checkpoint-2500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07659196397114015,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003063678558845606,
      "grad_norm": 3.0355441570281982,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.0534,
      "step": 100
    },
    {
      "epoch": 0.006127357117691212,
      "grad_norm": 2.961895227432251,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.9361,
      "step": 200
    },
    {
      "epoch": 0.009191035676536818,
      "grad_norm": 2.8523459434509277,
      "learning_rate": 9.987820251299121e-06,
      "loss": 2.9092,
      "step": 300
    },
    {
      "epoch": 0.012254714235382424,
      "grad_norm": 2.9632089138031006,
      "learning_rate": 9.890738003669029e-06,
      "loss": 2.8945,
      "step": 400
    },
    {
      "epoch": 0.015318392794228029,
      "grad_norm": 2.8018319606781006,
      "learning_rate": 9.698463103929542e-06,
      "loss": 2.8791,
      "step": 500
    },
    {
      "epoch": 0.018382071353073636,
      "grad_norm": 2.877758741378784,
      "learning_rate": 9.414737964294636e-06,
      "loss": 2.8601,
      "step": 600
    },
    {
      "epoch": 0.02144574991191924,
      "grad_norm": 2.7049593925476074,
      "learning_rate": 9.045084971874738e-06,
      "loss": 2.8707,
      "step": 700
    },
    {
      "epoch": 0.024509428470764847,
      "grad_norm": 2.8549087047576904,
      "learning_rate": 8.596699001693257e-06,
      "loss": 2.8554,
      "step": 800
    },
    {
      "epoch": 0.027573107029610452,
      "grad_norm": 2.643270969390869,
      "learning_rate": 8.078307376628292e-06,
      "loss": 2.8639,
      "step": 900
    },
    {
      "epoch": 0.030636785588456058,
      "grad_norm": 2.577594757080078,
      "learning_rate": 7.500000000000001e-06,
      "loss": 2.8589,
      "step": 1000
    },
    {
      "epoch": 0.03370046414730166,
      "grad_norm": 2.69144344329834,
      "learning_rate": 6.873032967079562e-06,
      "loss": 2.8316,
      "step": 1100
    },
    {
      "epoch": 0.03676414270614727,
      "grad_norm": 2.6036555767059326,
      "learning_rate": 6.209609477998339e-06,
      "loss": 2.8323,
      "step": 1200
    },
    {
      "epoch": 0.039827821264992874,
      "grad_norm": 2.630338430404663,
      "learning_rate": 5.522642316338268e-06,
      "loss": 2.8346,
      "step": 1300
    },
    {
      "epoch": 0.04289149982383848,
      "grad_norm": 2.5683858394622803,
      "learning_rate": 4.825502516487497e-06,
      "loss": 2.8368,
      "step": 1400
    },
    {
      "epoch": 0.04595517838268409,
      "grad_norm": 2.70560359954834,
      "learning_rate": 4.131759111665349e-06,
      "loss": 2.8206,
      "step": 1500
    },
    {
      "epoch": 0.049018856941529694,
      "grad_norm": 2.657520055770874,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 2.8048,
      "step": 1600
    },
    {
      "epoch": 0.0520825355003753,
      "grad_norm": 2.621300220489502,
      "learning_rate": 2.8081442660546126e-06,
      "loss": 2.8104,
      "step": 1700
    },
    {
      "epoch": 0.055146214059220905,
      "grad_norm": 2.6119415760040283,
      "learning_rate": 2.204035482646267e-06,
      "loss": 2.8202,
      "step": 1800
    },
    {
      "epoch": 0.058209892618066514,
      "grad_norm": 2.7000575065612793,
      "learning_rate": 1.6543469682057105e-06,
      "loss": 2.8078,
      "step": 1900
    },
    {
      "epoch": 0.061273571176912116,
      "grad_norm": 2.788527727127075,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 2.8143,
      "step": 2000
    },
    {
      "epoch": 0.06433724973575772,
      "grad_norm": 2.729123830795288,
      "learning_rate": 7.597595192178702e-07,
      "loss": 2.7989,
      "step": 2100
    },
    {
      "epoch": 0.06740092829460333,
      "grad_norm": 2.7026212215423584,
      "learning_rate": 4.322727117869951e-07,
      "loss": 2.8086,
      "step": 2200
    },
    {
      "epoch": 0.07046460685344894,
      "grad_norm": 2.68709397315979,
      "learning_rate": 1.9369152030840553e-07,
      "loss": 2.807,
      "step": 2300
    },
    {
      "epoch": 0.07352828541229454,
      "grad_norm": 2.7309343814849854,
      "learning_rate": 4.865965629214819e-08,
      "loss": 2.7994,
      "step": 2400
    },
    {
      "epoch": 0.07659196397114015,
      "grad_norm": 2.7638888359069824,
      "learning_rate": 0.0,
      "loss": 2.8006,
      "step": 2500
    }
  ],
  "logging_steps": 100,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.3916038848512e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}