{
  "best_global_step": 69,
  "best_metric": 2.486570358276367,
  "best_model_checkpoint": "distilbert_km_50_v2_stsb/checkpoint-69",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 184,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 7.5051774978637695,
      "learning_rate": 4.9e-05,
      "loss": 2.9949,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.08567839689922303,
      "eval_loss": 2.4938485622406006,
      "eval_pearson": 0.09136476846258665,
      "eval_runtime": 0.6636,
      "eval_samples_per_second": 2260.528,
      "eval_spearmanr": 0.07999202533585942,
      "eval_steps_per_second": 9.042,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.660618305206299,
      "learning_rate": 4.8e-05,
      "loss": 1.9579,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.17147653489357378,
      "eval_loss": 2.4972054958343506,
      "eval_pearson": 0.17822156338825823,
      "eval_runtime": 0.6612,
      "eval_samples_per_second": 2268.608,
      "eval_spearmanr": 0.1647315063988893,
      "eval_steps_per_second": 9.074,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.71493673324585,
      "learning_rate": 4.7e-05,
      "loss": 1.7843,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.15940543906076132,
      "eval_loss": 2.486570358276367,
      "eval_pearson": 0.16962054228491097,
      "eval_runtime": 0.6542,
      "eval_samples_per_second": 2292.714,
      "eval_spearmanr": 0.1491903358366117,
      "eval_steps_per_second": 9.171,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.555704593658447,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.5797,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.2180498958810761,
      "eval_loss": 2.5043983459472656,
      "eval_pearson": 0.22608453383062685,
      "eval_runtime": 0.6878,
      "eval_samples_per_second": 2180.934,
      "eval_spearmanr": 0.2100152579315253,
      "eval_steps_per_second": 8.724,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.86571979522705,
      "learning_rate": 4.5e-05,
      "loss": 1.3075,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.2488092482658246,
      "eval_loss": 2.578871726989746,
      "eval_pearson": 0.25308607419612567,
      "eval_runtime": 0.6839,
      "eval_samples_per_second": 2193.418,
      "eval_spearmanr": 0.24453242233552352,
      "eval_steps_per_second": 8.774,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 9.119850158691406,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.0461,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.23000273926412904,
      "eval_loss": 2.786653757095337,
      "eval_pearson": 0.23812569074460113,
      "eval_runtime": 0.6409,
      "eval_samples_per_second": 2340.462,
      "eval_spearmanr": 0.22187978778365694,
      "eval_steps_per_second": 9.362,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 6.085598945617676,
      "learning_rate": 4.3e-05,
      "loss": 0.8285,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.27353572128706094,
      "eval_loss": 2.63958477973938,
      "eval_pearson": 0.2728874586821158,
      "eval_runtime": 0.6161,
      "eval_samples_per_second": 2434.62,
      "eval_spearmanr": 0.2741839838920061,
      "eval_steps_per_second": 9.738,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 14.216178894042969,
      "learning_rate": 4.2e-05,
      "loss": 0.6271,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.28101601976734525,
      "eval_loss": 2.882035255432129,
      "eval_pearson": 0.28054127784666816,
      "eval_runtime": 0.6428,
      "eval_samples_per_second": 2333.55,
      "eval_spearmanr": 0.2814907616880224,
      "eval_steps_per_second": 9.334,
      "step": 184
    },
    {
      "epoch": 8.0,
      "step": 184,
      "total_flos": 3046165974478848.0,
      "train_loss": 1.5157460907231206,
      "train_runtime": 58.5522,
      "train_samples_per_second": 4909.298,
      "train_steps_per_second": 19.641
    }
  ],
  "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": 3046165974478848.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}