trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9985315712187959,
  "eval_steps": 500,
  "global_step": 510,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019579050416054823,
      "grad_norm": 9.262737274169922,
      "learning_rate": 1.25e-06,
      "loss": 9.0302,
      "step": 1
    },
    {
      "epoch": 0.09789525208027411,
      "grad_norm": 0.5365363955497742,
      "learning_rate": 1.9767147448363366e-05,
      "loss": 3.6591,
      "step": 50
    },
    {
      "epoch": 0.19579050416054822,
      "grad_norm": 0.5503742098808289,
      "learning_rate": 1.8606772750713503e-05,
      "loss": 1.3343,
      "step": 100
    },
    {
      "epoch": 0.2936857562408223,
      "grad_norm": 0.5394380688667297,
      "learning_rate": 1.6583491273822763e-05,
      "loss": 1.2801,
      "step": 150
    },
    {
      "epoch": 0.39158100832109644,
      "grad_norm": 0.4574528634548187,
      "learning_rate": 1.3900155277567157e-05,
      "loss": 1.1802,
      "step": 200
    },
    {
      "epoch": 0.48947626040137054,
      "grad_norm": 0.5185055732727051,
      "learning_rate": 1.0825793454723325e-05,
      "loss": 1.2836,
      "step": 250
    },
    {
      "epoch": 0.5873715124816447,
      "grad_norm": 0.5709959268569946,
      "learning_rate": 7.668638372318359e-06,
      "loss": 1.2413,
      "step": 300
    },
    {
      "epoch": 0.6852667645619187,
      "grad_norm": 0.710220992565155,
      "learning_rate": 4.745223370156797e-06,
      "loss": 1.2651,
      "step": 350
    },
    {
      "epoch": 0.7831620166421929,
      "grad_norm": 0.512089192867279,
      "learning_rate": 2.348647231832131e-06,
      "loss": 1.2194,
      "step": 400
    },
    {
      "epoch": 0.8810572687224669,
      "grad_norm": 0.5229557156562805,
      "learning_rate": 7.19188381862519e-07,
      "loss": 1.2265,
      "step": 450
    },
    {
      "epoch": 0.9789525208027411,
      "grad_norm": 0.5461034774780273,
      "learning_rate": 2.0214801355192826e-08,
      "loss": 1.2294,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 510,
  "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": 7.294468431418491e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}