Run1-500step_allCheckpoints/checkpoint-200/trainer_state.json

{
  "best_global_step": 200,
  "best_metric": 8.553091902285814e-05,
  "best_model_checkpoint": "./UltiVul_focal_loss_checkpoints/checkpoint-200",
  "epoch": 0.05630630630630631,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002815315315315315,
      "grad_norm": 49.37904357910156,
      "learning_rate": 4.5e-06,
      "loss": 23.6642,
      "step": 10
    },
    {
      "epoch": 0.00563063063063063,
      "grad_norm": 32.69184112548828,
      "learning_rate": 9.5e-06,
      "loss": 18.4995,
      "step": 20
    },
    {
      "epoch": 0.008445945945945946,
      "grad_norm": 17.92224884033203,
      "learning_rate": 1.45e-05,
      "loss": 10.2669,
      "step": 30
    },
    {
      "epoch": 0.01126126126126126,
      "grad_norm": 12.185972213745117,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 4.8376,
      "step": 40
    },
    {
      "epoch": 0.014076576576576577,
      "grad_norm": 2.712137460708618,
      "learning_rate": 2.45e-05,
      "loss": 1.0611,
      "step": 50
    },
    {
      "epoch": 0.016891891891891893,
      "grad_norm": 0.8478547930717468,
      "learning_rate": 2.95e-05,
      "loss": 0.0324,
      "step": 60
    },
    {
      "epoch": 0.019707207207207207,
      "grad_norm": 1.0729281902313232,
      "learning_rate": 3.45e-05,
      "loss": 0.0033,
      "step": 70
    },
    {
      "epoch": 0.02252252252252252,
      "grad_norm": 0.003953734878450632,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 0.001,
      "step": 80
    },
    {
      "epoch": 0.02533783783783784,
      "grad_norm": 0.25488701462745667,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 0.0011,
      "step": 90
    },
    {
      "epoch": 0.028153153153153154,
      "grad_norm": 0.0010484829545021057,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 0.001,
      "step": 100
    },
    {
      "epoch": 0.028153153153153154,
      "eval_loss": 0.00028092681895941496,
      "eval_runtime": 1519.0849,
      "eval_samples_per_second": 2.291,
      "eval_steps_per_second": 1.145,
      "step": 100
    },
    {
      "epoch": 0.030968468468468468,
      "grad_norm": 0.0045521012507379055,
      "learning_rate": 4.9937880765328895e-05,
      "loss": 0.0006,
      "step": 110
    },
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 0.008847632445394993,
      "learning_rate": 4.972354390769318e-05,
      "loss": 0.0006,
      "step": 120
    },
    {
      "epoch": 0.0365990990990991,
      "grad_norm": 0.013454323634505272,
      "learning_rate": 4.9357537087851815e-05,
      "loss": 0.0004,
      "step": 130
    },
    {
      "epoch": 0.039414414414414414,
      "grad_norm": 0.06617984175682068,
      "learning_rate": 4.884210562470972e-05,
      "loss": 0.0007,
      "step": 140
    },
    {
      "epoch": 0.04222972972972973,
      "grad_norm": 0.0029065811540931463,
      "learning_rate": 4.818041150308695e-05,
      "loss": 0.0002,
      "step": 150
    },
    {
      "epoch": 0.04504504504504504,
      "grad_norm": 0.0019135670736432076,
      "learning_rate": 4.737651397609031e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.04786036036036036,
      "grad_norm": 0.018747340887784958,
      "learning_rate": 4.643534466306984e-05,
      "loss": 0.0004,
      "step": 170
    },
    {
      "epoch": 0.05067567567567568,
      "grad_norm": 0.0025554385501891375,
      "learning_rate": 4.536267729592528e-05,
      "loss": 0.0001,
      "step": 180
    },
    {
      "epoch": 0.05349099099099099,
      "grad_norm": 0.00040266645373776555,
      "learning_rate": 4.416509229935797e-05,
      "loss": 0.0002,
      "step": 190
    },
    {
      "epoch": 0.05630630630630631,
      "grad_norm": 0.22791388630867004,
      "learning_rate": 4.284993642235523e-05,
      "loss": 0.0001,
      "step": 200
    },
    {
      "epoch": 0.05630630630630631,
      "eval_loss": 8.553091902285814e-05,
      "eval_runtime": 1509.8715,
      "eval_samples_per_second": 2.305,
      "eval_steps_per_second": 1.152,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 501,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1228802957656064e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}