trainer_state.json

{
  "best_metric": 0.6931407942238267,
  "best_model_checkpoint": "output/fine_tuned/t5-base/RTE/checkpoint-780",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 780,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.49458483754512633,
      "eval_loss": 0.6981508135795593,
      "eval_runtime": 0.6368,
      "eval_samples_per_second": 434.966,
      "eval_steps_per_second": 54.96,
      "step": 78
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5631768953068592,
      "eval_loss": 0.6822376251220703,
      "eval_runtime": 0.6345,
      "eval_samples_per_second": 436.546,
      "eval_steps_per_second": 55.159,
      "step": 156
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.592057761732852,
      "eval_loss": 0.664194643497467,
      "eval_runtime": 0.627,
      "eval_samples_per_second": 441.797,
      "eval_steps_per_second": 55.823,
      "step": 234
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6101083032490975,
      "eval_loss": 0.6544933915138245,
      "eval_runtime": 0.632,
      "eval_samples_per_second": 438.261,
      "eval_steps_per_second": 55.376,
      "step": 312
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6389891696750902,
      "eval_loss": 0.6432966589927673,
      "eval_runtime": 0.6232,
      "eval_samples_per_second": 444.454,
      "eval_steps_per_second": 56.158,
      "step": 390
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6606498194945848,
      "eval_loss": 0.6844415068626404,
      "eval_runtime": 0.6263,
      "eval_samples_per_second": 442.269,
      "eval_steps_per_second": 55.882,
      "step": 468
    },
    {
      "epoch": 6.410256410256411,
      "grad_norm": 4.859732627868652,
      "learning_rate": 1.794871794871795e-05,
      "loss": 0.5942,
      "step": 500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6462093862815884,
      "eval_loss": 0.7054325342178345,
      "eval_runtime": 0.6316,
      "eval_samples_per_second": 438.543,
      "eval_steps_per_second": 55.412,
      "step": 546
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6642599277978339,
      "eval_loss": 0.7449424266815186,
      "eval_runtime": 0.6256,
      "eval_samples_per_second": 442.773,
      "eval_steps_per_second": 55.946,
      "step": 624
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6714801444043321,
      "eval_loss": 0.7661617994308472,
      "eval_runtime": 0.6292,
      "eval_samples_per_second": 440.229,
      "eval_steps_per_second": 55.625,
      "step": 702
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.6931407942238267,
      "eval_loss": 0.7698411345481873,
      "eval_runtime": 0.636,
      "eval_samples_per_second": 435.503,
      "eval_steps_per_second": 55.028,
      "step": 780
    },
    {
      "epoch": 10.0,
      "step": 780,
      "total_flos": 3802086289152000.0,
      "train_loss": 0.5113652938451523,
      "train_runtime": 165.5156,
      "train_samples_per_second": 150.439,
      "train_steps_per_second": 4.713
    }
  ],
  "logging_steps": 500,
  "max_steps": 780,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 3802086289152000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}