last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017204745068689945,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.440949013737989e-05,
      "eval_loss": NaN,
      "eval_runtime": 257.9461,
      "eval_samples_per_second": 47.44,
      "eval_steps_per_second": 23.722,
      "step": 1
    },
    {
      "epoch": 0.00010322847041213967,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00020645694082427934,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.000309685411236419,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0004129138816485587,
      "grad_norm": NaN,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0004473233717859386,
      "eval_loss": NaN,
      "eval_runtime": 257.1909,
      "eval_samples_per_second": 47.579,
      "eval_steps_per_second": 23.792,
      "step": 13
    },
    {
      "epoch": 0.0005161423520606983,
      "grad_norm": NaN,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.000619370822472838,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0007225992928849776,
      "grad_norm": NaN,
      "learning_rate": 0.00016494480483301836,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0008258277632971174,
      "grad_norm": NaN,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0008946467435718772,
      "eval_loss": NaN,
      "eval_runtime": 257.0689,
      "eval_samples_per_second": 47.602,
      "eval_steps_per_second": 23.803,
      "step": 26
    },
    {
      "epoch": 0.000929056233709257,
      "grad_norm": NaN,
      "learning_rate": 0.00012334453638559057,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0010322847041213967,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0011355131745335364,
      "grad_norm": NaN,
      "learning_rate": 7.66554636144095e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.001238741644945676,
      "grad_norm": NaN,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.0013419701153578156,
      "grad_norm": NaN,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.0013419701153578156,
      "eval_loss": NaN,
      "eval_runtime": 256.6865,
      "eval_samples_per_second": 47.673,
      "eval_steps_per_second": 23.838,
      "step": 39
    },
    {
      "epoch": 0.0014451985857699553,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.001548427056182095,
      "grad_norm": NaN,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0016516555265942347,
      "grad_norm": NaN,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.0,
      "step": 48
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 901192876032000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}