{
  "best_metric": 0.06150464341044426,
  "best_model_checkpoint": "/content/drive/MyDrive/dataset_for_research/ct_rate/data/ct_rate_jpn/model_output/sbintuitions_modernbert-ja-130m/checkpoint-2278",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 9112,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21949078138718173,
      "grad_norm": 7.839651584625244,
      "learning_rate": 1.8902546093064093e-05,
      "loss": 0.2808,
      "step": 500
    },
    {
      "epoch": 0.43898156277436345,
      "grad_norm": 3.2797462940216064,
      "learning_rate": 1.7805092186128183e-05,
      "loss": 0.0933,
      "step": 1000
    },
    {
      "epoch": 0.6584723441615452,
      "grad_norm": 2.731287956237793,
      "learning_rate": 1.6707638279192274e-05,
      "loss": 0.0792,
      "step": 1500
    },
    {
      "epoch": 0.8779631255487269,
      "grad_norm": 3.9177889823913574,
      "learning_rate": 1.561018437225637e-05,
      "loss": 0.0695,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9815139986342796,
      "eval_f1": 0.9535225948862591,
      "eval_loss": 0.06150464341044426,
      "eval_precision": 0.9613625123639961,
      "eval_recall": 0.9458095122247901,
      "eval_runtime": 32.5019,
      "eval_samples_per_second": 140.176,
      "eval_steps_per_second": 17.537,
      "step": 2278
    },
    {
      "epoch": 1.0974539069359086,
      "grad_norm": 2.4581689834594727,
      "learning_rate": 1.4512730465320458e-05,
      "loss": 0.0588,
      "step": 2500
    },
    {
      "epoch": 1.3169446883230904,
      "grad_norm": 2.0007755756378174,
      "learning_rate": 1.3415276558384549e-05,
      "loss": 0.0554,
      "step": 3000
    },
    {
      "epoch": 1.536435469710272,
      "grad_norm": 0.9888765811920166,
      "learning_rate": 1.2317822651448641e-05,
      "loss": 0.0508,
      "step": 3500
    },
    {
      "epoch": 1.755926251097454,
      "grad_norm": 3.2408642768859863,
      "learning_rate": 1.122036874451273e-05,
      "loss": 0.0502,
      "step": 4000
    },
    {
      "epoch": 1.9754170324846356,
      "grad_norm": 2.510002613067627,
      "learning_rate": 1.0122914837576823e-05,
      "loss": 0.0501,
      "step": 4500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9830382401716906,
      "eval_f1": 0.9576650333262319,
      "eval_loss": 0.06173006817698479,
      "eval_precision": 0.9584526347852574,
      "eval_recall": 0.9568787252159104,
      "eval_runtime": 32.5239,
      "eval_samples_per_second": 140.082,
      "eval_steps_per_second": 17.526,
      "step": 4556
    },
    {
      "epoch": 2.194907813871817,
      "grad_norm": 5.879360675811768,
      "learning_rate": 9.025460930640914e-06,
      "loss": 0.0346,
      "step": 5000
    },
    {
      "epoch": 2.4143985952589992,
      "grad_norm": 0.7706089615821838,
      "learning_rate": 7.928007023705005e-06,
      "loss": 0.0349,
      "step": 5500
    },
    {
      "epoch": 2.633889376646181,
      "grad_norm": 4.287876129150391,
      "learning_rate": 6.830553116769097e-06,
      "loss": 0.0321,
      "step": 6000
    },
    {
      "epoch": 2.853380158033363,
      "grad_norm": 2.919949531555176,
      "learning_rate": 5.7330992098331876e-06,
      "loss": 0.0315,
      "step": 6500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9846478392351966,
      "eval_f1": 0.9614760870230409,
      "eval_loss": 0.06240718811750412,
      "eval_precision": 0.9674856826159246,
      "eval_recall": 0.9555406884807202,
      "eval_runtime": 32.6149,
      "eval_samples_per_second": 139.691,
      "eval_steps_per_second": 17.477,
      "step": 6834
    },
    {
      "epoch": 3.0728709394205445,
      "grad_norm": 0.055859215557575226,
      "learning_rate": 4.6356453028972785e-06,
      "loss": 0.0263,
      "step": 7000
    },
    {
      "epoch": 3.292361720807726,
      "grad_norm": 0.41953563690185547,
      "learning_rate": 3.53819139596137e-06,
      "loss": 0.0149,
      "step": 7500
    },
    {
      "epoch": 3.511852502194908,
      "grad_norm": 0.9124375581741333,
      "learning_rate": 2.440737489025461e-06,
      "loss": 0.0161,
      "step": 8000
    },
    {
      "epoch": 3.7313432835820897,
      "grad_norm": 1.055453896522522,
      "learning_rate": 1.3432835820895524e-06,
      "loss": 0.014,
      "step": 8500
    },
    {
      "epoch": 3.9508340649692713,
      "grad_norm": 5.611504077911377,
      "learning_rate": 2.458296751536436e-07,
      "loss": 0.013,
      "step": 9000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9850014632718759,
      "eval_f1": 0.9624152050357514,
      "eval_loss": 0.08579593896865845,
      "eval_precision": 0.967084254482928,
      "eval_recall": 0.9577910229899039,
      "eval_runtime": 32.6214,
      "eval_samples_per_second": 139.663,
      "eval_steps_per_second": 17.473,
      "step": 9112
    }
  ],
  "logging_steps": 500,
  "max_steps": 9112,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3278248486495112e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}