last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00018640979397057522,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.864097939705752e-05,
      "grad_norm": 1.0879372358322144,
      "learning_rate": 2e-05,
      "loss": 2.3836,
      "step": 1
    },
    {
      "epoch": 1.864097939705752e-05,
      "eval_loss": 2.422119617462158,
      "eval_runtime": 781.5039,
      "eval_samples_per_second": 28.903,
      "eval_steps_per_second": 14.452,
      "step": 1
    },
    {
      "epoch": 3.728195879411504e-05,
      "grad_norm": 1.0720592737197876,
      "learning_rate": 4e-05,
      "loss": 2.4509,
      "step": 2
    },
    {
      "epoch": 5.592293819117256e-05,
      "grad_norm": 1.1764265298843384,
      "learning_rate": 6e-05,
      "loss": 2.3824,
      "step": 3
    },
    {
      "epoch": 5.592293819117256e-05,
      "eval_loss": 2.4102935791015625,
      "eval_runtime": 779.9175,
      "eval_samples_per_second": 28.962,
      "eval_steps_per_second": 14.481,
      "step": 3
    },
    {
      "epoch": 7.456391758823009e-05,
      "grad_norm": 1.0699489116668701,
      "learning_rate": 8e-05,
      "loss": 2.393,
      "step": 4
    },
    {
      "epoch": 9.320489698528761e-05,
      "grad_norm": 1.1504356861114502,
      "learning_rate": 0.0001,
      "loss": 2.5008,
      "step": 5
    },
    {
      "epoch": 0.00011184587638234512,
      "grad_norm": 0.9129418730735779,
      "learning_rate": 0.00012,
      "loss": 2.2523,
      "step": 6
    },
    {
      "epoch": 0.00011184587638234512,
      "eval_loss": 2.2946419715881348,
      "eval_runtime": 781.5975,
      "eval_samples_per_second": 28.9,
      "eval_steps_per_second": 14.45,
      "step": 6
    },
    {
      "epoch": 0.00013048685577940266,
      "grad_norm": 0.8296093940734863,
      "learning_rate": 0.00014,
      "loss": 2.2445,
      "step": 7
    },
    {
      "epoch": 0.00014912783517646017,
      "grad_norm": 0.748724102973938,
      "learning_rate": 0.00016,
      "loss": 2.1062,
      "step": 8
    },
    {
      "epoch": 0.00016776881457351768,
      "grad_norm": 0.8164461255073547,
      "learning_rate": 0.00018,
      "loss": 2.1827,
      "step": 9
    },
    {
      "epoch": 0.00016776881457351768,
      "eval_loss": 2.2403993606567383,
      "eval_runtime": 781.9116,
      "eval_samples_per_second": 28.888,
      "eval_steps_per_second": 14.444,
      "step": 9
    },
    {
      "epoch": 0.00018640979397057522,
      "grad_norm": 1.0933417081832886,
      "learning_rate": 0.0002,
      "loss": 2.4171,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 800155729133568.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}