run-px14tzqx/checkpoint-100/trainer_state.json

{
  "best_metric": 0.8192771084337349,
  "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-px14tzqx/checkpoint-100",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 1.840433955192566,
      "learning_rate": 3.6141992925016376e-05,
      "loss": 0.5748,
      "step": 10
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.9818997383117676,
      "learning_rate": 3.212621593334789e-05,
      "loss": 0.4969,
      "step": 20
    },
    {
      "epoch": 0.6,
      "grad_norm": 2.860091209411621,
      "learning_rate": 2.8110438941679397e-05,
      "loss": 0.3766,
      "step": 30
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.881857395172119,
      "learning_rate": 2.4094661950010915e-05,
      "loss": 0.4191,
      "step": 40
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.081721782684326,
      "learning_rate": 2.007888495834243e-05,
      "loss": 0.3327,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8775,
      "eval_f1": 0.8,
      "eval_loss": 0.3189445436000824,
      "eval_precision": 0.8032786885245902,
      "eval_recall": 0.7967479674796748,
      "eval_runtime": 1.5271,
      "eval_samples_per_second": 261.938,
      "eval_steps_per_second": 16.371,
      "step": 50
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.8768179416656494,
      "learning_rate": 1.6063107966673943e-05,
      "loss": 0.247,
      "step": 60
    },
    {
      "epoch": 1.4,
      "grad_norm": 4.414927005767822,
      "learning_rate": 1.2047330975005458e-05,
      "loss": 0.3165,
      "step": 70
    },
    {
      "epoch": 1.6,
      "grad_norm": 10.319426536560059,
      "learning_rate": 8.031553983336972e-06,
      "loss": 0.2812,
      "step": 80
    },
    {
      "epoch": 1.8,
      "grad_norm": 6.239277362823486,
      "learning_rate": 4.015776991668486e-06,
      "loss": 0.3342,
      "step": 90
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.691807270050049,
      "learning_rate": 0.0,
      "loss": 0.2599,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8875,
      "eval_f1": 0.8192771084337349,
      "eval_loss": 0.28145602345466614,
      "eval_precision": 0.8095238095238095,
      "eval_recall": 0.8292682926829268,
      "eval_runtime": 1.5969,
      "eval_samples_per_second": 250.483,
      "eval_steps_per_second": 15.655,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "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": 423630740901888.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "_wandb": {},
    "assignments": {},
    "learning_rate": 4.015776991668486e-05,
    "metric": "eval/loss",
    "num_train_epochs": 2,
    "per_device_train_batch_size": 32,
    "seed": 31
  }
}