{
  "best_metric": 0.017509404569864273,
  "best_model_checkpoint": "/kaggle/working/output/checkpoint-77",
  "epoch": 26.857142857142858,
  "eval_steps": 500,
  "global_step": 94,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8571428571428571,
      "eval_LCC": 0.1969856506206926,
      "eval_SROCC": 0.10444177671068428,
      "eval_loss": 0.14835341274738312,
      "eval_runtime": 35.5463,
      "eval_samples_per_second": 1.407,
      "eval_steps_per_second": 0.056,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_LCC": 0.1712787386505908,
      "eval_SROCC": 0.11068427370948379,
      "eval_loss": 0.0292142815887928,
      "eval_runtime": 34.8973,
      "eval_samples_per_second": 1.433,
      "eval_steps_per_second": 0.057,
      "step": 7
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 7.9004807472229,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.1442,
      "step": 10
    },
    {
      "epoch": 2.857142857142857,
      "eval_LCC": 0.11784921848546775,
      "eval_SROCC": 0.027899159663865542,
      "eval_loss": 0.05484883487224579,
      "eval_runtime": 35.127,
      "eval_samples_per_second": 1.423,
      "eval_steps_per_second": 0.057,
      "step": 10
    },
    {
      "epoch": 4.0,
      "eval_LCC": 0.06886859888985782,
      "eval_SROCC": -0.06276110444177671,
      "eval_loss": 0.030970515683293343,
      "eval_runtime": 34.9536,
      "eval_samples_per_second": 1.43,
      "eval_steps_per_second": 0.057,
      "step": 14
    },
    {
      "epoch": 4.857142857142857,
      "eval_LCC": 0.0550252891230114,
      "eval_SROCC": -0.06180072028811524,
      "eval_loss": 0.04757826402783394,
      "eval_runtime": 35.0545,
      "eval_samples_per_second": 1.426,
      "eval_steps_per_second": 0.057,
      "step": 17
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 2.093867301940918,
      "learning_rate": 1.925925925925926e-05,
      "loss": 0.0425,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_LCC": 0.005142275506506862,
      "eval_SROCC": -0.09781512605042017,
      "eval_loss": 0.029744217172265053,
      "eval_runtime": 34.9107,
      "eval_samples_per_second": 1.432,
      "eval_steps_per_second": 0.057,
      "step": 21
    },
    {
      "epoch": 6.857142857142857,
      "eval_LCC": -0.0038686428258717766,
      "eval_SROCC": -0.09061224489795917,
      "eval_loss": 0.025907116010785103,
      "eval_runtime": 34.9938,
      "eval_samples_per_second": 1.429,
      "eval_steps_per_second": 0.057,
      "step": 24
    },
    {
      "epoch": 8.0,
      "eval_LCC": 0.007887024520170878,
      "eval_SROCC": -0.027034813925570226,
      "eval_loss": 0.029399558901786804,
      "eval_runtime": 34.9296,
      "eval_samples_per_second": 1.431,
      "eval_steps_per_second": 0.057,
      "step": 28
    },
    {
      "epoch": 8.571428571428571,
      "grad_norm": 1.0898091793060303,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 0.0242,
      "step": 30
    },
    {
      "epoch": 8.857142857142858,
      "eval_LCC": 0.032333468238550225,
      "eval_SROCC": -0.014645858343337334,
      "eval_loss": 0.023686964064836502,
      "eval_runtime": 35.0539,
      "eval_samples_per_second": 1.426,
      "eval_steps_per_second": 0.057,
      "step": 31
    },
    {
      "epoch": 10.0,
      "eval_LCC": 0.08086510887243141,
      "eval_SROCC": 0.015222088835534215,
      "eval_loss": 0.02260431833565235,
      "eval_runtime": 35.1001,
      "eval_samples_per_second": 1.424,
      "eval_steps_per_second": 0.057,
      "step": 35
    },
    {
      "epoch": 10.857142857142858,
      "eval_LCC": 0.11583787359004848,
      "eval_SROCC": 0.03385354141656663,
      "eval_loss": 0.023615412414073944,
      "eval_runtime": 34.9014,
      "eval_samples_per_second": 1.433,
      "eval_steps_per_second": 0.057,
      "step": 38
    },
    {
      "epoch": 11.428571428571429,
      "grad_norm": 0.41205185651779175,
      "learning_rate": 1.6296296296296297e-05,
      "loss": 0.0146,
      "step": 40
    },
    {
      "epoch": 12.0,
      "eval_LCC": 0.17529865995122038,
      "eval_SROCC": 0.05623049219687875,
      "eval_loss": 0.021260255947709084,
      "eval_runtime": 34.8745,
      "eval_samples_per_second": 1.434,
      "eval_steps_per_second": 0.057,
      "step": 42
    },
    {
      "epoch": 12.857142857142858,
      "eval_LCC": 0.22410038594433127,
      "eval_SROCC": 0.06775510204081632,
      "eval_loss": 0.019894730299711227,
      "eval_runtime": 34.9972,
      "eval_samples_per_second": 1.429,
      "eval_steps_per_second": 0.057,
      "step": 45
    },
    {
      "epoch": 14.0,
      "eval_LCC": 0.27017897046913114,
      "eval_SROCC": 0.0981032412965186,
      "eval_loss": 0.020490916445851326,
      "eval_runtime": 34.9294,
      "eval_samples_per_second": 1.431,
      "eval_steps_per_second": 0.057,
      "step": 49
    },
    {
      "epoch": 14.285714285714286,
      "grad_norm": 0.5113194584846497,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.0116,
      "step": 50
    },
    {
      "epoch": 14.857142857142858,
      "eval_LCC": 0.3000317546087649,
      "eval_SROCC": 0.12451380552220888,
      "eval_loss": 0.019025439396500587,
      "eval_runtime": 35.0048,
      "eval_samples_per_second": 1.428,
      "eval_steps_per_second": 0.057,
      "step": 52
    },
    {
      "epoch": 16.0,
      "eval_LCC": 0.35113038666324353,
      "eval_SROCC": 0.1594717887154862,
      "eval_loss": 0.019477322697639465,
      "eval_runtime": 34.8356,
      "eval_samples_per_second": 1.435,
      "eval_steps_per_second": 0.057,
      "step": 56
    },
    {
      "epoch": 16.857142857142858,
      "eval_LCC": 0.3803764092219919,
      "eval_SROCC": 0.1829051620648259,
      "eval_loss": 0.019361073151230812,
      "eval_runtime": 34.9637,
      "eval_samples_per_second": 1.43,
      "eval_steps_per_second": 0.057,
      "step": 59
    },
    {
      "epoch": 17.142857142857142,
      "grad_norm": 0.8568110466003418,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0096,
      "step": 60
    },
    {
      "epoch": 18.0,
      "eval_LCC": 0.4030357760137721,
      "eval_SROCC": 0.21440576230492195,
      "eval_loss": 0.018257679417729378,
      "eval_runtime": 34.9221,
      "eval_samples_per_second": 1.432,
      "eval_steps_per_second": 0.057,
      "step": 63
    },
    {
      "epoch": 18.857142857142858,
      "eval_LCC": 0.4085909204754596,
      "eval_SROCC": 0.21200480192076832,
      "eval_loss": 0.01950741559267044,
      "eval_runtime": 34.7591,
      "eval_samples_per_second": 1.438,
      "eval_steps_per_second": 0.058,
      "step": 66
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.403394877910614,
      "learning_rate": 1.1851851851851852e-05,
      "loss": 0.0075,
      "step": 70
    },
    {
      "epoch": 20.0,
      "eval_LCC": 0.41267287372763267,
      "eval_SROCC": 0.216422569027611,
      "eval_loss": 0.018830113112926483,
      "eval_runtime": 34.862,
      "eval_samples_per_second": 1.434,
      "eval_steps_per_second": 0.057,
      "step": 70
    },
    {
      "epoch": 20.857142857142858,
      "eval_LCC": 0.4223673737494469,
      "eval_SROCC": 0.2221848739495798,
      "eval_loss": 0.020868387073278427,
      "eval_runtime": 35.0558,
      "eval_samples_per_second": 1.426,
      "eval_steps_per_second": 0.057,
      "step": 73
    },
    {
      "epoch": 22.0,
      "eval_LCC": 0.43043752892141784,
      "eval_SROCC": 0.2288115246098439,
      "eval_loss": 0.017509404569864273,
      "eval_runtime": 34.8413,
      "eval_samples_per_second": 1.435,
      "eval_steps_per_second": 0.057,
      "step": 77
    },
    {
      "epoch": 22.857142857142858,
      "grad_norm": 0.4386737048625946,
      "learning_rate": 1.037037037037037e-05,
      "loss": 0.0076,
      "step": 80
    },
    {
      "epoch": 22.857142857142858,
      "eval_LCC": 0.4326080523141859,
      "eval_SROCC": 0.24321728691476588,
      "eval_loss": 0.021145235747098923,
      "eval_runtime": 34.9315,
      "eval_samples_per_second": 1.431,
      "eval_steps_per_second": 0.057,
      "step": 80
    },
    {
      "epoch": 24.0,
      "eval_LCC": 0.43274315513728545,
      "eval_SROCC": 0.23457382953181274,
      "eval_loss": 0.018896810710430145,
      "eval_runtime": 35.0475,
      "eval_samples_per_second": 1.427,
      "eval_steps_per_second": 0.057,
      "step": 84
    },
    {
      "epoch": 24.857142857142858,
      "eval_LCC": 0.4313378675752595,
      "eval_SROCC": 0.2293877551020408,
      "eval_loss": 0.018819700926542282,
      "eval_runtime": 34.8537,
      "eval_samples_per_second": 1.435,
      "eval_steps_per_second": 0.057,
      "step": 87
    },
    {
      "epoch": 25.714285714285715,
      "grad_norm": 0.4886440336704254,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.006,
      "step": 90
    },
    {
      "epoch": 26.0,
      "eval_LCC": 0.43430975581338493,
      "eval_SROCC": 0.23899159663865546,
      "eval_loss": 0.022326407954096794,
      "eval_runtime": 35.0745,
      "eval_samples_per_second": 1.426,
      "eval_steps_per_second": 0.057,
      "step": 91
    },
    {
      "epoch": 26.857142857142858,
      "eval_LCC": 0.4398680198859831,
      "eval_SROCC": 0.2510924369747899,
      "eval_loss": 0.0202498622238636,
      "eval_runtime": 34.9908,
      "eval_samples_per_second": 1.429,
      "eval_steps_per_second": 0.057,
      "step": 94
    },
    {
      "epoch": 26.857142857142858,
      "step": 94,
      "total_flos": 7.519124344516116e+17,
      "train_loss": 0.028724998592379244,
      "train_runtime": 4511.5827,
      "train_samples_per_second": 2.372,
      "train_steps_per_second": 0.033
    }
  ],
  "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": 7.519124344516116e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}