trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 701,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14265335235378032,
      "grad_norm": 0.18888814747333527,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.3747,
      "step": 100
    },
    {
      "epoch": 0.28530670470756064,
      "grad_norm": 0.19710859656333923,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.3565,
      "step": 200
    },
    {
      "epoch": 0.42796005706134094,
      "grad_norm": 0.3654402792453766,
      "learning_rate": 2e-05,
      "loss": 2.2623,
      "step": 300
    },
    {
      "epoch": 0.5706134094151213,
      "grad_norm": 0.49523496627807617,
      "learning_rate": 1.7084903626036743e-05,
      "loss": 2.1081,
      "step": 400
    },
    {
      "epoch": 0.7132667617689016,
      "grad_norm": 0.6492739319801331,
      "learning_rate": 1.003917187804572e-05,
      "loss": 2.0141,
      "step": 500
    },
    {
      "epoch": 0.8559201141226819,
      "grad_norm": 0.6684784293174744,
      "learning_rate": 2.9706021701242127e-06,
      "loss": 1.9425,
      "step": 600
    },
    {
      "epoch": 0.9985734664764622,
      "grad_norm": 0.7805252075195312,
      "learning_rate": 3.068872059253103e-10,
      "loss": 1.8983,
      "step": 700
    },
    {
      "epoch": 1.0,
      "step": 701,
      "total_flos": 1.27303437975552e+16,
      "train_loss": 2.136012787315543,
      "train_runtime": 218.6299,
      "train_samples_per_second": 6.408,
      "train_steps_per_second": 3.206
    }
  ],
  "logging_steps": 100,
  "max_steps": 701,
  "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": 1.27303437975552e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}