{
  "best_global_step": 69,
  "best_metric": 2.302304267883301,
  "best_model_checkpoint": "distilbert_rand_10_v1_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": 6.179130554199219,
      "learning_rate": 4.9e-05,
      "loss": 2.7957,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.11565682451597416,
      "eval_loss": 2.4696602821350098,
      "eval_pearson": 0.1288272748718879,
      "eval_runtime": 0.6378,
      "eval_samples_per_second": 2351.929,
      "eval_spearmanr": 0.10248637416006043,
      "eval_steps_per_second": 9.408,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 11.912776947021484,
      "learning_rate": 4.8e-05,
      "loss": 1.9109,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.1916002227797744,
      "eval_loss": 2.3163304328918457,
      "eval_pearson": 0.2022115996108116,
      "eval_runtime": 0.7207,
      "eval_samples_per_second": 2081.364,
      "eval_spearmanr": 0.1809888459487372,
      "eval_steps_per_second": 8.325,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.381529331207275,
      "learning_rate": 4.7e-05,
      "loss": 1.6472,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.2559620526322318,
      "eval_loss": 2.302304267883301,
      "eval_pearson": 0.2627241218496804,
      "eval_runtime": 0.6465,
      "eval_samples_per_second": 2320.257,
      "eval_spearmanr": 0.24919998341478328,
      "eval_steps_per_second": 9.281,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 15.540834426879883,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.2862,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.30084146998207484,
      "eval_loss": 2.339672088623047,
      "eval_pearson": 0.30497233434422855,
      "eval_runtime": 0.6328,
      "eval_samples_per_second": 2370.537,
      "eval_spearmanr": 0.2967106056199212,
      "eval_steps_per_second": 9.482,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 16.138242721557617,
      "learning_rate": 4.5e-05,
      "loss": 0.9605,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.3012594687724821,
      "eval_loss": 2.6705973148345947,
      "eval_pearson": 0.3056484041420934,
      "eval_runtime": 0.6524,
      "eval_samples_per_second": 2299.13,
      "eval_spearmanr": 0.2968705334028709,
      "eval_steps_per_second": 9.197,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 10.69510269165039,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6815,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.35194111850838516,
      "eval_loss": 2.311020612716675,
      "eval_pearson": 0.35230496410604195,
      "eval_runtime": 0.6792,
      "eval_samples_per_second": 2208.462,
      "eval_spearmanr": 0.35157727291072843,
      "eval_steps_per_second": 8.834,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 7.482017517089844,
      "learning_rate": 4.3e-05,
      "loss": 0.5565,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.34259897624067936,
      "eval_loss": 2.534219980239868,
      "eval_pearson": 0.3425005931718702,
      "eval_runtime": 0.6428,
      "eval_samples_per_second": 2333.505,
      "eval_spearmanr": 0.3426973593094885,
      "eval_steps_per_second": 9.334,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 9.193314552307129,
      "learning_rate": 4.2e-05,
      "loss": 0.4389,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.33981879171380913,
      "eval_loss": 2.6021981239318848,
      "eval_pearson": 0.34138227291330525,
      "eval_runtime": 0.6458,
      "eval_samples_per_second": 2322.767,
      "eval_spearmanr": 0.338255310514313,
      "eval_steps_per_second": 9.291,
      "step": 184
    },
    {
      "epoch": 8.0,
      "step": 184,
      "total_flos": 3046165974478848.0,
      "train_loss": 1.2846648693084717,
      "train_runtime": 58.2837,
      "train_samples_per_second": 4931.907,
      "train_steps_per_second": 19.731
    }
  ],
  "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
}