{
  "best_global_step": 92,
  "best_metric": 2.33183217048645,
  "best_model_checkpoint": "distilbert_rand_20_v2_stsb/checkpoint-92",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 207,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 13.393118858337402,
      "learning_rate": 4.9e-05,
      "loss": 2.8409,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.09548641455415285,
      "eval_loss": 2.648338794708252,
      "eval_pearson": 0.1073052403250683,
      "eval_runtime": 0.6956,
      "eval_samples_per_second": 2156.551,
      "eval_spearmanr": 0.0836675887832374,
      "eval_steps_per_second": 8.626,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.511842250823975,
      "learning_rate": 4.8e-05,
      "loss": 1.937,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.18499614242304205,
      "eval_loss": 2.4295544624328613,
      "eval_pearson": 0.19815297399307064,
      "eval_runtime": 0.6549,
      "eval_samples_per_second": 2290.253,
      "eval_spearmanr": 0.17183931085301346,
      "eval_steps_per_second": 9.161,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.056204795837402,
      "learning_rate": 4.7e-05,
      "loss": 1.7127,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.22696034198522702,
      "eval_loss": 2.4167613983154297,
      "eval_pearson": 0.23342164714435498,
      "eval_runtime": 0.6574,
      "eval_samples_per_second": 2281.773,
      "eval_spearmanr": 0.22049903682609903,
      "eval_steps_per_second": 9.127,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.891855239868164,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.3482,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.29739575301700216,
      "eval_loss": 2.33183217048645,
      "eval_pearson": 0.3011378946428058,
      "eval_runtime": 0.6175,
      "eval_samples_per_second": 2429.023,
      "eval_spearmanr": 0.29365361139119855,
      "eval_steps_per_second": 9.716,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.851858139038086,
      "learning_rate": 4.5e-05,
      "loss": 0.9691,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.2958901839140248,
      "eval_loss": 2.5005791187286377,
      "eval_pearson": 0.30144219875437855,
      "eval_runtime": 0.6498,
      "eval_samples_per_second": 2308.273,
      "eval_spearmanr": 0.29033816907367105,
      "eval_steps_per_second": 9.233,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 11.34286117553711,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.7285,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.3301548041604065,
      "eval_loss": 2.4678592681884766,
      "eval_pearson": 0.33486413382941466,
      "eval_runtime": 0.625,
      "eval_samples_per_second": 2400.149,
      "eval_spearmanr": 0.3254454744913983,
      "eval_steps_per_second": 9.601,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 13.800930976867676,
      "learning_rate": 4.3e-05,
      "loss": 0.572,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.3491733742134768,
      "eval_loss": 2.5068540573120117,
      "eval_pearson": 0.35097989232592086,
      "eval_runtime": 0.6398,
      "eval_samples_per_second": 2344.562,
      "eval_spearmanr": 0.3473668561010327,
      "eval_steps_per_second": 9.378,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 5.356657028198242,
      "learning_rate": 4.2e-05,
      "loss": 0.4434,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.35938112134837014,
      "eval_loss": 2.440427541732788,
      "eval_pearson": 0.36359788899548684,
      "eval_runtime": 0.689,
      "eval_samples_per_second": 2177.02,
      "eval_spearmanr": 0.35516435370125343,
      "eval_steps_per_second": 8.708,
      "step": 184
    },
    {
      "epoch": 9.0,
      "grad_norm": 5.340475559234619,
      "learning_rate": 4.1e-05,
      "loss": 0.3722,
      "step": 207
    },
    {
      "epoch": 9.0,
      "eval_combined_score": 0.3460783711216901,
      "eval_loss": 2.360334873199463,
      "eval_pearson": 0.3500750197504243,
      "eval_runtime": 0.6257,
      "eval_samples_per_second": 2397.2,
      "eval_spearmanr": 0.3420817224929559,
      "eval_steps_per_second": 9.589,
      "step": 207
    },
    {
      "epoch": 9.0,
      "step": 207,
      "total_flos": 3426936721288704.0,
      "train_loss": 1.2137784543244734,
      "train_runtime": 66.4149,
      "train_samples_per_second": 4328.096,
      "train_steps_per_second": 17.315
    }
  ],
  "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": 3426936721288704.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}