trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9781021897810218,
  "eval_steps": 500,
  "global_step": 136,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.291970802919708,
      "grad_norm": 0.6184127926826477,
      "learning_rate": 4.970219740227693e-05,
      "loss": 1.8198,
      "step": 20
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 0.39668646454811096,
      "learning_rate": 4.460299516441777e-05,
      "loss": 1.0179,
      "step": 40
    },
    {
      "epoch": 0.8759124087591241,
      "grad_norm": 0.4097144603729248,
      "learning_rate": 3.4418197340879635e-05,
      "loss": 0.9564,
      "step": 60
    },
    {
      "epoch": 1.1605839416058394,
      "grad_norm": 0.40845298767089844,
      "learning_rate": 2.1790041121336225e-05,
      "loss": 0.9085,
      "step": 80
    },
    {
      "epoch": 1.4525547445255476,
      "grad_norm": 0.39498740434646606,
      "learning_rate": 9.994642986290797e-06,
      "loss": 0.852,
      "step": 100
    },
    {
      "epoch": 1.7445255474452555,
      "grad_norm": 0.4478401243686676,
      "learning_rate": 2.092077387824884e-06,
      "loss": 0.8879,
      "step": 120
    }
  ],
  "logging_steps": 20,
  "max_steps": 136,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.877561308192768e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}