{
  "best_global_step": 69,
  "best_metric": 2.2659010887145996,
  "best_model_checkpoint": "distilbert_rand_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": 5.209988117218018,
      "learning_rate": 4.9e-05,
      "loss": 3.0153,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.11169171991142945,
      "eval_loss": 2.435251235961914,
      "eval_pearson": 0.1203307983582516,
      "eval_runtime": 0.63,
      "eval_samples_per_second": 2380.971,
      "eval_spearmanr": 0.10305264146460733,
      "eval_steps_per_second": 9.524,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.652449131011963,
      "learning_rate": 4.8e-05,
      "loss": 1.9567,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.1773046476534294,
      "eval_loss": 2.4981181621551514,
      "eval_pearson": 0.1854188149451587,
      "eval_runtime": 0.6407,
      "eval_samples_per_second": 2341.369,
      "eval_spearmanr": 0.16919048036170012,
      "eval_steps_per_second": 9.365,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.820231914520264,
      "learning_rate": 4.7e-05,
      "loss": 1.7232,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.24302973944840472,
      "eval_loss": 2.2659010887145996,
      "eval_pearson": 0.24933683251264216,
      "eval_runtime": 0.6407,
      "eval_samples_per_second": 2341.333,
      "eval_spearmanr": 0.23672264638416732,
      "eval_steps_per_second": 9.365,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.110631942749023,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.4358,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.2852490366012619,
      "eval_loss": 2.2972590923309326,
      "eval_pearson": 0.2886789914476714,
      "eval_runtime": 0.6871,
      "eval_samples_per_second": 2183.124,
      "eval_spearmanr": 0.28181908175485243,
      "eval_steps_per_second": 8.732,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 10.900781631469727,
      "learning_rate": 4.5e-05,
      "loss": 1.0785,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.23962746259723686,
      "eval_loss": 2.625922679901123,
      "eval_pearson": 0.24526634505777975,
      "eval_runtime": 0.6596,
      "eval_samples_per_second": 2274.179,
      "eval_spearmanr": 0.23398858013669396,
      "eval_steps_per_second": 9.097,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 15.664032936096191,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.7743,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.28487240151697624,
      "eval_loss": 2.5244739055633545,
      "eval_pearson": 0.28727712627400626,
      "eval_runtime": 0.6198,
      "eval_samples_per_second": 2420.319,
      "eval_spearmanr": 0.2824676767599462,
      "eval_steps_per_second": 9.681,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 7.396364688873291,
      "learning_rate": 4.3e-05,
      "loss": 0.5991,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.30640903003447406,
      "eval_loss": 2.6254544258117676,
      "eval_pearson": 0.30810453615893424,
      "eval_runtime": 0.6684,
      "eval_samples_per_second": 2244.168,
      "eval_spearmanr": 0.3047135239100139,
      "eval_steps_per_second": 8.977,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 11.145502090454102,
      "learning_rate": 4.2e-05,
      "loss": 0.479,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.2845158208876023,
      "eval_loss": 2.6336708068847656,
      "eval_pearson": 0.28868199337934963,
      "eval_runtime": 0.6334,
      "eval_samples_per_second": 2367.996,
      "eval_spearmanr": 0.28034964839585497,
      "eval_steps_per_second": 9.472,
      "step": 184
    },
    {
      "epoch": 8.0,
      "step": 184,
      "total_flos": 3046165974478848.0,
      "train_loss": 1.3827226939408674,
      "train_runtime": 59.5343,
      "train_samples_per_second": 4828.307,
      "train_steps_per_second": 19.317
    }
  ],
  "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
}