trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 2544,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.179245283018868,
      "grad_norm": 15.49643325805664,
      "learning_rate": 2.410377358490566e-05,
      "loss": 1.8144,
      "step": 500
    },
    {
      "epoch": 2.358490566037736,
      "grad_norm": 19.69099998474121,
      "learning_rate": 1.8207547169811322e-05,
      "loss": 1.0437,
      "step": 1000
    },
    {
      "epoch": 3.5377358490566038,
      "grad_norm": 13.478647232055664,
      "learning_rate": 1.2311320754716983e-05,
      "loss": 0.4616,
      "step": 1500
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 2.125852108001709,
      "learning_rate": 6.415094339622642e-06,
      "loss": 0.148,
      "step": 2000
    },
    {
      "epoch": 5.89622641509434,
      "grad_norm": 0.09522629529237747,
      "learning_rate": 5.188679245283019e-07,
      "loss": 0.0987,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "step": 2544,
      "total_flos": 3.780810569313792e+16,
      "train_loss": 0.7023615477220068,
      "train_runtime": 12579.5465,
      "train_samples_per_second": 6.46,
      "train_steps_per_second": 0.202
    }
  ],
  "logging_steps": 500,
  "max_steps": 2544,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 3.780810569313792e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}