trainer_state.json

{
  "best_metric": 0.6027122735977173,
  "best_model_checkpoint": "distilbert_lda_100_v1_cola/checkpoint-102",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 272,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.6636441946029663,
      "learning_rate": 4.9e-05,
      "loss": 0.6159,
      "step": 34
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 0.6177998185157776,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.4528,
      "eval_samples_per_second": 2303.491,
      "eval_steps_per_second": 11.043,
      "step": 34
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2404123544692993,
      "learning_rate": 4.8e-05,
      "loss": 0.6093,
      "step": 68
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 0.6119470000267029,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.4511,
      "eval_samples_per_second": 2312.02,
      "eval_steps_per_second": 11.084,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.806337594985962,
      "learning_rate": 4.7e-05,
      "loss": 0.5931,
      "step": 102
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6941514611244202,
      "eval_loss": 0.6027122735977173,
      "eval_matthews_correlation": 0.07380739515541786,
      "eval_runtime": 0.4523,
      "eval_samples_per_second": 2306.148,
      "eval_steps_per_second": 11.055,
      "step": 102
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.064990282058716,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.5666,
      "step": 136
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6759347915649414,
      "eval_loss": 0.6384022235870361,
      "eval_matthews_correlation": 0.059256956031148784,
      "eval_runtime": 0.4708,
      "eval_samples_per_second": 2215.273,
      "eval_steps_per_second": 10.62,
      "step": 136
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.6135334968566895,
      "learning_rate": 4.5e-05,
      "loss": 0.5078,
      "step": 170
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6778523325920105,
      "eval_loss": 0.6254388689994812,
      "eval_matthews_correlation": 0.159181560428127,
      "eval_runtime": 0.4559,
      "eval_samples_per_second": 2287.607,
      "eval_steps_per_second": 10.966,
      "step": 170
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.216343402862549,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.4515,
      "step": 204
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6577181220054626,
      "eval_loss": 0.6839206218719482,
      "eval_matthews_correlation": 0.1393279362508076,
      "eval_runtime": 0.4589,
      "eval_samples_per_second": 2272.583,
      "eval_steps_per_second": 10.894,
      "step": 204
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.1916520595550537,
      "learning_rate": 4.3e-05,
      "loss": 0.3898,
      "step": 238
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6490891575813293,
      "eval_loss": 0.7272051572799683,
      "eval_matthews_correlation": 0.1521485882058856,
      "eval_runtime": 0.4625,
      "eval_samples_per_second": 2255.152,
      "eval_steps_per_second": 10.811,
      "step": 238
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.3879318237304688,
      "learning_rate": 4.2e-05,
      "loss": 0.3342,
      "step": 272
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6615532040596008,
      "eval_loss": 0.8068291544914246,
      "eval_matthews_correlation": 0.13447152115893618,
      "eval_runtime": 0.4674,
      "eval_samples_per_second": 2231.527,
      "eval_steps_per_second": 10.698,
      "step": 272
    },
    {
      "epoch": 8.0,
      "step": 272,
      "total_flos": 4530914903629824.0,
      "train_loss": 0.5085263637935414,
      "train_runtime": 81.8126,
      "train_samples_per_second": 5225.968,
      "train_steps_per_second": 20.779
    }
  ],
  "logging_steps": 1,
  "max_steps": 1700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4530914903629824.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}