18.857142857142858,
      "eval_LCC": 0.27459457148225125,
      "eval_SROCC": 0.11548619447779111,
      "eval_loss": 0.022057028487324715,
      "eval_runtime": 35.3202,
      "eval_samples_per_second": 1.416,
      "eval_steps_per_second": 0.057,
      "step": 66
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.4893428087234497,
      "learning_rate": 6.434016163555452e-06,
      "loss": 0.0103,
      "step": 70
    },
    {
      "epoch": 20.0,
      "eval_LCC": 0.28310987276640803,
      "eval_SROCC": 0.12297719087635053,
      "eval_loss": 0.022805728018283844,
      "eval_runtime": 35.2653,
      "eval_samples_per_second": 1.418,
      "eval_steps_per_second": 0.057,
      "step": 70
    },
    {
      "epoch": 20.857142857142858,
      "eval_LCC": 0.2943832703125549,
      "eval_SROCC": 0.13267707082833133,
      "eval_loss": 0.024481065571308136,
      "eval_runtime": 35.4504,
      "eval_samples_per_second": 1.41,
      "eval_steps_per_second": 0.056,
      "step": 73
    },
    {
      "epoch": 20.857142857142858,
      "step": 73,
      "total_flos": 5.848207823512535e+17,
      "train_loss": 0.042697800195788685,
      "train_runtime": 3517.7769,
      "train_samples_per_second": 3.042,
      "train_steps_per_second": 0.043
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.848207823512535e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}