trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9954337899543378,
  "eval_steps": 500,
  "global_step": 109,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0091324200913242,
      "grad_norm": 22.5,
      "learning_rate": 9.090909090909091e-07,
      "loss": 1.6621,
      "step": 1
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 3.671875,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.5917,
      "step": 10
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 2.390625,
      "learning_rate": 9.793339265183303e-06,
      "loss": 1.4031,
      "step": 20
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 1.984375,
      "learning_rate": 9.10086127298478e-06,
      "loss": 1.3219,
      "step": 30
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 1.8125,
      "learning_rate": 7.99055265245608e-06,
      "loss": 1.2743,
      "step": 40
    },
    {
      "epoch": 0.45662100456621,
      "grad_norm": 1.71875,
      "learning_rate": 6.575541090118105e-06,
      "loss": 1.2351,
      "step": 50
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 1.703125,
      "learning_rate": 5e-06,
      "loss": 1.2429,
      "step": 60
    },
    {
      "epoch": 0.639269406392694,
      "grad_norm": 1.640625,
      "learning_rate": 3.424458909881897e-06,
      "loss": 1.2251,
      "step": 70
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 1.734375,
      "learning_rate": 2.00944734754392e-06,
      "loss": 1.2427,
      "step": 80
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 1.7734375,
      "learning_rate": 8.991387270152202e-07,
      "loss": 1.2333,
      "step": 90
    },
    {
      "epoch": 0.91324200913242,
      "grad_norm": 1.7734375,
      "learning_rate": 2.0666073481669714e-07,
      "loss": 1.2286,
      "step": 100
    },
    {
      "epoch": 0.9954337899543378,
      "step": 109,
      "total_flos": 2.216988177648845e+16,
      "train_loss": 1.2956732773999555,
      "train_runtime": 586.8184,
      "train_samples_per_second": 2.986,
      "train_steps_per_second": 0.186
    }
  ],
  "logging_steps": 10,
  "max_steps": 109,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.216988177648845e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}