trainer_state.json

{
  "best_metric": 0.3185526132583618,
  "best_model_checkpoint": "gal_enpt_mBERT/checkpoint-1250",
  "epoch": 6.0,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8731599607458292,
      "eval_f1": 0.5058593750000001,
      "eval_loss": 0.44716718792915344,
      "eval_precision": 0.5272471030378953,
      "eval_recall": 0.4861391856771585,
      "eval_runtime": 5.2955,
      "eval_samples_per_second": 188.274,
      "eval_steps_per_second": 11.897,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.5676,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8998405299313053,
      "eval_f1": 0.6311310190369541,
      "eval_loss": 0.360060453414917,
      "eval_precision": 0.6534240222600093,
      "eval_recall": 0.6103089806526133,
      "eval_runtime": 5.4164,
      "eval_samples_per_second": 184.072,
      "eval_steps_per_second": 11.631,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9048699705593719,
      "eval_f1": 0.6652892561983471,
      "eval_loss": 0.3387094736099243,
      "eval_precision": 0.6566807313642756,
      "eval_recall": 0.674126479930696,
      "eval_runtime": 5.4866,
      "eval_samples_per_second": 181.716,
      "eval_steps_per_second": 11.483,
      "step": 750
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.267,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9111261040235525,
      "eval_f1": 0.6826845833637625,
      "eval_loss": 0.3349935710430145,
      "eval_precision": 0.6907048913846608,
      "eval_recall": 0.6748483973433439,
      "eval_runtime": 5.3165,
      "eval_samples_per_second": 187.529,
      "eval_steps_per_second": 11.85,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9160942100098135,
      "eval_f1": 0.7013214572534131,
      "eval_loss": 0.3185526132583618,
      "eval_precision": 0.7093486929552504,
      "eval_recall": 0.6934738665896621,
      "eval_runtime": 5.434,
      "eval_samples_per_second": 183.474,
      "eval_steps_per_second": 11.594,
      "step": 1250
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.88e-05,
      "loss": 0.184,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.913610157016683,
      "eval_f1": 0.699079031912615,
      "eval_loss": 0.3342382609844208,
      "eval_precision": 0.6914277644400508,
      "eval_recall": 0.7069015304649148,
      "eval_runtime": 5.3519,
      "eval_samples_per_second": 186.288,
      "eval_steps_per_second": 11.771,
      "step": 1500
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 100,
  "total_flos": 934904811170400.0,
  "trial_name": null,
  "trial_params": null
}