trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6834733893557423,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11204481792717087,
      "grad_norm": 1.4617097988720995,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.3759,
      "step": 10
    },
    {
      "epoch": 0.22408963585434175,
      "grad_norm": 0.5030711731517111,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.2768,
      "step": 20
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 0.34724806213757886,
      "learning_rate": 4.999143312438893e-05,
      "loss": 0.2534,
      "step": 30
    },
    {
      "epoch": 0.4481792717086835,
      "grad_norm": 0.2640009491462751,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 0.2475,
      "step": 40
    },
    {
      "epoch": 0.5602240896358543,
      "grad_norm": 0.21382710937703125,
      "learning_rate": 4.8970493371704826e-05,
      "loss": 0.2435,
      "step": 50
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 0.2041583125640159,
      "learning_rate": 4.783863644106502e-05,
      "loss": 0.2419,
      "step": 60
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.1856937663812898,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 0.2431,
      "step": 70
    },
    {
      "epoch": 0.896358543417367,
      "grad_norm": 0.22075682864303506,
      "learning_rate": 4.442864903642428e-05,
      "loss": 0.2397,
      "step": 80
    },
    {
      "epoch": 1.011204481792717,
      "grad_norm": 0.5875925402624772,
      "learning_rate": 4.220886439234385e-05,
      "loss": 0.2529,
      "step": 90
    },
    {
      "epoch": 1.123249299719888,
      "grad_norm": 0.21373061509492958,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.178,
      "step": 100
    },
    {
      "epoch": 1.2352941176470589,
      "grad_norm": 0.34659399467675955,
      "learning_rate": 3.692896900649021e-05,
      "loss": 0.174,
      "step": 110
    },
    {
      "epoch": 1.3473389355742298,
      "grad_norm": 0.1904508545611185,
      "learning_rate": 3.39591987386325e-05,
      "loss": 0.1741,
      "step": 120
    },
    {
      "epoch": 1.4593837535014005,
      "grad_norm": 0.1842044231227866,
      "learning_rate": 3.083613409639764e-05,
      "loss": 0.1737,
      "step": 130
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.2611855983071268,
      "learning_rate": 2.761321158169134e-05,
      "loss": 0.1739,
      "step": 140
    },
    {
      "epoch": 1.6834733893557423,
      "grad_norm": 0.1588238851357534,
      "learning_rate": 2.4345576292303176e-05,
      "loss": 0.1716,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 267,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 176325063081984.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}