run-1/checkpoint-4276/trainer_state.json

{
  "best_metric": 0.4209858842371305,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-4276",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 4276,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23386342376052385,
      "grad_norm": 3.146369218826294,
      "learning_rate": 1.653715321124928e-06,
      "loss": 0.6079,
      "step": 500
    },
    {
      "epoch": 0.4677268475210477,
      "grad_norm": 5.078900337219238,
      "learning_rate": 1.5725712916291023e-06,
      "loss": 0.6126,
      "step": 1000
    },
    {
      "epoch": 0.7015902712815716,
      "grad_norm": 7.2771897315979,
      "learning_rate": 1.4914272621332766e-06,
      "loss": 0.5551,
      "step": 1500
    },
    {
      "epoch": 0.9354536950420954,
      "grad_norm": 22.494115829467773,
      "learning_rate": 1.4102832326374508e-06,
      "loss": 0.523,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5956234335899353,
      "eval_matthews_correlation": 0.3084289905217366,
      "eval_runtime": 31.6888,
      "eval_samples_per_second": 32.914,
      "eval_steps_per_second": 2.083,
      "step": 2138
    },
    {
      "epoch": 1.1693171188026192,
      "grad_norm": 14.600356101989746,
      "learning_rate": 1.329139203141625e-06,
      "loss": 0.501,
      "step": 2500
    },
    {
      "epoch": 1.4031805425631432,
      "grad_norm": 20.79261589050293,
      "learning_rate": 1.2479951736457994e-06,
      "loss": 0.5081,
      "step": 3000
    },
    {
      "epoch": 1.637043966323667,
      "grad_norm": 26.76811981201172,
      "learning_rate": 1.1668511441499738e-06,
      "loss": 0.4969,
      "step": 3500
    },
    {
      "epoch": 1.8709073900841908,
      "grad_norm": 24.809595108032227,
      "learning_rate": 1.0857071146541479e-06,
      "loss": 0.5316,
      "step": 4000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5633124113082886,
      "eval_matthews_correlation": 0.4209858842371305,
      "eval_runtime": 30.8324,
      "eval_samples_per_second": 33.828,
      "eval_steps_per_second": 2.141,
      "step": 4276
    }
  ],
  "logging_steps": 500,
  "max_steps": 10690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 65361794770440.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.7348593506207536e-06,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 4,
    "seed": 22
  }
}