trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 200.0,
  "global_step": 1715,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4577259475218658,
      "grad_norm": 0.005862534046173096,
      "learning_rate": 8.01980198019802e-07,
      "loss": 0.0387,
      "step": 500
    },
    {
      "epoch": 2.9154518950437316,
      "grad_norm": 39.22230911254883,
      "learning_rate": 4.7194719471947193e-07,
      "loss": 0.0292,
      "step": 1000
    },
    {
      "epoch": 4.373177842565598,
      "grad_norm": 29.80740737915039,
      "learning_rate": 1.419141914191419e-07,
      "loss": 0.0235,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "step": 1715,
      "total_flos": 4932286995774600.0,
      "train_loss": 0.030539887709103243,
      "train_runtime": 1868.9702,
      "train_samples_per_second": 14.671,
      "train_steps_per_second": 0.918
    }
  ],
  "logging_steps": 500,
  "max_steps": 1715,
  "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": 4932286995774600.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}