trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19480519480519481,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.032467532467532464,
      "grad_norm": 0.8865271806716919,
      "learning_rate": 0.0002,
      "loss": 1.43,
      "step": 25
    },
    {
      "epoch": 0.06493506493506493,
      "grad_norm": 0.28116825222969055,
      "learning_rate": 0.0002,
      "loss": 0.3415,
      "step": 50
    },
    {
      "epoch": 0.09740259740259741,
      "grad_norm": 0.2447807788848877,
      "learning_rate": 0.0002,
      "loss": 0.214,
      "step": 75
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 0.25722232460975647,
      "learning_rate": 0.0002,
      "loss": 0.1801,
      "step": 100
    },
    {
      "epoch": 0.16233766233766234,
      "grad_norm": 0.10945671796798706,
      "learning_rate": 0.0002,
      "loss": 0.1676,
      "step": 125
    },
    {
      "epoch": 0.19480519480519481,
      "grad_norm": 0.16471615433692932,
      "learning_rate": 0.0002,
      "loss": 0.1463,
      "step": 150
    }
  ],
  "logging_steps": 25,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1530062910259200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}