trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6722689075630253,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11204481792717087,
      "grad_norm": 2.205965941210718,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5102,
      "step": 10
    },
    {
      "epoch": 0.22408963585434175,
      "grad_norm": 0.4058151034644555,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.4111,
      "step": 20
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 0.5207078476987901,
      "learning_rate": 4.999164333474219e-05,
      "loss": 0.3608,
      "step": 30
    },
    {
      "epoch": 0.4481792717086835,
      "grad_norm": 0.29162902979770594,
      "learning_rate": 4.969974623692023e-05,
      "loss": 0.3412,
      "step": 40
    },
    {
      "epoch": 0.5602240896358543,
      "grad_norm": 0.33919346816403395,
      "learning_rate": 4.8995585819447796e-05,
      "loss": 0.3247,
      "step": 50
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 0.3077614142891388,
      "learning_rate": 4.789091521972515e-05,
      "loss": 0.318,
      "step": 60
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.3140985050455907,
      "learning_rate": 4.640417248825667e-05,
      "loss": 0.3104,
      "step": 70
    },
    {
      "epoch": 0.896358543417367,
      "grad_norm": 0.2608695216839159,
      "learning_rate": 4.4560172839257995e-05,
      "loss": 0.3072,
      "step": 80
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.24232443759299604,
      "learning_rate": 4.238969446006105e-05,
      "loss": 0.2978,
      "step": 90
    },
    {
      "epoch": 1.112044817927171,
      "grad_norm": 0.34109273034793913,
      "learning_rate": 3.9928964792569655e-05,
      "loss": 0.2709,
      "step": 100
    },
    {
      "epoch": 1.2240896358543418,
      "grad_norm": 0.25045860103100287,
      "learning_rate": 3.721905586123911e-05,
      "loss": 0.2632,
      "step": 110
    },
    {
      "epoch": 1.3361344537815127,
      "grad_norm": 0.2009404443210539,
      "learning_rate": 3.4305198740156755e-05,
      "loss": 0.2599,
      "step": 120
    },
    {
      "epoch": 1.4481792717086834,
      "grad_norm": 0.20858659288302173,
      "learning_rate": 3.1236028601449534e-05,
      "loss": 0.2594,
      "step": 130
    },
    {
      "epoch": 1.5602240896358543,
      "grad_norm": 0.19787474538096303,
      "learning_rate": 2.8062772945911137e-05,
      "loss": 0.2598,
      "step": 140
    },
    {
      "epoch": 1.6722689075630253,
      "grad_norm": 0.1891173836762629,
      "learning_rate": 2.4838396565086516e-05,
      "loss": 0.2587,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 947242156425216.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}