trainer_state.json

{
  "best_metric": 0.6493010279892045,
  "best_model_checkpoint": "./models/as_TrA50_XLM/checkpoint-4986",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 4986,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9987966305655837,
      "grad_norm": 4.042017936706543,
      "learning_rate": 4.1676694745286805e-05,
      "loss": 0.7179,
      "step": 830
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.5016971754152019,
      "eval_loss": 0.3967933654785156,
      "eval_precision": 0.48018796774380695,
      "eval_recall": 0.525223681705692,
      "eval_runtime": 36.5565,
      "eval_samples_per_second": 303.339,
      "eval_steps_per_second": 4.76,
      "step": 831
    },
    {
      "epoch": 1.9975932611311673,
      "grad_norm": 3.9885966777801514,
      "learning_rate": 3.335338949057361e-05,
      "loss": 0.4331,
      "step": 1660
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.5287363073037502,
      "eval_loss": 0.36940571665763855,
      "eval_precision": 0.4921277061010278,
      "eval_recall": 0.5712291389047528,
      "eval_runtime": 36.6256,
      "eval_samples_per_second": 302.766,
      "eval_steps_per_second": 4.751,
      "step": 1662
    },
    {
      "epoch": 2.996389891696751,
      "grad_norm": 3.235121250152588,
      "learning_rate": 2.5030084235860413e-05,
      "loss": 0.3391,
      "step": 2490
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.607596501529808,
      "eval_loss": 0.289639949798584,
      "eval_precision": 0.5922400289191468,
      "eval_recall": 0.623770543816232,
      "eval_runtime": 36.3105,
      "eval_samples_per_second": 305.393,
      "eval_steps_per_second": 4.792,
      "step": 2493
    },
    {
      "epoch": 3.9951865222623346,
      "grad_norm": 5.095285415649414,
      "learning_rate": 1.6706778981147215e-05,
      "loss": 0.2637,
      "step": 3320
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.6188354585957905,
      "eval_loss": 0.2840094566345215,
      "eval_precision": 0.5999046824734898,
      "eval_recall": 0.638999936544197,
      "eval_runtime": 36.309,
      "eval_samples_per_second": 305.407,
      "eval_steps_per_second": 4.792,
      "step": 3324
    },
    {
      "epoch": 4.993983152827918,
      "grad_norm": 3.0477702617645264,
      "learning_rate": 8.383473726434016e-06,
      "loss": 0.2006,
      "step": 4150
    },
    {
      "epoch": 5.0,
      "eval_f1": 0.6398084151812781,
      "eval_loss": 0.2787846028804779,
      "eval_precision": 0.6125137848975565,
      "eval_recall": 0.6696490894092265,
      "eval_runtime": 36.4904,
      "eval_samples_per_second": 303.888,
      "eval_steps_per_second": 4.768,
      "step": 4155
    },
    {
      "epoch": 5.992779783393502,
      "grad_norm": 3.478201150894165,
      "learning_rate": 6.01684717208183e-08,
      "loss": 0.1535,
      "step": 4980
    },
    {
      "epoch": 6.0,
      "eval_f1": 0.6493010279892045,
      "eval_loss": 0.27660489082336426,
      "eval_precision": 0.6217911487977698,
      "eval_recall": 0.6793578272733042,
      "eval_runtime": 36.2487,
      "eval_samples_per_second": 305.914,
      "eval_steps_per_second": 4.8,
      "step": 4986
    }
  ],
  "logging_steps": 830,
  "max_steps": 4986,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 4.58906727159972e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}