{
  "best_metric": 0.0846095159649849,
  "best_model_checkpoint": "/cronus_data/avirinchipur/implicit_motives/schone_ach_roba_large/final/checkpoint-1660",
  "epoch": 4.992481203007519,
  "eval_steps": 500,
  "global_step": 1660,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 2.906954526901245,
      "learning_rate": 9.698795180722893e-06,
      "loss": 0.3261,
      "step": 50
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 2.4998762607574463,
      "learning_rate": 9.397590361445785e-06,
      "loss": 0.2116,
      "step": 100
    },
    {
      "epoch": 0.45112781954887216,
      "grad_norm": 2.2140071392059326,
      "learning_rate": 9.096385542168675e-06,
      "loss": 0.2101,
      "step": 150
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 2.7675399780273438,
      "learning_rate": 8.795180722891567e-06,
      "loss": 0.2021,
      "step": 200
    },
    {
      "epoch": 0.7518796992481203,
      "grad_norm": 3.146375894546509,
      "learning_rate": 8.493975903614459e-06,
      "loss": 0.1879,
      "step": 250
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 2.361593008041382,
      "learning_rate": 8.19277108433735e-06,
      "loss": 0.185,
      "step": 300
    },
    {
      "epoch": 0.9984962406015038,
      "eval_loss": 0.15738171339035034,
      "eval_roc_auc": 0.9583146269309021,
      "eval_runtime": 37.5317,
      "eval_samples_per_second": 434.326,
      "eval_steps_per_second": 1.705,
      "step": 332
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 4.361939907073975,
      "learning_rate": 7.891566265060243e-06,
      "loss": 0.1854,
      "step": 350
    },
    {
      "epoch": 1.2030075187969924,
      "grad_norm": 2.5755579471588135,
      "learning_rate": 7.590361445783133e-06,
      "loss": 0.1681,
      "step": 400
    },
    {
      "epoch": 1.3533834586466165,
      "grad_norm": 2.735053539276123,
      "learning_rate": 7.289156626506025e-06,
      "loss": 0.1685,
      "step": 450
    },
    {
      "epoch": 1.5037593984962405,
      "grad_norm": 4.289336681365967,
      "learning_rate": 6.987951807228917e-06,
      "loss": 0.1537,
      "step": 500
    },
    {
      "epoch": 1.6541353383458648,
      "grad_norm": 3.1198232173919678,
      "learning_rate": 6.686746987951808e-06,
      "loss": 0.1658,
      "step": 550
    },
    {
      "epoch": 1.8045112781954886,
      "grad_norm": 2.722614049911499,
      "learning_rate": 6.385542168674699e-06,
      "loss": 0.168,
      "step": 600
    },
    {
      "epoch": 1.954887218045113,
      "grad_norm": 2.933856964111328,
      "learning_rate": 6.084337349397591e-06,
      "loss": 0.1607,
      "step": 650
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.12831807136535645,
      "eval_roc_auc": 0.9730460251844583,
      "eval_runtime": 37.2749,
      "eval_samples_per_second": 437.318,
      "eval_steps_per_second": 1.717,
      "step": 665
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 2.1795623302459717,
      "learning_rate": 5.783132530120482e-06,
      "loss": 0.1448,
      "step": 700
    },
    {
      "epoch": 2.255639097744361,
      "grad_norm": 3.511441230773926,
      "learning_rate": 5.4819277108433745e-06,
      "loss": 0.1407,
      "step": 750
    },
    {
      "epoch": 2.406015037593985,
      "grad_norm": 3.4894182682037354,
      "learning_rate": 5.180722891566266e-06,
      "loss": 0.1462,
      "step": 800
    },
    {
      "epoch": 2.556390977443609,
      "grad_norm": 2.4312453269958496,
      "learning_rate": 4.8795180722891575e-06,
      "loss": 0.1395,
      "step": 850
    },
    {
      "epoch": 2.706766917293233,
      "grad_norm": 2.9382171630859375,
      "learning_rate": 4.578313253012049e-06,
      "loss": 0.1379,
      "step": 900
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 2.9116907119750977,
      "learning_rate": 4.27710843373494e-06,
      "loss": 0.1357,
      "step": 950
    },
    {
      "epoch": 2.998496240601504,
      "eval_loss": 0.10705896466970444,
      "eval_roc_auc": 0.9818360739923565,
      "eval_runtime": 37.422,
      "eval_samples_per_second": 435.599,
      "eval_steps_per_second": 1.71,
      "step": 997
    },
    {
      "epoch": 3.007518796992481,
      "grad_norm": 2.7223000526428223,
      "learning_rate": 3.975903614457832e-06,
      "loss": 0.1395,
      "step": 1000
    },
    {
      "epoch": 3.1578947368421053,
      "grad_norm": 2.47904634475708,
      "learning_rate": 3.6746987951807235e-06,
      "loss": 0.1247,
      "step": 1050
    },
    {
      "epoch": 3.308270676691729,
      "grad_norm": 3.8209755420684814,
      "learning_rate": 3.3734939759036146e-06,
      "loss": 0.1138,
      "step": 1100
    },
    {
      "epoch": 3.4586466165413534,
      "grad_norm": 2.873736619949341,
      "learning_rate": 3.072289156626506e-06,
      "loss": 0.121,
      "step": 1150
    },
    {
      "epoch": 3.6090225563909772,
      "grad_norm": 2.8755416870117188,
      "learning_rate": 2.771084337349398e-06,
      "loss": 0.1184,
      "step": 1200
    },
    {
      "epoch": 3.7593984962406015,
      "grad_norm": 3.195455312728882,
      "learning_rate": 2.469879518072289e-06,
      "loss": 0.1201,
      "step": 1250
    },
    {
      "epoch": 3.909774436090226,
      "grad_norm": 5.824981212615967,
      "learning_rate": 2.168674698795181e-06,
      "loss": 0.1214,
      "step": 1300
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.09776945412158966,
      "eval_roc_auc": 0.9869506244923937,
      "eval_runtime": 37.3331,
      "eval_samples_per_second": 436.636,
      "eval_steps_per_second": 1.714,
      "step": 1330
    },
    {
      "epoch": 4.06015037593985,
      "grad_norm": 2.435054063796997,
      "learning_rate": 1.8674698795180723e-06,
      "loss": 0.1167,
      "step": 1350
    },
    {
      "epoch": 4.2105263157894735,
      "grad_norm": 3.873215436935425,
      "learning_rate": 1.566265060240964e-06,
      "loss": 0.1077,
      "step": 1400
    },
    {
      "epoch": 4.360902255639098,
      "grad_norm": 3.5485968589782715,
      "learning_rate": 1.2650602409638555e-06,
      "loss": 0.1027,
      "step": 1450
    },
    {
      "epoch": 4.511278195488722,
      "grad_norm": 4.283125877380371,
      "learning_rate": 9.638554216867472e-07,
      "loss": 0.1144,
      "step": 1500
    },
    {
      "epoch": 4.661654135338345,
      "grad_norm": 4.050317287445068,
      "learning_rate": 6.626506024096387e-07,
      "loss": 0.1075,
      "step": 1550
    },
    {
      "epoch": 4.81203007518797,
      "grad_norm": 3.838085889816284,
      "learning_rate": 3.614457831325301e-07,
      "loss": 0.1078,
      "step": 1600
    },
    {
      "epoch": 4.962406015037594,
      "grad_norm": 3.882603645324707,
      "learning_rate": 6.02409638554217e-08,
      "loss": 0.1011,
      "step": 1650
    },
    {
      "epoch": 4.992481203007519,
      "eval_loss": 0.0846095159649849,
      "eval_roc_auc": 0.9888130720155254,
      "eval_runtime": 37.3263,
      "eval_samples_per_second": 436.716,
      "eval_steps_per_second": 1.715,
      "step": 1660
    },
    {
      "epoch": 4.992481203007519,
      "step": 1660,
      "total_flos": 4.323837898114577e+16,
      "train_loss": 0.14982930845524892,
      "train_runtime": 2902.6478,
      "train_samples_per_second": 146.465,
      "train_steps_per_second": 0.572
    }
  ],
  "logging_steps": 50,
  "max_steps": 1660,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4.323837898114577e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}