trainer_state.json

{
  "best_metric": 0.8917858651698956,
  "best_model_checkpoint": "/kaggle/working/sweep_10/checkpoint-290",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 290,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 1.1105767488479614,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.1464,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8466257668711656,
      "eval_f1_macro": 0.6189095670064528,
      "eval_loss": 0.1092783659696579,
      "eval_precision_macro": 0.9203821656050956,
      "eval_recall_macro": 0.5967741935483871,
      "eval_runtime": 0.9405,
      "eval_samples_per_second": 173.321,
      "eval_steps_per_second": 6.38,
      "step": 58
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 4.811639308929443,
      "learning_rate": 6.985294117647059e-06,
      "loss": 0.1023,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8834355828220859,
      "eval_f1_macro": 0.8289422811378073,
      "eval_loss": 0.06354018300771713,
      "eval_precision_macro": 0.8046747967479675,
      "eval_recall_macro": 0.8663245356793744,
      "eval_runtime": 0.9481,
      "eval_samples_per_second": 171.927,
      "eval_steps_per_second": 6.329,
      "step": 116
    },
    {
      "epoch": 2.586206896551724,
      "grad_norm": 2.146620273590088,
      "learning_rate": 5.147058823529411e-06,
      "loss": 0.0693,
      "step": 150
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9263803680981595,
      "eval_f1_macro": 0.8582608695652174,
      "eval_loss": 0.09711485356092453,
      "eval_precision_macro": 0.9583333333333333,
      "eval_recall_macro": 0.8064516129032258,
      "eval_runtime": 0.9496,
      "eval_samples_per_second": 171.655,
      "eval_steps_per_second": 6.319,
      "step": 174
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 3.015160322189331,
      "learning_rate": 3.308823529411765e-06,
      "loss": 0.0577,
      "step": 200
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6441717791411042,
      "eval_f1_macro": 0.6175566343042072,
      "eval_loss": 0.09405244886875153,
      "eval_precision_macro": 0.6741573033707865,
      "eval_recall_macro": 0.7803030303030303,
      "eval_runtime": 0.9464,
      "eval_samples_per_second": 172.229,
      "eval_steps_per_second": 6.34,
      "step": 232
    },
    {
      "epoch": 4.310344827586207,
      "grad_norm": 1.337144374847412,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 0.0689,
      "step": 250
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9325153374233128,
      "eval_f1_macro": 0.8917858651698956,
      "eval_loss": 0.047600872814655304,
      "eval_precision_macro": 0.8871660305343512,
      "eval_recall_macro": 0.8966275659824048,
      "eval_runtime": 0.9309,
      "eval_samples_per_second": 175.093,
      "eval_steps_per_second": 6.445,
      "step": 290
    }
  ],
  "logging_steps": 50,
  "max_steps": 290,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 823562615180892.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}