trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21052631578947367,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 0.6013352870941162,
      "learning_rate": 0.0002961615786970389,
      "loss": 1.7199,
      "step": 10
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.2632163166999817,
      "learning_rate": 0.0002778325235483954,
      "loss": 1.8633,
      "step": 20
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 0.43362969160079956,
      "learning_rate": 0.00024621123294467096,
      "loss": 1.6853,
      "step": 30
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.3705150783061981,
      "learning_rate": 0.00020458574054452313,
      "loss": 1.8084,
      "step": 40
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.4706592857837677,
      "learning_rate": 0.00015728433331716724,
      "loss": 1.5581,
      "step": 50
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 0.4183749854564667,
      "learning_rate": 0.00010922548916454855,
      "loss": 1.7214,
      "step": 60
    },
    {
      "epoch": 0.14736842105263157,
      "grad_norm": 0.34439632296562195,
      "learning_rate": 6.540644552236401e-05,
      "loss": 1.7939,
      "step": 70
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.3492596745491028,
      "learning_rate": 3.038357841559191e-05,
      "loss": 1.5683,
      "step": 80
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 0.3816680610179901,
      "learning_rate": 7.798623006559435e-06,
      "loss": 1.505,
      "step": 90
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.3192552626132965,
      "learning_rate": 0.0,
      "loss": 1.675,
      "step": 100
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 1.6974681615829468,
      "eval_runtime": 2.4034,
      "eval_samples_per_second": 41.608,
      "eval_steps_per_second": 20.804,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "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": 62667383685120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}