trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 621,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1610305958132045,
      "grad_norm": 0.049451954662799835,
      "learning_rate": 1.7054009819967267e-05,
      "loss": 0.0992,
      "step": 100
    },
    {
      "epoch": 0.1610305958132045,
      "eval_accuracy": 0.9986595174262735,
      "eval_accuracy_label_GD622:NO": 0.9982174688057041,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 0.9986607261106767,
      "eval_loss": 0.006988690234720707,
      "eval_precision": 0.9986667243218311,
      "eval_recall": 0.9986595174262735,
      "eval_runtime": 14.5108,
      "eval_samples_per_second": 51.41,
      "eval_steps_per_second": 6.478,
      "step": 100
    },
    {
      "epoch": 0.322061191626409,
      "grad_norm": 0.009679725393652916,
      "learning_rate": 1.3780687397708677e-05,
      "loss": 0.0082,
      "step": 200
    },
    {
      "epoch": 0.322061191626409,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:NO": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0001819185126805678,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 14.1036,
      "eval_samples_per_second": 52.894,
      "eval_steps_per_second": 6.665,
      "step": 200
    },
    {
      "epoch": 0.4830917874396135,
      "grad_norm": 0.004012643825262785,
      "learning_rate": 1.0507364975450083e-05,
      "loss": 0.0002,
      "step": 300
    },
    {
      "epoch": 0.4830917874396135,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:NO": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 8.742377394810319e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 14.2465,
      "eval_samples_per_second": 52.364,
      "eval_steps_per_second": 6.598,
      "step": 300
    },
    {
      "epoch": 0.644122383252818,
      "grad_norm": 0.007226710207760334,
      "learning_rate": 7.234042553191491e-06,
      "loss": 0.0001,
      "step": 400
    },
    {
      "epoch": 0.644122383252818,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:NO": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 6.116439180914313e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 14.0833,
      "eval_samples_per_second": 52.971,
      "eval_steps_per_second": 6.675,
      "step": 400
    },
    {
      "epoch": 0.8051529790660226,
      "grad_norm": 0.0017265487695112824,
      "learning_rate": 3.9607201309328975e-06,
      "loss": 0.0001,
      "step": 500
    },
    {
      "epoch": 0.8051529790660226,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:NO": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 5.098180554341525e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 14.2966,
      "eval_samples_per_second": 52.18,
      "eval_steps_per_second": 6.575,
      "step": 500
    },
    {
      "epoch": 0.966183574879227,
      "grad_norm": 0.002074724994599819,
      "learning_rate": 6.873977086743044e-07,
      "loss": 0.0052,
      "step": 600
    },
    {
      "epoch": 0.966183574879227,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:NO": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 5.632078318740241e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 14.2886,
      "eval_samples_per_second": 52.209,
      "eval_steps_per_second": 6.579,
      "step": 600
    },
    {
      "epoch": 1.0,
      "step": 621,
      "total_flos": 118713820492800.0,
      "train_loss": 0.01817948298567033,
      "train_runtime": 610.2056,
      "train_samples_per_second": 16.281,
      "train_steps_per_second": 1.018
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 1.0,
      "eval_accuracy_label_GD622:NO": 1.0,
      "eval_accuracy_label_GD622:YES": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 5.621322270599194e-05,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 14.2274,
      "eval_samples_per_second": 52.434,
      "eval_steps_per_second": 6.607,
      "step": 621
    }
  ],
  "logging_steps": 100,
  "max_steps": 621,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 118713820492800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}