trainer_state.json

{
  "best_metric": 0.8877093139479653,
  "best_model_checkpoint": "output/fine_tuned/t5-base/STSB/checkpoint-1800",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_combined_score": 0.8180482570214538,
      "eval_loss": 1.1720354557037354,
      "eval_pearson": 0.8127714519274175,
      "eval_runtime": 6.1681,
      "eval_samples_per_second": 243.187,
      "eval_spearmanr": 0.82332506211549,
      "eval_steps_per_second": 30.479,
      "step": 180
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.8587908976854779,
      "eval_loss": 0.742409348487854,
      "eval_pearson": 0.858468016418284,
      "eval_runtime": 5.5517,
      "eval_samples_per_second": 270.19,
      "eval_spearmanr": 0.8591137789526717,
      "eval_steps_per_second": 33.864,
      "step": 360
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 9.448566436767578,
      "learning_rate": 3.611111111111111e-05,
      "loss": 1.0195,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.8756494156711507,
      "eval_loss": 0.6313198804855347,
      "eval_pearson": 0.8756494253345521,
      "eval_runtime": 5.5762,
      "eval_samples_per_second": 269.0,
      "eval_spearmanr": 0.8756494060077492,
      "eval_steps_per_second": 33.715,
      "step": 540
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.8803476568427875,
      "eval_loss": 0.5849104523658752,
      "eval_pearson": 0.8801132024277427,
      "eval_runtime": 5.5748,
      "eval_samples_per_second": 269.07,
      "eval_spearmanr": 0.8805821112578323,
      "eval_steps_per_second": 33.723,
      "step": 720
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.8832547961263721,
      "eval_loss": 0.6234210729598999,
      "eval_pearson": 0.8837629286843717,
      "eval_runtime": 5.6064,
      "eval_samples_per_second": 267.551,
      "eval_spearmanr": 0.8827466635683727,
      "eval_steps_per_second": 33.533,
      "step": 900
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 4.101786136627197,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.315,
      "step": 1000
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.8859068112770171,
      "eval_loss": 0.6468810439109802,
      "eval_pearson": 0.8864173415011244,
      "eval_runtime": 5.6494,
      "eval_samples_per_second": 265.517,
      "eval_spearmanr": 0.8853962810529098,
      "eval_steps_per_second": 33.278,
      "step": 1080
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.8860814636373492,
      "eval_loss": 0.5570630431175232,
      "eval_pearson": 0.8866005090966069,
      "eval_runtime": 5.5744,
      "eval_samples_per_second": 269.085,
      "eval_spearmanr": 0.8855624181780914,
      "eval_steps_per_second": 33.725,
      "step": 1260
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.8869178602756509,
      "eval_loss": 0.5628612637519836,
      "eval_pearson": 0.8876742023161693,
      "eval_runtime": 5.5511,
      "eval_samples_per_second": 270.215,
      "eval_spearmanr": 0.8861615182351323,
      "eval_steps_per_second": 33.867,
      "step": 1440
    },
    {
      "epoch": 8.333333333333334,
      "grad_norm": 7.962216377258301,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.2087,
      "step": 1500
    },
    {
      "epoch": 9.0,
      "eval_combined_score": 0.887651980785236,
      "eval_loss": 0.5568861365318298,
      "eval_pearson": 0.8882155423406275,
      "eval_runtime": 5.5766,
      "eval_samples_per_second": 268.98,
      "eval_spearmanr": 0.8870884192298445,
      "eval_steps_per_second": 33.712,
      "step": 1620
    },
    {
      "epoch": 10.0,
      "eval_combined_score": 0.8877093139479653,
      "eval_loss": 0.5495743751525879,
      "eval_pearson": 0.8882396089595147,
      "eval_runtime": 5.5645,
      "eval_samples_per_second": 269.566,
      "eval_spearmanr": 0.8871790189364159,
      "eval_steps_per_second": 33.786,
      "step": 1800
    },
    {
      "epoch": 10.0,
      "step": 1800,
      "total_flos": 8778357242181120.0,
      "train_loss": 0.0,
      "train_runtime": 0.3122,
      "train_samples_per_second": 184170.898,
      "train_steps_per_second": 5766.353
    }
  ],
  "logging_steps": 500,
  "max_steps": 1800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8778357242181120.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}