last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0881057268722467,
  "eval_steps": 5,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005873715124816446,
      "grad_norm": 0.0762479305267334,
      "learning_rate": 1e-05,
      "loss": 10.3821,
      "step": 1
    },
    {
      "epoch": 0.005873715124816446,
      "eval_loss": NaN,
      "eval_runtime": 13.5498,
      "eval_samples_per_second": 84.651,
      "eval_steps_per_second": 10.627,
      "step": 1
    },
    {
      "epoch": 0.011747430249632892,
      "grad_norm": 0.07673076540231705,
      "learning_rate": 2e-05,
      "loss": 10.3819,
      "step": 2
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 0.07368427515029907,
      "learning_rate": 3e-05,
      "loss": 10.3821,
      "step": 3
    },
    {
      "epoch": 0.023494860499265784,
      "grad_norm": 0.07770584523677826,
      "learning_rate": 4e-05,
      "loss": 10.3819,
      "step": 4
    },
    {
      "epoch": 0.02936857562408223,
      "grad_norm": 0.0834246352314949,
      "learning_rate": 5e-05,
      "loss": 10.3819,
      "step": 5
    },
    {
      "epoch": 0.02936857562408223,
      "eval_loss": NaN,
      "eval_runtime": 1.4517,
      "eval_samples_per_second": 790.082,
      "eval_steps_per_second": 99.191,
      "step": 5
    },
    {
      "epoch": 0.03524229074889868,
      "grad_norm": 0.07079087197780609,
      "learning_rate": 6e-05,
      "loss": 10.3819,
      "step": 6
    },
    {
      "epoch": 0.041116005873715125,
      "grad_norm": 0.07339663058519363,
      "learning_rate": 7e-05,
      "loss": 10.3814,
      "step": 7
    },
    {
      "epoch": 0.04698972099853157,
      "grad_norm": 0.07698862254619598,
      "learning_rate": 8e-05,
      "loss": 10.3817,
      "step": 8
    },
    {
      "epoch": 0.05286343612334802,
      "grad_norm": 0.07521183043718338,
      "learning_rate": 9e-05,
      "loss": 10.3813,
      "step": 9
    },
    {
      "epoch": 0.05873715124816446,
      "grad_norm": 0.08161938935518265,
      "learning_rate": 0.0001,
      "loss": 10.3804,
      "step": 10
    },
    {
      "epoch": 0.05873715124816446,
      "eval_loss": NaN,
      "eval_runtime": 1.4366,
      "eval_samples_per_second": 798.388,
      "eval_steps_per_second": 100.234,
      "step": 10
    },
    {
      "epoch": 0.06461086637298091,
      "grad_norm": 0.08185140043497086,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3807,
      "step": 11
    },
    {
      "epoch": 0.07048458149779736,
      "grad_norm": 0.07860841602087021,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3804,
      "step": 12
    },
    {
      "epoch": 0.0763582966226138,
      "grad_norm": 0.08291763812303543,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3801,
      "step": 13
    },
    {
      "epoch": 0.08223201174743025,
      "grad_norm": 0.07697901129722595,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3793,
      "step": 14
    },
    {
      "epoch": 0.0881057268722467,
      "grad_norm": 0.08883082866668701,
      "learning_rate": 5e-05,
      "loss": 10.3791,
      "step": 15
    },
    {
      "epoch": 0.0881057268722467,
      "eval_loss": NaN,
      "eval_runtime": 1.4409,
      "eval_samples_per_second": 796.022,
      "eval_steps_per_second": 99.936,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 25105174364160.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}