{
  "best_metric": 1.5578951835632324,
  "best_model_checkpoint": "/nfs/production/literature/amina-mardiyyah/new_data/OT-Entity-Extraction-Pipeline/model_outputs/Continued_pretraining/TAPT/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext/Mardiyyah/TAPT_data_V2_split/tapt_llrd_only_LR-2e-05/checkpoint-1827",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 6090,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 31.149822235107422,
      "learning_rate": 2e-05,
      "loss": 1.8412,
      "step": 609
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6327614784240723,
      "eval_runtime": 3.3806,
      "eval_samples_per_second": 575.345,
      "eval_steps_per_second": 36.088,
      "step": 609
    },
    {
      "epoch": 2.0,
      "grad_norm": 42.3134651184082,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 1.6676,
      "step": 1218
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.6140305995941162,
      "eval_runtime": 3.4237,
      "eval_samples_per_second": 568.095,
      "eval_steps_per_second": 35.634,
      "step": 1218
    },
    {
      "epoch": 3.0,
      "grad_norm": 40.80204772949219,
      "learning_rate": 1.555555555555556e-05,
      "loss": 1.5616,
      "step": 1827
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.5578951835632324,
      "eval_runtime": 3.3764,
      "eval_samples_per_second": 576.059,
      "eval_steps_per_second": 36.133,
      "step": 1827
    },
    {
      "epoch": 4.0,
      "grad_norm": 36.631927490234375,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.4876,
      "step": 2436
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.6425701379776,
      "eval_runtime": 3.4142,
      "eval_samples_per_second": 569.684,
      "eval_steps_per_second": 35.733,
      "step": 2436
    },
    {
      "epoch": 5.0,
      "grad_norm": 58.63182067871094,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 1.416,
      "step": 3045
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.6180479526519775,
      "eval_runtime": 3.4615,
      "eval_samples_per_second": 561.887,
      "eval_steps_per_second": 35.244,
      "step": 3045
    },
    {
      "epoch": 6.0,
      "grad_norm": 25.30164909362793,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.3898,
      "step": 3654
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.6720105409622192,
      "eval_runtime": 3.4401,
      "eval_samples_per_second": 565.384,
      "eval_steps_per_second": 35.464,
      "step": 3654
    },
    {
      "epoch": 7.0,
      "grad_norm": 27.665294647216797,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.3674,
      "step": 4263
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.682289481163025,
      "eval_runtime": 3.4548,
      "eval_samples_per_second": 562.987,
      "eval_steps_per_second": 35.313,
      "step": 4263
    },
    {
      "epoch": 8.0,
      "grad_norm": 35.61056137084961,
      "learning_rate": 4.444444444444444e-06,
      "loss": 1.3325,
      "step": 4872
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.6565485000610352,
      "eval_runtime": 3.4917,
      "eval_samples_per_second": 557.031,
      "eval_steps_per_second": 34.94,
      "step": 4872
    },
    {
      "epoch": 9.0,
      "grad_norm": 24.077539443969727,
      "learning_rate": 2.222222222222222e-06,
      "loss": 1.3063,
      "step": 5481
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.6364006996154785,
      "eval_runtime": 3.3972,
      "eval_samples_per_second": 572.532,
      "eval_steps_per_second": 35.912,
      "step": 5481
    },
    {
      "epoch": 10.0,
      "grad_norm": 21.178720474243164,
      "learning_rate": 0.0,
      "loss": 1.3161,
      "step": 6090
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.6274725198745728,
      "eval_runtime": 3.3662,
      "eval_samples_per_second": 577.807,
      "eval_steps_per_second": 36.243,
      "step": 6090
    },
    {
      "epoch": 10.0,
      "step": 6090,
      "total_flos": 4339270626462000.0,
      "train_loss": 1.4685930624775503,
      "train_runtime": 599.5073,
      "train_samples_per_second": 162.35,
      "train_steps_per_second": 10.158
    }
  ],
  "logging_steps": 500,
  "max_steps": 6090,
  "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": 4339270626462000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}