run-qc7leity/checkpoint-75/trainer_state.json

{
  "best_metric": 0.8081632653061225,
  "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-qc7leity/checkpoint-75",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.7251797914505005,
      "learning_rate": 4.999394652050283e-05,
      "loss": 0.5546,
      "step": 10
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.5507678985595703,
      "learning_rate": 4.56466468230678e-05,
      "loss": 0.4465,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.845,
      "eval_f1": 0.7232142857142857,
      "eval_loss": 0.35433030128479004,
      "eval_precision": 0.801980198019802,
      "eval_recall": 0.6585365853658537,
      "eval_runtime": 1.5353,
      "eval_samples_per_second": 260.541,
      "eval_steps_per_second": 16.284,
      "step": 25
    },
    {
      "epoch": 1.2,
      "grad_norm": 2.895219326019287,
      "learning_rate": 4.1299347125632775e-05,
      "loss": 0.3557,
      "step": 30
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.417137622833252,
      "learning_rate": 3.695204742819774e-05,
      "loss": 0.295,
      "step": 40
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.1863083839416504,
      "learning_rate": 3.260474773076271e-05,
      "loss": 0.2889,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.875,
      "eval_f1": 0.7767857142857143,
      "eval_loss": 0.2988013029098511,
      "eval_precision": 0.8613861386138614,
      "eval_recall": 0.7073170731707317,
      "eval_runtime": 1.5258,
      "eval_samples_per_second": 262.156,
      "eval_steps_per_second": 16.385,
      "step": 50
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.8937768936157227,
      "learning_rate": 2.8257448033327686e-05,
      "loss": 0.2208,
      "step": 60
    },
    {
      "epoch": 2.8,
      "grad_norm": 4.932840824127197,
      "learning_rate": 2.3910148335892658e-05,
      "loss": 0.2086,
      "step": 70
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8825,
      "eval_f1": 0.8081632653061225,
      "eval_loss": 0.30829551815986633,
      "eval_precision": 0.8114754098360656,
      "eval_recall": 0.8048780487804879,
      "eval_runtime": 1.5157,
      "eval_samples_per_second": 263.911,
      "eval_steps_per_second": 16.494,
      "step": 75
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "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": 593189011181568.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "_wandb": {},
    "assignments": {},
    "learning_rate": 5.434124621793786e-05,
    "metric": "eval/loss",
    "num_train_epochs": 5,
    "per_device_train_batch_size": 64,
    "seed": 14
  }
}