trainer_state.json

{
  "best_metric": 0.06556913256645203,
  "best_model_checkpoint": "deberta-v3-xsmall-zyda-2-transformed-sentiment-new/checkpoint-6033",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 6033,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2486325211337643,
      "grad_norm": 2.0000367164611816,
      "learning_rate": 4.5856124647770596e-05,
      "loss": 0.2003,
      "step": 500
    },
    {
      "epoch": 0.4972650422675286,
      "grad_norm": 2.3387935161590576,
      "learning_rate": 4.17122492955412e-05,
      "loss": 0.1052,
      "step": 1000
    },
    {
      "epoch": 0.7458975634012929,
      "grad_norm": 1.853918194770813,
      "learning_rate": 3.7568373943311785e-05,
      "loss": 0.085,
      "step": 1500
    },
    {
      "epoch": 0.9945300845350572,
      "grad_norm": 1.7671293020248413,
      "learning_rate": 3.342449859108238e-05,
      "loss": 0.0792,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.08709739148616791,
      "eval_mse": 0.08709739712527088,
      "eval_runtime": 14.8419,
      "eval_samples_per_second": 673.767,
      "eval_steps_per_second": 84.221,
      "step": 2011
    },
    {
      "epoch": 1.2431626056688214,
      "grad_norm": 1.0026581287384033,
      "learning_rate": 2.928062323885298e-05,
      "loss": 0.0594,
      "step": 2500
    },
    {
      "epoch": 1.4917951268025857,
      "grad_norm": 0.9303980469703674,
      "learning_rate": 2.5136747886623573e-05,
      "loss": 0.0594,
      "step": 3000
    },
    {
      "epoch": 1.74042764793635,
      "grad_norm": 1.7368980646133423,
      "learning_rate": 2.0992872534394168e-05,
      "loss": 0.0551,
      "step": 3500
    },
    {
      "epoch": 1.9890601690701144,
      "grad_norm": 0.6475295424461365,
      "learning_rate": 1.684899718216476e-05,
      "loss": 0.0541,
      "step": 4000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.06912554055452347,
      "eval_mse": 0.06912553393413896,
      "eval_runtime": 13.2293,
      "eval_samples_per_second": 755.898,
      "eval_steps_per_second": 94.487,
      "step": 4022
    },
    {
      "epoch": 2.2376926902038785,
      "grad_norm": 0.6805059909820557,
      "learning_rate": 1.2705121829935357e-05,
      "loss": 0.0444,
      "step": 4500
    },
    {
      "epoch": 2.486325211337643,
      "grad_norm": 1.3735737800598145,
      "learning_rate": 8.56124647770595e-06,
      "loss": 0.043,
      "step": 5000
    },
    {
      "epoch": 2.734957732471407,
      "grad_norm": 0.9396611452102661,
      "learning_rate": 4.417371125476545e-06,
      "loss": 0.0422,
      "step": 5500
    },
    {
      "epoch": 2.9835902536051715,
      "grad_norm": 0.756208062171936,
      "learning_rate": 2.7349577324714074e-07,
      "loss": 0.0411,
      "step": 6000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.06556913256645203,
      "eval_mse": 0.06556913494220615,
      "eval_runtime": 13.2288,
      "eval_samples_per_second": 755.924,
      "eval_steps_per_second": 94.491,
      "step": 6033
    },
    {
      "epoch": 3.0,
      "step": 6033,
      "total_flos": 6357984788759040.0,
      "train_loss": 0.07220485827706652,
      "train_runtime": 846.782,
      "train_samples_per_second": 455.926,
      "train_steps_per_second": 7.125
    }
  ],
  "logging_steps": 500,
  "max_steps": 6033,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 6357984788759040.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}