trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.888888888888889,
  "eval_steps": 500,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 22.716827392578125,
      "learning_rate": 9.428571428571429e-05,
      "loss": 72.2396,
      "step": 2
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": NaN,
      "learning_rate": 9.428571428571429e-05,
      "loss": 71.5578,
      "step": 4
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 21.451290130615234,
      "learning_rate": 8.857142857142857e-05,
      "loss": 70.6857,
      "step": 6
    },
    {
      "epoch": 1.126984126984127,
      "grad_norm": 51.5858154296875,
      "learning_rate": 8.285714285714287e-05,
      "loss": 89.6281,
      "step": 8
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 34.84550094604492,
      "learning_rate": 7.714285714285715e-05,
      "loss": 61.9926,
      "step": 10
    },
    {
      "epoch": 1.6349206349206349,
      "grad_norm": 34.304344177246094,
      "learning_rate": 7.142857142857143e-05,
      "loss": 56.7774,
      "step": 12
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 36.56817626953125,
      "learning_rate": 6.571428571428571e-05,
      "loss": 56.0385,
      "step": 14
    },
    {
      "epoch": 2.253968253968254,
      "grad_norm": 38.7420654296875,
      "learning_rate": 6.285714285714286e-05,
      "loss": 89.2308,
      "step": 16
    },
    {
      "epoch": 2.507936507936508,
      "grad_norm": 20.377830505371094,
      "learning_rate": 5.714285714285714e-05,
      "loss": 49.2758,
      "step": 18
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 20.033254623413086,
      "learning_rate": 5.142857142857143e-05,
      "loss": 49.5245,
      "step": 20
    },
    {
      "epoch": 3.126984126984127,
      "grad_norm": 36.59492492675781,
      "learning_rate": 4.5714285714285716e-05,
      "loss": 66.279,
      "step": 22
    },
    {
      "epoch": 3.380952380952381,
      "grad_norm": 20.715099334716797,
      "learning_rate": 4e-05,
      "loss": 46.2812,
      "step": 24
    },
    {
      "epoch": 3.634920634920635,
      "grad_norm": 19.177288055419922,
      "learning_rate": 3.428571428571429e-05,
      "loss": 46.2588,
      "step": 26
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 14.749308586120605,
      "learning_rate": 2.857142857142857e-05,
      "loss": 45.0001,
      "step": 28
    },
    {
      "epoch": 4.253968253968254,
      "grad_norm": 13.775603294372559,
      "learning_rate": 2.2857142857142858e-05,
      "loss": 61.0067,
      "step": 30
    },
    {
      "epoch": 4.507936507936508,
      "grad_norm": 14.531506538391113,
      "learning_rate": 1.7142857142857145e-05,
      "loss": 43.0824,
      "step": 32
    },
    {
      "epoch": 4.761904761904762,
      "grad_norm": 10.866065979003906,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 42.6889,
      "step": 34
    },
    {
      "epoch": 4.888888888888889,
      "step": 35,
      "total_flos": 559732817637624.0,
      "train_loss": 59.40860770089286,
      "train_runtime": 1324.2808,
      "train_samples_per_second": 0.476,
      "train_steps_per_second": 0.026
    }
  ],
  "logging_steps": 2,
  "max_steps": 35,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 559732817637624.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}