last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0414651002073255,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00138217000691085,
      "eval_loss": NaN,
      "eval_runtime": 5.9798,
      "eval_samples_per_second": 51.005,
      "eval_steps_per_second": 25.586,
      "step": 1
    },
    {
      "epoch": 0.00414651002073255,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.006910850034554251,
      "eval_loss": NaN,
      "eval_runtime": 5.4854,
      "eval_samples_per_second": 55.602,
      "eval_steps_per_second": 27.892,
      "step": 5
    },
    {
      "epoch": 0.0082930200414651,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.01243953006219765,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.013821700069108501,
      "eval_loss": NaN,
      "eval_runtime": 5.583,
      "eval_samples_per_second": 54.63,
      "eval_steps_per_second": 27.405,
      "step": 10
    },
    {
      "epoch": 0.0165860400829302,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.02073255010366275,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.02073255010366275,
      "eval_loss": NaN,
      "eval_runtime": 5.5966,
      "eval_samples_per_second": 54.497,
      "eval_steps_per_second": 27.338,
      "step": 15
    },
    {
      "epoch": 0.0248790601243953,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.027643400138217002,
      "eval_loss": NaN,
      "eval_runtime": 5.504,
      "eval_samples_per_second": 55.415,
      "eval_steps_per_second": 27.798,
      "step": 20
    },
    {
      "epoch": 0.02902557014512785,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0331720801658604,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.03455425017277125,
      "eval_loss": NaN,
      "eval_runtime": 5.5219,
      "eval_samples_per_second": 55.235,
      "eval_steps_per_second": 27.708,
      "step": 25
    },
    {
      "epoch": 0.03731859018659295,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0414651002073255,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0414651002073255,
      "eval_loss": NaN,
      "eval_runtime": 5.5446,
      "eval_samples_per_second": 55.008,
      "eval_steps_per_second": 27.594,
      "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
}