last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08379888268156424,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002793296089385475,
      "eval_loss": NaN,
      "eval_runtime": 4.257,
      "eval_samples_per_second": 35.471,
      "eval_steps_per_second": 17.853,
      "step": 1
    },
    {
      "epoch": 0.008379888268156424,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.01675977653631285,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0223463687150838,
      "eval_loss": NaN,
      "eval_runtime": 3.465,
      "eval_samples_per_second": 43.579,
      "eval_steps_per_second": 21.934,
      "step": 8
    },
    {
      "epoch": 0.025139664804469275,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0335195530726257,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.04189944134078212,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0446927374301676,
      "eval_loss": NaN,
      "eval_runtime": 3.4903,
      "eval_samples_per_second": 43.263,
      "eval_steps_per_second": 21.775,
      "step": 16
    },
    {
      "epoch": 0.05027932960893855,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.05865921787709497,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0670391061452514,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0670391061452514,
      "eval_loss": NaN,
      "eval_runtime": 3.4981,
      "eval_samples_per_second": 43.167,
      "eval_steps_per_second": 21.726,
      "step": 24
    },
    {
      "epoch": 0.07541899441340782,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "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": 1544053158051840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}