{
  "best_global_step": 115,
  "best_metric": 2.246450424194336,
  "best_model_checkpoint": "distilbert_km_100_v2_stsb/checkpoint-115",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 230,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.8221588134765625,
      "learning_rate": 4.9e-05,
      "loss": 2.9541,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.10309112346462598,
      "eval_loss": 2.3048012256622314,
      "eval_pearson": 0.10999356791924093,
      "eval_runtime": 0.6262,
      "eval_samples_per_second": 2395.414,
      "eval_spearmanr": 0.09618867901001105,
      "eval_steps_per_second": 9.582,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.722611904144287,
      "learning_rate": 4.8e-05,
      "loss": 1.9575,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.21732914782401608,
      "eval_loss": 2.3279268741607666,
      "eval_pearson": 0.22615016191971274,
      "eval_runtime": 0.6348,
      "eval_samples_per_second": 2362.875,
      "eval_spearmanr": 0.20850813372831944,
      "eval_steps_per_second": 9.452,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.280568599700928,
      "learning_rate": 4.7e-05,
      "loss": 1.7269,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.2317663937793672,
      "eval_loss": 2.4054489135742188,
      "eval_pearson": 0.23874127077966723,
      "eval_runtime": 0.6404,
      "eval_samples_per_second": 2342.166,
      "eval_spearmanr": 0.22479151677906717,
      "eval_steps_per_second": 9.369,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.37396240234375,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.4551,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.26369598865989163,
      "eval_loss": 2.480987787246704,
      "eval_pearson": 0.27055105984754857,
      "eval_runtime": 0.6161,
      "eval_samples_per_second": 2434.721,
      "eval_spearmanr": 0.2568409174722347,
      "eval_steps_per_second": 9.739,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.097450256347656,
      "learning_rate": 4.5e-05,
      "loss": 1.1316,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.3318435221320142,
      "eval_loss": 2.246450424194336,
      "eval_pearson": 0.33415891418163296,
      "eval_runtime": 0.6481,
      "eval_samples_per_second": 2314.298,
      "eval_spearmanr": 0.3295281300823954,
      "eval_steps_per_second": 9.257,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 8.786614418029785,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.8642,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.3384605621008755,
      "eval_loss": 2.5217232704162598,
      "eval_pearson": 0.3352842056283115,
      "eval_runtime": 0.7413,
      "eval_samples_per_second": 2023.465,
      "eval_spearmanr": 0.3416369185734395,
      "eval_steps_per_second": 8.094,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 9.015091896057129,
      "learning_rate": 4.3e-05,
      "loss": 0.6447,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.3415818921196417,
      "eval_loss": 2.430701494216919,
      "eval_pearson": 0.3411610615547312,
      "eval_runtime": 0.6172,
      "eval_samples_per_second": 2430.16,
      "eval_spearmanr": 0.3420027226845522,
      "eval_steps_per_second": 9.721,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 8.16442584991455,
      "learning_rate": 4.2e-05,
      "loss": 0.5298,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.3379933686633788,
      "eval_loss": 2.423891067504883,
      "eval_pearson": 0.33885518923564895,
      "eval_runtime": 0.6321,
      "eval_samples_per_second": 2372.867,
      "eval_spearmanr": 0.33713154809110873,
      "eval_steps_per_second": 9.491,
      "step": 184
    },
    {
      "epoch": 9.0,
      "grad_norm": 17.56764030456543,
      "learning_rate": 4.1e-05,
      "loss": 0.429,
      "step": 207
    },
    {
      "epoch": 9.0,
      "eval_combined_score": 0.3257186671984066,
      "eval_loss": 2.685605049133301,
      "eval_pearson": 0.32812559834043686,
      "eval_runtime": 0.6556,
      "eval_samples_per_second": 2287.85,
      "eval_spearmanr": 0.32331173605637636,
      "eval_steps_per_second": 9.151,
      "step": 207
    },
    {
      "epoch": 10.0,
      "grad_norm": 12.405738830566406,
      "learning_rate": 4e-05,
      "loss": 0.3557,
      "step": 230
    },
    {
      "epoch": 10.0,
      "eval_combined_score": 0.3398008480007896,
      "eval_loss": 2.5756754875183105,
      "eval_pearson": 0.34141282805310713,
      "eval_runtime": 0.6346,
      "eval_samples_per_second": 2363.527,
      "eval_spearmanr": 0.33818886794847197,
      "eval_steps_per_second": 9.454,
      "step": 230
    },
    {
      "epoch": 10.0,
      "step": 230,
      "total_flos": 3807707468098560.0,
      "train_loss": 1.2048658205115277,
      "train_runtime": 73.8422,
      "train_samples_per_second": 3892.761,
      "train_steps_per_second": 15.574
    }
  ],
  "logging_steps": 1,
  "max_steps": 1150,
  "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": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3807707468098560.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}