run-hc8i9nht/checkpoint-200/trainer_state.json

{
  "best_metric": 0.7901234567901234,
  "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-hc8i9nht/checkpoint-200",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 3.6317474842071533,
      "learning_rate": 8.174509670130923e-05,
      "loss": 0.543,
      "step": 10
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.941434860229492,
      "learning_rate": 8.091938865382126e-05,
      "loss": 0.4521,
      "step": 20
    },
    {
      "epoch": 0.15,
      "grad_norm": 8.016721725463867,
      "learning_rate": 8.009368060633328e-05,
      "loss": 0.4908,
      "step": 30
    },
    {
      "epoch": 0.2,
      "grad_norm": 2.4489011764526367,
      "learning_rate": 7.92679725588453e-05,
      "loss": 0.4119,
      "step": 40
    },
    {
      "epoch": 0.25,
      "grad_norm": 3.7478549480438232,
      "learning_rate": 7.844226451135734e-05,
      "loss": 0.5418,
      "step": 50
    },
    {
      "epoch": 0.3,
      "grad_norm": 20.588834762573242,
      "learning_rate": 7.761655646386936e-05,
      "loss": 0.3073,
      "step": 60
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.3618388175964355,
      "learning_rate": 7.67908484163814e-05,
      "loss": 0.4359,
      "step": 70
    },
    {
      "epoch": 0.4,
      "grad_norm": 7.6314921379089355,
      "learning_rate": 7.596514036889342e-05,
      "loss": 0.5815,
      "step": 80
    },
    {
      "epoch": 0.45,
      "grad_norm": 5.3096113204956055,
      "learning_rate": 7.513943232140545e-05,
      "loss": 0.4516,
      "step": 90
    },
    {
      "epoch": 0.5,
      "grad_norm": 8.00711441040039,
      "learning_rate": 7.431372427391748e-05,
      "loss": 0.5594,
      "step": 100
    },
    {
      "epoch": 0.55,
      "grad_norm": 2.1074318885803223,
      "learning_rate": 7.348801622642951e-05,
      "loss": 0.4839,
      "step": 110
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.2857903242111206,
      "learning_rate": 7.266230817894153e-05,
      "loss": 0.3655,
      "step": 120
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.47830930352211,
      "learning_rate": 7.183660013145356e-05,
      "loss": 0.4362,
      "step": 130
    },
    {
      "epoch": 0.7,
      "grad_norm": 6.92142915725708,
      "learning_rate": 7.101089208396559e-05,
      "loss": 0.3585,
      "step": 140
    },
    {
      "epoch": 0.75,
      "grad_norm": 12.701593399047852,
      "learning_rate": 7.018518403647762e-05,
      "loss": 0.4539,
      "step": 150
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.4179468154907227,
      "learning_rate": 6.935947598898965e-05,
      "loss": 0.291,
      "step": 160
    },
    {
      "epoch": 0.85,
      "grad_norm": 6.713927745819092,
      "learning_rate": 6.853376794150168e-05,
      "loss": 0.533,
      "step": 170
    },
    {
      "epoch": 0.9,
      "grad_norm": 4.076853275299072,
      "learning_rate": 6.77080598940137e-05,
      "loss": 0.4721,
      "step": 180
    },
    {
      "epoch": 0.95,
      "grad_norm": 4.515071868896484,
      "learning_rate": 6.688235184652574e-05,
      "loss": 0.4085,
      "step": 190
    },
    {
      "epoch": 1.0,
      "grad_norm": 5.7936811447143555,
      "learning_rate": 6.605664379903777e-05,
      "loss": 0.391,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8725,
      "eval_f1": 0.7901234567901234,
      "eval_loss": 0.337982714176178,
      "eval_precision": 0.8,
      "eval_recall": 0.7804878048780488,
      "eval_runtime": 1.5299,
      "eval_samples_per_second": 261.453,
      "eval_steps_per_second": 16.341,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 211815370450944.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "_wandb": {},
    "assignments": {},
    "learning_rate": 8.25708047487972e-05,
    "metric": "eval/loss",
    "num_train_epochs": 5,
    "per_device_train_batch_size": 8,
    "seed": 17
  }
}