{
  "best_metric": 0.9838492597577388,
  "best_model_checkpoint": "./DiMa_new_artifacts\\checkpoint-377",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 377,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13262599469496023,
      "grad_norm": 6.313917636871338,
      "learning_rate": 6.622516556291392e-06,
      "loss": 0.6543,
      "step": 50
    },
    {
      "epoch": 0.26525198938992045,
      "grad_norm": 8.760651588439941,
      "learning_rate": 1.3245033112582784e-05,
      "loss": 0.3545,
      "step": 100
    },
    {
      "epoch": 0.3978779840848806,
      "grad_norm": 12.38838005065918,
      "learning_rate": 1.9867549668874173e-05,
      "loss": 0.1951,
      "step": 150
    },
    {
      "epoch": 0.5305039787798409,
      "grad_norm": 13.237753868103027,
      "learning_rate": 1.9277818717759768e-05,
      "loss": 0.1559,
      "step": 200
    },
    {
      "epoch": 0.6631299734748011,
      "grad_norm": 11.964133262634277,
      "learning_rate": 1.8540899042004423e-05,
      "loss": 0.1602,
      "step": 250
    },
    {
      "epoch": 0.7957559681697612,
      "grad_norm": 27.106698989868164,
      "learning_rate": 1.780397936624908e-05,
      "loss": 0.1055,
      "step": 300
    },
    {
      "epoch": 0.9283819628647215,
      "grad_norm": 0.026046760380268097,
      "learning_rate": 1.7067059690493736e-05,
      "loss": 0.1148,
      "step": 350
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9774647887323944,
      "eval_f1": 0.9838492597577388,
      "eval_loss": 0.08887767791748047,
      "eval_precision": 0.9905149051490515,
      "eval_recall": 0.9772727272727273,
      "eval_runtime": 62.9416,
      "eval_samples_per_second": 16.92,
      "eval_steps_per_second": 1.064,
      "step": 377
    }
  ],
  "logging_steps": 50,
  "max_steps": 1508,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 207660400442880.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}