trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008,
      "grad_norm": 0.2573789358139038,
      "learning_rate": 1.8e-05,
      "loss": 0.8789,
      "step": 10
    },
    {
      "epoch": 0.0016,
      "grad_norm": 0.2554769217967987,
      "learning_rate": 3.8e-05,
      "loss": 0.9406,
      "step": 20
    },
    {
      "epoch": 0.0024,
      "grad_norm": 0.1636732518672943,
      "learning_rate": 5.8e-05,
      "loss": 0.9042,
      "step": 30
    },
    {
      "epoch": 0.0032,
      "grad_norm": 0.1901659220457077,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.8011,
      "step": 40
    },
    {
      "epoch": 0.004,
      "grad_norm": 0.19001711905002594,
      "learning_rate": 9.8e-05,
      "loss": 0.868,
      "step": 50
    },
    {
      "epoch": 0.0048,
      "grad_norm": 0.21186105906963348,
      "learning_rate": 0.000118,
      "loss": 0.8855,
      "step": 60
    },
    {
      "epoch": 0.0056,
      "grad_norm": 0.18638649582862854,
      "learning_rate": 0.000138,
      "loss": 0.8751,
      "step": 70
    },
    {
      "epoch": 0.0064,
      "grad_norm": 0.20771396160125732,
      "learning_rate": 0.00015800000000000002,
      "loss": 0.8288,
      "step": 80
    },
    {
      "epoch": 0.0072,
      "grad_norm": 0.18098486959934235,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.8364,
      "step": 90
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.19161753356456757,
      "learning_rate": 0.00019800000000000002,
      "loss": 0.7082,
      "step": 100
    },
    {
      "epoch": 0.0088,
      "grad_norm": 0.21872420608997345,
      "learning_rate": 0.00019985483870967743,
      "loss": 0.8027,
      "step": 110
    },
    {
      "epoch": 0.0096,
      "grad_norm": 0.19647376239299774,
      "learning_rate": 0.00019969354838709677,
      "loss": 0.7546,
      "step": 120
    },
    {
      "epoch": 0.0104,
      "grad_norm": 0.174669086933136,
      "learning_rate": 0.00019953225806451614,
      "loss": 0.7488,
      "step": 130
    },
    {
      "epoch": 0.0112,
      "grad_norm": 0.25444668531417847,
      "learning_rate": 0.00019937096774193548,
      "loss": 0.6572,
      "step": 140
    },
    {
      "epoch": 0.012,
      "grad_norm": 0.2063271701335907,
      "learning_rate": 0.00019920967741935485,
      "loss": 0.7714,
      "step": 150
    },
    {
      "epoch": 0.0128,
      "grad_norm": 0.21145090460777283,
      "learning_rate": 0.0001990483870967742,
      "loss": 0.7931,
      "step": 160
    },
    {
      "epoch": 0.0136,
      "grad_norm": 0.21990713477134705,
      "learning_rate": 0.00019888709677419355,
      "loss": 0.7836,
      "step": 170
    },
    {
      "epoch": 0.0144,
      "grad_norm": 0.1941397488117218,
      "learning_rate": 0.00019872580645161292,
      "loss": 0.8162,
      "step": 180
    },
    {
      "epoch": 0.0152,
      "grad_norm": 0.18625402450561523,
      "learning_rate": 0.00019856451612903226,
      "loss": 0.7964,
      "step": 190
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.1731642633676529,
      "learning_rate": 0.00019840322580645163,
      "loss": 0.7157,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 12500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8444666897014784e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}