{
  "best_metric": 0.49937015771865845,
  "best_model_checkpoint": "sequence_classification/checkpoint-9794",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 9794,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10210332856851133,
      "grad_norm": 65.69414520263672,
      "learning_rate": 9.489483357157444e-05,
      "loss": 0.7807,
      "step": 500
    },
    {
      "epoch": 0.20420665713702266,
      "grad_norm": 63.07129669189453,
      "learning_rate": 8.978966714314887e-05,
      "loss": 0.6422,
      "step": 1000
    },
    {
      "epoch": 0.306309985705534,
      "grad_norm": 25.590089797973633,
      "learning_rate": 8.46845007147233e-05,
      "loss": 0.6025,
      "step": 1500
    },
    {
      "epoch": 0.4084133142740453,
      "grad_norm": 15.698567390441895,
      "learning_rate": 7.957933428629773e-05,
      "loss": 0.579,
      "step": 2000
    },
    {
      "epoch": 0.5105166428425567,
      "grad_norm": 21.827106475830078,
      "learning_rate": 7.447416785787217e-05,
      "loss": 0.5758,
      "step": 2500
    },
    {
      "epoch": 0.612619971411068,
      "grad_norm": 16.527406692504883,
      "learning_rate": 6.93690014294466e-05,
      "loss": 0.5614,
      "step": 3000
    },
    {
      "epoch": 0.7147232999795793,
      "grad_norm": 38.88615417480469,
      "learning_rate": 6.426383500102104e-05,
      "loss": 0.5579,
      "step": 3500
    },
    {
      "epoch": 0.8168266285480906,
      "grad_norm": 30.469078063964844,
      "learning_rate": 5.9158668572595464e-05,
      "loss": 0.5451,
      "step": 4000
    },
    {
      "epoch": 0.918929957116602,
      "grad_norm": 31.0489444732666,
      "learning_rate": 5.40535021441699e-05,
      "loss": 0.5408,
      "step": 4500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7511115271212617,
      "eval_f1-score": 0.7514023934181002,
      "eval_loss": 0.5151644945144653,
      "eval_precision": 0.7523871934094739,
      "eval_recall": 0.7504201680672269,
      "eval_runtime": 6409.5702,
      "eval_samples_per_second": 3.334,
      "eval_steps_per_second": 0.417,
      "step": 4897
    },
    {
      "epoch": 1.0210332856851134,
      "grad_norm": 30.953594207763672,
      "learning_rate": 4.8948335715744334e-05,
      "loss": 0.5478,
      "step": 5000
    },
    {
      "epoch": 1.1231366142536248,
      "grad_norm": 22.760286331176758,
      "learning_rate": 4.384316928731877e-05,
      "loss": 0.54,
      "step": 5500
    },
    {
      "epoch": 1.225239942822136,
      "grad_norm": 63.70338821411133,
      "learning_rate": 3.8738002858893204e-05,
      "loss": 0.5308,
      "step": 6000
    },
    {
      "epoch": 1.3273432713906472,
      "grad_norm": 15.89914321899414,
      "learning_rate": 3.363283643046763e-05,
      "loss": 0.5258,
      "step": 6500
    },
    {
      "epoch": 1.4294465999591588,
      "grad_norm": 13.948808670043945,
      "learning_rate": 2.8527670002042067e-05,
      "loss": 0.5244,
      "step": 7000
    },
    {
      "epoch": 1.53154992852767,
      "grad_norm": 43.452964782714844,
      "learning_rate": 2.34225035736165e-05,
      "loss": 0.5135,
      "step": 7500
    },
    {
      "epoch": 1.6336532570961815,
      "grad_norm": 12.346921920776367,
      "learning_rate": 1.8317337145190937e-05,
      "loss": 0.5244,
      "step": 8000
    },
    {
      "epoch": 1.7357565856646926,
      "grad_norm": 11.3629150390625,
      "learning_rate": 1.3212170716765368e-05,
      "loss": 0.4938,
      "step": 8500
    },
    {
      "epoch": 1.8378599142332042,
      "grad_norm": 30.596006393432617,
      "learning_rate": 8.1070042883398e-06,
      "loss": 0.4958,
      "step": 9000
    },
    {
      "epoch": 1.9399632428017153,
      "grad_norm": 21.20801544189453,
      "learning_rate": 3.001837859914233e-06,
      "loss": 0.5157,
      "step": 9500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7600037440913558,
      "eval_f1-score": 0.7677746580925641,
      "eval_loss": 0.49937015771865845,
      "eval_precision": 0.7454273654590221,
      "eval_recall": 0.7915032679738562,
      "eval_runtime": 8190.7633,
      "eval_samples_per_second": 2.609,
      "eval_steps_per_second": 0.326,
      "step": 9794
    }
  ],
  "logging_steps": 500,
  "max_steps": 9794,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 4.589981822188339e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}