{
  "best_global_step": 2000,
  "best_metric": 5.987252022653418,
  "best_model_checkpoint": "outputs/bert-tiny-stage2-sbert/checkpoints/checkpoint-2000",
  "epoch": 0.47303689687795647,
  "eval_steps": 2000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011825922421948912,
      "grad_norm": 37.57676696777344,
      "learning_rate": 2.3173327027666118e-07,
      "loss": 18.0327,
      "step": 50
    },
    {
      "epoch": 0.023651844843897825,
      "grad_norm": 43.198524475097656,
      "learning_rate": 4.6819579096713174e-07,
      "loss": 17.7132,
      "step": 100
    },
    {
      "epoch": 0.035477767265846734,
      "grad_norm": 36.470436096191406,
      "learning_rate": 7.046583116576024e-07,
      "loss": 17.0003,
      "step": 150
    },
    {
      "epoch": 0.04730368968779565,
      "grad_norm": 34.2964973449707,
      "learning_rate": 9.411208323480729e-07,
      "loss": 16.0668,
      "step": 200
    },
    {
      "epoch": 0.05912961210974456,
      "grad_norm": 33.23365020751953,
      "learning_rate": 1.1775833530385434e-06,
      "loss": 14.9137,
      "step": 250
    },
    {
      "epoch": 0.07095553453169347,
      "grad_norm": 28.96517562866211,
      "learning_rate": 1.4140458737290142e-06,
      "loss": 13.9439,
      "step": 300
    },
    {
      "epoch": 0.08278145695364239,
      "grad_norm": 31.533185958862305,
      "learning_rate": 1.6505083944194847e-06,
      "loss": 12.7951,
      "step": 350
    },
    {
      "epoch": 0.0946073793755913,
      "grad_norm": 33.31780242919922,
      "learning_rate": 1.8869709151099552e-06,
      "loss": 11.7283,
      "step": 400
    },
    {
      "epoch": 0.10643330179754021,
      "grad_norm": 36.39932632446289,
      "learning_rate": 2.123433435800426e-06,
      "loss": 10.694,
      "step": 450
    },
    {
      "epoch": 0.11825922421948912,
      "grad_norm": 39.11393356323242,
      "learning_rate": 2.3598959564908965e-06,
      "loss": 9.4759,
      "step": 500
    },
    {
      "epoch": 0.13008514664143803,
      "grad_norm": 32.978511810302734,
      "learning_rate": 2.596358477181367e-06,
      "loss": 8.6215,
      "step": 550
    },
    {
      "epoch": 0.14191106906338694,
      "grad_norm": 33.80763244628906,
      "learning_rate": 2.8328209978718375e-06,
      "loss": 7.729,
      "step": 600
    },
    {
      "epoch": 0.15373699148533584,
      "grad_norm": 32.52557373046875,
      "learning_rate": 3.069283518562308e-06,
      "loss": 7.1881,
      "step": 650
    },
    {
      "epoch": 0.16556291390728478,
      "grad_norm": 29.276039123535156,
      "learning_rate": 3.3057460392527786e-06,
      "loss": 6.9661,
      "step": 700
    },
    {
      "epoch": 0.1773888363292337,
      "grad_norm": 29.209379196166992,
      "learning_rate": 3.5422085599432495e-06,
      "loss": 6.4771,
      "step": 750
    },
    {
      "epoch": 0.1892147587511826,
      "grad_norm": 28.865949630737305,
      "learning_rate": 3.77867108063372e-06,
      "loss": 6.1275,
      "step": 800
    },
    {
      "epoch": 0.2010406811731315,
      "grad_norm": 29.751232147216797,
      "learning_rate": 4.01513360132419e-06,
      "loss": 6.12,
      "step": 850
    },
    {
      "epoch": 0.21286660359508042,
      "grad_norm": 27.77039337158203,
      "learning_rate": 4.2515961220146615e-06,
      "loss": 5.9566,
      "step": 900
    },
    {
      "epoch": 0.22469252601702933,
      "grad_norm": 28.1367130279541,
      "learning_rate": 4.488058642705131e-06,
      "loss": 5.8145,
      "step": 950
    },
    {
      "epoch": 0.23651844843897823,
      "grad_norm": 26.56863021850586,
      "learning_rate": 4.7245211633956025e-06,
      "loss": 5.559,
      "step": 1000
    },
    {
      "epoch": 0.24834437086092714,
      "grad_norm": 24.36810302734375,
      "learning_rate": 4.960983684086072e-06,
      "loss": 5.2348,
      "step": 1050
    },
    {
      "epoch": 0.26017029328287605,
      "grad_norm": 25.959495544433594,
      "learning_rate": 5.197446204776543e-06,
      "loss": 5.3013,
      "step": 1100
    },
    {
      "epoch": 0.27199621570482496,
      "grad_norm": 26.230960845947266,
      "learning_rate": 5.433908725467014e-06,
      "loss": 5.0565,
      "step": 1150
    },
    {
      "epoch": 0.28382213812677387,
      "grad_norm": 26.86113166809082,
      "learning_rate": 5.670371246157485e-06,
      "loss": 4.8716,
      "step": 1200
    },
    {
      "epoch": 0.2956480605487228,
      "grad_norm": 21.906108856201172,
      "learning_rate": 5.906833766847954e-06,
      "loss": 4.7829,
      "step": 1250
    },
    {
      "epoch": 0.3074739829706717,
      "grad_norm": 23.101173400878906,
      "learning_rate": 6.143296287538426e-06,
      "loss": 4.8804,
      "step": 1300
    },
    {
      "epoch": 0.3192999053926206,
      "grad_norm": 24.288232803344727,
      "learning_rate": 6.379758808228896e-06,
      "loss": 4.6464,
      "step": 1350
    },
    {
      "epoch": 0.33112582781456956,
      "grad_norm": 22.537385940551758,
      "learning_rate": 6.616221328919367e-06,
      "loss": 4.7044,
      "step": 1400
    },
    {
      "epoch": 0.34295175023651847,
      "grad_norm": 21.849151611328125,
      "learning_rate": 6.852683849609837e-06,
      "loss": 4.5196,
      "step": 1450
    },
    {
      "epoch": 0.3547776726584674,
      "grad_norm": 24.385927200317383,
      "learning_rate": 7.089146370300309e-06,
      "loss": 4.4961,
      "step": 1500
    },
    {
      "epoch": 0.3666035950804163,
      "grad_norm": 23.45542335510254,
      "learning_rate": 7.325608890990778e-06,
      "loss": 4.4388,
      "step": 1550
    },
    {
      "epoch": 0.3784295175023652,
      "grad_norm": 24.437057495117188,
      "learning_rate": 7.562071411681249e-06,
      "loss": 4.1692,
      "step": 1600
    },
    {
      "epoch": 0.3902554399243141,
      "grad_norm": 22.47982406616211,
      "learning_rate": 7.79853393237172e-06,
      "loss": 4.2153,
      "step": 1650
    },
    {
      "epoch": 0.402081362346263,
      "grad_norm": 22.51207160949707,
      "learning_rate": 8.03499645306219e-06,
      "loss": 3.9962,
      "step": 1700
    },
    {
      "epoch": 0.4139072847682119,
      "grad_norm": 23.745113372802734,
      "learning_rate": 8.271458973752661e-06,
      "loss": 4.1288,
      "step": 1750
    },
    {
      "epoch": 0.42573320719016083,
      "grad_norm": 24.001792907714844,
      "learning_rate": 8.507921494443131e-06,
      "loss": 4.023,
      "step": 1800
    },
    {
      "epoch": 0.43755912961210974,
      "grad_norm": 20.710079193115234,
      "learning_rate": 8.744384015133602e-06,
      "loss": 3.9173,
      "step": 1850
    },
    {
      "epoch": 0.44938505203405865,
      "grad_norm": 19.746440887451172,
      "learning_rate": 8.980846535824072e-06,
      "loss": 3.7544,
      "step": 1900
    },
    {
      "epoch": 0.46121097445600756,
      "grad_norm": 22.844385147094727,
      "learning_rate": 9.217309056514543e-06,
      "loss": 3.8234,
      "step": 1950
    },
    {
      "epoch": 0.47303689687795647,
      "grad_norm": 22.3209285736084,
      "learning_rate": 9.453771577205015e-06,
      "loss": 3.8007,
      "step": 2000
    },
    {
      "epoch": 0.47303689687795647,
      "eval_runtime": 48.8183,
      "eval_samples_per_second": 0.0,
      "eval_steps_per_second": 0.0,
      "eval_validation_loss": 5.987252022653418,
      "step": 2000
    }
  ],
  "logging_steps": 50,
  "max_steps": 21140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}